基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法

荣弘扬; 汤永华; 林森; 张志鹏; 王腾川; 刘兴通

doi:10.13300/j.cnki.hnlkxb.2025.02.009

您当前的位置：

首页 >

文章列表页 >

基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法

智慧养殖专题 | 更新时间：2026-11-05

- 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
- 华中农业大学学报 2025年44卷第2期页码：83-93
- 作者机构：
  
  1.沈阳工业大学信息科学与工程学院/沈阳工业大学辽宁省机器视觉重点实验室，沈阳 110870
  2.沈阳理工大学自动化与电气工程学院，沈阳 110159
- 作者简介：
  
  荣弘扬，E-mail：ronghy0716@outlook.com
  汤永华，E-mail： tangyonghua@sut.edu.cn
- 基金信息：
  
  辽宁省机器人联合基金项目(20180520022);辽宁省应用基础研究计划项目(2023JH2/101300237)
- DOI：10.13300/j.cnki.hnlkxb.2025.02.009
  中图分类号： TP391.4
- 收稿：2024-07-01，
  
  纸质出版：2025-03-06
- 稿件说明：
移动端阅览
荣弘扬，汤永华，林森，等.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.

RONG Hongyang,TANG Yonghua,LIN Sen,et al.A method of detecting fish diseases with CEH-YOLOv8 based on dual-channel and hierarchical synergism[J].Journal of Huazhong Agricultural University,2025,44(02):83-93.
荣弘扬，汤永华，林森，等.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. DOI： 10.13300/j.cnki.hnlkxb.2025.02.009.

RONG Hongyang,TANG Yonghua,LIN Sen,et al.A method of detecting fish diseases with CEH-YOLOv8 based on dual-channel and hierarchical synergism[J].Journal of Huazhong Agricultural University,2025,44(02):83-93. DOI： 10.13300/j.cnki.hnlkxb.2025.02.009.

摘要

针对在鱼体病害检测中病害形状不规则、纹理不清晰以及病斑分散导致难以定位真实病害区域的问题，提出一种基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法。首先，提出一种双通道特征提取网络，增强模型对不规则以及不清晰纹理病斑的提取能力。然后，提出一种高效通道空间注意力机制（ECSA），提升模型对分布式目标的识别能力。同时为强化改进后的主干网络，提出一种分层协同的特征金字塔网络（HBFPN），对主干网络提取出的信息进行分层次特征融合，增强模型的特征表达能力。试验结果显示，CEH-YOLOv8 网络对鱼体病害的识别精确率、召回率和mAP分别达到83.2%、72.5%和76.2%，相比于SOTA方法YOLOv10提升了6.9、11.6和11.9百分点，相比原模型提高4.3、6.9和6百分点，单帧图像推理时间为9.1 ms。以上结果表明，改进后的YOLOv8网络可以精准筛选出带病鱼体，可用于提早发现渔业病害以减少经济损失。

Abstract

A method of detecting fish diseases with CEH-YOLOv8 based on dual-channel and hierarchical synergism was developed to solve the problems of the irregular shapes， unclear textures， and scattered disease spots making it difficult to localize the true lesion areas in the detection of fish diseases. A dual-channel feature extraction network was introduced to enhance the ability of model to extract irregular lesion areas with unclear textures. Then， an efficient channel spatial attention （ECSA） mechanism was proposed to improve the capability of model to recognize distributed targets. A hierarchical and balanced feature pyramid network （HBFPN） for was presented to reinforce the improved backbone network and perform 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 percent 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

Keywords

references

ALI TOUFIQUE K，FAROOK S N，BELTON B.Managing fisheries for food security：implications from demand analysis［J］.Marine resource economics，2018，33（1）：61-85．

HUANG Y P，KHABUSI S P.A CNN-OSELM multi-layer fusion network with attention mechanism for fish disease recognition in aquaculture［J］.IEEE access，2023，11：58729-58744.

AZHAR A S B M，HARUN N H B，YUSOFF N B，et al. Image enhancement on underwater images for protozoan white spot fish disease detection［C］//2022 international conference on intelligent systems and computer vision （ISCV）. Fez，Morocco：IEEE，2022： 1-4.

汤永华，石非凡，林森，等.基于融合非局部操作的YOLOv5s高密度锦鲤鱼苗检测方法［ J］.浙江农业学报，2024，36（4）：952-967. TANG Y H，SHI F F，LIN S，et al.YOLOv5s high-density koi fry detection method based on fusion non-local operation［J］.Acta agriculturae zhejiangensis，2024，36（4）：952-967 （in Chinese with English abstract） .

NOMAN M A，HOSSEN M S，ISLAM M，et al. HYBRID-CNN： for identification of rohu fish disease［C］//2022 13th international conferenceon computing communication and networking technologies （ICCCNT）. Kharagpur，India：IEEE，2022：1-6.

KHABUSI S P，HUANG Y P，LEE M F. Attention-Based mechanism for fish disease classification in aquaculture［C］//2023 international conference on system science and engineering （ICSSE）. Ho Chi Minh，Vietnam：IEEE，2023： 95-100.

