THERMAL SCIENCE

International Scientific Journal

External Links

EXTRACTION METHOD OF POSITION AND POSTURE INFORMATION OF ROBOT ARM PICKING UP TARGET BASED ON RGB-D DATA

ABSTRACT
There is a big error in the traditional method to extract the position and attitude information of the robot. In the process of obtaining the target attitude, a method of extracting the target attitude information of robot arm based on RGB-D data is proposed. The position and attitude of the manipulator target are acquired by depth image processing, and the detected target position is sent to the manipulator control node, and the feature points of the manipulator are extracted. The 3-D mapping is carried out on the acquired RGB image, and the depth and RGB values of feature points, as well as position and attitude information are calculated by using the Gauss mixture model. Finally, the target is extracted by combining the covariance matrix of feature points. The experimental results show that the co-ordinate error and angle error of the robot arm extracted by this method are small. The maximum extraction error is only 28%, which is much lower than the traditional method, which shows that the proposed method is more applicable.
KEYWORDS
PAPER SUBMITTED: 2019-06-25
PAPER REVISED: 2019-08-18
PAPER ACCEPTED: 2019-08-19
PUBLISHED ONLINE: 2020-02-08
DOI REFERENCE: https://doi.org/10.2298/TSCI190625012T
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2020, VOLUME 24, ISSUE 3, PAGES [1481 - 1488]
REFERENCES
  1. Choi J, Park JI, Park H (2016) Twenty-one degrees of freedom model based hand pose tracking using a monocular RGB camera. Optical Engineering 1: 013-101.
  2. Chang JY (2018) Dr-net: Denoising and reconstruction network for 3d human pose estimation from monocular RGB videos. Electronics Letters 2: 70-72.
  3. Cui Z, Zhang SX, Cui YG (2016) Simulation study on the trajectory planning problem of redundant robots. Computer Simulation 3:268-273.
  4. Funes-Mora KA, Odobez JM (2016) Gaze estimation in the 3d space using RGB-D sensors. International Journal of Computer Vision 2: 194-216.
  5. Li J, Li S (2016) Gaze estimation from color image based on the eye model with known head pose. IEEE Transactions on Human-Machine Systems 3:414-423.
  6. Ling S, Cai Z, Li L, Ke L (2017) Performance evaluation of deep feature learning for RGB-D image/video classification. Information Sciences 86:266-283.
  7. Li CF, Gong ML, Sun C (2017) Realizing the transformation of martial arts education from the existence of posture to the existence of reality. Journal of Guangzhou Sport University 4: 113-115.
  8. Pandey PK, Jaboob SSA (2018) A finite difference method for a numerical solution of elliptic boundary value problems. Applied Mathematics & Nonlinear Sciences 3(1): 311-320.
  9. Brzeziński DW (2018) Review of numerical methods for NumILPT with computational accuracy assessment for fractional calculus. Applied Mathematics & Nonlinear Sciences 3(2): 487-502.
  10. Li XY, Xiong SJ, Lin BJ. (2016) Attitude control algorithm for simultaneous control of thruster attitude and orbit. Journal of Jilin University (Science Edition) 3: 603-608.
  11. Liu HB, Li JX, Yuan H, Han YK, Wang G (2016) Research on information interoperability technology for electric vehicle charging and replacing facilities. Chinese Journal of Power Sources 12: 2449-2452, 4 pages.
  12. Hu JH, Qin ZC, Shi L, Lu Z, Zhou B (2016) Spatial information cloud service platform architecture and application research. Journal of China Academy of Electronics 1:51-58.
  13. Massarelli C, Matarrese R, Uricchio VF, Muolo MR, Laterza M, Ernesto L (2017) Detection of asbestos-containing materials in agro-ecosystem by the use of airborne hyperspectral casi-1500 sensor including the limited use of two UAVS equipped with RGB cameras. International Journal of Remote Sensing 10:2135-2149.
  14. Ni T, Zhao YJ, Zhang HY, Liu XF, Huang LT. (2017) Real-time pose control system for robotic arm based on Kinect dynamic gesture recognition. Journal of Agricultural Machinery 10: 417-423.
  15. Qiu X, Wang Q, Yu L (2017) Implementation of visual odometer based on RGB-D camera. Journal of Zhejiang University of Technology 6:634-638.
  16. Ren BY, Wei K, Dai Y (2019) A target recognition and 3d pose estimation method in non-structural environment. Journal of Harbin Institute of Technology 1:38-44.
  17. Sun WL, Qian L. (2018) Research on attitude calculation based on mems and Kalman filter. Automation & Instrumentation 1: 1-3.
  18. Tan DJ, Tombari F, Navab N (2017) Real-time accurate 3d head tracking and pose estimation with consumer RGB-D cameras. International Journal of Computer Vision 1: 1-26.
  19. Theobalt, Christian (2017) Vnect: Real-time 3d human pose estimation with a single RGB camera. Acm Transactions on Graphics 2:44.

© 2020 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence