Authors:
Emre Başeski
1
;
Lars Baunegaard With Jensen
1
;
Nicolas Pugeault
1
;
Florian Pilz
2
;
Karl Pauwels
3
;
Marc M. Van Hulle
3
;
Florentin Wörgötter
4
and
Norbert Krüger
1
Affiliations:
1
The Mærsk Mc-Kinney Møller Institute, Univeristy of Southern Denmark, Denmark
;
2
Department for Media Technology, Aalborg University Copenhagen, Denmark
;
3
Laboratorium voor Neuro- en Psychofysiologie, Belgium
;
4
Bernstein Center for Computational Neuroscience, University of Göttingen, Germany
Keyword(s):
Large scale maps, Lane detection, Independently moving objects.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Early Vision and Image Representation
;
Geometry and Modeling
;
Image and Video Analysis
;
Image-Based Modeling
;
Motion, Tracking and Stereo Vision
;
Pattern Recognition
;
Software Engineering
;
Statistical Approach
;
Visual Navigation
Abstract:
In this work, we address the problem of road interpretation for driver assistance based on an early cognitive vision system. The structure of a road and the relevant traffic are interpreted in terms of ego-motion estimation of the car, independently moving objects on the road, lane markers and large scale maps of the road. We make use of temporal and spatial disambiguation mechanisms to increase the reliability of visually extracted 2D and 3D information. This information is then used to interpret the layout of the road by using lane markers that are detected via Bayesian reasoning. We also estimate the ego-motion of the car which is used to create large scale maps of the road and also to detect independently moving objects. Sample results for the presented algorithms are shown on a stereo image sequence, that has been collected from a structured road.