陈科，周勇，薛明洋，等.基于机器视觉和改进YOLOv5s的鲫病害轻量级无损检测模型［J］.水生生物学报，2024，48（7）：1141-1148. CHEN K，ZHOU Y，XUE M Y，et al.Lightweight nondestructive detection model of crucian carp disease based on machine vision and improved YOLOv5s［J］.Acta hydrobiologica sinica，2024，48（7）：1141-1148 （in Chinese with English abstract） .

YU G，ZHANG J，CHEN A，et al. Detection and identification of fish skin health status referring to four common diseases based on improved YOLOv4 model［J/OL］. Fishes，2023，8（4）： 186［2024-07-01］. https：//doi.org/10.3390/fishes8040186.

魏立明，赵奎，王宁，等.细粒度鱼类疫病图像识别算法模型［J］.激光与光电子学进展，2023，60（16）：119-128. WEI L M，ZHAO K，WANG N，et al.Fine-Grained fish disease image recognition algorithm model［J］.Laser & optoelectronics progress，2023，60（16）：119-128 （in Chinese with English abstract） .

LI D L，LI X，WANG Q，et al.Advanced techniques for the intelligent diagnosis of fish diseases：a review［J/OL］.Animals，2022，12（21）：2938［2024-07-01］.https：//doi.org/10.3390/ani12212938.

HATZILYGEROUDIS I，DIMITROPOULOS K，KOVAS K，et al.Expert systems for farmed fish disease diagnosis：an overview and a proposal［J/OL］.Journal of marine science and engineering，2023，11（5）：1084［2024-07-01］. https：//doi.org/10.3390/jmse11051084.

MIA M J，BIN MAHMUD R，SADAD M S，et al.An in-depth automated approach for fish disease recognition［J］.Journal of King Saud University（computer and information sciences），2022，34（9）：7174-7183.

LI R，WU Y P.Improved YOLO v5 wheat ear detection algorithm based on attention mechanism［J/OL］.Electronics，2022，11（11）：1673［2024-07-01］.https：//doi.org/10.3390/electronics11111673 .

WANG C Y，BOCHKOVSKIY A，LIAO H Y M. YOLOv7：trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［C］//2023 IEEE/CVF international conference on computer vision （ICCV）. Vancouver，Canada：IEEE，2023： 7464-7475.

陈科. 基于机器视觉和改进YOLOv5s的鲫鱼病害轻量级无损检测模型研究［D］.杭州：浙江科技大学，2024.CHEN K. Lightweight nondestructive detection model of Crucian disease based on machine vision and improved YOLOv5s［D］.Hangzhou：Zhejiang University of Science and Technology，2024 （in Chinese with English abstract） .

周涛，王骥，麦仁贵.基于改进YOLOv8的实时菠萝成熟度目标检测方法［J］.华中农业大学学报，2024，43（5）：10-20.ZHOU T，WANG J，MAI R G. Real-time object detection method of pineapple ripeness based on improved YOLOv8［J］. Journal of Huazhong Agricultural University，2024，43（5）：10-20. （in Chinese with English abstract） .

QI Y L，HE Y T，QI X M，et al.Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation［C］//2023 IEEE/CVF international conference on computer vision （ICCV）.Paris，France：IEEE，2023：6047-6056.

WANG Q L，WU B G，ZHU P F，et al.ECA-Net：Efficient channel attention for deep convolutional neural networks［C］//2020 IEEE/CVF conference on computer vision and pattern recognition （CVPR）.Seattle，WA，USA：IEEE，2020：11531-11539.

LIN T Y，DOLLÁR P，GIRSHICK R，et al.Feature pyramid networks for object detection［C］//2017 IEEE conference on computer vision and pattern recognition （CVPR）.Honolulu，HI，USA：IEEE，2017：936-944.

LIU S，QI L，QIN H F，et al.Path aggregation network for instance segmentation［C］//2018 IEEE/CVF conference on computer vision and pattern recognition.Salt Lake City，UT，USA：IEEE，2018：8759-8768.

TAN M X，PANG R M，LE Q V.Efficientdet：Scalable and efficient object detection［C］//2020 IEEE/CVF conference on computer vision and pattern recognition （CVPR）.Seattle，WA，USA.IEEE，2020：10778-10787.

WANG C Y，YEH I H，MARK LIAO H Y.YOLOv9：Learning what you want to learn using programmable gradient information［C］// Computer vision – ECCV 2024.Cham：Springer Nature Switzerland，2025：1-21.

WANG A，CHEN H，LIU L H，et al.YOLOv10：Real-Time end-to-end object detection［DB/OL］.Arxiv，2024：2405.14458［2024-07-01］.https：//arxiv.org/abs/2405.14458v2.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于YOLOv8-DBCS的循环水养殖环境下大口黑鲈异常体表特征检测

基于EDW-YOLOv8的棉花叶片病害检测

基于剪枝和知识蒸馏的YOLOv8轻量化苹果叶片病害检测方法

EMD-YOLO：基于YOLOv8n改进的轻量化作物叶部病害检测算法

中药防治猪流行性腹泻的作用机制研究进展