Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video

We present a computer vision tool that analyses video from a CCTV system installed on fishing trawlers to monitor discarded fish catch. The system aims to support expert observers who review the footage and verify numbers, species and sizes of discarded fish. The operational environment presents a significant challenge for these tasks. Fish are processed below deck under fluorescent lights, they are randomly oriented and there are multiple occlusions. The scene is unstructured and complicated by the presence of fishermen processing the catch. We describe an approach to segmenting the scene and counting fish that exploits the $N^4$-Fields algorithm. We performed extensive tests of the algorithm on a data set comprising 443 frames from 6 belts. Results indicate the relative count error (for individual fish) ranges from 2\% to 16\%. We believe this is the first system that is able to handle footage from operational trawlers.