3D SYSTEM AND METHOD FOR AUTOMATIC SELECTION OF 3D ALIGNMENT ALGORITHMS IN A VISION SYSTEM

摘要

Systems and methods are provided for selecting among 3D alignment algorithms in a 3D vision system. Such systems and methods include a runtime 3D range image having features of a runtime image or runtime object defined by at least a 3D point cloud, and a 3D camera assembly for obtaining a vision system processor. Training images are provided. This is defined by a 3D point cloud or 3D range image with the features of the model. The selection process is powered by the vision processor. The vision process analyzes at least one training area of the training image with the features of the model to determine the distribution of surface normals in the at least one training area. The vision process also selects at least one 3D alignment algorithm from the plurality of available 3D alignment algorithms, based on the nature of the distribution, to align the features of the model with respect to the features of the runtime object.