Estimating Human Body Shape from Images

Friday, February 19, 2010 - 4:56pm


Monday February 22, 2010
3:30 – 4:30
Computer Science Conference Room, Harold Frank Hall Rm. 1132

HOST: Matthew Turk

SPEAKER: Michael J. Black
Professor, Computer Science Department, Brown University

Title: Estimating Human Body Shape from Images


Body shape is central to understanding gender, identity, age, etc. yet
it’s estimation from images and video is not well studied. Unlike rigid
3D scenes, humans are highly non-rigid and articulated. They also wear
clothing that moves and obscures their form. This talk will explore our
recent work on body shape estimation and the pieces needed to solve this
problem. First we show how a parametric 3D human body model (SCAPE) can
be used to estimate body shape from image measurements in a calibrated
and controlled environment. This model has the important property of
factoring body shape variation due to identity from body shape variation
due to pose. Second, we exploit this factorization to recover the shape
of a person appearing in different poses. By assuming body shape is
constant across pose, we are able to infer body shape under clothing.
Finally we show how shading cues can be used to estimate body shape from
a single image or painting. Several applications of
body-shape-from-video will be discussed.


Michael Black received his B.Sc. from the University of British Columbia
(1985), his M.S. from Stanford (1989), and his Ph.D. in computer science
from Yale University in 1992. He has been a visiting researcher at the
NASA Ames Research Center and an Assistant Professor in the Dept. of
Computer Science at the University of Toronto. In 1993 Prof. Black
joined the Xerox Palo Alto Research Center where he managed the Image
Understanding area and later founded the Digital Video Analysis group.
In 2000, Prof. Black joined the faculty of Brown University where he is
a Professor of Computer Science. At CVPR’91 he received the IEEE
Computer Society Outstanding Paper Award for his work with P. Anandan on
robust optical flow estimation. His work also received Honorable Mention
for the Marr Prize in 1999 (with David Fleet) and 2005 (with Stefan
Roth). Prof. Black’s research interests
in machine vision include optical flow estimation, human motion analysis
and probabilistic models of the visual world. In computational
neuroscience his work focuses on probabilistic models of the neural
code, the neural control of movement and the development of neural
interface systems that directly connect brains and machines to restore
lost function to people with central motor system injury.