Generic fitted shapes (GFS): Volumetric object segmentation in service robotics

In this paper, a simultaneous 3D volumetric segmentation and reconstruction method, based on the so-called Generic Fitted Shapes (GFS) is proposed. The aim of this work is to cope with the lack of volumetric information encountered in visually controlled mobile manipulation systems equipped with stereo or RGB-D cameras. Instead of using primitive volumes, such as cuboids or cylinders, for approximating objects in point clouds, their volumetric structure has been estimated based on fitted generic shapes. The proposed GFSs can capture the shapes of a broad range of object classes without the need of large a-priori shape databases. The fitting algorithm, which aims at determining the particular geometry of each object of interest, is based on a modified version of the active contours approach extended to the 3D Cartesian space. The proposed volumetric segmentation system produces comprehensive closed object surfaces which can be further used in mobile manipulation scenarios. Within the experimental setup, the proposed technique has been evaluated against two state-of-the-art methods, namely superquadrics and 3D Object Retrieval (3DOR) engines.

[1]  Dieter Fox,et al.  Manipulator and object tracking for in-hand 3D object modeling , 2011, Int. J. Robotics Res..

[2]  Nico Blodow,et al.  General 3D modelling of novel objects from a single view , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[3]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

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

[5]  Jorge Dias,et al.  Extracting data from human manipulation of objects towards improving autonomous robotic grasping , 2012, Robotics Auton. Syst..

[6]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[7]  Antonio Adán,et al.  A hybrid human-computer approach for recovering incomplete cultural heritage pieces , 2012, Comput. Graph..

[8]  Nico Blodow,et al.  Combined 2D–3D categorization and classification for multimodal perception systems , 2011, Int. J. Robotics Res..

[9]  Peter K. Allen,et al.  Learning grasp stability , 2012, 2012 IEEE International Conference on Robotics and Automation.

[10]  Kazufumi Kaneda,et al.  Reconstructing a 3-D structure with multiple deformable solid primitives , 1997, Comput. Graph..

[11]  Peter Eisert,et al.  3-D object reconstruction using spatially extended voxels and multi-hypothesis voxel coloring , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  Anis Sahbani,et al.  Special issue "Autonomous Grasping" , 2012, Robotics Auton. Syst..

[13]  Zoltan-Csaba Marton,et al.  Using Web Catalogs to Locate and Categorize Unknown Furniture Pieces in 3 D Laser Scans , 2011 .

[14]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[15]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[16]  Angel P. del Pobil,et al.  Task planning for intelligent robot manipulation , 2007, Artificial Intelligence and Applications.

[17]  Tiberiu T. Cocias,et al.  Multiple-superquadrics based object surface estimation for grasping in service robotics , 2012, 2012 13th International Conference on Optimization of Electrical and Electronic Equipment (OPTIM).

[18]  Demetri Terzopoulos,et al.  A finite element model for 3D shape reconstruction and nonrigid motion tracking , 1993, 1993 (4th) International Conference on Computer Vision.

[19]  Remco C. Veltkamp,et al.  A Survey of Content Based 3D Shape Retrieval Methods , 2004, SMI.

[20]  K. Mardia,et al.  Statistical Shape Analysis , 1998 .

[21]  Stefan Holzer,et al.  Towards autonomous robotic butlers: Lessons learned with the PR2 , 2011, 2011 IEEE International Conference on Robotics and Automation.

[22]  Óscar Martínez Mozos,et al.  Furniture Models Learned from the WWW , 2011, IEEE Robotics & Automation Magazine.

[23]  Markus Vincze,et al.  Efficient 3D Object Detection by Fitting Superquadrics to Range Image Data for Robot's Object Manipulation , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[24]  Antonio Morales,et al.  Vision-based three-finger grasp synthesis constrained by hand geometry , 2006, Robotics Auton. Syst..

[25]  Dejan Pangercic,et al.  Real-time CAD model matching for mobile manipulation and grasping , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[26]  Thomas Malzbender,et al.  A Survey of Methods for Volumetric Scene Reconstruction from Photographs , 2001, VG.

[27]  Xin Li,et al.  An estimation-based approach for range image segmentation: on the reliability of primitive extraction , 2003, Pattern Recognit..

[28]  Peter K. Allen,et al.  Graspit! A versatile simulator for robotic grasping , 2004, IEEE Robotics & Automation Magazine.

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

[30]  Christopher J. Taylor,et al.  Statistical models of shape - optimisation and evaluation , 2008 .

[31]  Axel Gräser,et al.  A BCI-controlled robotic assistant for quadriplegic people in domestic and professional life , 2011, Robotica.

[32]  J. Rodgers,et al.  Thirteen ways to look at the correlation coefficient , 1988 .

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