Research on Recognition of Marine Ships under Complex Conditions

摘要

The maritime navigation environment is complicated and there are many interference factors. In order to improve the recognition effect of ships under complex weather conditions, a deep learning algorithm based on You Only Look Once (YOLO) V3 is proposed to identify ships, and an improved dark channel defogging algorithm is used to reduce the recognition of clouds and fog as soon as possibly. By the trained convolutional neural network to predict the attributes and types of cargo in this block diagram. Experimental results prove that it can meet the needs of ship identification.