Surface patch reconstruction via curve sampling

This paper introduces a method that reconstructs a surface patch by sampling along three concurrent curves on the surface with a touch sensor. These data curves, each lying in a different plane, form a "skeleton" from which the patch is built in two phases. First, the Darboux frame at the curve intersection is estimated to reflect the local geometry. Second, polynomial fitting is carried out in the Darboux frame. The use of total (absolute) Gaussian curvature effectively prevents unnecessary folding of the surface normally expected to result from fitting over one-dimensional data. The reconstructed patch attains remarkable accuracy as demonstrated through experiments. This work carries a promise for in-hand manipulation. It also has potential application in building accurate models for complex curved objects which can cause occlusion to a camera or a range sensor

[1]  Jean Ponce,et al.  Using Geometric Distance Fits for 3-D Object Modeling and Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Friedrich Lange,et al.  Learning force control with position controlled robots , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[3]  Daniel Keren,et al.  Fitting Curves and Surfaces With Constrained Implicit Polynomials , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Anil K. Jain,et al.  On reliable curvature estimation , 1989, CVPR.

[5]  David B. Cooper,et al.  Describing Complicated Objects by Implicit Polynomials , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Francis Schmitt,et al.  Intrinsic Surface Properties from Surface Triangulation , 1992, ECCV.

[7]  Ilan Shimshoni,et al.  Estimating the principal curvatures and the darboux frame from real 3-D range data , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[8]  Ernest M. Stokely,et al.  Surface Parametrization and Curvature Measurement of Arbitrary 3-D Objects: Five Practical Methods , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Gabriel Taubin,et al.  Estimating the tensor of curvature of a surface from a polyhedral approximation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Yan-Bin Jia,et al.  High precision contour tracking with a joystick sensor , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[11]  Peter K. Allen,et al.  Acquisition and interpretation of 3-D sensor data from touch , 1990, IEEE Trans. Robotics Autom..

[12]  S. Shankar Sastry,et al.  Kinematics and control of multifingered hands with rolling contact , 1989 .

[13]  Shahram Payandeh,et al.  Shape Description of Curved Surfaces from Contact Sensing Using Surface Normals , 1999, Int. J. Robotics Res..

[14]  Anil K. Jain,et al.  Segmentation and Classification of Range Images , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  David B. Cooper,et al.  The 3L Algorithm for Fitting Implicit Polynomial Curves and Surfaces to Data , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Brian A. Barsky,et al.  Reconstructing curved surfaces from specular reflection patterns using spline surface fitting of normals , 1996, SIGGRAPH.

[17]  David J. Kriegman,et al.  Parameterized Families of Polynomials for Bounded Algebraic Curve and Surface Fitting , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  B. O'neill.  Elementary Differential Geometry , 1966 .

[19]  J. De Schutter,et al.  Hybrid vision/force control at corners in planar robotic-contour following , 2002 .

[20]  Yan-Bin Jia,et al.  Semidifferential Invariants for Tactile Recognition of Algebraic Curves , 2005, Int. J. Robotics Res..