Abstract
Terrestrial Laser Scanning has been established as a leading tools to collect dense point cloud over object surface. The collected point cloud does not provide semantic information about the scanned object. Therefore, different methods have been developed to deal with this problem, it may be the most effective one to segment point cloud into basic primitives. This paper intrudes a modified method based on RANSAC to identify planar, cylindrical and spherical surfaces in point cloud. The method firstly construct space division by 3D grid, draw a random sample to determine a sub-cell and carry local-RANSAC method to detect multi-primitive models in it, and get the candidate model(s) by local score, then the best model in the candidate modelscan be obtained by statistic inference, and its consensus set determined by distance and normal vector constrains in the global range. Finally the experimental results show that our method can segment man-made objects with regular geometry shape efficiently, and deal with the over and under segmentation properly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Xiong, X.H., Adan, A., Akinci, B., et al.: Automatic creation of semantically rich 3D building models from laser scanner data. Automation in Construction 31, 325–337 (2013)
Rabbani, T.: Automatic Reconstruction of Industrial Installations Using Point Clouds and Images. D. Delft. Delft University of Technology (2006)
Guarnieri, A., Vettore, A., Camarda, M., Domenica, C.: Automatic registration of large range datasets with spin-images. Journal of Cultural Heritage 12(4), 476–484 (2011)
Lari, Z., Ayman, H.: An adaptive approach for the segmentation and extraction of planar and linear/cylindrical features from laser scanning data. ISPRS Journal of Photogrammetry and Remote Sensing 93, 192–212 (2014)
Jiang, J.J., Zhang, Z.X., Ming, Y.: Data Segmentation for Geometric Feature Extraction from Lidar Point Clouds. In: IEEE IGRSS 2005, pp. 3277–3280 (2005)
Liu, Y., Xiong, Y.L.: Automatic Segmentation of Unorganized Noisy Point Clouds Based on the Gaussian Map. Computer-Aided Design 40, 576–594 (2008)
Shahar, B., Sagi, F.: Segmentation of Terrestrial Laser Scanning Data Using Geometry and Image Information. ISPRS Journal of Photogrammetry and Remote Sensing (2012)
Sapkota, P.P.: Segmentation of Coloured Point Cloud Data. Enschede, The Netherlands:International Institute for Geo-Information Science and Earth Observation (2008)
Belton, D.: Classification and Segmentation of 3D Terrestrial Laser Scanner Point Clouds. Bentley, Curtin University of Technology (2008)
Han, S.H., Lee, J.H., Yu, K.Y.: An Approach for Segmentation of Airborne Laser Point Clouds Utilizing Scan-line Characteristics. ETRI Journal 29(5), 642–648 (2007)
Xiao, C.X., Feng, J.Q., Miao, Y.W., et al.: Geodesic Path Computation and Region Decomposition of Point-Based Surface Based on Level Set Method. Chinese Journal of Computers 28(2), 250–258 (2005)
Yamazaki, I., Natarajan, V., Bai, Z.J., Hamann, B.: Segmenting Point Sets. In: Proc. IEEE Intl. Conf. Shape Modeling and Applications (SMI), vol. 6, pp. 4–13 (2006)
Iiiingworth, J., Kittler, J.: A Survey of the Hough Transform. Computer Vision,Graphics,and Image Processing 44(1), 87–116 (1988)
Bolles, R.C., Fischler, M.A.: A RANSAC-BASED Approach to Model Fitting and Its Application to Finding Cylinders in Range Data. In: Proceedings of the 7th International Joint Conference on Artificial Intelligence, pp. 637–643 (1981)
Chaperon, T., Goulette, F.: Extracting Cylinders in Full 3-d Data Using a Random Sampling Method and The Gaussian Image. In: VMV 2001, pp. 35–42 (2001)
Wang, Z., Li, H.Y., Wu, L.X., He, Z.X.: Building Outline Extraction from Airborne LiDAR Data Based on RANSAC Model. Journal of Northeastern University (Natural Science) 33(2), 271–275 (2009)
Huangfu, Z.M., Yan, L.H., Liu, X.M.: Parameters Extraction of Rotational Surface Based on RANSAC Algorithm. Computer Engineer and Design 30(5), 1295–1298 (2009)
Tarek, M.A.: Planar Surface Extraction for Complex Facades from Unstructured TLS Point Clouds. Wuhan University, Wuhan(2010)
Fischler, M.A., Bolles, R.C.: Random Sample Consensus:A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Comm. of the ACM 24, 381–395 (1981)
Myatt, D.R., Torr, P.H.S., Nasuto, S.J., Bishop, J.M., Craddock, R.: Napsac:High Noise,High Dimensional robust Estimation-it’s in the bag. In: BMVC 2002, pp. 458–467 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Y., Shi, H. (2015). A Segmentation Method for Point Cloud Based on Local Sample and Statistic Inference. In: Bian, F., Xie, Y. (eds) Geo-Informatics in Resource Management and Sustainable Ecosystem. GRMSE 2014. Communications in Computer and Information Science, vol 482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45737-5_28
Download citation
DOI: https://doi.org/10.1007/978-3-662-45737-5_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45736-8
Online ISBN: 978-3-662-45737-5
eBook Packages: Computer ScienceComputer Science (R0)