An Underwater Target Wake Detection in Multi-Source Images Based on Improved YOLOv5

In the marine environment, underwater targets improve "stealth" performance through innovation in technology, so traditional target tracking methods are difficult to use for tracking underwater targets stably and accurately. This paper proposes an improved YOLOv5 (You Look Only Once) based method to detect the wake of the underwater target accurately in multi-source images. We obtain optical images and thermal images through model simulation and scaled experiment. Improve the generalization ability of the detection network through data augmentation. The proposed method introduces linear features detection to enhance feature propagation, and promote feature reuse. The result shows that the proposed method is better than the original object detection algorithms. The improved algorithm can detect underwater targets status (underwater or surface) and image types (optical wake or thermal wake).