BZBingchen Zhang

Bingchen Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bingchen Zhang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hyper-ISTA-GHD: An Adaptive Hyperparameter Selection Framework for Highly Squinted Mode Sparse SAR Imaging

    by Tiancheng Chen, Bailing Ding, Heli Gao, Lei Liu, Bingchen Zhang, Yirong Wu

    The highly squinted mode, as an operational configuration of synthetic aperture radar (SAR), fulfills specific remote sensing demands. Under equivalent conditions, it necessitates a higher pulse repetition frequency (PRF) than the side-looking mode but produces inferior imaging quality, thereby constraining its widespread application. By applying the sparse SAR imaging method to highly squinted SAR systems, imaging quality can be enhanced while simultaneously reducing PRF requirements and expanding swath. Hyperparameters in sparse SAR imaging critically influence reconstruction quality and computational efficiency, making hyperparameter optimization (HPO) a persistent research focus. Inspired by HPO techniques in the deep unfolding network (DUN), we modified the iterative soft-thresholding algorithm (ISTA) employed in fast sparse SAR reconstruction based on approximate observation operators. Our adaptation enables adaptive regularization parameter tuning during iterations while accelerating convergence. To improve the robustness of this enhanced algorithm under realistic SAR echoes with noise, we integrated hypergradient descent (HD) to automatically adjust the ISTA step size after regularization parameter convergence, thereby mitigating overfitting. The proposed method, named Hyper-ISTA-GHD, adaptively selects regularization parameters and step sizes. It achieves high-precision, rapid imaging for highly squinted SAR. Owing to its training-free iterative minimization framework, this approach exhibits superior generalization capabilities compared to existing DUN methods and demonstrates broad applicability across diverse SAR imaging modes and scene characteristics. Simulations show that the hyperparameter selection and reconstruction results of the proposed method are almost consistent with the optimal values of traditional methods under different signal-to-noise ratios and sampling rates, but the time consumption is only one-tenth of that of traditional methods. Comparative experiments on the generalization performance with DUN show that the generalization performance of the proposed method is significantly better than DUN in extremely sparse scenarios.

  • Open Access

    Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection

    by Yanxing Liu, Jiancheng Pan, Bingchen Zhang

    Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited training data makes it difficult to represent the data distribution of realistic remote sensing scenes, which results in the notorious overfitting problem. Current researchers have begun to enhance the diversity of few-shot novel instances by leveraging diffusion models to solve the overfitting problem. However, naively increasing the diversity of objects is insufficient, as surrounding contexts also play a crucial role in object detection, and in cases where the object diversity is sufficient, the detector tends to overfit to monotonous contexts. Accordingly, we propose Control Copy-Paste, a controllable diffusion-based method to enhance the performance of FSOD by leveraging diverse contextual information. Specifically, we seamlessly inject a few-shot novel objects into images with diverse contexts by a conditional diffusion model. We also develop an orientation alignment strategy to mitigate the integration distortion caused by varying aspect ratios of instances. Experiments on the public DIOR dataset demonstrate that our method can improve detection performance by an average of 10.76%.

  • Open Access

    Undistorted and Consistent Enhancement of Automotive SAR Image via Multi-Segment-Reweighted Regularization

    by Yan Zhang, Bingchen Zhang, Yirong Wu

    In recent years, synthetic aperture radar (SAR) technology has been increasingly explored for automotive applications. However, automotive SAR images generated via matched filter (MF) often exhibit challenges such as noisy backgrounds, sidelobe artifacts, and limited resolution. Sparse regularization methods have the potential to enhance image quality. Nevertheless, conventional unweighted l1 regularization methods struggle to address cases with radar cross section (RCS) distributed over a wide dynamic range, often resulting in insufficient sidelobe suppression, amplitude distortion, and inconsistent super-resolution performance. In this paper, we propose a novel reweighted regularization method, termed multi-segment-reweighted regularization (MSR), for automotive SAR image restoration. By introducing a novel weighting scheme, MSR localizes the global scattering point enhancement problem to the mainlobe scale, effectively mitigating sidelobe interference. This localization ensures consistent enhancement capability independent of RCS variations. Furthermore, MSR employs multi-segment regularization to constrain amplitude within the mainlobes, preserving the characteristics of the original response. Correspondingly, a new thresholding function, named Thinner Response Undistorted THresholding (TRUTH), is introduced. An iterative algorithm for enhancing automotive SAR images using MSR is also presented. Real data experiments validate the feasibility and effectiveness of the proposed method.


  • Open Access

    Undistorted and Consistent Enhancement of Automotive SAR Image via Multi-Segment-Reweighted Regularization

    by Yan Zhang, Bingchen Zhang, Yirong Wu

    In recent years, synthetic aperture radar (SAR) technology has been increasingly explored for automotive applications. However, automotive SAR images generated via the matched filter (MF) often exhibit challenges such as noisy backgrounds, sidelobe artifacts, and limited resolution. Sparse regularization methods ave the potential to enhance image quality. Nevertheless, conventional unweighted ℓ1 regularization methods struggle to address cases with radar cross section (RCS) distributed over a wide dynamic range, often resulting in insufficient sidelobe suppression, amplitude distortion, and inconsistent super-resolution performance. In this paper, we propose a novel reweighted regularization method, termed Multi-Segment-Reweighted Regularization (MSR), for automotive SAR image restoration. By introducing a novel weighting scheme, MSR localizes the global scattering point enhancement problem to the mainlobe scale, effectively mitigating sidelobe interference. This localization ensures consistent enhancement capability independent of RCS variations. Furthermore, MSR employs multi-segment regularization to constrain amplitude within the mainlobes, preserving the characteristics of the original response. Correspondingly, a new thresholding function, named Thinner Response Undistorted THresholding (TRUTH), is introduced. An iterative algorithm for enhancing automotive SAR images using MSR is also presented. Real data experiments validate the feasibility and effectiveness of the proposed method.


  • Open Access

    A Novel Gridless Non-Uniform Linear Array Direction of Arrival Estimation Approach Based on the Improved Alternating Descent Conditional Gradient Algorithm for Automotive Radar System

    by Mingxiao Shao, Yizhe Fan, Yan Zhang, Zhe Zhang, Jie Zhao, Bingchen Zhang

    In automotive millimeter-wave (MMW) radar systems, achieving high-precision direction of arrival (DOA) estimation with a limited number of array elements is a crucial research focus. Compressive sensing (CS) techniques have been demonstrated to offer superior performance in DOA estimation compared to spectral estimation methods. However, traditional CS methods suffer from an off-grid effect, which causes their reconstruction results to deviate from the actual positions of the signal sources, thereby reducing the accuracy. Currently, as a gridless method, atomic norm minimization (ANM) has shown effectiveness in DOA estimation for uniform linear arrays (ULAs). However, the performance of ANM is suboptimal in non-uniform linear arrays (NULAs), and their computational efficiency is not satisfactory. In this paper, we propose a novel algorithm for DOA estimation in NULA, drawing inspiration from the alternating descent conditional gradient algorithm framework. First, we construct an atomic set based on the observation scene and select the atoms with the highest correlation to the residuals as potential signal sources for global estimation. Then, we construct a mapping function for the signal sources in the continuous domain and perform conditional gradient descent in the neighborhood of each signal source, addressing the bias introduced by the off-grid effect. We compared the proposed algorithm with ANM, Iterative Shrinkage Thresholding (IST), and Multiple Signal Classification (MUSIC) algorithms. Simulation experiments validate that the proposed algorithm effectively addresses the off-grid effect and is applicable to DOA estimation in coprime and random arrays. Furthermore, real data experiments confirm the effectiveness of the proposed algorithm.


  • Open Access

    Gridless DOA Estimation with Extended Array Aperture in Automotive Radar Applications

    by Pengyu Jiang, Silin Gao, Jie Zhao, Zhe Zhang, Bingchen Zhang

    Millimeter-wave automotive radar has become an essential tool for autonomous driving, providing reliable sensing capabilities under various environmental conditions. To reduce hardware size and cost, sparse arrays are widely employed in automotive radar systems. Additionally, because the targets detected by automotive radar typically exhibit sparsity, compressed sensing-based algorithms have been utilized for sparse array reconstruction, achieving superior performance. However, traditional compressed sensing algorithms generally assume that targets are located on a finite set of grid points and perform sparse reconstruction based on predefined grids. When targets are off-grid, significant off-grid errors can occur. To address this issue, we propose an automotive radar sparse reconstruction algorithm based on accelerated Atomic Norm Minimization (ANM). By using the Iterative Vandermonde Decomposition and Shrinkage Threshold (IVDST) algorithm, we can achieve fast ANM, which effectively mitigates off-grid errors while reducing reconstruction complexity. Furthermore, we adopt a Generalized Likelihood Ratio Test (GLRT) detector to eliminate noise and clutter in the automotive radar operating environment. Simulation results show that our proposed algorithm significantly improves reconstruction accuracy compared to the iterative soft threshold (IST) algorithm while maintaining the same computational complexity. The effectiveness of the proposed algorithm in practical applications is further validated through real-world data experiments, demonstrating its superior capability in clutter elimination.


