Weigang Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weigang Zhu has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Yonggang Li
Space Engineering University, Beijing 101400, China
5 shared publications - Aoxiang Pan
Space Engineering University, Beijing 101400, China
4 shared publications - Jiahao Wang
Space Engineering University, Beijing 101400, China
4 shared publications - Yonghua He
Space Engineering University, Beijing 101400, China
4 shared publications - Wei Qu
Space Engineering University, Beijing 101400, China
3 shared publications - Wenhang Ji
Space Engineering University, Beijing 101400, China
3 shared publications
Latest Publications
- Open Access
ISAR-Mamba: A Dual-Stream Gated Mamba with Hierarchical Spatial Summaries for ISAR Image Captioning
Inverse Synthetic Aperture Radar (ISAR) imagery plays a crucial role in space situational awareness, yet its interpretation remains largely confined to tasks such as classification and segmentation, lacking the ability to generate detailed natural language captions. To address this limitation, this paper proposes ISARCap 1.0, the first dataset specifically designed for ISAR image captioning, covering 38 classes of space targets and comprising 102,965 simulated images and 514,825 image–text pairs. On this basis, this paper proposes ISAR-Mamba, a dual-stream gated state space model for ISAR image captioning. The model introduces a Dual-Stream Asymmetric Encoder (DSAE), which performs complementary patch partitioning and scanning along the range and azimuth dimensions, respectively, to accommodate the physical dimensional differences of ISAR images. Meanwhile, a Sparsity-Aware Gating Mechanism (SAGM) is introduced, which jointly suppresses the interference of empty patches on state updates by leveraging scattering energy priors and a learnable scoring module. Furthermore, a Hierarchical Spatial Summarization (HSS) strategy is proposed to extract structured summary tokens from different depths and spatial regions of the encoder, thereby enhancing visual information perception during text sequence generation. Experimental results on the ISARCap 1.0 dataset indicate that ISAR-Mamba outperforms existing image captioning methods on multiple metrics, suggesting the effectiveness of the proposed method and the usability of the dataset.
Open AccessISAR-Mamba: A Dual-Stream Gated Mamba with Hierarchical Spatial Summaries for ISAR Image Captioning
Inverse Synthetic Aperture Radar (ISAR) imagery plays a crucial role in space situational awareness, yet its interpretation remains largely confined to tasks such as classification and segmentation, lacking the ability to generate detailed natural language captions. To address this limitation, this paper proposes ISARCap 1.0, the first dataset specifically designed for ISAR image captioning, covering 38 classes of space targets and comprising 102,965 simulated images and 514,825 image–text pairs. On this basis, this paper proposes ISAR-Mamba, a dual-stream gated state space model for ISAR image captioning. The model introduces a Dual-Stream Asymmetric Encoder (DSAE), which performs complementary patch partitioning and scanning along the range and azimuth dimensions, respectively, to accommodate the physical dimensional differences of ISAR images. Meanwhile, a Sparsity-Aware Gating Mechanism (SAGM) is introduced, which jointly suppresses the interference of empty patches on state updates by leveraging scattering energy priors and a learnable scoring module. Furthermore, a Hierarchical Spatial Summarization (HSS) strategy is proposed to extract structured summary tokens from different depths and spatial regions of the encoder, thereby enhancing visual information perception during text sequence generation. Experimental results on the ISARCap 1.0 dataset indicate that ISAR-Mamba outperforms existing image captioning methods on multiple metrics, suggesting the effectiveness of the proposed method and the usability of the dataset.
