Indoor Pose Estimation Using 3D Scene Landmarks for Service Robotics

In this paper, a markerless approach for estimating the pose of a robot using only 3D visual information is presented. As opposite to traditional methods, our approach makes use of 3D features solely for determining a relative position between the imaged scene (e.g. landmarks present on site) and the robot. Such a landmark is calculated from stored 3D map of the environment. The recognition of the landmark is performed via a 3D Object Retrieval (3DOR) search engine. The presented pose estimation technique produces a reliable and accurate pose information which can be further used for complex scene understanding and/or navigation. The performance of the proposed approach has been evaluated against a traditional marker-based position estimation library.

[1]  Cindy Grimm,et al.  Local Shape Descriptors, a Survey and Evaluation , 2011, 3DOR@Eurographics.

[2]  Gigel Macesanu,et al.  Robust camera pose and scene structure analysis for service robotics , 2011, Robotics Auton. Syst..

[3]  Richard Hartley.  An object-oriented approach to scene reconstruction , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[4]  E. Fiume,et al.  Shape matching of 3D contours using normalized Fourier descriptors , 2002, Proceedings SMI. Shape Modeling International 2002.

[5]  Wanlei Zhou,et al.  Spectral shape descriptor using spherical harmonics , 2010, Integr. Comput. Aided Eng..

[6]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Michal Perdoch,et al.  Efficient sequential correspondence selection by cosegmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark (Figures 1 and 2) , 2004, Shape Modeling International Conference.

[9]  Thomas A. Funkhouser,et al.  Early experiences with a 3D model search engine , 2003, Web3D '03.

[10]  Federico Tombari,et al.  Unique Signatures of Histograms for Local Surface Description , 2010, ECCV.

[11]  Philip N. Klein,et al.  Recognition of Shapes by Editing Shock Graphs , 2001, ICCV.

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

[13]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[14]  Mongi A. Abidi,et al.  Outlier rejection by oriented tracks to aid pose estimation from video , 2006, Pattern Recognit. Lett..

[15]  Bruce H. Thomas,et al.  Measuring ARTootKit accuracy in long distance tracking experiments , 2002, The First IEEE International Workshop Agumented Reality Toolkit,.

[16]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..