FishTrack22: An Ensemble Dataset for Multi-Object Tracking Evaluation

Tracking fish in optical underwater imagery contains a number of challenges not encountered in terrestrial domains. Video may contain large schools comprised of many individuals, dynamic natural backgrounds, variable target scales, volatile collection conditions, and non-fish moving confusors including debris, marine snow, and other organisms. Lastly, there is a lack of public datasets for algorithm evaluation available in this domain. FishTrack22 aims to address these challenges by providing a large quantity of expert-annotated fish groundtruth tracks, in imagery and video collected across a range of different backgrounds, locations, collection conditions, and organizations. Approximately 1 million bounding boxes across 45k tracks are included in the release of the ensemble, with potential for future growth in later releases.

How to cite
Dawkins Matt, Campbell Matthiew, Prior Jack, Faillettaz Robin, Simon Julien, Lucero Matthew, Banez Thompson, Richards Benjamin, Rollo Audrey, Salvi Mary, Lewis Byron, Davis Brandon, Blue Rusty, Hoogs Anthony, Chaudhary Aashish (2022). FishTrack22: An Ensemble Dataset for Multi-Object Tracking Evaluation. CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling. June 19-24 2022, New Orleans, Louisiana, USA.

Copy this text