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

朱明; 汪荣; 万鹏; 雷翔; 范豪

doi:10.13300/j.cnki.hnlkxb.2026.02.028

您当前的位置：

首页 >

文章列表页 >

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

食品与农业工程 | 更新时间：2026-11-05

- 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
- Detecting characteristics of abnormal body surface in Micropterus salmoides under recirculating aquaculture systems based on YOLOv8-DBCS
- 华中农业大学学报 2026年45卷第2期页码：269-279
- 作者机构：
  
  1.华中农业大学工学院/农业农村部水产养殖设施工程重点实验室，武汉 430070
  2.农业农村部长江中下游农业装备重点实验室，武汉 430070
- 作者简介：
  
  朱明，E-mail：13801392760@163.com
  万鹏，E-mail：wanpeng09@mail.hzau.edu.cn
- 基金信息：
  
  国家重点研发计划项目(2022YFD2001705);湖北省科技重大专项(2023BBA001)
- DOI：10.13300/j.cnki.hnlkxb.2026.02.028
  中图分类号： S965.211
- 收稿：2025-07-19，
  
  纸质出版：2026-03-15
- 稿件说明：
移动端阅览
朱明，汪荣，万鹏，等.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［J］.华中农业大学学报，2026，45（2）：269‐279.

ZHU Ming,WANG Rong,WAN Peng,et al.Detecting characteristics of abnormal body surface in Micropterus salmoides under recirculating aquaculture systems based on YOLOv8-DBCS[J].Journal of Huazhong Agricultural University,2026,45(02):269-279.
朱明，汪荣，万鹏，等.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［J］.华中农业大学学报，2026，45（2）：269‐279. DOI： 10.13300/j.cnki.hnlkxb.2026.02.028.

ZHU Ming,WANG Rong,WAN Peng,et al.Detecting characteristics of abnormal body surface in Micropterus salmoides under recirculating aquaculture systems based on YOLOv8-DBCS[J].Journal of Huazhong Agricultural University,2026,45(02):269-279. DOI： 10.13300/j.cnki.hnlkxb.2026.02.028.

摘要

大口黑鲈（

Micropterus salmoides

）在循环水养殖过程中容易感染细菌和病毒，得病早期体表会出现充血和白斑等异常特征。为避免大口黑鲈大规模养殖死亡，提出一种基于YOLOv8的大口黑鲈异常体表特征检测模型YOLOv8-DBCS。首先，基于StarNet网络提出一种动态深度卷积（DIConv）主干网络DIStarNet，DIConv通过设计动态卷积核权重机制自适应调整卷积操作，进而有效捕捉多尺度的特征信息；其次，在颈部网络引入加权双向特征金字塔网络（bi-directional feature pyramid network，BiFPN）增强对来自主干网络多尺度信息的特征融合能力；此外，在检测头前加入CBAM（convolutional block attention module）注意力机制，提升对鱼体异常体表特征图像的学习与预测；最后将目标识别损失函数替换为SIoU（SCYLLA-int

ersection over union），以改善模型预测框与真实框的重合度，进一步提高模型对鱼体异常体表特征识别准确率。结果显示：YOLOv8-DBCS在检测性能上表现优异，YOLOv8-DBCS评价指标准确率（precision）、召回率（recall）、mAP

和mAP

50-95

分别为95.8%、92.4%、97.5%和66.2%；与基线模型相比分别提高3.6、4.9、7.0和3.4百分点。在模型大小上，YOLOv8-DBCS的参数量（parameters）为1.85×10

，与基线模型相比降低了38.5%。

Abstract

Micropterus salmoides

is prone to bacterial and viral infections under recirculating aquaculture systems （RAS）. Characteristics of abnormal body surface in

M. salmoides

including redness and white spots may appear at the early stages of its illness. A YOLOv8-BCS model for detecting the characteristics of abnormal body surface in

