A detection method for shallow-buried linear targets in synthetic aperture sonar based on DeepLabv3+ semantic segmentation

doi:10.13474/j.cnki.11-2246.2026.1028

Abstract

Abstract: [Purposes] Addressing the lack of research on the detection of linear targets using synthetic aperture sonar (SAS) and the difficulty of obtaining precise contours with traditional bounding box detection，this paper aims to develop a precise detection method suitable for shallow-buried linear targets. [Methods] By analyzing the slender structural characteristics of linear targets，a pixel-level semantic segmentation strategy was employed to construct a detection model for shallow-buried linear targets based on the DeepLabv3+ semantic segmentation network.A dataset was constructed using real SAS images，and the model was trained using Kaiming initialization，the SGD optimizer，and a dynamic learning rate strategy. [Findings] Experimental results show that the model achieved a precision of 0.812，a recall of 0.756，a mean pixel accuracy of 0.824，and a mean intersection over union of 0.791，outperforming comparison models such as U-Net，which demonstrates the ability to accurately segment the edge contours of linear targets and effectively distinguish targets from the seabed background. [Conclusions] This method effectively enables the automated and precise detection of shallow-buried linear targets，providing a methodological foundation for the automated detection of such targets in large-area seabed topography images．

Key words: synthetic aperture sonar, shallow-buried target detection, linear targets, semantic segmentation, DeepLabv3+

CLC Number:

P237

Wang Lu, Tang Tian, Ren Hanxin. A detection method for shallow-buried linear targets in synthetic aperture sonar based on DeepLabv3+ semantic segmentation[J]. Bulletin of Surveying and Mapping, 2026, 0(10): 180-186.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://tb.chinasmp.com/EN/10.13474/j.cnki.11-2246.2026.1028

http://tb.chinasmp.com/EN/Y2026/V0/I10/180

References

[1] 张羽，王迎迎，刘纪元，等.大测绘带合成孔径声呐斜距向分段运动补偿分析[J].信号处理，2019，35(9)：1544-1554．
[2] Raney R K，Runge H，Bamler R，et al.Precision SAR processing using chirp scaling[J].IEEE Transactions on Geoscience and Remote Sensing，1994，32(4)：786-799.
[3] 杨敏，宋士林，徐栋，等.合成孔径声纳技术以及在海底探测中的应用研究[J].海洋技术学报，2016，35(2)：51-55．
[4] 刘纪元.合成孔径声呐技术研究进展[J].中国科学院院刊，2019，34(3)：283-288．
[5] 许宝华，刘传杰，王露，等.基于CVT-SR的合成孔径声呐高低频图像融合方法[J].水利水电快报，2024，45(10)：55-61．
[6] 张元科.水下声纳图像目标检测技术研究[D].哈尔滨：哈尔滨工程大学，2014．
[7] 赵建虎，王晓，张红梅，等.侧扫声呐图像分割的中性集合与量子粒子群算法[J].测绘学报，2016，45(8)：935-942．
[8] 盛蕴霞，霍冠英，刘静.基于超像素聚类的侧扫声呐图像分割算法[J].计算机工程，2018，44(6)：219-225．
[9] Xu Lixue，Wang Xiubo，Wang Xudong.Shipwrecks detection based on deep generation network and transfer learning with small amount of sonar images[C]//Proceedings of the 8th Data Driven Control and Learning Systems Conference (DDCLS).Dali：IEEE，2019：638-643.
[10] Jiang Longyu，Cai Tao，Ma Qixiang，et al.Active object detection in sonar images[J].IEEE Access，2020，8：102540-102553.
[11] Yu Yongcan，Zhao Jianhu，Gong Quanhua，et al.Real-time underwater maritime object detection in side-scan sonar images based on transformer-YOLOv5[J].Remote Sensing，2021，13(18)：3555.
[12] Hoang T L，Phung S L，Chapple P B，et al.Deep Gabor neural network for automatic detection of mine-like objects in sonar imagery[J].IEEE Access，2020，8：94126-94139.
[13] Gerg I D，Monga V.Deep multi-look sequence processing for synthetic aperture sonar image segmentation[J].IEEE Transactions on Geoscience and Remote Sensing，2023，61：4200915.
[14] Li Jiayuan，Wang Zhen，You Zhuhong，et al.U-SAS：U-shape network with multilevel enhancement and global decoding for synthetic aperture sonar image semantic segmentation[J].IEEE Sensors Journal，2025，25(1)：1799-1813.
[15] Chen L C，Zhu Yukun，Papandreou G，et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of 2018 Computer Vision-ECCV.Cham：Springer International Publishing，2018：833-851.
[16] Du Shouji，Du Shihong，Liu Bo，et al.Incorporating DeepLabv3+and object-based image analysis for semantic segmentation of very high resolution remote sensing images[J].International Journal of Digital Earth，2021，14(3)：357-378.
[17] Huang Chao，Zhao Jianhu，Zhang Hongmei，et al.Seg2Sonar：a full-class sample synthesis method applied to underwater sonar image target detection，recognition，and segmentation tasks[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5909319.
[18] 赵曦，袁强强，徐佳丹.面向复杂海洋环境的侧扫声呐目标样本生成与增强方法[J].测绘学报，2026，55(7)：1229-1239．
[19] 于永灿，赵建虎，李冰墨，等.侧扫声呐图像目标识别模型类增量更新方法[J].测绘学报，2026，55(3)：502-514．
[20] 马海伟，栾坤祥，陈良.利用线性调频声呐及波束角调节技术的海底管缆探测[J].测绘通报，2024(6)：171-175．
[21] 薛剑锋，罗昌龙，王胜平，等.融合侧窗快速引导滤波与PM扩散的侧扫声呐海底线检测方法[J].测绘通报，2026(7)：178-184．