Muyao Yu
Muyao Yu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Ben Zhang
University of Chinese Academy of Sciences, Beijing 101408, China
1 shared publication - Qiancheng Wei
University of Chinese Academy of Sciences, Beijing 101408, China
1 shared publication - Qiya Su
Beijing Institute of Remote Sensing Equipment, Beijing 100005, China
1 shared publication - Shangchao Liu
Beijing Institute of Remote Sensing Equipment, Beijing 100854, China
1 shared publication - Shengbo Dong
Beijing Institute of Remote Sensing Equipment, Beijing 100854, China
1 shared publication - Xiangyu Duan
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
1 shared publication
Latest Publications
- Open Access
- 18 May 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (10) , 1795
DDFNet-A: Attention-Based Dual-Branch Feature Decomposition Fusion Network for Infrared and Visible Image Fusion
The fusion of infrared and visible images aims to leverage the strengths of both modalities, thereby generating fused images with enhanced visible perception and discrimination capabilities. However, current image fusion methods frequently treat common features between modalities (modality-commonality) and unique features from each modality (modality-distinctiveness) equally during processing, neglecting their distinct characteristics. Therefore, we propose a DDFNet-A for infrared and visible image fusion. DDFNet-A addresses this limitation by decomposing infrared and visible input images into low-frequency features depicting modality-commonality and high-frequency features representing modality-distinctiveness. The extracted low and high features were then fused using distinct methods. In particular, we propose a hybrid attention block (HAB) to improve high-frequency feature extraction ability and a base feature fusion (BFF) module to enhance low-frequency feature fusion ability. Experiments were conducted on public infrared and visible image fusion datasets MSRS, TNO, and VIFB to validate the performance of the proposed network. DDFNet-A achieved competitive results on three datasets, with EN, MI, VIFF, , FMI, and metrics reaching the best performance on the TNO dataset, achieving 7.1217, 2.1620, 0.7739, 0.5426, 0.8129, and 0.9079, respectively. These values are , , , , , and higher than those of the second-best methods, respectively. The experimental results confirm that our DDFNet-A achieves better fusion performance than state-of-the-art (SOTA) methods.- 18 May 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16 (10) , 1795
Open AccessDDFNet-A: Attention-Based Dual-Branch Feature Decomposition Fusion Network for Infrared and Visible Image Fusion
The fusion of infrared and visible images aims to leverage the strengths of both modalities, thereby generating fused images with enhanced visible perception and discrimination capabilities. However, current image fusion methods frequently treat common features between modalities (modality-commonality) and unique features from each modality (modality-distinctiveness) equally during processing, neglecting their distinct characteristics. Therefore, we propose a DDFNet-A for infrared and visible image fusion. DDFNet-A addresses this limitation by decomposing infrared and visible input images into low-frequency features depicting modality-commonality and high-frequency features representing modality-distinctiveness. The extracted low and high features were then fused using distinct methods. In particular, we propose a hybrid attention block (HAB) to improve high-frequency feature extraction ability and a base feature fusion (BFF) module to enhance low-frequency feature fusion ability. Experiments were conducted on public infrared and visible image fusion datasets MSRS, TNO, and VIFB to validate the performance of the proposed network. DDFNet-A achieved competitive results on three datasets, with EN, MI, VIFF, , FMI, and metrics reaching the best performance on the TNO dataset, achieving 7.1217, 2.1620, 0.7739, 0.5426, 0.8129, and 0.9079, respectively. These values are , , , , , and higher than those of the second-best methods, respectively. The experimental results confirm that our DDFNet-A achieves better fusion performance than state-of-the-art (SOTA) methods. - Open Access
A Novel Interference Suppression Method for Interrupted Sampling Repeater Jamming Based on Singular Spectrum Entropy Function
As a new type of jamming, the interrupted sampling repeater jamming (ISRJ) derived from the digital radio frequency memory (DRFM) technology, can generate coherent multiple false targets after pulse compression. At present, the traditional interference suppression method and its improved methods have insufficient characteristics and poor detection performance under the condition of low signal-to-noise ratio (SNR). Aiming at addressing this defect, this paper proposes an interference suppression method for ISRJ based on singular spectrum entropy function (SSEF) from the aspects of singular value decomposition (SVD) and information entropy theories. In this method, firstly, considering the local fine characteristics and extraction efficiency, an adaptive multi-scale segmentation (AMS) method is proposed. The purpose of this processing is to extend the salient characteristics while to smooth the similar ones. In AMS, the segmentation criterion based on average energy of segments and the constraint of minimum segmentation is also proposed, then the improved delay embedded matrix is established from the improved trajectory matrix by AMS and delay embedded mapping. Secondly, the singular spectrum of the improved delay embedded matrix is extracted by SVD. Thirdly, because the recognition algorithms based on singular spectrum analysis (SSA), classical SSE and other characteristics fail at low SNR, this paper proposes a characteristic named as SSEF retrieved from the Shannon entropy model. The following proposed entropy-based threshold detection is carried out on the echo signal to realize the band-pass filtering and interference suppression. Finally, experiment results show that in comparison with other interference suppression approaches, SSEF can increase the probability of target detection and the peak-to-side-lobe ratio (PSR) after pulse compression, which validates its stability to noise and jamming especially in the condition of low SNRs.
Open AccessA Novel Interference Suppression Method for Interrupted Sampling Repeater Jamming Based on Singular Spectrum Entropy Function
As a new type of jamming, the interrupted sampling repeater jamming (ISRJ) derived from the digital radio frequency memory (DRFM) technology, can generate coherent multiple false targets after pulse compression. At present, the traditional interference suppression method and its improved methods have insufficient characteristics and poor detection performance under the condition of low signal-to-noise ratio (SNR). Aiming at addressing this defect, this paper proposes an interference suppression method for ISRJ based on singular spectrum entropy function (SSEF) from the aspects of singular value decomposition (SVD) and information entropy theories. In this method, firstly, considering the local fine characteristics and extraction efficiency, an adaptive multi-scale segmentation (AMS) method is proposed. The purpose of this processing is to extend the salient characteristics while to smooth the similar ones. In AMS, the segmentation criterion based on average energy of segments and the constraint of minimum segmentation is also proposed, then the improved delay embedded matrix is established from the improved trajectory matrix by AMS and delay embedded mapping. Secondly, the singular spectrum of the improved delay embedded matrix is extracted by SVD. Thirdly, because the recognition algorithms based on singular spectrum analysis (SSA), classical SSE and other characteristics fail at low SNR, this paper proposes a characteristic named as SSEF retrieved from the Shannon entropy model. The following proposed entropy-based threshold detection is carried out on the echo signal to realize the band-pass filtering and interference suppression. Finally, experiment results show that in comparison with other interference suppression approaches, SSEF can increase the probability of target detection and the peak-to-side-lobe ratio (PSR) after pulse compression, which validates its stability to noise and jamming especially in the condition of low SNRs.