Deep learning methods applied to electronic monitoring data: automated catch event detection for longline fishing
Open Access
- 27 December 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in ICES Journal of Marine Science
- Vol. 78 (1) , 25-35
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.Keywords
Funding Information
- CSIRO Research Plus Postdoctoral Fellowship
- Australian Fisheries Management Authority
- Australian Fisheries Management Authority
This publication has 12 references indexed in Scilit:
- Deep neural networks for analysis of fisheries surveillance video and automated monitoring of fish discardsICES Journal of Marine Science, 2019
- Machine intelligence and the data-driven future of marine scienceICES Journal of Marine Science, 2019
- How emerging data technologies can increase trust and transparency in fisheriesICES Journal of Marine Science, 2019
- Opportunities to improve fisheries management through innovative technology and advanced data systemsFish and Fisheries, 2019
- Automatic fish detection in underwater videos by a deep neural network-based hybrid motion learning systemICES Journal of Marine Science, 2019
- A prototype to measure rainbow trout's length using image processingAquacultural Engineering, 2017
- Fish identification from videos captured in uncontrolled underwater environmentsICES Journal of Marine Science, 2016
- Region-Based Convolutional Networks for Accurate Object Detection and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Selecting and interpreting measures of thematic classification accuracyRemote Sensing of Environment, 1997