A spontaneous electroencephalogram (EEG)-based brain-computer interface (BCI) is an ideal form of brain-computer interaction. The classical decoding methods can achieve classification by using meaningful manual features, but their performance is poor. The neural network (NN) methods have significantly improved the performance, but their interpretability and computational efficiency are much lower than those of the classical methods. This is because NN abandons the strong a priori knowledge of neuroscience and completely relies on training to extract EEG features. How to integrate the characteristics of neural signals into the design of the basic operator of the NNs while retaining its learning ability is the focus of this work. In this work, we proposed a function predefined convolutional NN (FPCNN) to search for the best frequency points and channel weights to decode spontaneous EEG signals. Among the FPCNN, a novel function predefined convolutional (FPC) layer adopts a learnable way to search for the key spatial-frequency parameters of spontaneous EEG, making its parameters have clear physical meanings. Furthermore, a trainable quadrature detector (TQD) based on FPC was constructed, and the quadrature characteristic was utilized to ensure the capture of complex phase change signals. The core contribution of our method lies in the proposal of a novel NN operator for decoding spontaneous EEG, and a quadrature scheme for handling the phase changes of signals. The experimental results show that the proposed FPCNN significantly improves the performance by 2.09% ( ${}^{\ast } $ ), 3.08% ( ${}^{\ast } $ ), and 3.41% ( ${}^{\ast \ast }$ ), respectively, compared with the state-of-the-art (SOTA) methods on three spontaneous EEG datasets. Moreover, the training and testing time cost of FPCNN in a non-GPU environment only takes 67.96 and 19.36 s per epoch. Its savings in computing resources and time are very beneficial for EEG processing in diverse environments. In addition, visualization experiments demonstrated the interpretability and stability of the proposed FPCNN. The experimental results show that our method is efficient, stable, and interpretable. This work has effectively improved the decoding efficiency of spontaneous EEG signals and demonstrated the power of combining traditional signal processing methods with NNs.

In the hyperspectral image (HSI) classification, convolutional neural networks (CNNs)-based approaches often struggle with the scarcity of labeled samples. The letter proposes an HSI classification method based on data expansion and consistency regularization with small samples. Specifically, we leverage the pixel-pair feature (PPF) to expand the dataset, which facilitates the adequate tuning of CNN parameters and alleviates the issue of overfitting. In addition, a designed CNN structure is employed to extract discriminative features from the limited number of labeled PPFs and numerous unlabeled PPFs. The CNN is trained via minimizing the weighted sum of supervised and unsupervised losses, where the supervised loss is calculated through the cross-entropy function while the unsupervised loss is evaluated with the consistency regularization item. Moreover, reliable references required in the consistency regularization item are provided after making an exponential moving average (EMA) on the outputs of CNNs at different training epochs. Ultimately, we conduct experiments on three real HSI datasets, and the results show that the proposed approach gains superior classification accuracy compared to several existing CNN-based approaches.

In view of the practical value of open datasets of hyperspectral images (HSIs), HSI open-set classification (OSC) has attracted more and more attention. Existing HSI OSC methods are usually based on learning labeled samples to identify unknown classes. However, due to the complex high-dimensional characteristics of HSIs and the limited number of labeled samples, the recognition of unknown classes based only on limited labeled samples often has low and unstable accuracy. To address this problem, we propose a semi-supervised graph constraint dual classifier network (SSGCDCN) that can achieve efficient and stable OSC by learning unknown class features and relationships among samples. First, a dual classifier consisting of a multi-classifier and multiple binary classifiers is constructed, which has the ability to discover the unknown class samples by assigning and enabling pseudo-labels to participate in model training to achieve unknown class feature learning. Then, to improve the classification accuracy of both known and unknown classes, a homogeneous graph constraint is imposed on SSGCDCN to learn the relationship information among samples (including labeled and unlabeled samples). This constraint can bring the features of similar samples closer while pushing apart features of dissimilar samples. Experiments evaluated on three datasets demonstrate that the proposed method can obtain superior OSC performance than other state-of-the-art classification methods.

Hyperspectral image open-set classification has gained increasing attention due to its practical significance. However, existing approaches face two major challenges: (1) poor and unstable classification performance under limited labeled samples, and (2) the lack of end-to-end open-set classification frameworks. To address these issues, we propose an Incremental Multi-Task Contrastive Learning Network (IMTCLN), which integrates four learning tasks to achieve end-to-end open-set classification under few-shot conditions through feature sharing and multi-task collaboration. First, we introduce an expanded class labeling method in the model’s output layer, enabling end-to-end open-set classification. Second, among the four learning tasks, the supervised classification task learns the mapping between known-class samples and their labels using limited labeled data. To enhance classification performance under few-shot conditions, we design a semi-supervised Euclidean contrastive learning task, which improves intra-class compactness and inter-class separability by modeling homogeneous and heterogeneous sample relationships. Additionally, for effective unknown-class recognition, we propose a supervised Mahalanobis contrastive learning task, optimizing the Mahalanobis distance among known classes to identify unknown-class samples. Finally, to further enhance classification stability, we introduce an incremental learning task, which leverages pseudo-labeled unknown-class samples to learn their discriminative features, enabling robust discrimination between known and unknown classes. Extensive experiments on three public datasets demonstrate that IMTCLN significantly outperforms existing methods, particularly under extremely limited labeled samples, showcasing superior open-set classification performance and stability.

