This talk will have two parts both of which address fundamental 3D computer vision problems. In the first part, I will present some previous work in 3D reconstruction including an approach for real-time, large-scale 3D reconstruction for modeling scenes captured by video cameras mounted on a moving vehicle. This will serve as motivation for identifying shortcomings of current 3D reconstruction research; most algorithms cannot handle dynamic scenes and have no means of evaluating their own performance on a given data set. In the second part of the talk, I will present research on analyzing range data that cover an entire city to detect roads, buildings and smaller objects of interest.

Philippos Mordohai is an Assistant Professor of Computer Science at the Stevens Institute of Technology. Prior to that, he held postdoctoral researcher positions at the University of North Carolina and the University of Pennsylvania. He holds the Diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki, Greece, and the MS and PhD degrees, both in Electrical Engineering, from the University of Southern California. His research interest include 3D reconstruction from images and video, range data analysis, perceptual organization and manifold learning. Dr. Mordohai serves as an Associate Editor for the Journal of Image and Vision Computing and as a reviewer for numerous international journals and conferences. He has also organized several workshops and symposia.