Paper Info
Title
A 2D/3D Vision Based Approach Applied to Road Detection in Urban Environments.
Abstract
This paper presents an approach for road detection based on image segmentation. This segmentation is resulted from merging 2D and 3D image processing data from a stereo vision system. The 2D layer returns a matrix containing pixel's clusters based on the Watershed transform. Whereas the 3D layer return labels, that are classified by the V-Disparity technique, to free spaces, obstacles and non-classified area. Thus, a feature's descriptor for each cluster is composed with features from both layers. The road pattern recognition was performed by an artificial neural network, trained to obtain a final result from this feature's descriptor. The proposed work reports real experiments carried out in a challenging urban environment to illustrate the validity and application of this approach.
Year
DOI
Venue
2013
10.1109/IVS.2013.6629589
Intelligent Vehicles Symposium
Keywords
Field
DocType
image segmentation,matrix algebra,neural nets,object detection,roads,stereo image processing,transforms,2D layer,2D vision based approach,3D vision based approach,V-Disparity technique,artificial neural network,image segmentation,road detection,road pattern recognition,stereo vision system,urban environments,watershed transform,Computer Vision,Image Segmentation,Road Detection,V-Disparity Map,Watershed Transform
Object detection,Computer vision,Scale-space segmentation,Feature detection (computer vision),Feature (computer vision),Image texture,Computer science,Segmentation-based object categorization,Scale space,Image segmentation,Artificial intelligence
Conference
ISSN
Citations 
PageRank 
1931-0587
6
0.47
References 
Authors
0
4
Name
Order
Citations
PageRank
Giovani B. Vitor160.47
Danilo A. Lima2233.97
Alessandro Corrêa Victorino3435.32
Janito V. Ferreira4222.57