Submit Manuscript
Peer Review
Editor WorkMost Downloaded
1
2025, 14(5): 1276-1293.
Abstract
5239KB
This study addresses the issue of fine-grained feature extraction and classification for Low-Slow-Small (LSS) targets, such as birds and drones, by proposing a multi-band multi-angle feature fusion classification method. First, data from five types of rotorcraft drones and bird models were collected at multiple angles using K-band and L-band frequency-modulated continuous-wave radars, forming a dataset for LSS target detection. Second, to capture the periodic vibration characteristics of the L-band target signals, empirical mode decomposition was applied to extract high-frequency features and reduce noise interference. For the K-band echo signals, short-time Fourier transform was applied to obtain high-resolution micro-Doppler features from various angles. Based on these features, a Multi-band Multi-angle Feature Fusion Network (MMFFNet) was designed, incorporating an improved convolutional long short-term memory network for temporal feature extraction, along with an attention fusion module and a multiscale feature fusion module. The proposed architecture improves target classification accuracy by integrating features from both bands and angles. Validation using a real-world dataset showed that compared with methods relying on single radar features, the proposed approach improved the classification accuracy for seven types of LSS targets by 3.1% under a high Signal-to-Noise Ratio (SNR) of 5 dB and by 12.3% under a low SNR of −3 dB.
This study addresses the issue of fine-grained feature extraction and classification for Low-Slow-Small (LSS) targets, such as birds and drones, by proposing a multi-band multi-angle feature fusion classification method. First, data from five types of rotorcraft drones and bird models were collected at multiple angles using K-band and L-band frequency-modulated continuous-wave radars, forming a dataset for LSS target detection. Second, to capture the periodic vibration characteristics of the L-band target signals, empirical mode decomposition was applied to extract high-frequency features and reduce noise interference. For the K-band echo signals, short-time Fourier transform was applied to obtain high-resolution micro-Doppler features from various angles. Based on these features, a Multi-band Multi-angle Feature Fusion Network (MMFFNet) was designed, incorporating an improved convolutional long short-term memory network for temporal feature extraction, along with an attention fusion module and a multiscale feature fusion module. The proposed architecture improves target classification accuracy by integrating features from both bands and angles. Validation using a real-world dataset showed that compared with methods relying on single radar features, the proposed approach improved the classification accuracy for seven types of LSS targets by 3.1% under a high Signal-to-Noise Ratio (SNR) of 5 dB and by 12.3% under a low SNR of −3 dB.
2
2026, 15(4): 1238-1257.
To address issues such as insufficient feature extraction, limited spatiotemporal correlation modeling, and poor classification performance in radar classification of sea-air targets, this paper investigates on graph network-based feature extraction and classification methods. First, focusing on digital array ubiquitous radar, a radar detection dataset for sea-air targets, named LSS-DAUR-1.0, is constructed; it contains Doppler and track data for six types of targets: Passenger ships, speedboats, helicopters, rotor drones, birds, and fixed-wing drones. Second, based on this dataset, the multidomain and multidimensional characteristics of the targets are analyzed, and the complementarity between Doppler and physical motion features is verified through correlation and cosine similarity analyses. On this basis, a Graph Convolutional Network with Dynamic Graph Construction (DG-GCN) classification method fusing dual features is proposed. An adaptive window adjustment, a hybrid attenuation function, and a dynamic threshold mechanism are designed to construct an adaptive dynamic graph based on spatiotemporal correlation. Combined with graph convolution-based feature learning and classification modules, this approach achieves refined classification of low, slow, and small targets. Validation on the LSS-DAUR-1.0 dataset shows that the DG-GCN achieves 99.66% classification accuracy, which is 6.78% and 17.97% higher than that of ResNet and Transformer models, respectively. The total processing time is only 4.98 ms, which is more than 80% lower than that of the aforementioned comparison models. Hence, the DG-GCN achieves both high accuracy and efficiency. In addition, noise environment tests show good robustness. Ablation experiments verify that the dynamic edge weight mechanism compensates for the lack of spatial feature correlation in purely temporal connections and improves the model’s generalizability.
To address issues such as insufficient feature extraction, limited spatiotemporal correlation modeling, and poor classification performance in radar classification of sea-air targets, this paper investigates on graph network-based feature extraction and classification methods. First, focusing on digital array ubiquitous radar, a radar detection dataset for sea-air targets, named LSS-DAUR-1.0, is constructed; it contains Doppler and track data for six types of targets: Passenger ships, speedboats, helicopters, rotor drones, birds, and fixed-wing drones. Second, based on this dataset, the multidomain and multidimensional characteristics of the targets are analyzed, and the complementarity between Doppler and physical motion features is verified through correlation and cosine similarity analyses. On this basis, a Graph Convolutional Network with Dynamic Graph Construction (DG-GCN) classification method fusing dual features is proposed. An adaptive window adjustment, a hybrid attenuation function, and a dynamic threshold mechanism are designed to construct an adaptive dynamic graph based on spatiotemporal correlation. Combined with graph convolution-based feature learning and classification modules, this approach achieves refined classification of low, slow, and small targets. Validation on the LSS-DAUR-1.0 dataset shows that the DG-GCN achieves 99.66% classification accuracy, which is 6.78% and 17.97% higher than that of ResNet and Transformer models, respectively. The total processing time is only 4.98 ms, which is more than 80% lower than that of the aforementioned comparison models. Hence, the DG-GCN achieves both high accuracy and efficiency. In addition, noise environment tests show good robustness. Ablation experiments verify that the dynamic edge weight mechanism compensates for the lack of spatial feature correlation in purely temporal connections and improves the model’s generalizability.
3
2026, 15(2): 387-408.
