2020
DOI: 10.1109/access.2020.2995369
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: 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 re… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 15 publications
(4 citation statements)
references
References 39 publications
0
4
0
Order By: Relevance
“…The convergence accuracy of the ICP algorithm mainly depends on the ratio of overlapping regions [14,15]. Previous works stated that corresponding points were difficult to be extracted correctly if the overlapping ratio was under 50% [16,17]. Therefore, the ICP algorithm requires data to complete rough alignment in advance to avoid acquiring a less qualified initial value from the local optimization process.…”
Section: Fine Registrationmentioning
confidence: 99%
“…The convergence accuracy of the ICP algorithm mainly depends on the ratio of overlapping regions [14,15]. Previous works stated that corresponding points were difficult to be extracted correctly if the overlapping ratio was under 50% [16,17]. Therefore, the ICP algorithm requires data to complete rough alignment in advance to avoid acquiring a less qualified initial value from the local optimization process.…”
Section: Fine Registrationmentioning
confidence: 99%
“…To improve the accuracy and real-time performance of a 3D vision-based robotic arm to complete disorderly grasping, this paper incorporates some better point cloud processing algorithms to improve the algorithm processing, improve the Euclidean clustering algorithm, and fuse point cloud edge information to complete point cloud segmentation [3] to improve the accuracy of point cloud segmentation. A new set of metazoans is introduced into the FPFH to increase the accuracy of point cloud feature recognition and obtain point cloud data with high information content [4][5][6] , and then the GPD algorithm is used to obtain the 6DOF gripping coordinates of the robot arm. The gripping coordinates are then used to obtain the 6DOF gripping coordinates of the robot arm [7] .…”
Section: Introductionmentioning
confidence: 99%
“…Li et al [5] fused the SAC-IA algorithm with the improved ICP algorithm, which improved the alignment time but the accuracy of the alignment was not much different from the original ICP; Wang et al [6] proposed a point cloud alignment method based on Normal Distribution Transform (NDT) combined with ICP, which had an advantage in alignment time compared to the SAC-IA algorithm but the accuracy of the alignment was slightly worse;3.In other aspects, Drost et al [7] proposed a PPF point pair feature algorithm. Later, many researchers have improved the PPF algorithm [8][9][10][11][12], and the improvement effect of Reference [9] is the most obvious. The algorithm significantly improves the ability of point-to-point features to cope with noise by spreading features into the neighborhood.…”
Section: Introductionmentioning
confidence: 99%