Multi-attribute statistics histograms for accurate and robust pairwise registration of range images

Yang, Jiaqi; Zhang, Qian; Cao, Zhiguo

doi:10.1016/j.neucom.2017.04.015

Cited by 40 publications

(35 citation statements)

References 53 publications

(124 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further verify our pairwise registration, two criteria are employed for quantitative assessment of registration's results, i.e., the rotation error θ r and the translation error θ t which are used in [15], [34]. θ r represents error between the ground truth rotation matrix R GT and the actual matrix R A .…”

Section: Experiments Of Pairwise Registrationmentioning

confidence: 99%

“…The above feature descriptors are invariant to translation and rotation, but are still sensitive to noise [8], so it is hard to find correct correspondences by using them. In recent years, people have also put forward some local feature descriptors such as point feature histogram (PFH) [9], rotational projection statistics (RoPS) [10]- [13], signature of histogram of orientations (SHOT) [14], multi-attribute statistics histograms (MaSH) [15], local feature statistic histogram (LFSH) [16], binary shape context descriptor [17], [18], voxel-based buffer-weighted binary descriptor [19], 3D descriptor with global structural frames and local signatures of histograms [20], signature of geometric centroids descriptor [21], etc. These local feature descriptors have a certain improvement on finding correct point-to-point correspondences in noisy point clouds, and outperform global feature descriptors in pairwise registration of point clouds.…”

Section: Introduction and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds

Xiong

Biao

Wang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Aiming to problems in the pairwise registration of point clouds, such as keypoints are difficult to describe accurately, corresponding points are difficult to match accurately and convergence speed is slow due to uncertainty of initial transformation matrix, we propose a novel feature descriptor based on ratio of rotational volume to describe effectively keypoints, and on the basis of the feature descriptor, we proposed an improved coarse-to-fine registration pipeline of point clouds, in which we use coarse registration to obtain a good initial transformation matrix and then use fine registration based on a modified ICP algorithm to obtain an accurate transformation matrix. Experimental results show that our proposed feature descriptor has a good robustness to rotation, noise, scale and varying mesh resolution, less storage space and faster running speed than PFH, FPFH, SHOT and RoPS descriptors, and our improved pairwise registration pipeline is very effective to solve the problems in the pairwise registration of point clouds.

show abstract

Section: Experiments Of Pairwise Registrationmentioning

confidence: 99%

Section: Introduction and Related Workmentioning

confidence: 99%

A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds

Xiong

Biao

Wang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the strategy S1, a support radius for calculating the direction of LRA is fixed to 20 mesh resolution (hereinafter mr which is computed as the average distance between neighbor points in this paper.) with referring to [12,31], and a support radius used for eliminating sign ambiguity increases from 3 mr to 20 mr with a step of 1 mr. In the strategy S2, the support radii of calculating the direction and eliminating sign ambiguity are simultaneously increased from 3 mr to 20 mr with a step of 1 mr. (a) Tested on B3R dataset with the combination of Gaussian noise and varying mesh resolutions.…”

Section: Local Reference Axismentioning

confidence: 99%

“…In this section, we evaluate the performance of our SDASS descriptor in the application of 3D matching, and compared with the ten feature descriptors (including SI, SHOT, RoPS, TriSI, LFSH, TOLDI, SI+LMA, SHOT+LMA, LFSH+LMA and SDASS+Yang). The performance of these descriptors in 3D matching are evaluated by the percentage of correct correspondences (PCC) [31]. Specifically, we first randomly sample some key points on scene and 1000 key points on model.…”

Section: Applications To 3d Matchingmentioning

confidence: 99%

A novel SDASS descriptor for fully encoding the information of a 3D local surface

Zhao

2019

Information Sciences

View full text Add to dashboard Cite

Local feature description is a fundamental yet challenging task in 3D computer vision. This paper proposes a novel descriptor, named Statistic of Deviation Angles on Subdivided Space (SDASS), of encoding geometrical and spatial information of local surface on Local Reference Axis (LRA). In terms of encoding geometrical information, considering that surface normals, which are usually used for encoding geometrical information of local surface, are vulnerable to various nuisances (e.g., noise, varying mesh resolutions etc.), we propose a robust geometrical attribute, called Local Minimum Axis (LMA), to replace the normals for generating the geometrical feature in our SDASS descriptor. For encoding spatial information, we use two spatial features for fully encoding the spatial information of a local surface based on LRA which usually presents high overall repeatability than Local Reference Axis (LRF). Besides, an improved LRA is proposed for increasing the robustness of our SDASS to noise and varying mesh resolutions. The performance of the SDASS descriptor is rigorously tested on four popular datasets. The results show that our descriptor has a high descriptiveness and strong robustness, and its performance outperform existing algorithms by a large margin. Finally, the proposed descriptor is applied to 3D registration. The accurate result further confirms the effectiveness of our SDASS method.

show abstract

“…Although it solves the local minimum problem, it is still sensitive to the initialization. A coarse-to-fine strategy [10,11] is presented, where the coarse registration provides an initial estimation for the fine registration to obtain a precise alignment. This strategy can accurately register point clouds without initialization.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Optimization of 3D Point Cloud Registration

Liu

Zhang

Xie

et al. 2020

Sensors

View full text Add to dashboard Cite

Rigid registration of 3D point clouds is the key technology in robotics and computer vision. Most commonly, the iterative closest point (ICP) and its variants are employed for this task. These methods assume that the closest point is the corresponding point and lead to sensitivity to the outlier and initial pose, while they have poor computational efficiency due to the closest point computation. Most implementations of the ICP algorithm attempt to deal with this issue by modifying correspondence or adding coarse registration. However, this leads to sacrificing the accuracy rate or adding the algorithm complexity. This paper proposes a hierarchical optimization approach that includes improved voxel filter and Multi-Scale Voxelized Generalized-ICP (MVGICP) for 3D point cloud registration. By combining traditional voxel sampling with point density, the outlier filtering and downsample are successfully realized. Through multi-scale iteration and avoiding closest point computation, MVGICP solves the local minimum problem and optimizes the operation efficiency. The experimental results demonstrate that the proposed algorithm is superior to the current algorithms in terms of outlier filtering and registration performance.

show abstract

Multi-attribute statistics histograms for accurate and robust pairwise registration of range images

Cited by 40 publications

References 53 publications

A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds

A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds

A novel SDASS descriptor for fully encoding the information of a 3D local surface

Hierarchical Optimization of 3D Point Cloud Registration

Contact Info

Product

Resources

About