Segmentation of LiDAR Point Cloud Based on Similarity Measures in Multi-dimension Euclidean Space

Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 141)


The segmentation of LiDAR point cloud is a key but difficult step for 3D reconstruction of architecture. Many researchers have tried to develop segmentation methods including edge-based, surface-based and cluster-based segmentation, etc. In this paper, we present a point data segmentation method based on similarity measures in multi-dimension Euclidean space. The main workflow of this method is made by calculating point normal vector, transforming color values, calculating Euclidean distance and angle in multi-dimension space, comparing the similarity among adjacent points, and segmenting the raw points set at last. The proposed method takes the both advantages of geo-metrical segmentation and color-metrical segmentation as compared with three different segmentation methods. It has been applied to LiDAR point data obtained by TLS (terrain laser scanner), the experiment results show that the segmentation method is promising.


LiDAR Point cloud segmentation Euclidean Space 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fan, T., Medioni, G., Nevatia, R.: Segmented description of 3-D surfaces. IEEE Transactions on Robotics and Automation RA-3(6), 527–538 (1987)Google Scholar
  2. 2.
    Sappa, A.D., Devy, M.: Fast range image segmentation by an edge detection strategy. In: Proceedings of the Third International Conference on 3-D Digital Imaging and Modeling, pp. 292–299. IEEE Computer Soc., Los Alamitos (2001)CrossRefGoogle Scholar
  3. 3.
    Meyer, A., Marin, P.: Segmentation of 3D triangulated data points using edges constructed with a C1 discontinuous surface fitting. Computer-Aided Design 36, 1327–1336 (2004)CrossRefGoogle Scholar
  4. 4.
    Besl, P.J., Jain, R.C.: Segmentation through variable-order surface fitting. IEEE Transactions on Pattern Analysis and Machine Intelligence 10(2), 167–192 (1988)CrossRefGoogle Scholar
  5. 5.
    Pu, S., Vosselman, G.: Automatic extraction of building features from terrestrial laser scanning. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 36(5), 25–27 (2006)Google Scholar
  6. 6.
    Rabbani, T., van den Heuvel, F., Vosselmann, G.: Segmentation of Point Clouds using Smoothness Constraint. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 36(5), 248–253 (2006)Google Scholar
  7. 7.
    Lucieer, A., Stein, A.: Texture-based landform segmentation of LiDAR imagery. International Journal of Applied Earth Observation and Geoinformation 6(2-3), 261–270 (2005)CrossRefGoogle Scholar
  8. 8.
    Zhan, Q., Liang, Y., Xiao, Y.: Color-based segmentation of point clouds. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 248–252 (2009)Google Scholar
  9. 9.
    Hernandez, J., Marcotegui, B.: Point cloud segmentation towards urban ground modeling. In: 2009 Joint Urban Remote Sensing Event, May 20-May 22. IEEE Computer Society, Shanghai (2009)Google Scholar
  10. 10.
    Awrangjeb, M., Ravanbakhsh, M., Fraser, C.S.: Automatic detection of residential buildings using LIDAR data and multispectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing (2010) (in Press)Google Scholar
  11. 11.
    Mitra, N.J., Nguyen, A.: Estimating surface normals in noisy point cloud data. In: Proceedings of the Nineteenth Annual Symposium on Computational Geometry, pp. 322–328. ACM, San Diego (2003)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.School of Urban DesignWuhan University Research Center for Digital City, Wuhan UniversityWuhanChina
  2. 2.State Key Laboratory of Information Engineering in SurveyingMapping and Remote Sensing Wuhan UniversityWuhanChina

Personalised recommendations