Advancing Multi-Person Tracking for Autism Behavior Analysis: Challenges Opportunities and Future Directions in Clinical Settings

Somaieh Amraee, Eva Blanco-Mallo, Deniz Erdogmus, Aston McCullough, Matthew Goodwin, Sarah Ostadabbas; Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025, pp. 73-82

Multi-person tracking (MPT) has emerged as a crucial tool for behavior monitoring in clinical settings offering significant potential for advancing autism research. In this paper we assess the state of the art in MPT with a specific focus on its application to autism spectrum disorder (ASD) behavior analysis. Clinical environments present unique challenges for MPT including frequent occlusions visually similar appearances such as uniforms and complex social interactions. We explore these challenges in depth while highlighting recent advancements in tracking algorithms that present opportunities for improving behavioral monitoring in healthcare. Through a comprehensive review we examine the limitations of existing MPT methods when applied to our clinical dataset BAV-ASD (behavioral analysis videoset for ASD) discussing their applicability and gaps in addressing the unique demands of clinical autism studies. Our findings emphasize the critical role of MPT in enabling non-intrusive accurate and continuous monitoring of challenging behaviors such as aggression and self-injury in individuals with ASD. By addressing the limitations of existing methods this work paves the way for future research aimed at enhancing the reliability and effectiveness of MPT systems in clinical environments ultimately supporting early intervention strategies and improving outcomes for individuals with ASD