Abstract

Based on binocular vision, this paper proposes an algorithm for fast and accurate three-dimensional measurement. The binocular 3D measurement system is mainly divided into four parts: binocular calibration, binocular correction, binocular matching and pose calculation. In this paper, an international softwareM is used to achieve camera calibration, the FAST algorithm is used to achieve the extraction of feature points, and the matching method that combines gray-level correlation coefficient (cc) and epipolar constraint is selected. Experiments have verified that this algorithm can accurately achieve three-dimensional pose measurement.

Details

Title
Research on 3D Pose Measurement Algorithm Based on Binocular Vision
Author
Fu, Qiang Shan 1 ; Wang, Feng 1 ; Hai Feng Zhang 1 

 Xi’an Institute of Optics and Precision Mechanics of UCAS, University of Chinese Academy of Sciences, Xi’an, Shanxi, 710119, China 
Publication year
2021
Publication date
Feb 2021
Publisher
IOP Publishing
ISSN
17426588
e-ISSN
17426596
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2513004855
Copyright
© 2021. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.