Paper
16 August 2024 Floating debris detection algorithm based on modified YOLOv8 network
Jianwen Zheng, Zhihuan Hu, Yufan Fang, Weidong Zhang
Author Affiliations +
Proceedings Volume 13230, Third International Conference on Machine Vision, Automatic Identification, and Detection (MVAID 2024); 132302Y (2024) https://doi.org/10.1117/12.3036625
Event: Third International Conference on Machine Vision, Automatic Identification and Detection, 2024, Kunming, China
Abstract
The detection technology for floating debris plays a vital role in environmental protection tasks. This paper addresses challenges including surface reflection interference, shore background interference, and insufficient accuracy in recognizing small objects. To figure out these issues, an enhanced GST-YOLOv8 object detection method is proposed to improve detection accuracy in this paper. The improvement is achieved by introducing a global attention layer in the backbone network to facilitate the concentration of critical image information, enhancing processing efficiency. Additionally, a small object perception layer is incorporated into the neck network to enhance the perception of shallow-level information during detection. This perception layer leads to improved accuracy in detecting small objects. Comparative experiments and ablation experiments conducted on a dedicated public dataset illustrate the efficacy of the enhanced method.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jianwen Zheng, Zhihuan Hu, Yufan Fang, and Weidong Zhang "Floating debris detection algorithm based on modified YOLOv8 network", Proc. SPIE 13230, Third International Conference on Machine Vision, Automatic Identification, and Detection (MVAID 2024), 132302Y (16 August 2024); https://doi.org/10.1117/12.3036625
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Object detection

Detection and tracking algorithms

Feature extraction

Neck

Ablation

Education and training

Head

Back to Top