Seminar 2006 11 01 Dynamic Textures
From CISSTwiki
CISST ERC Seminar
Modeling and Segmentation of Dynamic Textures
Date: Wednesday, November 1, 2006
Time: 12:00pm, Lunch will be served before the seminar.
Place: Maryland Hall 110
Speaker: Rene Vidal
Title: Modeling and Segmentation of Dynamic Textures
Presentation slideshow: PDF, 9Mb ( info )
Abstract:
Dynamic textures are video sequences of nonrigid scenes whose temporal evolution exhibits certain stationarity, e.g. video sequences of water, fire, smoke, steam, foliage, or a beating heart. Previous work has shown how such complex scenes can be modeled as the output of simple linear dynamical models. However, in real world scenes the camera could also move, or different regions of an image could correspond to different dynamic textures, e.g. a bird floating on water.
In this talk, we will consider the problem of modeling and segmenting a scene containing multiple dynamic textures undergoing multiple rigid-body motions. We propose to model each moving dynamic texture with a time varying linear dynamical system (LDS) plus a 2-D translational motion model. For scenes with a single moving dynamic texture, we show how to compute the optical flow of the scene using the so-called dynamic texture constancy constraint (DTCC). For scenes with multiple dynamic textures, we propose to segment the scene by minimizing a spatial-temporal generalization of the Mumford-Shah energy functional.
Several experiments will show the applicability of our method to segmenting scenes using only dynamics, only appearance, and both dynamics and appearance.
Bio:
Professor Vidal received his B.S. degree in Electrical Engineering (highest honors) from the Pontificia Universidad Catolica de Chile in 1997 and his M.S. and Ph.D. degrees in Electrical Engineering and Computer Sciences from the University of California at Berkeley in 2000 and 2003, respectively. He was a research fellow at the National ICT Australia since September 2003 and joined The Johns Hopkins University in January 2004 as an Assistant Professor in the Department of Biomedical Engineering and the Center for Imaging Science.
His areas of research are biomedical imaging (DTI registration and clustering, heart motion analysis), computer vision (segmentation of static and dynamic scenes, multiple view geometry, omnidirectional vision), machine learning (generalized principal component analysis GPCA, kernel GPCA, dynamic GPCA), vision-based coordination and control of unmanned vehicles, and hybrid systems identification and control.