Title :
Curve finder combining perceptual grouping and a Kalman like fitting
Author :
Guichard, Frédéric ; Tarel, Jean-Philippe
Author_Institution :
INRETS, Arcueil, France
Abstract :
We present an algorithm that extracts curves from a set of edgels within a specific class in a decreasing order of their “length”. The algorithm inherits the perceptual grouping approaches. But, instead of using only local cues, a global constraint is imposed on each extracted subset of edgels, that the underlying curve belongs to a specific class. In order to reduce the complexity of the solution, we work with a linearly parameterized class of curves, a function of one image coordinate. This first allows one to use recursive Kalman based fitting and, second, to cast the problem as an optimal path search in a directed graph. Experiments on finding lane-markings on roads demonstrate that real-time processing is achievable
Keywords :
Kalman filters; automated highways; edge detection; Kalman like fitting; complexity; curve extraction algorithm; curve finder; directed graph; edgels; global constraint; image coordinate; linearly parameterized curve class; optimal path search; perceptual grouping; real-time processing; recursive Kalman based fitting; road lane marking finding; Aggregates; Cameras; Curve fitting; Dynamic programming; Joining processes; Kalman filters; Navigation; Read only memory; Road vehicles; Vehicle detection;
Conference_Titel :
Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on
Conference_Location :
Kerkyra
Print_ISBN :
0-7695-0164-8
DOI :
10.1109/ICCV.1999.790378