Version 1
: Received: 10 April 2024 / Approved: 11 April 2024 / Online: 11 April 2024 (09:20:11 CEST)
How to cite:
Jiang, X.; Zhuang, X.; Chen, J.; Zhang, J.; Zhang, Y. YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module. Preprints2024, 2024040779. https://doi.org/10.20944/preprints202404.0779.v1
Jiang, X.; Zhuang, X.; Chen, J.; Zhang, J.; Zhang, Y. YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module. Preprints 2024, 2024040779. https://doi.org/10.20944/preprints202404.0779.v1
Jiang, X.; Zhuang, X.; Chen, J.; Zhang, J.; Zhang, Y. YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module. Preprints2024, 2024040779. https://doi.org/10.20944/preprints202404.0779.v1
APA Style
Jiang, X., Zhuang, X., Chen, J., Zhang, J., & Zhang, Y. (2024). YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module. Preprints. https://doi.org/10.20944/preprints202404.0779.v1
Chicago/Turabian Style
Jiang, X., Jian Zhang and Yiwen Zhang. 2024 "YOLOv8-Mu: An Improved YOLOv8 Underwater Detector Based on Large Kernel Block and Multi-branch Heavy Parameterization Module" Preprints. https://doi.org/10.20944/preprints202404.0779.v1
Abstract
Underwater visual detection technology plays a pivotal role in fields such as marine exploration. With the increasing demand for underwater monitoring, the quest for efficient and reliable methods for underwater target recognition has become particularly significant. To address this requirement, this study developed an innovative underwater object detection architecture based on YOLOv8, named YOLOv8-MU, aimed at significantly enhancing detection accuracy.By integrating the LarK module proposed in UniRepLKNet to optimize the backbone network, YOLOv8-MU aims to achieve a larger receptive field without increasing the model’s depth. Further, this research introduces C2fSTR, an innovative method that combines Swin Transformer with the C2f module. Additionally, we have incorporated the SPPFCSPC_EMA module, which combines Cross-Stage Partial Fast Spatial Pyramid Pooling (SPPFCSPC) with attention mechanisms, significantly improving the detection accuracy and robustness of various biological targets. Moreover, by introducing a fusion block based on DAMO-YOLO into the neck of the model, we further enhanced the model’s capability in multi-scale feature extraction. Finally, the adoption of the MPDIoU loss function, designed around vertex distance, effectively tackles the challenges of localization accuracy and boundary clarity in underwater organism detection. Experimental results on the URPC2019 dataset demonstrate that the YOLOv8-MU model achieved an mAP@0.5 of 78.4%, marking improvements of 5.6%, 1.1%, and 4.0% over YOLOv5s, YOLOv7, and YOLOv8n respectively, indicating the leading performance (SOTA) of this method. On the other hand, further evaluation on the URPC2020 dataset confirmed the generalization capability of the YOLOv8-MU architecture, with its mAP@0.5 reaching 80.4%, surpassing various models including YOLOv5x and YOLOv8n, showcasing the wide applicability of our proposed improved model architecture.
Keywords
object detection; deep learning; YOLOv8; UniRepLKNet; Swin Transformer; SPPFCSPC
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
