Identifying Loitering Behavior with Trajectory Analysis
Published in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
Loitering, the act of remaining in a public area for an extended period, is often associated with suspicious activity and public safety concerns. However, research on loitering detection lacks standardization, leading to challenges in generalizing detection methods. In this work, we provide a clear definition of loitering and introduce a new dataset with annotated loitering behaviors, drawn from the Long-term Thermal Drift Dataset, which respects privacy standards. We utilize trajectory analysis methods to identify loitering by quantifying parameters such as movement directionality, pace, and dwell time. Our dataset and code are available at the provided link, contributing to the study of loitering detection through real-world thermal surveillance.
Recommended citation: Johnny Núnez, Zenjie Li, Sergio Escalera, Kamal Nasrollahi. (2024). "Identifying Loitering Behavior with Trajectory Analysis." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 251-259.
Download Paper | Download Slides