Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discards

French, Geoffrey, Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880, Fisher, Mark, Holah, Helen, Kilburn, Rachel, Campbell, Neil and Needle, Coby (2020) Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discards. ICES Journal of Marine Science, 77 (4). 1340–1353. ISSN 1054-3139

[thumbnail of Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discards]
Preview
PDF (Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discards) - Accepted Version
Available under License Unspecified licence.

Download (1MB) | Preview

Abstract

We report on the development of a computer vision system that analyses video from CCTV systems installed on fishing trawlers for the purpose of monitoring and quantifying discarded fish catch. Our system is designed to operate in spite of the challenging computer vision problem posed by conditions on-board fishing trawlers. We describe the approaches developed for isolating and segmenting individual fish and for species classification. We present an analysis of the variability of manual species identification performed by expert human observers and contrast the performance of our species classifier against this benchmark. We also quantify the effect of the domain gap on the performance of modern deep neural network-based computer vision systems.

Item Type: Article
Additional Information: Funding information: This work was funded under the European Union Horizon 2020 SMARTFISH project, Grant Agreement No. 773521.
Uncontrolled Keywords: computer vision and cctv,deep learning,oceanography,ecology, evolution, behavior and systematics,aquatic science,ecology ,/dk/atira/pure/subjectarea/asjc/1900/1910
Faculty \ School: Faculty of Science > School of Computing Sciences
UEA Research Groups: Faculty of Science > Research Groups > Colour and Imaging Lab
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 05 Sep 2019 08:30
Last Modified: 17 Jun 2024 08:30
URI: https://ueaeprints.uea.ac.uk/id/eprint/72106
DOI: 10.1093/icesjms/fsz149

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item