Deep learning is primarily used for target detection in Synthetic Aperture Radar (SAR) images; however, its performance heavily relies on large-scale labeled datasets. The detection performance of deep learning models degrades when applied to SAR data with varying distributions, hindering their real-world applicability. In addition, manual labeling of SAR data is costly. Hence, cross-domain learning strategies based on multisource information are being explored to address these challenges. These strategies can assist detection models in realizing cross-domain knowledge migration by integrating prior information from optical remote sensing images or heterogeneous SAR images acquired from different sensors. This paper focuses on cross-domain learning technologies within the deep learning framework. In addition, it provides a systematic overview of the latest research progress in this field and analyzes the core issues, advantages, and applicable scenarios of existing technologies from a methodological perspective. It outlines future research directions based on the law of technological evolution, aiming to offer theoretical support and methodological references to enhance the generalizability of target detection in SAR images.
Deep learning is primarily used for target detection in Synthetic Aperture Radar (SAR) images; however, its performance heavily relies on large-scale labeled datasets. The detection performance of deep learning models degrades when applied to SAR data with varying distributions, hindering their real-world applicability. In addition, manual labeling of SAR data is costly. Hence, cross-domain learning strategies based on multisource information are being explored to address these challenges. These strategies can assist detection models in realizing cross-domain knowledge migration by integrating prior information from optical remote sensing images or heterogeneous SAR images acquired from different sensors. This paper focuses on cross-domain learning technologies within the deep learning framework. In addition, it provides a systematic overview of the latest research progress in this field and analyzes the core issues, advantages, and applicable scenarios of existing technologies from a methodological perspective. It outlines future research directions based on the law of technological evolution, aiming to offer theoretical support and methodological references to enhance the generalizability of target detection in SAR images.
4
2026, 15(4): 1258-1277.
The threat from low-altitude targets to airspace security such as airport is increasing, making accurate detection and recognition essential for radar systems. High-quality measured radar datasets are crucial for advancing low-altitude target recognition. However, most existing public radar datasets for these targets consist of simulation data or short-range collected data, which have difficulty accurately reflecting and verifying radar target recognition performance in long-range scenarios. To overcome these limitations, this study creates a low-altitude target detection and recognition dataset based on Holographic Staring Radar (HSR), including measured data collection and recognition validation for typical low-altitude targets in outdoor environments. The dataset includes common targets such as multirotor unmanned aerial vehicles, sparrows, and large migratory birds, along with representative motion scenarios like hovering, circling, and radial flight. It also offers synchronized target micro-Doppler waterfall plots and radar-measured track information (including azimuth and elevation angles, radial velocity, and normalized signal-to-noise ratio), providing a data foundation for exploring the intrinsic link between target detailed features and motion states. Building on this, a multimodal adaptive feature fusion network is developed to extract and combine Doppler and kinematic features from different targets, demonstrating the dataset’s effectiveness in distinguishing various low-altitude targets.
The threat from low-altitude targets to airspace security such as airport is increasing, making accurate detection and recognition essential for radar systems. High-quality measured radar datasets are crucial for advancing low-altitude target recognition. However, most existing public radar datasets for these targets consist of simulation data or short-range collected data, which have difficulty accurately reflecting and verifying radar target recognition performance in long-range scenarios. To overcome these limitations, this study creates a low-altitude target detection and recognition dataset based on Holographic Staring Radar (HSR), including measured data collection and recognition validation for typical low-altitude targets in outdoor environments. The dataset includes common targets such as multirotor unmanned aerial vehicles, sparrows, and large migratory birds, along with representative motion scenarios like hovering, circling, and radial flight. It also offers synchronized target micro-Doppler waterfall plots and radar-measured track information (including azimuth and elevation angles, radial velocity, and normalized signal-to-noise ratio), providing a data foundation for exploring the intrinsic link between target detailed features and motion states. Building on this, a multimodal adaptive feature fusion network is developed to extract and combine Doppler and kinematic features from different targets, demonstrating the dataset’s effectiveness in distinguishing various low-altitude targets.
5
2023, 12(2): 456-469.
Marine target detection and recognition depend on the characteristics of marine targets and sea clutter. Therefore, understanding the essential features of marine targets based on the measured data is crucial for advancing target detection and recognition technology. To address the issue of insufficient data on the scattering characteristics of marine targets, the Sea-Detecting Radar Data-Sharing Program (SDRDSP) was upgraded to obtain data on marine targets and their environment under different polarizations and sea states. This upgrade expanded the physical dimension of radar target observation and improved radar and auxiliary data acquisition capabilities. Furthermore, a dual-polarized multistate scattering characteristic dataset of marine targets was constructed, and the statistical distribution characteristics, time and space correlation, and Doppler spectrum were analyzed, supporting the data usage. In the future, the types and quantities of maritime targets will continue to accumulate, providing data support for improving marine target detection and recognition performance and intelligence.
Marine target detection and recognition depend on the characteristics of marine targets and sea clutter. Therefore, understanding the essential features of marine targets based on the measured data is crucial for advancing target detection and recognition technology. To address the issue of insufficient data on the scattering characteristics of marine targets, the Sea-Detecting Radar Data-Sharing Program (SDRDSP) was upgraded to obtain data on marine targets and their environment under different polarizations and sea states. This upgrade expanded the physical dimension of radar target observation and improved radar and auxiliary data acquisition capabilities. Furthermore, a dual-polarized multistate scattering characteristic dataset of marine targets was constructed, and the statistical distribution characteristics, time and space correlation, and Doppler spectrum were analyzed, supporting the data usage. In the future, the types and quantities of maritime targets will continue to accumulate, providing data support for improving marine target detection and recognition performance and intelligence.
6
2026, 15(4): 1125-1151.
