Change detection (CD) in heterogeneous remote sensing images plays a crucial role in earth observation tasks, such as disaster monitoring and destruction assessment. Recent advancements in heterogeneous CD studies have substantially enhanced the capability to detect changes, but existing methodologies frequently lack effective control mechanisms for increasing false alarms when facing different heterogeneous scenes. Consequently, even with a high detection rate for changes, the real changes co-exist with lots of false alarms, thereby reducing the reliability and practical utility of the CD results. To address this issue, inspired by the insight of adaptive thresholding for false alarm control in constant false alarm rate (CFAR) detection, we propose a copula theory-based CD framework, named FAR-Aware-Copula-CD, to control false alarm rate (FAR) in heterogeneous CD. In the proposed FAR-Aware-Copula-CD, the heterogeneous CD problem is represented as a binary hypothesis testing problem. Then, the binary hypothesis testing problem is solved by a generalized likelihood ratio test based on copula theory, which effectively characterizes change statistics based on superpixel-level dependence within various heterogeneous image pairs. Finally, the decision thresholds of the copula-based change statistics are determined so as to satisfy the FAR constraint and ensure that the final CD result approaches a prespecified false alarm rate. Our FAR-Aware-Copula-CD provides a new approach for implementing controllable false alarms in heterogeneous CD tasks. Experimental results on four real-world datasets demonstrate the effectiveness of our proposed method.

Sea surface salinity (SSS) is a fundamental parameter for understanding ocean phenomena and plays a vital role in studying global climate change and weather prediction models. Following the earlier launch of Soil Moisture and Ocean Salinity (SMOS), Aquarius, and Soil Moisture Active Passive (SMAP) satellites, the Chinese Ocean Salinity and Soil Moisture Mission (COSM) was successfully launched on November 14, 2024. The launched satellite is equipped with the 2-D L-band Aperture Synthesis Microwave Radiometer (LASMR) and the Microwave Imager Combined Active and Passive (MICAP) components to gather high-precision SSS information. This paper presents the Airborne LASMR (ALASMR), which features a Y-shaped two-dimensional synthetic aperture microwave radiometer and contains 11 antenna units with a unit spacing of 0.82λ. The ground test investigations of the ALASMR have been conducted to evaluate antenna patterns, test the sensitivity of receiving channels, and conduct ocean aviation experiments. To examine the flight observation, uniform salinity is assumed for the sea area obtained from the calibration platform of National Satellite Ocean Application Service (NSOAS) whereas the salinity gradient is taken for the Laizhou Bay area. The ALASMR exhibits enhanced imaging performance, with a spatial resolution of about 0.35 km and a width of about 1.24 km at the flight altitude of 1.2 km. The retrieval of SSS in the sea area of the ocean calibration platform is also demonstrated in this work. This indicates that ALASMR can reliably execute salinity observation of near-shore with high precision and provide a cross-calibration data source for COSM after its launch.

Change detection (CD) in heterogeneous remote sensing images has been widely used for disaster monitoring and land-use management. In the past decade, the heterogeneous CD problem has significantly benefited from the development of deep neural networks (DNNs). However, the purely data-driven DNNs perform like a black box where the lack of interpretability limits the trustworthiness and controllability of DNNs in most practical CD applications. As a powerful knowledge-driven tool, copula theory performs well in modeling dependence among random variables. To enhance the interpretability of existing neural networks for heterogeneous CD, we propose a knowledge-data-driven heterogeneous CD method based on a copula-guided neural network, named NN-Copula-CD. In our NN-Copula-CD, the mathematical characteristics of copula are employed as the loss functions to supervise a neural network to learn the dependence between bi-temporal heterogeneous superpixel pairs, and then the changed regions are identified via binary classification based on the degrees of dependence of all the superpixel pairs in the bi-temporal images. We conduct in-depth experiments on four datasets with heterogeneous images, including synthetic aperture radar (SAR), multispectral, and near-infrared images, where quantitative and visual results demonstrate the effectiveness and interpretability of our proposed NN-Copula-CD method.

Recently, convolution neural networks (CNNs) have been extensively utilized in synthetic aperture radar (SAR) ship detection owing to their strong feature extraction and representation capability. However, existing CNN-based SAR ship detectors often suffer from poor sensitivity to small-scale ship targets due to the limited extractable features, especially in complex inshore scenarios. Moreover, the hand-designed components like nonmaximum suppression (NMS) calculation and anchor generation imposed in CNN-based detector significantly affect their robustness. In the face of these challenges, a novel end-to-end (E2E) transformer-based detection framework for small-scale ship targets in SAR images, named detection transformer (DETR) with improved de-noising (DN) anchor box (DINO) with refined DN and box (RDB-DINO), is proposed in this article. First, we introduce a complete contrastive DN (CCD) training technique which reconstructs and exploits different kinds of noised queries to reduce the confusion between small ships and complex backgrounds. Second, a look twice toward maximum (LTTM) algorithm for iterative box refinement is designed to mine the abnormal sample information and obtain abundant features of small ships in the training process. Finally, substantial experiments conducted on two widely used open SAR ship datasets demonstrate that the proposed approach yields superior results in small ship detection performance, outperforming prevailing state-of-the-art (SOTA) benchmarks.

A key issue of existing deep-learning-based object detection methods in remote sensing images is that they often struggle to differentiate the background and small object regions due to multi-level downsampling operations therein. Downsampling operations help extract high-level semantic features but result in excessive loss of spatial features of small objects. In this paper, we propose a new small object detector using multispectral remote sensing images, named content-aware downsampling-based detection network (CADDN), where we newly design a content-aware downsampling-based module (CADM). Unlike conventional downsampling operations that apply uniform downsampling parameters across the entire feature map, CADM adaptively assigns higher weights to feature elements that are critical for distinguishing objects from the background, and this assignment is guided by the contextual awareness of object locations during the downsampling process. Experiments based on multispectral remote sensing images with small ships and vehicles demonstrate that CADM can accurately identify and preserve the locations of important object-related features, and CADDN correspondingly achieves superior small object detection performance than state-of-the-art methods.

In this study, an Atmospheric Motion Vector (AMV)-based method for retrieving wind vectors using 183.31-GHz water vapor absorption channels is introduced. The effectiveness of this approach is validated through a comparative analysis with the ERA5 reanalysis data and the wind product derived from the Visible Infrared Imaging Radiometer Suite (VIIRS). Furthermore, this methodology demonstrates a complementary performance with the VIIRS wind product, suggesting its potential for enhancing the diversity of wind field data.

The Chinese Ocean Salinity Mission was officially initiated in 2020. In July 2023, a flight campaign was conducted to assess the system design, data processing methodologies, and performance criteria. This paper discusses the system architecture of the L/C/K-band one-dimensional microwave interferometric radiometers (MIR) tested in the flight campaign and presents the performance evaluations derived from imaging results.

Existing convolution neural network (CNN)-based synthetic aperture radar (SAR) ship detectors often suffer from poor performance to small-scale ship targets due to the scarcity of extractable features and the bottleneck of local receptive field in the CNN framework. To address the challenges, we propose a novel end-to-end transformer-based detection network for small-scale ship targets in SAR images, named DINO with Refined Denoising and Box (R2DB-DINO). First, we propose a complete contrastive denoising (CCD) training technique which can reconstruct and exploit various types of noisy queries to alleviate the confusion between small ships and background. Second, a look twice towards maximum (LTTM) algorithm for iterative box refinement is devised to acquire abundant features of prediction boxes for small ships by enhancing gradient information. Experiments conducted on measured dataset demonstrate the superiority of the proposed method in small-scale ship detection compared with existing methods.

Multispectral satellite images (MSSIs) offer abundant information crucial for water quality monitoring, particularly for sandy water mapping. This paper proposes a multi-band fusion (MBF) method for sandy water extent mapping (SWEM) using multi-source MSSIs. Compared with other ground surface objects, the reflectance intensity differences (RIDs) of sandy water areas are more significant between red and blue bands, as well as between near-infrared and green bands. First, we calculate the RIDs among data of the aforementioned four bands of original MSSIs. Second, we normalize and fuse RIDs, where sandy and non-sandy water areas have prominent distribution differences. The final SWEM results are obtained via the hierarchical fuzzy C- means clustering method. The robustness and superiority of our proposed MBF method for SWEM missions are validated through experimental results derived from measured MSSIs.

Existing satellite remote sensing change detection (CD) methods often crop large-scale bi-temporal image pairs into small patch pairs and use pixel-level CD methods to fairly process all the patch pairs. However, due to the sparsity of changed areas, existing pixel-level CD methods suffer from a waste of computational cost and memory resources on many unchanged areas, which hinders the deployment of the CD model on on-board platforms with extremely limited resources. To address this issue, we propose a lightweight patch-level CD network (LPCDNet) to rapidly remove the unchanged patch pairs in large-scale bi-temporal optical image pairs, which is helpful to accelerate the subsequent pixel-level processing and reduce its memory costs. In LPCDNet, based on the multi-scale max-pooling structure, the multilayer feature compression (MLFC) module is designed to compress and fuse the multi-level feature information from backbone network. Moreover, a sensitivity-guided network pruning method is proposed to remove unimportant channels and construct a lightweight backbone network based on ResNet18. Experiments on two datasets demonstrate the effectiveness and efficiency of our proposed method compared with existing methods.

The concept of a new type of high-resolution microwave interferometric radiometer (MIR) using beamforming antennas is proposed in this paper. Using large sampling intervals can effectively reduce the system complexity of large-scale arrays, but aliasing effect is also magnified. Through dedicated simulations, the aliasing effect can be suppressed when the interferometric element size exceeds the sampling interval, thus a dual-arm Y-shaped array is recommended for the overall system design. A ground-based demonstrator is currently under development, accompanied by preliminary experimental results.

Existing deep neural network (DNN)-based target detectors in remote sensing images (RSIs) often face challenges in distinguishing small targets from the background. This is mainly because the downsampling process in DNN-based target detectors results in excessive loss of small-target-related features. This paper proposes a new small target detector in RSIs named content-perception downsampling-based target detector (CPDTD), where a novel content-perception downsampling module (CPDM) is designed to replace standard downsampling methods (e.g. pooling and convolution with stride greater than 1). CPDM encodes the input feature map and predicts the location of important features that distinguish targets from backgrounds, assigning larger weights to critical features according to the perception of the position of targets in the content during the downsampling process. Experiments on measured multispectral RSIs regarding small ship and vehicle targets demonstrate the superiorities of our proposed CPDTD in comparison with existing methods.

This paper proposes a lightweight Siamese network based on the online all-integer-pruning (OAIP) training strategy for efficient change detection in heterogeneous remote sensing images. OAIP training strategy efficiently quantizes parameters to integers and prunes insignificant weights in the filter level based on the L1-norm criterion to reduce memory usage and accelerate the online training process for change detection. Experimental results based on measured heterogeneous remote sensing images demonstrate that our proposed method provides comparable change detection performance with higher efficiency compared with state-of- the-art methods.

