Share Email Print

Proceedings Paper

A robust and efficient point matching method for stereovision measurement using dynamic programming
Author(s): Peng Sun; Naiguang Lu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Many vision tasks such as 3D measurement, scene reconstruction, object recognition, etc., rely on feature correspondence among images. This paper presents a novel binocular method taking full account of the causes of matching ambiguities. On the basis of rectification which increases the distribution similarity of the points from the two images, the dynamic programming technique is used to search for an optimal path with the matching fashions of the most appropriate correspondences along each scan line as its nodes, which makes a global minimization of the summation of all the intra- and inter-scan line disparity gradients. This method was applied to the 3D surface measurement for an inflatable parabolic reflector with satisfactory results despite the significantly different viewpoints and occlusion that indicates the robustness, efficiency and application feasibility in real-time measurement field of this method.

Paper Details

Date Published: 28 November 2007
PDF: 10 pages
Proc. SPIE 6834, Optical Design and Testing III, 68342W (28 November 2007); doi: 10.1117/12.756598
Show Author Affiliations
Peng Sun, Beijing Information Science and Technology Univ. (China)
Naiguang Lu, Beijing Information Science and Technology Univ. (China)

Published in SPIE Proceedings Vol. 6834:
Optical Design and Testing III
Yongtian Wang; Theo T. Tschudi; Jannick P. Rolland; Kimio Tatsuno, Editor(s)

© SPIE. Terms of Use
Back to Top