UCF’s Yogesh Rawat is developing software for video cameras that will address privacy issues that come with computer vision surveillance tools. “Automation allows us to watch a lot of footage, which is not possible by humans,” Rawat says. “Surveillance is important for society, but there are always privacy concerns. This development will enable surveillance with privacy preservation.”
The software obscures identifying elements such as faces or clothing by adding perturbations to the RGB (color) pixels in the video feed, so human eyes are unable to recognize them. The new technology must analyze the data quickly and not require a lot of computing power, since it is designed for drones and public surveillance cameras that are not dependent on an outside server.
View Related Expert Profiles: Go to Source
