IMPROVING 3D LIDAR POINT CLOUD REGISTRATION USING OPTIMAL NEIGHBORHOOD KNOWLEDGE

Abstract. Automatic 3D point cloud registration is a main issue in computer vision and photogrammetry. The most commonly adopted solution is the well-known ICP (Iterative Closest Point) algorithm. This standard approach performs a fine registration of two overlapping point clouds by iteratively estimating the transformation parameters, and assuming that good a priori alignment is provided. A large body of literature has proposed many variations of this algorithm in order to improve each step of the process. The aim of this paper is to demonstrate how the knowledge of the optimal neighborhood of each 3D point can improve the speed and the accuracy of each of these steps. We will first present the geometrical features that are the basis of this work. These low-level attributes describe the shape of the neighborhood of each 3D point, computed by combining the eigenvalues of the local structure tensor. Furthermore, they allow to retrieve the optimal size for analyzing the neighborhood as well as the privileged local dimension (linear, planar, or volumetric). Besides, several variations of each step of the ICP process are proposed and analyzed by introducing these features. These variations are then compared on real datasets, as well with the original algorithm in order to retrieve the most efficient algorithm for the whole process. Finally, the method is successfully applied to various 3D lidar point clouds both from airborne, terrestrial and mobile mapping systems.

[1]  George Vosselman,et al.  An integrated approach for modelling and global registration of point clouds , 2007 .

[2]  Marc Rioux,et al.  Three-dimensional registration using range and intensity information , 1994, Other Conferences.

[3]  Robert B. Fisher,et al.  Special Issue on Registration and Fusion of Range Images , 2002, Comput. Vis. Image Underst..

[4]  Marc Levoy,et al.  Zippered polygon meshes from range images , 1994, SIGGRAPH.

[5]  J. Demantké,et al.  DIMENSIONALITY BASED SCALE SELECTION IN 3D LIDAR POINT CLOUDS , 2012 .

[6]  Kari Pulli,et al.  Multiview registration for large data sets , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[7]  Dimitri Lague,et al.  3D Terrestrial LiDAR data classification of complex natural scenes using a multi-scale dimensionality criterion: applications in geomorphology , 2011, ArXiv.

[8]  David Fofi,et al.  A review of recent range image registration methods with accuracy evaluation , 2007, Image Vis. Comput..

[9]  Katsuhiko Sakaue,et al.  Registration and integration of multiple range images for 3-D model construction , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[10]  Derek D. Lichti,et al.  A method for automated registration of unorganised point clouds , 2008 .

[11]  Boris Jutzi,et al.  Segmentation of tree regions using data of a full-waveform laser , 2007 .

[12]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[13]  Hermann Gross,et al.  EXTRACTION OF LINES FROM LASER POINT CLOUDS , 2006 .

[14]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[16]  B. Jutzi,et al.  NEAREST NEIGHBOUR CLASSIFICATION ON LASER POINT CLOUDS TO GAIN OBJECT STRUCTURES FROM BUILDINGS , 2009 .

[17]  Sang Wook Lee,et al.  ICP Registration Using Invariant Features , 2002, IEEE Trans. Pattern Anal. Mach. Intell..