Point Set Registration: Coherent Point Drift

被引:2087
作者
Myronenko, Andriy [1 ]
Song, Xubo [1 ]
机构
[1] Oregon Hlth & Sci Univ, Sch Med, Dept Sci & Engn, Beaverton, OR 97006 USA
基金
美国国家科学基金会;
关键词
Registration; correspondence; matching; alignment; rigid; nonrigid; point sets; Coherent Point Drift (CPD); Gaussian mixture model (GMM); coherence; regularization; EM algorithm; ALGORITHM; ALIGNMENT;
D O I
10.1109/TPAMI.2010.46
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Point set registration is a key component in many computer vision tasks. The goal of point set registration is to assign correspondences between two sets of points and to recover the transformation that maps one point set to the other. Multiple factors, including an unknown nonrigid spatial transformation, large dimensionality of point set, noise, and outliers, make the point set registration a challenging problem. We introduce a probabilistic method, called the Coherent Point Drift (CPD) algorithm, for both rigid and nonrigid point set registration. We consider the alignment of two point sets as a probability density estimation problem. We fit the Gaussian mixture model (GMM) centroids (representing the first point set) to the data (the second point set) by maximizing the likelihood. We force the GMM centroids to move coherently as a group to preserve the topological structure of the point sets. In the rigid case, we impose the coherence constraint by reparameterization of GMM centroid locations with rigid parameters and derive a closed form solution of the maximization step of the EM algorithm in arbitrary dimensions. In the nonrigid case, we impose the coherence constraint by regularizing the displacement field and using the variational calculus to derive the optimal transformation. We also introduce a fast algorithm that reduces the method computation complexity to linear. We test the CPD algorithm for both rigid and nonrigid transformations in the presence of noise, outliers, and missing points, where CPD shows accurate results and outperforms current state-of-the-art methods.
引用
收藏
页码:2262 / 2275
页数:14
相关论文
共 49 条
[1]  
[Anonymous], 2002, Lanczos algorithms for large symmetric eigenvalue computations
[2]  
[Anonymous], 2007, Advances in Neural Information Processing Systems
[3]  
[Anonymous], 2010, STANFORD 3D SCANNING
[4]   LEAST-SQUARES FITTING OF 2 3-D POINT SETS [J].
ARUN, KS ;
HUANG, TS ;
BLOSTEIN, SD .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (05) :699-700
[5]   Shape matching and object recognition using shape contexts [J].
Belongie, S ;
Malik, J ;
Puzicha, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (04) :509-522
[6]   A METHOD FOR REGISTRATION OF 3-D SHAPES [J].
BESL, PJ ;
MCKAY, ND .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1992, 14 (02) :239-256
[7]  
Bishop CM., 1995, NEURAL NETWORKS PATT
[9]   On different facets of regularization theory [J].
Chen, Z ;
Haykin, S .
NEURAL COMPUTATION, 2002, 14 (12) :2791-2846
[10]   A new point matching algorithm for non-rigid registration [J].
Chui, HL ;
Rangarajan, A .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2003, 89 (2-3) :114-141