Skip to Main Content
Introduces a new primitive, the half-chunk, for encoding boundary, region, and surface information in graph form. General graph matching is discussed and a specific graph matching system based on half-chunk graphs is presented. Following matching, bindings are interpreted as object component motion or depth. The half-chunk graph allows scale and coordinate system independent object models to be represented. Half-chunk graphs may encode 2-D or 3-D structure equally well.