Infrared small-target detection (ISTD) in a single frame is an essential, yet challenging task due to its small size of targets, weak energy, and clutter background. Current methods either design complex network architectures to facilitate multilevel information interaction (e.g., DNA-Net and UIU-Net) or introduce structural texture priors to enhance feature discrimination (e.g., SRNet and CSRNet). However, both methods fail to explicitly distinguish or suppress the interference of complex background from infrared small targets, which makes them easy to “get lost” in clutter background with insufficient attention to the targets. In this work, we innovatively propose a novel background-masking approach (denoted as BGM) for ISTD. The proposed BGM aims to force the network to focus exclusively on the target by masking out irrelevant background information, thereby enhancing the network’s ability to detect weak and small infrared targets. Specifically, we present a new ISTD method that leverages a proxy training task with masking, enabling the network to simultaneously predict on both the original input and the masked data, where the background is randomly masked/forgotten. This strategy allows for a better concentration of the model on the shapeless targets rather than the cluttered background. The method is flexible with a simple U-shaped network without complicated manipulation and also computationally efficient without increasing the overall computational burden during inference. Extensive experiments demonstrate that our proposed BGM effectively enhances the detection performance of infrared small targets and achieves 70.8% mean intersection over union (mIoU) on IRSTD-1K. The source code would be available athttps://github.com/ZhihaoMa123/BGM

Time-domain modulated metasurfaces (TMMs) enable passive radar jamming by dynamically altering incident waveforms. We introduce the concept of passive barrage jamming, where a TMM redistributes target energy to suppress dominant features in the synthetic aperture radar (SAR) imaging without active radiation. Traditional approaches, such as random phase modulation, can disperse target energy but lack a principle framework for shaping the SAR response, leaving detectable residual signatures. In this work, the design of TMM modulation sequences is formulated as a non-convex minimax optimization problem to improve the energy distribution of the SAR imaging. An alternating direction method of multipliers framework is developed to solve the problem efficiently under the constant-modulus constraint, with theoretical guarantees of monotonic convergence under suitable parameter settings. In SAR simulations, the optimized TMM sequences achieve a peak reduction of 70.18 dB for a point target and 48.29 dB for an extended target compared to the unmodulated baseline, outperforming both random and structured coding schemes. Experimental validation on a practical 1-bit TMM platform confirms a 12.87 dB peak reduction in one-dimensional matched filtering, despite phase quantization and hardware nonidealities. These results highlight the effectiveness of the proposed optimization approach in enhancing TMM-based barrage jamming performance, providing a robust and practical solution for radar countermeasures.

Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment) fail to catch them simultaneously. To address the deficiency, current approaches have to adopt multi-branch models and take as input the multi-resolution data, which burdens the model complexity. In this work, instead of stacking up models, a more elegant data sampling method (named as SAMA, scaling and masking) is explored, which compacts both the local and global content in a regular input size. The basic idea is to scale the data into a pyramid first, and reduce the pyramid into a regular data dimension with a masking strategy. Benefiting from the spatial and temporal redundancy in images and videos, the processed data maintains the multi-scale characteristics with a regular input size, thus can be processed by a single-branch model. We verify the sampling method in image and video quality assessment. Experiments show that our sampling method can improve the performance of current single-branch models significantly, and achieves competitive performance to the multi-branch models without extra model complexity. The source code will be available at https://github.com/Sissuire/SAMA.

The classification performance of land features is strongly associated with the quality of samples. However, in the real world, the presence of class noise is inevitable. Class noise may seriously mislead the construction of model and limit the improvement of classifier performance. In response to this situation, a stratified mislabeled instances removal method based on the idea of density spatial clustering optimally (SD-SCM) is proposed. Herein, the convolutional neural network (CNN) is employed to evaluate the effectiveness of the proposed method.Besides, a famous noise filter, KNN-kernel Cluster based technology, is adopted to compare with SD-SCM. The results on two benchmark datasets, Indian Pines and Pavia University, demonstrate the effectiveness of the proposed noise removal method.

Existing methods for hyperspectral image classification (HSIC) typically assume a closed-set scenario, where all target types are known, and the classifier can assign only predefined classes to samples (pixels). However, in real remote sensing applications, open-set scenarios are common, where unknown classes exist. To address this problem, we propose a graph-constrained deep multi-task approach for open-set HSIC. Our method tackles the challenge of detecting unknown classes by integrating multiple-class classifiers and multiple binary classifiers. Additionally, to handle the limited labeled samples issue in HSIC, we propose utilizing homogeneous and heterogeneous graphs to constrain the two types of classifiers, thereby improving the accuracy of unknown class detection and known class classification. Experimental results on the Pavia University dataset demonstrate that our proposed method outperforms other closed-set and open-set classification methods significantly.

Infrared and visible images with distinct and complementary information are fused to obtain more comprehensive information. However, traditional fusion algorithms often suffer from losing details and low fusion quality. Convolutional neural networks (CNN) have been proven to possess excellent feature extraction capabilities. Therefore, a fusion algorithm for infrared and visible image fusion based on CNN and Multi-Scale Transform (MST) is proposed in this paper. In this fusion algorithm, a dual-branch CNN is employed to map the original images to the weight map. The low-pass and high-pass bands obtained through multi-scale transformation are fused separately by combining the weight map with different fusion strategies. In the experiment, five MST algorithms and 21 pairs of images are tested. The experimental results demonstrate that the proposed fusion algorithm significantly enhances the fusion quality of the original MST algorithms.

Nowadays, various types of foundational models have emerged, showcasing remarkable performance across a multitude of downstream tasks. However, in the domain of hyperspectral image classification (HSIC), substantial research is still required to effectively leverage the advantages of foundational models and adapt them to hyperspectral data. Consequently, we propose a HSIC algorithm based on a fixed-parameter SAM encoder. Specifically, the global feature extraction subnetwork integrates global patch information to obtain processed features. Subsequently, the semantic information extraction subnetwork is trained using cross-entropy to extract semantic features of categories, culminating in pixel-level classification. Experiments on two HSI datasets indicate that the proposed method can obtain better classification performance when compared with seven state-of-the-art methods.

In radar target recognition, anti-corner reflector interference is a critical research area. Radar cross section (RCS), commonly used radar data, serves to recognize of ship and coner reflector. However, considering the current circumstances, RCS-based ship recognition heavily relies on single-frequency multi-angle data, which limits its potential. In terms of classification methods, manual feature extraction for classification has drawbacks like subjectivity, high workload, and limited adaptability. Direct use of convolutional neural networks (CNNs) also presents limitations, including data dependency and the problem of performance upper bounds. To address these challenges, we propose a feature fusion approach for ship and corner reflector recognition using RCS under agile frequency conditions. We introduce an automatic weighting module based on channel attention mechanism for interpretable features extracted manually. These weighted interpretable features are combined with deep features from the improved Omni-Scale CNNs (OS-CNN). The experiment shows that the proposed method effectively discriminates between ships and corner reflectors and reduces reliance on observation angles during training. The overall recognition accuracy on the test set reaches 96.2%, higher than the existing methods of 3.4%~10.6%, and is robust to the fluctuation of varying sea conditions.

Interrupted-sampling and repeater jamming (ISRJ), as a novel form of active jamming, has emerged as a focal point and challenge in radar jamming countermeasures. In this letter, to enhance the suppression capability against ISRJ, we propose a recognition and suppression method based on the UNet-attention (UNet-A) semantic segmentation model. First, an attention-based direct connection structure between the encoder and decoder is designed to enhance the ability of UNet-A to identify the boundaries of jamming and the target. Then, an adaptive time-frequency (TF) filter based on the refined recognition results is designed to improve the signal-to-jamming ratio improvement factor (SJRIF). Finally, to improve the jamming suppression capability while reducing the target energy loss, an annotation method based on the target energy loss constraint criterion is proposed, and a dataset is constructed based on this. Numerical results and comparisons with the existing methods are included to demonstrate that the proposed method can effectively enhance anti-ISRJ performance.

With the increasing complexity of the electromagnetic environment and a growing number of jamming sources, radar systems are facing an unprecedented threat of compound jamming. Precision in estimating the key parameters of compound jamming is of paramount significance for developing effective anti-jamming strategies. In response to the current lack of effective solutions for estimating parameters of compound interrupted sampling and repeating jamming (ISRJ), a dualcompound ISRJ parameter estimation method is proposed, which employs Gaussian multi-peak fitting for adaptively decoupling jamming signals and leverages the inherent temporal periodicity characteristics of ISRJ for parameter matching. The proposed method fully exploits the latent information in the received signals and conducts efficient processing, while being able to adapt to various jamming scenarios. The simulation results demonstrate the effectiveness and robustness of the proposed method

High resolution range profile (HRRP) provides abundant target information but is susceptible to external electromagnetic interference. While infrared sensor possesses strong anti-jamming capability, it has limited detection range and is vulnerable to weather conditions, leading to reduced imaging resolution. The integration of radar and infrared sensors can synergize their respective strengths to not only improve the reliability and robustness of the system but also enhance the credibility and accuracy of the data. However, there exist many challenges in the research on the fusion of heterogeneous data like HRRP 1D data and infrared 2D data. In this letter, a radar infrared sensor fusion method based on hierarchical features mining (HFM) is proposed to solve the problems above. The method is applied to multi-target recognition tasks to verify the effectiveness. The results demonstrate that the proposed method can enhance the information completeness of the target and improve the accuracy of target recognition.

