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

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 automat...

Full description

Saved in:
Bibliographic Details
Published in:Canadian journal of fisheries and aquatic sciences 2022-02, Vol.79 (2), p.257-266
Main Authors: Khokher, M. Rizwan, Little, L. Richard, Tuck, Geoffrey N, Smith, Daniel V, Qiao, Maoying, Devine, Carlie, O’Neill, Helen, Pogonoski, John J, Arangio, Rhys, Wang, Dadong
Format: Article
Language:English
Subjects:
Animal populations
Artificial intelligence
Artificial neural networks
Barriers
Bycatch
Cameras
Commercial fishing
Computer vision
Fisheries
Fishery management
Fishery technology
Fishing
Learning algorithms
Machine learning
Management
Monitoring
Neural networks
Optical tracking
Remote sensing
Ships
Species
Species classification
Target detection
Technology application
Tracking systems
Video data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0706-652X
1205-7533
DOI:10.1139/cjfas-2020-0446