20 May 2015 Exploring discriminative features for anomaly detection in public spaces
Author Affiliations +
Context data, collected either from mobile devices or from user-generated social media content, can help identify abnormal behavioural patterns in public spaces (e.g., shopping malls, college campuses or downtown city areas). Spatiotemporal analysis of such data streams provides a compelling new approach towards automatically creating real-time urban situational awareness, especially about events that are unanticipated or that evolve very rapidly. In this work, we use real-life datasets collected via SMU's LiveLabs testbed or via SMU's Palanteer software, to explore various discriminative features (both spatial and temporal - e.g., occupancy volumes, rate of change in topic{specific tweets or probabilistic distribution of group sizes) for such anomaly detection. We show that such feature primitives fit into a future multi-layer sensor fusion framework that can provide valuable insights into mood and activities of crowds in public spaces.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shriguru Nayak, Shriguru Nayak, Archan Misra, Archan Misra, Kasthuri Jayarajah, Kasthuri Jayarajah, Philips Kokoh Prasetyo, Philips Kokoh Prasetyo, Ee-peng Lim, Ee-peng Lim, } "Exploring discriminative features for anomaly detection in public spaces", Proc. SPIE 9464, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VI, 946403 (20 May 2015); doi: 10.1117/12.2184316; https://doi.org/10.1117/12.2184316


Back to Top