{"id":111678,"date":"2020-08-07T10:15:08","date_gmt":"2020-08-07T14:15:08","guid":{"rendered":"https:\/\/www.ucf.edu\/news\/?p=111678"},"modified":"2020-09-29T16:44:28","modified_gmt":"2020-09-29T20:44:28","slug":"ucf-team-wins-worldwide-competition-in-computer-vision","status":"publish","type":"post","link":"https:\/\/www.ucf.edu\/news\/ucf-team-wins-worldwide-competition-in-computer-vision\/","title":{"rendered":"UCF Team Wins Worldwide Competition in Computer Vision"},"content":{"rendered":"
A research team with the 女仆AV\u2019s Center for Research in Computer Vision<\/a> recently won a competition to improve computer vision by creating technology that can automatically track behavior<\/a> in long security videos.<\/p>\n The competition, called the Activities in Extended Video Challenge for 2020, was sponsored by the U.S. Department of Commerce\u2019s National Institute of Standards and Technology and was held virtually in June as part of the Conference on Computer Vision and Pattern Recognition.<\/p>\n Top computer vision teams from around the world, including teams from IBM, Massachusetts Institute of Technology, Carnegie Mellon University, and Purdue University competed in the challenge.<\/p>\n \u201cVideo surveillance is of great importance for security, and manually watching surveillance videos is not only difficult but inefficient,\u201d says Yogesh Rawat, an assistant professor at the center and team leader. \u201cAlso, with so many closed-circuit television cameras all around, it is not possible to manually watch those videos. We need automatic analysis of these security videos to improve efficiency as well as accuracy.\u201d<\/p>\n That need for \u201cextra eyes\u201d is why the UCF computer vision team developed a deep-learning system, named Gabriella, that can detect multiple activities happening in a security video efficiently, at a speed of 100 frames per second.<\/p>\n \u201cThis is a first step toward analyzing these security videos, and it will have a lot of applications in national security,\u201d Rawat says.<\/p>\n