Visual Processing and Understanding of Human Faces and Bodies
Keynote Talk at Zürich Vision Meeting
April 19, 2011, 13:40
ETH Zurich, main building (HG), Auditorium Maximum (F30)
Carnegie Mellon University
Pittsburgh, PA 15213, USA
A human face and body convey important information to understand a person: identity, emotion, action, and intention of the person. Technologies to process video of human faces and bodies have many applications, ranging from biometrics to medical diagnosis and from surveillance to cognitive human-robot interaction. This talk will give highlights of the progress that the CMU Vision Group has made, in particular, to robust face (and object) alignment, real-time face tracking, facial Action Unit (AU) recognition for emotion analysis, 2D and 3D body tracking, and facial video cloning for understanding human dyadic communication. Also, I will cover the new vision scenario which we named First-Person Vision. Instead of viewing a person from the environment (third-person’s view), First-Person Vision analyzes the scene in which the person acts and her behaviors in it from the images taken from her view point by a wearable vision device.
Takeo Kanade is the U. A. and Helen Whitaker University Professor of Computer Science and Robotics and the director of Quality of Life Technology Engineering Research Center at Carnegie Mellon University. He received his Doctoral degree in Electrical Engineering from Kyoto University, Japan, in 1974. After holding a faculty position in the Department of Information Science, Kyoto University, he joined Carnegie Mellon University in 1980. He was the Director of the Robotics Institute from 1992 to 2001. He also founded the Digital Human Research Center in Tokyo and served as the founding director from 2001 to 2010.
Dr. Kanade works in multiple areas of robotics: computer vision, multi-media, manipulators, autonomous mobile robots, medical robotics and sensors. He has written more than 350 technical papers and reports in these areas, and holds more than 20 patents. He has been the principal investigator of more than a dozen major vision and robotics projects at Carnegie Mellon.
Dr. Kanade has been elected to the National Academy of Engineering and the American Academy of Arts and Sciences. He is a Fellow of the IEEE, a Fellow of the ACM, a Founding Fellow of American Association of Artificial Intelligence (AAAI), and the former and founding editor of International Journal of Computer Vision. Awards he received include the Franklin Institute Bower Prize, ACM/AAAI Allen Newell Award, Okawa Award, C&C Award, Tateishi Grand Prize, Joseph Engelberger Award, IEEE Robotics and Automation Society Pioneer Award, and IEEE PAMI-TC Azriel Rosenfeld Lifetime Accomplishment Award.