-------------------------------------------------------------------------------
                                       
                                       
		   B O S T O N   U N I V E R S I T Y
                                       
		      Computer Science Department
                                       
			  C O L L O Q U I U M
                                       
         Computational Models for Computer Perception of Human Motion

                             Yaser Yacoob
                         Computer Vision Lab
                       University of Maryland


 		       Thursday, April 9th
                                       
			        3:30pm 
		       (Coffee served at 3:15pm)

                                       
			 Seminar Room / MCS 135
                                       

-------------------------------------------------------------------------------




  Computer understanding of human actions from video imagery has gained
recognition as a challenging research area with applications in human-computer
interaction, coding, animation and surveillance.
     In this talk I will discuss computational approaches for modeling, estimation and
recognition of rigid, deformable and articulated motions in video sequences.  I will
demonstrate the application of these models to the analysis of rigid regions, human
face expressions, speech and articulated movement. The motion models will explore
the following dimensions:
   (1) Stationary versus moving camera
   (2) Instantaneous versus temporal formulations
   (3) Movement-specific versus general models
   (4) Region-based versus point-based approaches
   (5) Learned versus analytical models.

I will initially propose models for instantaneous motion estimation based on spatial
constraints. Then, I will define the concept of spatio-temporal motion
trajectories of brightness in image sequences, formalize learning and estimation
of movement trajectories and demonstrate its use in tracking and interpreting
human motion as observed from stationary and moving cameras.  Finally, I will
discuss future research directions and challenges that lie ahead.



Host: Wayne Snyder (snyder@cs.bu.edu)

-------------------------------------------------------------------------------
For colloquium info, including directions, see http://cs-www.bu.edu/colloquium
-------------------------------------------------------------------------------