M. salmoides

based on YOLOv8 was proposed to prevent large-scale mortality in aquaculture. A dynamic depthwise convolution（DIConv） feature extraction network， DIStarNet， was proposed based on the StarNet network. DIConv adaptively adjusted the convolution operation by designing a dynamic convolution kernel weight mechanism， thereby effectively capturing multi-scale feature information. A weighted bidirectional feature pyramid network（bi-directional feature pyramid network，BiFPN） was introduced into the neck network to enhance the feature fusion capability of multi-scale information from the backbone network. A convolutional block attention module （CBAM） attention mechanism was added before detection to improve the learning and extracting images of the characteristics of abnormal body surface in fish. The target recognition loss function was replaced with SCYLLA-intersection over union （SIoU） to improve the overlap between the model's predicted bounding boxes and the ground truth bounding boxes， thereby further enhancing the accuracy of recognizing the characteristics of abnormal body surface in fish. The results showed that YOLOv8 DBCS exhibited excellent performance of detection， with evaluation metrics including Precision， Recall， mAP

， and mAP

50-95

ing 95.8%， 92.4%， 97.5%， and 66.2%， respectively. Compared with that of the baseline model， these metrics increased by 3.6， 4.9， 7.0， and 3.4 percentage point， respectively. The model size of YOLOv8-DBCS was 1.85 million parameters， with a reduction of 38.5% compared with that of the baseline model. It will provide valuable reference for detecting the characteristics of abnormal body surface and early warning of diseases under recirculating aquaculture systems for

M. salmoides

关键词

Keywords

references

雷燕，戚瑞荣，崔龙波，等.大口黑鲈鱼种弹状病毒病的诊断［J］.大连海洋大学学报，2015，30（3）：305-308.LEI Y，QI R R，CUI L B，et al.Diagnosis of rhabdovirus disease in juvenile largemouth bass Micropterus salmonides ［J］.Journal of Dalian Fisheries University，2015，30（3）：305-308 （in Chinese with English abstract） .

董寒旭，曾伟伟.大口黑鲈蛙虹彩病毒病研究进展［J］.病毒学报，2022，38（3）：746-756.DONG H X，ZENG W W.Research progress on largemouth bass ranavirus disease［J］.Chinese journal of virology，2022，38（3）：746-756 （in Chinese with English abstract） .

PEYGHAN R， REZAIE A， HASSANI F， et al.Histopathological study of gill and fish treatment in ichthyophthiriasis of white skirt tetra （ Gymnocorymbus ternetzi ）［J］.Iranian veterinary journal，2021，17（1）：106-110.

GORGOGLIONE B， BAILEY C， FAST M D， et al.Co-infections and multiple stressors in fish［J］.Bulletin of the European Association of Fish Pathologists，2020，40（1）：4-19.

PARK J S，OH M J，HAN S.Fish disease diagnosis system based on image processing of pathogens' microscopic images［C］//2007 Frontiers in the Convergence of Bioscience and Information Technologies， October 11-13，2007 ，Jeju，Korea.Jeju ：IEEE，2008：878-883.

SIKDER J，SAREK K I，DAS U K.Fish disease detection system：a case study of freshwater fishes of Bangladesh［J］.International journal of advanced computer science and applications，2021，12（6）：867-871.

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）， July 27-28，2023 ，Ho Chi Minh，Vietnam.Ho Chi Minh：IEEE，2023：95-100.

KUMAR S， KARTHIKEYAN P， SURESHKUMAR C.Fish disease detection in aquaculture using pseudo hamiltonian neural network optimized with Philippine eagle optimization algorithm［J/OL］.Knowledge-based systems，2025，317：113374［2025-07-19］.https：//doi.org/10.1016/j.knosys.2025.113374.

WALEED A，MEDHAT H，ESMAIL M，et al.Automatic recognition of fish diseases in fish farms［C］//2019 14th International Conference on Computer Engineering and Sy stems （ICCES）， December 17-17，2019 ，Cairo，Egypt.Cairo：IEEE，2020：201-206.

AHMED M S，AURPA T T，AZAD M A K.Fish disease detection using image based machine learning technique in aquaculture［J］.Journal of King Saud University（computer and information sciences），2022，34（8）：5170-5182.

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） .

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 H Y，TANG Y H，LIN S，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（2）：83-93 （in Chinese with English abstract） .

LOU H T，DUAN X H，GUO J M，et al.DC-YOLOv8：small-size object detection algorithm based on camera sensor［J/OL］.Electronics，2023，12（10）：2323［2025-07-19］.https：//doi.org/10.3390/electronics12102323.

