Fish School Detection Algorithm Improved Based on Yolov5

Water conservancy experts obtain fish school information through analyzing sonar videos, providing objective basis for the construction of fishway and guiding their construction. In order to reduce the missed detection rate of object detection in video analysis, a position attention module was introduced on YOLOv5s to enhance the expression ability of learning features in mobile networks; Introducing a coordinate attention module allows the network to understand the spatial relationships between objects in the image, perceive coordinate information to a certain extent, and improve detection performance. Final, the enhanced model outperforms the original YOLOv5s model by improving mAP0.5:0.95 by 1.3% and Recall by 2.58%.