Abstract | ||
---|---|---|
We present a new application of computer vision: continuous measurement of the geometrical visibility range on inter-urban roads, solely based on a monocular image acquisition system. To tackle this problem, we propose first a road segmentation scheme based on a Parzen-windowing of a color feature space with an original update that allows us to cope with heterogeneously paved-roads, shadows and reflections, observed under various and changing lighting conditions. Second, we address the under-constrained problem of retrieving the depth information along the road based on the flat word assumption. This is performed by a new region-fitting iterative least squares algorithm, derived from half-quadratic theory, able to cope with vanishing-point estimation, and allowing us to estimate the geometrical visibility range. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-76390-1_80 | ACCV |
Keywords | Field | DocType |
depth information,new application,inter-urban road,region fitting,continuous measurement,computer vision,under-constrained problem,road segmentation scheme,new region-fitting iterative,geometrical visibility range estimation,geometrical visibility range,color feature space,least square,vanishing point,management system,mobile robot,feature space | Computer vision,Visibility,Feature vector,Pattern recognition,Computer science,Segmentation,Least mean square algorithm,Monocular image,Artificial intelligence,Continuous measurement,Mobile robot | Conference |
Volume | ISSN | ISBN |
4844 | 0302-9743 | 3-540-76389-9 |
Citations | PageRank | References |
3 | 0.42 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Erwan Bigorgne | 1 | 21 | 3.89 |
Jean-Philippe Tarel | 2 | 805 | 56.63 |