- Open Access
Semi-Supervised Structural Prior-Guided Network for Space Target Component Segmentation in ISAR Images
Segmenting key components of space targets using Inverse Synthetic Aperture Radar (ISAR) images is an important interpretation task in space situational awareness. However, the scarcity of pixel-level annotated data, inter-class confusion caused by morphological differences among multiple target classes, and the absence of structural priors for components restrict the performance improvement in existing deep models on this task. Therefore, this paper proposes a Semi-Supervised Structural Prior-Guided Network (SSPNet). First, a Gated Manifold-Constrained Hyper-Connections Vision Transformer (GMHC-ViT) encoder is proposed to broaden the feature representation space via parallel multi-feature streams with adaptive gating, thereby alleviating inter-class confusion and enhancing cross-category generalization. Second, a Prior-Guided Module (PGM) is proposed to extract shape and edge priors of components, and it adaptively enhances the weakly activated channels of encoder features through cross-attention, thereby injecting structural knowledge independent of image quality into the segmentation process. Furthermore, to effectively leverage large amounts of unlabeled data, a strong perturbation strategy tailored to the characteristics of ISAR images is designed for consistency regularization. Experimental results on a simulated ISAR dataset containing 38 classes of space targets demonstrate that SSPNet outperforms existing methods and exhibits strong segmentation capability even under low signal-to-noise ratio (SNR) conditions.
Open AccessSemi-Supervised Structural Prior-Guided Network for Space Target Component Segmentation in ISAR Images
Segmenting key components of space targets using Inverse Synthetic Aperture Radar (ISAR) images is an important interpretation task in space situational awareness. However, the scarcity of pixel-level annotated data, inter-class confusion caused by morphological differences among multiple target classes, and the absence of structural priors for components restrict the performance improvement in existing deep models on this task. Therefore, this paper proposes a Semi-Supervised Structural Prior-Guided Network (SSPNet). First, a Gated Manifold-Constrained Hyper-Connections Vision Transformer (GMHC-ViT) encoder is proposed to broaden the feature representation space via parallel multi-feature streams with adaptive gating, thereby alleviating inter-class confusion and enhancing cross-category generalization. Second, a Prior-Guided Module (PGM) is proposed to extract shape and edge priors of components, and it adaptively enhances the weakly activated channels of encoder features through cross-attention, thereby injecting structural knowledge independent of image quality into the segmentation process. Furthermore, to effectively leverage large amounts of unlabeled data, a strong perturbation strategy tailored to the characteristics of ISAR images is designed for consistency regularization. Experimental results on a simulated ISAR dataset containing 38 classes of space targets demonstrate that SSPNet outperforms existing methods and exhibits strong segmentation capability even under low signal-to-noise ratio (SNR) conditions.
- Open Access
CD-TrGNN: A Complex-Domain Transformer–Graph Neural Network for ISAR Space Target Attitude Estimation
In ground-based space surveillance, space target attitude estimation is critical for space situational awareness, yet existing methods based on inverse synthetic aperture radar (ISAR) images suffer from three core limitations: phase information is discarded in amplitude-only processing, convolutional neural networks have a restricted global receptive field, and the physical topology of satellite components is not explicitly modeled. To address these issues, we propose a complex-domain Transformer–graph neural network (CD-TrGNN) that unifies global context modeling and adaptive topological reasoning in an end-to-end framework. Specifically, a complex-domain Transformer module (CD-Transformer) with tailored attention captures long-range dependencies among image patches while preserving both amplitude and phase information; a complex-domain graph convolution module (CD-GC) with learnable adjacency matrices and a dual-path update mechanism explicitly encodes the structural relationships among satellite parts. On a self-built ISAR complex image dataset, CD-TrGNN achieves a three-axis mean absolute error of only 1.70°, substantially outperforming six representative baselines. Ablation experiments confirm the effectiveness of complex-domain processing, global attention, and topological reasoning. At a 5 dB signal-to-noise ratio, the error remains at 2.81°, and the accuracy stays below 2° for two different satellite structures. These results demonstrate that CD-TrGNN can fully exploit the information in ISAR complex images, enabling high-accuracy and highly robust attitude estimation.