Nowadays, foundation models have demonstrated exceptional performance across numerous downstream tasks. However, the effective application of these models to hyperspectral image classification (HSIC) is challenged by the unique characteristics of hyperspectral data, including high dimensionality, high variability, and high spatial structure complexity. Therefore, methods need to be developed, which leverage the advantages of foundation models while addressing these challenges. First, a novel HSIC algorithm based on a frozen-parameter segment anything model (SAM) encoder, called SAGFFNet, is proposed. This framework represents the first attempt to use a frozen SAM encoder for global feature extraction and to use spectral dimension data as prompts, enabling precise global spatial-spectral feature extraction with the aid of spectral information. Second, by introducing the self-adaptive padding mechanism and the global feature extraction subnetwork (GFEsNet), the model is enabled to extract distinctive and discriminative features for each category from hyperspectral data through varying padding sizes, thereby enhancing the feature extraction and generalization capabilities of the foundation model. Subsequently, the spectral feature prompt subnetwork (SFPsNet) is designed to extract spectral feature information from samples of different classes as prompt features, assisting the framework in better understanding the global features extracted by GFEsNet. Finally, the semantic information decoder subnetwork (SIDsNet) is introduced as a semantic information decoder, achieving efficient fusion of global spatial-spectral features and spectral prompt features, which significantly improves classification performance. Experiments conducted on four hyperspectral image datasets show that the proposed method outperforms nine existing approaches in terms of classification accuracy.

The classification of hyperspectral image (HSI) has become the focus of the remote sensing field. However, limited training data, which makes the classification task face a major challenge, is inevitable in remote sensing. To eliminate the negative effects of limited labeled samples, an enhanced ensemble method named RoXGBoost, which inherently combines Rotation Forest (RoF) and eXtreme Gradient Boosting (XGBoost) is proposed in this paper. This algorithm could increase the diversity of base classifiers by random feature selection and data transformation. Five ensemble learning methods, Random Forest (RF), AdaBoost, RoF, Rotation Boost and XGBoost, are applied as comparisons. The results on two benchmark datasets, Indian Pines and Pavia University, demonstrate the effectiveness of the RoXGBoost.

An ensemble alignment subspace adaptation method is proposed in this letter for the cross-scene classification. It can settle the problem of both foreign objects in the same spectrum and different spectrums. The algorithm combines the idea of ensemble learning with the domain adaptive (DA) algorithm. Considering the sample imbalance problem of the original data (OD), the source data (SD) is obtained by multiple random sampling of OD according to certain rules and used as input. Then, geometric alignment and statistical alignment of SD and target data (TD) are performed to build a communal subspace, followed by the classification of TD. The classification labels are finally ensembled by counting the multiple classification results with retaining valid information. This technique can reduce the uncertainty and randomness of generating subspace projections. The experimental results on two real datasets show that the proposed algorithm has a terrific accuracy improvement compared with the traditional machine learning and DA methods.

In a direction-finding process, high-resolution subspace-based algorithms are the most popular ones. It is well-known that their performance of direction of arrival estimation mainly depends on the accuracy of the signal subspace. However, the traditional methods of capturing the signal subspace do not mine the information hidden in the array output in depth, which may restrict their application to some extent. In this study, we elaborate on a novel scheme to extract the signal subspace through refinement of the correlation matrix of the array output. In the developed scheme, a collection of spatial temporal correlation matrices is firstly established. Then, we define a weighting vector for the correlation matrices, and take the weighted average of the correlation matrices as the covariance matrix of the array output. It is clear that this covariance matrix is more general than the traditional covariance matrix, and the signal subspace can be optimized through adjustment of the weighting vector. In this study, we present an optimal weighting vector by adopting the particle swarm optimization. Simulation results demonstrate that the proposed approach has better performance in root mean square error compared to the existing schemes.

The accuracy of a classifier, whether it is an ensemble or not, is directly influenced by the training data used in learning. In remote sensing, training data mislabeling is inevitable and faces a major challenge. This paper proposes a versatile data cleaning which handles the mislabeling problem by exploiting the ensemble concepts for identifying, then eliminating or correcting the mislabeled training data. A powerful ensemble method, random forest, is at the core of our filter design and helps to distinguish mislabeled data from uncorrupted data more accurately. The major contribution of this work lies on the explicit use of the hypothesis margin as a decision means to identify and eliminate or correct mislabeled training data in an ensemble learning framework. Another key development that makes our algorithm superior to existing approaches is a design that avoids rare class instances to be mistaken for class noise. This fundamental aspect makes our data cleaning system particularly suitable for remote sensing classification tasks which usually suffer from both mislabeling and imbalance problems. The effectiveness of our algorithm is demonstrated in performing mapping of land covers. The generalization performance of two major supervised noise-sensitive classifiers, boosting and K-nearest neighbors, is strengthened by effective class noise reduction. A comparative analysis is conducted with respect to random forest, deep convolutional neural networks, as well as two well-established ensemble-based class noise filters, the majority vote and the consensus vote filters. This analysis demonstrates that our approach is more accurate than deep convolutional neural networks (one-dimensional CNN, AlexNet, EfficientNet, ResNet50 and ShuffletNet) and the reference ensemble methods.

