SEECS Colloquium

Recent hardware developments have rendered controlled active vision a practical option for a broad range of problems, spanning applications as diverse as intelligent vehicle highway systems, robotic-assisted surgery, micro assembly of micro-electromechanical systems (MEMS), automated spacecraft docking, unmanned vehicles, and inspection and vision assisted grasping.

However, realizing this potential requires having a framework for synthesizing robust active vision systems, capable of moving beyond carefully controlled environments.

“A Novel Approach to Active Vision Systems: Modeling, Control and Real-Time Tracking” aims to find a general framework to synthesize robust active vision systems using recently developed robust identification and robust control synthesis techniques.

First of all, the proposed approach shows how recently developed robust identification techniques can be used to find a family of models for an active vision system in a unified sense, treating cameras, motors and image processing hardware as a single system without requiring any camera calibration.

Moreover, we use this family of models to design a robust controller by using m-synthesis techniques. The designed controller is shown to be capable of delivering good performance for a range of conditions such as noise, changing camera parameters (various zoom values), depth of the scene, uncertain time delays (largely due to the time required by the image processing algorithm to locate the object in the scene), unmodeled dynamics, noisy and blurred visual feedback. These techniques eliminate the need for tuning controller parameters a posteriori, by trial and error, and for calibrating the system.

Finally, these results are experimentally validated using a UniSight/BiSight robotic head-eye platform.

Mr. Tamer Inanc was born in Izmir, Turkey. He received his B.S. degree, in Electrical and Electronics Engineering from the Dokuz Eylul University, Izmir, Turkey, in July 1991, ranking 6th among about 100 graduates. He received his M.S. degree in Electrical Engineering at the Pennsylvania State University, University Park, PA, in August 1996.

Currently he is about the finish his Ph.D. degree in Electrical Engineering Department at the Pennsylvania State University, University Park, PA, under the supervision of ProfessorMario Sznaier. His research interests are Robust Identification, Robust Control, Robust Active Vision Systems, and Computer Vision.