Underwater-Yolo: Underwater Object Detection Network with Dilated Deformable Convolutions and Dual-Branch Occlusion Attention Mechanism
Journal of Marine Science and Engineering · 12.12.2024 · 12 (12) · 2291
DOI: 10.3390/jmse12122291 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 12.12.2024. Verfasst von Zhenming Li und 9 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Southern Marine Science and Engineering Guangdong Laboratory.
Abstract (Originalsprache)
Underwater object detection is critical for marine ecological monitoring and biodiversity research, yet existing algorithms struggle in detecting densely packed objects of varying sizes, particularly in occluded and complex underwater environments. This study introduces Underwater-Yolo, a novel detection network that enhances performance in these challenging scenarios by integrating a dual-branch occlusion-handling attention mechanism (GLOAM) and a Cross-Stage Partial Dilated Deformable Convolution (CSP-DDC) backbone. The dilated deformable convolutions (DDCs) in the backbone and neck expand the receptive field, thereby improving the detection of small objects, while the deformable convolutions enhance the model’s adaptive feature extraction capabilities for unstructured objects. Additionally, the CARAFE up-sampling operator in the neck aggregates contextual information across a broader spatial domain. The GLOAM, consisting of a global branch (using a Vision Transformer to capture global features and object–background relationships) and a local branch (enhancing the detection of occluded objects through depthwise–pointwise convolutions), further optimizes performance. By incorporating these innovations, the model effectively addresses the challenges of detecting small and occluded objects in dense underwater environments. The evaluation on the CLfish-V1 dataset shows significant improvements over state-of-the-art algorithms, with an AP50 of 93.8%, an AP75 of 88.9%, and an AP-small of 76.4%, marking gains of 4.7%, 16.7%, and 6%, respectively. These results demonstrate the model’s effectiveness in complex underwater scenarios.
Förderung
- Southern Marine Science and Engineering Guangdong Laboratory
Zitieren
APA
Li, Z., Zheng, B., Chao, D., Zhu, W., Li, H., Duan, J., Zhang, X., Zhang, Z., Fu, W., & Zhang, Y. (2024). Underwater-Yolo: Underwater Object Detection Network with Dilated Deformable Convolutions and Dual-Branch Occlusion Attention Mechanism. Journal of Marine Science and Engineering, 12(12), 2291. https://doi.org/10.3390/jmse12122291
Vancouver
Li Z, Zheng B, Chao D, Zhu W, Li H, Duan J, et al. Underwater-Yolo: Underwater Object Detection Network with Dilated Deformable Convolutions and Dual-Branch Occlusion Attention Mechanism. Journal of Marine Science and Engineering. 2024;12(12):2291. doi:10.3390/jmse12122291
BibTeX
@article{Li2024,
author = {Li, Zhenming and Zheng, Bing and Chao, Dong and Zhu, Wenbo and Li, Haibing and Duan, Jin and Zhang, Xinming and Zhang, Zhongbo and Fu, Weijie and Zhang, Yunzhi},
title = {Underwater-Yolo: Underwater Object Detection Network with Dilated Deformable Convolutions and Dual-Branch Occlusion Attention Mechanism},
journal = {Journal of Marine Science and Engineering},
year = {2024},
volume = {12},
number = {12},
pages = {2291},
doi = {10.3390/jmse12122291}
}
EUVIMED