Public Release: 

UTSA researcher receives Department of Army grant to catch bad guys

Computer science professor works to make finding criminals through surveillance easier

University of Texas at San Antonio

Qi Tian wants computer science to make the world a better place, and not in the way you might think. The UTSA Computer Science professor has received a $399,067 grant from the Department of the Army to use image searching to make combing through surveillance videos easier.

"It's large-scale image retrieval search," Tian said. "This isn't just big data, this is very big data."

When the Boston Marathon was bombed in 2013, officials painstakingly searched surveillance video of the area where they knew the bomb had been planted, and were able to identify the Tsarnaev brothers in the crowd. What Tian is developing through the grant is a way to capture a person's face in such a crowded, hectic situation and search across huge amounts of surveillance videos from other locations across a city or even a country to find another instance of that person.

"You can find the bad guys a little quicker," he said. "Otherwise, you're sitting and looking at an unimaginable number of surveillance videos, looking for this person."

Cities like London, which is known for its wealth of surveillance cameras, already have numerous instances of criminals being caught by tracking them through public surveillance.

"It's computer science making the world better," Tian said. "And hopefully safer."

Tian's algorithm will also be able to detect a suspicious vehicle, although that's relatively easier, since it's rigid. A human face is harder to search for because it's non-rigid and changes with every expression.

"This is closely rooted with the computer vision field," Tian said. "We teach the computer to see, to recognize a world or an object, and yes, a person's face, which can be especially challenging. That's the future. One day you might not need your credit card. You can pay with your face."


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.