A Fast Registration Method Using IP and Its Application to Ultrasound Image Registration

This paper presents a fast registration method based on solving an energy minimization problem derived by implicit polynomials (IPs). Once a target object is encoded by an IP, it will be driven fast towards a corresponding source object along the IP’s gradient flow without using point-wise correspondences. This registration process is accelerated by a new IP transformation method. Instead of the time-consuming transformation to a large discrete data set, the new method can transform the polynomial coefficients to maintain the same Euclidean transformation. Its computational efficiency enables us to improve a new application for real-time Ultrasound (US) pose estimation. The reported experimental results demonstrate the capabilities of our method in overcoming the limitations of a noisy, unconstrained, and freehand US image, resulting in fast and robust registration.

[1]  B. Donald,et al.  Symbolic and Numerical Computation for Artificial Intelligence , 1997 .

[2]  Takeshi Oishi,et al.  6-DOF pose estimation from single Ultrasound image using 3D IP models , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[3]  David B. Cooper,et al.  Pose Estimation of Free-Form 3D Objects without Point Matching using Algebraic Surface Models , 1998 .

[4]  Andreas Koschan,et al.  Gaussian energy functions for registration without correspondences , 2004, ICPR 2004.

[5]  Katsushi Ikeuchi,et al.  Adaptively Determining Degrees of Implicit Polynomial Curves and Surfaces , 2007, ACCV.

[6]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[7]  Gérard G. Medioni,et al.  Surface description of complex objects from multiple range images , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  S. Umeyama,et al.  Least-Squares Estimation of Transformation Parameters Between Two Point Patterns , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

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

[10]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

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

[12]  G. Champleboux,et al.  From accurate range imaging sensor calibration to accurate model-based 3D object localization , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  情報処理学会 IPSJ transactions on computer vision and applications , 2009 .

[14]  Charles V. Stewart,et al.  Covariance-Based Registration , 2002 .

[15]  Pavel Krsek,et al.  The Trimmed Iterative Closest Point algorithm , 2002, Object recognition supported by user interaction for service robots.

[16]  Gabriel Taubin,et al.  Estimation of Planar Curves, Surfaces, and Nonplanar Space Curves Defined by Implicit Equations with Applications to Edge and Range Image Segmentation , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  W. D. Evans,et al.  PARTIAL DIFFERENTIAL EQUATIONS , 1941 .

[18]  Mustafa Unel,et al.  Fitting globally stabilized algebraic surfaces to range data , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[19]  David Fofi,et al.  A review of recent range image registration methods with accuracy evaluation , 2007, Image Vis. Comput..

[20]  David B. Cooper,et al.  Improving the stability of algebraic curves for applications , 2000, IEEE Trans. Image Process..

[21]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[22]  Aly A. Farag,et al.  Shape Representation and Registration using Vector Distance Functions , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Atsushi Nakazawa,et al.  Fast simultaneous alignment of multiple range images using index images , 2005, Fifth International Conference on 3-D Digital Imaging and Modeling (3DIM'05).

[24]  Charles V. Stewart,et al.  Fast and robust registration of 3D surfaces using low curvature patches , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[25]  David B. Cooper,et al.  The Complex Representation of Algebraic Curves and Its Simple Exploitation for Pose Estimation and Invariant Recognition , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Ryo Kurazume,et al.  Fast model–image registration using a two-dimensional distance map for surgical navigation system , 2007, Adv. Robotics.

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