Share Email Print

Proceedings Paper

Unsupervised Model Building Of 3D Objects Using Range Information
Author(s): Denis Laurendeau; Denis Poussart
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presents a method for building the model of a 3D object from a range image provided by a fast range finder. The model is an adjacency graph describing the connectivity properties of neighbouring regions (facets) of the object. Each region is obtained from the segmentation scheme based on the analysis of the hemispheric histogram. The histogram organizes the surface orientation information. The model is built in an unsupervised manner and provides a compact description of the object. The model builder could be integrated in an automatic 3D object recognition system.

Paper Details

Date Published: 23 October 1986
PDF: 8 pages
Proc. SPIE 0665, Optical Techniques for Industrial Inspection, (23 October 1986); doi: 10.1117/12.938793
Show Author Affiliations
Denis Laurendeau, Universite Laval (Canada)
Denis Poussart, Universite Laval (Canada)

Published in SPIE Proceedings Vol. 0665:
Optical Techniques for Industrial Inspection
Paolo G. Cielo, Editor(s)

© SPIE. Terms of Use
Back to Top