一种面向SAR图像快速舰船检测的轻量化网络*

doi:10.7523/j.ucas.2023.017

摘要/Abstract

摘要： 在基于深度学习的SAR(synthetic aperture radar)图像舰船检测领域中,传统的模型通常结构复杂、计算量大,无法适配低算力平台和实现实时检测;依赖于预设锚框的卷积神经网络因锚框位置较难合理设置容易导致大量计算冗余。针对上述问题,本文提出一种基于无锚框端到端的轻量化卷积神经网络,设计了一种轻量的通道注意力模块（EESE）并将其应用于解耦合检测头（ED-Head）上,解决了分类和定位两种不同任务的冲突。此外,提出了一种优化的EIOU损失函数,在保证推理速度几乎不变的情况下有效提升网络性能。所提方法在SSDD数据集上进行了实验,结果表明：该方法与YOLOX-nano相比,AP₅₀和AP分别提高了2.1%和7.4%,在CPU上推理延迟仅5.33ms,速度比YOLOX-nano快2倍多,实现了精度与效率的平衡。

关键词: 合成孔径雷达(SAR), 舰船检测, 深度学习, 轻量化网络, 无锚框目标检测

Abstract: In the field of SAR image ship detection based on deep learning, traditional models are usually complex in structure and require a large amount of calculation, which cannot be adapted to low computing power platforms and achieve real-time detection; Convolutional neural networks that rely on preset anchor boxes will lead to a lot of computational redundancy due to the difficulty of setting a reasonable anchor box. To solve these problems, an end-to-end lightweight convolutional neural network based on anchor-free frames is proposed, and a lightweight channel attention module (EESE) is designed and applied to the detection head (ED-Head), which solves the conflict between classification and localization tasks. In addition, an optimized EIOU loss function is proposed, which enables the model to effectively improve the network performance without increasing the inference time. The proposed method is tested on the SSDD dataset, and the experimental results show that compared with YOLOX-nano, AP₅₀ and AP are improved by 2.1% and 7.4%, the CPU latency is only 5.33ms, and the speed is more than twice as fast as YOLOX-nano. The proposed method achieves a balance between accuracy and efficiency.

Key words: (Synthetic Aperture Radar) SAR, ship detection, deep learning, lightweight network, anchor-free detection

中图分类号:

TP39

周文雪, 张华春. 一种面向SAR图像快速舰船检测的轻量化网络^*[J]. 中国科学院大学学报, DOI: 10.7523/j.ucas.2023.017.

ZHOU Wenxue, ZHANG Huachun. A lightweight network for fast ship detection in SAR images[J]. Journal of University of Chinese Academy of Sciences, DOI: 10.7523/j.ucas.2023.017.

