Abstract
Video surveillance systems have become a key element in efforts by security services, the military and law enforcement to counterterrorism since the attacks of 11 September 2001. Primarily involving closed circuit television, collected using a variety of hardware platforms and software algorithms, systematic imagery analysis has typically been used as a tool for post-event forensics to identify tactics, techniques and perpetrators of terrorist attacks. Advanced video surveillance applied to detecting suspicious behaviours embedded in crowd signatures can also be a powerful tool for pre-event deterrence. In this article, we examine case studies of attempts by terrorists to target civilians and create mass casualty incidents and evaluate existing behaviour detection algorithms with the goal of elucidating links between potential threats indicated by suspicious behaviours and possible deterrent mechanisms based on video surveillance.
Acknowledgements
This research was supported by the US Department of Homeland Security, Science and Technology Directorate (PI: Regens). The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DHS or the US Government.