OBJECT POSE BASED ON MATCHING 2.5D DEPTH INFORMATION TO 3D INFORMATION

摘要

By matching (26) depth information with 3D information, pose of an object (14) relative to a camera (12) is determined (30). Orthographic projections of the 3D information are created (24) from different viewpoints. The orthographic projections may be represented as 2.5D data structures, allowing matching (26) with 2.5D data from a depth sensor (12) of the camera (12). Using orthographic projections may be invariant to camera (12) parameters and allow simple scaling for matching (26). The matching (26) provides (30) the pose, allowing transfer of metadata from the 3D information to the camera (12) images.