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

Track point and traffic sign position optimization method and system

A technology of traffic signs and trajectory points, which is applied in structured data retrieval, special data processing applications, road network navigators, etc., can solve the problem of reducing the accuracy of high-precision map data, and achieve improved accuracy, reduced time consumption and calculation amount. , easy to create updated effects

Pending Publication Date: 2020-04-10
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a method and system for optimizing the location of track points and traffic signs, which is used to solve the problem of the decrease in the accuracy of high-precision map data when the amount of collected data does not meet the requirements

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
  • Track point and traffic sign position optimization method and system
  • Track point and traffic sign position optimization method and system
  • Track point and traffic sign position optimization method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] In the process of making high-precision maps for autonomous driving, traditional high-precision surveying and mapping equipment collects high-precision map raw data for centralized composition of production line tools. Distributed big data composition by means of packet collection vehicles can effectively reduce costs, but due to the existence of a large amount of low-precision crowdsourcing data, it is necessary to effectively improve key points such as trajectory points and traffic signs in crowdsourcing data without increasing hardware costs. The accuracy of map parameters, while reducing the requirements for the amount of data collected.

[0021] see figure 1 , a schematic flowchart of a method for optimizing the location of track points and traffic signs provided by an embodiment of the present invention, including:

[0022] S101. Perform preprocessing on trajectory data and traffic sign data in the crowdsourced collection source data, and remove noise in the traj...

Embodiment 2

[0065] image 3 A schematic structural diagram of a track point and traffic sign position optimization system provided in Embodiment 2 of the present invention, including:

[0066] The preprocessing module 310 is used to preprocess the track data and traffic sign data in the crowdsourced collection source data, and remove the noise in the track data and traffic sign data;

[0067] The trajectory point optimization module 320 is used to optimize the trajectory point position in the trajectory data by establishing a graph optimization model of the trajectory point based on the trajectory point motion law and observation value;

[0068] Optionally, the removal of noise in the track data and traffic sign data includes:

[0069] Carrying out zero-value processing on track points with less than a predetermined speed in the crowdsourcing data, performing normalization processing on track points collected at less than a predetermined time interval, and filtering out high frequencies ...

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 track point and traffic sign position optimization method and system, and belongs to the field of automatic driving. The method comprises the steps of: preprocessing track data and traffic sign data in crowdsourcing collection source data, and removing noise in the track data and the traffic sign data; optimizing the positions of track points in the track data by establishing a graph optimization model of the track points on the basis of track point movement law and observation values; and acquiring observation data of the track points in the track data to traffic signs, and based on the optimized track point positions, establishing a graph optimization model through a BA algorithm to optimize the traffic sign positions in the traffic sign data. According to thescheme, relatively low-precision track points and traffic sign positions acquired based on crowdsourcing low-cost equipment can be efficiently and accurately optimized integrally, the data precision of a high-precision map in a crowdsourcing low-cost acquisition mode can be improved, and the precision of the high-precision map is guaranteed when the acquired data volume is insufficient.

Description

technical field [0001] The invention relates to the field of automatic driving, in particular to a method and system for optimizing the positions of track points and traffic signs. Background technique [0002] In autonomous driving, the production of high-precision maps is a time-consuming and costly engineering task. Traditional map production methods have been difficult to meet the driving needs of modern high-precision maps. In the big data environment, using low-cost hardware for crowdsourcing collection to generate high-precision maps can better match the cost requirements of high-precision maps, but many low-cost crowdsourcing data cannot meet the requirements of autonomous driving. High-precision map accuracy requirements. [0003] Aiming at the problem that the crowdsourcing data is complex and the accuracy is difficult to meet the requirements, the method of calculating the density distribution of a large number of low-cost crowdsourcing data to approximate the tr...

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): G01C21/32G06F16/29
CPCG01C21/32G06F16/29
Inventor 尹玉成赵彦植朱紫威刘奋
Owner WUHAN ZHONGHAITING DATA TECH CO LTD