ICP with Bounded Scale for Registration of M-D Point Sets

Du, Shaoyi; Zheng, Nanning; Ying, Shihui; Wei, Jishang

doi:10.1109/icme.2007.4284894

Cited by 22 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One simple way is to match the transformed shapes by trying all such possible transformations, while a more efficient method is to use high-order moments, such as third-order moments. With , the initial affine transformation can be easily estimated as (12) Therefore, we estimate the initial translation vector (13) …”

Section: Initial Parameters Estimation Using Icamentioning

confidence: 99%

“…We use some shapes of Part B of CE-Shape-1 which is a large 2-D shapes database, and then extract the edges of 2-D shapes as point sets. We further perform the experiments on Bunny (bun_zipper with 35 947 points and bun_zipper_res2 with 1 http://graphics.stanford.edu/data/3Dscanrep/ (12) and (13) to estimate the initial parameters of our algorithm. The RMS of the compared results is shown in Table I.…”

Section: A Rigid Registrationmentioning

confidence: 99%

See 1 more Smart Citation

Affine Registration of Point Sets Using ICP and ICA

Zheng

Meng

et al. 2008

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

This letter proposes a novel algorithm for affine registration of point sets in the way of incorporating an affine transformation into the iterative closest point (ICP) algorithm. At each iterative step of this algorithm, a closed-form solution of the affine transformation is derived. Similar to the ICP algorithm, this new algorithm converges monotonically to a local minimum from any given initial parameters. To get the best affine registration result, good initial parameters are required which are successfully estimated by using independent component analysis (ICA). Experimental results demonstrate the robustness and high accuracy of this algorithm.Index Terms-Affine registration, independent component analysis (ICA), iterative closest point (ICP).

show abstract

Section: Initial Parameters Estimation Using Icamentioning

confidence: 99%

Section: A Rigid Registrationmentioning

confidence: 99%

Affine Registration of Point Sets Using ICP and ICA

Zheng

Meng

et al. 2008

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

show abstract

“…Generally, the original ICP can only deal with models with the same scale. To account for the scale problem, Du et al proposed an extension of the ICP algorithm, called the Iterative Closest Points with Bounded Scale (ICPBS) algorithm, which integrated a scale parameter with boundaries into the original one [6], but it's unclear how to determine the upper and lower boundaries of scales that contain the optimal scale.…”

Section: Icp-based Registrationmentioning

confidence: 99%

Automatic 3D Facial Model and Texture Reconstruction from Range Scans

Xiang

Holt

2010

Articulated Motion and Deformable Objects

View full text Add to dashboard Cite

Abstract. This paper presents a fully automatic approach to fitting a generic facial model to detailed range scans of human faces to reconstruct 3D facial models and textures with no manual intervention (such as specifying landmarks). A Scaling Iterative Closest Points (SICP) algorithm is introduced to compute the optimal rigid registrations between the generic model and the range scans with different sizes. And then a new template-fitting method, formulated in an optmization framework of minimizing the physically based elastic energy derived from thin shells, faithfully reconstructs the surfaces and the textures from the range scans and yields dense point correspondences across the reconstructed facial models. Finally, we demonstrate a facial expression transfer method to clone facial expressions from the generic model onto the reconstructed facial models by using the deformation transfer technique.

show abstract

“…To overcome this shortage, many researchers have extended the original ICP algorithm to scale registration. Du et al [3] proposed the ICP with a bounded scale algorithm for isotropic scale registration with few outliers. Zhu et al [4] further extended the algorithm for anisotropic scale registration.…”

mentioning

confidence: 99%

“…Step 3: Compute the scale transformation by minimising the following function: Steps 1 and 3 can be solved like [3,4]. For (5) or (6) of step 2, we sort the squared distances of {(s k−1 R k−1 p i + t k−1 , m ck (i) )} we add a paired point to the subset P r and compute the corresponding value of f (r).…”

mentioning

confidence: 99%