|
The IBM Smart Surveillance system (S3) is developed by the Exploratory Computer Vision Group in IBM T.J. Watson Research Center. The system is a middleware offering for use in surveillance systems and provides video based behavioral analysis capabilities. Release 1 of the Smart Surveillance System provides two components:
- Smart Surveillance Engine (SSE) which provides the front end video analysis capabilities.
- Middleware for Large Scale Surveillance (MILS) which provides data management capabilities.
Operational Capability: The S3-R1 system draws on some of the Smart Surveillance technologies created by IBM Research. S3-R1 provides the following functionality:
- Web based Real Time Alerts including Motion Detection, Directional Motion, Abandoned Object, Object Removal & Camera Move/Blind: User Designed Alerts: Specified using simple SQL like interface.
- Web based Event Search using Object Type, Object Size, Object Speed, Object Location, Object Color, Track Duration & Compound Queries
- Web based Event Statistics including Distributions & Moments
Commercial Availability: The S3-R1 system is currently available to end customers on a pilot basis. Business partners can also license the technology for product development.
Application Scenarios While being able to provide real time alarms to “pre-programmed” events is useful, the ability to search through event data and understand patterns enables new “security strategies”.
Force Protection: Understanding long term patterns of activity and the ability to search through events can help identify potential vulnerabilities.
Border Monitoring: While real-time alarms are useful, reacting to a large number of real time alarms is infeasible. Understanding patterns of violations for effective deployment of patrols is critical.
Large Scale Investigations: In large scale investigations like the Washington Sniper incident, the ability to sift through large numbers of surveillance video tapes to identify commonality is essential.
Smart Surveillance Technology Base:
Last updated 10 Jun 2006
|
|
Arun Hampapur; Andrew W. Senior; Chiao-Fe Shu; Lisa Brown; Max Lu; Ying Li Tian
Watson Research Center (Hawthorne)
s3 white paper [pdf] s3 video
|
