PAIRWISE LINKAGE FOR POINT CLOUD SEGMENTATION

Abstract. In this paper, we first present a novel hierarchical clustering algorithm named Pairwise Linkage (P-Linkage), which can be used for clustering any dimensional data, and then effectively apply it on 3D unstructured point cloud segmentation. The P-Linkage clustering algorithm first calculates a feature value for each data point, for example, the density for 2D data points and the flatness for 3D point clouds. Then for each data point a pairwise linkage is created between itself and its closest neighboring point with a greater feature value than its own. The initial clusters can further be discovered by searching along the linkages in a simple way. After that, a cluster merging procedure is applied to obtain the finally refined clustering result, which can be designed for specialized applications. Based on the P-Linkage clustering, we develop an efficient segmentation algorithm for 3D unstructured point clouds, in which the flatness of the estimated surface of a 3D point is used as its feature value. For each initial cluster a slice is created, then a novel and robust slicemerging method is proposed to get the final segmentation result. The proposed P-Linkage clustering and 3D point cloud segmentation algorithms require only one input parameter in advance. Experimental results on different dimensional synthetic data from 2D to 4D sufficiently demonstrate the efficiency and robustness of the proposed P-Linkage clustering algorithm and a large amount of experimental results on the Vehicle-Mounted, Aerial and Stationary Laser Scanner point clouds illustrate the robustness and efficiency of our proposed 3D point cloud segmentation algorithm.

[1]  Joseph O'Rourke,et al.  Handbook of Discrete and Computational Geometry, Second Edition , 1997 .

[2]  Hamid R. Arabnia,et al.  Parallel Edge-Region-Based Segmentation Algorithm Targeted at Reconfigurable MultiRing Network , 2003, The Journal of Supercomputing.

[3]  Michel Devy,et al.  Fast range image segmentation by an edge detection strategy , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[4]  Jiawei Han,et al.  Efficient and Effective Clustering Methods for Spatial Data Mining , 1994, VLDB.

[5]  Sunil Arya,et al.  An optimal algorithm for approximate nearest neighbor searching fixed dimensions , 1998, JACM.

[6]  Gert Vegter,et al.  In handbook of discrete and computational geometry , 1997 .

[7]  Hans-Peter Seidel,et al.  Feature sensitive mesh segmentation with mean shift , 2005, International Conference on Shape Modeling and Applications 2005 (SMI' 05).

[8]  Junhao Xiao,et al.  Three-dimensional point cloud plane segmentation in both structured and unstructured environments , 2013, Robotics Auton. Syst..

[9]  R. Reulke,et al.  Remote Sensing and Spatial Information Sciences , 2005 .

[10]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Jian Liang,et al.  Point Cloud Segmentation and Denoising via Constrained Nonlinear Least Squares Normal Estimates , 2013, Innovations for Shape Analysis, Models and Algorithms.

[12]  Atilla Baskurt,et al.  A new CAD mesh segmentation method, based on curvature tensor analysis , 2005, Comput. Aided Des..

[13]  Roland Siegwart,et al.  FAST RANGE IMAGE SEGMENTATION FOR INDOOR 3D-SLAM , 2007 .

[14]  Robin Sibson,et al.  SLINK: An Optimally Efficient Algorithm for the Single-Link Cluster Method , 1973, Comput. J..

[15]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[16]  Tamás Várady,et al.  Segmentation methods for smooth point regions of conventional engineering objects , 2004, Comput. Aided Des..

[17]  Abdul Nurunnabi,et al.  Outlier detection and robust normal-curvature estimation in mobile laser scanning 3D point cloud data , 2015, Pattern Recognit..

[18]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[19]  Hans-Peter Seidel,et al.  Mesh segmentation driven by Gaussian curvature , 2005, The Visual Computer.

[20]  Luc Van Gool,et al.  Efficient Non-Maximum Suppression , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[21]  Kenji Shimada,et al.  Surface mesh segmentation and smooth surface extraction through region growing , 2005, Comput. Aided Geom. Des..

[22]  D. Lichti,et al.  CLASSIFICATION AND SEGMENTATION OF TERRESTRIAL LASER SCANNER POINT CLOUDS USING LOCAL VARIANCE INFORMATION , 2006 .

[23]  Yu Liu,et al.  Automatic segmentation of unorganized noisy point clouds based on the Gaussian map , 2008, Comput. Aided Des..

[24]  Sunil Arya,et al.  ANN: library for approximate nearest neighbor searching , 1998 .

[25]  George Vosselman,et al.  Segmentation of point clouds using smoothness constraints , 2006 .

[26]  T. Rabbani,et al.  SEGMENTATION OF POINT CLOUDS USING SMOOTHNESS CONSTRAINT , 2006 .

[27]  Martin Buss,et al.  Comparison of surface normal estimation methods for range sensing applications , 2009, 2009 IEEE International Conference on Robotics and Automation.

[28]  Semyung Wang,et al.  A new segmentation method for point cloud data , 2002 .

[29]  Eric L. Miller,et al.  Three-Dimensional Surface Mesh Segmentation Using Curvedness-Based Region Growing Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Xi Zhang,et al.  3D Mesh Segmentation Using Mean-Shifted Curvature , 2008, GMP.

[31]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  J. MacQueen Some methods for classification and analysis of multivariate observations , 1967 .