论文:2018,Vol:36,Issue(5):942-948
引用本文:
杨丽娟, 田铮, 温金环, 延伟东. 基于变分贝叶斯的自适应非刚性点集匹配[J]. 西北工业大学学报
Yang Lijuan, Tian Zheng, Wen Jinhuan, Yan Weidong. Adaptive Non-Rigid Point Set Registration Based on Variational Bayesian[J]. Northwestern polytechnical university

基于变分贝叶斯的自适应非刚性点集匹配
杨丽娟1, 田铮1,2, 温金环1, 延伟东1
1. 西北工业大学 应用数学系, 陕西 西安 710129;
2. 中国科学院 遥感科学国家重点实验室, 北京 100101
摘要:
针对存在异常值的非刚性点集匹配问题,提出了一种基于贝叶斯混合t分布模型的匹配方法。在变分贝叶斯框架下,点集匹配问题转化为最大化对数似然的变分下界,利用变分推断确定变换参数。利用先验模型,将空间正则化约束并入贝叶斯混合t分布模型中,根据不同的点集可自适应地确定正则化参数。与高斯分布相比,t分布对异常值更加稳健。最后,在模拟点集和真实图像上的实验对比分析,验证了该方法在处理存在异常值的非刚性点集匹配问题时的有效性。
关键词:    非刚性    点集匹配    变分贝叶斯    混合t分布    异常值    稳健   
Adaptive Non-Rigid Point Set Registration Based on Variational Bayesian
Yang Lijuan1, Tian Zheng1,2, Wen Jinhuan1, Yan Weidong1
1. Department of Applied Mathematics, Northwestern Polytechnical University, Xi'an 710129, China;
2. The State Key Laboratory of Remote Sensing Science, Chinese Academy of Sciences, Beijing 100101, China
Abstract:
For the existence of outliers in non-rigid point set registration, a method based on Bayesian student's t mixture model(SMM) is proposed. Under the framework of variational Bayesian, the point set registration problem is converted to maximize the variational lower bound of log-likelihood, where the transformation parameters are found through variational inference. By prior model, the constraint over spatial regularization is incorporated into the Bayesian SMM, which can adaptively be determined for different data sets. Compared with Gaussian distribution, the student's t distribution is more robust to outliers. The experimental comparative analysis of simulated points and real images verify the effectiveness of the proposed method on the non-rigid point set registration with outliers.
Key words:    non-rigid    point set registration    variational Bayesian    student's t mixture model    outliers    robust   
收稿日期: 2017-09-12     修回日期:
DOI:
基金项目: 国家自然科学基金青年科学基金(61201323,61301196)、国家自然科学基金面上项目(60972150)、遥感科学国家重点实验室开放基金(OFSLRSS201206)、陕西省自然科学基础研究计划(2017JM6026)与陕西省教育厅专项科研计划项目(16JK1326)资助
通讯作者:     Email:
作者简介: 杨丽娟(1987-),女,西北工业大学博士研究生,主要从事遥感图像配准及模式识别研究。
相关功能
PDF(1627KB) Free
打印本文
把本文推荐给朋友
作者相关文章
杨丽娟  在本刊中的所有文章
田铮  在本刊中的所有文章
温金环  在本刊中的所有文章
延伟东  在本刊中的所有文章

参考文献:
[1] Goshtasby A A. 2-D and 3-D Image Registration:for Medical, Remote Sensing, and Industrial Applications[M]. New Jersey, Voiley-Interscience, 2005
[2] Crum W R, Hartkens T, Hill D L G. Non-Rigid Image Registration:Theory and Practice[J]. The British Journal of Radiology, 2004, 77(Suppl 2):140-153
[3] McLachlan G, Peel D. Finite Mixture Models[M]. New York, John Wiley & Sons, 2004
[4] Jian B, Vemuri B C. Robust Point Set Registration Using Gaussian Mixture Models[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2011, 33(8):1633-1645
[5] Myronenko A, Song X. Point Set Registration:Coherent Point Drift[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 32(12):2262-2275
[6] Zhou Z Y, Zheng J, Dai Y K, et al. Robust Non-Rigid Point Set Registration Using Student's-T Mixture Model[J]. PloS One, 2014, 9(3):e91381
[7] Bishop C M. Pattern Recognition and Machine Learning[M]. New York, Springer-Verlay, 2006
[8] Blei D M, Kucukelbir A, McAuliffe J D. Variational Inference:a Review for Statisticians[J]. Journal of the American Statistical Association, 2017, 112(518):859-877
[9] Qu H B, Wang J Q, Li B, et al. Probabilistic Model for Robust Affine and Non-Rigid Point Set Matching[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2017, 39(2):371-384
[10] Simpson I J, Schnabel J A, Groves A R, et al. Probabilistic Inference of Regularisation in Non-Rigid Registration[J]. NeuroImage, 2012, 59(3):2438-2451
[11] Svensén M, Bishop C M. Robust Bayesian Mixture Modelling[J]. Neurocomputing, 2005, 64:235-252
[12] Archambeau C, Verleysen M. Robust Bayesian Clustering[J]. Neural Networks, 2007, 20(1):129-138
[13] Baldacchino T, Worden K, Rowson J. Robust Nonlinear System Identification:Bayesian Mixture of Experts Using the T-Distribution[J]. Mechanical Systems and Signal Processing, 2017, 85:977-992
[14] Impens C. Stirling's Series Made Easy[J]. The American Mathematical Monthly, 2003, 110(8):730-735
[15] Chui H, Rangarajan A. A New Point Matching Algorithm for Non-Rigid Registration[J]. Computer Vision and Image Understanding, 2003, 89(2):114-141
相关文献:
1.赵伟, 田铮, 杨丽娟, 延伟东, 温金环.图像稳健配准的非负子空间匹配方法[J]. 西北工业大学学报, 2016,34(2): 362-366