In this letter, we propose an efficient flood detection (EFD) method using multisource satellite images based on the algorithm–hardware co-design strategy. This method aims to improve flood detection efficiency in resource-constrained edge computing environments. First, a hybrid heterogeneous computing platform is designed to incorporate central processing units (CPUs), graphics processing units (GPUs), and field programmable gate arrays (FPGAs) hardware units to combine their individual advantages for efficient satellite image processing during the flood detection process. Second, the different flood detection algorithm modules (containing convolutional neural networks and information fusion operations) are designed and assigned to appropriate hardware units based on the characteristics of each algorithm module and the capabilities of each hardware, to reduce hardware computation waste during the operation of flood detection algorithms. Experimental results based on measured data from four flood events demonstrate that our proposed flood detection method achieves a significant improvement in computational efficiency without a noticeable loss in flood detection accuracy compared with existing state-of-the-art methods.

Most of existing studies regarding cross-modal content-based remote sensing image retrieval (CM-CBRSIR) focus on reducing/enlarging the Euclidean distances of cross modal (CM) data with the same/different content in a common feature space. The advantages of using Euclidean distance lie in its straightforwardness. However, the Euclidean distances of CM data features are sensitive to the outlier data and may lead to non-robust retrieval performance, particularly in the case of noisy images with low-quality. To address this issue, we propose a robust Hirschfeld–Gebelein–Rényi maximal correlation (HGRMC) augmented algorithm for CM-CBRSIR in this work, named by HAC. In HAC, not only the projected features of CM data in Euclidean distance space but also maximal correlation information of HGRMC are learned during the training phase of the retrieval model, where HGRMC is additionally used to capture the statistical dependency between CM data to enhance the retrieval performance with the strongly noisy input data. In the retrieval phase, we also develop a fusion scheme based on the Dempster-Shafer (DS) evidence theory to combine the superiorities of Euclidean distance and HGRMC correlation criterions. Extensive experimental results demonstrate that our proposed HAC algorithm provides better and more robust retrieval performance in comparison with existing state-of-the-art CM-CBRSIR methods.

Existing satellite remote sensing change detection (CD) methods often crop large-scale bi-temporal image pairs into small patch pairs and then use pixel-level CD methods for fair processing. However, due to the sparsity of change, existing pixel-level methods suffer from a waste of computational cost and memory resources on many unchanged areas, which reduces the processing efficiency on hardware platforms with extremely limited computation and memory resources. To address this issue, we propose a lightweight patch-level CD network (LPCDNet) to rapidly remove lots of unchanged patch pairs in large-scale bi-temporal optical image pairs, helping to accelerate the subsequent pixel-level CD process and reduce memory cost. In our LPCDNet, a sensitivity-guided network pruning method is proposed to remove unimportant channels and construct the lightweight backbone network on basis of the ResNet18 network. Then, the multi-layer feature compression (MLFC) module with multi-scale max-pooling structure is designed to compress and fuse the multi-level feature information of image patches. The output of MLFC module is fed into the fully-connected decision network to generate the predicted binary label. Finally, a weighted cross-entropy loss is utilized in the training process to tackle the change/unchanged class imbalance problem. Experiments on two CD datasets demonstrate that our LPCDNet achieves more than 1000 frames per second on an edge computation platform, i.e., NVIDIA Jetson AGX Orin, which is more than 3 times that of the existing methods without noticeable performance loss. In addition, the computational cost of the pixel-level CD processing stage can be reduced by more than 60%.

For the task of change detection (CD) in remote sensing images, deep convolution neural networks (CNNs)-based methods have recently aggregated transformer modules to improve the capability of global feature extraction. However, they suffer degraded CD performance on small changed areas due to the simple single-scale integration of deep CNNs and transformer modules. To address this issue, we propose a hybrid network based on multi-scale CNN-transformer structure, termed MCTNet, where the multi-scale global and local information is exploited to enhance the robustness of the CD performance on changed areas with different sizes. Especially, we design the ConvTrans block to adaptively aggregate global features from transformer modules and local features from CNN layers, which provides abundant global-local features with different scales. Experimental results demonstrate that our MCTNet achieves better detection performance than existing state-of-the-art CD methods.

The geometrical theory of diffraction (GTD) has been widely investigated to describe the target scattering behaviors with the low-frequency ultra-wideband (LFW) radar. In this paper, we propose a new model-based deep learning method for GTD parameter estimation. The proposed method is designed by unfolding the fast iterative shrinkage thresholding algorithm (FISTA) into a deep neural network. Unlike existing methods based on compressed sensing (CS), the key parameters in our algorithm are fully learnable, avoiding nontrivial parameter tuning procedures. Our network with simple convolution operations is more computationally efficient than existing methods, which require matrix inversions or quadratic programming and have low convergence speed. A novel loss function is designed for the new network to improve the capacity of target enhancement. Experiments on simulation data show that the new method achieves higher computational efficiency while maintaining or improving the precision of GTD parameter estimation compared with existing methods.

The Moon is an ideal target for cross-calibration of radiometric measurements due to its stable surface geophysical properties. To explore the lunar calibration capability for the space-borne microwave radiometer missions, a ground-based interferometric radiometry concept for lunar observation is proposed in this paper, the observation model, site environment and array design are discussed. A large antenna spacing design is considered to achieve satisfactory spatial resolution while maintaining a reasonable system size. The resulting aliasing error is evaluated through imaging simulations.

In this paper, we consider the problem of change detection in heterogeneous remote sensing images. Existing deep learning-based methods for change detection often utilize square convolution receptive fields, which do not sufficiently exploit the contextual information in heterogeneous images. Square receptive fields reduce the robustness to change detection scenarios with complex contextual structures, increase the number of false alarms, and degrade the performance of change detection. To address the aforementioned issue, we propose an unsupervised Siamese superpixel-based network (US2N) for change detection in heterogeneous remote sensing images. Our newly proposed method innovatively combines superpixels with the square receptive fields to generate the boundary adherence receptive fields and better capture the contextual information than existing methods only with the regular square receptive fields. Experiments based on two real data sets demonstrate that the proposed method achieves higher accuracy than other commonly used change detection methods in heterogeneous remote sensing images.

In this paper, we proposed a novel Label Augmentation network based on Self-Distillation (LASDet) for inshore ship detection in synthetic aperture radar (SAR) images. Different from canonical convolution neural network (CNN)-based approaches under the guidance of hard label, the new semisoft labels produced by self-distillation are leveraged for ship detection to boost the information of negative sample in complex scenarios. Additionally, an angle-related balance intersection-over-union (ArBIoU) loss criterion is developed to alleviate ambiguity expression of inshore ship targets by using the adaptive weight association of the aspect ratio difference and the center point deviation in regression. Experimental results on open datasets demonstrate the superiority of the proposed method compared with the existing commonly used network, especially in complex inshore scenarios.

Multi-source heterogeneous satellite image time series (MSH-SITS) have become a robust way to acquire flood detection results thanks to their high-resolution and wide coverage areas advantages. In this paper, we propose an extremely lightweight and soft fusion-based Unet (LSFUnet) architecture for flood detection based on MSH-SITS to improve the computation efficiency of existing methods. Specifically, we build the encoder-decoder module with lightweight residual blocks using a reduced number of convolution layers and smaller convolution kernel size to accelerate our flood detection method. To compensate for the performance loss caused by lightweight operations, we utilize the historical flood information as the long-term and short-term constraints on the current flood detection results. Experimental results using Gaofen-1, Gaofen-3, Gaofen-6, Huanjing-2, Sentinel-1, and Sentinel-2 satellite images demonstrate the efficiency and effectiveness of our proposed LSFUnet method.

Most existing methods for cross-modal content-based remote sensing image retrieval (CM-CBRSIR) have only focused on implementations by optimizing the projected features in a common space under the Euclidean distance criterion. In this work, to better bridge the heterogeneity gap caused by the modality difference, we propose a Hirschfeld–Gebelein–Rényi (HGR) maximal correlation augmented CM-CBRSIR method by utilizing the HGR maximal correlation between different modalities. Except for optimizing the projected features under the Euclidean distance constraints, another feature projection, which carries the information of the HGR maximal correlation, is learned during the training phase. In the retrieval phase, we combine the information learned by the Euclidean distance criterion and HGR maximal correlation based on the Dempster–Shafer (DS) evidence theory. Experimental results show that the proposed method outperforms the existing state-of-the-art methods.1

The detection of densely distributed ship targets is one of the hot issues in the context of convolutional neural network (CNN)-based synthetic aperture radar (SAR) image processing. In this case, the bounding boxes of the ships may overlap with each other. Traditional detectors do not specifically consider the processing of overlapping areas, resulting in low detection performance. To address this problem, we proposed a new SAR ship detector, where classification confidence score-based method is developed to consider the centrality prior information among the overlap areas. Then, in the shallow layers of the network, the auxiliary heads are used to guide the network to learn the features related to centers of ships. Experimental results on the open datasets with dense ships show that our method achieves the better detection performance without the obvious increase of computation burden compared with the current state-of-the-art detectors.

Accurate estimation of the sizes of ship targets plays a critical role in the task of ship classification in synthetic aperture radar (SAR) images. Existing deep neural networks (DNNs)-based methods for SAR ship size estimation (SSE) often adopt a fully connected structure that has limited capability in accurately modeling the relationships of features extracted from SAR images, leading to degraded performance of size estimation. It has been demonstrated that capsule networks provide new guidelines to capture relationships of image features by replacing traditional neurons with capsules, where the dynamic routing strategy is used to calculate correlations among capsules. In this letter, we propose an improved method for SAR SSE based on the capsule network named Caps-SSE network (SSENet). In our Caps-SSENet, a capsule-neural-mixing size mapping module is designed to transform the extracted image features into capsules and complete the estimation of ship sizes using informative feature correlations from dynamic routing. In addition, an average scaled mean square error (ASMSE) loss is proposed to improve the size estimation performance of small ships. Experimental results based on measured SAR data show that the proposed method reduces the estimation error of ship sizes in SAR images in comparison with the existing state-of-the-art method.

Quad-pol synthetic aperture radar (SAR) is one of the most effective approaches for dry and wet snow identification data, but its applicability is limited by the high cost of quad-pol SAR data. Dual-pol SAR such as Sentinel-1 has larger spatial coverage, longer time sequences, and freely accessible data, but there is still a highly uncertainty in dual-pol SAR to distinguish dry and wet snow due to limited polarimetric information. In this study, a pixel neighborhood-based snow identification algorithm was developed and verified using dual-pol C-band SAR data in Northern Xinjiang, China. A total of six decomposed parameters were obtained to characterize the polarimetric information of dual-pol SAR data by modifying the H-$\alpha $decomposition applicable to dual-pol SAR data. In the case of limited training samples, polarimetric features that were most sensitive to snow identification were selected as the optimal features for support vector machine (SVM), and the result derived from SVM was employed as the initial labels of Markov random field (MRF) model to separate dry and wet snow using iterative conditional mode (ICM). Then, the proposed algorithm, dual-pol SVM-MRF (DSVM-MRF), was validated and compared with previously published methods. The results show that the DSVM-MRF acquires the superior snow recognition with the overall accuracy (OA) and Kappa coefficient of 84.5% and 0.58%, respectively.

