Perceptive Agents and Interfaces using Computer Vision
Trevor Darrell, Interval Research
Seminar on People, Computers, and Design
Stanford University September 27, 1996
Ideally, man-machine interfaces should respond to people's intuitive modes of communication. Recent advances in real-time computer vision offer the promise of endowing man-machine interfaces with direct perception of human users. In this talk I'll first discuss visual control and compositing in virtual environments, including direct navigation and manipulation. I'll then cover recognition of hand and face gestures: offering iconic, diectic, and emotional signals to computer systems. Finally I'll discuss Avatars and agency, and in particular the issue of literal control vs. autonomy in virtual user representations. I'll show examples of several systems developed which use visual perception-- including real-time hand, face, and body tracking-- to create interactive virtual environments. Each of these systems utilizes real-time vision techniques with no gloves, markers, or other intrusive artifacts.
Trevor Darrell recently completed his doctoral degree in the Perceptual Computing Section of the MIT Media Lab and joined Interval Research as a member of the research staff. He has done research in the use of computer vision and machine learning for interactive systems, including the tracking and interpolation of gestures made by human users. Previously he worked on multiple-model robust estimation techniques for signal understanding. He has published several ACM and IEEE journal papers on these topics, and won Honorable Mention in the Ars Electronica competition in 1994 for his work on the ALIVE visual Interface. He obtained the M.S. degree from MIT in 1991 and the B.S.E. degree in Computer Science from the University of Pennsylvania in 1988, where he worked in the GRASP Computer Vision and Robotics Laboratory on real-time depth from focus estimation.
Titles and abstracts for all years are available by year and by speaker.
For more information about HCI at Stanford see