Will IP Cameras Alarm on Behavior?

Researchers at Queen Mary, University of London intend to find the answers.

Queen Mary, University of London, one of the UK’s leading higher education research institutions, has installed a network of megapixel IP cameras (Iqeye from IQinVision) to help meet the requirements of the “Behaviour-based Enhancement of Wide-Area Situational Awareness” (BEWARE) research project. In addition to the cameras and video management software (from Milestone Systems), the university is partnering with a local systems integrator, Smart CCTV Ltd., for installation and ongoing consultation.

The Queen Mary project is a three-year grant-funded research project to gather real world data and build models and algorithms for software application development relating to the BEWARE study. The project runs from 2007 to 2010 with a budget of £600,000, provided by the Engineering and Physical Sciences Research Council (EPSRC). 

It will develop novel techniques for video-based people tagging and behavior monitoring across a distributed network of security cameras for the enhancement of global situational awareness in a wide area. Queen Mary’s Dr. Tony Xiang explained, “The problem we want to address is behavior analysis using multiple cameras. We need to develop a model for detection and tagging of people across cameras, enabling an automated video analytics system to track the same person, for example, between camera 1 to camera 2.” The next project objective is to automate PTZ cameras through software instructions linked with the tagging and behavior profiling. Dr. Xiang added, “Camera actions would be determined by the behavior profiling. If the smart camera detects suspicious behavior, it will automatically focus and follow on the tagged person.”