Range image segmentation using pseudoreflectance images

Ho-Keun Song; Kug-Chan Cha; Jong Soo Choi

doi:10.1117/12.206700

21 April 1995 Range image segmentation using pseudoreflectance images

Ho-Keun Song, Kug-Chan Cha, Jong Soo Choi

Proceedings Volume 2501, Visual Communications and Image Processing '95; (1995) https://doi.org/10.1117/12.206700
Event: Visual Communications and Image Processing '95, 1995, Taipei, Taiwan

Abstract

In this paper, a range image segmentation method using Pseudo Reflectance Images (PRIs) is proposed. The PRI is generated of the range image by assuming a light source position and applying a shading algorithm. It is assumed that surfaces within a PRI correspond to physical surfaces in a scene. Planar surface points within the PRI can be readily extracted from the condition of homogeneous reflectance value in addition to the invariant characteristic of reflectance gradient. The extraction of quadratic surface points within the PRI is associated with the fact that is has a direct relationship between elliptical, hyperbolic and parabolic points and rotational change of the image reflectance gradient produced from varying light source position. Moreover, the major part of edges in range image are formed by jumps in reflectance values within the PRI, and these types of edges can be detected by common edge operator.

Citation Download Citation

Ho-Keun Song, Kug-Chan Cha, and Jong Soo Choi "Range image segmentation using pseudoreflectance images", Proc. SPIE 2501, Visual Communications and Image Processing '95, (21 April 1995); https://doi.org/10.1117/12.206700

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