Micro-motion feature vectors of space targets are usually unevenly and multi-cluster distributed, which limits the performance of traditional radar anomaly detection methods. To solve this problem, a novel detection method of radar space target abnormal motion method via local density peaks and micro-motion feature is proposed in this paper. Firstly, two discriminative micro-motion features are extracted from the radar echoes to construct a 2-D feature space. Then the abnormal motion detector is derived by classifying the feature vectors into different clusters according to the local density peaks and minimum spanning tree clustering, and solving for the decision thresholds of each cluster with the local density peaks, neighbors and some preset false alarm rates. Electromagnetic simulation experiment results demonstrate that the detection rate of the proposed method is 2.49%, 5.26%, 9.63%, 15.37%, 27.99% and 49.45% higher than six state-of-art methods respectively when the false alarm rate is 5%.

This paper explores nonuniform multiple-input multiple-output (MIMO) sampling and reconstruction of signals with multiple bands in the fractional Fourier domain. We investigate discrete-time fractional Fourier transforms of nonuniformly sampled output signals of MIMO channel and study the resulting fractional spectral aliasing. In order to tackle the problem that the spectral aliasing differs with respect to multiple-output signals, we define combined aliasing boundaries and perform spectrum analysis within the fractional frequency sub-intervals separated by these elaborated boundaries. Moreover, we derive the conditions for combined reconstructing the fractional spectra of the input/output signals of MIMO channel and devise relevant reconstruction methods. Simulation results verify the effectiveness of our proposed methods.

This paper considers the problem of change detection (CD) with multi-sensor optical remote sensing (RS) images. Copulas are adopted to characterize the dependence structure between the image pair. For this problem, a conditional copula-based CD technique has been proposed in the literature. However, in this technique, it is difficult to select the best copula function in an analytical framework. Resulting copula misspecification may lead to performance degradation. To deal with this problem, we model the CD problem as a binary hypothesis testing problem and propose a new superpixel-level copula-based statistical method (SCOPS) for CD, where an explicit strategy for copula selection is provided for the proposed method. The effectiveness of the copula selection strategy is verified on CD tasks with simulated multi-sensor optical RS images. Experiments on real RS datasets demonstrate the superiority of SCOPS over the state-of-the-art methods.

Change detection (CD) in optical remote sensing images has significantly benefited from the development of deep convolutional neural networks (CNNs) due to their strong capability of local modeling in bi-temporal images. In addition, the recent rise of transformer modules leads to the improvement of global feature extraction of bi-temporal remote sensing images. Note that the existing simple cascade of deep CNNs and transformer modules shows limited CD performance on small changed areas due to deficiencies of multi-scale information therein. To address the aforementioned issue, we propose a new CNN-transformer network (ConvTransNet) with multi-scale framework to better exploit global-local information in optical remote sensing images. In our ConvTransNet, we propose the parallel-branch ConvTrans block as the basic component to generate global-local features, i.e., adaptively integrates the global features summarized by a transformer-based branch and the local features extracted by a convolution-based branch, providing better identifiability between changed areas and unchanged areas. By fusing multiple global-local features with different scales, our ConvTransNet improves the robustness of the CD performance on changed areas with different sizes, especially small changed areas. Experiments on two public change detection datasets of optical remote sensing images, i.e., LEVIR-CD and CDD, demonstrate that our ConvTransNet achieves enhanced CD performance than the other commonly used methods.

Distribution of snow and its melting is a critical factor affecting local weather, avalanche and flood forecasting, livelihood of people residing, and hydropower production. Most of the existing dry and wet snow identification methods were based on expensive quad-pol SAR with finite generalizability, while dual-pol SAR with larger coverage, longer time series and open availability has more advantages. In this study, an unsupervised algorithm for dry and wet snow discrimination, NSAE-WFCM, is proposed based on a variety of polarimetric features derived from H-α decomposition in dual-pol mode using C-band Sentinel-1 SAR data. NSAE-WFCM constructs a deep training network using the pixel neighborhood-based sparse autoencoder (NSAE) to optimize polarimetric parameters, and inputs reconstructed features with different weights into feature-weighted fuzzy C-means clustering (WFCM) to distinguish dry and wet snow for each underlying surface. Ground observation was carried out during the snow melting period of March 2021 in Altay, China, to validate dual-pol NSAE-WFCM method with an overall accuracy and kappa coefficient of 88.8% and 0.68, respectively. The results show that NSAE-WFCM’s accuracy is similar to that of the quad-pol SAR-based dry and wet snow result (90.0%), and significantly better than that of previously published approaches extended to dual-pol SAR, such as SVM (76.7%), H-α-Wishart (65.5%), SPAN-based threshold method (51.7%), and wet snow-based method (43.1%). Therefore, the NSAE-WFCM algorithm improves the ability to classify wet and dry snow based on dual-pol polarimetric features, overcomes the high dependence of existing methods on quad-pol SAR data, and reduces manual interpretation by using unsupervised clustering.

With the soaring development of deep learning (DL) mechanisms in recent years, convolution neural network (CNN)-based methods have been extensively investigated to achieve high accuracy of ship detection in Synthetic Aperture Radar (SAR) images. However, existing CNN-based SAR ship detection methods still suffer from challenges in complex inshore scenarios due to the strong interference therein. To tackle this issue, a novel Semi-Soft Label-guided network based on Self-Distillation (SD) for SAR ship detection (S2LSDNet) is proposed in this article. First, different from the existing CNN-based detectors to extract features from the image domain only under the guidance of one-hot label, an efficient SD training strategy is devised to extract semi-soft label information to boost the inshore ship detection accuracy. Second, an angle-related and Balanced Intersection-over-Union (ArBIoU) loss is developed to enhance the inshore ship positioning performance by using the adaptive weights of center point bias and the aspect ratio difference. Experiments on the open SAR ship detection datasets demonstrate the effectiveness and superiority of the proposed method compared with the existing state-of-the-art approaches, especially in inshore scenes.

Flood monitoring is of crucial importance for protecting lives and properties. Change detection (CD) methods on multisource remote sensing images have been widely used for flood extent monitoring. In this article, we propose a spatiotemporal fusion CD (STFCD) algorithm, exploiting the spatial dependence and temporal interaction of multisource heterogeneous (MSH) satellite image time series (SITS), to realize improved flood CD performance in comparison with existing methods. The proposed STFCD algorithm mainly contains two steps, i.e., spatial clustering and temporal fusion (TF). In the spatial clustering step, we propose a sparse Markov random field (MRF)-based strategy to exploit contextually spatial features in each image of MSH-SITS, which provides a larger local receptive field than the commonly used MRF. In the TF step, the historical information of flood detection results is employed as constraints to effectively reduce the effects of terrain shadows in synthetic aperture radar (SAR) images and cloud shadows and topography shadows in optical images on flood CD results of existing methods in accordance with the temporal dependence among MSH-SITS. Experiments on real MSH-SITS (containing Gaofen-1, Gaofen-3, Gaofen-6, Sentinel-1, and Sentinel-2 satellite images) covering Chinese Amur and Huma Rivers show that the overall flood CD accuracy of our proposed STFCD algorithm is higher than the other commonly used algorithms for CD of flood extents and demonstrate the robustness of our proposed STFCD algorithm.

Convolutional neural networks (CNNs) have been widely applied in the context of ship detection in synthetic aperture radar (SAR) images, but the detection performance is still not ideal in scenarios with clutter interference. Mining frequency-domain information to suppress the sea clutter in SAR ship detection has attracted wide attention. However, existing frequency-domain ship detection methods do not process frequency-domain information adaptively, which results in the degradation of ship detection performance. To overcome this problem, this article proposes a novel deep learning network called YOLO-FA. YOLO-FA contains the proposed frequency attention module (FAM), which can process frequency-domain information of SAR images adaptively. The proposed method can suppress the sea clutter in the SAR images with the help of frequency-domain information. We evaluate the proposed method YOLO-FA on two datasets, i.e., the high-resolution SAR images’ dataset (HRSID) and SAR ship detection dataset (SSDD). Compared with the baseline method YOLOv5 and the existing commonly used methods, YOLO-FA achieves state-of-the-art detection performance on both the datasets.

Radar is an extremely valuable sensing technology for detecting moving targets and measuring their range, velocity, and angular positions. When people are monitored at home, radar is more likely to be accepted by end-users, as they already use WiFi, is perceived as privacy-preserving compared to cameras, and does not require user compliance as wearable sensors do. Furthermore, it is not affected by lighting conditions nor requires artificial lights that could cause discomfort in the home environment. So, radar-based human activities classification in the context of assisted living can empower an aging society to live at home independently longer. However, challenges remain as to the formulation of the most effective algorithms for radar-based human activities classification and their validation. To promote the exploration and cross-evaluation of different algorithms, our dataset released in 2019 was used to benchmark various classification approaches. The challenge was open from February 2020 to December 2020. A total of 23 organizations worldwide, forming 12 teams from academia and industry, participated in the inaugural Radar Challenge, and submitted 188 valid entries to the challenge. This paper presents an overview and evaluation of the approaches used for all primary contributions in this inaugural challenge. The proposed algorithms are summarized, and the main parameters affecting their performances are analyzed.

In this article, we investigate the problem of decentralized federated learning (DFL) in Internet of Things (IoT) systems, where a number of IoT clients train models collectively for a common task without sharing their private training data in the absence of a central server. Most of the existing DFL schemes are composed of two alternating steps, i.e., model updating and model averaging. However, averaging model parameters directly to fuse different models at the local clients suffers from client-drift, especially when the training data are heterogeneous across different clients. This leads to slow convergence and degraded learning performance. As a possible solution, we propose the DFL via a mutual knowledge transfer (Def-KT) algorithm, where local clients fuse models by transferring their learned knowledge to each other. Our experiments on the MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 data sets reveal that the proposed Def-KT algorithm significantly outperforms the baseline DFL methods with model averaging, i.e., Combo and FullAvg, especially when the training data are not independent and identically distributed (non-IID) across different clients.

In this article, we consider the problem of federated learning (FL) with training data that are non independent and identically distributed (non-IID) across the clients. To cope with data heterogeneity, an iterative federated clustering algorithm (IFCA) has been proposed. IFCA partitions the clients into a number of clusters and lets the clients in the same cluster optimize a shared model. However, in IFCA, the clusters are nonoverlapping, which leads to an inefficient utilization of the local information since the knowledge of a client is used by only one cluster during each round. To capture the complex nature of real-world data, soft clustering methods with overlapping clusters have been proposed that attain superior performance over the hard ones. Motivated by this, we propose a new algorithm named FL with soft clustering (FLSC) by combining the strengths of soft clustering and IFCA, where the clients are partitioned into overlapping clusters and the information of each participating client is used by multiple clusters simultaneously during each round. The experimental results show that FLSC achieves better learning performance on the classification tasks on the MNIST and Fashion-MNIST data sets, compared with the state-of-the-art baseline methods, i.e., the global model method and IFCA.

