Evaluation of 3D registration reliability and speed - A comparison of ICP and NDT

By Martin Magnusson, Andreas Nüchter, C. Lörken, Achim J. Lilienthal, Joachim Hertzberg. 2009

225 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

The three-dimensional normal-distributions transform : an efficient representation for registration, surface analysis, and loop detection (2009, methodology): “In our previous publication on this comparison [69], we also counted the number of failed registrations in a larger data set, with initial poses from odometry.”
Voxelized GICP for Fast and Accurate 3D Point Cloud Registration (2020, methodology): “, multi-resolution [9] and trilinear voxel smoothing [3]).”
Robust localization using 3D NDT scan matching with experimentally determined uncertainty and road marker matching (2017, background): “It is reported that the error of NDT when scan matching fails is larger than that of ICP scan matching [12].”
Computing Systems for Autonomous Driving: State of the Art and Challenges (2020, background): “ICP iteratively selects the closest point to calculate the best match.”
Autonomous driving based on accurate localization using multilayer LiDAR and dead reckoning (2017, background): “It has been reported that the computational cost and robustness of NDT are superior to those of point-to-point based ICP scan matching [12].”
A portable three-dimensional LIDAR-based system for long-term and wide-area people behavior measurement (2019, methodology): “For 3-D LIDARs, NDT shows a better performance than other scan matching algorithms, such as iterative closest points,(35) in terms of both the reliability and the processing speed.(36) Let pt be the sensor pose at t, consisting of a translation vector t and a quaternion q, and rt;tþ1 be the relative”
FAST-LIO2: Fast Direct LiDAR-Inertial Odometry (2021, unknown): “Other works based on Normal Distribution Transformation (NDT) [34]– [36] also register raw points, but NDT has lower stability compared to ICP and may diverge in some scenes [36].”