Home
학과소식
세미나
기존 세미나
기존 세미나
[세미나]Generalized Background Subtraction(Prof. Bohyung Han - POSTECH)
1. 제 목 : Generalized Background Subtraction
2. 연 사 : Prof. Bohyung Han (POSTECH)
3. 일 시 : 2012년 5월 10일 (목) 오후 4시30분
4. 장 소 : 301동 1512-2호 세미나실
5. 내용 :
Background subtraction is one of the most popular techniques to identify moving objects in the scene, but can only be applied to static camera environment. I present a novel background subtraction algorithm for the videos captured by a moving camera. In this technique, foreground and background appearance models in each frame are constructed and propagated sequentially by Bayesian filtering the posterior of appearance is computed by the product of the image likelihood in the current frame and the prior appearance propagated from the previous frame. The motion, which transfers the previous appearance models to the current frame, is estimated by nonparametric belief propagation, so the initial motion field is obtained by optical flow and noisy and incomplete motions are corrected effectively through the inference procedure. This framework is represented by a unified graphical model, where the sequential inference of motion and appearance is performed by the combination of belief propagation and Bayesian filtering.
6. Bio :
Bohyung Han received the BS and MS degrees from the Department of Computer Engineering at Seoul National University, Korea, in 1997 and 2000, respectively, and the PhD degree from the Department of Computer Science at the University of Maryland, College Park, in 2005. He was a research staff at Samsung Electronics R&D Center, Irvine, California and Mobileye Vision Technologies, Princeton, New Jersey. He is currently an assistant professor in the Department of Computer Science and Engineering at POSTECH, Korea. His research interests include computer vision, machine learning, pattern recognition, and computer graphics.
7. 문 의 : 기계항공공학부 박종우 교수 (880-7133)
2. 연 사 : Prof. Bohyung Han (POSTECH)
3. 일 시 : 2012년 5월 10일 (목) 오후 4시30분
4. 장 소 : 301동 1512-2호 세미나실
5. 내용 :
Background subtraction is one of the most popular techniques to identify moving objects in the scene, but can only be applied to static camera environment. I present a novel background subtraction algorithm for the videos captured by a moving camera. In this technique, foreground and background appearance models in each frame are constructed and propagated sequentially by Bayesian filtering the posterior of appearance is computed by the product of the image likelihood in the current frame and the prior appearance propagated from the previous frame. The motion, which transfers the previous appearance models to the current frame, is estimated by nonparametric belief propagation, so the initial motion field is obtained by optical flow and noisy and incomplete motions are corrected effectively through the inference procedure. This framework is represented by a unified graphical model, where the sequential inference of motion and appearance is performed by the combination of belief propagation and Bayesian filtering.
6. Bio :
Bohyung Han received the BS and MS degrees from the Department of Computer Engineering at Seoul National University, Korea, in 1997 and 2000, respectively, and the PhD degree from the Department of Computer Science at the University of Maryland, College Park, in 2005. He was a research staff at Samsung Electronics R&D Center, Irvine, California and Mobileye Vision Technologies, Princeton, New Jersey. He is currently an assistant professor in the Department of Computer Science and Engineering at POSTECH, Korea. His research interests include computer vision, machine learning, pattern recognition, and computer graphics.
7. 문 의 : 기계항공공학부 박종우 교수 (880-7133)