In this article, the problem of federated learning (FL) in the presence of label quality disparity is considered. To address this problem, the federated opportunistic computing for ubiquitous system (FOCUS) has been proposed very recently. In FOCUS, the central server utilizes its accurately labeled benchmark samples to quantify the credibility of different clients by computing the cross-entropy (CE) loss of the locally updated models on the benchmark data set and the CE loss of the global model on the local data sets. However, FOCUS assumes the availability of the accurate labels of the benchmark data set, which is difficult to guarantee under many practical scenarios. To overcome this limitation of FOCUS, we propose a new algorithm named robust federated opportunistic learning (RFOL), which does not require the benchmark samples at the central server to be labeled. In RFOL, the client credibility is evaluated by computing the Kullback–Leibler (KL) divergence among the soft predictions on the benchmark samples of different locally updated models and the CE loss of the global model on the local data sets. The experimental results on several popular data sets reveal that: 1) with an unlabeled benchmark data set at the server, the proposed RFOL algorithm attains almost the same learning performance as FOCUS, which requires an accurately labeled benchmark data set at the server; 2) with an inaccurately labeled benchmark data set, RFOL outperforms FOCUS, which shows that the former is more robust to the inaccurate labels of the benchmark samples; and 3) RFOL outperforms FedAvg, which assigns equal credibility to all the clients.

The maximum unambiguous Doppler in classical saw-tooth frequency-modulated continuous wave (FMCW) radar is inherently limited by the sweep repetition frequency (SRF). In this letter, an unambiguous Doppler extension method for FMCW radar is proposed, based on the combination of Poisson disk sampling (PDS) and sparse recovery. The PDS is adopted in the slow time domain such that there are random intervals between adjacent transmitted sweeps and no overlaps. Taking advantages of the excellent spectrum antialiasing performance of PDS, the maximum unambiguous Doppler of FMCW radar can be extended without reducing the range resolution. Then, the iterative soft thresholding-like (IST-like) algorithm is utilized to reconstruct the accurate range-Doppler spectrum. Compared with the existing unambiguous Doppler extension methods, the proposed method performs better in multitarget and low signal-to-noise ratio (SNR) scenarios. The effectiveness of the proposed method is verified by the experiments on real FMCW radar data.

Image matching is a primary technology for optical and synthetic aperture radar (SAR) image fusion but often shows limited performance due to the highly nonlinear differences between optical and SAR modalities. Recently, deep neural networks (DNNs) have been investigated to effectively extract nonlinear features for image matching tasks, where DNNs are trained based on the elaborated design of loss functions and a low loss value is often expected to obtain better image matching performance. In this letter, we first theoretically demonstrate that when the value of a state-of-the-art loss function decreases, the corresponding matching performance may not consistently improve due to the imbalanced effect of positive and negative samples. To tackle this issue, we proposed an improved loss function to train DNNs for image matching of SAR and optical images. We theoretically prove that the improved loss function ensures the improvement of the matching performance when the loss value decreases based on Taylor’s series expansion analysis. Experimental results on an open dataset with extensive optical and SAR image pairs show that 1) the proposed loss function is better than the original one in terms of image matching performance and 2) the combination of our loss function and existing multiscale convolutional gradient feature (MCGF)-based network provides better matching performance than other state-of-art approaches.

The performance of moving target detection in heterogeneous environments with the traditional space-time adaptive processing (STAP) may degrade when the real clutter environments deviate from the prior assumption on the clutter distribution. In this letter, a new detector for STAP applications based on volume cross-correlation function (VCF), namely VCF-STAP, is proposed to achieve robust performance of moving target detection in heterogeneous environments. In the new VCF-STAP, the VCF is used to form a distance measure between the sample signal subspace and the target subspace without modeling the clutter distribution. Then, a new robust STAP detection statistic is constructed using this distance measure. Simulation and experimental results show that the proposed VCF-STAP achieves robust performance of moving target detection in heterogeneous environments, especially it achieves much superior detection performance compared with existing STAP methods when the real clutter environments do not satisfy their prior assumptions. Besides, it is also shown that VCF-STAP has the constant false alarm rate (CFAR) property.

Existing ship detection approaches in optical remote sensing images often suffer from bottlenecks in inshore scenarios due to the substantial interference. In addition, the ship targets with different orientation angles and large aspect ratios increase the difficulty to accurately profile and locate them in optical remote sensing images. To address the aforementioned issues, a novel dual separation attention network (DSA-Net) based on the skew complete intersection-over-union (SkewCIoU) loss is proposed in this letter. In our DSA-Net, we construct a contextual location module (CLM) as the spatial attention in the backbone stage and a global channel module (GCM) as the channel attention in the neck stage, respectively. The two separated attention modules enhance the discrimination between ship targets and complex inshore interferences. Moreover, a SkewCIoU loss considering both the angles and aspect ratios of ship targets is introduced to obtain a well-trained neural network with more accurate detection performance of slender ships. Experiments on the dataset of high-resolution ship collection 2016 (HRSC2016) manifest the superiority of the proposed algorithm in comparison to the existing state-of-the-art methods.

Multiple extended target tracking (METT) is a common and challenging problem. Various solutions for METT have been proposed, however, most of them focus on the single-sensor or centralized multi-sensor scenarios. In this letter, we explore the multi-sensor METT problem in a distributed fusion framework. Specifically, there are two stages in the implementation process: 1) to perform aGamma Gaussian Inverse Wishart Cardinalized Probability Hypothesis Density(GGIW-CPHD) filter for each sensor node, and 2) to perform a fusion by resorting to the so-calledGeneralized Covariance Intersection(GCI) fusion rule. In the fusion stage, we derive an approximate GGIW mixture form of the fused spatial density. Lastly, simulation experiments via a consensus sensor network are provided to verify the effectiveness of the proposed approach.

There is an inherent tradeoff between range swath width and azimuth resolution in the traditional spaceborne single-channel synthetic aperture radar (SAR). The range swath can be extended with reduced pulse repetition frequency (PRF), but this leads to the decrease of the azimuth resolution of SAR images. It is difficult for traditional SAR imaging methods that follow the Nyquist sampling theorem to obtain high-resolution and wide-swath imaging results simultaneously. Considering the influence of transmit pulse occlusion and the nadir echo on the selection of PRF in spaceborne SAR, a random PRF variation pulse transmission pattern that is constrained by the coverage diagram is designed in this article for wide-swath imaging. The minimum interval length between adjacent transmitted pulses is set to be larger than the Nyquist sampling interval, thus offering the capability to widen the range swath of spaceborne SAR imaging results. Then, the fast iterative shrinkage thresholding-like algorithm (FISTA-like) is performed on the nonuniformly sampled data to achieve sparse reconstruction of the high-resolution imaging results. Compared with the existing SAR imaging methods, the proposed method realizes high-resolution and wide-swath imaging for spaceborne single-channel SAR with lower hardware implementation difficulty. Simulations and experiments on measured spaceborne SAR data demonstrate the effectiveness of the proposed method.

Microwave Imager Combined Active and Passive (MICAP), which is a package of active and passive microwave instruments including L/C/K-band radiometers and L-band scatterometer, has been chosen as one of the primary payloads for the Chinese Ocean Salinity Mission (COSM). The L-band one-dimensional synthetic aperture radiometer (L-Rad) is the key part of MICAP to measure sea surface salinity (SSS). As radio frequency interference (RFI) has been reported as a severe threat to L-band radiometry, it can be foreseen that MICAP L-Rad will encounter RFI contaminations unavoidably. Due to the conflict between the huge transmission data volume and the limited downlink budget, it is challenging for MICAP L-Rad to transmit all rapidly sampled sub-band data products and conduct on-ground RFI processing like Soil Moisture Active Passive (SMAP) microwave radiometer. The onboard real-time RFI detection and mitigation strategy is proposed accordingly for MICAP L-Rad. It is designed based on the distributed digital processing structure and the synthetic-aperture feature. The proposed RFI processing strategy is evaluated and verified by the system simulations and hardware experiment, demonstrating its RFI detection capability and low false alarm rate performance.

Radar imaging with 1-bit data is attractive thanks to its low storage and transmission burden. Existing 1-bit radar imaging methods cannot satisfactorily suppress the artifacts in the imaging result induced by 1-bit quantization error and noise. In this article, we propose a new 1-bit compressive sensing (CS) based algorithm, i.e., the adversarial-sample-based binary iterative hard thresholding (AS-BIHT) algorithm, to improve the 1-bit radar imaging performance. First, we formulate a parametric model for 1-bit radar imaging with a new adjustable quantization level parameter. The parametric 1-bit radar imaging model updates the imaging scene and the quantization level parameter in an iterative fashion based on adversarial samples. Then, we design a mechanism to generate adversarial samples by attacking the 1-bit radar imaging model to resist the quantization consistency condition, such that forcing quantization consistent reconstruction on adversarial samples mitigates the quantization error and noise. The quantization level parameter is then tuned based on the adversarial samples. In this way, the ability of the model to adapt to echo data contaminated by noise and quantization error is enhanced, and the artifacts are well suppressed. Simulation and experimental results on real radar data demonstrate the effectiveness of the proposed AS-BIHT algorithm in 1-bit radar imaging.

Change detection in heterogeneous remote sensing images is crucial for emergencies, such as disaster assessment. Existing methods based on homogeneous transformation suffer from the high computational cost that makes the change detection tasks time-consuming. To solve this problem, this article presents a new semisupervised Siamese network (S3N) based on transfer learning. In the proposed S3N, the low- and deep-level features are separated and treated differently for transfer learning. By incorporating two identical subnetworks that are both pretrained on natural images, the proposed S3N eliminates the computational cost for learning the low-level features that are universal for both remote sensing images and natural images. As the deep-level features contain different semantics between remote sensing images and natural images, a novel transfer learning strategy is presented to train only the weights of the layers for deep-level features in the proposed S3N. The decrease in the number of network parameters to be trained reduces the demand for training samples, leading to a significant decrease in computational cost. Afterward, the thresholding method,Otsu, is applied to the difference map derived by the proposed S3N to obtain the final binary map of change detection. Three data sets including different types of heterogeneous remote sensing images are employed to evaluate the performance of the proposed S3N. The experimental results demonstrate that the proposed S3N can achieve a comparable detection performance with much lower computational cost, compared with state-of-the-art change detection algorithms.

Traditional micro-Doppler (m-D)-based human activity classification system using monostatic radar suffers from the drawback that classification performance is vulnerable to the variation of human motion aspect angle. This leads to a performance degradation if the human movements are not directly toward or away with respect to the radar line of sight. The multistatic radar system has been suggested as an effective solution to solve the problem, as it can observe the target from multiple views and achieve favorable aspect angles to the targets. In this article, a novel human activity classification method based on motion orientation determining using multistatic m-D signals is proposed. First, the aspect angles of target motion direction with respect to each radar nodes are inferred by using the proposed motion orientation estimation method. The multistatic m-D data are then divided into several intervals based on the measured angle, and the data in the same interval are fused at the data level. Finally, the classification results are obtained through the adaptive weighted decision-level fusion. Compared with the traditional multistatic classification method, due to the consideration of the time-varying human motion aspect angle, the proposed method is more reasonable in data fusion and has better classification performance.

