Massive multiple-input multiple-output (MIMO) is considered as a key technology in the sixth generation (6 G) communication systems, bringing unique channel characteristics such as spherical wavefront and spatial non-stationarity effects. In this paper, we propose a super-resolution ray launching (SRRL) method to efficiently and accurately model the channel characteristics of massive MIMO scenarios. SR-RL simplifies simulations by performing RL only on the selected antenna elements based on the coherence distance and ignoring other elements. Ray paths traced from the selected elements are distributed to the ignored elements using the reflecting planes and possible obstacles along the ray trajectory. The obtained ray paths of both selected and ignored elements are recorded in a table, revealing a pattern of changes in multipath components across the antenna array. Compared to traditional brute-force methods, SR-RL can reduce computational time significantly, and captures spherical wavefront and spatial non-stationarity effects without sacrificing accuracy.

Reconfigurable intelligent surface (RIS) technology has emerged as a key direction for 6 G mobile communication systems due to its revolutionary potential in channel control, coverage enhancement, and energy efficiency optimization. In this paper, a novel ray tracing (RT) channel model for RIS-based beamforming at the transmitter (Tx) side is proposed. The model considers line-of-sight (LoS) conditions for both the Tx and receiver (Rx). At the Tx side, the feed antenna directs the beam toward the RIS, ensuring that at least one reflected ray from the center of the RIS reaches the Rx. The Rx captures the reflected rays arriving from the direction of the RIS. The statistical properties of the channel model for RIS-based beamforming in indoor scenarios are analyzed including path loss, delay power spectral density (PSD), and angular PSD. The statistical properties of the proposed channel model can well matched the channel measurements.

The Industrial Internet of Things (IIoT) is a promising scenario for Industry 4.0, where the existence of rich scatterers can affect the quality of communication in the factory. In this paper, we investigate the multiple base stations (BSs) deployment problem based on the ray tracing (RT) method in IIoT scenarios considering coverage. We simplify the construction of IIoT scenarios by considering the geometric and channel characteristics to improve computational efficiency in RT simulation. Then, the BS deployment problem is formulated subject to the path loss and energy efficiency. The particle swarm optimization (PSO) algorithm with the surrogate model from RT simulation is proposed to solve the formulated problem. Moreover, the surrogate model is used to replace the all-time RT simulation in the PSO algorithm. The simulation results demonstrate that the proposed method effectively addresses BS deployment challenges in IIoT scenarios.

In the field of synthetic aperture radar automatic target recognition (SAR ATR), inherent distributional discrepancies between electromagnetic synthetic and measured SAR images pose significant challenges to the potential applications of the former. To bridge the gap, a novel unsupervised domain adaptation framework based on Multi-modal Feature fusion and global-local Joint Alignment (MFJA) is proposed in this article. The multi-modal feature fusion focuses on describing each target more comprehensively by leveraging both visual and scattering topological information. In the visual branch, the full-aperture image is decomposed into multiple sub-aperture images to explore the scattering variations of the target at different azimuths, facilitating a richer visual description. Meanwhile, both local scattering and spatial position information of keypoints are simultaneously integrated into the feature extraction in the scattering topological branch, promoting a more comprehensive scattering topological representation. Subsequently, a gated feature fusion module is developed to effectively fuse features derived from different modalities. The global-local joint alignment aims to align different domains with greater precision. Specifically, a power normalized weighted gradient reversal layer is proposed to guide the network to focus more on hard-to-align samples during global domain alignment, thus mitigating their interference with local domain alignment. While MFJA achieves satisfactory cross-domain recognition performance, its inference efficiency is somewhat constrained. Therefore, a domain-invariant cross-modal knowledge distillation (DCKD) algorithm with a tri-path collaborative alignment strategy is further developed to distill discriminative and domain-invariant knowledge from the multi-modal model into a compact visual model based on full-aperture images, thereby accelerating inference. Experiments conducted in three scenarios on the public Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset validate the effectiveness of both MFJA and DCKD.

Base station (BS) deployment is not a one-time endeavor, as when transitioning to higher frequency bands, coverage holes may arise, and the initial deployment may be unsatisfactory. In such cases, the deployment of additional BSs may be necessary. In this paper, we formulate an optimization problem to deploy additional BSs, attempting to minimize overlap coverage rate while satisfying the limitations of coverage rate and spectral efficiency. An improved genetic algorithm is adopted to solve the optimization problem. Numerical results show that the improved genetic algorithm can effectively minimize the overlap coverage rate and outperforms the original genetic algorithm and the particle swarm optimization (PSO) algorithm in terms of the minimum overlap coverage, spectral efficiency, the number additional BSs, and the convergence speed.

