From invariant line features clustering to line matching: theory and applications

Djemaa Kachi; Xiaowei Tu

doi:10.1117/1.482696

1 April 1999 From invariant line features clustering to line matching: theory and applications

Djemaa Kachi, Xiaowei Tu

Journal of Electronic Imaging, Vol. 8, Issue 2, (April 1999). https://doi.org/10.1117/1.482696

In this paper, we formulate a complete approach of line matching, based on geometrical invariants. In the proposed technique, it is not necessary to have a priori knowledge about the observed objects and the camera calibration coefficients. This technique can be used in on-line tasks in robotics, tracking, and target recognition applications. A line segment is locally represented by invariant parameters under the group of displacements within an image and the scale changes. The matching process is achieved through two steps, features clustering and hypotheses verification. In order to be matched, a pair of lines represented by neighboring features in the parameter space must satisfy geometrical constraints (relative angle and distance) in the image plane. Conducted analysis and tests proved the stability of proposed line invariants under complex movements of camera. Experimental results have shown a high rate matching on different types of computer generated and real images.

Citation Download Citation

Djemaa Kachi and Xiaowei Tu "From invariant line features clustering to line matching: theory and applications," Journal of Electronic Imaging 8(2), (1 April 1999). https://doi.org/10.1117/1.482696

Published: 1 April 1999

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