参考文献

[1] Sciotti M, Pastina D, Lombardo P.Exploiting the polarimetric information for the detection of ship targets in non-homogeneous SAR images[C]//IEEE International Geoscience and Remote Sensing Symposium. June 24-28, 2002, Toronto, ON, Canada. IEEE, 2002: 1911-1913. DOI: 10.1109/IGARSS.2002.1026297.
[2] 林旭, 洪峻, 孙显, 等. ScanSAR图像舰船目标快速检测方法[J]. 中国科学院大学学报, 2013, 30(6):793-799. DOI: 10.7523/j.issn.2095-6134.2013.06.012.
[3] Girshick R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. June 23-28, 2014, Columbus, OH, USA. IEEE, 2014: 580-587. DOI: 10.1109/CVPR.2014.81.
[4] He K M, Zhang X Y, Ren S Q, et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. DOI: 10.1109/TPAMI.2015.2389824.
[5] Girshick R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). December 7-13, 2015, Santiago, Chile. IEEE, 2016: 1440-1448. DOI: 10.1109/ICCV.2015.169.
[6] Ren S Q, He K M, 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, 2017, 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.
[7] He K M, Gkioxari G, Dollar P, et al.Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386-397. DOI: 10.1109/TPAMI.2018.2844175.
[8] Redmon J, Divvala S, Girshick R, et al.You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 779-788. DOI: 10.1109/CVPR.2016.91.
[9] Liu W, Anguelov D, Erhan D, et al.SSD: Single Shot MultiBox Detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37. DOI: 10.1007/978-3-319-46448-0_2.
[10] Redmon J, Farhadi A.YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 6517-6525. DOI: 10.1109/CVPR.2017.690.
[11] Redmon J, Farhadi A. YOLOv3: An incremental improvement[EB/OL].2018: arXiv: 1804.02767.(2018-04-08) [2023-02-20]. https://arxiv.org/abs/1804.02767.
[12] Bochkovskiy A, Wang C-Y, Liao H-Y M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. arXiv:2004.10934. (2020-04-23) [2023-02-20]. https://arxiv.org/abs/2004.10934.
[13] Iandola F N, Moskewicz M W, Ashraf K, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size[EB/OL]. arXiv:1602.07360. (2016-02-24) [2023-02-20]. https://arxiv.org/abs/1602.07360.
[14] Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[EB/OL]. arXiv:1704.04861. (2017-04-17) [2023-02-20]. https://arxiv.org/abs/1704.04861.
[15] Sandler M, Howard A, Zhu M L, et al.MobileNetV2: inverted residuals and linear bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 4510-4520. DOI: 10.1109/CVPR.2018.00474.
[16] Ma N N, Zhang X Y, Zheng H T, et al.ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design[C]//European Conference on Computer Vision. Cham: Springer, 2018: 122-138. DOI: 10.1007/978-3-030-01264-9_8.
[17] Zhang X Y, Zhou X Y, Lin M X, et al.ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 6848-6856. DOI: 10.1109/CVPR.2018.00716.
[18] Han K, Wang Y H, Tian Q, et al.GhostNet: more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 1577-1586. DOI: 10.1109/CVPR42600.2020.00165.
[19] Ge Z, Liu S, Wang F, et al. YOLOX: Exceeding YOLO series in2021[EB/OL]. arXiv: 2107.08430.(2021-07-18) [2023-02-20]. https://arxiv.org/abs/2107.08430.
[20] Law H, Deng J.CornerNet: Detecting Objects as Paired Keypoints[C]//European Conference on Computer Vision. Cham: Springer, 2018: 765-781. DOI: 10.1007/978-3-030-01264-9_45.
[21] Tian Z, Shen C H, Chen H, et al.FCOS: fully convolutional one-stage object detection[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27 - November 2, 2019, Seoul, Korea (South). IEEE, 2020: 9626-9635. DOI: 10.1109/ICCV.2019.00972.
[22] 刘方坚, 李媛. 基于视觉显著性的SAR遥感图像NanoDet舰船检测方法[J]. 雷达学报, 2021, 10(6): 885-894. DOI: 10.12000/JR21105.
[23] Liu S, Qi L, Qin H F, et al.Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 8759-8768. DOI: 10.1109/CVPR.2018.00913.
[24] 张晓玲, 张天文, 师君, 等. 基于深度分离卷积神经网络的高速高精度SAR舰船检测[J]. 雷达学报, 2019, 8(6): 841-851. DOI: 10.12000/JR19111.
[25] Song G L, Liu Y, Wang X G.Revisiting the sibling head in object detector[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 11560-11569. DOI: 10.1109/CVPR42600.2020.01158.
[26] Hu J, Shen L, Sun G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. June 18-23, 2018, Salt Lake City, UT, USA. IEEE, 2018: 7132-7141. DOI: 10.1109/CVPR.2018.00745.
[27] Woo S, Park J, Lee J Y, et al.CBAM: Convolutional Block Attention Module[C]//European Conference on Computer Vision. Cham: Springer, 2018: 3-19. DOI: 10.1007/978-3-030-01234-2_1.
[28] 李松, 魏中浩, 张冰尘, 等. 深度卷积神经网络在迁移学习模式下的SAR目标识别[J]. 中国科学院大学学报, 2018, 35(1): 75-83. DOI: 10.7523/j.issn.2095-6134.2018.01.010.
[29] Lee Y, Park J.CenterMask: real-time anchor-free instance segmentation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 13903-13912. DOI: 10.1109/CVPR42600.2020.01392.
[30] Li D, Hu J, Wang C H, et al.Involution: inverting the inherence of convolution for visual recognition[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 20-25, 2021, Nashville, TN, USA. IEEE, 2021: 12316-12325. DOI: 10.1109/CVPR46437.2021.01214.
[31] Feng C J, Zhong Y J, Gao Y, et al.TOOD: task-aligned one-stage object detection[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). October 10-17, 2021, Montreal, QC, Canada. IEEE, 2022: 3490-3499. DOI: 10.1109/ICCV48922.2021.00349.
[32] Xu S, Wang X, Lv W, et al. PP-YOLOE:An evolved version of YOLO[EB/OL]. arXiv:2203.16250. (2022-03-20) [2023-02-20]. https://arxiv.org/abs/2203.16250.
[33] Rezatofighi H, Tsoi N, Gwak J, et al.Generalized intersection over union: A metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 15-20, 2019, Long Beach, CA, USA. IEEE, 2020: 658-666. DOI: 10.1109/CVPR.2019.00075.
[34] Zhang Y-F, Ren W, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression[EB/OL]. arXiv:2101.08158. (2021-01-20) [2023-02-20]. https://arxiv.org/abs/2101.08158.
[35] 谭显东, 彭辉. 改进YOLOv5的SAR图像舰船目标检测[J]. 计算机工程与应用, 2022, 58(4): 247-254. DOI: 10.3778/j.issn.1002-8331.2108-0308.
[36] Zhang T W, Zhang X L, Li J W, et al.SAR ship detection dataset (SSDD): Official release and comprehensive data analysis[J]. Remote Sensing, 2021, 13(18): 3690. DOI: 10.3390/rs13183690.
[37] Molchanov P, Tyree S, Karras T, et al. Pruning convolutional neural networks for resource efficient transfer learning[EB/OL]. arXiv:1611.06440. (2016-11-19) [2023-02-20]. https://arxiv.org/abs/1611.06440.
[38] Wang Y Y, Wang C, Zhang H, et al.A SAR dataset of ship detection for deep learning under complex backgrounds[J]. Remote Sensing, 2019, 11(7): 765. DOI: 10.3390/rs11070765.

