           |
GRASP Seminar Series: Fall 2009
October 16th, 11:00 a.m., Wu & Chen Auditorium, Levine Hall (3330 Walnut Street)
Jana Kosecka
George Mason University
"3D Reconstruction and Semantic Parsing of Urban Environments"
Abstract: Recent advances in techniques for capturing large scale models of urban environments, give rise to many novel applications which require rapid and realistic 3D modeling. I will present an 3D reconstruction approach utilizing properties of piecewise planarity and restricted number of plane orientations to suppress the ambiguities causing failures of standard dense stereo methods. I will describe how to formulate this problem in MRF framework built on an image presegmented into superpixels and demonstrate superior performance in problematic scenarios containing many repetitive structures and no or low textured regions. Using the same type of representation, I will briefly introduce some on-going work on semantic parsing of urban areas using spatial co-occurrence of visual words and 3D geometry. I will show some preliminary results on challenging environments with varying viewpoints and large number of categories appearing simultaneously.
Biography: Jana Kosecka is an Associate Professor at the Department of Computer Science, George Mason University. She obtained her M.S.E. in Electrical Engineering and Computer Science from Slovak Technical University and Ph.D. in Computer Science from University of Pennsylvania in 1996. In 1996 - 1999 she was a postdoctoral fellow at the EECS Department at University of California, Berkeley. She is the recipient of David Marr's prize (with Y. Ma, S. Soatto and S. Sastry) and received the National Science Foundation CAREER Award. Jana is an Associate Editor of IEEE Transactions on Robotics and a Member of the Editorial Board of International Journal of Computer Vision. Her general research interests are in Robotics and Computer Vision. In particular she is interested 'seeing' systems engaged in autonomous tasks, acquisition of static and dynamic models of environments by means of visual sensing and human-computer interaction.
GRASP
Laboratory
Site maintained by graspadm@grasp.cis.upenn.edu
Last update:5 October, 2009