Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video

French, Geoffrey, Fisher, Mark, Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880 and Needle, Coby (2015) Convolutional Neural Networks for Counting Fish in Fisheries Surveillance Video. In: Proceedings of the Machine Vision of Animals and their Behaviour (MVAB). BMVA Press, GBR. ISBN 1-901725-57-X

[thumbnail of MVAB_workshop_paper_11 (Submitted Manuscript)]
Preview
PDF (MVAB_workshop_paper_11 (Submitted Manuscript)) - Draft Version
Download (2MB) | Preview
[thumbnail of AppendixB (Best Paper Award)]
Preview
PDF (AppendixB (Best Paper Award)) - Draft Version
Download (227kB) | Preview

Abstract

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.

Item Type: Book Section
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Interactive Graphics and Audio
Faculty of Science > Research Groups > Colour and Imaging Lab
Related URLs:
Depositing User: Pure Connector
Date Deposited: 01 Dec 2015 07:36
Last Modified: 18 Jun 2024 23:47
URI: https://ueaeprints.uea.ac.uk/id/eprint/55574
DOI: 10.5244/C.29.MVAB.7

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item