Building an image library for fisheries
Electronic monitoring is increasingly being utilized in fisheries in the US and internationally to collect catch data. This comes with a significant need for efficient video processing. The aim of this project was to develop a training data set for artificial intelligence (AI) algorithms by leveraging existing at-sea fish processing that occurs as a part of semi-annual fish trawl surveys conducted by NOAA. This survey samples large quantities of fish that are caught by vessels in the Northeast Multispecies Groundfish Fishery and supplies expert species identifications.
NOAA hired CVision AI to install computer vision cameras in the wet lab on the Henry B. Bigelow. The cameras were installed in collaboration with New England Marine Monitoring (NEMM). Over the course of a year, 600 hours of video was collected from four sampling stations. Data was annotated and an object detection and tracking algorithm was developed. After inference, the dataset contains 45 million bounding boxes around individual fish, labeled by species using ground truth data from NOAA's Fisheries Scientific Computing System (FSCS).
