🚀 go-pugleaf

See http://amp.ece.cmu.edu/ECESeminar/
Host: Prof. Tsuhan Chen
                               *****************************
                               TO SCHDULE AN APPOINTMENT TO
                               MEET WITH DR. REHG, email
                               carol@ece.cmu.edu RUSH
                               ****************************

                               ----------------------------
                                    ECE Seminar Series
                             ***Note Day and Location****
        
                                WEDNESDAY, MARCH 22, 2000
                                         4:00 PM
                                  Refreshments: 3:30 PM
                               HAMERSCHLAG HALL, ROOM 1112
                              _____________________________

                                     Dr. Jim Rehg
                      Cambridge Research Lab, Compaq Computer Co.
                                    Cambridge, MA


                                     ABSTRACT

Video is the primary archival source for human movement, with examples
ranging from sports coverage of Olympic events to dance routines in
Hollywood movies. If the human figure could be tracked reliably in
unconstrained monocular video, much of this archive could be unlocked for
analysis. Significant technical challenges exist, however, due to the
complexity of human movement, the variability of human appearance, and
the loss of 3-D information.

My talk will describe some recent progress in modeling and estimating
figure motion from monocular video. Two important themes are the
separation of 2-D (registration) and 3-D (reconstruction) effects in
kinematic modeling, and the role of learning in dynamic modeling. In
particular, I will describe a framework for learning switching linear dynamic
system models from data and show its application to figure motion. I will
describe some applications to video editing and computer animation
currently underway at Compaq Research.

                                       BIO

Jim Rehg received his Ph.D. from Carnegie Mellon University in 1995. He
subsequently joined the Cambridge Research Lab where he leads the
vision-based human sensing project. His research interests include
computer vision, novel user-interfaces, and parallel computing.