Lightweight ship target detection algorithm based on improved YOLOv5s

• Published in: Journal of real-time image processing 2024-02, Vol.21 (1), p.3, Article 3
• Main Authors: Qian, Long, Zheng, Yuanzhou, Cao, Jingxin, Ma, Yong, Zhang, Yuanfeng, Liu, Xinyu
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial intelligence; Computer Graphics; Computer networks; Computer Science; Efficiency; Entropy; Frames per second; Image Processing and Computer Vision; Inland waterways; Lightweight; Mathematical models; Model accuracy; Multimedia Information Systems; Navigation; Object recognition; Parameters; Pattern Recognition; Safety management; Scylla; Semantics; Shipping industry; Ships; Signal,Image and Speech Processing; Target detection; Technical services
• ISSN: 1861-8200; 1861-8219
• DOI: 10.1007/s11554-023-01381-w

Accurate identification of ship targets is the key technology of intelligent inland waterway navigation. Given the complicated navigation environment of inland waterway ships and model detection's low accuracy and efficiency, this paper proposes an enhanced detection algorithm MGS-YOLO based on YOLOv5s. Firstly, the original backbone network is replaced by the MobileNetv3 algorithm, and the improved network parameter is only 7.54 MB. Secondly, the Gated Convolution (GnConv) structure is introduced into the original feature fusion module, which effectively improves the spatial interaction ability of feature information at different levels and further reduced the computational complexity of the model. Finally, to further improve the training speed and reasoning accuracy of the model, the SCYLLA-IoU (SIoU) is introduced into MGS-YOLO to effectively solve the problem of mismatching in the direction between the real box and the regression box. The final results show that the mean Average Precision (mAP), F1, and Average Frames Per Second (AVGFPS) of MGS-YOLO reach 0.977, 0.95, and 95.24 on the established ship dataset. It means that MGS-YOLO does not lose prediction accuracy when reducing network parameters and it has certain real-time performance. Comparing with the current representative lightweight learning models YOLOv5s, YOLOv3-tiny, YOLOv4-tiny, and YOLOv7 with good performance, the MGS-YOLO model has higher detection accuracy and efficiency and provides certain technical support for the safety detection and management of inland ships.