Practitioner Centric Video Analytics

This award was competitively made in response to a proposal submitted by General Electric Global Research to a National Institute of Justice FY 2013 solicitation: Applied Technology Research and Development for Criminal Justice Purposes

In this application, General Electric Global Research with the University at Albany, State University of New York (SUNY Albany) will further refine a predictive video analytic system developed with NIJ funding. GE proposes to work in collaboration with the Schenectady Municipal Police Department (SMPD) to determine how best to configure the system for optimal utility. Three research questions have been identified. First, what are the optimal mechanisms for presenting a nominated video highlight so as to support the concept of recognition at a glance? Second, how can a new event recognition engine be constructed given a single example? Third, for purposes of face recognition, what is the best method for exploiting certain distinguishing features, which may be observable even in low quality facial images? Performance of the technology can be measured by the quantity of actionable information extracted from the video data that can be leveraged by law enforcement. Deliverables include reporting on the above project and making the technology available to third parties for use. There is a letter of support from GE Idea Works included with the application package to work to commercialize the products resulting from this project. GE Idea Works licenses technologies such as video analytic algorithms to customers for field use and product development. ca/ncf