Abstract
This paper compares implementation of multiple view approach of pose estimation on an eye-in-hand robotic system. By combining RGB-D frames from multiple view with the eye-in-hand robotic system, geometry information of target objects can be best recovered thus pose estimation performance can get improved. Two primary approaches for pose estimation, namely 3D point cloud registration and 2D image matching are implemented and compared. For the 3D method, we reconstruct target objects by taking advantage of the eye-in-hand system to get an accurate representation of target objects. For the 2D method, we discuss distance metrics and regression for 6DOF pose and apply RANSAC with it to fuse multiple estimation results. State-of-the-art pose estimation algorithms which cover both the 3D and 2D approaches are implemented and compared. Experiments show that the multiple view approach can provide more accurate and reliable pose estimation results when compared with conventional single view approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lehnert, C., Sa, I., McCool, C., Upcroft, B., Perez, T.: Sweet pepper pose detection and grasping for automated crop harvesting. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 2428–2434. IEEE (2016)
Zeng, A., Yu, K.T., Song, S., Suo, D., Walker Jr., E., Rodriguez, A., Xiao, J.: Multi-view self-supervised deep learning for 6D pose estimation in the Amazon picking challenge. arXiv preprint arXiv:1609.09475 (2016)
Duncan, K., Sarkar, S., Alqasemi, R., Dubey, R.: Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects. In: 2013 IEEE International Conference on Robotics and Automation (ICRA), pp. 4238–4243. IEEE (2013)
Besl, P.J., McKay, N.D.: Method for registration of 3-D shapes. In: Robotics-DL Tentative, pp. 586–606. International Society for Optics and Photonics (1992)
Drost, B., Ulrich, M., Navab, N., Ilic, S.: Model globally, match locally: efficient and robust 3D object recognition. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 998–1005. IEEE (2010)
Choi, C., Taguchi, Y., Tuzel, O., Liu, M.Y., Ramalingam, S.: Voting-based pose estimation for robotic assembly using a 3D sensor. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 1724–1731. IEEE (2012)
Choi, C., Christensen, H.I.: RGB-D object pose estimation in unstructured environments. Robot. Autonom. Syst. 75, 595–613 (2016)
Collet, A., Berenson, D., Srinivasa, S.S., Ferguson, D.: Object recognition and full pose registration from a single image for robotic manipulation. In: 2009 IEEE International Conference on Robotics and Automation (ICRA), pp. 48–55. IEEE (2009)
Liu, M.Y., Tuzel, O., Veeraraghavan, A., Taguchi, Y., Marks, T.K., Chellappa, R.: Fast object localization and pose estimation in heavy clutter for robotic bin picking. Int. J. Robot. Res. 31(8), 951–973 (2012)
Hinterstoisser, S., Cagniart, C., Ilic, S., Sturm, P., Navab, N., Fua, P., Lepetit, V.: Gradient response maps for real-time detection of textureless objects. IEEE Trans. Pattern Anal. Mach. Intell. 34(5), 876–888 (2012)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Endres, F., Hess, J., Engelhard, N., Sturm, J., Cremers, D., Burgard, W.: An evaluation of the RGB-D slam system. In: 2012 IEEE International Conference on Robotics and Automation (ICRA), pp. 1691–1696. IEEE (2012)
Wang, Y., Chirikjian, G.S.: Nonparametric second-order theory of error propagation on motion groups. Int. J. Robot. Res. 27(11–12), 1258–1273 (2008)
Acknowledgements
This research was supported in part by National Natural Science Foundation of China under Grant 51675325 and National Science and Technology Support Program under Grant 2015BAF01B02.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Li, K., Zhuang, C., Wu, J., Xiong, Z. (2017). Implementation of Multiple View Approach for Pose Estimation with an Eye-In-Hand Robotic System. In: Huang, Y., Wu, H., Liu, H., Yin, Z. (eds) Intelligent Robotics and Applications. ICIRA 2017. Lecture Notes in Computer Science(), vol 10463. Springer, Cham. https://doi.org/10.1007/978-3-319-65292-4_52
Download citation
DOI: https://doi.org/10.1007/978-3-319-65292-4_52
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65291-7
Online ISBN: 978-3-319-65292-4
eBook Packages: Computer ScienceComputer Science (R0)