山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (2): 15-22.doi: 10.6040/j.issn.1672-3961.0.2021.356
• • 上一篇
郑子阳1, 张婷1, 刘兆英1*, 李玉鑑1,2, SUN Changming3
ZHENG Ziyang1, ZHANG Ting1, LIU Zhaoying1*, LI Yujian1, 2, SUN Changming3
摘要： 提出一种合成孔径雷达(synthetic aperture radar, SAR)图像旋转舰船检测方法,以提高SAR图像中旋转舰船的检测精度。从先验框设计和边界框回归公式对YOLOv4-CSP目标检测网络进行改进,加入旋转角度使其适用于基于旋转框的检测场景;提出一种基于旋转边界框外接圆和交并比的损失函数,该函数不仅考虑预测框和真实框的中心点的距离,而且考虑旋转框各个参数之间的相关性,具有很好的效果;为进一步提升SAR图像中的舰船检测精度,引入转移注意力模块,使得网络能够充分学习有效特征,提高检测精度。试验结果证明,改进后的模型结合提出的损失函数能够有效提升旋转舰船的检测精度,在图像分辨率为416像素×416像素情况下,平均精度均值(mean average precision, mAP)达到95.79%;加入注意力模块后,在图像分辨率为416像素×416像素情况下,mAP达到96.40%,在图像分辨率为800像素×800像素情况下,mAP达到96.98%。本研究不仅可以为海洋监测等应用提供重要的技术支持,还具有重要的理论价值和应用价值。
中图分类号:
| [1] STEENSON B O. Detection performance of a mean-level threshold[J]. IEEE Transactions on Aerospace and Electronic Systems, 1968(4): 529-534. [2] NOVAK L M, BURL M C, IRVING W W. Optimal polarimetric processing for enhanced target detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 1993, 29(1): 234-244. [3] 李其. 基于深度特征的 SAR 图像舰船目标检测方法研究[D]. 成都:成都电子科技大学, 2020. LI Qi. Research of ship detection in SAR images based on depth features[D]. Chengdu: Chengdu University of Electronic Science and Technology of China, 2020. [4] 张永红, 林宗坚, 张继贤, 等. SAR 影像几何校正[J]. 测绘学报, 2002, 31(2): 134-138. ZHANG Yonghong, LIN Zongjian, ZHANG Jixian, et al. Geometric rectification of SAR images[J]. Acta Geodaetica et Cartographica Sinica, 2002, 31(2): 134-138. [5] 尹奎英, 刘宏伟, 金林. 快速的 Otsu 双阈值 SAR 图像分割法[J]. 吉林大学学报(工学版), 2011, 41(6): 1760-1765. YIN Kuiying, LIU Hongwei, JIN Lin. Fast SAR image segmentation method based on otsu adaptive double threshold[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(6): 1760-1765. [6] WANG Yinghua, LIU Hongwei. A hierarchical ship detection scheme for high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(10): 4173-4184. [7] ZHAO Zhongqiu, ZHENG Peng, XU Shoutao, et al. Object detection with deep learning: a review[J]. IEEE transactions on neural networks and learning systems, 2019, 30(11): 3212-3232. [8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 580-587. [9] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6): 1137-1149. [10] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multiBox detector[C] //Proceedings of the European Conference on Computer Vision. Amsterdam, Netherlands: Springer, 2016: 21-37 [11] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016: 1063-1069. [12] ZHAO Yan, ZHAO Lingjun, XIONG Boli, et al. Attention receptive pyramid network for ship detection in SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 2738-2756. [13] KANG M, JI K, LENG X, et al. Contextual region-based convolutional neural network with multilayer fusion for SAR ship detection[J]. Remote Sensing, 2017, 9(8): 860. [14] 江源,李建伟,张玉婷.基于特征重用和语义聚合的SAR图像舰船目标检测[J].海军航空工程学院学报,2019,34(6):470-479. JIANG Yuan, LI Jianwei, ZHANG Yuting. Ship object detection of SAR images based on feature reuse and semantic aggregation[J]. Journal of Naval Aeronautical Engineering Institute, 2019, 34(6): 470-479. [15] AN Quanzhi, PAN Zongxu, LIU Lei, et al. DRBox-v2: an improved detector with rotatable boxes for target detection in SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(99): 8333-8349. [16] LEI Songlin, QIU Xiaolan, DING Chibiao, et al. A Feature Enhancement Method Based on the Sub-Aperture Decomposition for Rotating Frame Ship Detection in SAR Images[C] //Proceedings of the IEEE International Geoscience and Remote Sensing Symposium. Brussels, Belgium: IEEE, 2021: 3573-3576. [17] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaled-YOLOv4: scaling cross stage partial network[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Tennessee, USA: IEEE, 2021: 13029-13038. [18] ZHANG Qinglong, YANG Yubin. SA-Net: shuffle attention for deep convolutional neural networks[C] //Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Toronto, Canada: IEEE, 2021: 2235-2239. [19] YANG Xue, YAN Junchi, FENG Ziming, et al. R3Det: refined single-stage detector with feature refinement for rotating object[C] //Proceedings of the AAAI Conference on Artificial Intelligence. [S.l] : AAAI, 2021: 3163-3171. [20] YANG Xue, YAN Junchi. Arbitrary-oriented object detection with circular smooth label[C] //Proceedings of the European Conference on Computer Vision. Glasgow, UK: Springer, 2020: 677-694. [21] YI Jingru, WU Pengxiang, LIU Bo, et al. Oriented object detection in aerial images with box boundary-aware vectors[C] //Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Hawaii, USA: IEEE, 2021: 2150-2159. |
| [1] | 肖乔,裴继红,王荔霞,龚志成. 基于多通道Gabor滤波模糊融合的遥感图像舰船检测[J]. 山东大学学报 (工学版), 2015, 45(5): 29-35. |
|
||
