By Topic

The surface geometry of the single texture object recovery based on a single image

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Lijing Zhang ; Information & Network Management Center, North China Electric Power University, Baoding, China ; Xufeng Li

The method of surface geometry of object recovery mentioned in this paper can gain 3D dimensions of objects surface geometry only using a single image on the basis of brightness change. In this paper, the background knowledge and the methods related to SFS are briefly introduced. Based on the analysis and comparison of various reconstruction algorithms, this paper gives a new method of surface geometry recovery of objects from a single image. It is more simple and applicable. Using this method, hardware equipments only include image pick-up system and a computer. The operation mode is the uncomplicated principle of optical lens imaging. The core idea of this research is using image shading to recover surface geometry of objects. The shading is the 3D cues left in 2D image. In the coordinates of light source, the surface normal vectors corresponding to every pixel are calculated. Then these vectors are converted to the coordinates of image through the coordinate conversion, so surface geometry of objects are gained. This paper also analyzed the precision of the 3D recovery results.

Published in:

Advanced Computer Control (ICACC), 2010 2nd International Conference on  (Volume:5 )

Date of Conference:

27-29 March 2010