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

A lane line drawing method, device and storage medium

A lane line and data technology, applied in the computer field, can solve the problems of high requirements for point cloud data processing of acquisition equipment, high cost of lane line drawing, and errors, etc., to reduce data collection costs, reduce data accuracy requirements, and ensure accurate data. Effect

Active Publication Date: 2021-05-18
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] If the lane lines are drawn directly by hand, not only the efficiency is low, but also there are errors. However, the acquisition of high-precision point clouds by surveying and mapping vehicles and the extraction of lane lines from high-precision point cloud data can guarantee the accuracy of lane lines, but the acquisition equipment And point cloud data processing requirements are high, resulting in high cost of lane line drawing

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 lane line drawing method, device and storage medium
  • A lane line drawing method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] see figure 1 , a schematic flowchart of a lane line drawing method provided in an embodiment of the present invention, including:

[0027] S101. Collect lane line data, where the lane line data includes lane line images, GPS data, inertial measurement data, and mileage data;

[0028] The lane line image is a lane image captured by a vehicle-mounted camera, and the lane contains clearly identifiable lane lines. The inertial measurement data is the measurement data in the IMU (Inertial Measurement Unit, Inertial Measurement Unit), which can obtain vehicle roll, pitch and yaw data, and at the same time facilitate the extraction of vehicle speed and acceleration. The mileage data is the vehicle body odometer measurement data . The lane line images, GPS data, inertial measurement data, and mileage data can all be collected by cheap equipment or sensors, and there is no high requirement for data measurement accuracy.

[0029] Further, collect the lane line image, the inert...

Embodiment 2

[0051] figure 2 A schematic structural diagram of a lane drawing device provided in Embodiment 2 of the present invention, including:

[0052] A collection module 210, configured to collect lane marking data, the lane marking data including lane marking images, GPS data, inertial measurement data and mileage data;

[0053] Optionally, the collection of lane line data also includes:

[0054] Collecting the lane line image, the inertial measurement data, and the mileage data, and adding a time stamp based on the GPS data collection time to the lane line image, the inertial measurement data, and the mileage data.

[0055] The extraction module 220 is used to detect the lane line image based on deep learning to extract the lane line, and calculate the three-dimensional scatter point of the lane line in the camera coordinate system;

[0056] Optionally, the calculation of the three-dimensional scatter points of the lane line in the camera coordinate system is specifically:

[0...

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 lane line drawing method, device and storage medium, belonging to the technical field of computers. The method includes: collecting lane line data; extracting lane lines based on deep learning, and calculating the three-dimensional scatter points of the lane lines in the camera coordinate system; calculating the relative pose between the lane line images according to the inertial measurement data and vehicle mileage data; The relative pose between the lane line images, splicing three-dimensional scattered points to obtain lane lines, and associating the spliced ​​lane lines with corresponding GPS positions; clustering the spliced ​​lane lines, and fitting the clustered lane lines . Through this scheme, the cost of crowdsourcing data collection can be reduced under the premise of ensuring the accuracy of lane line drawing.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a lane line drawing method, device and storage medium. Background technique [0002] In the field of autonomous driving, in order to accurately control vehicles and provide reliable reference for vehicle trajectory planning, it is often necessary to draw high-precision maps. High-precision map drawing needs to be accurate to the lane line level, and when making maps, drawing based on crowdsourcing data requires high data accuracy. [0003] If the lane lines are drawn directly by hand, not only the efficiency is low, but also there are errors. However, the acquisition of high-precision point clouds by surveying and mapping vehicles and the extraction of lane lines from high-precision point cloud data can guarantee the accuracy of lane lines, but the acquisition equipment And point cloud data processing requirements are high, resulting in high cost of lane line drawing. ...

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): G01C21/32G01S19/45G01S19/47
CPCG01C21/32G01S19/45G01S19/47
Inventor 胡铮铭白海江杨贵陶靖琦刘奋
Owner WUHAN ZHONGHAITING DATA TECH CO LTD