Radar systems acquire target information by transmitting waveforms, receiving echoes, and processing signals; thus, waveform performance is a critical determinant of radar system performance. Compared with other radar systems, Synthetic Aperture Radar (SAR) operates under unique conditions, including distributed target scenes, waveforms with large time-bandwidth products, wide-swath and long-range imaging, and range-azimuth coupling. These characteristics impose additional stringent requirements on SAR waveform design. Drawing on the authors’ research and expertise in SAR waveform coding, this paper reviews recent domestic and international advances in SAR waveform design, discusses key technical challenges, and highlights the role of waveform design in enhancing system imaging performance. Finally, this study outlines future trends and potential directions for SAR waveform design methodologies.
Radar systems acquire target information by transmitting waveforms, receiving echoes, and processing signals; thus, waveform performance is a critical determinant of radar system performance. Compared with other radar systems, Synthetic Aperture Radar (SAR) operates under unique conditions, including distributed target scenes, waveforms with large time-bandwidth products, wide-swath and long-range imaging, and range-azimuth coupling. These characteristics impose additional stringent requirements on SAR waveform design. Drawing on the authors’ research and expertise in SAR waveform coding, this paper reviews recent domestic and international advances in SAR waveform design, discusses key technical challenges, and highlights the role of waveform design in enhancing system imaging performance. Finally, this study outlines future trends and potential directions for SAR waveform design methodologies.
7
2023, 12(4): 906-922.
This study proposes a Synthetic Aperture Radar (SAR) aircraft detection and recognition method combined with scattering perception to address the problem of target discreteness and false alarms caused by strong background interference in SAR images. The global information is enhanced through a context-guided feature pyramid module, which suppresses strong disturbances in complex images and improves the accuracy of detection and recognition. Additionally, scatter key points are used to locate targets, and a scatter-aware detection module is designed to realize the fine correction of the regression boxes to improve target localization accuracy. This study generates and presents a high-resolution SAR-AIRcraft-1.0 dataset to verify the effectiveness of the proposed method and promote the research on SAR aircraft detection and recognition. The images in this dataset are obtained from the satellite Gaofen-3, which contains 4,368 images and 16,463 aircraft instances, covering seven aircraft categories, namely A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and other. We apply the proposed method and common deep learning algorithms to the constructed dataset. The experimental results demonstrate the excellent effectiveness of our method combined with scattering perception. Furthermore, we establish benchmarks for the performance indicators of the dataset in different tasks such as SAR aircraft detection, recognition, and integrated detection and recognition.
This study proposes a Synthetic Aperture Radar (SAR) aircraft detection and recognition method combined with scattering perception to address the problem of target discreteness and false alarms caused by strong background interference in SAR images. The global information is enhanced through a context-guided feature pyramid module, which suppresses strong disturbances in complex images and improves the accuracy of detection and recognition. Additionally, scatter key points are used to locate targets, and a scatter-aware detection module is designed to realize the fine correction of the regression boxes to improve target localization accuracy. This study generates and presents a high-resolution SAR-AIRcraft-1.0 dataset to verify the effectiveness of the proposed method and promote the research on SAR aircraft detection and recognition. The images in this dataset are obtained from the satellite Gaofen-3, which contains 4,368 images and 16,463 aircraft instances, covering seven aircraft categories, namely A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and other. We apply the proposed method and common deep learning algorithms to the constructed dataset. The experimental results demonstrate the excellent effectiveness of our method combined with scattering perception. Furthermore, we establish benchmarks for the performance indicators of the dataset in different tasks such as SAR aircraft detection, recognition, and integrated detection and recognition.
8
2026, 15(1): 1-25.
With the increasing demands on imaging accuracy, efficiency, and robustness in modern three-Dimensional (3D) Synthetic Aperture Radar (SAR) imaging systems, the performance of traditional 3D imaging methods, such as matched filtering and compressed sensing, has become limited in these aspects. In recent years, the rapid development of Deep Learning (DL) technology has provided new theoretical solutions for SAR 3D imaging by enabling the integration of neural networks with physical radar imaging models, leading to the emergence of a learning-based imaging paradigm that combines data-driven and model-driven approaches. This paper systematically reviews recent research progress in DL-based SAR 3D imaging. Focusing on two core issues, namely super-resolution imaging and enhanced imaging, this paper discusses current research advances and hotspots in SAR 3D imaging. These include super-resolution 3D imaging methods based on feedforward neural networks and deep unfolding networks, as well as 3D enhancement techniques such as multichannel data preprocessing and point cloud post-processing. This paper also summarizes publicly available datasets for SAR 3D imaging. In addition, this paper explores current research challenges in DL SAR 3D imaging, including high-generalization and high-precision DL SAR super-resolution 3D imaging technology, DL SAR elevation dimension disambiguation technology, integrated study of DL SAR 3D imaging and image enhancement, and the construction of DL SAR 3D imaging datasets. This paper provides an outlook on future development trends, aiming to offer research references and technical guidance for scholars in related fields.
With the increasing demands on imaging accuracy, efficiency, and robustness in modern three-Dimensional (3D) Synthetic Aperture Radar (SAR) imaging systems, the performance of traditional 3D imaging methods, such as matched filtering and compressed sensing, has become limited in these aspects. In recent years, the rapid development of Deep Learning (DL) technology has provided new theoretical solutions for SAR 3D imaging by enabling the integration of neural networks with physical radar imaging models, leading to the emergence of a learning-based imaging paradigm that combines data-driven and model-driven approaches. This paper systematically reviews recent research progress in DL-based SAR 3D imaging. Focusing on two core issues, namely super-resolution imaging and enhanced imaging, this paper discusses current research advances and hotspots in SAR 3D imaging. These include super-resolution 3D imaging methods based on feedforward neural networks and deep unfolding networks, as well as 3D enhancement techniques such as multichannel data preprocessing and point cloud post-processing. This paper also summarizes publicly available datasets for SAR 3D imaging. In addition, this paper explores current research challenges in DL SAR 3D imaging, including high-generalization and high-precision DL SAR super-resolution 3D imaging technology, DL SAR elevation dimension disambiguation technology, integrated study of DL SAR 3D imaging and image enhancement, and the construction of DL SAR 3D imaging datasets. This paper provides an outlook on future development trends, aiming to offer research references and technical guidance for scholars in related fields.
