Lane line extraction method and device based on crowdsourcing data and storage medium

A lane line and data technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of poor lane line extraction, high algorithm complexity, and large amount of clustering algorithm calculations, etc., to achieve guaranteed extraction , reduce the amount of calculation, and ensure accurate results

Active Publication Date: 2019-09-27
WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF8 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, it is more common to use cluster analysis to extract the lane lines of the road. By clustering multiple collected lane lines and analyzing the track points, the lane lines are extracted. This method can ex

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
  • Lane line extraction method and device based on crowdsourcing data and storage medium
  • Lane line extraction method and device based on crowdsourcing data and storage medium
  • Lane line extraction method and device based on crowdsourcing data and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] see figure 1 , a schematic flow chart of a vehicle trajectory type detection method provided in an embodiment of the present invention, including:

[0029] S101. Collect the original lane line cluster data, and obtain each lane line end point to form a point set;

[0030] The original lane line cluster data is the lane line in the crowdsourcing data, the lane line is preprocessed and expressed as a line segment, and a plurality of line segments form a line cluster. Obtain the two end points of the line segment corresponding to each lane line. The end points of multiple line segments form a point set. Generally, the end points are (x, y), and the set of multiple (x, y) is a point set.

[0031] S102. Calculate the main direction line segment of the point set based on the obb algorithm;

[0032] The obb (Oriented Bounding Box) algorithm is the bounding box algorithm, which is an algorithm for solving the optimal bounding space of discrete point sets. By calculating the ...

Embodiment 2

[0057] Figure 4 A schematic structural diagram of a lane line extraction device based on crowdsourcing data provided in Embodiment 2 of the present invention, including:

[0058] The collection module 410 is used to collect the original lane line cluster data, and obtain each lane line end point to form a point set;

[0059] The first calculation module 420 is used to calculate the main direction line segment of the point set based on the obb algorithm;

[0060] Optionally, the first calculation module 420 includes:

[0061] A first calculation unit, used to calculate the covariance matrix, eigenvalue and eigenvector set of the point set respectively;

[0062] An acquisition unit, configured to acquire the eigenvector corresponding to the maximum eigenvalue of the point set, and obtain the slope of the line segment in the main direction;

[0063] The second calculation unit is used to calculate the bounding box edges of all points based on the obb bounding box according to...

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 extraction method and device based on crowdsourcing data and a storage medium, and belongs to the field of automatic driving. The method comprises the following steps: collecting original lane line cluster data, and obtaining an end point of each lane line to form a point set; calculating a main direction line segment of the point set based on an obb algorithm; equally dividing the main direction line segment according to a certain length interval, and establishing a vertical line segment of a main direction line segment equal division point; when a plurality of intersection points exist between any vertical line segment on the equipartition point and the lane line cluster, solving the median of the plurality of intersection points, and marking the position corresponding to the median as an effective point; and compressing the ordered shape point string formed by all the effective points to obtain a representative lane line of the lane line cluster. Through the scheme, the representative lane lines can be quickly and accurately extracted from the crowdsourcing lane line cluster data, the calculated amount is reduced, and the extraction process is simplified.

Description

technical field [0001] The present invention relates to the field of automatic driving, in particular to a lane line extraction method, device and storage medium based on crowdsourcing data. Background technique [0002] In the process of making high-precision maps, the collection of crowdsourcing data is often involved. Since the crowdsourcing data is collected by multiple vehicles, the collection equipment, collection lines, and angles are different, resulting in large differences in the actual lane lines. In order to make road maps accurately, it is necessary to optimize the lane line clusters and reasonably extract the lane lines. Lines represent clusters of lane lines. [0003] At present, it is more common to use cluster analysis to extract the lane lines of the road. By clustering multiple collected lane lines and analyzing the track points, the lane lines are extracted. This method can extract lane lines more accurately, but using clustering The calculation amount ...

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): G06K9/00
CPCG06V20/588
Inventor 胡丹丹尹玉成石涤文罗跃军
Owner WUHAN ZHONGHAITING DATA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap