Validation of Point Cloud Data for 3D Plane Detection

Part of the Studies in Computational Intelligence book series (SCI, volume 559)


There are number of plane detection techniques for a given 3D point cloud utilized in different applications. All of the methods measure planes quality by computing sum of square error for a fitted plane model but no one of techniques may count the number of planes in the point cloud. In this chapter we present new strategy for validating number of found planes in the 3D:point cloud by applied cluster validity indices. For a planes finding in point cloud we have engaged the RANdom SAmple Consensus (RANSAC) method to synthetic and real scanned data. The experimental results have shown that the cluster validity indices may help in tuning RANSAC parameters as well as in determination the number of planes in 3D data.



This research is funded by the European Social Fund under the project “Microsensors, microactuators and controllers for mechatronic systems (Go-Smart)” (Agreement No VP1-3.1-ŠMM-08-K-01-015).


  1. Ansari Z, Azeem MF, Ahmed W, Babu AV (2011) Quantitative evaluation of performance and validity indices for clustering the web navigational sessions. World Comput Sci Inf Technol J 1:217–226Google Scholar
  2. Davies DL, Bouldin DW (1979) A cluster separation measure. Pattern Anal Mach Intell 1:224–227Google Scholar
  3. Dunn JC (1974) Well separated clusters and optimal fuzzy partitions. J Cybern 4(1):95–104CrossRefMathSciNetGoogle Scholar
  4. Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395CrossRefMathSciNetGoogle Scholar
  5. Gokturk SB, Yalcin H, Bamji C (2004) A time-of-flight depth sensor—system description, issues and solutions. In: Proceedings of computer vision and pattern recognition workshop, p 35Google Scholar
  6. Halkidi M, Batistakis Y, Vazirgiannis M (2001) On clustering validation techniques. J Intell Inf Syst 17:107–145CrossRefMATHGoogle Scholar
  7. Huang H, Brenner C (2011) Rule-based roof plane detection and segmentation from laser point clouds. In: Proceedings of urban remote sensing event, pp 293–296Google Scholar
  8. Junhao X, Jianhua Z, Jianwei Z, Houxiang Z, Hildre H. P (2011) Fast plane detection for SLAM from noisy range images in both structured and unstructured environments. In: Proceedings of international conference on mechatronics and automation, pp 1768–1773Google Scholar
  9. Kaufman L, Rousseeuw PJ (1990) Finding groups in data: an introduction to cluster analysis. Wiley, HobokenCrossRefGoogle Scholar
  10. Microsoft, Microsoft Kinect. Accessed 28 Jan 2013
  11. Milligan WG (1996) Clustering validation: results and implications for applied analyses. Clustering Classif 1:341–375CrossRefGoogle Scholar
  12. Pathak K, Birk A, Vaskevicius N, Poppinga J (2010a) Fast registration based on noisy planes with unknown correspondences for 3D mapping. IEEE Trans Rob 26(3):424–441CrossRefGoogle Scholar
  13. Pathak K, Birk A, Vaskevicius N, Pfingsthorn M, Schwertfeger S, Poppinga J (2010) Online 3D SLAM by registration of large planar surface segments and closed form pose-graph relaxation. J Field Rob 27:52–84 (Special Issue on 3D Mapping)Google Scholar
  14. Rousseew PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65CrossRefGoogle Scholar
  15. Schnabel R, Wahl R, Klein R (2007) Efficient RANSAC for point-cloud shape detection. Comput Graph Forum 26:214–226CrossRefGoogle Scholar
  16. Tarsha-Kurdi F, Landes T, Grussenmeyer P (2008) Hough-transform and extended ransac algorithms for automatic detection of 3d building roof planes from lidar data. Photogram J Finland 21(1):97–109Google Scholar
  17. Turk G, Levoy M (1994) Stanford University. Accessed 29 Jan 2013
  18. Vosselman G (2009) Advanced point cloud processing. Photogrammetric Week, StuttgartGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.The Mechatronics Centre for Studies, Information and ResearchKaunasLithuania
  2. 2.Department of Control TechnologiesKaunas University of TechnologyKaunasLithuania

Personalised recommendations