一种面向SAR图像快速舰船检测的轻量化网络^*

A lightweight network for fast ship detection in SAR images

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	嵇宏伟, 刘畅, 潘志刚, 申芳瑜. 基于相位一致性计算和RS-GLOH描述子的 SAR和光学图像匹配[J]. 中国科学院大学学报, 2023, 40(6): 788-799.
[2]	肖俊, 石光田. 三维点云去噪技术[J]. 中国科学院大学学报, 2023, 40(5): 577-595.
[3]	姚沐风, 昝露洋, 李柏鹏, 李庆亭, 陈正超. 基于CAR-Siamese网络的高分辨率遥感图像建筑物变化检测[J]. 中国科学院大学学报, 2023, 40(3): 380-387.
[4]	盛晓光, 王颖, 张迎伟, 项若曦, 付红萍. WILS：面向学业预警的非均衡增量式学习方法[J]. 中国科学院大学学报, 2023, 40(3): 422-432.
[5]	申晓天, 郑明洁. 一种新的基于FrFT的动目标测速和定位方法[J]. 中国科学院大学学报, 2023, 40(1): 84-92.
[6]	陈若男, 彭玲, 刘玉菲, 卫志超, 吕蓓茹, 陈德跃. 引入空间距离信息的城郊山区道路提取与应用[J]. 中国科学院大学学报, 2022, 39(5): 658-667.
[7]	古煜民, 阎福礼. 基于不同骨架UNet++网络的建筑物提取[J]. 中国科学院大学学报, 2022, 39(4): 512-523.
[8]	林大权, 范睿, 张良峰. 基于高维特征的图像对抗攻击算法[J]. 中国科学院大学学报, 2022, 39(3): 421-431.
[9]	赵敏钧, 赵亚伟, 赵雅捷, 罗刚. 一种新的基于深度学习的重叠关系联合抽取模型（英文）[J]. 中国科学院大学学报, 2022, 39(2): 240-251.
[10]	郑慧敏, 郑明洁, 张振宁, 申晓天. 基于低秩和一维稀疏矩阵分解的多通道SAR-GMTI方法[J]. 中国科学院大学学报, 2022, 39(2): 208-216.
[11]	王晓辉, 胡玉新, 吕鹏. 基于显著图融合的高分四号卫星光学遥感图像多运动舰船检测方法[J]. 中国科学院大学学报, 2021, 38(5): 649-659.
[12]	周龙, 王伟强, 吕科. FACR：一种快速且准确的车辆识别器[J]. 中国科学院大学学报, 2021, 38(1): 130-136.
[13]	李森, 彭玲, 胡媛, 池天河. 基于FD-RCF的高分辨率遥感影像耕地边缘检测[J]. 中国科学院大学学报, 2020, 37(4): 483-489.
[14]	矫腾章, 胡玉新, 吕鹏, 张凯, 台宪青. 一种在轨海上多运动舰船目标检测和跟踪方法[J]. 中国科学院大学学报, 2020, 37(3): 368-378.
[15]	闫凯, 沈汀, 陈正超, 闫弘轩. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020, 37(3): 360-367.