Paper Info
Title
Color Active Contours for Tracking Roads in Natural Environments
Abstract
Scene interpretation and feature tracking in natural environments are very complex perceptual functions. Complexity lies on several factors, for example: the lack of control on illumination conditions and the presence of different textures in the environment. This paper presents a real-time method to track roads in natural environments. The scene is previously characterized and classified in different regions by a combined ICA and color segmentation method (not described in this paper). This method is not so fast to track desired features in real time. The region tracking is executed on color active contours. New color potential fields are proposed: a) one to attract active contours depending on the selected region color, and b) the second one to repulse active contours when it is inside the region. Two potential fields are defined from the results of the initial characterization process and are updated by the same process at a given constant frequency, to avoid errors mainly due to global changes in illumination conditions or to local changes on the characteristics of the selected region. This approach has been evaluated on image sequences, acquired in natural environments.
Year
DOI
Venue
2004
10.1007/978-3-540-30463-0_15
Lecture Notes in Computer Science
Keywords
Field
DocType
natural environment,active contour,real time,global change
Active contour model,Computer vision,Color space,Pattern recognition,Computer science,Segmentation,Edge detection,Image processing,Artificial intelligence,Independent component analysis,Color image,Color gradient
Conference
Volume
ISSN
Citations 
3287
0302-9743
0
PageRank 
References 
Authors
0.34
7
3
Name
Order
Citations
PageRank
Antonio Marín-hernández1158.47
Michel Devy254271.47
Juan Gabriel Aviña-cervantes38210.58