Ray tracing (RT) is an effective deterministic channel modeling method, but the computational burden for dynamic scenarios is high. To address this issue, this study categorizes objects involved in various types of motion within dynamic scenarios based on their motion characteristics, distinguishing between static and dynamic objects. Subsequently, the subinterval of the optimal split plane suitable for bounding volume hierarchies (BVH) construction is calculated, and the simplified interval BVH algorithm (SIBVH) is applied to the vehicle-to-vehicle (V2V) communication scenario. The simulation results indicate that, SIBVH based RT algorithm can trace rays much faster than traditional RT method, and improve computational efficiency significantly. The proposed algorithm can be effectively used in complex high-mobility communication scenarios.

Recently, deep convolutional neural networks have been widely applied in target detection of synthetic aperture radar (SAR) images. However, the regular convolution kernel cannot effectively establish dependency between features of SAR image with geometric distortion. Meanwhile, SAR images contain a small number of vehicle targets, and the imbalance problem between foreground-background class is serious during training. To solve these problems, we propose a you only look once (YOLO) detector based on graph convolutional network (GCN) called GCN-YOLO. First, a multilayer GCN model called vision GNN (ViG) is used as feature extractor to model the local area and build long-term dependencies between features. In addition, a convolutional block attention module (CBAM) is embedded into the last layer to enhance semantic features. Then, we introduce the VariFocal loss (VFL) as confidence loss to relief the imbalance problem between positive and negative samples. The experimental results on the miniSAR data demonstrate the effectiveness of the proposed method.

Recently, metric-based meta-learning has been widely adopted to solve few-shot synthetic aperture radar (SAR) target classification, where the global features are employed to measure the similarity of each sample and the class prototypes. However, due to the high inter-class similarity of SAR images, the global features may suppress the detailed information in local features beneficial for SAR target classification. Besides, the prototypes obtained from a few SAR support samples at sparse azimuth angles tend to be biased. To tackle the above problems, we first integrate a local feature classification module into meta-learning and propose a multi-scale local classification network (MLC-Net) to enhance the target’s critical local detail features. Then, the feature generation and calibration network (FGC-Net) is proposed to generate SAR support features at the full range of azimuth angles to compensate for the real support features extracted by MLC-Net. Specifically, FGC-Net consists of a feature generative adversarial network (FGAN) and an adaptive feature calibration module (AFCM). FGAN is designed to generate support features for each class under the full range of azimuth angles. AFCM is proposed to calibrate the generated support features by adaptively re-weighting the generated and real support features of the same class. Finally, we devise the prototype mean square error (PMSE) loss and the central constraint (CC) loss to further narrow the distribution margin between the generated and real support features. FGC-Net and MLC-Net are unified for end-to-end training, resulting in consistent performance gains in feature generation and few-shot classification. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset under different few-shot settings demonstrate the effectiveness of our proposed method.

Image registration is the basis for joint utilization of multisource scene information. However, accurate automatic registration of multisource remote sensing images remains a challenging task, especially for optical and synthetic aperture radar (SAR) images. Due to the large geometric and intensity differences between images, many algorithms often fail to accurately register or even mismatch. In this article, we propose a novel coarse-to-fine method with stable high accuracy, which mainly consists of three steps. First, extract consistent features for robust coarse registration. Considering the differences in local gradient magnitudes between optical and SAR images, image intensity preprocessing is performed. Meanwhile, instead of the simple calculations via horizontal and vertical gradient operators, multidirectional gradient operators are defined in two scale spaces to obtain consistent local gradient information. Via multidirectional consistent gradients, highly repeatable keypoints are detected. On the multidirectional gradient maps, support regions with multiple scales are utilized to construct multiscale and multidirectional consistent cross-modal feature descriptors. Second, match the extracted features. Aiming to obtain a reliable alignment in coarse registration step, novel strategies are implemented for the first matching of a cascaded feature matching method. Sufficiently reliable initial matches are established via a new two-way matching strategy, and obvious outliers are removed by exploring the consistencies of both spatial scale and local neighborhood elements of the correct matches. Third, form distinctive pixelwise feature representations for accurate fine registration. In order to increase the distinctiveness of features to distinguish adjacent pixels, a new filter bank based on small receptive fields is defined. Fine features are constructed, appearing as thinner structures at the edges. Meanwhile, through multiscale and multidirectional convolutions, sufficient neighborhood information is mined. Therefore, more precise correspondences can be found to fine-tune the roughly corrected image pair. Overall, a combination method is proposed with a feature-based method and an area-based method for coarse registration and fine registration, respectively. On simulated and real image pairs, the above three steps and the two-stage framework are verified. Experimental results show that the proposed optical-to-SAR image registration method based on the designed multiscale, multidirectional consistent feature and multiscale, multidirectional fine feature (M2F2M) is superior to the current representative feature-based and area-based methods in robustness and accuracy.

