Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing

Khokher, MR; Little, LR; Tuck, GN; Smith, DV; Qiao, M; Devine, C; O’neill, H; Pogonoski, JJ; Arangio, R; Wang, D

Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing

Khokher, MR Little, LR Tuck, GN Smith, DV Qiao, M

Devine, C O’neill, H Pogonoski, JJ Arangio, R Wang, D

Permalink

Publisher:: Canadian Science Publishing
Publication Type:: Journal Article
Citation:: Canadian Journal of Fisheries and Aquatic Sciences, 2022, 79, (2), pp. 257-266
Issue Date:: 2022-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (4.76 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Khokher, MR
dc.contributor.author	Little, LR
dc.contributor.author	Tuck, GN
dc.contributor.author	Smith, DV
dc.contributor.author	Qiao, M https://orcid.org/0000-0002-0990-5506
dc.contributor.author	Devine, C
dc.contributor.author	O’neill, H
dc.contributor.author	Pogonoski, JJ
dc.contributor.author	Arangio, R
dc.contributor.author	Wang, D
dc.date.accessioned	2023-03-22T04:03:48Z
dc.date.available	2023-03-22T04:03:48Z
dc.date.issued	2022-01-01
dc.identifier.citation	Canadian Journal of Fisheries and Aquatic Sciences, 2022, 79, (2), pp. 257-266
dc.identifier.issn	0706-652X
dc.identifier.issn	1205-7533
dc.identifier.uri	http://hdl.handle.net/10453/168055
dc.description.abstract	Electronic monitoring (EM) is increasingly used to monitor catch and bycatch in wild capture fisheries. EM video data are still manually reviewed and adds to ongoing management costs. Computer vision, machine learning, and artificial intelligence-based systems are seen to be the next step in automating EM data workflows. Here we show some of the obstacles we have confronted and approaches taken as we develop a system to automatically identify and count target and bycatch species using cameras deployed to an industry vessel. A Convolutional Neural Network was trained to detect and classify target and bycatch species groups, and a visual tracking system was developed to produce counts. The multiclass detector achieved a mean average precision of 53.42%. Based on the detection results, the visual tracking system provided automatic fish counts for the test video data. Automatic counts were within two standard deviations of the manual counts for the target species and most times for the bycatch species. Unlike other recent attempts, weather and lighting conditions were largely controlled by mounting cameras under cover.
dc.language	en
dc.publisher	Canadian Science Publishing
dc.relation.ispartof	Canadian Journal of Fisheries and Aquatic Sciences
dc.relation.isbasedon	10.1139/cjfas-2020-0446
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0602 Ecology, 0608 Zoology, 0704 Fisheries Sciences
dc.subject.classification	Fisheries
dc.title	Early lessons in deploying cameras and artificial intelligence technology for fisheries catch monitoring: where machine learning meets commercial fishing
dc.type	Journal Article
utslib.citation.volume	79
utslib.for	0602 Ecology
utslib.for	0608 Zoology
utslib.for	0704 Fisheries Sciences
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	open_access	*
dc.date.updated	2023-03-22T04:03:45Z
pubs.issue	2
pubs.publication-status	Published
pubs.volume	79
utslib.citation.issue	2

Abstract:

Electronic monitoring (EM) is increasingly used to monitor catch and bycatch in wild capture fisheries. EM video data are still manually reviewed and adds to ongoing management costs. Computer vision, machine learning, and artificial intelligence-based systems are seen to be the next step in automating EM data workflows. Here we show some of the obstacles we have confronted and approaches taken as we develop a system to automatically identify and count target and bycatch species using cameras deployed to an industry vessel. A Convolutional Neural Network was trained to detect and classify target and bycatch species groups, and a visual tracking system was developed to produce counts. The multiclass detector achieved a mean average precision of 53.42%. Based on the detection results, the visual tracking system provided automatic fish counts for the test video data. Automatic counts were within two standard deviations of the manual counts for the target species and most times for the bycatch species. Unlike other recent attempts, weather and lighting conditions were largely controlled by mounting cameras under cover.

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

http://hdl.handle.net/10453/168055