Table of Contents

Registration Evaluations

Interested researchers should first start their readings with the following paper:

F. Pomerleau, F. Colas, R. Siegwart, and S. Magnenat, Comparing ICP variants on real-world data sets, Autonomous Robots, Volume 34, Issue 3, pp 133-148, Feb. 2013. Publisher Link, bibtex

The page aim at sharing registration algorithm results and configurations to ease and accelerate comparison. The targeted application is scene reconstruction which has implication in Simultaneous Localization and Mapping.

The Evaluation Protocol is fixed for every registration variant.

Solution Descriptions

Solution Name Parameters Implementation Tested on Multi-threaded
chen91 [1] [2] Besl92_pt2point.yaml C++ (libpointmatcher) 2.2 GHz Intel Core i7 No
besl92 [3] [2] Chen91_pt2plane.yaml C++ (libpointmatcher) 2.2 GHz Intel Core i7 No
p2d-ndt [4] [5] N/A C++ (ndt_registration) 3.5 GHz Intel Core i7 No
d2d-ndt [6] [5] N/A C++ (ndt_registration) 3.5 GHz Intel Core i7 No

Download Results

Solution Name Environments
ETH Apartment Stairs Wood Gazebo Plain
chen91 .csv .csv .csv .csv .csv .csv
besl92 .csv .csv .csv .csv .csv .csv
p2d-ndt .csv .csv .csv .csv .csv .csv
d2d-ndt .csv .csv .csv .csv .csv .csv

—-

[1] Y Chen and G Medioni, 1991. Object modeling by registration of multiple range images. Robotics and Automation. Proc. of IEEE International Conf. on, 3, pp. 2724 - 2729.
[2] Chetverikov, D and Svirko, D and Stepanov, D and Krsek, P, 2002. The Trimmed Iterative Closest Point algorithm. Pattern Recognition, 2002. Proceedings. 16th International Conference on, 3, pp. 2724 - 2729.
[3] P Besl and H McKay, 1992. A method for registration of 3-D shapes. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 14, pp. 239 - 256.
[4] Magnusson, Martin and Duckett, Tom and Lilienthal, Achim J., 2007. Scan Registration for Autonomous Mining Vehicles Using 3D-NDT. Journal of Field Robotics, 24, pp. 803 - 827.
[5] Martin Magnusson and Narunas Vaskevicius and Todor Stoyanov and Kaustubh Pathak and Andreas Birk, 2015. Beyond Points: Evaluating Recent 3D Scan-Matching Algorithms. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).
[6] Stoyanov, Todor and Magnusson, Martin and Lilienthal, Achim J., 2012. Fast and Accurate Scan Registration through Minimization of the Distance between Compact 3D NDT Representations. The International Journal of Robotics Research, 31, pp. 1377 - 1393.