Open AccessCD-TrGNN: A Complex-Domain Transformer–Graph Neural Network for ISAR Space Target Attitude Estimation
In ground-based space surveillance, space target attitude estimation is critical for space situational awareness, yet existing methods based on inverse synthetic aperture radar (ISAR) images suffer from three core limitations: phase information is discarded in amplitude-only processing, convolutional neural networks have a restricted global receptive field, and the physical topology of satellite components is not explicitly modeled. To address these issues, we propose a complex-domain Transformer–graph neural network (CD-TrGNN) that unifies global context modeling and adaptive topological reasoning in an end-to-end framework. Specifically, a complex-domain Transformer module (CD-Transformer) with tailored attention captures long-range dependencies among image patches while preserving both amplitude and phase information; a complex-domain graph convolution module (CD-GC) with learnable adjacency matrices and a dual-path update mechanism explicitly encodes the structural relationships among satellite parts. On a self-built ISAR complex image dataset, CD-TrGNN achieves a three-axis mean absolute error of only 1.70°, substantially outperforming six representative baselines. Ablation experiments confirm the effectiveness of complex-domain processing, global attention, and topological reasoning. At a 5 dB signal-to-noise ratio, the error remains at 2.81°, and the accuracy stays below 2° for two different satellite structures. These results demonstrate that CD-TrGNN can fully exploit the information in ISAR complex images, enabling high-accuracy and highly robust attitude estimation.
- Open Access
Complex-Domain Semantic Segmentation of Spacecraft Directly from ISAR Echoes
Semantic segmentation technology based on Inverse Synthetic Aperture Radar (ISAR) images can provide crucial perception and analytical capabilities for intelligent safety maintenance of on-orbit spacecraft. However, conventional semantic segmentation methods suffer from three main limitations: firstly, the lack of modeling for radar physical characteristics in the “image first, segment later” pipeline leads to loss of scattering information and phase details; secondly, reliance on extensive pixel-level manual annotation increases application costs; thirdly, ineffective utilization of spacecraft structural priors fails to guide networks to focus on the main body and edges of spacecraft segmentation. To address these issues, this paper proposes a complex-domain semantic segmentation framework named One-Stop Segmentation (OSS) based on ISAR echoes. The framework incorporates two innovative modules: an Automatic ISAR Labeling (AIL) method designed based on ISAR scattering characteristics to generate labels corresponding to ISAR echoes, and a complex-domain semantic segmentation network named One-Stop Segmentation Network (OSSNet) that performs semantic segmentation directly on echoes, avoiding information loss from imaging while shortening the data processing chain. Core contributions of OSSNet include: (1) a Domain Alignment Module (DAM) to effectively mitigate domain mismatch caused by data distribution differences between raw echo signals and labels; (2) a Multi-Perspective Attention (MPA) framework incorporating a Sliding Correlation Attention (SCA) module and a Subdomain Balanced Attention (SBA) module, lever-aging spacecraft structural priors to guide the network’s focus on main structures and edge details from complementary perspectives, significantly improving segmentation ac-curacy. Experimental results on a simulated ground-based radar dataset demonstrate that the proposed OSS framework achieves a mean Intersection over Union (mIoU) of 92.13% and a mean F1-score of 95.75% in ISAR spacecraft semantic segmentation tasks, outperforming existing methods.
Open AccessComplex-Domain Semantic Segmentation of Spacecraft Directly from ISAR Echoes
Semantic segmentation technology based on Inverse Synthetic Aperture Radar (ISAR) images can provide crucial perception and analytical capabilities for intelligent safety maintenance of on-orbit spacecraft. However, conventional semantic segmentation methods suffer from three main limitations: firstly, the lack of modeling for radar physical characteristics in the “image first, segment later” pipeline leads to loss of scattering information and phase details; secondly, reliance on extensive pixel-level manual annotation increases application costs; thirdly, ineffective utilization of spacecraft structural priors fails to guide networks to focus on the main body and edges of spacecraft segmentation. To address these issues, this paper proposes a complex-domain semantic segmentation framework named One-Stop Segmentation (OSS) based on ISAR echoes. The framework incorporates two innovative modules: an Automatic ISAR Labeling (AIL) method designed based on ISAR scattering characteristics to generate labels corresponding to ISAR echoes, and a complex-domain semantic segmentation network named One-Stop Segmentation Network (OSSNet) that performs semantic segmentation directly on echoes, avoiding information loss from imaging while shortening the data processing chain. Core contributions of OSSNet include: (1) a Domain Alignment Module (DAM) to effectively mitigate domain mismatch caused by data distribution differences between raw echo signals and labels; (2) a Multi-Perspective Attention (MPA) framework incorporating a Sliding Correlation Attention (SCA) module and a Subdomain Balanced Attention (SBA) module, lever-aging spacecraft structural priors to guide the network’s focus on main structures and edge details from complementary perspectives, significantly improving segmentation ac-curacy. Experimental results on a simulated ground-based radar dataset demonstrate that the proposed OSS framework achieves a mean Intersection over Union (mIoU) of 92.13% and a mean F1-score of 95.75% in ISAR spacecraft semantic segmentation tasks, outperforming existing methods.