Electromagnetic controlled surface (ECS) which can regulate the amplitude and phase of electromagnetic wave reflection characteristics has attracted extensive attention in recent years because of its radar stealth effect by reducing the radar cross Section (RCS). However, radar detection cannot be avoided only by stealth in the energy field gradually. It is a novel pulse Doppler radar jamming mode proposed in this article to use the self-correlation of radar-transmitted waveforms to result in signal processing and radar detection failure through the rapid time-domain variation of phase coding ECS. In principle, phase modulation alters the intrapulse characteristics of the original signal and fundamentally interferes with the processing of the radar signal. In this article, random and periodic phase coding sequences are proposed according to different forms of radar jamming. And through the derivation formula and simulation experiment, the jamming effect under multiphase modulation is verified. Among them, the target energy is dispersed to the surroundings to form a wide envelope through random coding modulation, which leads to noise barrage jamming. While we use periodic sequence coding modulation, the target is shifted in the range–Doppler domain, causing misplaced coherence on the radar echo and deceptive jamming to the radar. Moreover, the technology can also be widely used in synthetic aperture radar (SAR) imaging, microwave measurement, and other remote sensing fields. To further confirm the accuracy and efficiency of the proposed method, multiparameter contrast experiments and parameter sensitivity analyses are conducted.

In this paper, the fusion method of the weighted median filter Gram-Schmidt transform transplants to the digital signal processor (DSP). Image fusion technology has always been a key technology in the field of remote sensing image processing, but the algorithm is rarely implemented on mobile devices, so the scope of use has great limitations. The algorithm in the paper blends multispectral images and panchromatic images in the same location. The multispectral image is filtered by using a weighted median filter, and then the processed image and the panchromatic image are fused through the Gram-Schmidt transform. The filtering process reduces noise interference in the image, and the fused image combines the advantages of both images with high resolution and high color information. Due to the portability of DSP chips, the algorithm can be mounted on many mobile devices. Reduce the process of data transfer and make the image processing process more convenient.

Pine wilt disease is one of the most dangerous forest diseases. Because of its strong infectivity and harm, it is very important to find out and stop it in time. In this paper, a novel spatial-spectral random forest (SRF) algorithm for pine wilt monitoring is proposed, for solving the problem of small manual detection range, long investigation time, and untimely discovery of the diseased tree. The proposed method organically combines spatial features with spectral information to quickly and efficiently mark the location of diseased trees. In this way, the online monitoring of the target area using the data of the Beijing-2 satellite is realized. This paper analyses the location of diseased trees and provides early warnings for disease-prone trees. The accuracy of the proposed algorithm is 86.66%, by the confusion matrix analysis.

International audience

Light detection and ranging (LiDAR) technology has revolutionized forest analysis in past two decades. The increase of available LiDAR data volume is accelerating in recent years. However, the dense and large-volume point clouds may constitute challenges for proper data storage and processing. Point subsampling is often a prerequisite in this circumstance. Nonetheless, the commonly used uniform and random subsampling methods fail to preserve the topological details of branching structures, as they essentially drop points globally. This generates problems for studies on detailed branching structures, and currently there are no point subsampling methods designed for trees. In this letter, a structure-aware subsampling (SAS) method is proposed to tackle this issue. SAS relies on skeleton-adaptive clustering to subsample points locally and maintains the global integrity simultaneously. The proposed method was tested and compared with uniform and random subsampling for retrieving key tree parameters including height, diameter at breast height (DBH), crown area, and wood volume based on geometrical reconstructions. Three datasets from terrestrial, mobile, and unmanned aerial vehicles (UAV) LiDAR platforms were tested. Results showed that SAS was able to achieve similar accuracies of structural parameters compared to the full-resolution data, even with a subsampling rate (SR) of over 90%. More importantly, at the same sampling rate, SAS faithfully preserved more points of thin branches compared to uniform and random subsampling. These results imply that the proposed method maintains the complex tree topology while significantly reduces the data size. This study provides a crucial advancement in LiDAR and forest applications, where data reduction still remains widely unexplored.

This article would like to provide an optimal beam steering control method for high-speed maneuvering platform synthetic aperture radar (SAR) imaging. A corresponding imaging algorithm with 3-D spatial-variation correction is proposed. First, the coordinates of beam footprint are calculated by the transition rule in each pulse repetition time (PRT). The transition rule is designed to get a unified image resolution and minimize the Doppler bandwidth. By the proposed imaging algorithm, 2-D spatial-variation envelop is corrected by azimuth keystone transform and range chirp scaling. Then the space-variant (SV) Doppler terms are compensated by frequency domain perturbation and time-domain resampling. The SV components in both the second- and third-order terms are removed. Finally, the proposed beam steering method and the imaging algorithm are verified by simulated SAR data.

