Deep Convolutional Neural Networkによる漁業種類認識

抄録

This paper presents a method for the recognition of fishery types using Deep Convolutional Neural Network. As fishing boat acci-dents are among the highest causes of marine accidents involving death and missing people in Japan, countermeasures are in urgent demand. To prevent collisions between fishing boats and merchant ships, navigators are required to have knowledge in fishery types. This study aims to develop a fishery types recognition system to support navigators in their lookout and to decrease collisions be-tween fishing boats and merchant ships. Experimental results indicate that the trained network has the accuracy of fishery types recognition of 92.38%.