ROBUST AND AUTOMATIC VANISHING POINTS DETECTION WITH THEIR UNCERTAINTIES FROM A SINGLE UNCALIBRATED IMAGE, BY PLANES EXTRACTION ON THE UNIT SPHERE

This paper deals with the retrieval of vanishing points in uncalibrated images. Many authors did work on that subject in the computer vision field because the vanishing point represents a major information. In our case, starting with this information gives the orientation of the images at the time of the acquisition or the classification of the different directions of parallel lines from an unique view. The goal of this paper is to propose a simple and robust geometry embedded into a larger frame of image work starting with an efficient vanishing point extraction without any prior information about the scene and any knowledge of intrinsic parameters of the optics used.After this fully automatic classification of all segments belonging to the same vanishing point, the error analysis of the vanishing points found gives the covariance matrix on the vanishing point and on the orientation angles of the camera, when using the fact that the 3D directions of lines corresponding to the vanishing points are horizontal or vertical. A validation of estimated parameters with the help of the photo-theodolite has been experimented that demonstrate the interest of the method for real case. The algorithm has been tested on the database of a set of 100 images available on line.