- Open Access
A Method for Few-Shot Radar Target Recognition Based on Multimodal Feature Fusion
Enhancing generalization capabilities and robustness in scenarios with limited sample sizes, while simultaneously decreasing reliance on extensive and high-quality datasets, represents a significant area of inquiry within the domain of radar target recognition. This study introduces a few-shot learning framework that leverages multimodal feature fusion. We develop a cross-modal representation optimization mechanism tailored for the target recognition task by incorporating natural resonance frequency features that elucidate the target’s scattering characteristics. Furthermore, we establish a multimodal fusion classification network that integrates bi-directional long short-term memory and residual neural network architectures, facilitating deep bimodal fusion through an encoding-decoding framework augmented by an energy embedding strategy. To optimize the model, we propose a cross-modal equilibrium loss function that amalgamates similarity metrics from diverse features with cross-entropy loss, thereby guiding the optimization process towards enhancing metric spatial discrimination and balancing classification performance. Empirical results derived from simulated datasets indicate that the proposed methodology achieves a recognition accuracy of 95.36% in the 5-way 1-shot task, surpassing traditional unimodal image and concatenation fusion feature approaches by 2.26% and 8.73%, respectively. Additionally, the inter-class feature separation is improved by 18.37%, thereby substantiating the efficacy of the proposed method.
Open AccessA Method for Few-Shot Radar Target Recognition Based on Multimodal Feature Fusion
Enhancing generalization capabilities and robustness in scenarios with limited sample sizes, while simultaneously decreasing reliance on extensive and high-quality datasets, represents a significant area of inquiry within the domain of radar target recognition. This study introduces a few-shot learning framework that leverages multimodal feature fusion. We develop a cross-modal representation optimization mechanism tailored for the target recognition task by incorporating natural resonance frequency features that elucidate the target’s scattering characteristics. Furthermore, we establish a multimodal fusion classification network that integrates bi-directional long short-term memory and residual neural network architectures, facilitating deep bimodal fusion through an encoding-decoding framework augmented by an energy embedding strategy. To optimize the model, we propose a cross-modal equilibrium loss function that amalgamates similarity metrics from diverse features with cross-entropy loss, thereby guiding the optimization process towards enhancing metric spatial discrimination and balancing classification performance. Empirical results derived from simulated datasets indicate that the proposed methodology achieves a recognition accuracy of 95.36% in the 5-way 1-shot task, surpassing traditional unimodal image and concatenation fusion feature approaches by 2.26% and 8.73%, respectively. Additionally, the inter-class feature separation is improved by 18.37%, thereby substantiating the efficacy of the proposed method.
- Open Access
Wavenumber-Domain Joint Estimation of Rotation Parameters and Scene Center Offset for Large-Angle ISAR Cross-Range Scaling
While the wavenumber-domain approach enables large-angle inverse synthetic aperture radar (ISAR) cross-range scaling, its practical application remains constrained by the target’s non-uniform rotation and scene center offset (SCO). In response to this issue, this paper introduces a novel large-angle ISAR cross-range scaling method through a joint estimation method based on the wavenumber domain. A non-uniform rotational wavenumber-domain signal model with SCO is developed. Utilizing this model and the sensitivity of wavenumber-domain imaging to SCO, a joint estimation algorithm that combines particle swarm optimization (PSO) and image entropy evaluation is proposed, achieving accurate parameter estimation. Leveraging the estimated parameters, the range and cross-range scaling factors in the wavenumber-domain imaging are derived, facilitating ISAR cross-range scaling with higher accuracy than the traditional method. The effectiveness and robustness of the proposed method are validated under various conditions, through scattering point and electromagnetic computing simulation.
