Ioannis A. Kakadiaris is an Assistant Professor in the Department of Computer of the University of Houston since August 1997.

From November 1996 to July 1997 he was a Post-Doctoral Fellow in the Department of Computer and Information Science of the University of Pennsylvania.

Dr. Kakadiaris received the Ptychion (B.S.) (1989) in Physics from the University of Athens, Greece, the M.Sc. (1991) in Computer Science from the Northeastern University, Boston, MA and the PhD (1997) in Computer Science from the University of Pennsylvania, Philadelphia, PA.

Dr. Kakadiaris is the Director of the Visual Computing Lab and his expertise includes computer graphics, physics-based modeling and simulation, computer vision, and medical image analysis.

His research concentrates on developing algorithms, techniques and systems that increase our understanding on data interrogation and information extraction, and on data representations that facilitate these tasks.

He received the NSF Faculty Early Career Award in the Spring of 2000. Dr. Kakadiaris is the Focus Group Chairfor Graphics and Visualization for the Computing Curricula 2001.

Passive 3D Human Motion Capture: Vision-Based Tracking Meets Computer Animation Automatic, non-intrusive vision-based capture of the human body motion opens new possibilities in applications requiring the use of geometric and kinematic data from individuals (e.g., virtual reality, teleconferencing, performance measurement).

If synthesized motion is to be compelling, we must create actors for computer animations and virtual environments that appear realistic when they move. In this talk, I will present the formulations and techniques that we have developed for the three-dimensional model-based motion capture and animation of unconstrained human movement from multiple cameras. Our tracking and animation system consists of a human motion analysis and a synthesis components.

First, I will present novel analytical computer vision techniques to accurately recover the three-dimensional shape and pose of a subject's body parts. These techniques are based on the spatio-temporal analysis of a subject's silhouette from image sequences acquired simultaneously from multiple cameras. For the motion synthesis component, we have developed techniques that allow the efficient and realistic animation of the subject's estimated graphical model. The advantage of our system is that the subject does not have to wear markers or special equipment.

Finally, I will present motion estimation and animation results demonstrating the generality and robustness of our algorithm.