9
2026, 15(2): 409-440.
Synthetic Aperture Radar (SAR) is widely used in military and civilian applications, with intelligent target interpretation of SAR images being a crucial component of SAR applications. Vision-Language Models (VLMs) play an important role in SAR target interpretation. By incorporating natural language understanding, VLMs effectively address the challenges posed by large intraclass variability in target characteristics and the scarcity of high-quality labeled samples, thereby advancing the field from purely visual interpretation toward semantic understanding of targets. Drawing upon our team’s extensive research experience in SAR target interpretation theory, algorithms, and applications, this paper provides a comprehensive review of intelligent SAR target interpretation based on VLMs. We provide an in-depth analysis of existing challenges and tasks, summarize the current state of research, and compile available open-source datasets. Furthermore, we systematically outline the evolution, ranging from task-specific VLMs to contrastive-, conversational-, and generative-based VLMs and foundational models. Finally, we discuss the latest challenges and future outlooks in SAR target interpretation by VLMs.
Synthetic Aperture Radar (SAR) is widely used in military and civilian applications, with intelligent target interpretation of SAR images being a crucial component of SAR applications. Vision-Language Models (VLMs) play an important role in SAR target interpretation. By incorporating natural language understanding, VLMs effectively address the challenges posed by large intraclass variability in target characteristics and the scarcity of high-quality labeled samples, thereby advancing the field from purely visual interpretation toward semantic understanding of targets. Drawing upon our team’s extensive research experience in SAR target interpretation theory, algorithms, and applications, this paper provides a comprehensive review of intelligent SAR target interpretation based on VLMs. We provide an in-depth analysis of existing challenges and tasks, summarize the current state of research, and compile available open-source datasets. Furthermore, we systematically outline the evolution, ranging from task-specific VLMs to contrastive-, conversational-, and generative-based VLMs and foundational models. Finally, we discuss the latest challenges and future outlooks in SAR target interpretation by VLMs.
10
2024, 13(3): 539-553.
Detection of small, slow-moving targets, such as drones using Unmanned Aerial Vehicles (UAVs) poses considerable challenges to radar target detection and recognition technology. There is an urgent need to establish relevant datasets to support the development and application of techniques for detecting small, slow-moving targets. This paper presents a dataset for detecting low-speed and small-size targets using a multiband Frequency Modulated Continuous Wave (FMCW) radar. The dataset utilizes Ku-band and L-band FMCW radar to collect echo data from six UAV types and exhibits diverse temporal and frequency domain resolutions and measurement capabilities by modulating radar cycles and bandwidth, generating an LSS-FMCWR-1.0 dataset (Low Slow Small, LSS). To further enhance the capability for extracting micro-Doppler features from UAVs, this paper proposes a method for UAV micro-Doppler extraction and parameter estimation based on the local maximum synchroextracting transform. Based on the Short Time Fourier Transform (STFT), this method extracts values at the maximum energy point in the time-frequency domain to retain useful signals and refine the time-frequency energy representation. Validation and analysis using the LSS-FMCWR-1.0 dataset demonstrate that this approach reduces entropy on an average by 5.3 dB and decreases estimation errors in rotor blade length by 27.7% compared with traditional time-frequency methods. Moreover, the proposed method provides the foundation for subsequent target recognition efforts because it balances high time-frequency resolution and parameter estimation capabilities.
Detection of small, slow-moving targets, such as drones using Unmanned Aerial Vehicles (UAVs) poses considerable challenges to radar target detection and recognition technology. There is an urgent need to establish relevant datasets to support the development and application of techniques for detecting small, slow-moving targets. This paper presents a dataset for detecting low-speed and small-size targets using a multiband Frequency Modulated Continuous Wave (FMCW) radar. The dataset utilizes Ku-band and L-band FMCW radar to collect echo data from six UAV types and exhibits diverse temporal and frequency domain resolutions and measurement capabilities by modulating radar cycles and bandwidth, generating an LSS-FMCWR-1.0 dataset (Low Slow Small, LSS). To further enhance the capability for extracting micro-Doppler features from UAVs, this paper proposes a method for UAV micro-Doppler extraction and parameter estimation based on the local maximum synchroextracting transform. Based on the Short Time Fourier Transform (STFT), this method extracts values at the maximum energy point in the time-frequency domain to retain useful signals and refine the time-frequency energy representation. Validation and analysis using the LSS-FMCWR-1.0 dataset demonstrate that this approach reduces entropy on an average by 5.3 dB and decreases estimation errors in rotor blade length by 27.7% compared with traditional time-frequency methods. Moreover, the proposed method provides the foundation for subsequent target recognition efforts because it balances high time-frequency resolution and parameter estimation capabilities.
11
2026, 15(3): 983-995.
Synthetic Aperture Radar (SAR) and optical imagery are two key remote-sensing modalities in Earth observation, and cross-modal image matching between them is widely applied in tasks such as image fusion, joint interpretation, and high-precision geolocation. In recent years, with the rapid growth of Earth-observation data, the importance of cross-modal image matching between SAR and optical data has become increasingly prominent, and related studies have achieved notable progress. In particular, Deep Learning (DL)-based methods, owing to their strengths in cross-modal feature representation and high-level semantic extraction, have demonstrated excellent matching accuracy and adaptability across varying imaging conditions. However, most publicly available datasets are limited to small image patches and lack complete full-scene image pairs that cover realistic large-scale scenarios, making it difficult to comprehensively evaluate the performance of matching algorithms in practical remote-sensing settings and constraining advances in the training and generalization of DL models. To address these issues, this study develops and releases OSDataset2.0, a large-scale benchmark dataset for SAR-optical image matching. The dataset comprises two parts: A patch-level subset and a scene-level subset. The patch-level subset is composed of 6,476 registered 512 × 512 image pairs covering 14 countries (Argentina, Australia, Poland, Germany, Russia, France, Qatar, Malaysia, the United States, Japan, Türkiye, Singapore, India, and China); the scene-level subset consists of one pair of full-scene optical and SAR images. For full-scene images, high-precision, uniformly distributed ground-truth correspondences are provided, extracted under the principle of imaging-mechanism consistency, together with a general evaluation codebase that supports quantitative analysis of registration accuracy for arbitrary matching algorithms. To further assess the dataset’s effectiveness and challenge level, a systematic evaluation of 11 representative optical-SAR matching methods on OSDataset2.0 is conducted, covering traditional feature-based approaches and mainstream DL models. Experimental results show that the dataset not only supports effective algorithmic comparisons but also provides reliable training resources and a unified evaluation benchmark for subsequent research.
