Precise, automatic and fast method for vanishing point detection |
| |
Authors: | Mahzad Kalantari Franck Jung Jeanpierre Guedon |
| |
Affiliation: | (); () Ecole Nationale des Sciences Géographiques, Institut Géographique National (IGN), Marne la Vallée, France; () Institut de Recherche en Communications et Cybernétique de Nantes (IRCCyN), Ecole Polytechnique University of Nantes, France |
| |
Abstract: | A new automated approach for vanishing point detection in images of urban scenes is described. This method is based on the theorem of Thales. The main contribution of this paper is the automatic and simultaneous detection of all vanishing points of the image, achieved by converting this problem into the detection of circles in a complex cloud of points, in which each point corresponds to a segment and is associated with an uncertainty. This extraction of circles uses a RANSAC method, modified to improve its speed by using accumulation techniques (Hough transform or otherwise). This robust estimation is then refined by least squares error propagation using the individual variances of each segment. The algorithm is robust, its accuracy is optimised and it is entirely automatic. Its successful operation has been tested on a large number of images of varied urban scenes. |
| |
Keywords: | circle detection Thales' theorem uncertainty propagation urban images vanishing point detection |
|
|