YOLOv8-BaitScan: A Lightweight and Robust Framework for Accurate Bait Detection and Counting in Aquaculture
Fishes · 17.06.2025 · 10 (6) · 294
DOI: 10.3390/fishes10060294 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fishes, online erschienen am 17.06.2025. Verfasst von Jian Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Biological and Medical Sciences of Applied Summit Nurturing Disciplines in Anhui Province, Key projects of natural science research projects in Anhui universities, Scientific research project of Fuyang Normal University.
Abstract (Originalsprache)
Excessive bait wastage is a major issue in aquaculture, leading to higher farming costs, economic losses, and water pollution caused by bacterial growth from unremoved residual bait. To address this problem, we propose a bait residue detection and counting model named YOLOv8-BaitScan, based on an improved YOLO architecture. The key innovations are as follows: (1) By incorporating the channel prior convolutional attention (CPCA) into the final layer of the backbone, the model efficiently extracts spatial relationships and dynamically allocates weights across the channel and spatial dimensions. (2) The minimum points distance intersection over union (MPDIoU) loss function improves the model’s localization accuracy for bait bounding boxes. (3) The structure of the Neck network is optimized by adding a tiny-target detection layer, which improves the recall rate for small, distant bait targets and significantly reduces the miss rate. (4) We design the lightweight detection head named Detect-Efficient, incorporating the GhostConv and C2f-GDC module into the network to effectively reduce the overall number of parameters and computational cost of the model. The experimental results show that YOLOv8-BaitScan achieves strong performance across key metrics: The recall rate increased from 60.8% to 94.4%, mAP@50 rose from 80.1% to 97.1%, and the model’s number of parameters and computational load were reduced by 55.7% and 54.3%, respectively. The model significantly improves the accuracy and real-time detection capabilities for underwater bait and is more suitable for real-world aquaculture applications, providing technical support to achieve both economic and ecological benefits.
Förderung
- Biological and Medical Sciences of Applied Summit Nurturing Disciplines in Anhui Province
- Key projects of natural science research projects in Anhui universities
- Scientific research project of Fuyang Normal University
- School-level Undergraduate Teaching Project of Fuyang Normal University
- Technical Service Contract Between Shenzhen Mairuide Technology Co., Ltd.
Zitieren
APA
Li, J., Zhang, Z., Wei, Y., & Wang, T. (2025). YOLOv8-BaitScan: A Lightweight and Robust Framework for Accurate Bait Detection and Counting in Aquaculture. Fishes, 10(6), 294. https://doi.org/10.3390/fishes10060294
Vancouver
Li J, Zhang Z, Wei Y, Wang T. YOLOv8-BaitScan: A Lightweight and Robust Framework for Accurate Bait Detection and Counting in Aquaculture. Fishes. 2025;10(6):294. doi:10.3390/fishes10060294
BibTeX
@article{Li2025,
author = {Li, Jian and Zhang, Zehao and Wei, Yanan and Wang, Tan},
title = {YOLOv8-BaitScan: A Lightweight and Robust Framework for Accurate Bait Detection and Counting in Aquaculture},
journal = {Fishes},
year = {2025},
volume = {10},
number = {6},
pages = {294},
doi = {10.3390/fishes10060294}
}
EUVIMED