Synthetic Aperture Radar (SAR) and optical imagery are two key remote-sensing modalities in Earth observation, and cross-modal image matching between them is widely applied in tasks such as image fusion, joint interpretation, and high-precision geolocation. In recent years, with the rapid growth of Earth-observation data, the importance of cross-modal image matching between SAR and optical data has become increasingly prominent, and related studies have achieved notable progress. In particular, Deep Learning (DL)-based methods, owing to their strengths in cross-modal feature representation and high-level semantic extraction, have demonstrated excellent matching accuracy and adaptability across varying imaging conditions. However, most publicly available datasets are limited to small image patches and lack complete full-scene image pairs that cover realistic large-scale scenarios, making it difficult to comprehensively evaluate the performance of matching algorithms in practical remote-sensing settings and constraining advances in the training and generalization of DL models. To address these issues, this study develops and releases OSDataset2.0, a large-scale benchmark dataset for SAR-optical image matching. The dataset comprises two parts: A patch-level subset and a scene-level subset. The patch-level subset is composed of 6,476 registered 512 × 512 image pairs covering 14 countries (Argentina, Australia, Poland, Germany, Russia, France, Qatar, Malaysia, the United States, Japan, Türkiye, Singapore, India, and China); the scene-level subset consists of one pair of full-scene optical and SAR images. For full-scene images, high-precision, uniformly distributed ground-truth correspondences are provided, extracted under the principle of imaging-mechanism consistency, together with a general evaluation codebase that supports quantitative analysis of registration accuracy for arbitrary matching algorithms. To further assess the dataset’s effectiveness and challenge level, a systematic evaluation of 11 representative optical-SAR matching methods on OSDataset2.0 is conducted, covering traditional feature-based approaches and mainstream DL models. Experimental results show that the dataset not only supports effective algorithmic comparisons but also provides reliable training resources and a unified evaluation benchmark for subsequent research.
12
2026, 15(4): 1340-1359.
Reinforcement Learning (RL) is a critical approach for enabling cognitive radar target detection. Existing studies primarily focus on detection methods for centralized Multiple-Input Multiple-Output (MIMO) radar, which are limited to a single observation perspective. To address this issue, this paper proposes an RL-based multi-target detection method for a distributed MIMO radar system that possesses waveform and spatial diversity. The proposed method exploits spatial diversity to ensure robust target detection, while waveform diversity is used to construct a Markov decision process. Specifically, the radar first perceives target attributes through statistical signal detection techniques, then optimizes the transmit waveform accordingly, and iteratively updates its understanding of the environmental context using accumulated experience. This cyclic process gradually converges, yielding radar waveforms focused on target directions and achieving improved detection performance. To facilitate target localization, a maximization grid-based generalized likelihood ratio test detector for multi-antenna configurations is derived, using regularly shaped grids as the cell under test. For waveform optimization, two types of optimization problems, namely conventional and strong-target-limited formulations, are developed, and their solutions are obtained using continuous convex approximation. Simulation results across static and dynamic scenarios demonstrate that the proposed method can autonomously perceive environmental context and achieve superior detection performance compared with benchmark methods, particularly in weak target detection.
Reinforcement Learning (RL) is a critical approach for enabling cognitive radar target detection. Existing studies primarily focus on detection methods for centralized Multiple-Input Multiple-Output (MIMO) radar, which are limited to a single observation perspective. To address this issue, this paper proposes an RL-based multi-target detection method for a distributed MIMO radar system that possesses waveform and spatial diversity. The proposed method exploits spatial diversity to ensure robust target detection, while waveform diversity is used to construct a Markov decision process. Specifically, the radar first perceives target attributes through statistical signal detection techniques, then optimizes the transmit waveform accordingly, and iteratively updates its understanding of the environmental context using accumulated experience. This cyclic process gradually converges, yielding radar waveforms focused on target directions and achieving improved detection performance. To facilitate target localization, a maximization grid-based generalized likelihood ratio test detector for multi-antenna configurations is derived, using regularly shaped grids as the cell under test. For waveform optimization, two types of optimization problems, namely conventional and strong-target-limited formulations, are developed, and their solutions are obtained using continuous convex approximation. Simulation results across static and dynamic scenarios demonstrate that the proposed method can autonomously perceive environmental context and achieve superior detection performance compared with benchmark methods, particularly in weak target detection.
13
2026, 15(3): 996-1012.
A large-scale Vision-Language Model (VLM) pre-trained on massive image-text datasets performs well when processing natural images. However, there are two major challenges in applying it to Synthetic Aperture Radar (SAR) images: (1) The high cost of high-quality text annotation limits the construction of SAR image-text paired datasets, and (2) The considerable differences in image features between SAR images and optical natural images increase the difficulty of cross-domain knowledge transfer. To address these problems, this study developed a knowledge transfer method for VLM tailored to SAR images. First, this study leveraged paired SAR and optical remote sensing images and employed a generative VLM to automatically produce textual descriptions of the optical images, thereby indirectly constructing a low-cost SAR-text paired dataset. Second, a two-stage transfer strategy was designed to address the large domain discrepancy between natural and SAR images, reducing the difficulty of each transfer stage. Finally, experimental validation was conducted through the zero-shot scene classification, image retrieval, and object recognition of SAR images. The results demonstrated that the proposed method enables effective knowledge transfer from a large-scale VLM to the SAR image domain.
