Non-Rigid Point Set Registration via Mixture of Asymmetric Gaussians with Integrated Local Structures

被引:0
|
作者
Fu, Mingliang [1 ,2 ]
Zhou, Weijia [3 ]
机构
[1] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[2] Chinese Acad Sci, Shenyang Inst Automat, Shenyang 110016, Liaoning, Peoples R China
[3] Shenyang Inst Automat, Shenyang 110016, Liaoning, Peoples R China
关键词
D O I
暂无
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
As a fundamental problem in computer vision community, non-rigid point set registration is a challenging topic since the corresponding transformation model is often unknown and difficult to model. In this paper, we present a robust method for non-rigid point set registration. Firstly, a mixture of asymmetric Gaussian model (MoAG) is employed to capture spatially asymmetric distributions which the Gaussian mixture model (GMM) based methods neglect instinctively. Secondly, local structures among adjacent points are integrated into the MoAG-based point set registration framework to improve the correspondence estimation. Thirdly, Expectation-Maximization (EM) algorithm which provides a numerical method for finding maximum likelihood estimators is utilized to estimate parameters of the latent variable model in our proposed method. The transformation model is solved under regularization theory in the Reproducing Kernel Hilbert Space (RKHS). Conveniently, a fast implementation is achieved by the sparse approximation. Finally, experiments results show that the robustness of our algorithm outperforms the comparative state of art methods under various types of distortions, such as deformation, noise, outliers and occlusion.
引用
收藏
页码:999 / 1004
页数:6
相关论文
共 50 条
  • [41] Robust Non-rigid Point Set Registration based on Dynamic Tree
    Qu, Di
    Du, Shaoyi
    Liu, Juan
    Wang, Yike
    Xue, Jianru
    [J]. 2015 CHINESE AUTOMATION CONGRESS (CAC), 2015, : 707 - 711
  • [42] A Conditional Generative Adversarial Network for Non-rigid Point Set Registration
    Tang, Haolin
    Zhao, Yanxiao
    [J]. 2021 IEEE ASIA-PACIFIC CONFERENCE ON COMPUTER SCIENCE AND DATA ENGINEERING (CSDE), 2021,
  • [43] Non-rigid Articulated Point Set Registration for Human Pose Estimation
    Ge, Song
    Fan, Guoliang
    [J]. 2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2015, : 94 - 101
  • [44] Adaptive Non-Rigid Point Set Registration Based on Variational Bayesian
    基于变分贝叶斯的自适应非刚性点集匹配
    [J]. 2018, Northwestern Polytechnical University (36):
  • [45] Non-rigid point set registration by high-dimensional representation
    Huang, Huimin
    Zhou, Zuofeng
    Cao, Jianzhong
    [J]. IET IMAGE PROCESSING, 2018, 12 (10) : 1746 - 1752
  • [46] Non-rigid Point Set Registration Based on Iterative Linear Optimization
    Lin, Hongbin
    Zhang, Daqing
    [J]. ADVANCES IN IMAGE AND GRAPHICS TECHNOLOGIES, IGTA 2016, 2016, 634 : 167 - 175
  • [47] Non-rigid point set registration of curves: registration of the superficial vessel centerlines of the brain
    Marreiros, Filipe M. M.
    Wang, Chunliang
    Rossitti, Sandro
    Smedby, Orjan
    [J]. MEDICAL IMAGING 2016: IMAGE-GUIDED PROCEDURES, ROBOTIC INTERVENTIONS, AND MODELING, 2016, 9786
  • [48] A robust algorithm for point set registration using mixture of Gaussians
    Jian, B
    Vemuri, BC
    [J]. TENTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 1246 - 1251
  • [49] Non-rigid point set registration using dual-feature finite mixture model and global-local structural preservation
    Zhang, Su
    Yang, Kun
    Yang, Yang
    Luo, Yi
    Wei, Ziquan
    [J]. PATTERN RECOGNITION, 2018, 80 : 183 - 195
  • [50] Correction: Rotation robust non-rigid point set registration with Bayesian student’s t mixture model
    Lijuan Yang
    Ying Yang
    Changpeng Wang
    Fuxiao Li
    [J]. The Visual Computer, 2024, 40 : 457 - 457