Fusheng Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fusheng Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Bakun Zhu
Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China
3 shared publications - Shuge Wang
Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China
2 shared publications - Suqin Wu
Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China
2 shared publications - Wei Qu
Department of Electronic and Optical Engineering, Space Engineering University, Beijing 101416, China
2 shared publications - Hongfeng Pang
Department of Electronic and Optical Engineering, Space Engineering University, Beijing, China
1 shared publication - Jiawei Huang
Space Engineering University, Beijing 101416, China
1 shared publication
Latest Publications
- Open Access
- 16 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (22) , 3930
Physics-Driven Deep Learning for ISAR Imaging of Maneuvering Targets with a Large Rotation Angle
Inverse synthetic aperture radar (ISAR) is important for space target surveillance and recognition. However, under large rotation angles and uniformly accelerated target rotation, coupled high-order migration through range cells (MTRC) and two-dimensional space-variant phase errors cannot be accurately compensated by conventional methods based on small-angle or constant-rotation assumptions, causing image defocusing. To address this, a physics-driven subaperture differentiable back-projection (BP) ISAR imaging network is proposed. It embeds a parametric rotation model with angular velocity and acceleration: taking complex-valued HRRP sequences as input, the full aperture is partitioned into overlapping subapertures, and rotation parameters are regressed by a cross-subaperture parameter estimation network exploiting local scattering structures, temporal correlations, and motion evolution features; a differentiable BP imaging layer unifies rotation transformation, slant-range computation, complex-valued interpolation, phase compensation, and coherent accumulation into differentiable tensor operations, allowing image-domain losses to backpropagate to the parameter estimation module for closed-loop joint optimization of parameter estimation and focusing quality; and a phase registration and quality-guided coherent fusion mechanism adaptively suppresses sidelobes, defocusing, and noise from low-quality subapertures. Experiments on point-scatterer and electromagnetic simulation models demonstrate clear advantages, particularly at low SNR, providing a new path for high-resolution ISAR imaging of large-angle maneuvering targets.
- 16 November 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (22) , 3930
Open AccessPhysics-Driven Deep Learning for ISAR Imaging of Maneuvering Targets with a Large Rotation Angle
Inverse synthetic aperture radar (ISAR) is important for space target surveillance and recognition. However, under large rotation angles and uniformly accelerated target rotation, coupled high-order migration through range cells (MTRC) and two-dimensional space-variant phase errors cannot be accurately compensated by conventional methods based on small-angle or constant-rotation assumptions, causing image defocusing. To address this, a physics-driven subaperture differentiable back-projection (BP) ISAR imaging network is proposed. It embeds a parametric rotation model with angular velocity and acceleration: taking complex-valued HRRP sequences as input, the full aperture is partitioned into overlapping subapertures, and rotation parameters are regressed by a cross-subaperture parameter estimation network exploiting local scattering structures, temporal correlations, and motion evolution features; a differentiable BP imaging layer unifies rotation transformation, slant-range computation, complex-valued interpolation, phase compensation, and coherent accumulation into differentiable tensor operations, allowing image-domain losses to backpropagate to the parameter estimation module for closed-loop joint optimization of parameter estimation and focusing quality; and a phase registration and quality-guided coherent fusion mechanism adaptively suppresses sidelobes, defocusing, and noise from low-quality subapertures. Experiments on point-scatterer and electromagnetic simulation models demonstrate clear advantages, particularly at low SNR, providing a new path for high-resolution ISAR imaging of large-angle maneuvering targets.
- Open Access
Azimuth-Frequency Conditioned Mamba U-Net for ISAR Image Refocusing
High-order phase defocus occurs in ISAR imaging of maneuvering targets. Traditional methods are limited by motion model mismatches, whereas existing deep imaging relies on complex-valued convolutions or self-attention mechanisms, whose excessive computational complexity hinders real-time processing. To address these issues, this paper proposes an Azimuth-Frequency Conditioned Mamba U-Net (AFC-Mamba U-Net) for ISAR image refocusing. The method treats the real and imaginary parts of the defocused complex image as dual-channel real-valued inputs, integrating linear-complexity state-space modeling with cross-layer feature fusion to significantly reduce computational and memory overhead while maintaining high refocusing quality. Specifically, we design an Azimuth-Frequency Conditional Mamba block (AFCMambaBlock), which performs bidirectional selective state-space scanning along the azimuth axis to capture long-range defocus dependencies with linear time complexity, and introduces azimuth-frequency conditional gating to incorporate frequency-domain phase error information into spatial features. A phase-state bottleneck is constructed to aggregate multi-scale enhanced states via a cross-scale state bank, forming globally phase-error-aware representations. Furthermore, we propose a state-guided skip connection mechanism that dynamically gates encoder skip features using bottleneck states, effectively suppressing the propagation of defocus artifacts while reducing redundant computations in the decoder. Experiments conducted on a simulated dataset containing eight types of spaceborne targets and real-world Yak-42 aircraft data demonstrate that the proposed method reduces MSE by 35.8% and NMSE by 41.5% compared to CNN-based U-Net, while achieving an SSIM of 0.9901. Compared to the state-of-the-art complex-domain network CVPHD, the proposed method achieves a significantly better efficiency–accuracy trade-off: it reduces model parameters and computational complexity by approximately two orders of magnitude, improves inference speed by more than fivefold, and cuts GPU memory usage by about 96%, while maintaining competitive structural consistency (SSIM > 0.99). Although CVPHD retains better MSE and NMSE on simulated data, the proposed method provides a lightweight and feasible solution for real-time and embedded ISAR refocusing.
