A robust and efficient point matching method for stereovision measurement using dynamic programming

Peng Sun; Naiguang Lu

doi:10.1117/12.756598

28 November 2007 A robust and efficient point matching method for stereovision measurement using dynamic programming

Peng Sun, Naiguang Lu

Proceedings Volume 6834, Optical Design and Testing III; 68342W (2007) https://doi.org/10.1117/12.756598
Event: Photonics Asia 2007, 2007, Beijing, China

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.

Citation Download Citation

Peng Sun and Naiguang Lu "A robust and efficient point matching method for stereovision measurement using dynamic programming", Proc. SPIE 6834, Optical Design and Testing III, 68342W (28 November 2007); https://doi.org/10.1117/12.756598

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available