A method for the adaptation of a object model to a three-dimensional point cloud by the correction of the corresponding error tendencies

摘要

The invention relates to a method for adapting a object model (om) to a three-dimensional point cloud (pw), in which the point cloud (pw) by means of a stereo - method (s1) of two images (b1, b2) is generated and a clustering - a method (s2) to the point cloud (pw) is applied, in order to in each case a cluster (cl) to identify associated points, and subsequently a template matching (s3) is carried out, in which at least one object model (om) at least one cluster (cl) and superimposed on an optimum position of the object model (om) with respect to the cluster (cl) is determined, and wherein a correction (s4) of incorrect allocations of points by means of the adjusted object model (om) is carried out, wherein at least two iterations with the stereo - a method (s1), the clustering - a method (s2), of the template matching (s3) and the correction (s4) of incorrect allocations be carried out, whereby from the second iteration of the previous iteration a probability of the location for at least one of the points in the point cloud (pw, pw ′) is determined and in the formation of correspondences in the stereo - a method (s1) is taken into account.