极坐标编解码的轻量化SAR图像舰船斜框检测算法

doi:10.3778/j.issn.1673-9418.2405094

摘要/Abstract

摘要： 针对目前合成孔径雷达（SAR）图像舰船目标斜框检测算法中存在的参数量过大难以满足实时化检测需求以及边界不连续的问题，提出了一种基于极坐标编解码的轻量化SAR舰船目标斜框检测算法。基于ShuffleNetV2的Shuffle单元并利用轻量高效的PC卷积和Ghost卷积，提出了卷积协同单元，实现优化卷积操作，减少算法的复杂度。引入极坐标编解码方法，并提出余弦调和IoU加权损失函数，动态调节极坐标编码损失，解决斜框检测存在的边界不连续问题，同时使用双峰最大池化和椭圆二维高斯分布对极坐标编解码方法进行改进，以提高对近岸密集排布舰船的检测精度。提出多尺度条形卷积注意力模块和空间选择特征增强模块，通过获取不同尺度特征信息，以提高网络特征提取能力。在SSDD+和DSSDD数据集上的实验结果表明，该算法分别实现了85.7%和90.6%的检测精度，并在HRSID数据集上进行泛化测试，检测精度可达82.3%。相较于同类算法在检测精度相近的情况下，参数量和浮点运算量低于同类算法的1/10，仅为0.87 MB和1.21 GFLOPs，检测速度可达135 FPS，满足实时性检测需求。

关键词: 合成孔径雷达, 舰船目标斜框检测, 深度学习, 多尺度, 特征增强

Abstract: Aiming at the problem that the parameter quantity in the current synthetic aperture radar (SAR) image ship target oblique frame detection algorithm is too large to meet the real-time detection requirements and the problem of boundary discontinuity, a lightweight SAR ship target oblique frame detection algorithm based on polar coordinate encoding and decoding is proposed. Firstly, based on the Shuffle unit of ShuffleNetV2 and using lightweight and efficient PC and Ghost convolutions, a convolution collaborative unit is proposed to optimize convolution operations and reduce algorithm complexity. Then, the polar coordinate encoding and decoding method is introduced, and the cosine-harmonized IoU weighted loss function is proposed to dynamically adjust the polar coordinate encoding loss to solve the oblique frame detection boundary discontinuity problem. At the same time, the polar coordinate encoding and decoding method is improved by using double-peak max-pooling and elliptical two-dimensional Gaussian distribution to enhance the detection accuracy for the densely packed ships near shore. Finally, a multi-scale bar convolution attention module and a spatial selection feature enhancement module are proposed to obtain feature information at different scales to improve the network feature extraction capability. Experimental results on the SSDD+ and DSSDD datasets show that the algorithm achieves 85.7% and 90.6% detection accuracy, respectively, and a generalization test is conducted on the HRSID dataset with a detection accuracy of up to 82.3%. Compared with similar algorithms with similar detection accuracy, the parameter quantity and floating-point operations are less than one-tenth of similar algorithms, only 0.87 MB and 1.21 GFLOPs, and the detection speed reaches 135 FPS, meeting the real-time detection requirements.

Key words: synthetic aperture radar, ship target oblique frame detection, deep learning, multi-scale, feature enhancement

吕伏, 郑禹, 齐光尧, 李浩然. 极坐标编解码的轻量化SAR图像舰船斜框检测算法[J]. 计算机科学与探索, 2025, 19(6): 1564-1579.

LYU Fu, ZHENG Yu, QI Guangyao, LI Haoran. Lightweight SAR Image Ship Oblique Frame Detection Algorithm Based on Polar Coordinate Encoding and Decoding[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(6): 1564-1579.