Radar jamming signal identification at low JNR and with limited training data are both open problems. Though multiple studies were performed previously, there still existed two problems needed to be solved. On the one hand, it is difficult to obtain discriminative presentations from the radar jamming signal that are accompanied with the solid Gaussian White Noise (GWN). On the other hand, the available data for training is difficult to obyain from the actual complex noise environment. To solve these problems, we propose a novel siamese network architecture with self attention named SA-Siam for Radar jamming signal classification. Firstly, transforming the jamming signal to the time-frequency (TF) domain where can represent higher dimensional information. Then the intra-class aggregation and inter-class separability of radar jamming signals are enhanced through the siamese network which is beneficial to learn more discriminative features from TF image especially in the case of limited data. In addition, the self attention block (SA) can further capture spatial correlations of the TF image so as to improve the anti-noise performance of the siamese network. We conducted quantitative and qualitative experiments on own dataset with a set of Deep CNNs and classical siamese algorithms. The results verify that our proposed SA-Siam can fully explore the representation of noised jamming data and dramatically improve the radar jamming classification performance under limited training data.

With the improvement of hardware performance, graphics processing unit (GPU) has been applied to the acceleration of ray tracing (RT) wireless channel modeling. In this paper, a new RT acceleration algorithm based on message passing interface (MPI) and GPU called MPI fused with GPU tree algorithm (MGTree) is proposed. Moreover, the indoor conference room is modeled, and the forward algorithm shooting and bouncing ray (SBR) is used for RT. Considering the conventional reflection and diffraction, the three-dimensional (3D) RT acceleration algorithm based on the unified computing device architecture (CUDA) is used to optimize the conventional algorithm, which combines GPU with MPI to form multi-core distributed computing. Then field information is extracted at the receiving side and the wireless channel simulations are conducted. Through experiments, the new algorithm can effectively improve the upper limit of the acceleration ratio, support more rays, and alleviate the pressure of a single GPU kernel.

The performance of the polarimetric notch filter (PNF) algorithm based on the orthogonal projection technique has been widely recognized in the field of polarimetric synthetic aperture radar (PolSAR) ship detection. However, for detection problems in non-orthogonal target subspace and clutter subspace, using the orthogonal projection technique results in detection performance loss. In this letter, we propose a new ship target detector based on the oblique projection technique to deal with the condition that the target subspace and the clutter subspace are non-orthogonal. Since most sea clutter is inconspicuous in low-to-medium sea conditions, it is time-consuming to apply a fine target detector over the entire scene. Therefore, this letter proposes a keypoint detector based on the noncircularity and polarimetric scattering information to achieve fast localization of potential target regions. In general, we propose a novel two-step ship detection method for PolSAR data. The first step is to use the keypoint detector for potential target region localization, and the second step is to use the oblique projection detector to perform fine target detection on the potential target regions. Experiments on the synthetic and measured PolSAR data demonstrate that the proposed method is effective for ship detection.

Reconstructing an$s$-sparse signal${\boldsymbol{x}}$from an underdetermined noisy linear model arises in many applications. The iterative hard thresholding (IHT) and hard thresholding pursuit (HTP) algorithms are two popular sparse signal recovery algorithms. Since their recovery performances can be theoretically characterized by their sufficient conditions of stable sparse signal recovery, it is essential to establish less restrictive sufficient conditions. This work develops$\delta _{\text{2}s}$-based sufficient conditions for stable recovery with IHT and HTP. The two new sufficient conditions are significantly less restrictive than the state-of-the-art ones for IHT and HTP.

