Share Email Print

Proceedings Paper • Open Access

Efficient 3D object tracking approach based on convolutional neural network and Monte Carlo algorithms used for a pick and place robot
Author(s): Y. Zhang; C. Zhang; R. Nestler; M. Rosenberger; G. Notni

Paper Abstract

Currently, Deep Learning (DL) shows us powerful capabilities for image processing. But it cannot output the exact photometric process parameters and shows non-interpretable results. Considering such limitations, this paper presents a robot vision system based on Convolutional Neural Networks (CNN) and Monte Carlo algorithms. As an example to discuss about how to apply DL in industry. In the approach, CNN is used for preprocessing and offline tasks. Then the 6- DoF object position are estimated using a particle filter approach. Experiments will show that our approach is efficient and accurate. In future it could show potential solutions for human-machine collaboration systems.

Paper Details

Date Published: 17 September 2019
PDF: 6 pages
Proc. SPIE 11144, Photonics and Education in Measurement Science 2019, 1114414 (17 September 2019); doi: 10.1117/12.2530333
Show Author Affiliations
Y. Zhang, Technische Univ. Ilmenau (Germany)
C. Zhang, Technische Univ. Ilmenau (Germany)
R. Nestler, Technische Univ. Ilmenau (Germany)
M. Rosenberger, Technische Univ. Ilmenau (Germany)
G. Notni, Technische Univ. Ilmenau (Germany)

Published in SPIE Proceedings Vol. 11144:
Photonics and Education in Measurement Science 2019
Maik Rosenberger; Paul-Gerald Dittrich; Bernhard Zagar, 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?