杨大勇，黄正栎，郑昌贤，等.基于改进YOLOv8n的茶叶嫩稍检测方法［J］.农业工程学报，2024，40（12）：165-173.YANG D Y，HUANG Z Y，ZHENG C X，et al.Detecting tea shoots using improved YOLOv8n［J］.Transactions of the CSAE，2024，40（12）：165-173 （in Chinese with English abstract） .

MA X，DAI X Y，BAI Y，et al.Rewrite the stars［C］//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）， June 16-22，2024 ，Seattle，WA，USA.Seattle：IEEE，2024：5694-5703.

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）， June 13-19，2020 ，Seattle，WA，USA.Seattle： IEEE，2020：10778-10787.

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， June 18-23，2018 ，Salt Lake City，UT，USA.Salt Lake City IEEE，2018：8759-8768.

WOO S，PARK J，LEE J Y，et al.CBAM：convolutional block attention module［C］//Computer Vision–ECCV 2018： 15th European Conference， September 8–14，2018 ，Munich， Germany.Cham：Springer，2018：3-19.

袁杰，谢霖伟，郭旭，等.基于改进YOLO v7的苹果叶片病害检测方法［J］.农业机械学报，2024，55（11）：68-74.YUAN J，XIE L W，GUO X，et al.Apple leaf disease detection method based on improved YOLO v7［J］.Transactions of the CSAM，2024，55（11）：68-74 （in Chinese with English abstract） .

田有文，覃上声，闫玉博，等.基于改进YOLOv8的田间复杂环境下蓝莓成熟度检测［J］.农业工程学报，2024，40（16）：153-162.TIAN Y W，QIN S S，YAN Y B，et al.Detecting blueberr y maturity under complex field conditions using improved YOLOv8［J］.Transactions of the CSAE，2024，40（16）：153-162 （in Chinese with English abstract） .

GEVORGYAN Z.SIoU loss：more powerful learning for bounding box regression［DB/OL］.arXiv，2022：2205.12740［2025-07-19］.https：//arxiv.org/abs/2205.12740.

WOO S，DEBNATH S，HU R H，et al.ConvNeXt V2：co-designing and scaling ConvNets with masked autoencoders［C］//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）， June 17-24，2023 ，Vancouver，BC，Canada.Vancouver：IEEE，2023：16133-16142.

QIN D F，LEICHNER C，DELAKIS M，et al.MobileNetV4：universal models fortheMobile ecosystem［C］//Computer Vision–ECCV 2024：18th European Conference， September 29–October 4， 2024 ， Milan， Italy.Cham：Springer，2025：78-96.

CAI H，LI J Y，HU M Y，et al.EfficientViT：lightweight multi-scale attention for high-resolution dense prediction［C］//2023 IEEE/CVF International Conference on Computer Vision （ICCV）， October 1-6，2023 ，Paris，France.Paris：IEEE，2024：17256-17267.

REN S Q，HE K M，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks［J］.IEEE transactions on pattern analysis and machine intelligence，2017，39（6）：1137-1149.

LIU W，ANGUELOV D，ERHAN D，et al.SSD：single shot MultiBox detector［C］//Computer Vision–ECCV 2016.Cham：Springer，2016：21-37.

LIN T Y，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection［C］//2017 IEEE International Conference on Computer Vision （ICCV）. October 22-29，2017 ，Venice，Italy.Venice：IEEE，2017：2999-3007.

FU C Y，LIU W，RANGA A，et al.DSSD：deconvolutional single shot detector［DB/OL］.arXiv，2017：1701.06659［2025-07-19］.https：//arxiv.org/abs/1701.06659.

YANG C，HUANG Z H，WANG N Y.QueryDet：cascaded sparse query for accelerating high-resolution small object detection［C］//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR）. June 18-24，2022 ，New Orleans，LA，USA.New Orleans：IEEE，2022：13658-13667.

WANG A，CHEN H，LIU L H，et al.YOLOv10：real-time end-to-end object detection［DB/OL］.arXiv，2024：2405.14458［2025-07-19］.https：//arxiv.org/abs/2405.14458.

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EDW-YOLOv8的棉花叶片病害检测

基于双通道分层协同的CEH-YOLOv8鱼体病害检测方法

基于改进YOLO11的番茄叶片病害检测方法

基于双重注意力机制的鱼类体表病理识别方法

农业生物质增值化利用技术与装备团队