A new method for building roof segmentation from airborne LiDAR point cloud data

A new method based on the combination of two kinds of clustering algorithms for building roof segmentation from airborne LiDAR (light detection and ranging) point cloud data is proposed. The K-plane algorithm is introduced to classify the laser footprints that cannot be correctly classified by the traditional K-means algorithm. High-precision classification can be obtained by combining the two aforementioned clustering algorithms. Furthermore, to improve the performance of the new segmentation method, a new initialization method is proposed to acquire the number and coordinates of the initial cluster centers for the K-means algorithm. In the proposed initialization method, the geometrical planes of a building roof are estimated from the elevation image of the building roof by using the mathematical morphology and Hough transform techniques. By calculating the number and normal vectors of the estimated geometrical planes, the number and coordinates of the initial cluster centers for the K-means algorithm are obtained. With the aid of the proposed initialization and segmentation methods, the point cloud of the building roof can be rapidly and appropriately classified. The proposed methods are validated by using both simulated and real LiDAR data.

[1]  Prasanta K. Jana,et al.  Initialization for K-means Clustering using Voronoi Diagram , 2012 .

[2]  M. S. Millán.  Advanced optical correlation and digital methods for pattern matching—50th anniversary of Vander Lugt matched filter , 2012 .

[3]  Robert Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[4]  Hamid Ebadi,et al.  Design and implementation of an algorithm for automatic 3D reconstruction of building models using genetic algorithm , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[5]  Qing Liu,et al.  Adaptive simplification of point cloud using k-means clustering , 2011, Comput. Aided Des..

[6]  Tarig Ali,et al.  A novel computational paradigm for creating a Triangular Irregular Network (TIN) from LiDAR data , 2009 .

[7]  Lakhwinder Singh.  EXTRACTION OF DIFFERENT BUILDINGS FROM LIDAR DATA , 2006 .

[8]  Lijun Xu,et al.  Quantitative Evaluation of Impacts of Random Errors on ALS Accuracy Using Multiple Linear Regression Method , 2012, IEEE Transactions on Instrumentation and Measurement.

[9]  Jia Xu,et al.  Generation method of normal vector from disordered point cloud , 2009, 2009 Joint Urban Remote Sensing Event.

[10]  R. Yager,et al.  Approximate Clustering Via the Mountain Method , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[11]  Wen-June Wang,et al.  Image segmentation with complicated background by using seeded region growing , 2012 .

[12]  Lijun Xu,et al.  Estimation of cluster centers on building roof from LiDAR footprints , 2012, 2012 IEEE International Conference on Imaging Systems and Techniques Proceedings.

[13]  George Miliaresis,et al.  Segmentation and object-based classification for the extraction of the building class from LIDAR DEMs , 2007, Comput. Geosci..

[14]  Min Dai,et al.  Least-squares-based fitting of paraboloids , 2007, Pattern Recognit..

[15]  Samia Boukir,et al.  Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests , 2011 .

[16]  Klaus Tempfli,et al.  AUTOMATIC BUILDING EXTRACTION FROM AIRBORNE LASER SCANNING DATA , 2000 .

[17]  Roberto Manduchi,et al.  CC-RANSAC: Fitting planes in the presence of multiple surfaces in range data , 2011, Pattern Recognit. Lett..

[18]  Jie Shan,et al.  Segmentation and Reconstruction of Polyhedral Building Roofs From Aerial Lidar Point Clouds , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Hanan Samet,et al.  A fast all nearest neighbor algorithm for applications involving large point-clouds , 2007, Comput. Graph..

[20]  Ioannis K. Brilakis,et al.  Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features , 2011, Adv. Eng. Informatics.

[21]  Jie Shan,et al.  Building roof modeling from airborne laser scanning data based on level set approach , 2011 .

[22]  Sarah Smith-Voysey,et al.  Integrating building footprints and LiDAR elevation data to classify roof structures and visualise buildings , 2009, Computers, Environment and Urban Systems.

[23]  Dan Schonfeld,et al.  Theoretical Foundations of Spatially-Variant Mathematical Morphology Part I: Binary Images , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Yang Liu,et al.  Infrared point target detection with improved template matching , 2012 .

[25]  Hsi-Yung Feng,et al.  On the normal vector estimation for point cloud data from smooth surfaces , 2005, Comput. Aided Des..

[26]  Erkki Oja,et al.  Probabilistic and non-probabilistic Hough transforms: overview and comparisons , 1995, Image Vis. Comput..

[27]  Paul S. Bradley,et al.  k-Plane Clustering , 2000, J. Glob. Optim..

[28]  Thambipillai Srikanthan,et al.  Parallelizing the Hough Transform Computation , 2008, IEEE Signal Processing Letters.

[29]  Benoit Rivard,et al.  LIDAR remote sensing for secondary Tropical Dry Forest identification , 2012 .

[30]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .