Yuyuan Fang

Yuyuan Fang

Auto-generated profile, based on publicly available information

Yuyuan Fang

Southwest Jiaotong University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
22 November 2023 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
SWSong Wei
Song Wei
YFYuyuan Fang
Yuyuan Fang
YSYuxiao Song
Yuxiao Song
SWShaopeng Wei
Shaopeng Wei
LZLei Zhang
Lei Zhang
Recently, interrupted sampling repeater jamming (ISRJ) based on digital radio frequency memory (DRFM), which could easily form high-power false targets, has severely impacted radar detection capabilities. Conventional anti-ISRJ techniques ignore the operating characteristics of the jammer. Once the anti-ISRJ algorithm and the features of the jammer are mismatched, undesirable jamming residues or signal loss appear. In order to avoid these unwanted performance losses, an algorithm jointing the jam perception and the adaptive waveform is developed in this paper. First, a bi-directional Constant False Alarm Rate (CFAR) detector is introduced to locate and estimate the jamming component in radar echo. An ISRJ feature vector is then built to reconstruct and cancel jamming components for accurate detection under ISRJ. Second, an adaptive anti-ISRJ waveform is developed based on the vector, leading the DRFM to retransmit signals orthogonal to the real detection signal. Besides, the particle swarm optimization (PSO) algorithm efficiently works out the optimal waveform parameters to improve the suppression performance. As radar switches to the adaptive anti-ISRJ waveform, long-term suppression of ISRJ is achieved without locating, estimating, and suppressing the ISRJ components in each echo. Simulated experiments demonstrate that the suggested algorithm can accurately detect radar targets under ISRJ.

5 August 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YFYuyuan Fang
Yuyuan Fang
JHJun Hu
Jun Hu
CDChuan Du
Chuan Du
ZLZhibo Liu
Zhibo Liu
LZLei Zhang
Lei Zhang
The main difficulty of synthetic aperture radar (SAR)-optical image matching or registration lies in the significant heterogeneous characteristics introduced by the different imaging mechanisms between SAR and optical images. Instead of directly using the raw image pair, transforming the pair into a feature domain, where they have homogeneous feature representation, is believed more effective. Inspired by image segmentation, we develop an end-to-end deep learning model for the SAR-optical matching, based on a siamese U-net with a fast Fourier transform (FFT) correlation layer. First, the siamese U-net with sharing weights extracts the feature maps of the SAR and optical images and projects the heterogeneous images into a homogeneous space. Then, the two feature maps are cross-correlated or normalized cross-correlated by the FFT layer and a similarity heatmap is obtained. Finally, the heatmap is send into a softmax2d classifier to determine the best matching, and thus matching is converted into classification. The nonlinear mapping capability of deep learning can well tackle the intensity variation across the different imaging modals; the encoder–decoder architecture with skip connections in the U-net can take full advantage of the global information and simultaneously preserve the local resolution and position information and thus guarantees high accuracy and robustness; besides, the FFT correlation is helpful for the efficiency improvement and training with large image pairs. Experiments show that the proposed method can achieve a pixel-level matching error.

2 September 2022 in IEEE Transactions on Aerospace and Electronic Systems
Verified
Journal Article
Closed access
YFYuyuan Fang
Yuyuan Fang
LZLei Zhang
Lei Zhang
SWShaopeng Wei
Shaopeng Wei
TWTao Wang
Tao Wang
JWJianxin Wu
Jianxin Wu
Frequency-agile (FA) transmission strategy plays a crucial role in radar anti-jamming applications. This strategy is usually designed or trained offline, which would lose the advantage of adaptability and flexibility when facing diverse jamming patterns and non-stationary target echoes. Considering the scenarios where a radar detects a target with strong non-stationary scattering characteristics under fast-variant interference, the radar is required to immediately adjust the FA transmission strategy to react to the variation of both jamming signals and target echoes quickly. In order to enhance radar transmission strategy in both generalization and flexibility aspects, an online FA strategy, called Combinatorial Discounted Thompson Sampling (CDTS), is developed for the anti-jamming by exploiting the target's scattering change with the Multi-Armed Bandit (MAB) model. With the advantages of both optimal exploration and fast convergence, the proposed algorithm can efficiently adapt to the scattering fluctuation under dynamic frequency jamming emissions. Experimental comparisons with conventional Deep Reinforcement Learning (DRL) demonstrate the proposed algorithm's superiority for FA transmission strategy learning to boost radar detection performance under frequency response dynamics when avoiding frequency jamming.

5 June 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CHChao He
Chao He
LZLei Zhang
Lei Zhang
SWSong Wei
Song Wei
YFYuyuan Fang
Yuyuan Fang
Recognition of multifunction radar (MFR) working modes provides essential information to assess the behavior of a non-cooperative MFR. However, it typically depends on substantial previously intercepted waveforms. To enable better recognition with limited pre-observations, this paper proposes a radar-semantics-modeled LSTM recognition algorithm with embedding radar waveform functionality features and utilizing contextual recognition of an LSTM network. On the one hand, unsupervised hierarchical modeling and functional semantics embedding extract MFR behavior units and embed the artificial functional semantics of waveforms based on experts’ knowledge about waveform functionalities. On the other hand, an LSTM network captures static and dynamic features within sequences of radar semantic data, recognizing the MFR working mode. Experimental comparisons on preset datasets illustrate that the proposed algorithm adapts more effectively to parameter variations and migrates the recognition between the MFRs with similar functional behavior features.

7 August 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
XYXiaojie Yu
Xiaojie Yu
SWSong Wei
Song Wei
YFYuyuan Fang
Yuyuan Fang
JSJialian Sheng
Jialian Sheng
LZLei Zhang
Lei Zhang
For the preservation of low-airspace security, a comprehensive threat assessment of low-altitude slow small (LSS) flying targets is essential. Threat assessment intrinsically depends on effectively extracting the optimal attributes from tracks, which represent the target’s motion intention and specific characteristics. However, unavoidable measured noise and track jitters during observation impact assessment performance. To address this problem, long short-term memory (LSTM) is introduced due to its good performance on sequential perception. LSTM captures the permanent intent traits and reduces noise interference utilizing temporal correlations within its novel “memory’’ units. Compared to traditional algorithms, the proposed technique substantially reduces measurement noise, enhancing the accuracy of threat evaluations. Simulation experiments confirm the effectiveness and robustness of the proposed algorithms.

29 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CYCanming Yao
Canming Yao
PXPengfei Xie
Pengfei Xie
LZLei Zhang
Lei Zhang
YFYuyuan Fang
Yuyuan Fang
Syntheticap erture radar (SAR) ship detection in harbors is challenging due to the similar backscattering of ship targets to surrounding background interference. Prevalent two-stage ship detectors usually use an anchor-based region proposal network (RPN) to search for the possible regions of interest on the whole image. However, most pre-defined anchor boxes are redundantly and randomly tiled on the image, manifested as low-quality object proposals. To address these issues, this paper proposes a novel detection method combined with two feature enhancement modules to improve ship detection capability. First, we propose a flexible anchor-free detector (AFD) to generate fewer but higher-quality proposals around the object centers in a keypoint prediction manner, which completely avoids the complicated computation in RPN, such as calculating overlapping related to anchor boxes. Second, we leverage the proposed spatial insertion attention (SIA) module to enhance the feature discrimination between ship targets and background interference. It accordingly encourages the detector to pay attention to the localization accuracy of ship targets. Third, a novel weighted cascade feature fusion (WCFF) module is proposed to adaptively aggregate multi-scale semantic features and thus help the detector boost the detection performance of multi-scale ships in complex scenes. Finally, combining the newly-designed AFD and SIA/WCFF modules, we present a new detector, named anchor-free two-stage ship detector (ATSD), for SAR ship detection under complex background interference. Extensive experiments on two public datasets, i.e., SSDD and HRSID, verify that our ATSD delivers state-of-the-art detection performance over conventional detectors.