Share Email Print

Proceedings Paper

Automatically planning the inspection of three-dimensional objects using stereo computer vision
Author(s): A. David Marshall; D. R. Roberts
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper addresses the problems associated with the inspection of geometric features of machined objects using three-dimensional data provided from an active stereo vision system. The inspection strategies we are concerned with are mainly concerned with verifying geometric tolerances to typical engineering requirements, in other words, verifying the presence and the dimensions of features and measuring feature relationships. This paper discusses how three-dimensional data may be processed to produce relevant features, information and how these may be interrogated to perform inspection automatically using the described vision system. A key issue here is how best to acquire the data in the form of a series of images on which the inspection is performed. The main purpose of this paper is therefore to address problems of choosing appropriate inspection strategies so that an object can be accurately inspected using the minimum possible number of views. This is achieved by reasoning with geometric models in order that the inspection methods can be planned effectively. Consideration of the vision system configuration and the accessibility of viewpoints on the object provide other factors that need to be considered in the reasoning process.

Paper Details

Date Published: 19 January 1996
PDF: 12 pages
Proc. SPIE 2599, Three-Dimensional and Unconventional Imaging for Industrial Inspection and Metrology, (19 January 1996); doi: 10.1117/12.230369
Show Author Affiliations
A. David Marshall, Univ. of Wales College Cardiff (United Kingdom)
D. R. Roberts, Univ. of Wales College Cardiff (United Kingdom)

Published in SPIE Proceedings Vol. 2599:
Three-Dimensional and Unconventional Imaging for Industrial Inspection and Metrology
Michael R. Descour; Kevin G. Harding; Donald J. Svetkoff, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?