Open AccessAzimuth-Frequency Conditioned Mamba U-Net for ISAR Image Refocusing
High-order phase defocus occurs in ISAR imaging of maneuvering targets. Traditional methods are limited by motion model mismatches, whereas existing deep imaging relies on complex-valued convolutions or self-attention mechanisms, whose excessive computational complexity hinders real-time processing. To address these issues, this paper proposes an Azimuth-Frequency Conditioned Mamba U-Net (AFC-Mamba U-Net) for ISAR image refocusing. The method treats the real and imaginary parts of the defocused complex image as dual-channel real-valued inputs, integrating linear-complexity state-space modeling with cross-layer feature fusion to significantly reduce computational and memory overhead while maintaining high refocusing quality. Specifically, we design an Azimuth-Frequency Conditional Mamba block (AFCMambaBlock), which performs bidirectional selective state-space scanning along the azimuth axis to capture long-range defocus dependencies with linear time complexity, and introduces azimuth-frequency conditional gating to incorporate frequency-domain phase error information into spatial features. A phase-state bottleneck is constructed to aggregate multi-scale enhanced states via a cross-scale state bank, forming globally phase-error-aware representations. Furthermore, we propose a state-guided skip connection mechanism that dynamically gates encoder skip features using bottleneck states, effectively suppressing the propagation of defocus artifacts while reducing redundant computations in the decoder. Experiments conducted on a simulated dataset containing eight types of spaceborne targets and real-world Yak-42 aircraft data demonstrate that the proposed method reduces MSE by 35.8% and NMSE by 41.5% compared to CNN-based U-Net, while achieving an SSIM of 0.9901. Compared to the state-of-the-art complex-domain network CVPHD, the proposed method achieves a significantly better efficiency–accuracy trade-off: it reduces model parameters and computational complexity by approximately two orders of magnitude, improves inference speed by more than fivefold, and cuts GPU memory usage by about 96%, while maintaining competitive structural consistency (SSIM > 0.99). Although CVPHD retains better MSE and NMSE on simulated data, the proposed method provides a lightweight and feasible solution for real-time and embedded ISAR refocusing.
- Open Access
- 16 January 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (2) , 297
Geostationary Orbital Targets Imaging Based on Ground-Based Multiple-Input Multiple-Output Radar
Compared with the Earth’s surface, geostationary orbital (GEO) targets are relatively static, which makes it difficult to obtain two-dimensional radar images when the radar is ground-based without movement. This paper proposes an imaging method for GEO targets based on ground-based Multiple-Input Multiple-Output (MIMO) radar. It combines multiple ground-based radars distributed across the Earth’s surface to image GEO targets. When the virtual aperture of the MIMO radar is planar, three-dimensional imaging results can be obtained. First, the ground-based MIMO radar imaging scenario for GEO targets is introduced, and an analysis of the azimuth resolution is performed. Subsequently, a Three-Dimensional Target-Oriented (TDTO) coordinate system is established. The back-projection (BP) algorithm is then employed to reconstruct the target image. Finally, simulations are conducted and analyzed, including cases of a single-point target, multiple scatterers of a satellite model, and full-wave radar echo simulation using CST. The results show that when the center frequency is 35 GHz, and the baseline length is 1500 km, azimuth resolution of the imaging is better than 0.1 m.
- 16 January 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (2) , 297
Open AccessGeostationary Orbital Targets Imaging Based on Ground-Based Multiple-Input Multiple-Output Radar
Compared with the Earth’s surface, geostationary orbital (GEO) targets are relatively static, which makes it difficult to obtain two-dimensional radar images when the radar is ground-based without movement. This paper proposes an imaging method for GEO targets based on ground-based Multiple-Input Multiple-Output (MIMO) radar. It combines multiple ground-based radars distributed across the Earth’s surface to image GEO targets. When the virtual aperture of the MIMO radar is planar, three-dimensional imaging results can be obtained. First, the ground-based MIMO radar imaging scenario for GEO targets is introduced, and an analysis of the azimuth resolution is performed. Subsequently, a Three-Dimensional Target-Oriented (TDTO) coordinate system is established. The back-projection (BP) algorithm is then employed to reconstruct the target image. Finally, simulations are conducted and analyzed, including cases of a single-point target, multiple scatterers of a satellite model, and full-wave radar echo simulation using CST. The results show that when the center frequency is 35 GHz, and the baseline length is 1500 km, azimuth resolution of the imaging is better than 0.1 m.