Marine Object Detection Based on Improved YOLOv5

The detection of marine objects plays an important role in the exploration and exploitation of marine resources and other marine economic activities. Traditional detection methods are inefficient and low in accuracy. With the development of deep learning, YOLO series algorithms have been widely used in various applications. In this paper, an improved algorithm based on YOLOv5 for maritime object detection has been proposed. The improved algorithm modifies the backbone and neck structure of YOLOv5 through attention mechanism and BiFPN. Experimental results show that our proposed algorithm has superior performances and in particular it obtains better detection results for small objects compared with the original YOLOv5 algorithm. The index of mAP is improved by 1%, and the recall rate is improved by 2%.