volume | PIER Journals

Abstract

With the development of deep learning networks, convolutional neural network (CNN) and other techniques provide effective detection methods for synthetic aperture radar automatic target recognition (SAR ATR), and have been widely used. However, due to the objective factors such as complex scene interference inherent in SAR images, the recognition rate of traditional time-domain processing of SAR images is not high enough, which is still a key problem to be solved urgently. To solve this problem, we propose a space-frequency dynamic fusion network (SDF-Net). The network consists of four space-frequency joint processing (SJP) modules connected in series, each comprising convolutional layers and unbiased fast fourier convolution (UFFC) units at different scales to achieve joint feature extraction in the spatial and frequency domains. Building on a four-level series structure, residual paths from the original image features are introduced into the inputs of SJP2, SJP3, and SJP4. Additionally, residual paths from the features output by SJP1 are introduced into the inputs of SJP3 and SJP4, and from SJP2 into the input of SJP4. By incorporating residual paths of features from different stages, the network facilitates cross-stage information interaction, effectively integrating long-distance contextual information. At each fusion node, dynamically generated weights are used for feature fusion, followed by sequential progressive processing through spatial-frequency joint processing, ultimately leading to classification and recognition results. Experimental results on the MSTAR dataset and the FUSAR-Ship1.0 dataset show that compared to traditional methods, this network algorithm achieves a higher recognition rate.

1. Wang, Jielei, Zongyong Cui, Ting Jiang, Changjie Cao, and Zongjie Cao, "Lightweight deep neural networks for ship target detection in SAR imagery," IEEE Transactions on Image Processing, Vol. 32, 565-579, 2023.
doi:10.1109/tip.2022.3231126

2. Dong, Yingbo, Fangfang Li, Wen Hong, Xiao Zhou, and Huimin Ren, "Land cover semantic segmentation of port area with high resolution SAR images based on SegNet," 2021 SAR in Big Data Era (BIGSARDATA), 1-4, Nanjing, China, 2021.
doi:10.1109/BIGSARDATA53212.2021.9574376

3. Frey, Othmar, Charles L. Werner, and Roberto Coscione, "Car-borne and UAV-borne mobile mapping of surface displacements with a compact repeat-pass interferometric SAR system at L-band," IGARSS 2019 --- 2019 IEEE International Geoscience and Remote Sensing Symposium, 274-277, Yokohama, Japan, Aug. 2019.
doi:10.1109/IGARSS.2019.8897827

4. Lang, Haitao, Guang'an Yang, Chunnan Li, and Jianwen Xu, "Multisource heterogeneous transfer learning via feature augmentation for ship classification in SAR imagery," IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 1-14, 2022.
doi:10.1109/tgrs.2022.3178703

5. Zhang, Tianyi, Sirui Tian, Stanley Ebhohimhen Abhadiomhen, Zhiyong Xu, Xiang-jun Shen, Jing Wang, and Chao Wang, "Low-rank representation based model for SAR image denoising and edge-preserving," 2023 SAR in Big Data Era (BIGSARDATA), 1-4, Beijing, China, 2023.
doi:10.1109/BIGSARDATA59007.2023.10294373

6. Li, Chao, Jiacheng Ni, Ying Luo, Dan Wang, and Qun Zhang, "A dual-branch spatial-frequency domain fusion method with cross attention for SAR image target recognition," Remote Sensing, Vol. 17, No. 14, 2378, 2025.
doi:10.3390/rs17142378

7. Zhang, Zixin, Di Wu, Daiyin Zhu, and Yudong Zhang, "A multichannel SAR ground moving target detection algorithm based on subdomain adaptive residual network," IEEE Geoscience and Remote Sensing Letters, Vol. 20, 1-5, 2023.
doi:10.1109/lgrs.2023.3314968

8. Geng, Zhe, Ying Xu, Bei-Ning Wang, Xiang Yu, Dai-Yin Zhu, and Gong Zhang, "Target recognition in SAR images by deep learning with training data augmentation," Sensors, Vol. 23, No. 2, 941, 2023.
doi:10.3390/s23020941

9. Chen, Jie, Nawaz Amjad, and Wei Yang, "SAR and multispectral image fusion using multibranch CNN and cross domain learning for local climate zone classification," 2024 21st International Bhurban Conference on Applied Sciences and Technology (IBCAST), 484-489, Murree, Pakistan, 2024.
doi:10.1109/IBCAST61650.2024.10876963

