A Novel SAR Image Ship Small Targets Detection Method  

作　　者：Yu Song Min Li Xiaohua Qiu Weidong Du Yujie He Xiaoxiang Qi Yu Song;Min Li;Xiaohua Qiu;Weidong Du;Yujie He;Xiaoxiang Qi(Xi’an Institute of High Technology, Xi’an, China;School of Information and Communications, National University of Defense Technology, Xi’an, China)

机构地区：[1]Xi’an Institute of High Technology, Xi’an, China [2]School of Information and Communications, National University of Defense Technology, Xi’an, China

出　　处：《Journal of Computer and Communications》2021年第2期57-71,共15页电脑和通信（英文）

摘　　要：To satisfy practical requirements of high real-time accuracy and low computational complexity of synthetic aperture radar (SAR) image ship small target detection, this paper proposes a small ship target detection method based on the improved You Only Look Once Version 3 (YOLOv3). The main contributions of this study are threefold. First, the feature extraction network of the original YOLOV3 algorithm is replaced with the VGG16 network convolution layer. Second, general convolution is transformed into depthwise separable convolution, thereby reducing the computational cost of the algorithm. Third, a residual network structure is introduced into the feature extraction network to reuse the shallow target feature information, which enhances the detailed features of the target and ensures the improvement in accuracy of small target detection performance. To evaluate the performance of the proposed method, many experiments are conducted on public SAR image datasets. For ship targets with complex backgrounds and small ship targets in the SAR image, the effectiveness of the proposed algorithm is verified. Results show that the accuracy and recall rate improved by 5.31% and 2.77%, respectively, compared with the original YOLOV3. Furthermore, the proposed model not only significantly reduces the computational effort, but also improves the detection accuracy of ship small target.To satisfy practical requirements of high real-time accuracy and low computational complexity of synthetic aperture radar (SAR) image ship small target detection, this paper proposes a small ship target detection method based on the improved You Only Look Once Version 3 (YOLOv3). The main contributions of this study are threefold. First, the feature extraction network of the original YOLOV3 algorithm is replaced with the VGG16 network convolution layer. Second, general convolution is transformed into depthwise separable convolution, thereby reducing the computational cost of the algorithm. Third, a residual network structure is introduced into the feature extraction network to reuse the shallow target feature information, which enhances the detailed features of the target and ensures the improvement in accuracy of small target detection performance. To evaluate the performance of the proposed method, many experiments are conducted on public SAR image datasets. For ship targets with complex backgrounds and small ship targets in the SAR image, the effectiveness of the proposed algorithm is verified. Results show that the accuracy and recall rate improved by 5.31% and 2.77%, respectively, compared with the original YOLOV3. Furthermore, the proposed model not only significantly reduces the computational effort, but also improves the detection accuracy of ship small target.

关 键 词：The SAR Images The Neural Network Ship Small Target Target Detection 

分 类 号：TN9[电子电信—信息与通信工程]