Fish Tracking Challenge 2024: A Multi-Object Tracking Competition with Sweetfish Schooling Data

TL;DR

The Fish Tracking Challenge 2024 is a competition that uses the SweetFish dataset to develop and evaluate multi-object tracking algorithms for schooling sweetfish, aiming to advance aquatic animal movement analysis.

Contribution

It introduces a new dataset and competition focused on multi-object tracking of schooling fish, fostering innovation in aquatic animal tracking methods.

Findings

Baseline and winning approaches analyzed

Enhanced tracking accuracy demonstrated

Potential for scientific insights into fish behavior

Abstract

The study of collective animal behavior, especially in aquatic environments, presents unique challenges and opportunities for understanding movement and interaction patterns in the field of ethology, ecology, and bio-navigation. The Fish Tracking Challenge 2024 (https://ftc-2024.github.io/) introduces a multi-object tracking competition focused on the intricate behaviors of schooling sweetfish. Using the SweetFish dataset, participants are tasked with developing advanced tracking models to accurately monitor the locations of 10 sweetfishes simultaneously. This paper introduces the competition's background, objectives, the SweetFish dataset, and the appraoches of the 1st to 3rd winners and our baseline. By leveraging video data and bounding box annotations, the competition aims to foster innovation in automatic detection and tracking algorithms, addressing the complexities of aquatic animal movements. The challenge provides the importance of multi-object tracking for discovering the dynamics of collective animal behavior, with the potential to significantly advance scientific understanding in the above fields.