Underwater Dense Targets Detection and Classification based on YOLOv3

摘要

In order to meet the requirements of fast detection and classification of underwater targets during intelligent underwater robot operation, an improved YOLOv3 algorithm named YOLOv3-UW algorithm is proposed to improve the detection accuracy and detection speed. Compared with the YOLOv3 algorithm, the YOLOv3-UW algorithm improves the clusters algorithm of data sets, optimizes the network structure, and improves the residual module. The final experimental results show that detection speed and detection accuracy of the YOLOv3-UW algorithm are higher than the YOLOv3 algorithm.