Method and device for detecting lane line

A lane line detection and lane line technology, which is applied in the field of image processing, can solve the problems of reducing the accuracy of straight lane detection and increasing the calculation amount of straight lane detection.

Active Publication Date: 2016-01-20
NETPOSA TECH
View PDF5 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, there will be a large number of interference points (ie non-lane edge points) in the lane edge points after the lane image is binarized by the Canny edge detection a

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

[0074] see figure 2 , the present embodiment provides a lane line detection method, the method includes the following steps:

[0075] Step 200, the lane line detection device performs binarization processing on the lane image to be detected to obtain a binarized lane image.

[0076] When the vehicle starts to drive, the lane line detection equipment starts up and starts to detect the lane lines. The lane line detection equipment obtains the lane image of the current frame captured by the camera or video recorder pre-installed on the vehicle while the vehicle is running, to obtain The detected lane image of the current frame is used as the detected lane image; and then the lane image to be detected is binarized to obtain a binarized lane image.

[0077] The lane line detection equipment can be installed on the vehicle alone, or it can be integrated with a driving recorder or a car navigator to detect the lane lines of the driving vehicle.

[0078] The lane image is the image...

Embodiment 2

[0168] The technical solution relates to a lane detection method. The lane detection algorithm provided in this embodiment is mainly divided into two steps: 1) lane detection; 2) lane tracking. Specific steps are as follows:

[0169] 1. Lane detection

[0170] see image 3 , the lane line detection proposed in this embodiment is mainly divided into five steps: selecting a target processing area; binarization; filtering interference points; straight line detection and screening of straight lines. The five steps are described below:

[0171] 1) Target treatment area

[0172] It is mainly determined based on the image horizon, and the area below the horizon is selected as the target processing area (the horizon is the disappearing line, the horizon can be determined after the camera is installed and fixed, and the area above the horizon is invalid, so the area below the horizon is selected as the lane line target processing area).

[0173] 2) Binarization

[0174] Use the so...

Embodiment 3

[0208] see Figure 5 , this embodiment provides a lane line detection device for performing the lane line detection method described in the above embodiment, the device includes: a binarization processing module 500, a lane initial edge point extraction module 502, a lane edge point pair determination Module 504 and lane line detection module 506;

[0209] The binarization processing module 500 is used to perform binarization processing on the lane image to be detected to obtain a binarized lane image;

[0210] The lane initial edge point extraction module 502 is connected with the binarization processing module 500, and is used to extract the lane initial edge point in the binarized lane image, and determines two lane line initial edge points corresponding to each other according to the coordinates of the lane initial edge point the distance between;

[0211] The lane edge point pair determination module 504 is connected with the lane initial edge point extraction module 50...

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 provides a method and a device for detecting a lane line. The method comprises the steps of carrying out binarization processing on a lane image to be detected so as to acquire a binarized lane image; extracting lane initial edge points in the binarized lane image, and determining the distance between two mutually corresponding lane initial edge points according to coordinates of the lane initial edge points; screening out lane edge point pairs of the binarized lane image from the lane initial edge points according to the determined distance; and determining a lane line in the lane image to be detected according to the screened lane edge point pairs. Through the method and the device provided by the invention, interference points in the binarized image can be filtered, and influences imposed on subsequent lane line detection by the interference points are reduced.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a lane line detection method and device. Background technique [0002] At present, a car sometimes deviates from its own driving lane and enters an adjacent lane during driving, which affects the normal driving cars in the adjacent lane and may cause traffic accidents. The driving lane will detect the lane where the car is in the process of driving, so as to give an alarm when the car deviates from the lane, so as to ensure the driving safety of the car. [0003] The processing steps of the existing lane detection method include: acquiring a lane image, binarizing the lane image through a Canny edge detection algorithm, and performing straight lane detection on the lane in the binarized lane image. [0004] However, there will be a large number of interference points (ie non-lane edge points) in the lane edge points after the lane image is binarized by the Canny edge dete...

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 石园魏磊磊许健
Owner NETPOSA TECH
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