PrimiTect: Fast Continuous Hough Voting for Primitive Detection

This paper tackles the problem of data abstraction in the context of 3D point sets. Our method classifies points into different geometric primitives, such as planes and cones, leading to a compact representation of the data. Being based on a semi-global Hough voting scheme, the method does not need initialization and is robust, accurate, and efficient. We use a local, low-dimensional parameterization of primitives to determine type, shape and pose of the object that a point belongs to. This makes our algorithm suitable to run on devices with low computational power, as often required in robotics applications. The evaluation shows that our method outperforms state-of-the-art methods both in terms of accuracy and robustness.

[1]  K. Lingemann,et al.  The 3D Hough Transform for plane detection in point clouds: A review and a new accumulator design , 2011 .

[2]  Nassir Navab,et al.  A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Dan Wang,et al.  Range image segmentation based on randomized Hough transform , 2005, Pattern Recognit. Lett..

[4]  Luiz Velho,et al.  Hough Transform for real-time plane detection in depth images , 2018, Pattern Recognit. Lett..

[5]  Dragutin Petkovic,et al.  On improving the accuracy of the Hough transform , 2005, Machine Vision and Applications.

[6]  Leonidas J. Guibas,et al.  Supervised Fitting of Geometric Primitives to 3D Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Mark S. Nixon,et al.  Sphere Detection in Kinect Point Clouds via the 3D Hough Transform , 2013, CAIP.

[8]  Zhen Li,et al.  Primitive Fitting Based on the Efficient multiBaySAC Algorithm , 2015, PloS one.

[9]  Dietrich Paulus,et al.  Implicit Shape Models for 3D Shape Classification with a Continuous Voting Space , 2015, VISAPP.

[10]  Daniel Cohen-Or,et al.  GlobFit: consistently fitting primitives by discovering global relations , 2011, ACM Trans. Graph..

[11]  Vladlen Koltun,et al.  A Large Dataset of Object Scans , 2016, ArXiv.

[12]  R. Lakaemper,et al.  RMSD: A 3D real-time mid-level scene description system , 2013, 2013 IEEE Workshop on Robot Vision (WORV).

[13]  Alfred M. Bruckstein,et al.  Antialiasing the Hough transform , 1991, CVGIP Graph. Model. Image Process..

[14]  Sung Joon Ahn,et al.  Extraction of Geometric Primitives from Point Cloud Data , 2005 .

[15]  Eric Brachmann,et al.  BOP: Benchmark for 6D Object Pose Estimation , 2018, ECCV.

[16]  T. Rabbani,et al.  EFFICIENT HOUGH TRANSFORM FOR AUTOMATIC DETECTION OF CYLINDERS IN POINT CLOUDS , 2005 .

[17]  Manuel Menezes de Oliveira Neto,et al.  Real-time line detection through an improved Hough transform voting scheme , 2008, Pattern Recognit..

[18]  Subhransu Maji,et al.  CSGNet: Neural Shape Parser for Constructive Solid Geometry , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Manuel Menezes de Oliveira Neto,et al.  Real-time detection of planar regions in unorganized point clouds , 2015, Pattern Recognit..

[20]  Ming Zhang.  On the discretization of parameter domain in Hough transformation , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[21]  Nassir Navab,et al.  Model globally, match locally: Efficient and robust 3D object recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Andrew W. Fitzgibbon,et al.  An Experimental Comparison of Range Image Segmentation Algorithms , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Slobodan Ilic,et al.  Local Hough Transform for 3D Primitive Detection , 2015, 2015 International Conference on 3D Vision.

[24]  F. Tarsha-Kurdi,et al.  Hough-Transform and Extended RANSAC Algorithms for Automatic Detection of 3D Building Roof Planes from Lidar Data , 2007 .

[25]  Jinbo Bi,et al.  Regression Error Characteristic Curves , 2003, ICML.

[26]  J. Bethel,et al.  DETECTION AND ROBUST ESTIMATION OF CYLINDER FEATURES IN POINT CLOUDS , 2010 .

[27]  Alexandre Bernardino,et al.  Robust cylinder detection and pose estimation using 3D point cloud information , 2017, 2017 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC).

[28]  Tamy Boubekeur,et al.  A Survey of Simple Geometric Primitives Detection Methods for Captured 3D Data , 2018, Comput. Graph. Forum.

[29]  Denis Laurendeau,et al.  Extraction of Reliable Primitives from Unorganized Point Clouds , 2015 .

[30]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.