Paper Info
Title
Building Pedestrian Contour Hierarchies for Improving Detection in Traffic Scenes
Abstract
This paper presents a new method for extracting pedestrian contours from images using 2D and 3D information obtained from a stereo-vision acquisition system. Two pedestrian contour types are extracted. First is obtained from static pedestrian confidence images using fixed background scenes and second from general traffic scenes having variable background. A robust approach for building contour hierarchies of these contours is then presented. First hierarchy is built of "perfect" contours extracted from fixed background scenes and the second one is built of "imperfect" contours extracted from images with variable background. The objective is to evaluate the two hierarchies in order to identify the best one for real time pedestrian detection.
Year
DOI
Venue
2008
10.1007/978-3-642-02345-3_16
ICCVG
Keywords
Field
DocType
contour hierarchy,general traffic scene,pedestrian contour type,real time pedestrian detection,building pedestrian contour hierarchies,pedestrian contour,improving detection,static pedestrian confidence image,robust approach,fixed background scene,variable background,traffic scenes,new method,stereo vision,real time
Computer vision,Pedestrian,Imperfect,Pattern recognition,Computer science,Stereopsis,Artificial intelligence,Hierarchy,Pedestrian detection
Conference
Volume
ISSN
Citations 
5337
0302-9743
2
PageRank 
References 
Authors
0.37
7
2
Name
Order
Citations
PageRank
Ion Giosan122.06
Sergiu Nedevschi21321126.37