Share Email Print

Proceedings Paper

Visual robot guidance for an insertion task
Author(s): Dorin Ungureanu; Luc J. Van Gool; Theo Moons; Andre J. Oosterlinck
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Vision algorithms are proposed for an automated robot assembly task. The goal is to insert cylindrical objects with arbitrary cross-section shapes into narrowly matching holes. Scenes have variable compositions and the viewpoint of the camera is rather arbitrary. An affinely invariant shape description is used to compare inflection bounded segments of the image contours with similar segments describing a set of shapes in a model database. The comparison is a simple distance calculation between invariant segment signatures following a crude index-based preselection procedure. Once all matching image-model segment pairs have been found, they are grouped into complete model instances found in the image, by a consistency check algorithm. The typical shapes considered have no salient features, which moreover are small in number. This complicates the task of robust recognition. Besides recognition, the determination of object pose and position is described. A new method for determining camera focal length using image features is presented. Experimental results are discussed.

Paper Details

Date Published: 11 August 1995
PDF: 12 pages
Proc. SPIE 2573, Vision Geometry IV, (11 August 1995); doi: 10.1117/12.216433
Show Author Affiliations
Dorin Ungureanu, Katholieke Univ. Leuven (Belgium)
Luc J. Van Gool, Katholieke Univ. Leuven (Belgium)
Theo Moons, Katholieke Univ. Leuven (Belgium)
Andre J. Oosterlinck, Katholieke Univ. Leuven (Belgium)

Published in SPIE Proceedings Vol. 2573:
Vision Geometry IV
Robert A. Melter; Angela Y. Wu; Fred L. Bookstein; William D. K. Green, 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?