Deep learning methods applied to electronic monitoring data: Automated catch event detection for longline fishing

Qiao, M; Wang, D; Tuck, GN; Little, LR; Punt, AE; Gerner, M

Deep learning methods applied to electronic monitoring data: Automated catch event detection for longline fishing

Qiao, M

Wang, D Tuck, GN Little, LR Punt, AE Gerner, M

Permalink

Publisher:: Oxford University Press (OUP)
Publication Type:: Journal Article
Citation:: ICES Journal of Marine Science, 2021, 78, (1), pp. 25-35
Issue Date:: 2021-01-01

Closed Access

	Filename	Description	Size
	fsaa158 (1).pdf	Published version	1 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Qiao, M https://orcid.org/0000-0002-0990-5506
dc.contributor.author	Wang, D
dc.contributor.author	Tuck, GN
dc.contributor.author	Little, LR
dc.contributor.author	Punt, AE
dc.contributor.author	Gerner, M
dc.contributor.editor	Beyan, C
dc.date.accessioned	2023-03-08T01:06:39Z
dc.date.available	2023-03-08T01:06:39Z
dc.date.issued	2021-01-01
dc.identifier.citation	ICES Journal of Marine Science, 2021, 78, (1), pp. 25-35
dc.identifier.issn	1054-3139
dc.identifier.issn	1095-9289
dc.identifier.uri	http://hdl.handle.net/10453/166702
dc.description.abstract	Electronic monitoring (EM) systems have become functional and cost-effective tools for the conservation and sustainable harvesting of marine resources. EM is an alternative to on-board observers, which produces video segments that can subsequently be reviewed by analysts. It is currently used in a range of fisheries. There are two major challenges to the widespread adoption of EM. One is the large storage requirement for the video footage recorded and the other is the long time required by analysts to review the video footage. We propose an automated catch event detection framework to address these challenges. Our solution, based on deep learning techniques, automatically extracts video segments of catch events, which substantially reduces storage space and review time by analysts. Here, we demonstrate the framework using video footage from three longline fishing trips. The system recalled nearly 100% of the catch events across all trips.
dc.language	en
dc.publisher	Oxford University Press (OUP)
dc.relation.ispartof	ICES Journal of Marine Science
dc.relation.isbasedon	10.1093/icesjms/fsaa158
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Fisheries
dc.title	Deep learning methods applied to electronic monitoring data: Automated catch event detection for longline fishing
dc.type	Journal Article
utslib.citation.volume	78
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-08T01:06:38Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	78
utslib.citation.issue	1

Abstract:

Electronic monitoring (EM) systems have become functional and cost-effective tools for the conservation and sustainable harvesting of marine resources. EM is an alternative to on-board observers, which produces video segments that can subsequently be reviewed by analysts. It is currently used in a range of fisheries. There are two major challenges to the widespread adoption of EM. One is the large storage requirement for the video footage recorded and the other is the long time required by analysts to review the video footage. We propose an automated catch event detection framework to address these challenges. Our solution, based on deep learning techniques, automatically extracts video segments of catch events, which substantially reduces storage space and review time by analysts. Here, we demonstrate the framework using video footage from three longline fishing trips. The system recalled nearly 100% of the catch events across all trips.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166702