Behavioral profiling in CCTV cameras by combining multiple subtle suspicious observations of different surveillance operators
Lists
Only you see this
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).
BibTeX
@inproceedings{bouma2013behavioral,
author = {Henri Bouma and Jack Vogels and O.A.J. Aarts and Chris Kruszynski and Remco Wijn and Gertjan J. Burghouts},
title = {{Behavioral profiling in CCTV cameras by combining multiple subtle suspicious observations of different surveillance operators}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2013},
doi = {10.1117/12.2015869},
}Loading related content...