In recent years, how to accurately identify targets from measured synthetic aperture radar (SAR) images according to electromagnetic synthetic SAR images is attracting more and more research interest. Most existing algorithms only focus on decreasing the domain differences in visual representations, while the special characteristics of SAR images are not explored enough. Besides, these algorithms tend to align only the overall distribution of synthetic and measured images, while domain shifts between subclasses are ignored. To solve these problems, a novel unsupervised domain adaptation framework named visual and scattering topological feature fusion and alignment network (VSFA) is proposed in this article. First, considering that visual features are crucial for recognition, image reconstruction is introduced to enhance the generalization of visual features. Second, by analyzing the imaging mechanism of SAR, we explore the differences in scattering topologies between synthetic and measured images for the first time. To measure the differences quantitatively, we model the non-Euclidean scattering topology of the target as graph data and introduce graph neural networks (GNNs) to extract scattering topological features. Moreover, in order to describe the scattering topology of the target more comprehensively, we introduce two different but complementary scattering topological point extraction algorithms and achieve their fusion at the feature level by GNN for the first time. Finally, a simple but effective two-stage domain adaptation loss is proposed to constrain the network to align the distribution of synthetic and measured images class by class. Benefiting from the simultaneous reduction of distribution differences in visual space and scattering topological space, the proposed method achieves 99.15% and 98.18% recognition accuracies in two typical experiment scenarios of the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset, demonstrating its effectiveness.

Industrial Internet of things (IIoT) is a typical application scenario in the sixth generation (6G) mobile networks. IIoT scenarios involve dense multipath components (MPCs) and nonnegligible scattering components caused by many moving objects. In this paper, image method (IM) is applied and extended to analyze the channel properties of IIoT. Directive model is modified to adapt to IM. The moving patterns of objects are defined and their snapshots are established along the time axis. Multiple-input multiple-output (MIMO) is supported as it is widely applied in IIoT. A smart warehouse scenario equipped with moving handcars is selected to analyze the channel of IIoT scenario. Parameters such as azimuth angle, elevation angle, angular spread, power, and delay spread of received rays are calculated and compared with those generated by quasi-deterministic (Q-D) model traditionally used in IM. Maximum and minimum Doppler shifts, received power, and delay spread are calculated along the time axis to analyze the influence of mobility to channel properties. The results show that directive model generates scattering components more realistically compared with Q-D model, and that the channel properties may experience sudden changes due to the line-of-sight (LoS) component being obstructed.

Terahertz (THz) communication and the application of massive multiple-input multiple-output (MIMO) technology are significant for the sixth generation (6G) communication systems. In this paper, we employ the shooting and bouncing ray (SBR) method integrated with GPU acceleration technology to model THz and massive MIMO channel. The results of ray tracing (RT) simulation in this paper, i.e., angle of departure (AoD), angle of arrival (AoA), and power delay profile (PDP) under the frequency band supported by the commercial RT software Wireless Insite (WI) are in agreement with those produced by WI. Based on the Kirchhoff scattering effect on material surfaces and atmospheric absorption loss showing at THz frequency band, the modified propagation models of Fresnel reflection coefficients and free-space attenuation are consistent with the measured results. For massive MIMO, the channel capacity and the stochastic power distribution are analyzed. The results indicate the applicability of SBR method for building deterministic models of THz and massive MIMO channels with extensive functions and acceptable accuracy.

Ray tracing is an efficient channel modeling method. However, the traditional ray tracing method has high computation complexity. To solve this problem, an improved bounding volume hierarchies (BVH) algorithm is proposed in this paper. Based on surface area heuristic (SAH) and spatial distance, the proposed algorithm can effectively reduce the number of unnecessary intersection tests between ray and triangular facets. In addition, the algorithm fully considers the influence of ray action range, which can not only make up for the defects of spatial division based on uniform grid method and k-dimensional (KD) tree, but also solve the problem of unsatisfactory spatial division based on traditional BVH algorithm. The simulation results show that compared with the traditional BVH algorithm, the proposed algorithm can improve the computation efficiency by 20% to 35% while ensuring the computation accuracy.