With the dramatic increase in human space activities, anomaly detection becomes an important issue in passive space target surveillance. In this article, an anomaly detection algorithm based on Gaussian mixture model and radar micro-Doppler features is proposed to detect the abnormal motion status of the space target. By coherent sampling and time-frequency analysis on the radar echo with additive white Gaussian noise corresponding to the normal motion statuses of the target, four micro-Doppler features are extracted and tested for normal distribution. Furthermore, the distribution of the multi-dimensional features and the corresponding parameters are fitted and estimated by Gaussian mixture model and expectation-maximization algorithm. Then, an anomaly detector is derived by solving for decision region using the fitted probability density function and a preset confidence level. Experimental results show that the average anomaly detection rate of the proposed method is 16.7%, 19.1%, and 34.0% higher than the one-class support vector machine, the convex hull, and the convolutional autoencoder-based methods, respectively.

Fisher vectors (FVs) can capture multiple order information from superpixels (SPs) in synthetic aperture radar (SAR) images. Existing FV-based ship detectors mainly exploit the local contrast of FVs (LCFVs) but do not consider their global density features. This may lead to degraded performance in terms of discrimination between ship targets and the complex sea clutter. In this article, two new global cues from FVs are designed based on the fact that target FVs exhibit much lower densities than those of clutter FVs and also have large distances to the latter. Our two new global cues can suppress the sea clutter and significantly enhance ship targets throughout the SAR image. We also design an improved local cue from FVs for ship detection, in which the intensity contrast of SPs is incorporated into the existing LCFV indicator to reduce false alarms. By fusing the above two new global cues (and an improved local cue from FVs), we propose a new method for ship detection in SAR images. Experimental results based on Gaofen-3 SAR images show that the newly proposed detector provides better detection performance than other state-of-the-art detectors, especially in the presence of strong and highly heterogeneous sea clutter.

The simple linear iterative clustering (SLIC) has been shown as an efficient and widely used superpixel-based algorithm for segmenting marine synthetic aperture radar (SAR) images. However, SLIC does not consider the fact that the density of ship target pixels is significantly lower than that of sea clutter pixels, leading to a waste of computational cost and memory resources on lots of pure clutter areas and to the degradation of the compactness of superpixels. To address the aforementioned issues, we develop a new density-based SLIC (DSLIC) method for the superpixel-based segmentation of marine SAR images. In the initialization stage of our DSLIC, all the subimages in a large marine SAR image are rapidly prescreened via a new density-driven classifier, where most of the subimages only occupied by clutter pixels with comparatively high density are discarded and do not need to be segmented in the subsequent local clustering stage. The retained subimages contain both the clutter and potential target areas. This prescreening operation results in higher computation efficiency and memory savings. In the local clustering stage of DSLIC, besides the intensity proximity and the spatiality proximity (used in SLIC), the sparsity proximity (measured by density distances) is considered to reduce the coexistence of sparse target pixels with low density and nonsparse clutter pixels with high density within superpixels. Our theoretical and experimental results show that the proposed DSLIC method is faster and requires less memory than SLIC and other state-of-the-art superpixel-based segmentation methods for marine SAR images with similar or better segmentation accuracy.

The mirrored interferometric aperture synthesis (MIAS) is a promising technique for high-resolution observation in microwave radiometry. In this article, we present a new source localization method based on a novel hybrid coarray that can be constructed from the 1-D MIAS. The new method, namedMA-SSmethod, employs the spatial smoothing (SS) technique on the hybrid coarray of mirrored array (MA) in the MIAS. We show that it has the ability to resolve more sources than physical sensors. The theoretical analysis gives an upper bound on degrees of freedom (DOF) of$O(N^{2})$order using$N$physical sensors. Simulation and experiment results demonstrate that, compared with the discrete cosine transform (DCT) approach commonly utilized in the MIAS, the presented MA-SS method shows the superiorities on spatial resolution, sidelobe reduction, localization accuracy, and detection performance.

Model uncertainty is a serious challenge for robustness of tracking algorithms in radar systems. The smooth variable structure filter (SVSF) achieves error-bounded estimations for target state by scaling the magnitude of kinematic modeling error and accordingly performing a flexible switching strategy for the correction gain. However, the SVSF, without any smoothing functions, suffers from undesired chattering phenomenon since the measurement noise causes random disturbance to the identification of actual level of uncertainties, leading to obvious deterioration of tracking accuracy. In this paper, we present a new switching function for SVSF, i.e. the hyperbolic tangent function, for effective chattering suppression. Then we propose a new algorithm named as the Tanh-SVSF, which reformulates the correction gain with the new switching function, to improve the estimation accuracy for target state. A mathematical definition of SVSF chattering is proposed to quantify the chattering amplitude. It is demonstrated that the new switching function exerts a nonlinear compressing effect on the likelihood of measurement innovation and substantially reduces the disturbance of measurement noise, leading to elimination of the chattering problem. The stability of the Tanh-SVSF is analyzed, based on a proposed stability theorem and the numerical exhaustion strategy. Finally, the proposed method is tested on a simulated vehicle tracking scenario and real-world radar data from the Oxford Radar RobotCar Dataset, and shows superior performance over existing SVSF formulations and the Kalman filter, in view of tracking accuracy, track continuity and the proposed chattering indicator.

This paper concerns the robust state estimation of automotive radar targets in presence of model uncertainty. Smooth variable structure filter (SVSF) achieves error-bounded estimation for target state, even with an inaccurate description of target kinematic model. However, it suffers the undesired chattering phenomenon especially in case of a high model uncertainty level, and its performance is sensitive to a preset smoothing boundary layer parameter. In this paper, we propose a novel hybrid SVSF algorithm to handle these two problems simultaneously. First, we derive a nonlinear generalized variable smoothing boundary layer (NGVBL) parameter based on the conventional Tanh-SVSF method by minimizing the pseudo posterior estimation error covariance. Then this NGVBL is employed to realize an adaptive two-module switching strategy with respect to the uncertainty level to calculate the correction gain. If the uncertainty level is high, the undesired chattering is effectively suppressed by the standard Tanh-SVSF gain. In case of a low uncertainty level, the NGVBL is utilized to replace the preset smoothing boundary layer parameter and reformulate the correction gain. Furthermore, it is demonstrated that the NGVBL-based gain is quasi-optimal in the mean square error (MSE) sense. Accordingly, this novel NGVBL-based hybrid SVSF (NGVBL-SVSF) algorithm improves the estimation performance by avoiding parameter sensitivity in a low uncertainty level case, and maintains effective chattering suppression and robustness to increasing uncertainties. Simulation and real-world automotive radar data experiment results show that, the proposed NGVBL-SVSF outperforms existing SVSFs and the classical Kalman filter in terms of tracking accuracy and track continuity.

In recent years, unmanned aerial vehicles (UAV) have been widely adopted to support complex target tracking tasks for military and civilian applications, especially in open and unknown environments. In practical cases, the moving trajectory of the target cannot be known to the UAVs in advance, which brings great challenges to UAVs to realize real-time and effective tracking. In addition, the limited tracking ability of a single UAV can hardly meet the requirements of a high tracking success rate. To deal with these problems above, this paper establishes a multi-UAV cooperative target tracking system. Besides, a deep reinforcement learning (DRL) based algorithm is designed to enable UAVs to make flight action decisions intelligently to track the moving air target, according to the past and current position information of the target only. To further increase the detection coverage of the UAV network when tracking, spatial information entropy is introduced to the reward designing in this algorithm. Simulation results validate that the proposed algorithm yields impressive target tracking performances, and significantly outperforms several common DRL baselines in terms of the tracking success rate. The convergence of the algorithm is also verified by the simulations.

In the paper, we propose a new method based on multi-order superpixel-level saliency and fuzzy logic (MSSFL) to fuse spaceborne and airborne SAR images for vessel detection. First, we generate a new global regional contrast map (GRCM) by exploiting the multi-order superpixel-level saliency (MSS). In the generated GRCM, the vessel targets are well restored and the backgrounds are suppressed. Next, a new fuzzy logic approach is presented to fuse the MSS information provided by the GRCMs. This GRCM-based fuzzy fusion can further enhance the vessel target regions and filter out the inshore interference regions. Experimental results using Gaofen-3 satellite and unmanned aerial vehicle (UAV) SAR images show that the proposed MSSFL method yields higher target-to-cluster ratio (TCR) of fused images and improved detection performance compared with the commonly utilized image fusion approaches.

The performance of the European Space Agency (ESA) Soil Moisture and Ocean Salinity (SMOS) mission deteriorates due to radio-frequency interference (RFI) sources such as unwanted or unauthorized emissions in the L-band and its ad-j acent bands. Accurate detection of these RFI sources is the foundation of the following RFI localization and mitigation, which are crucial to guarantee the quality of SMOS products. In this paper, we present an RFI detection approach based on reweighted l1-norm minimization (RL1). This approach exploits the sparsity of RFI sources in the spatial domain and recovers the RFI source signals within an RL1 framework. Experimental results indicate that the presented RL1- based approach performs better RFI detection performance compared with the conventional approaches based on discrete Fourier transformation (DFT) and spatial spectrum analysis.

In this article, we investigate the problem of federated learning (FL) in a communication-constrained environment of the Internet of Things (IoT), where multiple IoT clients train a global model collectively by communicating model updates with a central server instead of sending raw data sets. To ease the communication burden in IoT systems, several approaches have been proposed for the FL tasks, including sparsification methods and data quantization strategies. To overcome the shortcomings of the existing methods, we propose two new FL algorithms based on compressed sensing (CS) referred to as the CS-FL algorithm and the 1-bit CS-FL algorithm, both of which compress the upstream and downstream data while communicating between the clients and the central server. The proposed algorithms improve upon the existing algorithms by letting the clients send analog and 1-bit data, respectively, to the server after compression with a random measurement matrix. Based on that, in CS-FL and 1-bit CS-FL, the clients update the model locally utilizing the result of sparse reconstruction obtained by iterative hard thresholding (IHT) and binary IHT (BIHT), respectively. Experiments conducted on the MNIST and the Fashion-MNIST data sets reveal the superiority of the proposed algorithm over the baseline algorithms, SignSGD with a majority vote, FL based on sparse ternary compression, and FedAvg.

Dynamic hand gesture recognition using the microwave or millimeter-wave radar sensors has become a typical technology for many human-computer interaction (HCI) applications. In this letter, a novel method is proposed for dynamic hand gesture recognition based on micro-Doppler radar signatures. The short-time Fourier transform is carried out on the raw data to obtain the time-frequency spectrogram. The time-frequency spectrograms associated with the same dynamic hand gesture are modeled by a hidden Gauss-Markov model (HGMM), and the testing gesture is recognized by the maximum likelihood criterion. Experimental results with real radar data demonstrate that the proposed method has a strong generalization ability for radar gesture recognition in the cases of low signal-to-noise ratio (SNR) and unknown users.

In this letter, we propose a new constant false alarm rate (CFAR) detector to accelerate the existing superpixel (SP)-based CFAR detectors for ship detection in synthetic aperture radar (SAR) images. In our method, we design a new density-censoring operation to rapidly identify background clutter SPs (BCSPs) with high densities before the local CFAR detection. In this way, a large number of non-informative BCSPs are removed without time-consuming calculation of decision thresholds, and only a few candidate ship target SPs (STSPs) are retained. This reduces the computational cost of the subsequent local CFAR detection and the number of false alarms produced by it. During the local CFAR detection process for the retained candidate STSPs, we also propose an improved method to define their neighboring clutter regions (for the calculation of decision thresholds) using BCSPs identified by the density-censoring operation. Experiments on measured SAR images validate that the proposed CFAR method reduces the computational cost of commonly used SP-based CFAR methods by 75%-96% with similar or better detection performance.

