Multiple Toddler Tracking in Indoor Videos

Somaieh Amraee, Bishoy Galoaa, Matthew Goodwin, Elaheh Hatamimajoumerd, Sarah Ostadabbas; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2024, pp. 11-20

Multiple toddler tracking (MTT) encompasses identifying and continually associating toddlers in video footage, a crucial task for their safety and development monitoring. While conventional multi-object tracking (MOT) algorithms are adept at tracking diverse subjects, toddlers pose unique challenges due to their unpredictable movements, diverse poses, and similar appearances. Moreover, tracking toddlers in indoor environments introduces complexities such as occlusions and limited fields of view. In this paper, we address the challenges of MTT and propose MTTSort, a customized method building upon the DeepSort algorithm. MTTSort is designed to achieve high accuracy in tracking multiple toddlers in indoor videos. Our contributions include discussing the primary challenges in MTT, introducing a genetic algorithm to optimize hyperparameters, proposing an accurate tracking algorithm, and curating the MTTrack dataset using unbiased AI co-labeling techniques. We quantitatively compare MTTSort with state-of-the-art MOT methods on MTTrack, DanceTrack, and MOT15 datasets. In our evaluation, the proposed method outperformed other MOT methods achieving 0.98, 0.68, and 0.98 in multiple object tracking accuracy (MOTA), higher order tracking accuracy (HOTA), and iterative and discriminative framework 1(IDF1) metrics, respectively.