Intelligence surveillance updateU Maryland team develops new surveillance technology

You see them in London, but also in downtown New York and in many other places where people gather: Surveillance cameras are sprouting up in more and more places, part of an increasignly more effective instrument for solving crimes after they happen. The problem with solving crime after it happened is precisely that: The crime has already happened. How about using CCTVs and other surveillance instruments to detect, prevent, or stop criminal and terrorist acts before they take place?

It is less of a problem to cover large areas with video surveillance which will monitor that area 24/7. The problem is paying enough people enough money to watch the monitors 24/7 and not get bored or distracted. Video analytics is part of the answer, but computerized monitoring depends on creating sophisticated, sensitive, and nuanced software programs that can recognize suspicious activities or suspect individuals. There are some video analytics solutions out there, and they are helpful, but they all still leave much to e desired.

Now, Professor Rama Chellappa of the department of electrical and computer engineering of the University of Maryland’s James Clark School of Engineering is currently working on developing a real-time computer monitoring system which will offer some answers to this problem. Chellappa says that his artificial intelligence system can reliably monitor surveillance images to detect certain suspicious movements or suspect individuals and alert human security personnel.

The system works this way: Chellappa and his research assistants used video data from digital surveillance cameras and corresponding algorithms to develop a compact, digital signature for characterizing human gait and corresponding activities, such as humans carrying objects like backpacks, handbags, or briefcases. When a person’s limbs are unencumbered, gait movements are symmetrical. Represented graphically, these movements form a twisted helical pattern resembling a “figure 8” called a double helical signature. Chellappa and his team call this pattern, which is slightly different in each individual, “human gait DNA.”

An individuals’ gait pattern is changed by any activity that changes the symmetry of the movements, such as carrying a package. By defining these signatures, the system can recognize unique patterns in human gait and automatically detect asymmetric movements like an individual walking with a hidden object tied to an ankle or wrist. Hidden objects secured to the body in ways that do not affect movement symmetry, for example, a fanny pack which is belted around the waist, are not currently detected by this technology. Chellappa and his team have integrated human gait DNA into a real-time video surveillance system and used it to study and locate pedestrians. Trials so far show that the approach is superior to many existing methods in terms of accuracy and reliability.

Note that the Maryland team has also developed advanced face recognition software that can be combined with their gait recognition technology, and has also recently developed two other recognition technologies which make the system more capable: height-recognition algorithm and a structured representation, known as attribute grammars, to detect unattended packages.

-read more in Mohamed Abdelkader, et. al., “Activity Modeling and Anomaly Detection Using Ground-Plane Trajectories,” Army Sceince Conference 2006 paper; this Scientific Computing profile of Chellappa; and this Technology News Daily report