Due to the indoor none-line-of-sight (NLoS) propagation and multi-access interference (MAI), it is a great challenge to achieve centimeter-level positioning accuracy in indoor scenarios. However, the sixth generation (6G) wireless communications provide a good opportunity for the centimeter-level positioning. In 6G, the millimeter wave (mmWave) and terahertz (THz) communications have ultra-broad bandwidth so that the channel state information (CSI) will have a high resolution. In this paper, a weighted random forest (WRF) based indoor positioning algorithm using CSI-based channel fingerprint feature is proposed to achieve high-precision positioning for 6G indoor communications. In addition, ray-tracing (RT) is used to improve the efficiency of establishing channel fingerprint database. The simulation results demonstrate the accuracy and robustness of the proposed algorithm. It is shown that the positioning accuracy of the algorithm is stable within 6 cm in different indoor scenarios when the channel fingerprint database is established at 0.2 m intervals.

Compared with image method (IM) based ray tracing (RT), shooting and bouncing ray (SBR) method is characterized by fast speed but low accuracy. In this paper, an iterative precise algorithm based on equiangular division is proposed to make rough paths accurate, allowing SBR to calculate exact channel information. Different ray launching methods are compared to obtain a better launching method. By using equiangular division, rays are launched more uniformly from transmitter (Tx) compared with the current equidistant division method. With the proposed iterative precise algorithm, error of angle of departure (AOD) and angle of arrival (AOA) is below 0.01 degrees. The relationship between the number of iterations and error reduction is also given. It is illustrated that the proposed method has the same accuracy as IM by comparing the power delay profile (PDP) and angle distribution of paths. This can solve the problem of low accuracy brought by SBR.

Ship classification from synthetic aperture radar (SAR) images tends to be a hotspot in the remote sensing community. Currently, more efforts have been made to the single-polarization (single-pol) SAR ship classification with limited performance. This letter proposes to explore the dual-polarization (dual-pol) SAR images for better ship classification. To be specific, a novel group bilinear convolutional neural network (GBCNN) model is developed to deeply extract discriminative second-order representations of ship targets from the pairwise VH and VV polarization SAR images. Particularly, the deep bilinear features are efficiently acquired by performing the bilinear pooling on sub-groups of deep feature maps derived, respectively, from the single-pol SAR images (self-bilinear pooling) and dual-pol SAR images (cross-bilinear pooling). To fully explore the polarization information, the multi-polarization fusion loss (MPFL) is constructed to train the proposed model for superior SAR ship representation learning. By extensive experiments, the proposed method can achieve an overall accuracy of 88.80% and 66.90% on the 3- and 5-category dual-pol OpenSARShip data sets, which outperform the state-of-the-art methods by at least 2.00% and 2.37%, respectively.

Recently, deep neural network has achieved enormous success on target detection but how to better apply these methods to synthetic aperture radar (SAR) images is still a challenge due to the following two reasons: the characteristics of SAR images are not utilized sufficiently; SAR images contain a smaller number of targets, and thus detectors face more serious foreground-background class imbalance problem during training. In this paper, we propose a constant false alarm rate (CFAR) guided dual stream single shot multibox detector to solve the above problems. Firstly, based on the proposed dual sub-networks and the interactive channel-spatial attention fusion (ICSAF) module, we effectively utilize the strong scattering characteristic of SAR target to improve the feature extraction ability. Then we integrate the CFAR indicative map into focal loss to alleviate the foreground-background class imbalance problem. In addition, a non-maximum suppression method based on area-ratio (AR-NMS) is proposed for problem caused by dividing large scene SAR image into blocks. The whole framework can realize end-to-end joint training, and the experimental results on miniSAR real data demonstrate the effectiveness of the proposed method.

Although several algorithms have achieved automatic registration on optical and synthetic aperture radar (SAR) images, it is still a challenge to establish enough reliable correspondences between such images due to their different imaging mechanisms. For this purpose, we propose a robust point-feature-based registration method. Considering the inherent properties of optical image and SAR image, two different gradient operators are utilized to construct scale spaces and extract features. A new gradient operator is defined for SAR image, yielding a more consistent gradient with optical image gradient calculated by the multiscale Sobel operator. Then, a novel cascaded matching method called cascaded sample consensus (CSC) is put forward to increase the number of correct correspondences. In the first matching, a simple but effective scale constraint strategy is used to remove outliers for a robust initial transformation model. Considering the spatial location relationship in each correct matching pair, the second matching constructs precise search spaces of the best matching points for more correspondences. Experimental results finally verify the robustness and accuracy of the proposed algorithm.

