Gait-recognition biometric technology to help soldiers manning checkpoints
basic form currently allows us to track the people more effectively, especially in crowds,” Burns says.
The next generation of Chellappa’s technology could extend the role of gait recognition. In early-stage research, he has shown that he can analyze the joint movements of a walking person and tell whether those movements are anomalous and possibly consistent with carrying heavy objects—and even whether the person has just deposited something on the ground.
This work is at an early stage. Chellappa has created a model of human movement based on the movements of eleven joints — including the knee, elbow, and hip — and established a database of normal movements for a variety of body types traveling at a variety of speeds. This forms a database of the normal range of human movements, against which videos of a walking person can be compared.
In a November demonstration at an army research conference in Orlando, Florida, Chellappa showed that his system could detect someone who had just surreptitiously deposited an object on the ground simply by noting changes in the way the person walked before and after dropping the object. And he is now developing software able to detect the gait of people who have a 15-pound object attached to their legs.
“We have clearly made a link between humans carrying things with them and the corresponding changes in their walking pattern,” Chellappa says. “We see differences in the way people walk when they strap even 15 pounds to their ankle, but it’s a very subtle thing.” He concedes that the work is preliminary—and that the problem of detecting extra weight on a torso is a research challenge—but he adds, “I believe it’s a reasonable way to approach it.”
His work represents a new direction for the field of human movement signatures, says Alex Vasilescu, a research scientist at MIT’s Media Lab. Some gait-recognition research has shown the potential for early detection of diseases like Parkinson’s. Several research groups are working on developing a way to take a person’s “gait fingerprint” (see “Gait-recognition Biometrics to Assist Other Biometric Measures,” 23 March 2007 HSNW; “Better Gait Recognition Biometrics Developed,” 17 June 2008 HSNW). This could allow a video system to identify that person based on previously stored information. Chellappa’s technology requires no previous information about an individual. “It’s very relevant to our times,” Vasilescu says. “I would like to know if someone is carrying a concealed weapon, and we’ll worry about who that person is afterwards.”
Han quotes Thomas McKenna, project manager at the Office of Naval Research, which funded Chellappa’s work, to say that what is really novel in this research is that rather than searching for a gait fingerprint, the technology searches for suspicious activities, says . “It’s a new way of using surveillance that looks at activities, instead of looking for people,” he says.
The first version of the CounterBomber to reach market won’t use gait recognition to determine whether someone is threatening. Rather, this first version uses only the reflected radar beam to make the determination. The next version of the technology could include gait recognition as a way to help identify suspicious activity. “By incorporating Rama’s full gait-recognition technology in the next generation of our system, we will be able to combine evidence both from the radar and the video sensors to improve our discrimination performance,” Burns says.
