23 May 2013 Behavioral profiling in CCTV cameras by combining multiple subtle suspicious observations of different surveillance operators
Author Affiliations +
Abstract
Camera surveillance and recognition of deviant behavior is important for the prevention of criminal incidents. A single observation of subtle deviant behavior of an individual may sometimes be insufficient to merit a follow-up action. Therefore, we propose a method that can combine multiple weak observations to make a strong indication that an intervention is required. We analyze the effectiveness of combining multiple observations/tags of different operators, the effects of the tagging instruction these operators received (many tags for weak signals or few tags for strong signals), and the performance of using a semi-automatic system for combining the different observations. The results show that the method can be used to increase hits (detecting criminals) whilst reducing false alarms (bothering innocent passers-by).
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Henri Bouma, Jack Vogels, Olav Aarts, Chris Kruszynski, Remco Wijn, Gertjan Burghouts, "Behavioral profiling in CCTV cameras by combining multiple subtle suspicious observations of different surveillance operators", Proc. SPIE 8745, Signal Processing, Sensor Fusion, and Target Recognition XXII, 87451A (23 May 2013); doi: 10.1117/12.2015869; https://doi.org/10.1117/12.2015869
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

A novel rain removal technology based on video image
Proceedings of SPIE (November 07 2016)
Surveillance data management system
Proceedings of SPIE (October 18 2002)
Multiple-camera tracking: UK government requirements
Proceedings of SPIE (October 08 2007)
Video face recognition against a watch list
Proceedings of SPIE (October 08 2007)

Back to Top