Due to the difficulties of obtaining sufficient real synthetic aperture radar (SAR) images, introducing simulated images can effectively enrich the training dataset in SAR target recognition. This letter explores how to accurately identify the targets in real SAR images by only using simulated training images. The key challenge is that there are distribution differences between the simulated (training) and real (test) data, which limits the performance of recognition methods. To solve this problem, a hierarchical recognition method is proposed. A well-trained convolutional neural network (CNN) is first utilized to pre-classify all the test images. Then, the focus of our proposed method is to find the hard test samples that are easy to be misclassified according to the CNN classification confidence and re-classify them. In fact, the distribution of these samples is relatively inconsistent with the distribution of the training data. Thus, we propose a multi-similarity fusion (MSF) classifier to re-classify them by comprehensively measuring the correlation between the hard samples and the training images through five similarity measures. During the fusion process, the bagging ensemble technique is used and the similarity measures are sampled to generate different subsets to enhance the diversity of sub-classifiers, thus the performance is improved. A large number of experiments finally verify the robustness and accuracy of the proposed method.

Thanks to the medium-to-high resolution and wide coverage imaging ability, satellite synthetic aperture radar (SAR) systems are momentously developed for intelligent maritime surveillance, especially for ship classification in SAR images. Previous researchers mostly utilized the geometric, radiometric, and structural features combined with the traditional machine-learning (ML) methods to conduct ship classification in high-resolution (HR) SAR images. However, the handcrafted features showed weak representation for the medium-resolution (MR) SAR images, and the normal ML methods are less powerful to deal with the intraclass diversity and interclass similarity in the MR SAR ship images. To address these issues, this article extends the dense convolutional networks to the MR SAR ship classification for better deep features extraction and proposes a multitask learning framework within which the softmax log-loss and the triplet loss are jointly minimized for more effective ship classification in MR SAR images. The triplet loss is computed by imposing a similarity constraint on the deep embeddings via the deep metric learning (DML) scheme such that the deep representations of the same class are pulled much closer to each other and those from different classes are pushed as farther apart as possible. However, the triplet loss in the usual DML utilizes the triplets mined in a training batch independently, which ignores the contextual information. So, we propose to impose a Fisher discrimination regularization term on the deep embeddings to explore the global information of learned embeddings, and hence the designed task-specific networks will be trained to have more robust and better recognition performance. Extensive experiments on the MR SAR ship data set collected from the Sentinel-1 SAR images demonstrate that the proposed method can achieve superior performance for the 3- and 5-class recognition tasks with regard to the comparing CNN models.

Synthetic aperture radar (SAR) images are especially susceptible to the target aspect angles. For the SAR target recognition, the lack of training data at different aspect angles inevitably deteriorates the performance. To solve the problem, this letter introduces an angular rotation generative network (ARGN). It is actually an attribute-guided transfer learning method, and the shared attribute between the source and target domains is the target aspect angle. The aspect angle of the data for each type in the source domain covers in the range of 0°-360°, while the information of the aspect angle in the target domain is not complete. Assume that there is a mapping in the feature space between the two images of the same target under different aspect angles, and the mapping relation is learned from sufficient data in the source domain. Then, the mapping can also be applied in the target domain according to the idea of transfer learning. The learned knowledge contained in the feature space helps to improve the target recognition performance in the target domain. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) benchmark data set illustrate that our framework is efficient. For the three-class recognition of the MSTAR data set, the recognition rate is about 87% even when only 23 samples of each class are utilized as the training data. For a given target data, the generation results with counterclockwise rotation of 1°-90° for the aspect angle are performed. The qualitative and quantitative comparisons between the generated images and the real data are also displayed.

To detect ships robustly and automatically in monitoring the marine areas, polarimetric synthetic aperture radar imagery is more and more important. In this letter, three superpixel-level dissimilarity measures are developed to enhance the contrast between ship targets and sea clutter, which are then used to construct an automatic detection algorithm. In the proposed method, multiscale superpixels are first generated. Second, the measurements between a certain superpixel and surrounding ones are calculated. The dissimilarity measures are then transformed from the superpixel level to the pixel level. Third, kernel Fisher discriminant analysis is utilized to improve the separability between ship targets and clutter. Finally, linear support vector machine classifier is utilized to complete the detection automatically. Experiments on the synthetic and real data demonstrate that the proposed method is effective for ship detection with only few false alarms existing, especially under the low signal-to-clutter ratio.

