Abstract
3D pose estimation plays an important role in human-computer cooperation and intelligent control. At present, the manipulator with sensor can realize spatial three-dimensional pose estimation, but the cost is too high. In this paper, the three-dimensional spatial positioning of the manipulator is carried out through the visual label. The two-dimensional pixel coordinates of the visual label on the manipulator are obtained by pasting the visual label on the manipulator and placing three cameras in different directions. By solving the three-dimensional coordinates of the manipulator through the three-dimensional vision fusion proposed in this paper, combined with the least square method to optimize the measurement results, multiple constraint equations can be established through multi-objective vision to improve the measurement accuracy, expand the motion range of the measured object, and have high robustness and economy. In the binocular vision pose detection, 89% of the measurement error within 2 m is less than 10 mm. The detection speed of the robot pose measurement system based on multi vision reaches 16 fps, and more than 96% of the measurement error within 2 m does not exceed 3 mm. Considering the needs of real-time monitoring of industrial detection in the production environment, it needs to have high robustness, and the multi vision pose detection scheme is recommended.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Krogius, M., Haggenmiller, A., Olson, E.: Flexible layouts for fiducial tags. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2019)
Lee, S., et al.: Vision based localization for multiple mobile robots using low-cost vision sensor. In: 2015 IEEE International Conference on Electro/Information Technology (EIT). IEEE (2015)
Yu, C., Cai, J., Chen, Q.: Multi-resolution visual fiducial and assistant navigation system for unmanned aerial vehicle landing. Aerosp. Technol. 67(aug.), 249–256 (2017)
Peng, J., Xu, W., Yuan, H.: An efficient pose measurement method of a space non-cooperative target based on stereo vision. IEEE Access 5, 22344–22362 (2017)
Zarándy, Á., et al.: A real-time multi-camera vision system for UAV collision warning and navigation. J. Real-Time Image Process. 12(4), 709–724 (2014)
Zhou, B., Chen, Z., Liu, Q.: An efficient solution to the perspective-n-point problem for camera with unknown focal length. IEEE Access PP(99), 1 (2020)
Zhenglong, G., Qiang, F., Quan, Q.: Pose estimation for multicopters based on monocular vision and apriltag. In: 2018 37th Chinese Control Conference (CCC)
Wu, L., Zhu, B.: Binocular stereovision camera calibration. In: IEEE International Conference on Mechatronics & Automation, pp. 2638–2642. IEEE (2015)
Bračun, D., Sluga, A., et al.: Stereo vision based measuring system for online welding path inspection. J. Mater. Process. Technol. 223, 328–336 (2015)
Li, S., Chi, X., Ming, X:. A robust O(n) solution to the perspective-n-point problem. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1444–1450 (2012)
Xia, R., et al.: Global calibration of multi-cameras with non-overlapping field of views based on photogrammetry and reconfigurable target. Meas. Sci. Technol. 29(6), 065005-1–065005-10 (2018)
Shahzad, A., Mu, Y., Gao, X.: Tracking RGB color markers through DLT calibrated monocular vision system. In: IEEE International Conference on Mechatronics & Automation. IEEE (2016)
Zhang, J., Zhu, J., Deng, H., et al.: Multi-camera calibration method based on a multi-plane stereo target. Appl. Opt. 58(34), 9353 (2019)
Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330–1334 (2000)
Yang, Y., et al.: Multi-camera visual SLAM for off-road navigation. Robot. Auton. Syst. 128, 103505 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Geng, X., Cai, C. (2022). 3D Pose Estimation of Manipulator Based on Multi View. In: Pan, Y., Mao, ZH., Luo, L., Zeng, J., Zhang, LJ. (eds) Artificial Intelligence and Mobile Services – AIMS 2021. AIMS 2021. Lecture Notes in Computer Science(), vol 12987. Springer, Cham. https://doi.org/10.1007/978-3-030-96033-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-96033-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96032-2
Online ISBN: 978-3-030-96033-9
eBook Packages: Computer ScienceComputer Science (R0)