SID-YOLOv5: Improved Object Detection Algorithm for Sea Surface Scenes
Accurate detection of objects on the sea surface is a crucial aspect of intelligent perception for smart ships. To tackle the challenges of difficult small object detection., poor detection accuracy., and low real-time performance in sea surface scenes, we propose a target detection algorithm called SID-YOLOv5, which incorporates the sliding window mechanism, involution operator, and decoupled detection heads. To train and evaluate the performance of the proposed method, we construct a dataset for sea surface scene object detection and conduct experiments to compare and verify the effectiveness of the proposed method against existing algorithms.
Authors
- Jianfeng Hu (ORCID: https://orcid.org/0000-0002-0669-4328)
- Hao Chang (ORCID: https://orcid.org/0000-0001-7082-2526)
- Xingang Pan (ORCID: https://orcid.org/0000-0002-5825-9467)
- Shubao Wang
- Li Xu (ORCID: https://orcid.org/0000-0002-1359-0164)
- Kun Shang (ORCID: https://orcid.org/0000-0003-3826-1102)
Institutions
- Hunan University (CN)
- Inner Mongolia Electric Power Survey & Design Institute (China) (CN)
Publication Details
- Published
- 2024-11-01
- DOI
- https://doi.org/10.1109/cac63892.2024.10865615
- Primary Topic
- Oil Spill Detection and Mitigation
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- National Defense Pre-Research Foundation of China
- Joint Fund of the National Natural Science Foundation of China and the Karst Science Research Center of Guizhou Province