YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm
In computer vision applications, the primary task of object detection is to answer the following question: “What object is present and where is it located?”. However, underwater environments introduce challenges, such as poor lighting, high complexity, and diverse marine organism shapes, leading to...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/5/947 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327190137634816 |
|---|---|
| author | Shengfu Luo Chao Dong Guixin Dong Rongmin Chen Bing Zheng Ming Xiang Peng Zhang Zhanwei Li |
| author_facet | Shengfu Luo Chao Dong Guixin Dong Rongmin Chen Bing Zheng Ming Xiang Peng Zhang Zhanwei Li |
| author_sort | Shengfu Luo |
| collection | DOAJ |
| description | In computer vision applications, the primary task of object detection is to answer the following question: “What object is present and where is it located?”. However, underwater environments introduce challenges, such as poor lighting, high complexity, and diverse marine organism shapes, leading to missed detections or false positives in deep learning-based algorithms. To improve detection accuracy and robustness, this paper proposes an enhanced YOLOv11-based algorithm for underwater object detection that strengthens the ability to capture both local and global details and global contextual information in complex underwater environments. To better capture local and global features while integrating contextual information, the proposed method introduces several enhancements. The backbone incorporates a DualBottleneck module to enhance feature extraction, replacing the standard bottleneck structure in C3k, thus enhancing the feature extraction and the channel aggregation. The detection head adopts DyHead-GDC, integrating ghost depthwise separable convolution with DyHead for greater efficiency. Furthermore, the ADown module replaces conventional feature extraction and downsampling convolutions, reducing parameters and FLOPs by 14%. The C2PSF module, combining focal modulation and C2, strengthens local feature extraction and global context processing. Additionally, a SCSA module is inserted before the detection head to fully utilize multi-semantic information, improving the detection performance in complex underwater scenes. Experimental results confirm the effectiveness of these improvements. The model achieves 84.2% mAP50 on UTDAC2020, 84.4% on DUO and 86.7% on RUOD, surpassing the baseline by 2.5%, 1.6% and 1.2%, respectively. It remains lightweight, with 6.5 M parameters and a computational cost of 7.1 GFLOPs. |
| format | Article |
| id | doaj-art-d3bdd1dc928e484a89c8aaa20a2da4c6 |
| institution | Kabale University |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-d3bdd1dc928e484a89c8aaa20a2da4c62025-08-20T03:47:57ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-0113594710.3390/jmse13050947YOLO-DAFS: A Composite-Enhanced Underwater Object Detection AlgorithmShengfu Luo0Chao Dong1Guixin Dong2Rongmin Chen3Bing Zheng4Ming Xiang5Peng Zhang6Zhanwei Li7School of Ocean Engineering and Technology, Sun Yat-sen University, Zhuhai 519082, ChinaKey Laboratory of Marine Environmental Survey Technology and Application, Guangzhou 510300, ChinaChimelong Group Co., Ltd., Guangzhou 511430, ChinaSchool of Ocean Engineering and Technology, Sun Yat-sen University, Zhuhai 519082, ChinaSchool of Ocean Engineering and Technology, Sun Yat-sen University, Zhuhai 519082, ChinaKey Laboratory of Marine Environmental Survey Technology and Application, Guangzhou 510300, ChinaChimelong Group Co., Ltd., Guangzhou 511430, ChinaChimelong Group Co., Ltd., Guangzhou 511430, ChinaIn computer vision applications, the primary task of object detection is to answer the following question: “What object is present and where is it located?”. However, underwater environments introduce challenges, such as poor lighting, high complexity, and diverse marine organism shapes, leading to missed detections or false positives in deep learning-based algorithms. To improve detection accuracy and robustness, this paper proposes an enhanced YOLOv11-based algorithm for underwater object detection that strengthens the ability to capture both local and global details and global contextual information in complex underwater environments. To better capture local and global features while integrating contextual information, the proposed method introduces several enhancements. The backbone incorporates a DualBottleneck module to enhance feature extraction, replacing the standard bottleneck structure in C3k, thus enhancing the feature extraction and the channel aggregation. The detection head adopts DyHead-GDC, integrating ghost depthwise separable convolution with DyHead for greater efficiency. Furthermore, the ADown module replaces conventional feature extraction and downsampling convolutions, reducing parameters and FLOPs by 14%. The C2PSF module, combining focal modulation and C2, strengthens local feature extraction and global context processing. Additionally, a SCSA module is inserted before the detection head to fully utilize multi-semantic information, improving the detection performance in complex underwater scenes. Experimental results confirm the effectiveness of these improvements. The model achieves 84.2% mAP50 on UTDAC2020, 84.4% on DUO and 86.7% on RUOD, surpassing the baseline by 2.5%, 1.6% and 1.2%, respectively. It remains lightweight, with 6.5 M parameters and a computational cost of 7.1 GFLOPs.https://www.mdpi.com/2077-1312/13/5/947underwater object detectionYOLOv11deep learning |
| spellingShingle | Shengfu Luo Chao Dong Guixin Dong Rongmin Chen Bing Zheng Ming Xiang Peng Zhang Zhanwei Li YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm Journal of Marine Science and Engineering underwater object detection YOLOv11 deep learning |
| title | YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm |
| title_full | YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm |
| title_fullStr | YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm |
| title_full_unstemmed | YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm |
| title_short | YOLO-DAFS: A Composite-Enhanced Underwater Object Detection Algorithm |
| title_sort | yolo dafs a composite enhanced underwater object detection algorithm |
| topic | underwater object detection YOLOv11 deep learning |
| url | https://www.mdpi.com/2077-1312/13/5/947 |
| work_keys_str_mv | AT shengfuluo yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT chaodong yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT guixindong yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT rongminchen yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT bingzheng yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT mingxiang yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT pengzhang yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm AT zhanweili yolodafsacompositeenhancedunderwaterobjectdetectionalgorithm |