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

Dynamic correction method for point cloud coordinates of roadside laser radar

A laser radar and dynamic correction technology, applied in the field of data processing, can solve problems such as not considering the impact, achieve the effect of low data calculation cost, fast data processing process, and improve correction accuracy

Active Publication Date: 2021-06-08
TONGJI UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This patent uses the difference in the laser radar reflection intensity of different feature points on the calibration plate to calibrate the external parameters of the sensor, and can perform external parameter calibration without performing rotation and translation operations on the camera and the laser radar, but the calibration of the sensor external parameters is Static, without considering the influence of the vibration of the lidar sensor itself on the detection results

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
  • Dynamic correction method for point cloud coordinates of roadside laser radar
  • Dynamic correction method for point cloud coordinates of roadside laser radar
  • Dynamic correction method for point cloud coordinates of roadside laser radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] The present invention provides a method for dynamically correcting point cloud coordinates of a roadside laser radar. The roadside laser radar is installed on the roadside through a pole, which includes the following steps:

[0049] S1: Set control points on the road surface as fixed feature points. Among them, the control points are feature points with stronger reflection intensity than the surrounding environment, including traffic signs, traffic markings or artificially added marker points. At the same time, each roadside lidar The scanning area includes at least 4 non-collinear control points, and the scanning area of ​​the adjacent roadside lidar includes at least 1 common control point. .

[0050] S2: Obtain the initial correction parameters of the roadside lidar.

[0051] S3: Obtain the deflection angle of the pole end of the roadside lidar installation pole, the real coordinates of fixed feature points, and the traffic scene point cloud data collected by the ro...

Embodiment 2

[0094] In this embodiment, when step (4) performs the second coordinate correction, the result after deflection correction in step (3) may not be quoted, and the rest is the same as in embodiment 1, that is, in the case of an inclination sensor failure, only through the step The secondary correction of (4) can still realize the point cloud coordinate correction function. According to the test results, the error correction conditions in different regions are different in this case, and the average error correction rate is above 70%.

[0095] Each noun in this patent is explained as follows:

[0096] Point cloud data: Point cloud data is the scanned data recorded in the form of points, and each point contains three-dimensional coordinates and reflection intensity information (Intensity).

[0097] Coordinate correction: Set up design road surface control points, and perform coordinate transformation on the phenomenon of drifting detection point cloud positioning coordinates cause...

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 relates to a dynamic correction method for point cloud coordinates of roadside laser radar, a road side laser radar is installed on a road side through a vertical rod, and the method comprises the following steps: S1, setting control points on a road surface as fixed feature points; S2, acquiring an initial correction parameter of the roadside laser radar; S3, acquiring a rod end deflection angle of a roadside laser radar mounting vertical rod, a real coordinate of a fixed feature point and traffic scene point cloud data acquired by the roadside laser radar, and performing preprocessing; S4, performing deflection correction on the roadside laser radar point cloud data according to the point cloud data, the rod end deflection angle and a deflection correction formula; and S5, according to the real coordinates of the fixed feature points, determining a mapping relation between the real coordinates of the fixed feature points and the coordinates of the point cloud data, and carrying out secondary coordinate correction on the roadside laser radar point cloud data. Compared with the prior art, the method has the advantages of high accuracy, good robustness and the like.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for dynamically correcting roadside lidar point cloud coordinates. Background technique [0002] Autonomous driving technology is one of the key projects in the current transportation field. Government departments at home and abroad and major software and hardware manufacturers are gradually increasing their efforts to provide a set of effective, safe and reliable autonomous driving solutions. Vehicle-road coordination technology uses advanced wireless communication technology to collect dynamic traffic information in the road network in a wide range of time and space in real time, and realizes real-time dynamic traffic between vehicles and vehicles and vehicles-roads on the basis of multi-source traffic data fusion. Sensing, combined with vehicle-side active safety control and road-side collaborative management, realizes a more efficient, safe, and green intelli...

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
IPC IPC(8): G01S7/497
CPCG01S7/497
Inventor 赵聪杜豫川王凤淇魏斯瑀
Owner TONGJI UNIV