Stereo vision and segmentation

I will describe models and algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from color/contrast or from stereo alone is known to be error-prone. Here, color, contrast and stereo matching information are fused to infer layers accurately and efficiently. The stereo-match likelihood is then fused with a contrast-sensitive color model that is learned on the fly, and stereo disparities are obtained by dynamic programming. Our "Layered Graph Cut" (LGC) algorithm, does not directly solve stereo. Instead the stereo match likelihood is marginalized over disparities to evaluate foreground and background hypotheses, and then fused with a contrastsensitive color model. Segmentation is solved efficiently by graph cut optimization. In a recent development, this segmentation procedure has been used, in turn, to improve the efficiency of stereo matching, by exploiting Panum fusional bands that are well known to operate in human stereo vision. Biography Andrew Blake graduated in 1977 from Trinity College, Cambridge with a B.A. in Mathematics and Electrical Sciences. After a year as a Kennedy Scholar at MIT and two years in the defence electronics industry, he studied for a doctorate at the University of Edinburgh which was awarded in 1983. Until 1987 he was on the faculty of the department of Computer Science at the University of Edinburgh and a Royal Society Research Fellow. From 1987 to 1999, he has been on the faculty of the Department of Engineering Science in the University of Oxford, where he ran the Visual Dynamics Research Group, became a Professor in 1996, and and was a Royal Society Senior Research Fellow for 1998-9. In 1999 he moved to Microsoft Research Cambridge to lead the Vision Group. He was elected Fellow of the Royal Academy of Engineering in 1998, and Fellow of the Royal Society in 2005. In 2006 the Royal Academy of Engineering awarded him its Silver Medal. His main research activities are in computer vision. He has published several books including "Visual Reconstruction" with A.Zisserman (MIT press), "Active Vision" with A. Yuille (MIT Press) and "Active Contours" with M. Isard (Springer-Verlag). He has twice won the prize of the European Conference on Computer Vision, with R. Cipolla in 1992 and with M. Isard in 1996, and was awarded the IEEE David Marr Prize (jointly with K. Toyama) in 2001. He has served as programme chairman for the International Conference on Computer Vision in 1995 and 1999, and is on the editorial boards of the journals "Image and Vision Computing", the "International Journal of Computer Vision" and "Computer Vision and Image Understanding". Current research spans image interaction, stereo vision and motion tracking. Detailed accounts are available from publication lists, both newer papers from Microsoft Research and older papers from Oxford University. Recent research work with colleagues at Microsoft Research has been written up in the BBC's Science and Technology section and in the Guardian newspaper. 978-1-4244-1696-7/07/$25.00 ©2007 IEEE. 4