By Topic

Acquisition of 3-D information using stereo vision system by relative stereo disparity with subpixel resolution

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
$31 $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

4 Author(s)
Jang Kyu Kim ; Graduate Sch. of Mech. & Intelligent Syst. Eng., Pusan Nat. Univ., South Korea ; Min Cheol Lee ; Cheol Ki Ahn ; Chi Yen Kim

For the acquisition of 3-dimensional information in real space, a stereo vision system is suitable. In the stereo system, the 3D real world position is derived from translation of the coordinates between the cameras and the world. Thus, to use stereo vision, there is a need to construct a precise system which provides kinematic precise translation between the camera and world coordinates, in spite of the intricacy and difficulty. Therefore, much cost and time should be spent to build the system. In this paper, facilely to solve the previous problem, a method which can easily obtain 3D information using reference objects and RSD (relative stereo disparity) is proposed. Instead of direct computation of the position with translation of coordinates, only relative stereo disparity in stereo image pair is used to find the reference depth of objects, and the real 3D position is computed with the initial condition of the reference objects. In computation, subpixel resolution is involved to find the disparity for accuracy. To find the RSD, corresponding points are calculated in subpixel resolution. The results of an experiment show that subpixel resolution is more accurate than 1 pixel resolution

Published in:

Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on  (Volume:3 )

Date of Conference:

2001