Method for estimating object position or orientation, involves stereoscopically recording scene of object by image-recording device, where three dimensional-point cloud representation of scene is attributed with movement information

摘要

The method involves stereoscopically recording a scene of an object (O1,O2,O3) in two images (B1,B2) by an image-recording device. A three dimensional-point cloud representation of the scene is attributed with the movement information. The cloud representation is determined by a stereo-algorithm or flow algorithm. The scene is segmented on the basis of the attributed three dimensional-point cloud representation. A three dimensional object model (OM) is provided for determining the position, orientation or movement.