[ibm] 
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:
- Object
Detection in the
presence of distraction motion - 2D Object
Tracking: Multi-object
tracking with occlusion resolution. - Object
Classification: View
independent object classification. - 3D Object
Tracking: Precise 3D
location using standard cameras. - Multi-scale
Tracking: Automatic PTZ
Camera control to track objects. - Multi-camera
Handoff: The ability
to track an object across cameras. - Face
Cataloging: Captures
faces at large distances from the camera. - XML
Metadata Representation for object
and its motion attributes. - Extensible
Engine Architecture for plug and
play video analytics. - Real Time
Event Indexing: Scene events
are instantaneously available for searching in a distributed database
environment. - Web
service interfaces for Event Search & Retrieval
support the
rapid application development of customer specific applications. - Scalable
Backend System: COTS
database technology allows for both distributed surveillance and
scalability.
Research Areas:
- Robust Background Subtraction
- Salient Motion
Detection - Object
Classification - 2D Tracking
- 3D Multi-Person Tracking
- Articulated Human Body
Tracking - Active Head Tracking
- Coarse Head Pose
Estimation - Position Independent
Absolute
Head
Pose Estimation - Face Cataloger
- Video Privacy
- Multi-scale Tracking &
Index Browser - Real Time Alerts
- Middleware for Large Scale
Surveillance (MILS) - Performance Evaluation
of
Surveillance Systems
