Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method for Extracting Planes from LiDAR 3D Point Cloud Data

A technology of lidar and 3D point cloud, applied in the field of artificial intelligence

Active Publication Date: 2022-04-12
苏州寻迹智行机器人技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, if it is necessary to extract surface information from the plane obtained by using 3D Hough transform, additional operations are required

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
  • A Method for Extracting Planes from LiDAR 3D Point Cloud Data
  • A Method for Extracting Planes from LiDAR 3D Point Cloud Data
  • A Method for Extracting Planes from LiDAR 3D Point Cloud Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The present invention will be further described below in conjunction with drawings and embodiments.

[0017] The method for extracting a plane from the three-dimensional point cloud data of the laser radar in the present invention takes the surrounding environment scanned by the multi-line laser radar as an example, and includes the following steps.

[0018] (1) Extract straight lines from the (2D) laser data for each plane

[0019] S1. Layer the 3D point cloud data obtained by multi-line lidar scanning. Each layer contains a set of 2D point cloud data representing a plane. The set of 2D point cloud data is generated by the lidar at a fixed angle h obtained by performing a measurement. In the 3D multi-line lidar, each layer will obtain a set of 2D data. This set of 2D data is generally obtained by measuring every other small angle. This small angle is the (plane) angular resolution, denoted as δ h , representing δ horitonal . For a typical 3D multi-line radar, Su...

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 belongs to the technical field of artificial intelligence, and specifically discloses a method for extracting a plane from three-dimensional point cloud data of laser radar, including steps: S1, layering the 3D point cloud data obtained by multi-line laser radar scanning; S2, from Extract the straight line from the 2D point cloud data of each plane; S3, extract the candidate of the plane from the plane straight line set obtained from all the planes; S4, according to the straight line endpoints of each group of plane straight line set, use the least square method to solve the plane equation, extract Planes in 3D point cloud data. This method can extract straight lines from each layer of 2D laser data more quickly, and can use all straight lines in each layer to extract 3D planes, which has the advantages of high efficiency and does not require any prior knowledge about the actual terrain. The 3D plane acquired by the invention can be used to correct single laser data falling in the plane, thereby greatly reducing the fluctuation of single laser data and improving the reliability of laser data.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method for extracting planes from 3D data of laser radars. The precision of the data for the device. The typical feature of the 3D laser data acquired by the multi-line lidar is that a frame of 3D data is actually a combination of multiple sets of 2D laser data with different pitch angles. Background technique [0002] At present, due to the high cost of 3D laser radar, there are relatively few technical materials on 3D laser radar data preprocessing, and more are 3D laser data processing technologies. Although the existing 3D data processing technology can extract the features in the data, these features often refer to 3D objects, that is, these features not only include the geometric information of the actual object, but also give the actual meaning of the object, such as extracting A car, a house, a pedestrian, etc. Although these very powerful...

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): G01S7/48
CPCG01S7/48
Inventor 王远鹏张二阳葛凯
Owner 苏州寻迹智行机器人技术有限公司