A large-scale Vision-Language Model (VLM) pre-trained on massive image-text datasets performs well when processing natural images. However, there are two major challenges in applying it to Synthetic Aperture Radar (SAR) images: (1) The high cost of high-quality text annotation limits the construction of SAR image-text paired datasets, and (2) The considerable differences in image features between SAR images and optical natural images increase the difficulty of cross-domain knowledge transfer. To address these problems, this study developed a knowledge transfer method for VLM tailored to SAR images. First, this study leveraged paired SAR and optical remote sensing images and employed a generative VLM to automatically produce textual descriptions of the optical images, thereby indirectly constructing a low-cost SAR-text paired dataset. Second, a two-stage transfer strategy was designed to address the large domain discrepancy between natural and SAR images, reducing the difficulty of each transfer stage. Finally, experimental validation was conducted through the zero-shot scene classification, image retrieval, and object recognition of SAR images. The results demonstrated that the proposed method enables effective knowledge transfer from a large-scale VLM to the SAR image domain.
14
2026, 15(3): 860-875.
Direction of Arrival (DOA) estimation for low-elevation angle targets is a critical challenge in meter-wave and holographic staring radar systems, as its accuracy directly affects target height measurement performance. Traditional beamspace methods reduce computational complexity by projecting high-dimensional element-space data onto a low-dimensional beamspace using a beamformer. However, this lossy mapping leads to partial information loss, resulting in degraded elevation-angle estimation accuracy compared to that of element-space methods. To address this issue, this study proposes a high-accuracy beamspace DOA estimation method for low-elevation angle targets. First, the Cramér-Rao Bound (CRB) for both element-space and beamspace DOA estimation is derived, and the conditions under which these bounds are equal are analyzed. Since these conditions are difficult to satisfy in practical scenarios, an approximate-condition-based beamformer design strategy is developed to reduce data dimensionality while preserving effective target information. Finally, precise elevation-angle estimation is achieved using the maximum likelihood criterion. Simulation and experimental results show that the proposed method significantly reduces data dimensionality while maintaining estimation accuracy comparable to that of element-space methods at low-elevation angles, clearly outperforming existing beamspace algorithms.
Direction of Arrival (DOA) estimation for low-elevation angle targets is a critical challenge in meter-wave and holographic staring radar systems, as its accuracy directly affects target height measurement performance. Traditional beamspace methods reduce computational complexity by projecting high-dimensional element-space data onto a low-dimensional beamspace using a beamformer. However, this lossy mapping leads to partial information loss, resulting in degraded elevation-angle estimation accuracy compared to that of element-space methods. To address this issue, this study proposes a high-accuracy beamspace DOA estimation method for low-elevation angle targets. First, the Cramér-Rao Bound (CRB) for both element-space and beamspace DOA estimation is derived, and the conditions under which these bounds are equal are analyzed. Since these conditions are difficult to satisfy in practical scenarios, an approximate-condition-based beamformer design strategy is developed to reduce data dimensionality while preserving effective target information. Finally, precise elevation-angle estimation is achieved using the maximum likelihood criterion. Simulation and experimental results show that the proposed method significantly reduces data dimensionality while maintaining estimation accuracy comparable to that of element-space methods at low-elevation angles, clearly outperforming existing beamspace algorithms.
15
2026, 15(3): 1059-1090.
Driven by complex electromagnetic environments and multi-target collaborative detection needs, enhancing the overall effectiveness of radar networks through autonomous coordination technology has become a key research area in radar collaborative surveillance. Extensive research has been conducted worldwide, yielding substantial advances in theoretical development, technical validation, and equipment application. This paper systematically discusses the foundational concepts and main features of autonomous coordination in radar networks, examining the primary technical challenges faced during implementation and performance optimization. It also reviews recent notable research findings and technological strategies, focusing on collaborative architecture design, sensing, intelligent decision-making and control, and autonomous evolution. Finally, this paper offers an outlook on future trends in the field and provides references for related theoretical research and practical applications.
Driven by complex electromagnetic environments and multi-target collaborative detection needs, enhancing the overall effectiveness of radar networks through autonomous coordination technology has become a key research area in radar collaborative surveillance. Extensive research has been conducted worldwide, yielding substantial advances in theoretical development, technical validation, and equipment application. This paper systematically discusses the foundational concepts and main features of autonomous coordination in radar networks, examining the primary technical challenges faced during implementation and performance optimization. It also reviews recent notable research findings and technological strategies, focusing on collaborative architecture design, sensing, intelligent decision-making and control, and autonomous evolution. Finally, this paper offers an outlook on future trends in the field and provides references for related theoretical research and practical applications.
16
2026, 15(3): 944-963.
Specific Emitter Identification (SEI) relies on subtle differences in the radio frequency fingerprints of device-emitted signals to determine the emitter identity attributes. SEI plays a fundamental role in wireless security, spectrum management, and situational awareness. However, as wireless scenarios become increasingly diverse and dynamic, deep learning models trained in a single domain (where the source and target domains share the same distribution) often suffer severe performance degradation in real-world settings such as cross-receiver and cross-time scenarios. This degradation has not yet been comprehensively analyzed. To address this issue, this paper first classifies SEI according to cross-scenario types, and then systematically reviews mainstream algorithm frameworks and representative SEI methods, with a particular focus on the core ideas and key technologies underlying each method. It also summarizes the main open-source cross-scenario SEI datasets. Finally, the paper identifies current research bottlenecks and outlines potential future directions, aiming to facilitate advances in SEI theories and methodologies applicable to complex electromagnetic environments.
