BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection
Sensors · 20.11.2024 · 24 (22) · 7411
DOI: 10.3390/s24227411 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.11.2024. Verfasst von Ruicheng Cao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Cybersecurity, Northwestern Polytechnical University, Xi'an 710072, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hainan province.
Abstract (Originalsprache)
Degraded underwater images decrease the accuracy of underwater object detection. Existing research uses image enhancement methods to improve the visual quality of images, which may not be beneficial in underwater image detection and lead to serious degradation in detector performance. To alleviate this problem, we proposed a bidirectional guided method for underwater object detection, referred to as BG-YOLO. In the proposed method, a network is organized by constructing an image enhancement branch and an object detection branch in a parallel manner. The image enhancement branch consists of a cascade of an image enhancement subnet and object detection subnet. The object detection branch only consists of a detection subnet. A feature-guided module connects the shallow convolution layers of the two branches. When training the image enhancement branch, the object detection subnet in the enhancement branch guides the image enhancement subnet to be optimized towards the direction that is most conducive to the detection task. The shallow feature map of the trained image enhancement branch is output to the feature-guided module, constraining the optimization of the object detection branch through consistency loss and prompting the object detection branch to learn more detailed information about the objects. This enhances the detection performance. During the detection tasks, only the object detection branch is reserved so that no additional computational cost is introduced. Extensive experiments demonstrate that the proposed method significantly improves the detection performance of the YOLOv5s object detection network (the mAP is increased by up to 2.9%) and maintains the same inference speed as YOLOv5s (132 fps).
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Cybersecurity, Northwestern Polytechnical University, Xi'an 710072, China.
- College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China.
- College of Computer Science, Chongqing University, Chongqin 400044, China.
- School of Tropical Agriculture and Forestry, Hainan University, Haikou 571158, China.
ORCID-Profile: Ruicheng Cao, Ruiteng Zhang, Xinyue Yan, Jian Zhang
Förderung
- Natural Science Foundation of Hainan province
Zitieren
APA
Cao, R., Zhang, R., Yan, X., & Zhang, J. (2024). BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection. Sensors, 24(22), 7411. https://doi.org/10.3390/s24227411
Vancouver
Cao R, Zhang R, Yan X, Zhang J. BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection. Sensors. 2024;24(22):7411. doi:10.3390/s24227411
BibTeX
@article{Cao2024,
author = {Cao, Ruicheng and Zhang, Ruiteng and Yan, Xinyue and Zhang, Jian},
title = {BG-YOLO: A Bidirectional-Guided Method for Underwater Object Detection},
journal = {Sensors},
year = {2024},
volume = {24},
number = {22},
pages = {7411},
doi = {10.3390/s24227411}
}
EUVIMED