10. Pan, Xingbo, Weibin Wang, Lin Wu, and Ning Li, "Improved moving target imaging method for a multichannel HRWS SAR system," IEEE Geoscience and Remote Sensing Letters, Vol. 20, 1-5, 2023.
doi:10.1109/lgrs.2023.3303354

11. Yang, Yue, Yihe Wan, and Qun Wan, "A 2D-PRM-based atmospheric phase correction method in GB-SAR interferometry application," IEEE Sensors Letters, Vol. 7, No. 6, 1-4, 2023.
doi:10.1109/lsens.2023.3276784

12. Liu, Yijun, Mingxin Lin, Yuanhui Mo, and Qingsong Wang, "SAR --- Optical image matching using self-supervised detection and a transformer-CNN-based network," IEEE Geoscience and Remote Sensing Letters, Vol. 21, 1-5, 2024.
doi:10.1109/lgrs.2024.3355472

13. Yuan, Sen, Ze Yu, Chunsheng Li, and Shusen Wang, "A novel SAR sidelobe suppression method based on CNN," IEEE Geoscience and Remote Sensing Letters, Vol. 18, No. 1, 132-136, 2021.
doi:10.1109/lgrs.2020.2968336

14. Zhao, Congxia, Xiongjun Fu, and Jian Dong, "CGA-Det: A CNN-GNN-based oriented SAR ship detector for complex scenes," IEEE Geoscience and Remote Sensing Letters, Vol. 22, 1-5, 2025.
doi:10.1109/lgrs.2025.3554675

15. Hao, Yisheng, Jun Wu, Yu Yao, and Yue Guo, "A robust anchor-free detection method for SAR ship targets with lightweight CNN," IEEE Transactions on Instrumentation and Measurement, Vol. 74, 1-19, 2025.
doi:10.1109/tim.2025.3563050

16. Zhang, Sen, Qiuyun Cheng, Dengxi Chen, and Haijun Zhang, "Image target recognition model of multi-channel structure convolutional neural network training automatic encoder," IEEE Access, Vol. 8, 113090-113103, 2020.
doi:10.1109/access.2020.3003059

17. Gao, Fei, Lingzhe Kong, Rongling Lang, Jinping Sun, Jun Wang, Amir Hussain, and Huiyu Zhou, "SAR target incremental recognition based on features with strong separability," IEEE Transactions on Geoscience and Remote Sensing, Vol. 62, 1-13, 2024.
doi:10.1109/tgrs.2024.3351636

18. Xu, Teng, Penghao Xiao, and Haipeng Wang, "MobileShuffle: An efficient CNN architecture for spaceborne SAR scene classification," IEEE Geoscience and Remote Sensing Letters, Vol. 21, 1-5, 2024.
doi:10.1109/lgrs.2024.3452075

19. Fukuzaki, Shota and Masaaki Ikehara, "Faster training of large kernel convolutions on smaller spatial scales," IEEE Access, Vol. 12, 161312-161328, 2024.
doi:10.1109/access.2024.3486085

20. Wang, Jun, Tong Zheng, Peng Lei, and Xiao Bai, "Ground target classification in noisy SAR images using convolutional neural networks," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 11, No. 11, 4180-4192, 2018.
doi:10.1109/jstars.2018.2871556

21. Zang, Bo, Linlin Ding, Zhenpeng Feng, Mingzhe Zhu, Tao Lei, Mengdao Xing, and Xianda Zhou, "CNN-LRP: Understanding convolutional neural networks performance for target recognition in SAR images," Sensors, Vol. 21, No. 13, 4536, 2021.
doi:10.3390/s21134536

22. Marzi, David, Javier I. Santtiz Jara, and Paolo Gamba, "A 3-D fully convolutional network approach for land cover mapping using multitemporal sentinel-1 SAR data," IEEE Geoscience and Remote Sensing Letters, Vol. 21, 1-5, 2024.
doi:10.1109/lgrs.2023.3332765

23. Guo, Yuxia, Zhiqiang Zeng, Mingming Jin, Jinping Sun, Zhongjie Meng, and Wen Hong, "Multilevel attention networks for synthetic aperture radar automatic target recognition," IEEE Geoscience and Remote Sensing Letters, Vol. 21, 1-5, 2024.
doi:10.1109/lgrs.2024.3417222

24. Huang, Zhongling, Chong Wu, Xiwen Yao, Zhicheng Zhao, Xiankai Huang, and Junwei Han, "Physics inspired hybrid attention for SAR target recognition," ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 207, 164-174, 2024.
doi:10.1016/j.isprsjprs.2023.12.004

25. Li, Xuesheng, Qiwei Xu, Xinlei Chen, and Chen Li, "Additive attention for CNN-based classification," 2021 IEEE International Conference on Mechatronics and Automation (ICMA), 55-59, Takamatsu, Japan, 2021.

