Image Home
Image People
Image Publication
Image Applications
Image Data & Code
Image Library
Image Seminar
Image Link
Image Album



Search LAMDA
»

Seminar abstract

Real-time Video Object Cutout using Locally Competing 1SVMs

Minglun Gong
Associate Professor
Memorial University of Newfoundland




Abstract: Many computer vision applications, such as surveillance and teleconferencing, require extracting objects of interest from their surrounding backgrounds. Over the years there have been significant amount of efforts on this topic, nevertheless there still lacks a simple yet effective algorithm that can process live videos of objects with fuzzy boundaries captured by freely moving cameras. This talk presents an algorithm toward this goal. The key idea is to train and maintain two competing one-class support vector machines (1SVMs) at each pixel location, which model local color distributions for foreground and background, respectively. We advocate the usage of two competing local classifiers, as it provides higher discriminative power and allows better handling of ambiguities. As a result, our algorithm can deal with a variety of videos with complex backgrounds and freely moving cameras with minimum user interactions. In addition, by introducing novel acceleration techniques and by exploiting the parallel structure of the algorithm, realtime processing speed is achieved for VGA-sized videos.

Bio: Dr. Minglun Gong is an associate professor at the Memorial University of Newfoundland and an adjunct professor at the University of Alberta. He obtained his Ph.D. from the University of Alberta in 2003, his M.Sc. from the Tsinghua University in 1997, and his B.Engr. from the Harbin Engineering University in 1994. Minglun's research interests cover various topics in the broad area of visual computing (including computer graphics, computer vision, visualization, image processing, and pattern recognition). So far, he has published over 70 referred technical papers in refereed journals and conference proceedings and submitted 2 patent applications. He served as program committee member for top-tier conferences, such as ICCV and CVPR, and reviewer for prestigious journals including IEEE TPAMI and IJCV. He was the recipient of the Izaak Walton Killam Memorial Award and the CFI New Opportunity Award.
  Name Size

Image
PoweredBy
(for FireFox 3+ and IE 7+)
Contact LAMDA: (email) contact@lamda.nju.edu.cn (tel) +86-025-89681608 © LAMDA, 2016