A new usage of ASIFT for the range image registration

Chun-Yang Liu; Dong Li; Jin-Dong Tian

doi:10.1117/12.2072047

13 November 2014 A new usage of ASIFT for the range image registration

Chun-Yang Liu, Dong Li, Jin-Dong Tian

Proceedings Volume 9276, Optical Metrology and Inspection for Industrial Applications III; 92761Y (2014) https://doi.org/10.1117/12.2072047
Event: SPIE/COS Photonics Asia, 2014, Beijing, China

Abstract

This paper addresses the range image registration problem for views having overlapping area and which may include substantial noise. The current state of the art in range image registration is best represented by the well-known iterative closest point (ICP) algorithm and numerous variations on it. Although this method is effective in many domains, it nevertheless suffers from two key limitations: It requires prealignment of the range surfaces to a reasonable starting point and it is not robust to outliers arising either from noise or low surface overlap. This paper proposes a new approach that avoids these problems for precision range image registration, by using a new, robust method based on ASIFT followed by ICP. Up to now, this approach has been evaluated by experiment. We define the fitness function to calculate the time for the convergence stage of ICP, because the time required is very important. ASIFT are capable of image matching even when there is fully affine variant. The novel ICP search algorithm we present following ASIFT offers much faster convergence than prior ICP methods, and ensures more precise alignments, even in the presence of significant noise, than mean squared error or other well-known robust cost functions.

Citation Download Citation

Chun-Yang Liu, Dong Li, and Jin-Dong Tian "A new usage of ASIFT for the range image registration", Proc. SPIE 9276, Optical Metrology and Inspection for Industrial Applications III, 92761Y (13 November 2014); https://doi.org/10.1117/12.2072047

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