With the continuous progress of computer deep learning technology, convolutional neural network (CNN), as a representative approach, provides a unique solution for hyperspectral image (HSI) classification. However, the parameters of CNN can not be well-tuned when the number of training samples is insufficient, resulting in unsatisfactory classification performance. To tackle the thorny problem, a deep ensemble CNN method based on sample expansion for HSI classification is studied in this paper. Specially, spatial information is first extracted and fused with original spectral bands to help classifiers obtain discriminant spectral-spatial features. Then we use the pixel-pair feature (PPF) to expand the number of training samples so that the parameters of CNN structure can be fully trained. In addition, deep ensemble CNN is employed in this paper, enabling the trained model to obtain better generalization ability and more robust classification results. Ultimately, the proposed method is applied to classify four widely used hyperspectral data sets. Experimental results show that the studied approach yields higher classification accuracy than some CNN-based methods even under the condition of small-size training set.

Accurate 2-D frequency spectrum (2-D FS) with acceleration, two-way range coupling terms, and spatial-variant Doppler parameters are the main problems to be solved in translational-variant bistatic forward-looking synthetic aperture radar (SAR) (TV BFSAR) with curved trajectory. For these issues, a modified omega-K imaging algorithm is derived in this article. The maximum usage of 2-D FS based on the method of series reversion (MSR) is achieved by linear range cell migration correction, and 2-D FS is linearized in bistatic range by using high-order polynomial fitting. Then, a method of azimuth resampling is introduced to implement compensation of spatial-variant Doppler parameters. Different from other bistatic omega-K methods, our newly proposed method focuses on the small-aperture data in the azimuth frequency domain to avoid azimuth aliasing without padding zeros and uses the frequency focusing position to study the model of spatial-variant phase. Simulation results and real data verify the effectiveness of the proposed method.

With the development of new active deception jamming, radar antijamming has become a major research hotspot, and the recognition of jamming type is one of its key steps. In recent years, deep learning has been successfully applied in the field of radar jamming recognition, such as convolutional neural networks (CNNs). However, it is difficult to effectively improve the accuracy of deep learning algorithms in the case of small sample. Furthermore, ensemble learning and transfer learning can effectively improve the model generalization performance. For the small sample problem, this article proposes a weighted ensemble CNN with transfer learning (WECNN-TL)-based radar active deception jamming recognition algorithm. The main idea of this method is to obtain the time–frequency distribution maps of jamming signals by the short-time Fourier transform (STFT), and then, their real parts, imaginary parts, moduli, and phases are combined differently to construct multiple datasets. Finally, an ensemble CNN (ECNN) model with weighted voting and transfer learning is constructed to realize jamming recognition. Experiments on the simulated and measured mixed datasets (including 12 types of samples) show that the proposed method can get better recognition performance than random forest (RF), support vector machine (SVM), and some CNN-based methods.

When airborne radar platforms have a hypersonic speed, the Doppler bandwidth will be several hundred times of that from the low speed platforms. There are contradictions between pulse repeat frequency (PRF), Doppler ambiguity and range swath during the system parameters design. Azimuth multichannel technique is applied to make the PRF lower and can get a wide range swath. The equivalent phase center (EPC) under high squint (HS) mode is calculated. Then the Doppler spectrum is reconstructed by spatial filtering method with azimuth dependent channel compensation.

In this paper, a novel forest disaster detection method based on fuzzy c-means (FCM) algorithm and genetic algorithm (GA) with neighborhood information (F-NGA) is proposed. The proposed method adopts FCM to pre-classify the original data first. Then, the neighborhood factors are added into the GA model to reclassify the results of FCM. Experiment results on two multispectral Formosat-2 forest images present that our algorithm obtains better detection performance when compared with FCM, fuzzy local information c-means (FLICM) and original GA algorithm.

Recently, convolutional neural network (CNN) is widely used in hyperspectral image classification (HSIC) because of its strong self-learning and efficient feature expression ability. However, the CNN model faces the “overfitting” problem when the number of training samples is small. To improve the classification accuracy of CNN under the condition of limited training set, an ensemble CNN method based on pixel-pair and random feature selection (RFS) for HSIC is proposed in this paper. With the purpose of expanding training samples, the pixel-pair feature (PPF) is used in the presented study. Besides, ensemble CNN based on RFS is applied to further improve the classification performance. Experimental results based on two standard hyperspectral images demonstrate that the proposed method achieves better classification performance than the PPF based on CNN (PPF-CNN) and RFS based on SVM (RFS-SVM) methods.

Convolution neural network (CNN) has been successfully applied to hyperspectral image classification. However, multiclass imbalance is a major problem in the classification of hyper spectral images, and traditional CNN can hardly improve the accuracy of minority classes effectively. In this paper, a new ensemble CNN with enhanced feature subspaces (ECNN-EFSs) algorithm is proposed, which utilizes an imbalanced training set to train the model and achieves accurate classification. Experimental results on two common hyperspectral datasets show that the proposed algorithm outperforms the traditional CNN and ensemble CNN algorithms.

