New surveillance system identifies suspicious, lost people

Published 19 December 2008

New surveillance software will attempt to recognize whether a person on the street is acting suspiciously or appears to be lost; intelligent video cameras will be connected to large video screens and geo-referencing software to help law enforcement and security agencies

Reynolds, the no-holds-barred director of a secretive surveillance program in the movie “Enemy of the State” (1998; the character is played by John Voight) would have loved to have this new solution, developed by engineers at Ohio State University, in his effort to monitor the movements of Robert Clayton Dean (Will Smith) and track down the elusive Brill (Gene Hackman). The computerized surveillance system, when completed, will attempt to recognize whether a person on the street is acting suspiciously or appears to be lost. Intelligent video cameras, large video screens, and geo-referencing software are among the technologies that will soon be available to law enforcement and security agencies.

In the recent Proceedings of the 2008 IEEE Conference on Advanced Video and Signal Based Surveillance, James Davis and doctoral student Karthik Sankaranarayanan report that they have completed the first three phases of the project: they have one software algorithm that creates a wide-angle video panorama of a street scene, another that maps the panorama onto a high-resolution aerial image of the scene, and a method for actively tracking a selected target. The ultimate goal is a networked system of “smart” video cameras that will let surveillance officers observe a wide area quickly and efficiently. Computers will carry much of the workload.

In my lab, we’ve always tried to develop technologies that would improve officers’ situational awareness, and now we want to give that same kind of awareness to computers,” said Davis, an associate professor of computer science and engineering at Ohio State University.

The research is not meant to gather specific information about individuals, he explained. “In our research, we care what you do, not who you are. We aim to analyze and model the behavior patterns of people and vehicles moving through the scene, rather than attempting to determine the identity of people. We are trying to automatically learn what typical activity patterns exist in the monitored area, and then have the system look for atypical patterns that may signal a person of interest — perhaps someone engaging in nefarious behavior or a person in need of help.”

The first piece of software expands the small field of view that traditional pan-tilt-zoom security cameras offer. When surveillance