华中农业大学学报2025，Vol.44Issue(2)：83-93,11.DOI:10.13300/j.cnki.hnlkxb.2025.02.009
基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法
A method of detecting fish diseases with CEH-YOLOv8 based on dual-channel and hierarchical synergism
摘要
Abstract
A method of detecting fish diseases with CEH-YOLOv8 based on dual-channel and hierar-chical synergism was developed to solve the problems of the irregular shapes,unclear textures,and scat-tered disease spots making it difficult to localize the true lesion areas in the detection of fish diseases.A du-al-channel feature extraction network was introduced to enhance the ability of model to extract irregular le-sion areas with unclear textures.Then,an efficient channel spatial attention(ECSA)mechanism was pro-posed to improve the capability of model to recognize distributed targets.A hierarchical and balanced fea-ture pyramid network(HBFPN)for was presented to reinforce the improved backbone network and per-form hierarchical feature fusion on the information extracted from the backbone network at different levels to enhance the ability of model to express feature.The results showed that the CEH-YOLOv8 network had an accuracy rate of 83.2%,a recall rate of 72.5%,and a mean average precision(mAP)of 76.2%in detecting fish diseases,respectively.Compared with the state-of-the-art(SOAT)YOLOv10 method and the original model,it increased the accuracy rate,recall rate,and mAP by 6.9,11.6,and 11.9 per-cent points,and 4.3,6.9,and 6 percent points,respectively.The inference time for a single frame was 9.1 ms.It is indicated that the improved YOLOv8 network can accurately screen fish with diseases and be used for early detection of fishery diseases to reduce economic losses.关键词
鱼体病害检测/YOLOv8/特征提取网络/注意力机制/特征金字塔Key words
detection of fish diseases/YOLOv8/feature extraction network/attention mechanism/feature pyramid分类
信息技术与安全科学引用本文复制引用
荣弘扬,汤永华,林森,张志鹏,王腾川,刘兴通..基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法[J].华中农业大学学报,2025,44(2):83-93,11.基金项目
辽宁省机器人联合基金项目(20180520022) （20180520022）
辽宁省应用基础研究计划项目(2023JH2/101300237) （2023JH2/101300237）