The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide complementary information and improve the accuracy of land cover classification. In this paper, a novel fusion method is proposed to fuse the HSI and LiDAR dataset based on multi-scale feature extraction and total variation. In the method, the extended multi-attribute profile (EMAP) is utilized to automatically extract structural information from HSI and LiDAR elements. The extracted features are then estimated in a lower-dimensional space by multi-scale total variation (MSTV). Finally, the classification map is generated by applying random forest classifiers on the fused data. In the experiment, the performance of the proposed method is evaluated on an urban dataset of Houston. The results demonstrate that classification accuracy could be significantly improved by the proposed method compared with other methods.

In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE-DRoF) algorithm is proposed for the classification of imbalanced hyperspectral image data. It builds a multi -level forests cascade model by training a balanced dataset generated by SMOTE. In this model, each level of the random forest produces misclassification information of the data which are used as guidance information to adjust the sample weight adaptively for the next level. Experiment results on the hyperspectral image Indian Pines AVRIS and University of Pavia ROSIS demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined random forest, and SMOTE combined rotation forest in imbalance learning.

Forward-looking multichannel synthetic aperture radar (FLMC-SAR) is an important tool for modern remote sensing applications, which has the capability to reconstruct the high-resolution image of the front area. However, due to the azimuth-variant characteristics of the motion errors over a long aperture, FLMC-SAR data processing is usually a challenging task, especially when involving the motion compensation (MOCO) coupled with Doppler ambiguity resolving. To accomplish an accurate MOCO for FLMC-SAR, a novel parametric azimuth-variant MOCO approach is proposed in this article. Aiming at the coupling problem of MOCO and Doppler ambiguity resolving over the full aperture, we can decouple them through the subaperture division. As a full synthetic aperture is decomposed into several subapertures, the high-order motion errors of the full aperture can be decomposed into the first-order motion errors of the subaperture. On this basis, the mismatch of the space–time spectrum caused by the motion errors can be solved by spectral estimation, yielding Doppler ambiguity resolving for each subaperture. Meanwhile, the azimuth-variant characteristic of motion errors in FLMC-SAR system is characterized by a parametric angle-dependent quadratic phase error (QPE) model. The motion parameters are estimated by a joint multichannel angle estimation-based signal quadratic decomposition method. Immediately, the MOCO for ambiguous targets with different motion errors can be processed separately to improve the imaging performance. Experimental results based on both simulated and real data demonstrate that the proposed method is suitable for FLMC-SAR system.

Forward-looking correlated imaging plays an increasingly important role in modern radar imaging systems. It overcomes disadvantages of traditional side or squint synthetic aperture radar (SAR) which is dependent on specific relative motion between the radar and target scene. A new microwave forward-looking correlated 3-D imaging method based on random radiation field combined with sparse reconstruction is proposed in this article. Firstly, phased array radar (PAR) is adopted to form different and random antenna patterns. Then, combined with the compressed sensing (CS) theory, the target image can be recovered with very few samples which can break through Rayleigh resolution limitation. Furthermore, the proposed method can achieve resolution at least 5.5 times higher than real aperture imaging. To raise computation efficiency of sparse reconstruction, an improved quasi-Newton iteration method based on graphics processing unit (GPU) platform is developed. Meanwhile, a GPU-based (NVIDIA Tesla K40c) accelerated computing method can significantly reduce the processing time compared with the time given by a personal computer (PC). Both simulation and field experiment verify the validity of the proposed method.

The classification is one of the most important tasks of the hyperspectral remote sensing. However, the task always suffers from the curse of dimensionality which makes most classifier models disabled. In this paper, a novel ensemble method named feature separation based rotation forest (FSRoF) is proposed to avoid the influence of high-dimensionality by training a series of independent classifiers with the datasets in a low-dimensionality rotation space and using the out-of-bag instances to select the base classifiers of high quality to construct the final ensemble model. The random forest (RF) and the traditional rotation forest (RoF) are adopted as the comparisons in our experiment.

The presence of noise is often unavoidable and has been a serious nuisance factor that needs to be taken into account in the hyperspectral image classification. Effective noise handling is one of the most difficult problems in data classification. Ensemble-based filtering has been demonstrated successful in dealing with the class noise problem. In this paper, a novel two-step ensemble-based data filtering method is proposed to improve the hyperspectral image classification accuracy in the presence of class noise. The proposed method is a combination of noise redundancy classifiers and sensitive algorithms. The experimental results on two public hyperspectral datasets demonstrate the effectiveness of the proposed approach.

Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image data, which could avoid the difficulty of manually extracting features. However, the number of training set for the classification of hyperspectral images is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. In this paper, a spectral-spatial feature (SSF) extraction based CNN method is proposed for an accurate classification with a small training set. Experimental results based on two standard hyperspectral images demonstrate the effectiveness of the proposed method.

