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

Method and device for detecting lane line

A technology of lane lines and lanes, applied in the computer field, can solve the problems of false detection of double yellow lines, inability to distinguish between single straight lines and double yellow lines, and low detection accuracy.

Active Publication Date: 2016-03-23
WUHU LION AUTOMOTIVE TECH CO LTD
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above method can be used to detect single-lane lines. However, for adjacent double-yellow lines, since it is impossible to distinguish between single-line and double-yellow lines, there will be false detection when detecting double-yellow lines, resulting in low detection accuracy.

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
  • Method and device for detecting lane line
  • Method and device for detecting lane line
  • Method and device for detecting lane line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] figure 1 It is a flow chart of a method for detecting lane lines provided by an embodiment of the present invention, see figure 1 , the method includes:

[0068] Step 101: Obtain a first grayscale region of interest from the color image of the road ahead of the vehicle, and obtain the grayscale segmentation threshold of each row of pixels included in the first grayscale region of interest.

[0069] Step 102: Perform image edge enhancement and binarization processing on the first gray-scale region of interest to obtain a second gray-scale region of interest.

[0070] Step 103: According to the grayscale segmentation threshold of each row of pixels and the edge feature point extraction algorithm, extract the edge feature points of the lane line included in the second grayscale area of ​​interest.

[0071] This step can be achieved through the following steps (1) to (4), including:

[0072] (1): Determine the first set of pixels from the first grayscale region of intere...

Embodiment 2

[0095] figure 2 It is a flow chart of a method for detecting lane lines provided by an embodiment of the present invention, and the execution body of the method may be a vehicle-mounted terminal of a vehicle. see figure 2 , the method includes:

[0096] Step 201: Obtain a first grayscale region of interest from a color image of the road ahead of the vehicle.

[0097] In this step, the color image of the road ahead of the vehicle can be converted into a grayscale image, and the first grayscale region of interest can be obtained from the grayscale image, that is, the following first implementation; it can also be obtained from the color image of the road ahead of the vehicle The first color region of interest is obtained from the image, and then the first color region of interest is converted into the first grayscale region of interest, which is the second implementation manner below.

[0098] For the first implementation, this step can be:

[0099] Collect a color image o...

Embodiment 3

[0173] An embodiment of the present invention provides a device for detecting lane lines, see image 3 , where the device includes:

[0174] An acquisition module 301, configured to acquire a first grayscale region of interest from the color image of the road ahead of the vehicle, and obtain the grayscale segmentation threshold of each row of pixels included in the first grayscale region of interest;

[0175] A processing module 302, configured to respectively perform image edge enhancement and binarization processing on the first gray-scale region of interest to obtain a second gray-scale region of interest;

[0176] The extraction module 303 is used to extract the edge feature points of the lane lines included in the second gray-scale area of ​​interest according to the gray-scale segmentation threshold of each row of pixels and the edge feature point extraction algorithm;

[0177] The first determination module 304 is used to determine whether the lane line is a double yel...

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 discloses a method and device for detecting a lane line, and belongs to the field of computers. The method comprises the following steps: acquiring a first interested gray region from a color image of an ahead road of a vehicle, and acquiring a gray-level segmentation threshold value of pixels per line included in the first interested gray region; respectively performing image edge enhancement and binarization processing on the first interested gray region, and obtaining a second interested gray region; exacting an edge feature point of a lane line included in the second interested gray region according to the ray-level segmentation threshold value of pixels per line and an edge feature point extraction algorithm; determining whether the lane line is a double amber line or a single line according to the edge feature point of the lane line; if the lane line is the double amber line, then fitting a virtual inner side lane line of the double amber line according to the edge feature point of the lane line; determining whether the virtual inner side lane line satisfies a preset lane condition; and if the virtual inner side lane line satisfies the preset lane condition, then determining the virtual inner side lane line as the an inner side lane line of the first interested gray region.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method and device for detecting lane lines. Background technique [0002] With the development of traffic and the improvement of automobile performance, the driving speed of automobiles is correspondingly accelerated. Therefore, people pay more and more attention to the driving safety of automobiles. In many traffic accidents, the accident caused by lane departure is an important part. Therefore, in order to ensure the driving safety of the car, it is necessary to detect the lane line on the road in front of the vehicle during driving. If the vehicle deviates from the lane line, timely Remind the driver to make adjustments to reduce the occurrence of traffic accidents. [0003] The current method for detecting lane lines can be as follows: obtain the region of interest from the grayscale image of the road ahead of the vehicle; construct at least one image matrix according to the regio...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/588
Inventor 王继贞张绍勇方啸
Owner WUHU LION AUTOMOTIVE TECH CO LTD