SAC-IA point cloud registration method based on three-dimensional shape context
A point cloud registration, three-dimensional shape technology, applied in image data processing, instruments, calculations, etc., can solve problems such as reducing registration efficiency, and achieve the effect of improving registration efficiency and high efficiency
Pending Publication Date: 2022-02-08
HEFEI UNIV OF TECH
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, although this method significantly improves the registration accuracy, it reduces the registration efficiency and is often used for initial registration.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0050] The SAC-IA point cloud registration method based on 3D shape context includes the following steps:
[0051] S1: Construct a 3D voxel grid according to the given target point cloud and source point cloud and perform downsampling filtering; create a 3D voxel grid for the input point cloud data, and then convert all points in each voxel They are all approximated by the center of gravity of the point set in the voxel, which greatly reduces the amount of data on the premise of ensuring accurate information; in order to ensure that the sampled points have different 3DSC features as much as possible, the distance between two sampling points It should be greater than the predetermined minimum distance threshold d;
[0052] S2: Calculate the 3DSC of the source point cloud and the target point cloud respectively. 3DSC is expanded on the basis of 2DSC. In 2DSC, any point p i as a reference point, at p i N concentric circles are established according to the logarithmic distance i...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an SAC-IA point cloud registration method based on a three-dimensional shape context. In the invention, a point cloud feature point extraction method based on a three-dimensional shape context (3D Shape Context) is provided. The 3Dsc is introduced into a point cloud model feature point extraction technology. Firstly, three-dimensional shape context features of a point cloud to be registered and a target point cloud are calculated, then according to the features, a rotation matrix and a translation matrix are solved through an SAC-IA algorithm, and initial registration is completed; and finally, on the basis of the initial registration, carrying out fine registration on the two point clouds by utilizing an ICP (Inductively Coupled Plasma) algorithm. Experimental results show that the method can effectively extract the point cloud feature points, the registration precision of the method is significantly superior to that of a point cloud feature point extraction method based on a fast point feature histogram (FPFH), and the registration efficiency is also improved.
Description
technical field [0001] The invention belongs to the technical field of registration algorithms, in particular to a SAC-IA point cloud registration method based on a three-dimensional shape context. Background technique [0002] The iterative closest point (ICP) algorithm proposed by Besl et al. is currently the most classic point cloud fine registration algorithm, but this algorithm has high requirements for the initial position of the point cloud, otherwise it is easy to fall into local optimum, and the convergence speed is slow. slow problem. Many scholars have improved and innovated the algorithm, and put forward some new algorithms. Rusu et al] proposed a fast point feature histogram feature based on point cloud, and a method of initial registration using sampling consistency. [0003] However, although this method significantly improves the registration accuracy, it reduces the registration efficiency and is often used for initial registration. [0004] Therefore, th...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/33
CPCG06T7/344G06T2207/10028G06T2207/20016
Inventor 张勇葛家顺
Owner HEFEI UNIV OF TECH