Region Proposal and Regression Network for Fishing Spots Detection from Sea Temperature

In this paper, we propose a two stage method for predicting the catch of skipjack tuna (Katsuwonus pelamis) from 2D sea temperature pattern. Following by the assumption that sea water temperature which fishermen often use for finding fishing spots has a correlation with the skipjack tuna catch, we propose a new approach of using the technique Faster-RCNN [1] in object detection. Our methods consist of two part. In the first part, taking a sea temperature map as input, faster-RCNN extracts the candidates of where skipjack tuna would be on the map. In the second part, Support Vector Regression (SVR) estimates the catch amount at each candidate. We evaluate our model by comparing the result with average fishermen ability on the skipjack tuna catches.