Convex hull indexed Gaussian mixture model (CH-GMM) for 3D point set registration

Fan, Jingfan; Yang, Jian; Ai, Danni; Xia, Likun; Zhao, Yitian; Gao, Xing; Wang, Yongtian

doi:10.1016/j.patcog.2016.02.023

Cited by 44 publications

(12 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Georgios et al [36] introduce a motion drift idea into the GMM framework and achieve good results on rigid and non-rigid point set registration. [37] extracts the convex hull and uses GMM to estimate the transformation matrix on these convex sets of a point set. [38] proposes a joint registration of a multiple point cloud (JR-MPC) solution to GMM-based approach by recasting registration as a clustering problem.…”

Section: Registration: Transformed Methodsmentioning

confidence: 99%

“…[38] proposes a joint registration of a multiple point cloud (JR-MPC) solution to GMM-based approach by recasting registration as a clustering problem. In the previous GMM-based registration methods [36], [35], [37], they estimate one GMM using one point clouds or two GMMs using two point clouds. This makes the reasonable assumption that points from one set are normally distributed around points belonging to the other set.…”

Section: Registration: Transformed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Coarse-to-Fine Algorithm for Matching and Registration in 3D Cross-Source Point Clouds

Huang

Zhang

et al. 2018

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We propose an efficient method to deal with the matching and registration problem found in cross-source point clouds captured by different types of sensors. This task is especially challenging due to the presence of density variation, scale difference, a large proportion of noise and outliers, missing data and viewpoint variation. The proposed method has two stages: in the coarse matching stage, we use the ESF descriptor to select potential K regions from the candidate point clouds for the target. In the fine stage, we propose a scale embedded generative GMM registration method to refine the results from the coarse matching stage. Following the fine stage, both the best region and accurate camera pose relationships between the candidates and target are found. We conduct experiments in which we apply the method to two applications: one is 3D object detection and localization in street-view ourdoor (LiDAR/VSFM) cross-source point clouds, and the other is 3D scene matching and registration in indoor (KinectFusion/VSFM) cross-source point clouds. The experiment results show that the proposed method performs well when compared with the existing methods. It also shows that the proposed method is robust under various sensing techniques such as LiDAR, Kinect and RGB camera.

show abstract

Section: Registration: Transformed Methodsmentioning

confidence: 99%

Section: Registration: Transformed Methodsmentioning

confidence: 99%

A Coarse-to-Fine Algorithm for Matching and Registration in 3D Cross-Source Point Clouds

Huang

Zhang

et al. 2018

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…The optimization based deformable registration methods can be divided into two categories (Oliveira and Tavares, 2014; Sotiras et al, 2013): intensity-based (Johnson and Christensen, 2002; Klein et al, 2010; Myronenko and Song, 2010; Tang et al, 2018, 2019; Vercauteren et al, 2009) and feature-based (Auzias et al, 2011; Avants et al, 2008; Ou et al, 2011; Shen and Davatzikos, 2002; Wu et al, 2014, 2010). The deformable registration is often based on linear (rigid/affine) registration (Fan et al, 2016a,b 2017), where the linear registration intends to globally align the two images and the deformation registration is used to correct the local deformations. But unlike linear registration, deformable registration is an often ill-posed high-dimensional optimization problem.…”

Section: Related Workmentioning

confidence: 99%

BIRNet: Brain image registration using dual-supervised fully convolutional networks

Fan

Cao

Yap

et al. 2019

Medical Image Analysis

Self Cite

245

146

View full text Add to dashboard Cite

In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Coarse guidance using deformation fields obtained by an existing registration method; and (2) Fine guidance using image similarity. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.

show abstract

“…In general, the Expectation-maximization (EM) algorithm [26] is applied to estimate GMM parameters. Because of its powerful capability, GMM serves in several fields extensively, such as rigid and non-rigid point set registration [29,28,7], compressive sensing [50], speech recognition [34], model denoising [24], model reconstruction [35] and skeleton learning [22,23]. For instance, Preiner et al [35] proposed a hierarchical EM algorithm to quickly reduce the number of model points, preserving the utmost details.…”

Section: Gaussian Mixture Modelmentioning

confidence: 99%

A Robust Scheme for 3D Point Cloud Copy Detection

Yang,

Lu,

Chen

2021

Preprint

View full text Add to dashboard Cite

Most existing 3D geometry copy detection research focused on 3D watermarking, which first embeds "watermarks" and then detects the added watermarks. However, this kind of methods is nonstraightforward and may be less robust to attacks such as cropping and noise. In this paper, we focus on a fundamental and practical research problem: judging whether a point cloud is plagiarized or copied to another point cloud in the presence of several manipulations (e.g., similarity transformation, smoothing). We propose a novel method to address this critical problem. Our key idea is first to align the two point clouds and then calculate their similarity distance. We design three different measures to compute the similarity. We also introduce two strategies to speed up our method. Comprehensive experiments and comparisons demonstrate the effectiveness and robustness of our method in estimating the similarity of two given 3D point clouds.

show abstract

Convex hull indexed Gaussian mixture model (CH-GMM) for 3D point set registration

Cited by 44 publications

References 49 publications

A Coarse-to-Fine Algorithm for Matching and Registration in 3D Cross-Source Point Clouds

A Coarse-to-Fine Algorithm for Matching and Registration in 3D Cross-Source Point Clouds

BIRNet: Brain image registration using dual-supervised fully convolutional networks

A Robust Scheme for 3D Point Cloud Copy Detection

Contact Info

Product

Resources

About