Motion-Driven Multi-Object Tracking of Model Organisms in Space Science Experiments

TL;DR

This paper introduces ART-Track, a motion-driven multi-object tracking framework designed for space science experiments involving model organisms, addressing challenges like low-quality imaging and complex behaviors.

Contribution

The paper presents a novel motion-driven tracking method with multi-model motion estimation, motion-state-driven association, and uncertainty-adaptive fusion tailored for microgravity biological videos.

Findings

Significantly reduces identity switches in zebrafish and fruitfly sequences.

Maintains stable tracking under occlusion, deformation, and high-density interactions.

Provides a reliable foundation for quantitative behavior analysis.

Abstract

Automated animal behavior analysis relies on long-term, interpretable individual trajectories; however, multi-animal tracking in space science experimental videos remains highly challenging due to weak appearance cues, low-quality imaging, complex maneuvering behaviors, and frequent interactions. To address this problem, we first construct the SpaceAnimal-MOT dataset to characterize the motion complexity and long-term identity preservation challenges in biological videos acquired under microgravity conditions. We then propose ART-Track (Adaptive Robust Tracking), a motion-driven tracking framework tailored to this setting. Specifically, multi-model motion estimation is introduced to handle abrupt maneuvers and nonlinear motion, motion-state-driven association is designed to reduce identity switches under dense interactions and temporary mismatch, and uncertainty-adaptive fusion is used to dynamically balance spatial and motion cues when prediction reliability varies. Experimental results show that ART-Track significantly reduces identity switches on zebrafish and fruitfly sequences, while maintaining more stable association under occlusion, deformation, and high-density interactions, thereby providing a more reliable tracking foundation for downstream quantitative behavior analysis. The code is publicly available at https://github.com/yyy7777777/ART_TRACK/tree/main.