Automatic detection of planar contours from uncalibrated images

The present paper describes an original technique developed for detecting and matching unknown planar structures between a pair of uncalibrated images. Problems related to bad segmentation or to occlusion are automatically solved in most cases. The match process works hierarchically on pertinent point which provide local consistency and on contours which ensure the global consistency. After matching, contours are split into planar contour according to collineations. Tests made over different pairs of images demonstrate the efficiency of our approach.