[중계, VOD, 세미나 파일]



1. 제   목 : Dynamic Sensor Fusion

2. 발표자 :  Professor Bir Bhanu
             Center for Research in Intelligent System
             University of California at Riverside
             Riverside, California

3. 일   시 :  2005년 11월 17일 (목) 15:00~16:30

4. 장   소 :  경북대 공대10호관 318호 

5. 초청교수 : 이 성 기 교수

6. 강사약력 : Bir Bhanu is the Professor Electrical Engineering and Computer Science (EECS) at the  University of California at Riverside since 1991 and the Director of the Center for Research in Intelligent Systems (CRIS) since 1998.  Previously, he was a Senior Honeywell Fellow at Honeywell Inc. 
He has been on the faculty of the Department of Computer Science at the University of Utah, and has worked at Ford Aerospace and Communications Corporation, INRIA-France and IBM San Jose Research Laboratory.  He has been the PI of various programs in the areas of learning and vision, 
image understanding, pattern recognition, target recognition, avigation, image databases, biometrics and machine vision applications. He received the S.M. and E.E. degrees in EECS from the Massachusetts  Institute of Technology the Ph.D. degree in E.E. from the Image Processing Institute, University of Southern California, and the M.B.A. degree from the University of California at Irvine.  Prof. Bhanu is a Fellow of AAAS, IEEE, IAPR  and SPIE.

7. 내용요약 :  A robust moving object detection system for an outdoor scene must be able to   handle adverse illumination conditions such as sudden illumination changes or lack of illumination in a scene. This is of particular importance for scenarios where active  illumination cannot be relied upon. Utilizing infrared and video sensors, we develop a novel
 sensor fusion system that automatically adapts to the environmental changes that affect sensor  measurements. The adaptation is done through a cooperative coevolutionary algorithm that fuses the scene contextual and statistical information through a physics-based method. 
The sensor fusion system maintains high detection rates under a variety of conditions.  The results are shown for a full 24 hour diurnal cycle.

8. 주최 : 대구신기술사업단 모바일단말상용화센터, 
            초일류 모바일-디스플레이산업 인력양성사업단
            BK21 정보기술인력양성사업단, 전자전기컴퓨터학부, 
            IEEE Taegu Section