数字海洋与水下攻防2026，Vol.9Issue(1)：49-55,7.DOI:10.19838/j.issn.2096-5753.2026.01.004
基于声呐图像的水下目标检测算法
Underwater Object Detection Algorithm Based on Sonar Images
许志平 1何艺松 1许德银 1林立雄 1郑佳春 1陈宗恒2
作者信息
- 1. 集美大学 海洋信息工程学院,福建 厦门 361000
- 2. 交通运输部东海航海保障中心 厦门航标处,福建 厦门 361000
- 折叠
摘要
Abstract
Underwater object detection based on sonar images is one of the key tasks of underwater intelligent sensing systems.However,inherent defects in the sonar imaging mechanism,such as missing target details and blurred edges,hinder the model from learning stable discriminative features.To address this issue,a high-precision underwater object detection algorithm based on sonar images is proposed in this study.Based on a single-stage target detection framework,it introduces a space mapping depth convolution module,a feature enhancement module,and a spatial and channel collaborative attention mechanism to achieve lossless downsampling,enhance shallow feature representation,and improve feature spatial sensitivity and channel selectivity.Experimental results on the sonar common target detection dataset demonstrate that this method effectively improves detection accuracy while reducing the number of model parameters.The experimental results verify the effectiveness and practicality of the proposed method,achieving a good balance between lightweight parameters and high detection accuracy,providing reliable technical support for optimizing the object detection performance of underwater intelligent sensing systems.关键词
声呐图像/水下目标检测/特征提取Key words
sonar image/underwater object detection/feature extraction分类
信息技术与安全科学引用本文复制引用
许志平,何艺松,许德银,林立雄,郑佳春,陈宗恒..基于声呐图像的水下目标检测算法[J].数字海洋与水下攻防,2026,9(1):49-55,7.
