Computer vision can be a valuable tool if you're tasked with analyzing hours of footage. It can speed up the process of identifying individuals, such as criminal suspects.
Privacy issues
However, there are privacy concerns in this process, so Yogesh Rawat, Assistant Professor at the University of Central Florida (UCF) Center for Research in Computer Vision, is developing advanced software to handle privacy, to be installed in video cameras.
His work is supported by $200,000 in funding from the National Science Foundation’s Accelerating Research Translation (NSF ART) program.
“Automation allows us to watch a lot of footage, which is not possible by humans, such as identifiable information that we can visually interpret,” Rawat says. He also aims to make the technology available in edge devices (not requiring an outside server) and in real time.
This also requires developing algorithms that can process the data as quickly as possible, so graphics processing units (GPUs) and central processing units (CPUs) can handle the workload of analyzing footage as it is captured.
Speed and size
“We want to do this very efficiently and very quickly in real time,” Rawat says. “We also don’t want to require a lot of computing power. We are not working with large computers there, but very small devices.”
The funding will also allow Rawat to identify potential users of the technology, including nursing homes, childcare centers and authorities using surveillance cameras.
His work builds on several previous projects, including work that allows analysis of untrimmed security videos, training artificial intelligence models to operate on a smaller scale, and a patent on software that allows for the detection of multiple actions, persons and objects of interest.
Funding sources for these works also include $3.9 million from the IARPA Biometric Recognition and Identification at Altitude and Range program, $2.8 million from Intelligence Advanced Research Projects Activity (IARPA) Deep Intermodal Video Analysis, and $475,000 from the U.S Combating Terrorism Technical Support Office.