Biography | Publications

Dr. Oh received his B.S. in Computer Science from Seoul National University (2003), his M.S. (2008), and his Ph.D. (2009) in Computer Science from GeorgiaTech. While at GeorgiaTech his research focused on applying temporal models such as switching linear dynamic systems to learn and recognize patterns that occur in multi-channel time-stream data. The developed algorithms have been successfully applied to the problems in computer vision and wearable computing to recognize on-going activities within signals. His research was primarily supported by a research fellowship award from Samsung.

In addition to his temporal modeling work, Dr. Oh has worked on a wide array of problems in computer vision, robotics, and wearable computing. He was a primary contributor of the GPS-based localization algorithm used in the System for Wearable Audio Navigation (SWAN) developed at GeorgiaTech; he co-developed the first affordance-based robotic vision algorithms for outdoor robot navigation at GeorgiaTech as part of DARPA Learning Applied to Ground Robotics (LAGR) program, and developed a fast facial landmark detection method with his collaborators at Microsoft Research. He has also been involved in diverse research programs at GeorgiaTech to improve the accuracy of SLAM and vision-based localization for indoor robotics, dynamic earth visualization projects, and video retrieval projects.

Dr. Oh joined Kitware in September 2009 where he works on computer vision and robotics problems.

Publications