Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes

Abstract Laser scanner is a powerful tool which helps in the control of as-built construction projects. The automatic registration of the acquired point clouds without the use of artificial targets is a relevant subject in current investigation. This work focuses on extracting descriptive keypoints from geometric point descriptors, in such a way that keypoints are suitable to perform 4 Points Congruent Sets coarse registration without artificial targets. These keypoints are obtained via 3D Difference of Gaussians over geometric scalar values of the points resulting in characteristic salient features. The registration procedure reduced the RMSE around 2 cm during coarse registration comparing against state of the art algorithms. These RMSE values allow the subsequence use of fine registration via ICP completing the automation of the registration process. Geometric keypoints are demonstrated to be a suitable way to obtain automatic point cloud registration and open the way to future developments.

[1]  Burcu Akinci,et al.  Automated processing of construction specifications to support inspection and quality control , 2007 .

[2]  Higinio González-Jorge,et al.  Evaluation of point cloud registration using Monte Carlo method , 2016 .

[3]  Hangbin Wu,et al.  Feature-constrained registration of building point clouds acquired by terrestrial and airborne laser scanners , 2014 .

[4]  Benjamin Wilkinson,et al.  Direct Georeferencing of Stationary LiDAR , 2009, Remote. Sens..

[5]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[6]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[7]  Radu Bogdan Rusu,et al.  3D is here: Point Cloud Library (PCL) , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[9]  Konrad Schindler,et al.  Keypoint-based 4-Points Congruent Sets – Automated marker-less registration of laser scans , 2014 .

[10]  Nico Blodow,et al.  Aligning point cloud views using persistent feature histograms , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Claus Brenner,et al.  Registration of terrestrial laser scanning data using planar patches and image data , 2006 .

[12]  Marc Pollefeys,et al.  Automatic Registration of RGB-D Scans via Salient Directions , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  Jens-André Paffenholz.  Direct geo-referencing of 3D point clouds with 3D positioning sensors , 2012 .

[14]  Michael Greenspan,et al.  Super Generalized 4PCS for 3D Registration , 2015, 2015 International Conference on 3D Vision.

[15]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  P. Arias,et al.  3D reconstruction of cubic armoured rubble mound breakwaters from incomplete lidar data , 2015 .

[17]  Niloy J. Mitra,et al.  Super4PCS: Fast Global Pointcloud Registration via Smart Indexing , 2019 .

[18]  Geraldine S. Cheok,et al.  Fast automatic registration of range images from 3D imaging systems using sphere targets , 2009 .

[19]  Bobby Bodenheimer,et al.  Synthesis and evaluation of linear motion transitions , 2008, TOGS.

[20]  J. Demantké,et al.  DIMENSIONALITY BASED SCALE SELECTION IN 3D LIDAR POINT CLOUDS , 2012 .

[21]  Stefan Hinz,et al.  CONTEXTUAL CLASSIFICATION OF POINT CLOUD DATA BY EXPLOITING INDIVIDUAL 3D NEIGBOURHOODS , 2015 .

[22]  Vladimir Pekar,et al.  Full orientation invariance and improved feature selectivity of 3D SIFT with application to medical image analysis , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[23]  Burcu Akinci,et al.  A formalism for utilization of sensor systems and integrated project models for active construction quality control , 2006 .

[24]  M. Devrim Mehmet Devrim Akça.  FULL AUTOMATIC REGISTRATION OF LASER SCANNER POINT CLOUDS , 2003 .

[25]  R. Navon,et al.  Research in automated measurement of project performance indicators , 2007 .

[26]  George Vosselman.  Design of an indoor mapping system using three 2D laser scanners and 6 DOF SLAM , 2014 .

[27]  Sagi Filin,et al.  REGISTRATION OF TERRESTRIAL LASER SCANS VIA IMAGE BASED FEATURES , 2007 .

[28]  N. Mitra,et al.  4-points congruent sets for robust pairwise surface registration , 2008, SIGGRAPH 2008.

[29]  Nicolas David,et al.  Towards 3D lidar point cloud registration improvement using optimal neighborhood knowledge , 2013 .

[30]  Konrad Schindler,et al.  AUTOMATIC REGISTRATION OF TERRESTRIAL LASER SCANNER POINT CLOUDS USING NATURAL PLANAR SURFACES , 2012 .

[31]  Pedro Arias,et al.  Terrestrial laser scanning for geometry extraction and change monitoring of rubble mound breakwaters , 2014 .

[32]  Konrad Schindler,et al.  Fast registration of laser scans with 4-point congruent sets - what works and what doesn't , 2014 .

[33]  Jiaolong Yang,et al.  Go-ICP: Solving 3D Registration Efficiently and Globally Optimally , 2013, 2013 IEEE International Conference on Computer Vision.

[34]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[35]  Steffen Urban,et al.  FINDING A GOOD FEATURE DETECTOR-DESCRIPTOR COMBINATION FOR THE 2D KEYPOINT-BASED REGISTRATION OF TLS POINT CLOUDS , 2015 .

[36]  Diego González-Aguilera,et al.  Metrological comparison of terrestrial laser scanning systems Riegl LMS Z390i and Trimble GX , 2011 .

[37]  Konrad Schindler,et al.  Markerless point cloud registration with keypoint-based 4-points congruent sets , 2013 .

[38]  Derek D. Lichti,et al.  A method for automated registration of unorganised point clouds , 2008 .

[39]  Yuriy Reshetyuk,et al.  Self-calibration and direct georeferencing in terrestrial laser scanning , 2009 .

[40]  Stefan Hinz,et al.  Fast and automatic image-based registration of TLS data , 2011 .

[41]  Radu Bogdan Rusu,et al.  Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments , 2010, KI - Künstliche Intelligenz.

[42]  Leonidas J. Guibas,et al.  Robust global registration , 2005, SGP '05.

[43]  Frédéric Bosché,et al.  As-built data acquisition and its use for production monitoring and automated layout in civil infrastructure: a survey , 2015 .

[44]  Ghassan Hamarneh,et al.  A Survey on Shape Correspondence , 2011, Comput. Graph. Forum.

[45]  Charles M. Eastman,et al.  BIM Handbook: A Guide to Building Information Modeling for Owners, Managers, Designers, Engineers and Contractors , 2008 .

[46]  Steffen Urban,et al.  Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas , 2015, Comput. Graph..

[47]  Henrique Lorenzo,et al.  DETECTION OF GEOMETRIC KEYPOINTS AND ITS APPLICATION TO POINT CLOUD COARSE REGISTRATION , 2016 .

[48]  Federico Tombari,et al.  SHOT: Unique signatures of histograms for surface and texture description , 2014, Comput. Vis. Image Underst..

[49]  Zhengyou Zhang,et al.  Iterative point matching for registration of free-form curves and surfaces , 1994, International Journal of Computer Vision.

[50]  Gary K. L. Tam,et al.  Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid , 2013, IEEE Transactions on Visualization and Computer Graphics.

[51]  Boris Jutzi,et al.  Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features , 2014 .

[52]  G. Impoco,et al.  RoboScan: an automatic system for accurate and unattended 3D scanning , 2004 .

[53]  Michael Greenspan,et al.  Generalized 4-Points Congruent Sets for 3D Registration , 2014, 2014 2nd International Conference on 3D Vision.

[54]  Gongjun Yan,et al.  Security challenges in vehicular cloud computing , 2013, IEEE Transactions on Intelligent Transportation Systems.

[55]  Igor Guskov,et al.  Multi-scale features for approximate alignment of point-based surfaces , 2005, SGP '05.