Specific Emitter Identification (SEI) relies on subtle differences in the radio frequency fingerprints of device-emitted signals to determine the emitter identity attributes. SEI plays a fundamental role in wireless security, spectrum management, and situational awareness. However, as wireless scenarios become increasingly diverse and dynamic, deep learning models trained in a single domain (where the source and target domains share the same distribution) often suffer severe performance degradation in real-world settings such as cross-receiver and cross-time scenarios. This degradation has not yet been comprehensively analyzed. To address this issue, this paper first classifies SEI according to cross-scenario types, and then systematically reviews mainstream algorithm frameworks and representative SEI methods, with a particular focus on the core ideas and key technologies underlying each method. It also summarizes the main open-source cross-scenario SEI datasets. Finally, the paper identifies current research bottlenecks and outlines potential future directions, aiming to facilitate advances in SEI theories and methodologies applicable to complex electromagnetic environments.
17
2025, 14(4): 1092-1114.
Compared to ground-based external radiation source radar, satellite signal-based external radiation source radar (i.e., satellite signal external radiation source radar) offers advantages such as global, all-time, and all-weather coverage, which can compensate for the limitations of ground-based external radiation source radar in terms of maritime coverage. In contrast to medium and high-altitude satellite signals, Low-Earth Orbit (LEO) communication satellite signals have advantages such as strong reception power and a large number of satellites, which can provide substantial detection range and accuracy for passive detection of maritime targets. In response to future development needs, this paper provides a detailed discussion of the research status and application prospects of satellite signal external radiation source radar, and presents a feasibility analysis for constructing a low-earth orbit communication satellite signal external radiation source radar system using Iridium and Starlink, two types of LEO communication satellite systems, which integrates high and low frequencies with both wide and narrow bandwidths. Based on this, the paper summarizes the technical challenges and potential solutions in the development of low-earth orbit communication satellite signal external radiation source radar systems. The aforementioned research can serve as an important reference for wide-area external radiation source radar detection.
Compared to ground-based external radiation source radar, satellite signal-based external radiation source radar (i.e., satellite signal external radiation source radar) offers advantages such as global, all-time, and all-weather coverage, which can compensate for the limitations of ground-based external radiation source radar in terms of maritime coverage. In contrast to medium and high-altitude satellite signals, Low-Earth Orbit (LEO) communication satellite signals have advantages such as strong reception power and a large number of satellites, which can provide substantial detection range and accuracy for passive detection of maritime targets. In response to future development needs, this paper provides a detailed discussion of the research status and application prospects of satellite signal external radiation source radar, and presents a feasibility analysis for constructing a low-earth orbit communication satellite signal external radiation source radar system using Iridium and Starlink, two types of LEO communication satellite systems, which integrates high and low frequencies with both wide and narrow bandwidths. Based on this, the paper summarizes the technical challenges and potential solutions in the development of low-earth orbit communication satellite signal external radiation source radar systems. The aforementioned research can serve as an important reference for wide-area external radiation source radar detection.
18
Vortex Electromagnetic Wave Radar (VEWR) leverages the orthogonality of Orbital Angular Momentum (OAM) modes, introducing a new physical dimension that theoretically overcomes the azimuth resolution limitations of conventional radar systems and enables enhanced micro-motion perception and forward-looking imaging. However, in practical engineering applications, the limited number of available OAM modes and the presence of complex electromagnetic noise often cause severe mode aliasing and resolution degradation. Existing sparse imaging methods face inherent trade-offs between accuracy and computational efficiency and exhibit limited robustness to noise. To address these issues, this paper proposes a super-resolution imaging framework that integrates Mode Correlation Weighting and Adaptive Regularization (MCWAR). First, a forward-looking imaging geometry and a wavefront-modulated signal model for VEWR are established. Subsequently, an OAM mode correlation matrix is designed to characterize the nonuniform distribution of radiation energy among modes, where Bessel-function-modulated weights reinforce the low-rank constraints of dominant radiation components. Finally, a compound optimization model combining sparsity and low-rankness priors is developed, incorporating an adaptive weighting mechanism that dynamically balances structural preservation and noise suppression. A joint optimization framework based on the Alternating Direction Method of Multipliers (ADMM) and Augmented Lagrange Multiplier (ALM) algorithms is constructed, in which the core image-updating subproblem is efficiently solved using a momentum-accelerated Two-Dimensional Conjugate Gradient Least Squares (2D-CGLS) method. Numerical simulations and electromagnetic experiments verify that the proposed method preserves target structural integrity under limited modes and strong noise, while effectively improving both computational efficiency and imaging quality.
Vortex Electromagnetic Wave Radar (VEWR) leverages the orthogonality of Orbital Angular Momentum (OAM) modes, introducing a new physical dimension that theoretically overcomes the azimuth resolution limitations of conventional radar systems and enables enhanced micro-motion perception and forward-looking imaging. However, in practical engineering applications, the limited number of available OAM modes and the presence of complex electromagnetic noise often cause severe mode aliasing and resolution degradation. Existing sparse imaging methods face inherent trade-offs between accuracy and computational efficiency and exhibit limited robustness to noise. To address these issues, this paper proposes a super-resolution imaging framework that integrates Mode Correlation Weighting and Adaptive Regularization (MCWAR). First, a forward-looking imaging geometry and a wavefront-modulated signal model for VEWR are established. Subsequently, an OAM mode correlation matrix is designed to characterize the nonuniform distribution of radiation energy among modes, where Bessel-function-modulated weights reinforce the low-rank constraints of dominant radiation components. Finally, a compound optimization model combining sparsity and low-rankness priors is developed, incorporating an adaptive weighting mechanism that dynamically balances structural preservation and noise suppression. A joint optimization framework based on the Alternating Direction Method of Multipliers (ADMM) and Augmented Lagrange Multiplier (ALM) algorithms is constructed, in which the core image-updating subproblem is efficiently solved using a momentum-accelerated Two-Dimensional Conjugate Gradient Least Squares (2D-CGLS) method. Numerical simulations and electromagnetic experiments verify that the proposed method preserves target structural integrity under limited modes and strong noise, while effectively improving both computational efficiency and imaging quality.