  • Open Access

    Multi-Modal Prototypes for Few-Shot Object Detection in Remote Sensing Images

    by Yanxing Liu, Zongxu Pan, Jianwei Yang, Peiling Zhou, Bingchen Zhang

    Few-shot object detection has attracted extensive attention due to the abomination of time-consuming or even impractical large-scale data labeling. Current studies attempted to employ prototype-matching approaches for object detection, constructing class prototypes from textual or visual features. However, single visual prototypes exhibit limited generalization in few-shot scenarios, while single textual prototypes lack the spatial details of remote sensing targets. Therefore, to achieve the best of both worlds, we propose a prototype aggregating module to integrate textual and visual prototypes, leveraging both semantics from textual prototypes and spatial details from visual prototypes. In addition, the transferability of multi-modal few-shot detectors from natural scenarios to remote sensing scenarios remains unexplored, and previous training strategies for FSOD do not adequately consider the characteristics of text encoders. To address the issue, we have conducted extensive ablation studies on different feature extractors of the detector and propose an efficient two-stage training strategy, which takes the characteristics of the text feature extractor into account. Experiments on two common few-shot detection benchmarks demonstrate the effectiveness of our proposed method. In four widely used data splits of DIOR, our method significantly outperforms previous state-of-the-art methods by at most 8.7%.


  • Morphology Regularization for TomoSAR in Urban Areas With Ultrahigh-Resolution SAR Images

    by Jie Li, Bingchen Zhang, Zhiyuan Li, Meng Qi, Kun Wang, Yirong Wu

    The current synthetic aperture radar (SAR) images with ultra high resolution provide the detailed structures of the urban areas. Utilizing stacks of the ultra high-resolution SAR images acquired with different view angles, tomographic synthetic aperture radar (TomoSAR) becomes an advanced technique to retrieve 3D spatial information of the detailed structures which presents the efficient density in the point clouds. The technique is a sparse reconstruction problem indeed and can be solved by compressive sensing (CS) algorithms. However, conventional CS algorithms process the pixel independently and the detailed structures of the targets are easily lost followed by the sparsity constraints. In this paper, we apply the morphology regularization as a prior term to form a novel approach based on the CS algorithm. The morphology regularization enhances the detailed 3D structural properties of targets, which can shrink the concatenations caused by outliers in the iterative reconstruction. As for the optimization algorithm for tomographic inversion, we apply the framework of the alternating direction method of multipliers (ADMM), where the Bregman iteration is adopted for solving the sub-problem with the morphology regularization. Both simulation experiments and tests on real data show that the proposed method can suppress the outliers and guarantee the detection rate, leading to excellent correctness and completeness.


  • Open Access

    A Sparse SAR Imaging Method for Low-Oversampled Staggered Mode via Compound Regularization

    by Mingqian Liu, Jie Pan, Jinbiao Zhu, Zhengchao Chen, Bingchen Zhang, Yirong Wu

    High-resolution wide-swath (HRWS) imaging is the research focus of the modern spaceborne synthetic-aperture radar (SAR) imaging field, with significant relevance and vast application potential. Staggered SAR, as an innovative imaging system, mitigates blind areas across the entire swath by periodically altering the radar pulse repetition interval (PRI), thereby extending the swath width to multiples of that achievable by conventional systems. However, the staggered mode introduces inherent challenges, such as nonuniform azimuth sampling and echo data loss, leading to azimuth ambiguities and substantially impacting image quality. This paper proposes a sparse SAR imaging method for the low-oversampled staggered mode via compound regularization. The proposed method not only effectively suppresses azimuth ambiguities arising from nonuniform sampling without necessitating the restoration of missing echo data, but also incorporates total variation (TV) regularization into the sparse reconstruction model. This enhances the accurate reconstruction of distributed targets within the scene. The efficacy of the proposed method is substantiated through simulations and real data experiments from spaceborne missions.


  • Open Access

    An Accurate and Efficient BP Algorithm Based on Precise Slant Range Model and Rapid Range History Construction Method for GEO SAR

    by Yifan Wu, Lijia Huang, Bingchen Zhang, Xiaochen Wang, Xiyu Qi

    The Geosynchronous Satellite Synthetic Aperture Radar (GEO SAR) operates at a high orbital altitude, resulting in an extended imaging time and substantial variations in slant range. Additionally, the GEO SAR satellite orbit experiences a bending effect, and the target’s movement, caused by the Earth’s rotation, is influenced by the Earth’s curvature. The back-projection (BP) algorithm has been proven to be a highly effective technique for precise imaging with GEO SAR by processing these specific echo signals. However, this approach necessitates considerable computational resources. Existing BP algorithms, such as the fast BP algorithm, do not consider the “Stop-and-Go” error present in GEO SAR. Consequently, we developed a Precise Slant Range Model that considers the motion of both the satellite and targets. The model incorporates velocity and acceleration factors to accurately represent the signal transmission from transmission to reception. Additionally, we propose a Rapid Range History Construction Method to lessen the computational burden of generating the three-dimensional range history array. By utilizing the Precise Slant Range Model and the Rapid Range History Construction Method, and employing parallel processing through aperture segmentation, we propose an Accurate and Efficient BP imaging algorithm suitable for GEO SAR applications. To validate its effectiveness, simulations were conducted using the parameters of a GEO SAR system. The results indicated that the proposed algorithm enhances the imaging quality of GEO SAR, reduces the processing time, and achieves high-precision rapid imaging, thereby improving operational efficiency.