MAS-YOLOv11: An Improved Underwater Object Detection Algorithm Based on YOLOv11
Sensors · 29.05.2025 · 25 (11) · 3433
DOI: 10.3390/s25113433 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2025. Verfasst von Yang Luo und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou 434023, China. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Observation and Research Station of South Yellow Sea Earth Multi-sphere, MNR.
Abstract (Originalsprache)
To address the challenges of underwater target detection, including complex background interference, light attenuation, severe occlusion, and overlap between targets, as well as the wide-scale variation in objects, we propose MAS-YOLOv11, an improved model integrating three key enhancements: First, we introduce the C2PSA_MSDA module, which integrates multi-scale dilated attention (MSDA) into the C2PSA module of the backbone, enhancing multi-scale feature representation via dilated convolutions and cross-scale attention. Second, an adaptive spatial feature fusion detection head (ASFFHead) replaces the original head. By employing learnable spatial weighting parameters, ASFFHead adaptively fuses features across different scales, significantly improving the robustness of multi-scale object detection. Third, we introduce a Slide Loss function with dynamic sample weighting to enhance hard sample learning. By mapping the loss weights nonlinearly to detection confidence, this mechanism effectively enhances the overall detection accuracy. The experimental results demonstrate that the improved model yields significant performance advancements on the DUO dataset: the recall rate is enhanced by 3.7%, the F1-score is elevated by 3%, and the mAP@50 and mAP@50-95 attain values of 77.4% and 55.1%, respectively, representing increases of 3.5% and 3.3% compared to the baseline model. Furthermore, the model achieves an mAP@50 of 76% on the RUOD dataset, which further corroborates its cross-domain generalization capability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic Information and Electrical Engineering, Yangtze University, Jingzhou 434023, China.
- School of Computing Science and Artificial Intelligent, Suzhou City University, Suzhou 215104, China.
ORCID-Profile: Aiping Wu, Qingqing Fu
Förderung
- National Natural Science Foundation of China
- Observation and Research Station of South Yellow Sea Earth Multi-sphere, MNR
Zitieren
APA
Luo, Y., Wu, A., & Fu, Q. (2025). MAS-YOLOv11: An Improved Underwater Object Detection Algorithm Based on YOLOv11. Sensors, 25(11), 3433. https://doi.org/10.3390/s25113433
Vancouver
Luo Y, Wu A, Fu Q. MAS-YOLOv11: An Improved Underwater Object Detection Algorithm Based on YOLOv11. Sensors. 2025;25(11):3433. doi:10.3390/s25113433
BibTeX
@article{Luo2025,
author = {Luo, Yang and Wu, Aiping and Fu, Qingqing},
title = {MAS-YOLOv11: An Improved Underwater Object Detection Algorithm Based on YOLOv11},
journal = {Sensors},
year = {2025},
volume = {25},
number = {11},
pages = {3433},
doi = {10.3390/s25113433}
}
EUVIMED