Along with the rapid growth of the smart devices, vast number of computer vision-based applications have been developed. In this talk, three promising assistive technologies will be introduced, remote eye gaze tracking, collision risk estimation, and color compensation for the color-blind people.
Sung-Jea Ko, BS’80, MS’86, PhD’88, Professor, Korea University
Sung-Jea Ko received his Ph.D. degree in 1988 and his M.S. degree in 1986, both in Electrical and Computer Engineering, from State University of New York at Buffalo, and his B.S. degree in Electronic Engineering at Korea University in 1980. In 1992, he joined the Department of Electronic Engineering at Korea University where he is currently a Professor. From 1988 to 1992, he was an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Michigan-Dearborn. He has published over 180 international journal articles. He also holds over 60 registered patents in fields such as video signal processing, computer vision, and multimedia communications.
Dr. Ko is the 1999 Recipient of the LG Research Award. He received the Hae-Dong best paper award from the Institute of Electronics and Information Engineers (IEIE) (1997), the best paper award from the IEEE Asia Pacific Conference on Circuits and Systems (1996), a research excellence award from Korea University (2004), and a technical achievement award from the IEEE Consumer Electronics (CE) Society (2012). He received a 15-year service award from the TPC of ICCE in 2014. He has served as the General Chairman of ITC-CSCC 2012 and the General Chairman of IEICE 2013. He is a member of the editorial board of the IEEE Transactions on Consumer Electronics. He is a distinguished lecturer of the IEEE. He is the Past President of the IEIE and the Vice-President of the IEEE CE Society. He is a Fellow of the IEEE (2012) and a Fellow of the Institution of Engineering and Technology (IET) (2000).
Remote eye gaze tracking (REGT)
Recent REGT methods can be categorized into 2-D and 3-D methods which aim to estimate the point of gaze on the 2-D screen and in the 3-D real-world respectively. The Homography Normalization method, one of the most popular 2-D gaze estimation methods, will be first reviewed, and several further works made to improve its performance will be presented. In addition, a brief introduction to the 3-D gaze estimation will be provided.
Collision risk estimation
Collision risk estimation is a beneficial technology helping the visually impaired to walk in real world environment without bumping into the surrounding objects. One of the state-of-the-art collision risk estimation system will be presented, where, based on the accurate and robust collision detection algorithm, most impending collisions can be detected and then be used in providing a warning about any upcoming obstacles.
Color compensation for the color-blind
Based on the success in simulating the color perception of people with color vision deficiency, many re-coloring algorithms have been developed to improve the color accessibility for the color-blind. One of the re-coloring methods will be introduced.