In this letter, the local scattering mechanism difference based on regression kernel (LSMDRK) is developed as a discriminative feature for ship detection. The LSMDRK measures the scattering mechanism dissimilarity of a center pixel to its neighboring pixels. A ship detection scheme is proposed based on the LSMDRK. The detection scheme consists of two stages. In the feature extraction stage, polarimetric target decomposition is required to improve the discriminative ability of the descriptor. In the detection stage, a saliency detection strategy is utilized to construct the saliency map. Then, local maximum detection is employed. Finally, an adaptive threshold method is designed to achieve the final detection. The effectiveness of the detection scheme is validated by a RADARSAT-2 data set. Experimental results demonstrate that the proposed method can acquire a better detection on weak targets and has much less false alarms than some classical detection methods.

To improve the synthetic aperture radar (SAR) target discrimination performance under complex scenes, this letter presents a new SAR target discrimination method based on the bag-of-words model. The method contains three main stages. In the local feature extraction stage, the SAR-SIFT feature is extracted. In the feature coding stage, we improve the existing category-specific and shared dictionary learning (CSDL) and propose the sample-reweighted CSDL (SR-CSDL). The local features are sparsely coded using the codebook learned from SR-CSDL. In the feature pooling stage, spatial pyramid matching with max pooling is used to aggregate the local coding coefficients to generate the global feature for each chip image. Experimental results using the miniSAR data verify the effectiveness of the proposed method.

Target discrimination has been one of the hottest issues in the interpretation of synthetic aperture radar (SAR) images. However, the presence of speckle noise and the absence of robust features make SAR discrimination difficult to deal with. Recently, convolutional neural network has obtained state-of-the-art results in pattern recognition. In this letter, we propose a target discrimination framework that jointly uses intensity and edge information of SAR images. This framework contains three parts, namely, feature extraction block, feature fusion block, and final classification block. In addition, a novel feature fusion method that can preserve the spatial relationship of different features is introduced. Experimental results on the miniSAR data demonstrate the effectiveness of our method.

In this paper, we propose a new discriminative non-linear dictionary learning approach, called correlation constrained structured kernel KSVD, for object recognition. The objective function for dictionary learning contains a reconstructive term and a discriminative term. In the reconstructive term, signals are implicitly non-linearly mapped into a space, where a structured kernel dictionary, each sub-dictionary of which lies in the span of the mapped signals from the corresponding class, is established. In the discriminative term, by analyzing the classification mechanism, the correlation constraint is proposed in kernel form, constraining the correlations between different discriminative codes, and restricting the coefficient vectors to be transformed into a feature space, where the features are highly correlated inner-class and nearly independent between-classes. The objective function is optimized by the proposed structured kernel KSVD. During the classification stage, the specific form of the discriminative feature is needless to be known, while the inner product of the discriminative feature with kernel matrix embedded is available, and is suitable for a linear SVM classifier. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art dictionary learning approaches for face, scene, and synthetic aperture radar vehicle target recognition.

In this letter, we propose a novel automatic target recognition (ATR) method based on dictionary learning and joint dynamic sparse representation (DL-JDSR) for synthetic aperture radar (SAR) images. First, in the feature extraction step, we extract two kinds of features, i.e., the image domain amplitude feature and the scale-invariant feature transform (SIFT) feature, of which the image domain amplitude feature describes intensity information and the SIFT feature describes gradient information. These two features will be jointly utilized to combine the two kinds of information for SAR ATR. Second, we introduce the dictionary-learning method, the label-consistent K-singular value decomposition, into the training step to learn dictionaries for the two features rather than directly using all training samples as the fixed dictionaries in the traditional sparse representation method. The learned dictionaries have smaller sizes and are more distinctive among different classes, which can speed up our recognition and improve the accuracies. Third, the JDSR algorithm used in the test step employs a more flexible atom selection method, which enables the two features from an image data to share the similar but not exactly the same sparse mode. Experiments on the moving and stationary target acquisition and recognition data set show that the proposed method is an effective way to recognize SAR images.

