Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Point cloud registration method based on geometric surface description of feature points

A geometric surface, point cloud registration technology, applied in the field of 3D reconstruction, can solve the problems of high computational complexity, weak anti-noise ability, poor robustness, etc., to achieve good robustness, speed up calculation, and improve registration efficiency Effect

Active Publication Date: 2021-06-22
SOUTHWEST PETROLEUM UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The main purpose of the present invention is to improve the problem of high computational complexity, poor robustness, weak anti-noise ability and poor precision of the initial algorithm of point cloud 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Point cloud registration method based on geometric surface description of feature points
  • Point cloud registration method based on geometric surface description of feature points
  • Point cloud registration method based on geometric surface description of feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] This embodiment is a point cloud registration method based on feature point geometric surface description, such as figure 1 As shown, the details are as follows:

[0051] Step 1: Collect two sets of data, the source point cloud P and the target point cloud Q, and the point cloud data is required to be obtained from different perspectives with a certain degree of overlap.

[0052]Step 2: Data downsampling based on point cloud curvature. The moving least square method surface fitting calculates the curvature of the point cloud. In order to ensure the running speed, the calculation simultaneously inserts and sorts the curvature values ​​from large to small. According to actual needs, the large curvature points are reserved by percentage, simplifying the data and speeding up the registration speed. The Gaussian curvature k is calculated by the following formula:

[0053]

[0054] Where g(x) is the minimum value of the partial derivative of the energy function e(y, a), ...

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

No PUM Login to View More

Abstract

The invention provides a point cloud registration method based on feature point geometric surface description, which belongs to the field of three-dimensional reconstruction. It first loads the source point cloud and the target point cloud, and calculates the curvature for data downsampling; then extracts all the feature points of the two point clouds through the 3D Harris detector, calculates the geometric distance between the feature points and constructs the three feature points with the closest distance. The sub-set, and then describe the target surface through the geometric transformation relationship of the sub-set; finally, calculate the rotation and translation matrix by matching the geometric surface description on the source point cloud and the target point cloud, and evaluate the registration effect by calculating the sum of the distances between the corresponding points after registration , select the optimal matrix, and complete the initial point cloud registration.

Description

technical field [0001] The invention relates to the field of three-dimensional reconstruction, in particular to a point cloud registration method based on feature point geometric surface description. Background technique [0002] Three-dimensional reconstruction (3D Reconstruction) refers to the establishment of a mathematical model suitable for computer representation and processing of three-dimensional objects, which is the basis for processing, operating and analyzing its properties in a computer environment, and is also the basis for establishing a virtual reality that expresses the objective world in a computer. key technologies. [0003] Point Cloud is a massive point collection of target surface information obtained by ranging equipment. The scanned data is recorded in the form of points, which can be three-dimensional coordinates (XYZ), color (RGB) or reflection intensity (Intensity) and other information. The commonly used point cloud data generally includes point...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/33
CPCG06T2207/10028G06T7/33
Inventor 秦大辉程栋段云飞苏铭著邵永波
Owner SOUTHWEST PETROLEUM UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products