August 7, 2008: Seminar: Dr. Yaser Sheikh: "Recovering the Structure of Dynamic Scenes from Moving Cameras"

Abstract:

With the proliferation of camera-enabled cell phones, domestic robots, and wearable computers, moving cameras are being introduced en masse into society. The confluence of camera motion and the motion of objects in the scene complicates the task of understanding the scene from video. In this talk, I discuss how and when it is possible to disambiguate these two sources of motion, towards the goal of analyzing dynamic scenes from moving cameras. I begin by considering a single camera viewing a dynamic scene. Unlike contemporary approaches to this problem, which try to model the variation in the shape of objects, I show that modeling the variation of points along time is better motivated physically and produces more stable reconstructions. This model also intuitively characterizes the inherent reconstruction ambiguity for a single camera and motivates the study of dynamic scenes from multiple moving cameras. I present the case for conducting this analysis in spacetime, where a dynamic scene is considered a body in spacetime, and each video a spacetime image of this body. Through this representation, I demonstrate that classic algorithms in multiview geometry that deal with static scenes can be lifted to spacetime, and applied directly for dynamic scene analysis.

Brief Bio:

Yaser Sheikh is an assistant research professor at the Robotics Institute at Carnegie Mellon University. His research is in computer vision, primarily in analyzing dynamic scene including human activity analysis, dynamic scene reconstruction, moving camera networks, and nonrigid motion estimation. He obtained his doctoral degree from the University of Central Florida in 2006 and is a recipient of the Hillman award for excellence in computer science research.