A novel knot selection method for the error-bounded B-spline curve fitting of sampling points in the measuring process

The B-spline curve has been widely used in the reconstruction of measurement data. The error-bounded sampling points reconstruction can be achieved by the knot addition method (KAM) based B-spline curve fitting. In KAM, the selection pattern of initial knot vector has been associated with the ultimate necessary number of knots. This paper provides a novel initial knots selection method to condense the knot vector required for the error-bounded B-spline curve fitting. The initial knots are determined by the distribution of features which include the chord length (arc length) and bending degree (curvature) contained in the discrete sampling points. Firstly, the sampling points are fitted into an approximate B-spline curve Gs with intensively uniform knot vector to substitute the description of the feature of the sampling points. The feature integral of Gs is built as a monotone increasing function in an analytic form. Then, the initial knots are selected according to the constant increment of the feature integral. After that, an iterative knot insertion (IKI) process starting from the initial knots is introduced to improve the fitting precision, and the ultimate knot vector for the error-bounded B-spline curve fitting is achieved. Lastly, two simulations and the measurement experiment are provided, and the results indicate that the proposed knot selection method can reduce the number of ultimate knots available.

[1]  Andrés Iglesias,et al.  Elitist clonal selection algorithm for optimal choice of free knots in B-spline data fitting , 2015, Appl. Soft Comput..

[2]  Caiming Zhang,et al.  Adaptive knot placement using a GMM-based continuous optimization algorithm in B-spline curve approximation , 2011, Comput. Aided Des..

[3]  D. F. Rogers.  Constrained B-spline curve and surface fitting , 1989 .

[4]  Tong Yang,et al.  Generating optical freeform surfaces considering both coordinates and normals of discrete data points. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.

[5]  Jiansong Deng,et al.  Knot calculation for spline fitting via sparse optimization , 2015, Comput. Aided Des..

[6]  Chen-Han Lee,et al.  A chord error conforming tool path B-spline fitting method for NC machining based on energy minimization and LSPIA , 2015, J. Comput. Des. Eng..

[7]  Miguel Pasadas,et al.  Evolutionary computation for optimal knots allocation in smoothing splines , 2013 .

[8]  Limin Zhu,et al.  Look-ahead interpolation of short line segments using B-spline curve fitting of dominant points , 2015 .

[9]  A. Iglesias,et al.  Firefly Algorithm for Explicit B-Spline Curve Fitting to Data Points , 2013 .

[10]  Shigefumi Tamura,et al.  Point-tangent/point-normal B-spline curve interpolation by geometric algorithms , 2009, Comput. Aided Des..

[11]  Michel Bercovier,et al.  Spline Curve Approximation and Design by Optimal Control Over the Knots , 2004, Computing.

[12]  Les A. Piegl,et al.  The NURBS book (2nd ed.) , 1997 .

[13]  Shi-Min Hu,et al.  A second order algorithm for orthogonal projection onto curves and surfaces , 2005, Comput. Aided Geom. Des..

[14]  J. Kruth,et al.  NURBS curve and surface fitting for reverse engineering , 1998 .

[15]  Hyungjun Park,et al.  B-spline curve fitting based on adaptive curve refinement using dominant points , 2007, Comput. Aided Des..

[16]  Gang Zhao,et al.  Adaptive knot placement in B-spline curve approximation , 2005, Comput. Aided Des..

[17]  Knut Mørken,et al.  Knot removal for parametric B-spline curves and surfaces , 1987, Comput. Aided Geom. Des..

[18]  Erkan Ülker.  B-Spline Curve Approximation Using Pareto Envelope- Based Selection Algorithm - PESA , 2013 .