FishTrack22: An Ensemble Dataset for Multi-Object Tracking Evaluation
| Type | Poster | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Date | 2022-06 | ||||||||
| Language | English | ||||||||
| Other localization | https://www.cv4animals.com/ | ||||||||
| Author(s) | Dawkins Matt1, Campbell Matthiew2, Prior Jack2, Faillettaz Robin 3, Simon Julien3, Lucero Matthew4, Banez Thompson4, Richards Benjamin2, Rollo Audrey2, Salvi Mary1, Lewis Byron1, Davis Brandon1, Blue Rusty1, Hoogs Anthony1, Chaudhary Aashish1 |
||||||||
| Affiliation(s) | 1 : Kitware Inc, USA 2 : NOAA Fisheries, USA 3 : Ifremer, France 4 : California Department of Fish and Wildlife, USA |
||||||||
| Meeting | CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling. June 19-24 2022, New Orleans, Louisiana, USA | ||||||||
| Abstract | 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. |
||||||||
| Full Text |
|