In microwave staring imaging, spatial-resolution of real aperture imaging is limited by actual antenna array aperture. In order to achieve high-resolution imaging of targets with sparse feature, this paper proposes a high-resolution imaging method based on temporal-spatial stochastic radiation field combining compressive sensing (CS) theory. Firstly, the formation and property of temporal-spatial stochastic radiation field are discussed. Then, signal model based on random radiation field is deduced in detail, and on this basis, high-resolution imaging method based on CS is discussed. The proposed method can distinguish targets within the beam coverage and higher quality image is achieved. Finally, numerical simulations and experiments in microwave chamber are performed to validate the method and its analysis.

There are two technical difficulties to overcome before obtaining a well-focused image from high squint (HS) synthetic aperture radar (SAR) with constant acceleration. One is effective range modeling and the other is the correction of space-variant (SV) Doppler parameters. Based on the imaging characteristics analysis, an orthogonal expansion range model (OERM) is proposed which can handle the coordinate rotation caused by range walk correction (RWC). Then a modified spectral analysis (SPECAN) with the Doppler resampling method is designed to correct the SV Doppler parameters. Finally, the proposed algorithm is verified by both simulated and real SAR data. Meanwhile, it shows an improvement in azimuth focusing quality over the reference one.

Bistatic forward-looking synthetic aperture radar (BFSAR) breaks through the limitations of the conventional monostatic SAR on the forward-looking imaging. However, the problems of range cell migration (RCM) caused by the linear range walk and 2-D spatial variability of Doppler parameters become more serious and complicated in translational variant BFSAR. In this article, a keystone transform is introduced to correct the linear RCM. Based on the characteristics of a small aperture, the nonlinear chirp scaling (NCS) is discussed in the frequency domain to equalize the azimuth-range-dependent Doppler parameters. The improved NCS in our newly proposed BFSAR imaging algorithm, especially the re-definition of range direction and the model of spatial variant phase, differentiates this article from all the existing studies in the literature on BFSAR signal processing. Simulation results and real data processing further validate the effectiveness of the proposed algorithm.

In[1], the result of Fig. 13(b) was incorrectly provided. Now, we provide the corrected result, as shown inFig. 1.

In this paper, we propose a novel ensemble margin based semi-supervised random forest (EMRF) algorithm for the classification of the hyperspectral image with limited training data. The proposed method tries to improve the effectiveness of the ensemble model via adaptively labeling the unlabeled instances with high classification probability then adding them into the training set. The classification probability of a training instance is reflected by the unsupervised margin value of this instance. The higher ensemble margin of an instance, the higher probability the instance being classified correctly and added into to the training set in the next iteration.

In order to reconstruct the linear frequency modulated (LFM) signal, such as radar signal due to the complexity. A novel parameter estimation method based on a modified convolution kernel function (MCKF) is proposed for multi-component LFM signal in this paper. The method has fewer external cross-terms and light computational burden because of non-searching operations. Moreover, it is robust against additive noise. Finally, simulated and real data results confirm the proposed method.

Chaotic‐based random stepped frequency signal is applied in the multiple‐input‐multiple‐output through‐the‐wall detection radar (MIMO‐TWDR)recently. When the frequency modulation (FM) sequence of transmission signal is controlled by the chaotic signal, the single‐frequency interference such as the power harmonics sneaking into the phase detector becomes periodical and therefore can be filtered in frequency domain. However, the target echo signal becomes random after chaotic modulation, where the matched filter usually is unable to be realised by Fourier transform and consequently the envelope of direct wave after the phase detector varies stochastically and is difficult to be eliminated by an analogue filter. The FM sequence of random disorganising cannot meet the demand of filtering out the single‐frequency interference and direct wave simultaneously. Therefore, a new method of FM sequence optimisation of chaotic‐based random stepped frequency signal based on genetic algorithm is proposed to solve these problems in this study. Simulations show that the optimised stepped frequency signal possesses the advantages of both chaotic‐based random and linear stepped frequency signal. The proposed scheme achieves excellent performance on direct wave and single‐frequency interference suppression and target detection. Moreover, it can avoid the interference between transmission antennas of MIMO radar.

Based on compressive sampling theory, a novel method for high-resolution inverse synthetic aperture radar (ISAR) imaging is presented in this letter by transmitting sparse probing frequencies. In this method, only a few measurements in the range frequency and cross-range time domains are needed to reconstruct the target scene by solving an inverse problem through either a linear program or a greedy pursuit. By transmitting merely a few probe frequencies instead of wideband signals, the proposed method can obtain an unambiguous ISAR image with superresolution. The validity of the proposed approach is also confirmed using numerical simulations and real data.

In this letter, a novel single-range image fusion method for radar imaging of spinning space debris with dimensions smaller than the radar range resolution is proposed. On the assumption that the target consists of isolated isotropic scattering centers, a 2-D image can be obtained using single-range unit cross-range echo data, which have a theoretical resolution of a quarter of a wavelength. The proposed approach is computationally efficient particularly for smaller sized targets, as the total rotational angle is divided into four small sections, allowing for easier processing of each region. Moreover, the proposed method can be used to directly obtain an image in Cartesian coordinates, unlike current algorithms where images are obtained in a polar format, requiring reformatting to the Cartesian grid. The validity of the proposed approach is confirmed using numerical simulations.