Speaker：Dr. Guoliang Fan, School of Electrical and Computer Engineering, Oklahoma State University
Time： 15:00-17:00 am , September 28, 2011
Venue： East Conference Room, fourth floor of Zutong Building
Venue： East Conference Room, fourth floor of Zutong Building
Introduction to Lecturer:
Guoliang Fan received the B.S. degree in Automation Engineering from Xi'an University of Technology, Xi'an, China, in 1993, the M.S. degree in Computer Engineering from Xidian University, Xi'an, China, in 1996, and the Ph.D. degree in Electrical Engineering from the University of Delaware, Newark, DE, in 2001. From 1996 to 1998, he was a graduate assistant in the Department of Electronic Engineering at the Chinese University of Hong Kong. Since 2001, Dr. Fan has been an assistant and associate professor in the School of Electrical and Computer Engineering at Oklahoma State University (OSU), Stillwater, OK, and the Director of Visual Computing and Image Processing Laboratory (VCIPL). His research interests include image processing, machine learning computer vision, biomedical imaging and remote sensing applications. Dr. Fan is a recipient of the 2004 National Science Foundation (NSF) CAREER award. He received the Halliburton Excellent Young Teacher Award in 2004, the Halliburton Outstanding Young Faculty Award in 2006 from the College of Engineering at OSU, and the Outstanding Professor Award from IEEE-OSU in 2008 and 2011. He is an associate editor of the IEEE Trans. Information Technology in Biomedicine, EURASIP Journal on Image and Video Processing and ISRN Machine Vision. Dr. Fan is a senior member of IEEE.
Guoliang Fan received the B.S. degree in Automation Engineering from Xi'an University of Technology, Xi'an, China, in 1993, the M.S. degree in Computer Engineering from Xidian University, Xi'an, China, in 1996, and the Ph.D. degree in Electrical Engineering from the University of Delaware, Newark, DE, in 2001. From 1996 to 1998, he was a graduate assistant in the Department of Electronic Engineering at the Chinese University of Hong Kong. Since 2001, Dr. Fan has been an assistant and associate professor in the School of Electrical and Computer Engineering at Oklahoma State University (OSU), Stillwater, OK, and the Director of Visual Computing and Image Processing Laboratory (VCIPL). His research interests include image processing, machine learning computer vision, biomedical imaging and remote sensing applications. Dr. Fan is a recipient of the 2004 National Science Foundation (NSF) CAREER award. He received the Halliburton Excellent Young Teacher Award in 2004, the Halliburton Outstanding Young Faculty Award in 2006 from the College of Engineering at OSU, and the Outstanding Professor Award from IEEE-OSU in 2008 and 2011. He is an associate editor of the IEEE Trans. Information Technology in Biomedicine, EURASIP Journal on Image and Video Processing and ISRN Machine Vision. Dr. Fan is a senior member of IEEE.
Summary of Lecture:
Automated target tracking and recognition (ATR) is an important capability in many civilian applications. ATR systems usually comprises several stages with the ability to detect, track and recognize targets. In this talk, we mainly focus on the tracking and recognition aspects for infrared (IR) imagery. The major challenge in vision-based ATR is how to cope with the variations of target appearances due to different viewpoints and underlying 3D structures. Both factors, identity in particular, are usually represented by discrete variables in most existing ATR algorithms. We propose a new couplet of identity and view manifolds for multi-view target modeling that is applied to automated target tracking and recognition (ATR). The identity manifold captures both inter-class and intra-class variability of target appearances by a continuous identity variable, while a hemisphere-shaped view manifold is involved to account for the variability of viewpoints. Combining these two manifolds via a non-linear tensor decomposition gives rise to a new target generative model that can be learned from a small training set and generalized to various known and unknown targets under arbitrary views. Not only can this model deal with arbitrary view/pose variations by tracking along the view manifold, it can also interpolate the appearance of an unknown target along the identity manifold. We also develop a particle filter-based ATR algorithm where the proposed model used for shape matching. The proposed algorithm is tested against the recently released SENSIAC ATR database and the experimental results validate its efficacy both qualitatively and quantitatively.
Automated target tracking and recognition (ATR) is an important capability in many civilian applications. ATR systems usually comprises several stages with the ability to detect, track and recognize targets. In this talk, we mainly focus on the tracking and recognition aspects for infrared (IR) imagery. The major challenge in vision-based ATR is how to cope with the variations of target appearances due to different viewpoints and underlying 3D structures. Both factors, identity in particular, are usually represented by discrete variables in most existing ATR algorithms. We propose a new couplet of identity and view manifolds for multi-view target modeling that is applied to automated target tracking and recognition (ATR). The identity manifold captures both inter-class and intra-class variability of target appearances by a continuous identity variable, while a hemisphere-shaped view manifold is involved to account for the variability of viewpoints. Combining these two manifolds via a non-linear tensor decomposition gives rise to a new target generative model that can be learned from a small training set and generalized to various known and unknown targets under arbitrary views. Not only can this model deal with arbitrary view/pose variations by tracking along the view manifold, it can also interpolate the appearance of an unknown target along the identity manifold. We also develop a particle filter-based ATR algorithm where the proposed model used for shape matching. The proposed algorithm is tested against the recently released SENSIAC ATR database and the experimental results validate its efficacy both qualitatively and quantitatively.
