METHOD FOR BUILDING A THREE-DIMENSIONAL SCENE MODEL BY ANALYSING A SEQUENCE OF IMAGES

摘要

The invention concerns a method comprising the following steps: calculating, for an image, a depth map (1) corresponding to the depth, in the three-dimensional space, of image pixels; calculating, for an image, a resolution map (2) corresponding to the three-dimensional resolution of the image pixels, based on the depth map; matching (6) a current image pixel with a pixel of another image of the sequence, pixels relating to a common point in the three-dimensional scene, by projecting the current image pixel onto the other image; selecting a current image pixel (6) according to its resolution and to that of the other pixels of the sequence matched with said pixel; constructing the three-dimensional model (8) from the selected pixels. One application concerns the generation of images for browsing.