2007 IEEE International Conference on Image Processing - San Antonio, Texas, U.S.A. - September 16-19, 2007

Technical Program

Paper Detail

Paper:WA-L2.2
Session:Video Object Segmentation and Tracking II
Time:Wednesday, September 19, 10:10 - 10:30
Presentation: Lecture
Title: A GRAPH-BASED FOREGROUND REPRESENTATION AND ITS APPLICATION IN EXAMPLE BASED PEOPLE MATCHING IN VIDEO
Authors: Kedar Patwardhan; University of Minnesota 
 Guillermo Sapiro; University of Minnesota 
 Vassilios Morellas; University of Minnesota 
Abstract: In this work, we propose a framework for foreground representation in video and illustrate it with a multi-camera people matching application. We first decompose the video into foreground and background. A low-level coarse segmentation of the foreground is then used to generate a simple graph representation. A vertex in the graph represents the ``appearance'' of a corresponding segment in the foreground, while the relationship between two segments is encoded by an edge between the corresponding vertices. This provides a simple yet powerful and general representation of the foreground, which can be very useful in problems such as people detection and tracking. We illustrate the effectiveness of this model using an ``example based query'' type of application for people matching in videos. Matching results are provided in multiple-camera situations and also under occlusion.



©2016 Conference Management Services, Inc. -||- email: webmaster@icip2007.com -||- Last updated Friday, August 17, 2012