CS Faculty Candidate Colloquium
Wednesday **Special Time & Location**
March 12
10:45 - 11:50 AM
Kelley 1007
Antoni Chan
EECS Colloquium: Computer Science Faculty Candidate
Ph.D. Candidate
University of California, San Diego
A Family of Dynamical Models for Video
One family of visual processes that has relevance for various
applications of computer vision is that of, what could be loosely
described as, visual processes composed of ensembles of particles
subject to stochastic motion. The particles can be microscopic (e.g
plumes of smoke), macroscopic (e.g. leaves blowing in the wind), or even
objects (e.g. a human crowd or a traffic jam). The applications range
from remote monitoring for the prevention of natural disasters (e.g.
forest fires), to background subtraction in challenging environments
(e.g. outdoor scenes with moving trees in the background), and to
surveillance (e.g. traffic monitoring). Despite their practical
significance, the visual processes in this family still pose tremendous
challenges for computer vision. In particular, the stochastic nature of
the motion fields tends to be highly challenging for traditional motion
representations such as optical flow, parametric motion models, and
object tracking. Recent efforts have advanced towards modeling video
motion probabilistically, by viewing video sequences as "dynamic
textures" or, more precisely, samples from a generative, stochastic,
texture model defined over space and time.
In this talk, I will present a family of dynamical models for video,
along with their applications to computer vision. In particular, I will
present two multimodal motion models, the {\em mixture of dynamic
textures} and the {\em layered dynamic texture}, which provide
principled frameworks for video clustering and motion segmentation. I
will also present a non-linear motion model, the {\em kernel dynamic
texture}, which can capture complex patterns of motion through a non-
linear manifold embedding. Finally, I will discuss applications of these
models to a variety of real-world computer vision problems, including
video texture segmentation, crowd monitoring, background subtraction,
and video classification.
Biography:
Antoni Chan is a Ph.D. candidate in Electrical and Computer Engineering
at the University of California, San Diego. He received the B.S. and
M.Eng. in Electrical Engineering from Cornell University in 2000 and
2001, respectively. From 2001 to 2003, he was a visiting scientist in
the Vision and Image Analysis Lab at Cornell University, and in 2005 he
was an intern at Google New York. He is currently a member of the
Statistical Visual Computing Lab at UCSD. His research focuses on
probabilistic models of images and video, with applications to
classification, annotation, and retrieval of images and video. He is
also interested in probabilistic kernel functions, feature selection,
and sparse classifiers. He is the recipient of an NSF IGERT fellowship.
_______________________________________________
Colloquium mailing list
[email protected]
https://secure.engr.oregonstate.edu/mailman/listinfo/colloquium
