Monitoring system of jellyfish distribution using an unmanned aerial vehicle in ocean environment

Abstract

In this paper, i propose a jellyfish distribution recognition monitoring system using an UAV (unmanned aerial vehicle). The UAV was designed to satisfy the requirements for flight in ocean environment. The target jellyfish, aurelia aurita, is recognized through convolution neural network and its distribution is calculated. The deep neural network architecture has been developed to have reliable recognition accuracy and fast operation speed. I also introduce the method for selecting candidates that are inputs of the proposed network. The recognition accuracy of the jellyfish is increased by removing the probability value of the meaningless class among the probability vectors of the evaluated input image and re-evaluating it by normalizing it. The jellyfish distribution is calculated based on the unit jellyfish image thus recognized. The distribution level is defined by using the novelty concept of the distribution map buffer.