Computer Systems Laboratory Colloquium

4:15PM, Wednesday, November 13, 2002
NEC Auditorium, Gates Computer Science Building B03
http://ee380.stanford.edu

We Know Where You Are: 3D Visual Person Tracking

Dr. John Woodfill
Co-Founder and CTO, Tyzx Inc.
About the talk:

Of all our senses, we rely most heavily on our sense of sight to interact with the world. As we incorporate embedded processors into everyday products to make them more intelligent, we can imbue them as well with this powerful capability. To date, however, machine vision has only achieved success in manufacturing facilities where lighting and scene variation are strictly controlled. Seeing in the real world is much harder.

The challenge to seeing is to view the world in real-time in three dimensions and color. Until recently, this was possible only with dedicated high-performance computers. Today, technology developed by Tyzx performs the task on a single IC at rates which outstrip the fastest CPUs.

Combined with commodity CMOS imagers, the result is a new platform for low-cost, low-power 3D sensing for a broad range of affordable applications. 3D vision-enabled applications from video games to automotive to robotics are now possible. In many ways, the most immediate and compelling application is in Homeland Defense.

Dr. Woodfill will discuss the merits of 3D technology for computer vision and its application to new security challenges.

About the speaker:

Dr. John Woodfill is a founder of Tyzx, Inc. John is known for his research in frame-rate depth and motion vision for systems that work in the real world. This focus has led to patented, stereo-vision hardware that is at the core of Tyzx's 3D imaging technology. Dr. Woodfill initiated and led Interval Research's work on computational stereo vision. He was previously a consultant at Xerox PARC and SRI, and a Visiting Scientist at the IBM Science Center in Heidelberg, Germany. John was also a member of the original team that developed the INGRES relational database system at UC Berkeley. He holds a dual AB degree from UC Berkeley in Computer Science and Philosophy, and an MS degree and PhD from Stanford in Computer Vision. His thesis work resulted in interactive robotic systems that tracked people (and cats) in unstructured environments based solely on estimates of optical flow.

Contact information:

John Woodfill
650-575-5427
woodfill@tyzx.com