As a powerful coding strategy for superpixels in synthetic aperture radar (SAR) images, Fisher vector (FV) lies in a low-dimensional subspace and can be sparsely represented as a linear combination of training samples. The existing ship detection methods based on FVs often consider the Euclidean distances between target FVs and clutter FVs, where the subspace features of FVs are generally not exploited. In this article, we propose a new ship detection algorithm based on nonnegative sparse locality-representation (NSLR) to exploit the subspace features of FVs. The proposed NSLR method is based on the assumption that FVs of superpixels in SAR images are sparsely represented by the dictionary of background sea clutter only under a null hypothesis. In addition, we propose two FV-based filters to enhance the robustness of our newly developed NSLR to heterogeneous sea clutter environments by further exploiting the intrinsic features of ship targets in terms of intensity and spatiality. The experimental results based on Gaofen-3 SAR images demonstrate that the proposed NSLR detection method provides higher target-to-clutter contrast and achieves better detection performance than other commonly used ship detection algorithms.

The Soil Moisture and Ocean Salinity (SMOS) mission led by the European Space Agency (ESA) is aimed to globally monitor the Earth surface moisture and ocean salinity. As the single payload of SMOS satellite, the Microwave Interferometric Radiometer with Aperture Synthesis (MIRAS) operates in the protected L-band. Nonetheless, the artificial sources emitting close to or/and fully in this band are contaminating the collected remote sensing data and deteriorating the performance of the SMOS mission. Identifying and localizing such sources is crucial to improve the quality of SMOS scientific products. In this article, we propose a method based on matrix completion (MC) for localization of radio frequency interference (RFI) sources. This method mainly exploits the low-rank property of the augmented covariance matrix (ACM) of the sparse array and addresses the ACM incompleteness (i.e., sampling data loss) due to inherent array geometry (e.g., the SMOS Y-shaped array) or potential hardware malfunction (e.g., the correlator failure). Validation results show that, compared with existing RFI localization approaches such as the discrete Fourier transformation (DFT) inversion and covariance-based direction-of-arrival (DOA) estimation, the proposed MC method possesses competitive localization accuracy, superior spatial resolution, and reduced artifacts.

In this paper, we present a new detector for the detection of sparse stochastic signals using 1-bit data in two-level two- degree tree-structured sensor networks (2L-2D TSNs). Related prior work mostly concentrates on parallel sensor networks (PSNs). However, PSNs may sometime become impractical in many applications including the case where some sensors are beyond the communication range of the fusion center (FC). Therefore, we design the proposed detector for 2L-2D TSNs where information is transmitted hierarchically. To satisfy severe resource constraints, each local sensor performs 1-bit quantization before transmission to the FC. The FC fuses the received 1-bit data employing the locally most powerful test (LMPT). It is shown theoretically and numerically that, compared with the LMPT detector with Q sensors that transmit analog measurements in 2L-2D TSNs, the proposed 1-bit LMPT detector that uses quantization thresholds derived in this paper asymptotically requires 1.74Q sensors to compensate for the performance loss induced by local quantization.

A mirrored array configuration, which consists of an ordinary linear array and a reflector, is proposed. The mirrored arrays can provide composable degrees of freedom (DOF) for array processing by combined measurements with the help of mechanical adjustment (e.g., movement or rotation). This composability naturally leads to DOF enhancement and facilitates its applications in direction-of-arrival (DOA) estimation. The feasibility and effectiveness of the proposed arrays are demonstrated through numerical analysis.

We examine the problem of Value of Information (VoI) based underwater information collection, which is the essence of many underwater applications such as depth surrounding oil platforms, monitoring of algal blooms and so on. Even if the information collection work has been carried out much in the terrestrial scenario, due to complicated physical, technological and economic differences between the terrestrial and underwater cases, it is not feasible to simply apply the existing terrestrial tricks. The existing cooperative Autonomous Underwater Vehicle (AUV) working paradigms are limited to omniscience of communication channel information among the AUVs, which is yet not practical in such a harsh communication environment. Therefore, we propose a contract based model which has little restriction on the communication channel to overcome information asymmetry and jointly optimizes energy consumption and VoI. Besides, we provide a concrete theoretical proof of the contract items and carry out a performance simulation which shows the mechanism we design is operative. At last, we summarize our work and give an insight of the future research directions.

In this paper, we propose an improved superpixel segmentation algorithm for ship target detection in synthetic aperture radar (SAR) images, called adaptive Fisher vector-based simple linear iterative clustering (AFVSLIC). Compared with existing algorithms, three new features produced by Fisher vectors, i.e., zero-order, first-order and second-order features, are exploited by the proposed AFVSLIC algorithm to enhance segmentation performance. Besides, AFVSLIC adaptively adjusts the weights of the features to maintain the segmentation performance in different signal-to-clutter ratio (SCR) scenarios. Experimental results demonstrate that the proposed AFVSLIC algorithm outperforms existing, commonly used algorithms for superpixel segmentation and (accordingly) improves the performance of ship target detection.

The artificial sources emitting close to or/and in the L-band are contaminating the collected remote sensing data and deteriorating the performance of the Soil Moisture and Ocean Salinity (SMOS) mission. Detecting and locating such sources is crucial to improve the quality of SMOS scientific products. In this paper, we present an approach based on matrix completion (MC) for localization of radio-frequency interference (RFI) sources. This approach exploits the low-rank property of the augmented covariance matrix (ACM) of the sparse array, and addresses the ACM incompleteness (i.e., sampling data loss) due to inherent array geometry (e.g., the SMOS Y-shaped array). Some experimental results indicate that, compared with existing approaches based on the discrete Fourier transformation (DFT) inversion and direction-of-arrival (DOA) estimation, the proposed MC approach has better performance such as superior spatial resolution and reduced artifacts.

In this letter, we consider the problem of distributed detection of stochastic sparse signals in battery-powered sensor networks (SNs). For this problem, an original locally most powerful test (oLMPT) detector has previously been developed, where compressed measurements are collected from all local sensors and then fused at the fusion center (FC) for making the global decision. However, since the sensors always operate on limited energy resources, allowing all the nodes to send their observations to the FC all the time exerts tremendous pressure on their energy consumption and hinders the longevity of the sensors. To solve this problem, we propose a new censoring LMPT (cen-LMPT) detector by combining the strengths of censoring strategy and the oLMPT detector, where sensors are designated to merely send observations deemed informative enough so as to utilize the local energy more efficiently, and the FC still makes the global decision based on LMPT. We analytically derive the relationship between the detection performance and the communication rate for the proposed detector. It is shown that, compared with the oLMPT detector, the proposed cen-LMPT detector with the same number of nodes can achieve almost the same detection performance with significantly lower communication rate and, therefore, much lower local energy consumption. The simulation results verify our theoretical findings.

Regularization method is an effective tool for synthetic aperture radar (SAR) image despeckling. Design of the effective regularization terms describing the image priors plays a vital role in this kind of method. In this article, a new combinational regularization model for speckle reduction (CRM-SR) is proposed, in which a regularization term is elaborately designed to contain both a fractional-order total variation (FrTV) regularization and a nonlocal low rank (NLR) regularization. The new regularization model inherits both the advantages of FrTV and NLR and improves the performance of SAR despeckling and, therefore, better preserves the edges and geometrical features of the images during the despeckling process. An efficient algorithm based on alternating direction optimization is derived to solve the proposed combinational regularization model. Experimental results show that the proposed model can effectively remove SAR image speckle and preserve the geometrical features of images according to both subjective visual assessment of image quality and objective evaluation.

Existing superpixel-based detection algorithms for ship targets in synthetic aperture radar (SAR) images are often derived from the local contrast of intensities (i.e., the local contrast of the first-order information of superpixels) leading to deteriorating performance in low signal-to-clutter ratio (SCR) cases due to the low contrast between the intensities of targets and the clutter. In this article, we propose a new superpixel-based detector to improve the performance of ship target detection in SAR images via the local contrast of fisher vectors (LCFVs). The new LCFV-based detector exploits multiorder features of the superpixels based on the Gaussian mixture model (GMM) and accordingly improves the discrimination capability between the ship targets and the sea clutter, especially in low SCR cases. Experimental results demonstrate that the proposed LCFV-based detection algorithm provides better detection performance than the commonly used detection algorithms.

The Microwave Interferometric Radiometer with Aperture Synthesis (MIRAS) is the payload of the Soil Moisture and Ocean Salinity (SMOS) satellite mission led by the European Space Agency. Although the MIRAS operates at the protected L-band, it is perturbed by radio frequency interferences (RFIs) that contaminate the acquired remote sensing data and further deteriorate the total performance of SMOS mission. Accurate location information of these sources is crucial for switching off illegal RFI emitters or mitigating RFI impacts from contaminated data. This article addresses the localization of SMOS RFI sources from a perspective of sparse signal reconstruction (SSR), which exploits the sparsity of RFI sources in the spatial domain. Such an SSR strategy possesses superior (at least comparable) performances over existing RFI localization methods [e.g., discrete Fourier transformation (DFT) inversion and subspace-based direction-of-arrival (DOA) estimation] using only SMOS measurements and even under situations in the presence of data missing due to correlator failures.

Homogeneous transformation receives considerable attention in recent years as it is essential for change detection in heterogeneous images. However, most existing methods perform the homogeneous transformation based on low-level features. It leads to inaccurate homogeneous representations of the heterogeneous images and accordingly causes unsatisfied performance of change detection. To solve this problem, this paper presents a new model that utilizes deep- level features for homogeneous transformation instead of low-level features. Experimental results on real remote sensing data show that, the proposed method achieves an overall change detection accuracy of 95.91%, providing better performance than the existing methods based on low- level features.

In this letter, we consider the detection of sparse stochastic signals with sensor networks (SNs), where the fusion center (FC) collects 1-bit data from the local sensors and then performs global detection. For this problem, a newly developed 1-bit locally most powerful test (LMPT) detector requires 3.3Q sensors to asymptotically achieve the same detection performance as the centralized LMPT (cLMPT) detector with Q sensors. This 1-bit LMPT detector is based on 1-bit quantized observations without any additional processing at the local sensors. However, direct quantization of observations is not the most efficient processing strategy at the sensors since it incurs unnecessary information loss. In this letter, we propose an improved-1-bit LMPT (Im-1-bit LMPT) detector that fuses local 1-bit quantized likelihood ratios (LRs) instead of directly quantized local observations. In addition, we design the quantization thresholds at the local sensors to ensure asymptotically optimal detection performance of the proposed detector. It is shown theoretically and numerically that, with the designed quantization thresholds, the proposed Im-1-bit LMPT detector for the detection of sparse signals requires less number of sensor nodes to compensate for the performance loss caused by 1-bit quantization.

