The surface-attribute probe—an “active-vision” approach to 3-D object characterization

摘要

The essence of model-based three-dimensional (3-D) object recognition is the establishment of unique correspondence between an arbitrarily oriented object apparent in an image, and one of a set of known model objects, or to demonstrate that no such correspondence exists. This paper describes an “active-vision” approach to the solution of this problem, which permits extracting only as much feature data as is needed to perform the recognition task rapidly and efficiently. The object is assumed illuminated with patterned light, and both edge and surface-curvature features are extracted in a mutually supportive manner from selected regions of interest in the image. An “active model” is hypothesized and progressively refined by extracting feature data from an increasing number of judiciously chosen image regions by means of a so-called surface-attribute probe (SAP), which extracts information about local surface orientation and curvature and can detect surface discontinuities. The process iterates until a definite recognition decision can be made.