桂林电子科技大学学报2026，Vol.46Issue(1)：43-50,8.DOI:10.16725/j.1673-808X.202449
基于混合局部通道注意力机制的水下光学图像目标检测算法
Underwater optical image target detection algorithm based on mixed local channel attention mechanism
摘要
Abstract
In underwater optical image target detection tasks,complex underwater environments,light attenuation,and the preva-lence of small underwater targets significantly affect detection accuracy.To improve this accuracy,an underwater target detection al-gorithm based on YOLOv5s is proposed.Firstly,the Spd-Conv module is introduced into the backbone network to enhance the recognition capability of small targets,effectively improving the detection accuracy.Secondly,the YOLOx_head module is added to the prediction network to enhance the model's convergence speed by using decoupled detection heads,enabling rapid convergence during training.Finally,building upon the existing Mixed Local Channel Attention mechanism,the C3-MLCA module is designed to capture local spatial information,thereby enhancing the model's ability to capture target features and further improving detection accuracy.Experimental results demonstrate that the improved algorithm increases a 2.0%increase mAP@0.5 by 2.0%,reaching 84.1%,and improves mAP@0.5:0.95 by 3.0%,reaching 48.0%.These results confirm the effectiveness of the proposed algorithm and the enhancement in detection accuracy.关键词
YOLOv5s/目标检测/光学图像/注意力机制/深度学习Key words
YOLOv5s/target detection/optical image/attention mechanism/deep learning分类
信息技术与安全科学引用本文复制引用
陈辉,王奎阳,张兆贤..基于混合局部通道注意力机制的水下光学图像目标检测算法[J].桂林电子科技大学学报,2026,46(1):43-50,8.基金项目
国家自然科学基金(62361018) （62361018）
广西自然科学基金(2021JJA170177) （2021JJA170177）
桂林电子科技大学研究生教育创新计划(2022YCXS027) （2022YCXS027）
