In order to enable intelligent underwater robots to quickly and accurately detect underwater magnetic targets in complex underwater environments, a lightweight YOLOv3 algorithm-YOLOv3-Metal is proposed. By improving the structure of the network YOLOv3 and reducing the residual structure to compress the network, the detection speed of the improved algorithm can be increased; the spatial pyramid pooling (SPP) module is introduced by improving the feature fusion network, which can enrich the deep features; by improving the loss function of the basic YOLOv3 algorithm, the detection accuracy of small targets can be improved. Secondly, a crawler program is developed, training data is obtained from the internet and annotated, and data enhancement technology is used to expand the training data. Finally, the underwater magnetic target detection experiment was carried out on the computer workstation and the embedded development board. From the experimental results, it can be concluded that the YOLOv3-Metal algorithm has higher detection accuracy and faster detection speed than the original YOLOv3 algorithm.
Underwater Magnetic Target Detection Method Based on Lightweight YOLOv3
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 10 ; 93-100
2022-03-18
8 pages
Article/Chapter (Book)
Electronic Resource
English
Underwater Magnetic Target Detection Method Based on Lightweight YOLOv3
British Library Conference Proceedings | 2022
|Ship target detection based on YOLOv3 algorithm
IEEE | 2023
|Ship Target Detection Algorithm Based on Improved YOLOv3 for Maritime Image
DOAJ | 2021
|Research on Smart Car Safety Based on YOLOv3 Target Detection Algorithm
Springer Verlag | 2024
|