26. Lingyun, Gu, Eugene Popov, and Dong Ge, "Spectral network combining Fourier transformation and deep learning for remote sensing object detection," 2022 International Conference on Electrical Engineering and Photonics (EExPolytech), 99-102, St. Petersburg, Russian Federation, 2022.
doi:10.1109/EExPolytech56308.2022.9950863

27. Khatavkar, Savita Annasaheb and N. B. Sambre, "DeepPatchNet: A FFT-CNN-based fusion approach for resilient phase correction in underwater image reconstruction," 2024 International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), 1-7, Bengaluru, India, 2024.
doi:10.1109/ICDSCNC62492.2024.10939375

28. Meng, Yishuo, Junfeng Wu, Siwei Xiang, Jianfei Wang, Jia Hou, Zhijie Lin, and Chen Yang, "A high-throughput and flexible CNN accelerator based on mixed-radix FFT method," IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 72, No. 2, 816-829, 2025.
doi:10.1109/tcsi.2024.3466563

29. Shi, Hao, Guo Cao, Youqiang Zhang, Zixian Ge, Yanbo Liu, and Di Yang, "F3Net: Fast Fourier filter network for hyperspectral image classification," IEEE Transactions on Instrumentation and Measurement, Vol. 72, 1-18, 2023.
doi:10.1109/tim.2023.3277100

30. Ruan, Xiyue, Ling Wang, Jun Guo, Daiyin Zhu, and Changyu Hu, "CNN-based SAR automatic target recognition using SAR raw data," 2021 CIE International Conference on Radar (Radar), 1405-1408, Haikou, Hainan, China, 2021.
doi:10.1109/Radar53847.2021.10028316

31. Li, Yi, Lan Du, and Di Wei, "Multiscale CNN based on component analysis for SAR ATR," IEEE Transactions on Geoscience and Remote Sensing, Vol. 60, 1-12, 2021.
doi:10.1109/tgrs.2021.3100137

32. Zhou, Feng, Li Wang, Xueru Bai, and Ye Hui, "SAR ATR of ground vehicles based on LM-BN-CNN," IEEE Transactions on Geoscience and Remote Sensing, Vol. 56, No. 12, 7282-7293, 2018.
doi:10.1109/tgrs.2018.2849967

33. Toumi, Abdelmalek, Jean-Christophe Cexus, Ali Khenchaf, and Mahdi Abid, "A combined CNN-LSTM network for ship classification on SAR images," Sensors, Vol. 24, No. 24, 7954, 2024.
doi:10.3390/s24247954

34. Wang, Ke, Qi Qiao, Gong Zhang, and Yihan Xu, "Few-shot SAR target recognition based on deep kernel learning," IEEE Access, Vol. 10, 89534-89544, 2022.
doi:10.1109/access.2022.3193773

35. Chen, Hongting, Chuan Du, Jinlin Zhu, and Dandan Guo, "Target-aspect domain continual learning for SAR target recognition," IEEE Transactions on Geoscience and Remote Sensing, Vol. 63, 1-14, 2025.
doi:10.1109/TGRS.2025.3538636

36. Xie, Nishang, Mingkang Xiong, Feiming Wei, Tao Zhang, Zhen Yang, and Wenxian Yu, "CA-LOSS: A cosine affinity loss for imbalanced SAR ship classification," IGARSS 2024 --- 2024 IEEE International Geoscience and Remote Sensing Symposium, 9070-9074, Athens, Greece, 2024.
doi:10.1109/IGARSS53475.2024.10640754

37. Lu, Li, Ganchun Zhang, Ying Nie, Jiayi Liu, Yibiao fang, Guoling Zhang, and Yahui Wu, "Application of improved CNN in SAR image noise reduction," Journal of Physics: Conference Series, Vol. 1792, No. 1, 012053, 2021.
doi:10.1088/1742-6596/1792/1/012053

Mr. Xinlin He

Dr. Chao Li

Dr. Kaiming Li

Dr. Ying Luo