Indoor Point Cloud Segmentation for Automatic Object Interpretation

The paper presents an algorithm for the automatic segmentation of point clouds from low cost sensors for object interpretation in indoor environments. This algorithm is considering the possible noisy character of the 3D point clouds and is using an iterative RANSAC approach for the segmentation task. For evaluating the robustness, it is applied on two indoor datasets, acquired with the Google Tango tablet and with the NavVis M3 trolley. The realized evaluation reveals the potential of the two systems for delivering data suitable for automatically interpreting indoor structures.

[1]  Michael Bosse,et al.  Zebedee: Design of a Spring-Mounted 3-D Range Sensor with Application to Mobile Mapping , 2012, IEEE Transactions on Robotics.

[2]  A. P. Kurian,et al.  A FAST AND FLEXIBLE METHOD FOR META-MAP BUILDING FOR ICP BASED SLAM , 2016 .

[3]  Jan Boehm,et al.  MOBILE LASER SCANNING FOR INDOOR MODELLING , 2013 .

[4]  Hugh F. Durrant-Whyte,et al.  Mobile robot localization by tracking geometric beacons , 1991, IEEE Trans. Robotics Autom..

[5]  Paul J. Besl,et al.  Method for registration of 3-D shapes , 1992, Other Conferences.

[6]  Ali Mohammad Khosravani,et al.  Automatic modeling of building interiors using low-cost sensor systems , 2016 .

[7]  David Fofi,et al.  A comparative survey on invisible structured light , 2004, IS&T/SPIE Electronic Imaging.

[8]  Sisi Zlatanova,et al.  FIRST EXPERIMENTS WITH THE TANGO TABLET FOR INDOOR SCANNING , 2016 .

[9]  P. Lancaster,et al.  Surfaces generated by moving least squares methods , 1981 .

[10]  M. Bassier,et al.  Evaluation of data acquisition techniques and workflows for Scan to BIM , 2015 .

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

[12]  Benjamin Huhle,et al.  Statistical Reconstruction of Indoor Scenes , 2009 .

[13]  Enrique Valero,et al.  Automatic Method for Building Indoor Boundary Models from Dense Point Clouds Collected by Laser Scanners , 2012, Sensors.

[14]  Esa Rahtu,et al.  Robust loop closures for scene reconstruction by combining odometry and visual correspondences , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[15]  Jan Boehm.  Accuracy Investigation for Structured-light Based Consumer 3D Sensors , 2014 .

[16]  Wolfram Burgard,et al.  A Tutorial on Graph-Based SLAM , 2010, IEEE Intelligent Transportation Systems Magazine.

[17]  Brian Okorn,et al.  Toward Automated Modeling of Floor Plans , 2010 .

[18]  Mingyang Li,et al.  Improving the accuracy of EKF-based visual-inertial odometry , 2012, 2012 IEEE International Conference on Robotics and Automation.

[19]  Andrew W. Fitzgibbon,et al.  KinectFusion: Real-time dense surface mapping and tracking , 2011, 2011 10th IEEE International Symposium on Mixed and Augmented Reality.

[20]  Jan Boehm,et al.  Toward automatic reconstruction of interiors from laser data , 2009 .

[21]  Cyrill Stachniss,et al.  Simultaneous Localization and Mapping , 2016, Springer Handbook of Robotics, 2nd Ed..

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