Open AccessWavenumber-Domain Joint Estimation of Rotation Parameters and Scene Center Offset for Large-Angle ISAR Cross-Range Scaling
While the wavenumber-domain approach enables large-angle inverse synthetic aperture radar (ISAR) cross-range scaling, its practical application remains constrained by the target’s non-uniform rotation and scene center offset (SCO). In response to this issue, this paper introduces a novel large-angle ISAR cross-range scaling method through a joint estimation method based on the wavenumber domain. A non-uniform rotational wavenumber-domain signal model with SCO is developed. Utilizing this model and the sensitivity of wavenumber-domain imaging to SCO, a joint estimation algorithm that combines particle swarm optimization (PSO) and image entropy evaluation is proposed, achieving accurate parameter estimation. Leveraging the estimated parameters, the range and cross-range scaling factors in the wavenumber-domain imaging are derived, facilitating ISAR cross-range scaling with higher accuracy than the traditional method. The effectiveness and robustness of the proposed method are validated under various conditions, through scattering point and electromagnetic computing simulation.
- Open Access
PP-ISEA: An Efficient Algorithm for High-Resolution Three-Dimensional Geometry Reconstruction of Space Targets Using Limited Inverse Synthetic Aperture Radar Images
As the variety of space targets expands, two-dimensional (2D) ISAR images prove insufficient for target recognition, necessitating the extraction of three-dimensional (3D) information. The 3D geometry reconstruction method utilizing energy accumulation of ISAR image sequence (ISEA) facilitates superior reconstruction while circumventing the laborious steps associated with factorization methods. Nevertheless, ISEA’s neglect of valid information necessitates a high quantity of images and elongated operation times. This paper introduces a partitioned parallel 3D reconstruction method utilizing sorted-energy semi-accumulation with ISAR image sequences (PP-ISEA) to address these limitations. The PP-ISEA innovatively incorporates a two-step search pattern—coarse and fine—that enhances search efficiency and conserves computational resources. It introduces a novel objective function ‘sorted-energy semi-accumulation’ to discern genuine scatterers from spurious ones and establishes a redundant point exclusion module. Experiments on the scatterer model and simulated electromagnetic model demonstrate that the PP-ISEA reduces the minimum image requirement from ten to four for high-quality scatterer model reconstruction, thereby offering superior reconstruction quality in less time.
Open AccessPP-ISEA: An Efficient Algorithm for High-Resolution Three-Dimensional Geometry Reconstruction of Space Targets Using Limited Inverse Synthetic Aperture Radar Images
As the variety of space targets expands, two-dimensional (2D) ISAR images prove insufficient for target recognition, necessitating the extraction of three-dimensional (3D) information. The 3D geometry reconstruction method utilizing energy accumulation of ISAR image sequence (ISEA) facilitates superior reconstruction while circumventing the laborious steps associated with factorization methods. Nevertheless, ISEA’s neglect of valid information necessitates a high quantity of images and elongated operation times. This paper introduces a partitioned parallel 3D reconstruction method utilizing sorted-energy semi-accumulation with ISAR image sequences (PP-ISEA) to address these limitations. The PP-ISEA innovatively incorporates a two-step search pattern—coarse and fine—that enhances search efficiency and conserves computational resources. It introduces a novel objective function ‘sorted-energy semi-accumulation’ to discern genuine scatterers from spurious ones and establishes a redundant point exclusion module. Experiments on the scatterer model and simulated electromagnetic model demonstrate that the PP-ISEA reduces the minimum image requirement from ten to four for high-quality scatterer model reconstruction, thereby offering superior reconstruction quality in less time.