Paper Info
Title
A novelty detection approach for foreground region detection in videos with quasi-stationary backgrounds
Abstract
Detecting regions of interest in video sequences is one of the most important tasks in many high level video processing applications. In this paper a novel approach based on support vector data description is presented, which detects foreground regions in videos with quasi-stationary backgrounds. The main contribution of this paper is the novelty detection approach which automatically segments video frames into background/foreground regions. By using support vector data description for each pixel, the decision boundary for the background class is modeled without the need to statistically model its probability density function. The proposed method is able to achieve very accurate foreground region detection rates even in very low contrast video sequences, and in the presence of quasi-stationary backgrounds. As opposed to many statistical background modeling approaches, the only critical parameter that needs to be adjusted in our method is the number of background training frames.
Year
DOI
Venue
2006
10.1007/11919476_5
ISVC (1)
Keywords
Field
DocType
background class,background training frame,segments video frame,support vector data description,quasi-stationary background,novelty detection approach,foreground region detection,statistical background modeling approach,low contrast video sequence,high level video processing,video sequence,foreground region,statistical model,video processing,probability density function,region of interest
Background subtraction,Computer vision,Video processing,Novelty detection,Pattern recognition,Computer science,Support vector machine,Image processing,Pixel,Artificial intelligence,Novelty,Decision boundary
Conference
Volume
ISSN
ISBN
4291
0302-9743
3-540-48628-3
Citations 
PageRank 
References 
8
0.45
13
Authors
3
Name
Order
Citations
PageRank
Alireza Tavakkoli116815.97
Mircea Nicolescu279255.76
George Bebis32397149.44