Model-based orientation-independent 3-D machine vision techniques

Orientation-dependent techniques for the identification of a three-dimensional (3-D) object by a machine vision system are represented in parts. In the first part, the data consist of intensity images of polyhedral objects obtained by a single camera, while in the second part, the data consist of range images of curved objects obtained by a laser scanner. In both cases, the attributed graph representation of the 3-D object surface is used to drive the respective algorithm. In this representation, a graph node represents a surface path and a link, the adjacency between two patches. The attributes assigned to nodes are moment invariants of the corresponding face for polyhedral objects. For range images, the Gaussian curvature is used as a segmentation criterion for providing symbolic shape attributes. Identification is achieved by an efficient graph-matching algorithm used to match the graph obtained from the data to a subgraph of one of the model graphs stored in the computer memory