Gerard Medioni: Computer Vision Contributor and Co-director of the USC Institute for Robotics and Intelligent Systems

January 24, 2008

Professor Gua9rard Medioni received the Diplub4me dIngenieur from ENST, Paris in 1977, a M.S. and Ph.D. from the University of Southern California in 1980 and 1983 respectively. He has been at USC since then, and is currently Professor of Computer Science and Electrical Engineering, Chairman of the Computer Science Department, co-director of the Institute for Robotics and Intelligent Systems (IRIS), and co-director of the USC Games Institute. Professor Medioni has made significant contributions to the field of computer vision. His research covers a broad spectrum of the field, such as edge detection, stereo and motion analysis, shape inference and description, and system integration. He has published 3 books, over 50 journal papers and 150 conference articles, and is the recipient of 8 international patents.

Prof. Medioni is associate editor of the Image and Vision Computing Journal, associate editor of the Pattern Recognition and Image Analysis Journal, and associate editor of the International Journal of Image and Video Processing.

Prof. Medioni served as program co-chair of the 1991 IEEE CVPR Conference in Hawaii, of the 1995 IEEE Symposium on Computer Vision in Miami, general co-chair of the1997 IEEE CVPR Conference in Puerto Rico, conference co-chair of the 1998 ICPR Conference in Australia, general co-chair of the 2001 IEEE CVPR Conference in Kauai, and general co-chair of the 2007 IEEE CVPR Conference in Minneapolis.
He is a Fellow of IAPR, a Fellow of the IEEE, and a Fellow of AAAI.

Below is a brief interview with Professor Medioni about his contributions to Computer Vision.

Help us understand what you are up to (Describe your work / research):
My area of interest is the automatic analysis of imagery, still, video, stereo, infrared, %ue2%u20ac%ua6
This field is called Computer Vision or Image Understanding.

What drives you to continue pursuing this area of study?
People perform this task effortlessly, but it is a very difficult endeavor. We have been studying this for over 30 years, and, while we have made good progress, are still far from having robust solutions. Its a large challenge, and an ideal research topic for many years to come.

Describe how your work might impact peoples lives, now and in the future.
Developing intelligent vision systems has huge societal impact.
1)For instance, the use of biometric data for identification (face, iris recognition) will likely replace/complement password, i.d. management.
2) face modeling from images leads to the creation of realistic avatars for entertainment purposes.
3) intelligent video surveillance systems can detect unusual or predefined patterns of activity.
4)Also, personal service robots are emerging as a vibrant industry. They need robust perceptual abilities, including vision to know where people and things are, to reach them, to clean floors, etc..
5) Augmented video, in which synthetic elements are automatically added to existing footage, allow a user to get a richer experience (i.e. yellow line in football, distance to the goal, %ue2%u20ac%ua6)

How did you come up with the idea?
I have created and licensed the following
- a biometric identification system now in use in some jails for booking/releasing inmates
- a face modeling system to create realistic 3D models of a person from a few images
- a vision system for personal service robot
- a system to insert graphic elements into sports video
I am working on
- a system to perform face recognition at a distance for non cooperative subjects

Has anyone ever doubted that your idea could work?
it is well known that you cannot make a 3D model of a face from 2 images
This was told by more than one researcher visiting the lab, %ue2%u20ac%ua6 before we actually showed them the result on their own face!

What is the next step in the innovation process for you (and how might people help)?
PR, PR, PR

What is the one innovation you cant live without?
High bandwidth connectivity

What would people be surprised to learn about you?
I have spent my entire career at USC, from MS to PhD to Prof to Chair. My first paper was one on solving the Rubiks cube puzzle.

What do you wish you would have invented?
The wheel, or the zipper

What is the most fun youve ever had?
Traveling to exotic places