Side-Scan Sonar Small Objects Detection Based on Improved YOLOv11

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(1), P. 162 - 162

Published: Jan. 18, 2025

Underwater object detection using side-scan sonar (SSS) remains a significant challenge in marine exploration, especially for small objects. Conventional methods face various obstacles, such as difficulties feature extraction and the considerable impact of noise on accuracy. To address these issues, this study proposes an improved YOLOv11 network named YOLOv11-SDC. Specifically, new Sparse Feature (SF) module is proposed, replacing Spatial Pyramid Pooling Fast (SPPF) from original architecture to enhance selection. Furthermore, proposed YOLOv11-SDC integrates Dilated Reparam Block (DRB) with C3k2 broaden model’s receptive field. A Content-Guided Attention Fusion (CGAF) also incorporated prior assign appropriate weights maps, thereby emphasizing relevant information. Experimental results clearly demonstrate superiority over several iterations YOLO versions performance. The method was validated through extensive real-world experiments, yielding precision 0.934, recall 0.698, [email protected] 0.825, [email protected]:0.95 0.598. In conclusion, offers promising solution detecting objects SSS images, showing substantial potential applications.

Language: Английский

Multi-scale detection of underwater objects using attention mechanisms and normalized Wasserstein distance loss

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(6)

Published: April 27, 2025

Language: Английский