An Improved YOLOv8 and OC-SORT Framework for Fish Counting

Accurate fish population estimation is crucial for fisheries management, ecological monitoring, and aquaculture optimization. Traditional manual counting methods are labor-intensive and error-prone, while existing automated approaches struggle with occlusions, small-object detection, and identity sw...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Li, Zhenpeng Wu, Ying Yu, Chichi Liu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/6/1016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432569900171264
author Yan Li
Zhenpeng Wu
Ying Yu
Chichi Liu
author_facet Yan Li
Zhenpeng Wu
Ying Yu
Chichi Liu
author_sort Yan Li
collection DOAJ
description Accurate fish population estimation is crucial for fisheries management, ecological monitoring, and aquaculture optimization. Traditional manual counting methods are labor-intensive and error-prone, while existing automated approaches struggle with occlusions, small-object detection, and identity switches. To address these challenges, this paper proposes an improved fish counting framework integrating YOLOv8-DT for detection and Byte-OCSORT for tracking. YOLOv8-DT incorporates the Deformable Large Kernel Attention Cross Stage Partial (DLKA CSP) module for adaptive receptive field adjustment and the Triple Detail Feature Infusion (TDFI) module for enhanced multi-scale feature fusion, improving small-object detection and occlusion robustness. Byte-OCSORT extends OC-SORT by integrating ByteTrack’s two-stage matching and a Class-Aware Cost Matrix (CCM), reducing ID switches and improving multi-species tracking stability. Experimental results on real-world underwater datasets demonstrate that YOLOv8-DT achieves a mAP<sub>50</sub> of 0.971 and mAP<sub>50:95</sub> of 0.742, while Byte-OCSORT reaches a MOTA of 72.3 and IDF1 of 69.4, significantly outperforming existing methods, confirming the effectiveness of the proposed framework for robust and accurate fish counting in complex aquatic environments.
format Article
id doaj-art-821f73385f5a42ca93cc567cdc8d1ebd
institution Kabale University
issn 2077-1312
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-821f73385f5a42ca93cc567cdc8d1ebd2025-08-20T03:27:19ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-01136101610.3390/jmse13061016An Improved YOLOv8 and OC-SORT Framework for Fish CountingYan Li0Zhenpeng Wu1Ying Yu2Chichi Liu3State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, ChinaState Key Laboratory of Marine Environmental Science, College of Ocean and Earth Sciences, Xiamen University, Xiamen 361105, ChinaAccurate fish population estimation is crucial for fisheries management, ecological monitoring, and aquaculture optimization. Traditional manual counting methods are labor-intensive and error-prone, while existing automated approaches struggle with occlusions, small-object detection, and identity switches. To address these challenges, this paper proposes an improved fish counting framework integrating YOLOv8-DT for detection and Byte-OCSORT for tracking. YOLOv8-DT incorporates the Deformable Large Kernel Attention Cross Stage Partial (DLKA CSP) module for adaptive receptive field adjustment and the Triple Detail Feature Infusion (TDFI) module for enhanced multi-scale feature fusion, improving small-object detection and occlusion robustness. Byte-OCSORT extends OC-SORT by integrating ByteTrack’s two-stage matching and a Class-Aware Cost Matrix (CCM), reducing ID switches and improving multi-species tracking stability. Experimental results on real-world underwater datasets demonstrate that YOLOv8-DT achieves a mAP<sub>50</sub> of 0.971 and mAP<sub>50:95</sub> of 0.742, while Byte-OCSORT reaches a MOTA of 72.3 and IDF1 of 69.4, significantly outperforming existing methods, confirming the effectiveness of the proposed framework for robust and accurate fish counting in complex aquatic environments.https://www.mdpi.com/2077-1312/13/6/1016fish countingobject detectionmulti-object trackingYOLOv8-DTByte-OCSORTunderwater fish monitoring
spellingShingle Yan Li
Zhenpeng Wu
Ying Yu
Chichi Liu
An Improved YOLOv8 and OC-SORT Framework for Fish Counting
Journal of Marine Science and Engineering
fish counting
object detection
multi-object tracking
YOLOv8-DT
Byte-OCSORT
underwater fish monitoring
title An Improved YOLOv8 and OC-SORT Framework for Fish Counting
title_full An Improved YOLOv8 and OC-SORT Framework for Fish Counting
title_fullStr An Improved YOLOv8 and OC-SORT Framework for Fish Counting
title_full_unstemmed An Improved YOLOv8 and OC-SORT Framework for Fish Counting
title_short An Improved YOLOv8 and OC-SORT Framework for Fish Counting
title_sort improved yolov8 and oc sort framework for fish counting
topic fish counting
object detection
multi-object tracking
YOLOv8-DT
Byte-OCSORT
underwater fish monitoring
url https://www.mdpi.com/2077-1312/13/6/1016
work_keys_str_mv AT yanli animprovedyolov8andocsortframeworkforfishcounting
AT zhenpengwu animprovedyolov8andocsortframeworkforfishcounting
AT yingyu animprovedyolov8andocsortframeworkforfishcounting
AT chichiliu animprovedyolov8andocsortframeworkforfishcounting
AT yanli improvedyolov8andocsortframeworkforfishcounting
AT zhenpengwu improvedyolov8andocsortframeworkforfishcounting
AT yingyu improvedyolov8andocsortframeworkforfishcounting
AT chichiliu improvedyolov8andocsortframeworkforfishcounting