Robert Pless, Associate Professor of Computer Science and Engineering at Washington University. Dept.
Cameras that don't move seem doomed to a boring existence, always watching the same ATM, airport security desk, skyline or traffic intersection. But a camera may learn a surprising amount about its surroundings by comparing many pictures taken at different times. Inspired by time-lapse artists Hiroshi Sugimoto and Jason Salavon, I will describe several tools to understand outdoor scenes as viewed from a single location. In order to test these approaches, we have captured images from nearly 1000 webcams every 30 minutes for more than a year. This database (AMOS: Archive of Many Outdoor Scenes) is available for research and I will highlight some of our early results on patterns of image change that seem to be common to all outdoor cameras.
Brief Biography:
Robert Pless is an Associate Professor of Computer Science and
Engineering at Washington University in St. Louis. His research focus
is the statistics and geometry of video, including anomaly detection
and motion pattern analysis with applications to surveillance video
and MR-imagery. Dr. Pless has Bachelors Degree in Computer Science
from Cornell University in 1994 and a PhD from the University of
Maryland, College Park in 2000. He chaired the IEEE Workshop on
Omnidirectional Vision and Camera Networks (OMNIVIS) in 2003, and
received the NSF CAREER award in 2006.