Qianyue Xue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qianyue Xue has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Bing Han
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
2 shared publications - Jiayuan Shen
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
2 shared publications - Di Yin
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication Jianbing Xiang
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
1 shared publication- Jiaxin Wan
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Shangyu Zhang
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication
Latest Publications
- Open Access
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-22
Uni-RSNet: A Unified Recognition-Sorting Framework for SAR Interference Signals in Complex Electromagnetic Environments
Synthetic aperture radar (SAR) often receives interference from multiple emitters operating within the same frequency band. These interference signals are densely overlapped in time and frequency domains and strongly coupled with SAR echoes, which substantially increases the difficulty of signal recognition and sorting. In conventional processing chains, recognition and sorting are treated as independent modules with task-specific inputs, resulting in severe information fragmentation and cumulative-error propagation under dense interference conditions. To address these limitations, this paper proposes a unified recognition-sorting network for overlapping SAR interference signals, termed Uni-RSNet. Based on continuous multi-frame time-frequency representations, Uni-RSNet jointly captures high-dimensional intra-pulse features and inter-pulse temporal correlations of signals from the same emitter, enabling simultaneous modulation classification, pulse-parameter estimation, and emitter attribution. This framework extends interference recognition from isolated pulses to entire frames, while simultaneously imposing modulation-aware constraints on the signal sorting process. Furthermore, a statistically consistent contrastive objective is designed to enhance intra-emitter compactness and inter-emitter separability, while a geometric consistency constraint improves the robustness of pulse localization. The unified architecture compresses the conventional serial processing chain and eliminates the need for task-dependent input adjustments. Extensive experiments on both simulated and GaoFen-3 (GF-3) satellite data demonstrate the superior performance of the proposed method under dense interference conditions. The code and datasets are publicly available at: https://github.com/QianyueXue/Uni-RSNet.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-22
Open AccessUni-RSNet: A Unified Recognition-Sorting Framework for SAR Interference Signals in Complex Electromagnetic Environments
Synthetic aperture radar (SAR) often receives interference from multiple emitters operating within the same frequency band. These interference signals are densely overlapped in time and frequency domains and strongly coupled with SAR echoes, which substantially increases the difficulty of signal recognition and sorting. In conventional processing chains, recognition and sorting are treated as independent modules with task-specific inputs, resulting in severe information fragmentation and cumulative-error propagation under dense interference conditions. To address these limitations, this paper proposes a unified recognition-sorting network for overlapping SAR interference signals, termed Uni-RSNet. Based on continuous multi-frame time-frequency representations, Uni-RSNet jointly captures high-dimensional intra-pulse features and inter-pulse temporal correlations of signals from the same emitter, enabling simultaneous modulation classification, pulse-parameter estimation, and emitter attribution. This framework extends interference recognition from isolated pulses to entire frames, while simultaneously imposing modulation-aware constraints on the signal sorting process. Furthermore, a statistically consistent contrastive objective is designed to enhance intra-emitter compactness and inter-emitter separability, while a geometric consistency constraint improves the robustness of pulse localization. The unified architecture compresses the conventional serial processing chain and eliminates the need for task-dependent input adjustments. Extensive experiments on both simulated and GaoFen-3 (GF-3) satellite data demonstrate the superior performance of the proposed method under dense interference conditions. The code and datasets are publicly available at: https://github.com/QianyueXue/Uni-RSNet.
- Open Access
- 24 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1143
Multi-Aspect Interpolation Method for SAR Complex Images of Typical Aircraft Target Using Multi-Aspect Scattering Information Complex Generative Adversarial Network
Due to the huge differences in Synthetic Aperture Radar (SAR) image features of the same target under different observing aspects, the demand for constructing multi-aspect SAR datasets of various typical targets is becoming increasingly urgent with the expansion of SAR technology application fields. Meanwhile, multi-aspect interpolation techniques for constructing multi-aspect SAR datasets, based on electromagnetic scattering features and on Generative Adversarial Networks (GANs), have some shortcomings that are difficult to address. The former method provide descriptions of the target scattering so overly idealized that they are not real, while the latter method suffers from incomplete amplitude information and a loss of phase information in multi-aspect interpolation results due to the SAR images input into GANs being phaseless and amplitude-quantized. In response to the above issues, this paper proposes the Multi-aspect Scattering Information Complex GAN (MS-CGAN) guided by the scattering information in observing aspects of SAR images to simulate the multi-aspect interpolation of SAR images from specific aspects. MS-CGAN provides a new approach for dataset construction and augmentation. Moreover, as a complex network, MS-CGAN does not require phase removal or amplitude quantization of the input SAR images; thus, the significant issue of the severe loss of scattering information in multi-aspect interpolation methods based on GANs is greatly addressed. In the experiments, assuming the absence of real SAR images from certain aspects, both the correlation coefficient and the phase correlation between interpolated SAR images from MS-CGAN and real SAR images achieve good results. In the case of a sampling aspect interval of 10°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images both reach over 80%. In the case of a sampling aspect interval of 20°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images remain above 75%. In the case of a sampling aspect interval of 30°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images can reach around 70%. Energy integration curves are completed at specific aspects, demonstrating the effectiveness of the MS-CGAN multi-aspect interpolation method.
- 24 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1143
Open AccessMulti-Aspect Interpolation Method for SAR Complex Images of Typical Aircraft Target Using Multi-Aspect Scattering Information Complex Generative Adversarial Network
Due to the huge differences in Synthetic Aperture Radar (SAR) image features of the same target under different observing aspects, the demand for constructing multi-aspect SAR datasets of various typical targets is becoming increasingly urgent with the expansion of SAR technology application fields. Meanwhile, multi-aspect interpolation techniques for constructing multi-aspect SAR datasets, based on electromagnetic scattering features and on Generative Adversarial Networks (GANs), have some shortcomings that are difficult to address. The former method provide descriptions of the target scattering so overly idealized that they are not real, while the latter method suffers from incomplete amplitude information and a loss of phase information in multi-aspect interpolation results due to the SAR images input into GANs being phaseless and amplitude-quantized. In response to the above issues, this paper proposes the Multi-aspect Scattering Information Complex GAN (MS-CGAN) guided by the scattering information in observing aspects of SAR images to simulate the multi-aspect interpolation of SAR images from specific aspects. MS-CGAN provides a new approach for dataset construction and augmentation. Moreover, as a complex network, MS-CGAN does not require phase removal or amplitude quantization of the input SAR images; thus, the significant issue of the severe loss of scattering information in multi-aspect interpolation methods based on GANs is greatly addressed. In the experiments, assuming the absence of real SAR images from certain aspects, both the correlation coefficient and the phase correlation between interpolated SAR images from MS-CGAN and real SAR images achieve good results. In the case of a sampling aspect interval of 10°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images both reach over 80%. In the case of a sampling aspect interval of 20°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images remain above 75%. In the case of a sampling aspect interval of 30°, the mean correlation of the amplitude and phase of the interpolated SAR images and the corresponding real SAR images can reach around 70%. Energy integration curves are completed at specific aspects, demonstrating the effectiveness of the MS-CGAN multi-aspect interpolation method.