The Mathematics of Body Shape
Thursday, May 9, 2013, 16:00 – 16:55, Room: Brahms
To understand people, computers must be able to detect them, track them, recognize them and understand their behavior. We argue that human body shape plays an important role in all these problems but has been largely ignored. What is human body shape and how should it be represented? What makes two people similar or dissimilar? How does shape vary with pose or emotion? How is body shape related to health? Answers to these and other questions require a precise mathematical description of human shape. We address this by registering thousands of detailed body scans of people, enabling the statistical analysis of body shape variation. This talk will describe the key ideas behind modeling and analyzing human body shape. It will also describe accurate body shape estimation from commodity range sensors. Finally it will explore applications of body shape models in computer vision, graphics, and neuroscience.
Professor Michael Black received his B.Sc. from the University of British Columbia (1985), his M.S. from Stanford (1989), and his Ph.D. from Yale University (1992). After post-doctoral research at the University of Toronto, he worked at Xerox PARC as a member of research staff and an area manager. From 2000 to 2010 he was on the faculty of Brown University in the Department of Computer Science (Assoc. Prof. 2000-2004, Prof. 2004-2010). He is presently one of the founding directors at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, where he leads the Perceiving Systems department. He is also a Honorarprofessor at the University of Tuebingen in Computer Science, Adjunct Professor (Research) in Computer Science at Brown University and a Visiting Professor of Electrical Engineering at Stanford University. His work has won several awards including the IEEE Computer Society Outstanding Paper Award (1991), Honorable Mention for the Marr Prize (1999 and 2005), and the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision.