Joint Rigid Registration of Multiple Generalized Point Sets With Hybrid Mixture Models

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

doi:10.1109/tase.2019.2906391

Cited by 31 publications

(13 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each case with one specific type of positional noise and one specific percentage of outliers, N trial = 30 registration trials have been repeated using the registration algorithms (i.e., ECMPR [36], JRMPC [34], HMM(Iso) [57] and our proposed algorithm). On one hand, we validate the advantage of considering anisotropic positional uncertainty by comparing our method with respect to JRMPC [34] and HMM(Iso) [57] where the assumption of isotropic positional localization error is adopted. On the other hand, we validate the advantage of incorporating the normal vectors by comparing our method with ECMPR [36] and JRMPC [34] where only positional vectors are used in the registration.…”

Section: Methodsmentioning

confidence: 99%

“…is updated. In our previous work in [57] where the positional error is isotropic, R q j , t q j have closed-form solutions. In contrast, there is no closed-form solution of the rigid transformation matrix when the positional error is generalized to the anisotropic case.…”

Section: B M-rigid Stepmentioning

confidence: 99%

“…The main/significant differences or improvements of our presented work with our previous work [57] include the follows. Scientifically (i) The positional error distribution is assumed to be anisotropic while the normal vectors extracted from the raw point sets are utilized in the simultaneous registration of multiple point sets, whereas the isotropic positional error is assumed in our previous work; Technically (ii) Both cases where the isotropic and anisotropic positional error vectors are injected into the point sets have been tested, whereas only the case of isotropic positional error is considered in our previous work; (iii) We have explored the influences of the hyperparameters including the weight of the outlier distribution in the hybrid mixture models(HMMs) and the number of central models' components on the registration performance; (iv) We have evaluated the registration performances under different magnitudes of noise injected into normal vectors(i.e., different values of the concentration parameter κ).…”

Section: Differences/improvements Compared With Our Previous Workmentioning

confidence: 99%

“…B. The adopted multi-variate Gaussian distribution generalizes the isotropic positional error distribution in our previous work [57]. The model parameters in our algorithm are summarized as…”

Section: Problem Formulationmentioning

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: Methodsmentioning

confidence: 99%

Section: B M-rigid Stepmentioning

confidence: 99%

Section: Differences/improvements Compared With Our Previous Workmentioning

confidence: 99%

Section: Problem Formulationmentioning

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

“…. n. In particular, since we used a rigid transformation model for transformation [21], the rotation matrix (R) had to satisfy these two constraints:…”

Section: A the Robot Stereo Vision System (Rsv) For Object Detectionmentioning

confidence: 99%

A Vision-Based Path Planning and Object Tracking Framework for 6-DOF Robotic Manipulator

et al. 2020

View full text Add to dashboard Cite

Generalized Non-rigid Point Set Registration with Hybrid Mixture Models Considering Anisotropic Positional Uncertainties

Min

Liu

Meng

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Joint Rigid Registration of Multiple Generalized Point Sets With Hybrid Mixture Models

Cited by 31 publications

References 63 publications

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

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

A Vision-Based Path Planning and Object Tracking Framework for 6-DOF Robotic Manipulator

Generalized Non-rigid Point Set Registration with Hybrid Mixture Models Considering Anisotropic Positional Uncertainties

Contact Info

Product

Resources

About