Learning Models for Predictive Behavioral Intent and Activity Analysis in Wide Area Video Surveillance

This project will continue development of an intelligent, non-obtrusive, real-time, continuous monitoring system for assessing activity and predicting emergent suspicious and criminal behavior across a network of distributed cameras. nca/ncf

This award was made competitively under the NIJ 2009 "Technology Research and Development for Law Enforcement and Corrections Application" solicitation. The goal of this effort is to develop software tools to enable the tracking of an individual across surveillance videos originating from CCTV cameras with non-overlapping fields of view in a wide area. Research to date shows that CCTV systems can have a positive effect on crime and prevention, but the effect is modest or inconsistent depending on a number of factors. This effort, and related research and development efforts, is intended to foster development of smart CCTV systems that will overcome these inhibiting factors. This award has been funded incrementally. This is the third and final supplement needed to complete the effort initially proposed by the University of Houston. nca/ncf