Takeo Kanade

Takeo Kanade
Computer and Cognitive Science
Bower Award and Prize for Achievement in Science
Carnegie Mellon University | Pittsburgh, Pennsylvania
For visionary leadership and scientific accomplishments in the design of perceptual robotic algorithms and systems that function in the physical world.

2008 Bower Science Award Theme: Robotics

From his early work on face recognition, to the 3-D imaging techniques he developed for the 2001 Super Bowl broadcast, to his work on computer-assisted surgical systems for hip replacement, Takeo Kanade has proven himself a leader in the field of robotics—for which he is presented with the 2008 Bower Award and Prize for Achievement in Science.

Born in 1945 in Hyogo, Japan, Kanade began his academic career in 1964 at Kyoto University where he earned a B.E., an M.E. and his Ph.D.—all in electrical engineering. In 1973 he began teaching in the Department of Information Science at Kyoto University, where he stayed until 1980, when he moved on to his current institution, Carnegie Mellon University.

In an age when most researchers specialize narrowly, Kanade has made important contributions in a number of areas ranging from foundational theoretical advances to innovative devices and algorithms that are widely used today. His earliest work was on face recognition where he ultimately developed techniques for facial expression analysis that could spot minute details and changes—unlike previous recognition systems which at best noted broad categories such as "happy" or "angry." Kanade also pioneered important techniques in motion analysis, introducing a fundamental algorithm for tracking particular image patches through a video sequence, opening the door for modern tracking and compression technologies. His interest in motion analysis led him to focus on 3-D images and the various ways one can extract three-dimensional information from two-dimensional images. He produced a seminal theory on how to recover the three-dimensional shape of an object from a single image in 1981 (known as the "Origami World" theory). He also pioneered the concept of "Virtualized Reality" in which several images of an event taken from various vantage points are combined into a coherent model which can then be used to create novel views of the scene from any desired viewpoint. The techniques that his research group developed were used by CBS in its 2001 broadcast of the Super Bowl to provide images of the field from the player's point of view. Kanade's innovations in robotic vision have been incorporated into several autonomous robots, including a driverless car, an autonomous helicopter and a computer-assisted hip-replacement surgery system, which is currently being tested in a clinical setting.

In addition to his extensive research, Kanade founded Carnegie Mellon's robotics doctoral program in 1989 and later its masters in robotics program. Under his directorship from 1992-2001 the Robotics Institute grew to be one of the preeminent centers for robotics research in the world. In 2001 Kanade founded the Digital Human Research Center in Tokyo, which observes, measures and models human functions, in an effort to understand this most important—and least understood—component of so many systems. Since 2006, he is a founding Director of Quality of Life Technology Center, an NSF-funded Engineering Research Center, to develop intelligent systems to help older adults and people with disabilities.

Dr. Kanade has been elected to the National Academy of Engineering and the American Academy of Arts and Sciences. He has won numerous awards including: the C&C Award, the Okawa Prize, IEEE Robotics and Automation Society's Pioneer Award, the Joseph Engelberger Award, FIT Funai Accomplishment Award, the first Azriel Rosenfeld Award, the Allen Newell Research Excellence Award, the Japan Society of Artificial Intelligence [JSAI] Career Accomplishment Award, the Japan Robot Association [JARA] Award for Research and Development, Longuet-Higgins Prize, and Marr Prize.

Information as of April 2008