【2012-02-08】Prof. Antoni Chan, "A Family of Dynamical Models for Video"

Poster:Post date:2012-01-30

Title: A Family of Dynamical Models for Video
Speaker: Antoni Chan (CUHK)
2012/2/8 2:00pm
Room 104

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 our work on multimodal motion models (mixtures of dynamic textures and layered dynamic textures) for video segmentation, as well as our recent work on hierarchical clustering of dynamic textures.  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, video classification, and video texture annotation and retrieval.

Antoni B. Chan received the BS and MEng degrees in electrical engineering from Cornell University in 2000 and 2001, respectively, and the PhD degree in electrical and computer engineering from University of California, San Diego (UCSD), in 2008.  From 2001 to 2003, he was a visiting scientist in the Vision and Image Analysis Lab at Cornell University, and in 2009, he was a postdoctoral researcher in the Statistical Visual Computing Lab at UCSD.  In 2009, he joined the Department of Computer Science at the City University of Hong Kong, as an assistant professor. From 2006 to 2008, he was the recipient of a US National Science Foundation (NSF) IGERT Fellowship.  His research interests are in computer vision, machine learning, pattern recognition, and music analysis.

Last modification time:2012-01-30 PM 6:11

cron web_use_log