Abstract

We describe an algorithm for segmenting a 3D object into its constituent volumetric parts from a single 2D line drawing. This algorithm is part of the bottom-up line drawing description process of PARVO, a generic object recognition system. In PARVO, an object is recognized as being a member of a class defined by qualitative geometrical properties and topological structure. Similarity between different 3D views of any member of a given class is a result of building coarse part-based structural descriptions from limited information. A preliminary stage to part segmentation of an object consists of extracting viewpoint-invariant and nonaccidental features from the line drawing. The segmentation process itself is described as a hierarchical decomposition of the line drawing on the basis of pairs of high-concavity points in its silhouette. The pairing of these so-called segmentation points rests on (i) an object visibility model describing the generic structures present in any line drawing satisfying our assumptions, and (ii) the feature instances extracted from the specific line drawing analyzed. First, we discuss the properties of the line drawings in the domain of PARVO. From them, geometrical models of important line drawing features may be developed. The latter are used both as cues in the segmentation process and as precursors to the representation from which part structure is understood.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.