Robust Generalized Point Cloud Registration Using Hybrid Mixture Model

Min, Zhe; Wang, Jiaole; Meng, Max Q.-H.

doi:10.1109/icra.2018.8460825

Cited by 36 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After that b q j has been calculated, then [dR q j , dt q j ] can be easily restored using the Rodrigues formula in (9) again. With [dR q j , dt q j ], the updated rotation matrice R q j ∈ SO(3) and the updated translation vector t q j ∈ R 3 in the current q step are computed as that in [2]: R q j = dR q j R q−1 j , t q j = dR q j t q−1 j + dt q j , where R q−1 j ∈ SO(3) and t q j ∈ R 3×1 are the rotation matrix and translation vector associated with D j in the (q −1)-th step.…”

Section: B M-rigid Stepmentioning

confidence: 99%

“…P OINT set registration (PSR) is a fundamental and challenging problem in the fields of medical robotics, medical image analysis (MIA) and computer-assisted surgery (CAS) [1]- [15]. The aim of the rigid PSR problem is to accurately compute the rigid transformation matrix between point sets (PSs) [2]. In CAS, both fiducial-based registration and surface registration (or generally speaking PSR) can be used to align the pre-operative volumetric image space to the intra-operative patient space [16]- [18].…”

Section: Introductionmentioning

confidence: 99%

“…The possible clinical applications of the registration problem to be dealt with in this article are summarized as follows. (1) Pre-operative to intra-operative space alignment in CAS [2], [17], [23], [24]. (2) Statistical shape modelling (SSM).…”

Section: Introductionmentioning

confidence: 99%

“…(1) In order to significantly improve the registration accuracy and robustness, we utilize the orientation-al information (i.e., the normal vectors) that can be extracted from the raw PS with various methods [2], [28], [29]. (2) The second motivation is to consider the anisotropic characteristic in the position localization error, which is common in many CAS applications [29]- [32]. (3) The third motivation is to remove the bias towards one specific PS in the PSR algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Joint Rigid Registration of Multiple Generalized Point Sets With Anisotropic Positional Uncertainties in Image-Guided Surgery

Min

Wang

Meng

2022

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

In medical image analysis (MIA) and computerassisted surgery (CAS), aligning two multiple point sets (PSs) together is an essential but also a challenging problem. For example, rigidly aligning multiple point sets into one common coordinate frame is a prerequisite for statistical shape modelling (SSM). Accurately aligning the pre-operative space with the intraoperative space in CAS is very crucial to successful interventions. In this article, we formally formulate the multiple generalized point set registration problem (MGPSR) in a probabilistic manner, where both the positional and the normal vectors are used. The six-dimensional vectors consisting of both positional and normal vectors are called as generalized points. In the formulated model, all the generalized PSs to be registered are considered to be the realizations of underlying unknown hybrid mixture models (HMMs). By assuming the independence of the positional and orientational vectors (i.e., the normal vectors), the probability density function (PDF) of an observed generalized point is computed as the product of Gaussian and Fisher distributions. Furthermore, to consider the anisotropic noise in surgical navigation, the positional error is assumed to obey a multi-variate Gaussian distribution. Finally, registering PSs is formulated as a maximum likelihood (ML) problem, and solved under the expectation maximization (EM) technique. By using more enriched information (i.e., the normal vectors), our algorithm is more robust to outliers. By treating all PSs equally, our algorithm does not bias towards any PS. To validate the Manuscript

show abstract

Section: B M-rigid Stepmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Joint Rigid Registration of Multiple Generalized Point Sets With Anisotropic Positional Uncertainties in Image-Guided Surgery

Min

Wang

Meng

2022

IEEE Trans. Automat. Sci. Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To overcome this limitation, [25] proposed a probabilistic point set registration approach based on Student's t-distributions (TMM), which confers the property of localized robustness to the registration process, via estimation of a unique shape parameter for each mixture component in the TMM. Numerous recent studies have employed hybrid shape representations [26,19,18,20,17,23], in order to increase the discriminative capacity of probabilistic point set registration approaches. In [26] for example, spatial positions and their associated surface normal vectors were modeled with Student's t-distributions, and Von-Mises-Fisher (vmF) distributions, respectively.…”

Section: Introductionmentioning

confidence: 99%