Share Email Print

Proceedings Paper

Measuring method for the object pose based on monocular vision technology
Author(s): Changku Sun; Zimiao Zhang; Peng Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Position and orientation estimation of the object, which can be widely applied in the fields as robot navigation, surgery, electro-optic aiming system, etc, has an important value. The monocular vision positioning algorithm which is based on the point characteristics is studied and new measurement method is proposed in this paper. First, calculate the approximate coordinates of the five reference points which can be used as the initial value of iteration in the camera coordinate system according to weakp3p; Second, get the exact coordinates of the reference points in the camera coordinate system through iterative calculation with the constraints relationship of the reference points; Finally, get the position and orientation of the object. So the measurement model of monocular vision is constructed. In order to verify the accuracy of measurement model, a plane target using infrared LED as reference points is designed to finish the verification of the measurement method and the corresponding image processing algorithm is studied. And then The monocular vision experimental system is established. Experimental results show that the translational positioning accuracy reaches ±0.05mm and rotary positioning accuracy reaches ±0.2o .

Paper Details

Date Published: 11 November 2010
PDF: 9 pages
Proc. SPIE 7855, Optical Metrology and Inspection for Industrial Applications, 78550Z (11 November 2010); doi: 10.1117/12.868984
Show Author Affiliations
Changku Sun, Tianjin Univ. (China)
Zimiao Zhang, Tianjin Univ. (China)
Peng Wang, Tianjin Univ. (China)

Published in SPIE Proceedings Vol. 7855:
Optical Metrology and Inspection for Industrial Applications
Kevin Harding; Peisen S. Huang; Toru Yoshizawa, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?