Using deep learning to automate the detection of bird scaring lines on fishing vessels

Acharya, D; Saqib, M; Devine, C; Untiedt, C; Little, LR; Wang, D; Tuck, GN

Using deep learning to automate the detection of bird scaring lines on fishing vessels

Acharya, D Saqib, M

Devine, C Untiedt, C Little, LR Wang, D Tuck, GN

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Biological Conservation, 2024, 296, pp. 110713
Issue Date:: 2024-08-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (2.52 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Acharya, D
dc.contributor.author	Saqib, M https://orcid.org/0000-0003-4374-0888
dc.contributor.author	Devine, C
dc.contributor.author	Untiedt, C
dc.contributor.author	Little, LR
dc.contributor.author	Wang, D
dc.contributor.author	Tuck, GN
dc.date.accessioned	2025-04-07T03:07:05Z
dc.date.available	2025-04-07T03:07:05Z
dc.date.issued	2024-08-01
dc.identifier.citation	Biological Conservation, 2024, 296, pp. 110713
dc.identifier.issn	0006-3207
dc.identifier.uri	http://hdl.handle.net/10453/186721
dc.description.abstract	Bird-scaring lines (BSLs) are an essential on-vessel bycatch mitigation device to reduce seabird interactions with fishing gear, such as the baited hooks of longline vessels. To ensure compliance with the behaviours required to operate successful BSLs, Electronic Monitoring (EM) cameras installed on fishing vessels can facilitate monitoring of commercial fishing activities. This study proposes an Artificial Intelligence and Machine Learning (AIML) framework based on a state-of-the-art deep learning computer vision approach called Faster RCNN to detect BSLs using vessel Electronic Monitoring (EM) video footage. The experiments include comprehensive analysis for detecting BSLs during daytime and night-time using footage from tuna longline vessels, under various weather conditions. Results show that a detection precision of 0.87 can be achieved. This valuable AIML tool can significantly reduce the time and costs associated with reviewing human EM footage, expand coverage, and automatically identify events for compliance checks and endangered species monitoring.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Biological Conservation
dc.relation.isbasedon	10.1016/j.biocon.2024.110713
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	05 Environmental Sciences, 06 Biological Sciences, 07 Agricultural and Veterinary Sciences
dc.subject.classification	Ecology
dc.subject.classification	3103 Ecology
dc.subject.classification	3109 Zoology
dc.subject.classification	4104 Environmental management
dc.title	Using deep learning to automate the detection of bird scaring lines on fishing vessels
dc.type	Journal Article
utslib.citation.volume	296
utslib.for	05 Environmental Sciences
utslib.for	06 Biological Sciences
utslib.for	07 Agricultural and Veterinary 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/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-04-07T03:07:03Z
pubs.publication-status	Published
pubs.volume	296

Abstract:

Bird-scaring lines (BSLs) are an essential on-vessel bycatch mitigation device to reduce seabird interactions with fishing gear, such as the baited hooks of longline vessels. To ensure compliance with the behaviours required to operate successful BSLs, Electronic Monitoring (EM) cameras installed on fishing vessels can facilitate monitoring of commercial fishing activities. This study proposes an Artificial Intelligence and Machine Learning (AIML) framework based on a state-of-the-art deep learning computer vision approach called Faster RCNN to detect BSLs using vessel Electronic Monitoring (EM) video footage. The experiments include comprehensive analysis for detecting BSLs during daytime and night-time using footage from tuna longline vessels, under various weather conditions. Results show that a detection precision of 0.87 can be achieved. This valuable AIML tool can significantly reduce the time and costs associated with reviewing human EM footage, expand coverage, and automatically identify events for compliance checks and endangered species monitoring.

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

http://hdl.handle.net/10453/186721