19
2025, 14(1): 73-90.
Millimeter-wave radar is increasingly being adopted for smart home systems, elder care, and surveillance monitoring, owing to its adaptability to environmental conditions, high resolution, and privacy-preserving capabilities. A key factor in effectively utilizing millimeter-wave radar is the analysis of point clouds, which are essential for recognizing human postures. However, the sparse nature of these point clouds poses significant challenges for accurate and efficient human action recognition. To overcome these issues, we present a 3D point cloud dataset tailored for human actions captured using millimeter-wave radar (mmWave-3DPCHM-1.0). This dataset is enhanced with advanced data processing techniques and cutting-edge human action recognition models. Data collection is conducted using Texas Instruments (TI)’s IWR1443-ISK and Vayyar’s vBlu radio imaging module, covering 12 common human actions, including walking, waving, standing, and falling. At the core of our approach is the Point EdgeConv and Transformer (PETer) network, which integrates edge convolution with transformer models. For each 3D point cloud frame, PETer constructs a locally directed neighborhood graph through edge convolution to extract spatial geometric features effectively. The network then leverages a series of Transformer encoding models to uncover temporal relationships across multiple point cloud frames. Extensive experiments reveal that the PETer network achieves exceptional recognition rates of 98.77% on the TI dataset and 99.51% on the Vayyar dataset, outperforming the traditional optimal baseline model by approximately 5%. With a compact model size of only 1.09 MB, PETer is well-suited for deployment on edge devices, providing an efficient solution for real-time human action recognition in resource-constrained environments.
Millimeter-wave radar is increasingly being adopted for smart home systems, elder care, and surveillance monitoring, owing to its adaptability to environmental conditions, high resolution, and privacy-preserving capabilities. A key factor in effectively utilizing millimeter-wave radar is the analysis of point clouds, which are essential for recognizing human postures. However, the sparse nature of these point clouds poses significant challenges for accurate and efficient human action recognition. To overcome these issues, we present a 3D point cloud dataset tailored for human actions captured using millimeter-wave radar (mmWave-3DPCHM-1.0). This dataset is enhanced with advanced data processing techniques and cutting-edge human action recognition models. Data collection is conducted using Texas Instruments (TI)’s IWR1443-ISK and Vayyar’s vBlu radio imaging module, covering 12 common human actions, including walking, waving, standing, and falling. At the core of our approach is the Point EdgeConv and Transformer (PETer) network, which integrates edge convolution with transformer models. For each 3D point cloud frame, PETer constructs a locally directed neighborhood graph through edge convolution to extract spatial geometric features effectively. The network then leverages a series of Transformer encoding models to uncover temporal relationships across multiple point cloud frames. Extensive experiments reveal that the PETer network achieves exceptional recognition rates of 98.77% on the TI dataset and 99.51% on the Vayyar dataset, outperforming the traditional optimal baseline model by approximately 5%. With a compact model size of only 1.09 MB, PETer is well-suited for deployment on edge devices, providing an efficient solution for real-time human action recognition in resource-constrained environments.
20
2020, 9(5): 803-827.
Flying birds and Unmanned Aerial Vehicles (UAVs) are typical “low, slow, and small” targets with low observability. The need for effective monitoring and identification of these two targets has become urgent and must be solved to ensure the safety of air routes and urban areas. There are many types of flying birds and UAVs that are characterized by low flying heights, strong maneuverability, small radar cross-sectional areas, and complicated detection environments, which are posing great challenges in target detection worldwide. “Visible (high detection ability) and clear-cut (high recognition probability)” methods and technologies must be developed that can finely describe and recognize UAVs, flying birds, and “low-slow-small” targets. This paper reviews the recent progress in research on detection and recognition technologies for rotor UAVs and flying birds in complex scenes and discusses effective detection and recognition methods for the detection of birds and drones, including echo modeling and recognition of fretting characteristics, the enhancement and extraction of maneuvering features in ubiquitous observation mode, distributed multi-view features fusion, differences in motion trajectories, and intelligent classification via deep learning. Lastly, the problems of existing research approaches are summarized, and we consider the future development prospects of target detection and recognition technologies for flying birds and UAVs in complex scenarios.
Flying birds and Unmanned Aerial Vehicles (UAVs) are typical “low, slow, and small” targets with low observability. The need for effective monitoring and identification of these two targets has become urgent and must be solved to ensure the safety of air routes and urban areas. There are many types of flying birds and UAVs that are characterized by low flying heights, strong maneuverability, small radar cross-sectional areas, and complicated detection environments, which are posing great challenges in target detection worldwide. “Visible (high detection ability) and clear-cut (high recognition probability)” methods and technologies must be developed that can finely describe and recognize UAVs, flying birds, and “low-slow-small” targets. This paper reviews the recent progress in research on detection and recognition technologies for rotor UAVs and flying birds in complex scenes and discusses effective detection and recognition methods for the detection of birds and drones, including echo modeling and recognition of fretting characteristics, the enhancement and extraction of maneuvering features in ubiquitous observation mode, distributed multi-view features fusion, differences in motion trajectories, and intelligent classification via deep learning. Lastly, the problems of existing research approaches are summarized, and we consider the future development prospects of target detection and recognition technologies for flying birds and UAVs in complex scenarios.
- First
- Prev
- 1
- 2
- 3
- 4
- 5
- Next
- Last
- Total:5
- To
- Go
微信 | 公众平台 
