Chenxuan Li

Chenxuan Li

Auto-generated profile, based on publicly available information

Chenxuan Li

Beijing Aerospace Command and Control Center, Beijing 100094, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 October 2023 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
CLChenxuan Li
Chenxuan Li
YLYonggang Li
Yonggang Li
WZWeigang Zhu
Weigang Zhu
JYJun Yang
Jun Yang
WQWei Qu
Wei Qu
YHYonghua He
Yonghua He
The application of deep learning to inverse synthetic aperture radar (ISAR) target recognition helps to improve accuracy in space target monitoring. However, the orbit transfer and maneuver of space targets are likely to cause range migration in radar echoes. Information deficiency of scattering points and the limitations of data acquisition methods pose enormous challenges to space target imaging and recognition. To address these issues, this paper proposes a semi-supervised space target recognition algorithm based on an integrated network of imaging and recognition in the radar signal domain. By directly processing radar signals, the algorithm can achieve high-precision space target imaging and recognition under the general situation and the conditions of range migrations. Based on the inherent characteristics of radar complex echoes, the algorithm utilizes unlabeled echoes to generate pseudo labels to achieve better generalization capabilities. Both real and complex convolutions are exploited to generate high-resolution features. Besides, feature optimization modules are designed to effectively integrate high-resolution texture features and contour features to magnify the difference between the target and background. The ablation experiments and contrast experiments indicate that, under the conditions of migration and missing components, the algorithm can obtain high-resolution features for imaging and recognition by only using a small amount of labeled data. Thus, the algorithm achieves high accuracy and robustness for migrated space target recognition and has superiority over other algorithms.

5 June 2024 in Chinese Journal of Aeronautics
Verified
Journal Article
Open access
CLChenxuan Li
Chenxuan Li
WZWeigang Zhu
Weigang Zhu
BZBakun Zhu
Bakun Zhu
YLYonggang Li
Yonggang Li

11 July 2024 in Sensors
Verified
Journal Article
Open access
PDF file
XLXuanchao Li
Xuanchao Li
YHYonghua He
Yonghua He
WZWeigang Zhu
Weigang Zhu
WQWei Qu
Wei Qu
YLYonggang Li
Yonggang Li
BZBakun Zhu
Bakun Zhu
Synthetic Aperture Radar (SAR) is renowned for its all-weather and all-time imaging capabilities, making it invaluable for ship target recognition. Despite the advancements in deep learning models, the efficiency of Convolutional Neural Networks (CNNs) in the frequency domain is often constrained by memory limitations and the stringent real-time requirements of embedded systems. To surmount these obstacles, we introduce the Split_ Composite method, an innovative convolution acceleration technique grounded in Fast Fourier Transform (FFT). This method employs input block decomposition and a composite zero-padding approach to streamline memory bandwidth and computational complexity via optimized frequency-domain convolution and image reconstruction. By capitalizing on FFT’s inherent periodicity to augment frequency resolution, Split_ Composite facilitates weight sharing, curtailing both memory access and computational demands. Our experiments, conducted using the OpenSARShip-4 dataset, confirm that the Split_ Composite method upholds high recognition precision while markedly enhancing inference velocity, especially in the realm of large-scale data processing, thereby exhibiting exceptional scalability and efficiency. When juxtaposed with state-of-the-art convolution optimization technologies such as Winograd and TensorRT, Split_ Composite has demonstrated a significant lead in inference speed without compromising the precision of recognition.

31 May 2024 in Sensors
Verified
Journal Article
Open access
PDF file
RWRundong Wang
Rundong Wang
WZWeigang Zhu
Weigang Zhu
CLChenxuan Li
Chenxuan Li
BZBakun Zhu
Bakun Zhu
HPHongfeng Pang
Hongfeng Pang
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.

26 May 2023
Verified
Conference Paper
Open access
CLChenxuan Li
Chenxuan Li
WZWeigang Zhu
Weigang Zhu
HQHengde Qiu
Hengde Qiu
Identifying the space targets rapidly and accurately is a significant mission in defending national rights and maintaining space security. The continuous emergence of new space targets has led to a dramatic decrease of the performance of Inverse Synthetic Aperture Radar (ISAR) automatic target recognition. This paper proposes a few-shot space target recognition method, which can adaptively excavate the new class features to improve the ISAR target recognition performance. Algorithm proposed in this paper facilitates existing data to predict unseen class and constructs the corresponding feature embedding space, which build the basis for unseen class recognition. Algorithm using memorizing complementary networks to extract global-focus features and local-focus features, which is conductive to increasing recognition accuracy while enhancing feature richness. To address the problem of catastrophic forgetting, this paper proposes an instance mining method based on inductive probability to extract hard-discriminative features at a deep level. Combing with these improving components mentioned above, algorithm of this paper can achieve compatibility and balance between new and old categories effectively. The experimental results demonstrate that algorithm proposed in this paper is superior to other advanced methods in the task of incremental space target recognition.

18 March 2022
Verified
Book Chapter
Closed access
PDF file
CLChenxuan Li
Chenxuan Li
PZPingyun Zhu
Pingyun Zhu
KQKun Qian
Kun Qian
YWYao Wang
Yao Wang