Semantic scan planning for indoor structural elements of buildings

The objective of this paper is to propose a new semantic 3D data acquisition method which is focused on sensing data belonging to indoor structural elements of buildings. Our system uses and processes 3D information coming from a 3D laser scanner sensor. The presented approach deals with some essential key issues in the scanning world which are rarely dealt with in papers. These are: the final goal of the scanning process, the hypotheses about the scene, lack of dynamic spaces in the next-best-scan-based solutions and the quality evaluation of the data sensed. Whereas most of the Next Best Scan (NBS) based approaches do not discriminate between data and clutter, we propose a scanning process in which potential structural elements of building indoors are learned as a new scan arrives. Our workspace is not a priori hypothesized, but a dynamic space which is updated as a new scan is added. This allows us to deal with more complex shape scenarios (i.e. concave-shaped spaces). Through the so called Structural Element (SE) membership probability, we introduce the data-quality concept in the scanning process which highly reduces the point cloud to be processed. This system has been tested in inhabited indoors and has yielded promising results. An experimental comparison with three close techniques is presented in an extended and detailed experimental section. The results yielded from our experimental work demonstrate the quality and validity of the proposed method.

[1]  Wolfram Burgard,et al.  Exploring Unknown Environments with Mobile Robots using Coverage Maps , 2003, IJCAI.

[2]  Jan Boehm,et al.  Automated 3D Reconstruction of Interiors from Point Clouds , 2010 .

[3]  Jongmoo Choi,et al.  Convex Cut: A realtime pseudo-structure extraction algorithm for 3D point cloud data , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[5]  Pedro Arias,et al.  3D Modeling of Building Indoor Spaces and Closed Doors from Imagery and Point Clouds , 2015, Sensors.

[6]  Sándor P. Fekete,et al.  Exact solutions and bounds for general art gallery problems , 2010, JEAL.

[7]  Ivan Petrović,et al.  Autonomous Exploration of Large Unknown Indoor Environments for Dense 3D Model Building , 2014 .

[8]  Peter K. Allen,et al.  Data acquisition and view planning for 3-D modeling tasks , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Per Bergström,et al.  Robust registration of point sets using iteratively reweighted least squares , 2014, Computational Optimization and Applications.

[10]  Cid C. de Souza,et al.  The Quest for Optimal Solutions for the Art Gallery Problem: A Practical Iterative Algorithm , 2013, SEA.

[11]  Luis Enrique Sucar,et al.  Probabilistic view planner for 3D modelling indoor environments , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Nico Blodow,et al.  Autonomous semantic mapping for robots performing everyday manipulation tasks in kitchen environments , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Joachim Hertzberg,et al.  Towards semantic maps for mobile robots , 2008, Robotics Auton. Syst..

[14]  Cid C. de Souza,et al.  Point guards and point clouds: solving general art gallery problems , 2013, SoCG '13.

[15]  Andrew Owens,et al.  SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels , 2013, 2013 IEEE International Conference on Computer Vision.

[16]  C. Ian Connolly,et al.  The determination of next best views , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[17]  Luigi Barazzetti,et al.  Towards automatic indoor reconstruction of cluttered building rooms from point clouds , 2014 .

[18]  Joachim Hertzberg,et al.  Building semantic object maps from sparse and noisy 3D data , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Andreas Uhl,et al.  BlenSor: Blender Sensor Simulation Toolbox , 2011, ISVC.

[20]  Vijay Kumar,et al.  Information-Theoretic Planning with Trajectory Optimization for Dense 3D Mapping , 2015, Robotics: Science and Systems.

[21]  Héctor H. González-Baños,et al.  A randomized art-gallery algorithm for sensor placement , 2001, SCG '01.

[22]  Chao Wang,et al.  Automatic BIM component extraction from point clouds of existing buildings for sustainability applications , 2015 .

[23]  Wolfram Burgard,et al.  Learning compact 3D models of indoor and outdoor environments with a mobile robot , 2003, Robotics Auton. Syst..

[24]  Nathan Michael,et al.  Obtaining Liftoff Indoors: Autonomous Navigation in Confined Indoor Environments , 2013, IEEE Robotics & Automation Magazine.

[25]  Burcu Akinci,et al.  Automatic Creation of Semantically Rich 3D Building Models from Laser Scanner Data , 2013 .

[26]  Gaurav S. Sukhatme,et al.  Towards geometric 3D mapping of outdoor environments using mobile robots , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[27]  M. Devy,et al.  Perception planning for an exploration task of a 3D environment , 2002, Object recognition supported by user interaction for service robots.

[28]  R. Dillmann,et al.  Using an attributed 2D-grid for next-best-view planning on 3D environment data for an autonomous robot , 2008, 2008 International Conference on Information and Automation.

[29]  A. Lastra,et al.  An Adaptive Hierarchical Next-Best-View Algorithm for 3D Reconstruction of Indoor Scenes , 2006 .

[30]  Reinhard Klein,et al.  Automatic reconstruction of parametric building models from indoor point clouds , 2016, Comput. Graph..

[31]  Antonio Adán,et al.  Semantic 3D Reconstruction of Furnished Interiors Using Laser Scanning and RFID Technology , 2016 .

[32]  Carl T. Haas,et al.  State of research in automatic as-built modelling , 2015, Adv. Eng. Informatics.

[33]  Jianxiong Xiao,et al.  Reconstructing the World’s Museums , 2012, International Journal of Computer Vision.

[34]  Cid C. de Souza,et al.  An exact algorithm for minimizing vertex guards on art galleries , 2011, Int. Trans. Oper. Res..

[35]  Klaus Schilling,et al.  ROBOTIC MAPPING OF CULTURAL HERITAGE SITES , 2015 .

[36]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[37]  Pablo Rodríguez-Gonzálvez,et al.  ACCURACY EVALUATION OF A MOBILE MAPPING SYSTEM WITH ADVANCED STATISTICAL METHODS , 2015 .

[38]  Jan Boehm,et al.  Automatic Geometry Generation from Point Clouds for BIM , 2015, Remote. Sens..

[39]  Antonio Adán,et al.  3D Reconstruction of Interior Wall Surfaces under Occlusion and Clutter , 2011, 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission.

[40]  Joachim Hertzberg,et al.  An autonomous mobile robot with a 3D laser range finder for 3D exploration and digitalization of indoor environments , 2003, Robotics Auton. Syst..

[41]  Johan A. K. Suykens,et al.  Benchmarking Least Squares Support Vector Machine Classifiers , 2004, Machine Learning.

[42]  Antonio Adán,et al.  Door detection in 3D colored laser scans for autonomous indoor navigation , 2016, 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[43]  Gaurav S. Sukhatme,et al.  A probabilistic framework for next best view estimation in a cluttered environment , 2014, J. Vis. Commun. Image Represent..

[44]  Frédéric Bosché,et al.  Planning for scanning using building information models: a novel approach with occlusion handling , 2015 .