We consider the distributed detection of weak signals from one-bit measurements collected by a sensor network where observation model uncertainties exist at all the sensor nodes. To solve this problem, a one-bit locally most powerful test (LMPT) detector is proposed in this letter. Moreover, asymptotically optimal one-bit quantizers at all the sensor nodes are designed for the proposed one-bit LMPT detector. In this letter, model uncertainties are interpreted as multiplicative noise and its variance represents the strength of model uncertainties. Theoretical analysis indicates that, when the strength of model uncertainties is finite, the proposed detector using one-bit data with πN/2 sensors approximately achieves the same detection performance as the clairvoyant detector that directly uses analog measurements with N sensors. Simulation results corroborate our theoretical analysis and show that, compared to the one-bit generalized likelihood ratio test detector, the proposed one-bit LMPT detector provides better detection performance in the presence of model uncertainties.

Conventional compressive sensing (CS) aims at sparse signal recovery from the measurements with continuous values. Quantized CS (QCS) methods arise in digital implementations where quantization of the receiver data is performed prior to signal processing. The extreme case of QCS is the so-called 1-bit CS where each real-valued measurement maintains only the sign information with one bit. The 1-bit CS alleviates the burden of storage and transmission of large data volumes and reduces the cost of the analog-to-digital converter. Recently, the 1-bit CS has been successfully applied to inverse scattering and radar imaging. In high-resolution radar imaging scenarios, targets assume spatial extent and occupy clustering pixels. The real and imaginary components of a complex sparse signal are the projections of the same complex value onto two orthogonal axes and, therefore, share a joint sparsity pattern. In this paper, a new 1-bit CS algorithm, referred to as enhanced-binary iterative hard thresholding (E-BIHT), is proposed to improve quality of 1-bit radar imaging by exploiting the two-level block sparsity exhibited in the two properties of clustering and the joint sparsity pattern of the real and imaginary parts of the target image. Simulations and experimental results demonstrate that compared to commonly used 1-bit CS algorithms, the proposed E-BIHT provides more informative imaging resulting in higher target-to-clutter ratio.

Since the width of range swath of synthetic aperture radar (SAR) is restricted by the pulse repetition frequency, there exists a tradeoff between the azimuth resolution and the range swath width. As a result, conventional SAR imaging methods based on the Nyquist sampling theorem can hardly achieve the high resolution and wide swath simultaneously. In this paper, we propose an algorithm of high-resolution and wide-swath SAR imaging based on the combination of Poisson disk sampling and iterative shrinkage thresholding. Poisson disk sampling adopted in the azimuth direction can ensure that the interval between any two adjacent pulses is longer than the Nyquist sampling interval, which provides the potential to widen SAR imaging swath in the range direction. The imaging formation is carried out by performing the inverse operator of the chirp scaling algorithm and the shrinkage thresholding in an iterative fashion. Compared with the existing SAR imaging methods, the proposed method can realize high-resolution and wide-swath SAR imaging simultaneously with affordable computational cost. Simulations and experiments on real SAR data demonstrate the effectiveness of the proposed method.

In this letter, we propose two methods for personnel recognition and gait classification using deep convolutional neural networks (DCNNs) based on multistatic radar micro-Doppler signatures. Previous DCNN-based schemes have mainly focused on monostatic scenarios, whereas directional diversity offered by multistatic radar is exploited in this letter to improve classification accuracy. We first propose the voted monostatic DCNN (VMo-DCNN) method, which trains DCNNs on each receiver node separately and fuses the results by binary voting. By merging the fusion step into the network architecture, we further propose the multistatic DCNN (Mul-DCNN) method, which performs slightly better than VMo-DCNN. These methods are validated on real data measured with a 2.4-GHz multistatic radar system. Experimental results show that the Mul-DCNN achieves over 99% accuracy in armed/unarmed gait classification using only 20% training data and similar performance in two-class personnel recognition using 50% training data, which are higher than the accuracy obtained by performing DCNN on a single radar node.

We consider the problem of detection of sparse stochastic signals with a distributed sensor network. Multiple sensors in the network are assumed to observe sparse signals, which share the joint sparsity pattern. The Bernoulli-Gaussian (BG) distribution with sparsity-enforcing capability is imposed on the sparse signals. The sparsity degree in the BG model is positive and close to zero in the presence of the sparse signals and is zero in the absence of the signals. Motivated by this, the problem of detection of the sparse signals with a distributed sensor network is formulated as the problem of close and one-sided hypothesis testing on the sparsity degree. For this problem, we propose a detector based on the locally most powerful test (LMPT) to decide on the presence or absence of sparse signals with sensor networks. The proposed LMPT detector does not require signal recovery, which alleviates the complexity of the detection system in sensor networks. Simulation results illustrate the performance of the proposed LMPT detector and corroborate our theoretical analysis. Simulation results also show that, compared to the detector based on matching pursuit, the proposed LMPT detector significantly reduces the computational burden without noticeable performance loss.

In this paper, we propose a two-level block matching pursuit (TLBMP) algorithm based on a probabilistic graph model for polarimetric through-wall radar imaging (TWRI). In typical L-band to X-band TWRI, indoor targets assume a spatial extent and occupy clustered pixels. When polarimetric sensing is used to obtain independent observations, radar images of clustered targets can be enhanced within the joint sparsity framework. Toward this objective, TLBMP is devised to exploit both the clustered property and the joint sparsity pattern of multiple polarimetric through-wall radar images. Simulations and experimental results based on polarimetric through-wall radar data demonstrate that compared to commonly used algorithms for solving the same underlying problem, TLBMP provides more informative imaging with higher target-to-clutter ratio.

The change detection in heterogeneous remote sensing images remains an important and open problem for damage assessment. We propose a new change detection method for heterogeneous images (i.e., SAR and optical images) based on homogeneous pixel transformation (HPT). HPT transfers one image from its original feature space (e.g., gray space) to another space (e.g., spectral space) in pixel-level to make the pre-event and post-event images represented in a common space for the convenience of change detection. HPT consists of two operations, i.e., the forward transformation and the backward transformation. In forward transformation, for each pixel of pre-event image in the first feature space, we will estimate its mapping pixel in the second space corresponding to post-event image based on the known unchanged pixels. A multi-value estimation method with noise tolerance is introduced to determine the mapping pixel using -nearest neighbors technique. Once the mapping pixels of pre-event image are available, the difference values between the mapping image and the post-event image can be directly calculated. After that, we will similarly do the backward transformation to associate the post-event image with the first space, and one more difference value for each pixel will be obtained. Then, the two difference values are combined to improve the robustness of detection with respect to the noise and heterogeneousness (modality difference) of images. Fuzzy-c means clustering algorithm is employed to divide the integrated difference values into two clusters: changed pixels and unchanged pixels. This detection results may contain some noisy regions (i.e., small error detections), and we develop a spatial-neighbor-based noise filter to further reduce the false alarms and missing detections using belief functions theory. The experiments for change detection with real images (e.g., SPOT, ERS, and NDVI) during a flood in U.K. are given to validate the effectiveness of the proposed method.

A new change detection method for heterogeneous remote sensing images (i.e. SAR & optics) has been proposed via pixel transformation. It is difficult to directly compare the pixels from heterogeneous images for detecting changes. We propose to transfer the pixels in different images to a common feature space for convenience of comparison. For each pixel in the 1stimage, it will be transferred to the 2ndfeature space associated with the 2ndimage according to the given unchanged pixel pairs. In fact, this transformation is done assuming that the pixel is not affected by the events. Then the difference value between the estimation of transferred pixel and the actual one in the same location of the 2ndimage can be calculated. The bigger difference value, the higher possibility of change happening. We can similarly do the opposite transformation from the 2ndimage to the 1stimage, and one more difference value is obtained in the 1stfeature space. Change occurrences will be detected using Fuzzy C-means clustering method based on the sum of two difference values. The flood detection in the SAR and optical images is given in the experiments, and it shows that the proposed method is able to efficiently detect changes.

This paper proposes a combinational regularization model for synthetic aperture radar (SAR) image despeckling. In contrast to most of the well-known regularization methods that only use one image prior property, the proposed combinational regularization model includes both fractional-order total variation (FrTV) regularization term and nonlocal low rank (NLR) regularization term. By characterizing the smoothness and nonlocal self-similarity property of the SAR image simultaneously, the proposed model, on the one hand, can better remove the noise in homogeneous regions of a noisy image, and on the other hand, can better preserve edges and geometrical features of the images during the despeckling process. Afterwards, an alternating direction method (ADM) is derived to efficiently solve the optimization problem in the proposed model. Experimental results demonstrate the good performance of the proposed model, both in removing SAR image speckles and preserving image texture and details.

A method of motion status estimation of airborne synthetic aperture radar (SAR) platform in short subapertures via parametric sparse representation is proposed for high-resolution SAR image autofocusing. The SAR echo is formulated as a jointly sparse signal through a parametric dictionary matrix, which converts the problem of SAR motion status estimation into a problem of dynamic representation of jointly sparse signals. A full synthetic aperture is decomposed into several subapertures to estimate the dynamic motion parameters of a platform, and SAR motion compensation is achieved by refining the estimation of the equivalent platform motion parameters, i.e., the azimuth velocity and the radial acceleration of the radar platform, at each subaperture in an iterative fashion. Experimental results based on both simulated and real data demonstrate that: 1) the proposed algorithm outperforms the map-drift algorithm and the phase gradient autofocus algorithm in terms of the imaging quality and 2) compared to the iterative minimum-entropy autofocus, the proposed algorithm produces the comparative imaging quality with less computational complexity in complex motion environment.

In this paper, we propose a novel greedy algorithm referred to as look-ahead hybrid matching pursuit (LAHMP) for multipolarization through-wall radar imaging (TWRI). From the viewpoint of compressive sensing, the task of multipolarization TWRI can be formulated as a problem of sparsity pattern recovery under the joint sparsity model. A newly developed greedy algorithm for joint sparsity model, hybrid matching pursuit (HMP), combines the strengths of orthogonal matching pursuit and subspace pursuit and improves the accuracy of the sparsity pattern recovery. Besides, the look-ahead strategy can select an optimal atom by evaluating its effectiveness on the overall reconstruction quality. Through integrating the virtues of HMP with the look-ahead strategy, the proposed LAHMP aims to more accurately select atoms corresponding to the true targets behind walls. Experiments based on measured radar data show that, compared to existing greedy algorithms, LAHMP provides better image quality at affordable expense of computational complexity.

In this paper, we consider the problem of fusion of multi-polarization radar images and develop a new greedy algorithm referred to as hybrid matching pursuit (HMP). By combining the strengths of the orthogonal matching pursuit algorithm and the subspace pursuit algorithm, HMP can enhance target reflections and attenuate background clutter. Experimental results based on measured radar data demonstrate that HMP offers better image quality with higher target-clutter-ratio compared to some popular greedy algorithms.

Compressive sensing (CS) provides a new perspective for data reduction without compromising performance when the signal of interest is sparse or has intrinsically low-dimensional structure. The theoretical foundation for most of the existing studies on CS is based on the stable embedding (i.e., a distance-preserving property) of vectors that are sparse or in a union of subspaces via random measurement matrices. To the best of our knowledge, few existing literatures of CS have clearly discussed the stable embedding of linear subspaces via compressive measurement systems. In this paper, we explore a volume-based stable embedding of multidimensional signals based on Grassmann manifold, via Gaussian random measurement matrices. The Grassmann manifold is a topological space, in which each point is a linear vector subspace, and is widely regarded as an ideal model for multidimensional signals generated from linear subspaces. In this paper, we formulate the linear subspace spanned by multidimensional signal vectors as points on the Grassmann manifold, and use the volume and the product of sines of principal angles (also known as the product of principal sines) as the generalized norm and distance measure for the space of Grassmann manifold. We prove a volume-preserving embedding property for points on the Grassmann manifold via Gaussian random measurement matrices, i.e., the volumes of all parallelotopes from a finite set in Grassmann manifold are preserved upon compression. This volume-preserving embedding property is a multidimensional generalization of the conventional stable embedding properties, which only concern the approximate preservation of lengths of vectors in certain unions of subspaces. In addition, we use the volume-preserving embedding property to explore the stable embedding effect on a generalized distance measure of Grassmann manifold induced from volume. It is proved that the generalized distance measure, i.e., the product of principal sines between different points on the Grassmann manifold, is well preserved in the compressed domain via Gaussian random measurement matrices. Numerical simulations are also provided for validation.

To solve the problem of joint sparsity pattern recovery in a decentralized network, we propose an algorithm named decentralized and collaborative subspace pursuit (DCSP). The basic idea of DCSP is to embed collaboration among nodes and fusion strategy into each iteration of the standard subspace pursuit (SP) algorithm. In DCSP, each node collaborates with several of its neighbors by sharing high-dimensional coefficient estimates and communicates with other remote nodes by exchanging low-dimensional support set estimates. Experimental evaluations show that, compared with several existing algorithms for sparsity pattern recovery, DCSP produces satisfactory results in terms of accuracy of sparsity pattern recovery with much less communication cost.

Compressive Sensing (CS) provides a new perspective for dimensionnality reduction without compromising performance. The theoretical foundation for most of existing studies of CS is a stable embedding (i.e., a distance-preserving property) of certain low-dimensional signal models such as sparse signals or signals in a union of linear subspaces. However, few existing literatures clearly discussed the embedding effect of points on the Grassmann manifold in under-sampled linear measurement systems. In this paper, we explore the stable embedding property of multi-dimensional signals based on Grassmann manifold, which is a topological space with each point being a linear subspace of ℝN(or ℂN), via the Gaussian random matrices. It should be noted that the stability mentioned here is about the volume-preserving instead of distance-preserving, because volume is the key characteristic for linear subspace spanned by multiple vectors. The theorem of the volume-preserving stable embedding property is proposed, and sketched proofs as well as discussions about our theorem is also given.

Based on the covariance-like fitting criterion we propose a direction of arrival (DOA) estimation algorithm that embeds a weighting scheme in the objective function without selection of any hyperparameters. With an assumption of uncorrelated sources, we formulate the problem of DOA estimation as a linearly constrained quadratic optimization under power constraints. Numerical results show that the proposed method not only is robust to this assumption but also has the superior performance in comparison with some other sparsity-driven methods.

A method of Micro-Doppler component separation based on parametric sparse time-frequency representation is proposed in this paper. The received signal is decomposed into a family of parametric basis signals that are dependent of the target angular velocity, and the significant coefficients of the sparse solution indicate the initial phases and the Doppler amplitudes of Micro-Doppler components. The performance of the proposed method in terms of Micro-Doppler component separation is evaluated by simulations.

A novel high resolution ISAR imaging method based on adaptive sparse recovery is proposed in his paper. The ISAR signal in each range bin is sparsely represented by an over-complete chirplet basis matrix, which can be determined by an unknown parameter set. An adaptive parametric sparse recovery method is proposed to retrieve both the parameter set and the ISAR image. This goal is achieved by sequentially minimizing the L1norm of the sparse signal and the energy of the recovery error in an iterative manner.

Using multiple measurement vectors (MMV), we propose an algorithm based on weighted ℓ1minimization for direction- of-arrival (DOA) estimation, in which the weights are obtained by exploiting the orthogonality between the noise subspace and the array manifold matrix. The proposed algorithm penalizes the nonzero entries whose indices correspond to the row support of the jointly sparse signals by smaller weights and the other entries whose indices are more likely to be outside of the row support of the jointly sparse signals by larger weights, and therefore it can encourage sparsity at the true source locations. Numerical examples prove that the proposed algorithm has better performance than existing algorithms based on regular ℓ1minimization.

Inverse synthetic aperture radar (ISAR) imaging of maneuvering targets via matching pursuit (MP) can produce high resolution and remove sidelobe effect, providing that the target rotation rate is already known. For non-cooperative uniformly rotating targets, the rotation rate is unknown and should be retrieved together with the ISAR image. In this paper, a computational efficient parametric MP is proposed to simultaneously retrieve the rotation rate and the high-resolution ISAR image. The joint estimation of ISAR image and rotation rate is converted into alternate independent estimations, i.e. alternately estimating the ISAR image and rotation rate in an iterative manner. With the iterations, the rotation rate estimate converges to the true value and meanwhile the clear ISAR image with high resolution and low sidelobes may be obtained. Numerical examples show that the approach is efficient in estimating the real target rotation rate and recovering the high resolution ISAR image.

An algorithm based on matching pursuit (MP) technique is proposed for inverse synthetic aperture radar (ISAR) imaging of maneuvering targets. The received ISAR echo is decomposed into many basis sub-signals that are generated by discretizing the target spatial domain and synthesizing the ISAR data for every discretized spatial position, and then the ISAR imaging problem is converted into the sub-signal selection problem. The basis sub-signals that indeed contribute to the ISAR echo are selected by using the MP technique, and the projection coefficients of the ISAR echo on the selected basis sub-signals represent the ISAR image. In the case of unknown rotation rate of the target, the true rotation rate is obtained by combining the MP technique with the maximum contrast search. Numerical examples show that the proposed algorithm can produce high resolution and remove sidelobe artifacts.

In this letter, a novel radial velocity estimation and range shift compensation algorithm is proposed for high-range resolution profiling of moving targets in stepped-frequency (SF) radar. Compared to traditional methods, this algorithm is based on a more precise signal model, and can therefore achieve much higher estimation accuracy. Furthermore, the range shift problem caused by target motion can be resolved without alterations to the radar waveform. The performance of this algorithm is demonstrated using simulated and experimental results.

A novel STAP algorithm based on sparse recovery technique, called CS-STAP, were presented. Instead of using conventional maximum likelihood estimation of covariance matrix, our method utilizes the echo statistics on spatial-temporal plane, which is extracted from sample data of only ONE training range cell with Compressed Sensing techniques, to construct a new estimator of covariance matrix, and build the optimal detector based on it. Full description of CS-STAP is given. Numerical result on real data has provided the evidence for great potential of CS-STAP as a effective approach when clutter is non-stationary because it need much less training data compared with common STAP methods.

In this letter, a synthetic aperture radar (SAR) data reformatting approach named Doppler keystone transform (DKT) is proposed to correct the range migration of a moving target. By using the DKT, the SAR imaging program, i.e., the 2-D matched filtering, can be transformed into separate 1-D operations along range or azimuth direction, and therefore, the DKT is suitable for the parallel implementation of SAR imaging of the moving target. Our simulations show that by combining the DKT and the Doppler phase compensation methods, the moving target can be well imaged in high signal-clutter-ratio case.

Velocity synthetic aperture radar (VSAR) is equipped with a linear array to receive the echoes from a radar illuminating area via multiple channels, each of which can reconstruct a reflectivity image for the same stationary scene. Based on analysis of pixel vector sampled among multi-images, VSAR may effectively suppress the strong ground clutter and improve moving target detection and location. In this paper, different Doppler-distributed properties are derived for the moving target and clutter, respectively. Then, we propose a novel parametric statistical model for VSAR by dividing the pixel vector into three components, namely, target, clutter, and noise. Furthermore, a method of adaptive implementation of optimal processing (AIOP-VSAR) is presented for moving target detection. It is shown that the optimum detection performance may be obtained via AIOP-VSAR, particularly for the slowly moving target in an inhomogeneous clutter environment. Also, the Cramer-Rao bounds (CRBs) are derived for the estimation of unknown model parameters, as well as the azimuth locations of moving targets, and the maximum-likelihood methods are proposed to reach these CRBs. Based on the proposed target detection and parameter estimation methods, we present a complete parametric flowchart for VSAR. It is demonstrated that the proposed flowchart may effectively mitigate the "azimuth location ambiguity" of VSAR and has the super-resolution ability to resolve "velocity layover" for multiple targets. Finally, some detailed numerical experiments and scene simulations are provided to show the effectiveness of the proposed methods.

Based on a parametric model and some optimum methods, it has been previously proved that parametric velocity synthetic aperture radar (VSAR) may improve the performances of moving target detection and parameter estimation simultaneously. In this paper, multilook processing is studied for parametric VSAR. At first, statistical signal models are established for azimuth multilook processing (AMLP) and range multilook processing (RMLP), respectively. By combining the multiple AMLP sublook pixel vectors, it is shown that the clutter parameter estimation accuracy can be further improved via the maximum-likelihood estimation methods. Meanwhile, based on the adaptive implementation for the optimum processing of VSAR, RMLP can be used to improve slowly moving target detection performance via the noncoherent integration of multiple range sublooks. Furthermore, it is shown that the Doppler frequencies of moving targets vary linearly with different range sublooks due to the different carrier frequencies of sublooks. Therefore, based on a proposed novel two-step multilook diversity (TS-MLD) estimator for RMLP, the "azimuth location ambiguity" of VSAR can be well resolved via least squares linear regression, without configuration change of the conventional VSAR. Also, the estimation accuracy of target's unambiguous Doppler frequency, as well as target's azimuth location, is derived for the proposed TS-MLD method. Finally, numerical experiments and scene simulations are provided to demonstrate the effectiveness of the proposed multilook-based methods.

A robust phase-unwrapping algorithm has been recently proposed and applied to accurately locate fast moving targets in multifrequency antenna array synthetic aperture radar imaging. This algorithm is based on two dimensional (2-D) searching and its complexity may be high. In this letter, we propose an efficient implementation of the robust phase-unwrapping algorithm. We show that the range of the 2-D searching, and therefore the complexity of the robust phase-unwrapping algorithm, can be significantly reduced.

In this paper, we propose a bistatic linear array synthetic aperture radar (BLA-SAR) system for moving target detection, location, and imaging. In the BLA-SAR system, a geostationary satellite is used as a transmitter, and two airborne linear array radars are used as passive receivers, where the transmitted waveforms from the geostationary satellite may have two different carrier frequencies, two linear array antennas on two different airplanes may be equipped with different spacings, or two airplanes may fly with two different velocities. It is shown that, using the BLA-SAR, not only the stationary clutter can be suppressed but also locations of both slow and fast moving targets can be accurately estimated. Furthermore, an effective BLA-SAR algorithm of moving target imaging is also proposed. Lastly, some numerical experiments are given to demonstrate the effectiveness of the BLA-SAR