参考文献

[1] 侯笑晗, 金国栋, 谭力宁. 基于深度学习的SAR图像舰船目标检测综述[J]. 激光与光电子学进展, 2021, 58(4): 0400005.
HOU X H, JIN G D, TAN L N. Survey of ship detection in SAR images based on deep learning[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0400005.
[2] 贺丰收, 何友, 刘准钆, 等. 卷积神经网络在雷达自动目标识别中的研究进展[J]. 电子与信息学报, 2020, 42(1): 119-131.
HE F S, HE Y, LIU Z G, et al. Research and development on applications of convolutional neural networks of radar automatic target recognition[J]. Journal of Electronics & Information Technology, 2020, 42(1): 119-131.
[3] LI J W, XU C A, SU H, et al. Deep learning for SAR ship detection: past, present and future[J]. Remote Sensing, 2022, 14(11): 2712.
[4] YANG R, PAN Z R, JIA X X, et al. A novel CNN-based detector for ship detection based on rotatable bounding box in SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 1938-1958.
[5] PAN Z R, YANG R, ZHANG A Z. MSR2N: multi-stage rotational region based network for arbitrary-oriented ship detection in SAR images[J]. Sensors, 2020, 20(8): 2340.
[6] CHEN S Q, ZHANG J, ZHAN R H. R2FA-det: delving into high-quality rotatable boxes for ship detection in SAR images[J]. Remote Sensing, 2020, 12(12): 2031.
[7] SUN K, LIANG Y, MA X R, et al. DSDet: a lightweight densely connected sparsely activated detector for ship target detection in high-resolution SAR images[J]. Remote Sensing, 2021, 13(14): 2743.
[8] CHEN B J, XUE F L, SONG H J. A lightweight arbitrarily oriented detector based on transformers and deformable features for ship detection in SAR images[J]. Remote Sensing, 2024, 16(2): 237.
[9] 苏航, 徐从安, 姚力波, 等. 一种轻量化SAR图像舰船目标斜框检测方法[J]. 航空学报, 2022, 43(S1): 157-164.
SU H, XU C A, YAO L B, et al. A lightweight oriented ship detection method in SAR images[J].?Journal?of?Aeronautics, 2022,?43(S1):?157-164.
[10] YANG X, YAN J C. Arbitrary-oriented object detection with circular smooth label[C]//Proceedings of the 16th European Conference on Computer Vision. Cham: Springer, 2020: 677-694.
[11] YANG X, YAN J C. On the arbitrary-oriented object detection: classification based approaches revisited[J]. International Journal of Computer Vision, 2022, 130(5): 1340-1365.
[12] YASIR M, LIU S W, XU M M, et al. Multi-scale ship target detection using SAR images based on improved Yolov5[J]. Frontiers in Marine Science, 2023, 9: 1086140.
[13] YU L, WU H Y, ZHONG Z, et al. TWC-net: a SAR ship detection using two-way convolution and multiscale feature mapping[J]. Remote Sensing, 2021, 13(13): 2558.
[14] YU J M, ZHOU G Y, ZHOU S B, et al. A fast and lightweight detection network for multi-scale SAR ship detection under complex backgrounds[J]. Remote Sensing, 2022, 14(1): 31.
[15] GAO F, HUO Y Y, SUN J P, et al. Ellipse encoding for arbitrary-oriented SAR ship detection based on dynamic key points[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5240528.
[16] HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1577-1586.
[17] BRODIE C, CONSTANTIN A, LUKAS A, et al. Flops for complete intersection Calabi-Yau threefolds[J]. Journal of Geometry and Physics, 2023, 186: 104767.
[18] HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1314-1324.
[19] HE Y S, GAO F, WANG J, et al. Learning polar encodings for arbitrary-oriented ship detection in SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 3846-3859.
[20] ZHOU X Y, WANG D Q, KR?HENBüHL P. Objects as points[EB/OL]. [2024-03-14]. https://arxiv.org/abs/1904.07850.
[21] GUO M H, LU C Z, LIU Z N, et al. Visual attention network[J]. Computational Visual Media, 2023, 9(4): 733-752.
[22] HOU Q B, LU C Z, CHENG M M, et al. Conv2Former: a simple transformer-style ConvNet for visual recognition[EB/OL]. [2024-03-14]. https://arxiv.org/abs/2211.11943.
[23] PASZKE A, GROSS S, MASSA F, et al. Pytorch: an imperative style, high-performance deep learning library[C]//Advances in Neural Information Processing Systems 32, 2019: 8024-8035.
[24] 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.
[25] HU Y X, LI Y N, PAN Z X. A dual-polarimetric SAR ship detection dataset and a memory-augmented autoencoder-based detection method[J]. Sensors, 2021, 21(24): 8478.
[26] WEI S J, ZENG X F, QU Q Z, et al. HRSID: a high-resolution SAR images dataset for ship detection and instance segmentation[J]. IEEE Access, 2020, 8: 120234-120254.
[27] CHICCO D, JURMAN G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation[J]. BMC Genomics, 2020, 21(1): 6.
[28] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[29] YI J R, WU P X, LIU B, et al. Oriented object detection in aerial images with box boundary-aware vectors[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 2149-2158.
[30] YANG X, YAN J C, FENG Z M, et al. R3Det: refined single-stage detector with feature refinement for rotating object[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(4): 3163-3171.
[31] HAN J M, DING J, LI J, et al. Align deep features for oriented object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5602511.
[32] HAN J M, DING J, XUE N, et al. ReDet: a rotation-equivariant detector for aerial object detection[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 2786-2795.