Volume 37, Number 3, June 2019
|Page(s)||496 - 502|
|Published online||20 September 2019|
Product Blind Area Assembly Method Based on Augmented Reality and Machine Vision
School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, 710072, China
2 Dongguan Sanhang Civil-Military Integration Innovation Institute, Dongguan 523808, China
In the manual assembly of the blind area, the worker's line of sight is blocked, and the real-time state of the parts to be assembled cannot be seen, which has a great impact on the efficiency and accuracy of the assembly. Aiming at this problem, a blind zone assembly method based on machine vision and augmented reality(AR) is proposed. Firstly, the ellipse is used as the marker point. The object to be assembled in the blind area is indirectly tracked by the detection and positioning of the ellipse, and the AR visualization guide assembly is then performed by projection and the assembly is precisely guided using the principle of local error amplification. Finally, the blind zone assembly experiment based on machine vision and augmented reality is designed to verify the effectiveness of the method. The experimental results show that this method can significantly improve the efficiency of assembly work in blind areas and can effectively reduce the assembly error rate.
Key words: blind area assembly / augmented reality / machine vision
关键字 : 盲区装配 / 增强现实 / 机器视觉
© 2019 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.