江苏大学学报（自然科学版）2025，Vol.46Issue(4)：402-408,7.DOI:10.3969/j.issn.1671-7775.2025.04.005
基于改进YOLOv5的水下鱼蟹检测算法
Underwater fish and crab detection algorithm based on improved YOLOv5
摘要
Abstract
To solve the problem of the existing underwater detection with low detection accuracy due to single variety and dense target,the improved YOLOv5 algorithm of RSC-YOLOv5 was proposed.The RepVGG Block module was used on Backbone to improve the recognition accuracy of targets of different scales and enhance the inference speed.The shuffle attention(SA)module was added to improve the feature extraction ability of the algorithm.Content-aware reassembly of features(CARAFE)upsampling was used in Neck to obtain larger receptive field.Varifocal Loss was introduced to pay more attention to the high-quality positive samples in intensive target sample training.The experimental results show that the average accuracy of the RSC-YOLOv5 fish and crab detection algorithm is 93.6％,which verifies that the proposed algorithm is suitable for the underwater fish and crab detection.关键词
鱼蟹检测/识别精度/特征提取/YOLOv5/RepVGG BlockKey words
fish and crab detection/recognition accuracy/feature extraction/YOLOv5/RepVGG Block分类
信息技术与安全科学引用本文复制引用
顾寅武,王玉周,张舜尧,马海亮,马一鸣,宋雪桦..基于改进YOLOv5的水下鱼蟹检测算法[J].江苏大学学报（自然科学版）,2025,46(4):402-408,7.基金项目
国家自然科学基金资助项目(62072217) （62072217）
