NICP: Dense normal based point cloud registration
- 1 September 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In this paper we present a novel on-line method to recursively align point clouds. By considering each point together with the local features of the surface (normal and curvature), our method takes advantage of the 3D structure around the points for the determination of the data association between two clouds. The algorithm relies on a least squares formulation of the alignment problem, that minimizes an error metric depending on these surface characteristics. We named the approach Normal Iterative Closest Point (NICP in short). Extensive experiments on publicly available benchmark data show that NICP outperforms other state-of-the-art approaches.Keywords
This publication has 15 references indexed in Scilit:
- Iterative Most-Likely Point Registration (IMLP): A Robust Algorithm for Computing Optimal Shape AlignmentPLOS ONE, 2015
- Using Augmented Measurements to Improve the Convergence of ICPLecture Notes in Computer Science, 2014
- Comparing ICP variants on real-world data setsAutonomous Robots, 2013
- Challenging data sets for point cloud registration algorithmsThe International Journal of Robotics Research, 2012
- Generalized-ICPPublished by Robotics: Science and Systems Foundation ,2009
- Scan registration for autonomous mining vehicles using 3D‐NDTJournal of Field Robotics, 2007
- Efficient simplification of point-sampled surfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Object modeling by registration of multiple range imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Closed-form solution of absolute orientation using orthonormal matricesJournal of the Optical Society of America A, 1988