Generalized Point Set Registration with the Kent Distribution

Min，Zhe1,2; Zhu，Delong2; Meng，Max Q.H.3,4,5

10.1109/ICRA48506.2021.9560824

2021

IEEE International Conference on Robotics and Automation (ICRA)

1050-4729

2577-087X

978-1-7281-9078-5

Proceedings - IEEE International Conference on Robotics and Automation

2021-May

7151-7158

MAY 30-JUN 05, 2021

null,Xian,PEOPLES R CHINA

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Point set registration (PSR) is an essential problem in communities of computer vision, medical robotics and biomedical engineering. This paper is motivated by considering the anisotropic characteristics of the error values in estimating both the positional and orientational vectors from the PSs to be registered. To do this, the multi-variate Gaussian and Kent distributions are utilized to model the positional and orientational uncertainties, respectively. Our contributions of this paper are three-folds: (i) the PSR problem using normal vectors is formulated as a maximum likelihood estimation (MLE) problem, where the anisotropic characteristics in both positional and normal vectors are considered; (ii) the matrix forms of the objective function and its associated gradients with respect to the desired parameters are provided, which can facilitate the computational process; (iii) two approaches of computing the normalizing constant in the Kent distribution are compared. We verify our proposed registration method on various PSs (representing pelvis and femur bones) in computer-assisted orthopedic surgery (CAOS). Extensive experimental results demonstrate that our method outperforms the state-of-the-art methods in terms of the registration accuracy and the robustness.

Maximum likelihood estimation Computer vision Uncertainty Orthopedic surgery Conferences Computational modeling Probabilistic logic

其他

英语

CPCI-S ; EI

Ocean Park Conservation Foundation, Hong Kong[#14210117];Hong Kong Arts Development Council[#N CUHK448/17];Shaanxi Key Science and Technology Innovation Team Project[JCYJ20170413161616163];

Automation & Control Systems ; Robotics

Automation & Control Systems ; Robotics

WOS:000771405400052

20220911737668

Anisotropy ; Biomedical engineering ; Geometry ; Medical computing

Biomedical Engineering:461.1 ; Computer Applications:723.5 ; Mathematics:921 ; Statistical Methods:922 ; Physical Properties of Gases, Liquids and Solids:931.2

2-s2.0-85125455942

Scopus

1.The University College London,London,United Kingdom
2.The Department of Electronic Engineering,The Chinese University of Hong Kong,N.T.,Hong Kong
3.The Department of Electronic and Electrical Engineering,Southern University of Science and Technology,Shenzhen,China
4.The Shenzhen Research Institute,The Chinese University of Hong Kong,Shenzhen,China
5.The Department of Electronic Engineering,Hong Kong

Min，Zhe,Zhu，Delong,Meng，Max Q.H.. Generalized Point Set Registration with the Kent Distribution[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2021:7151-7158.