Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

University of Victoria

$80,000.00

Towards Sustainable Fisheries: Computer Vision Methods for the Automatic Analysis of Fishing Imagery

FY 2023-24

Summary
The goal of the proposed research is to develop new computational methods for analyzing fishing video data automatically in the context of sustainable fisheries and environmental monitoring, using artificial intelligence (AI) and computer vision techniques. The video data are captured by cameras on board fishing vessels as part of electronic monitoring (EM) systems that provide valuable information about the sustainability of fisheries, stock assessments, regulatory compliance, and the state and health of marine ecosystems, while also supporting data-driven management decision and accountability. EM videos are currently reviewed by human reviewers who have to spend hours and hours sifting through the recordings for compliance and accountability purposes, which incurs high processing costs and may yield inconsistent results.This research is carried out in partnership with Archipelago, a company headquartered in Victoria, BC that provides marine resource management products and services to a diverse clientele, including regulators, non-governmental organizations (NGOs), and the fishing industry, to help develop cost-effective solutions for sustainable practices. It will contribute to the professional development of highly qualified personnel in cutting-edge CV and AI applications, who will gain skills that are in high demand in the Canadian academic and industrial sectors. The potential impacts of this research are significant with respect to efforts in sustainable fisheries and environmental monitoring, allowing for a switch from the traditional time-consuming, error-prone manual video analyses towards novel automatic AI methods.The topic is of high importance to Canada as a leader in ocean resource management and sustainable and ethical fisheries. The developed methods will benefit Canada by providing various Canadian stakeholders, including government agencies, NGOs, scientists and researchers in marine sciences, as well as fisheries managers and operators, with improved, economical, and timely means for EM video reviews and analyses.
Program
Alliance Grants
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
588178-2023
Name nom
Branzan Albu, Alexandra A
Department département
Electrical and Computer Engineering
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
80000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
402
Area of application group en
Environment
Area of application group fr
Environnement
Area of application en
Oceans, seas and estuaries
Area of application fr
Océans, mers et estuaires
Research subject code
2708
Research subject group en
Information technology
Research subject group fr
Image processing
Research subject en
Technologie de l'information
Research subject fr
Traitement des images
Application title
Towards Sustainable Fisheries: Computer Vision Methods for the Automatic Analysis of Fishing Imagery
Keyword
action recognition; automatic detection; computer vision; deep learning; electronic monitoring; image processing; pattern recognition; sustainable fisheries; video processing and analysis; video summarization
Application summary
The goal of the proposed research is to develop new computational methods for analyzing fishing video data automatically in the context of sustainable fisheries and environmental monitoring, using artificial intelligence (AI) and computer vision techniques. The video data are captured by cameras on board fishing vessels as part of electronic monitoring (EM) systems that provide valuable information about the sustainability of fisheries, stock assessments, regulatory compliance, and the state and health of marine ecosystems, while also supporting data-driven management decision and accountability. EM videos are currently reviewed by human reviewers who have to spend hours and hours sifting through the recordings for compliance and accountability purposes, which incurs high processing costs and may yield inconsistent results.This research is carried out in partnership with Archipelago, a company headquartered in Victoria, BC that provides marine resource management products and services to a diverse clientele, including regulators, non-governmental organizations (NGOs), and the fishing industry, to help develop cost-effective solutions for sustainable practices. It will contribute to the professional development of highly qualified personnel in cutting-edge CV and AI applications, who will gain skills that are in high demand in the Canadian academic and industrial sectors. The potential impacts of this research are significant with respect to efforts in sustainable fisheries and environmental monitoring, allowing for a switch from the traditional time-consuming, error-prone manual video analyses towards novel automatic AI methods.The topic is of high importance to Canada as a leader in ocean resource management and sustainable and ethical fisheries. The developed methods will benefit Canada by providing various Canadian stakeholders, including government agencies, NGOs, scientists and researchers in marine sciences, as well as fisheries managers and operators, with improved, economical, and timely means for EM video reviews and analyses.
University of Victoria - $80,000 Grant (2023-24) | Canada Spends