In this letter, a new superpixel-based constant-false-alarm-rate (CFAR) target detection algorithm for high-resolution synthetic aperture radar (SAR) images is proposed. The detection algorithm consists of three stages, i.e., segmentation, detection, and clustering. In the segmentation stage, a superpixel-generating algorithm is utilized to segment the SAR image. In the detection stage, based on the superpixels generated, the clutter distribution parameters for each pixel can be adaptively estimated, even in the multitarget situations. Then, the two-parameter CFAR test statistic can be adopted for detection. In the clustering stage, the hierarchical clustering is used to cluster the detected superpixels to get the candidate targets. The effectiveness of the proposed algorithm is demonstrated using the miniSAR data.

To improve the target detection performance under a low signal-to-clutter ratio, this letter presents a new polarimetric synthetic aperture radar (PolSAR) ship detector based on superpixel-level scattering mechanism (SM) distribution features. The proposed method is based on the observation that the SMs of targets and clutter have different distributions in the classical H/α plane. To make use of this difference in ship detection, multiscale superpixels are first generated for PolSAR images. Then, two features describing the SM distribution in the superpixel are proposed. Based on these features, a test statistic independent of the scattering intensity is finally defined. The performance improvement of the proposed method is verified using a synthetic data set and real PolSAR images obtained from a RADARSAT-2 data set.

This paper presents a new model-based decomposition method for the polarimetric synthetic aperture radar coherency matrices. We improve the model flexibility from the following two aspects: To reach a compromise between model flexibility and computation complexity, for the volume scattering component, the elementary scatterer shape is allowed to change from sphere/flat plate to dipole, then to dihedral, whereas orientation randomness is simplified by only considering two cases. Different orientation angles are considered for each component. Since the models become more complex, new decomposition procedures are developed. The three-component decomposition is first reformulated as a constrained sparse representation problem. Then, inspired by the orthogonal matching pursuit variant developed by Bruckstein et al. in 2008, new decomposition procedures are designed. The effectiveness of the proposed method is verified using a synthetic data set and two real SAR data sets, including a RADARSAT-2 data set and the NASA/JPL AIRSAR data set over San Francisco Bay.

This paper presents a new hierarchical scheme for detecting ships from high-resolution synthetic aperture radar (SAR) images. The scheme consists of two stages: detection and discrimination. In the detection stage, the existing internal Hermitian product is extended to obtain a new detector. The new detector makes a combined use of the complex coherence among more than two subapertures and the intensity of each subaperture. When the subaperture number is increased, the target/clutter contrast is shown to be improved. Ship candidates are obtained by applying a threshold. Ship discrimination is performed by using one-class classification. The covariance descriptor, developed by Tuzel in 2006, is introduced to SAR ship discrimination as the feature. The traditional one-class quadratic discriminator is used as the discriminator. After this stage, most false alarms are rejected, and the real ship targets in the candidates are maintained. The effectiveness of the proposed scheme is verified using RADARSAT-2 data. Experimental results show that the proposed scheme can detect most ship targets in the image and few false alarms occur.

We present a new segmentation method for the fully polarimetric synthetic aperture radar (PolSAR) data by coupling the cluster analysis in the tensor space and the Markov random field (MRF) framework. The PolSAR data are usually obtained as a set of 3 × 3 Hermitian positive definite polarimetric covariance matrices, which do not form a Euclidean space. If we regard each matrix as a tensor, the PolSAR data space can be represented as a Riemannian manifold. First, the mean shift algorithm is extended to the manifold to cluster such tensors. Then, under the MRF framework, the data energy term is defined by the memberships of all tensors in all the clusters, and the smoothness energy term is defined according to the cluster overlap rates. These parameters regarding the cluster analysis are computed under the Riemannian framework. The total energy is minimized using a graph-cut-based optimization to achieve the segmentation results. The effectiveness of the proposed method is verified using real fully PolSAR data and synthetic images.

We propose a three step method to extract buildings from the high-resolution PolSAR data, using both the region-based and edge-based information. Firstly, low-level detectors are employed to provide raw region and edge information of the scene. In the second step, improved region-based building detection results are achieved by fusion of label fields, meanwhile the building profile line segments are extracted under a line Markov random field framework. The last step gives the final building footprint estimates: initial rectangle buildings are defined from the building line segments; by optimizing a surface criterion, the final rectangles are retrieved to fit the region-based building detection results. The effectiveness of this method is demonstrated using the real full PolSAR data.