Highway and urban road lane line identification method

A technology for lane line recognition and high-speed road sections, which is applied in the field of image processing, can solve problems such as difficult detection of lane lines, and achieve the effects of enhanced real-time performance, high recognition accuracy, and improved accuracy

Active Publication Date: 2017-05-31
NANJING UNIV OF SCI & TECH
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a lane line identification method for high-speed road sections and urban roads, w

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
  • Highway and urban road lane line identification method
  • Highway and urban road lane line identification method
  • Highway and urban road lane line identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] combine figure 1 , a highway segment and urban road lane line identification method, comprising the following steps:

[0055] Step 1. Obtain the road image through the camera and calculate the relevant parameters

[0056] The image coordinates obtained by the camera are (u, v), and the mapping coordinates on the road surface coordinate system are (x, y). The camera is placed at a height h from the ground, and the deflection angle is Let the coordinates of point P in the road surface coordinate system be [x, y, z] T , while the coordinates of point P in the image coordinate system are [wu,wv,w] T , the corresponding relationship is where K is the camera calibration matrix, R is the rotation matrix, I is the identity matrix, [I 3×3|-T] is the concatenation of I and T, T=[0,0,h] T , the z coordinate of the road surface in the road surface coordinate system is 0, (u c ,v c ) is the principal point position of the image coordinate plane, and f is the effective f...

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 highway and urban road lane line identification method. The highway and urban road lane line identification method comprises the following steps of: obtaining a lane image through a camera, obtaining internal and external parameters of the camera by utilizing a camera parameter self-calibration method, and obtaining a lane plane vanishing line; performing gray-scale treatment of the lane image, and dividing an interested area; performing median filtering of the image obtained in the previous step; for the median filtered image, extracting textural features of a lane line by using Gabor transformation; describing edge features of the lane line by using multi-angle Haar features, and performing classified identification by utilizing an Adaboost classifier; for a structured road, designing a hyperbola combination model; and estimating parameters of the hyperbola combination model by utilizing an improved Ransac algorithm. By means of the highway and urban road lane line identification method disclosed by the invention, the lane line detection problem in complex environments, such as shadow, abrasion of the lane line and severe weather, can be solved; and furthermore, the highway and urban road lane line identification method has better real-time performance.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a lane line recognition method for highway sections and urban roads. Background technique [0002] Lane recognition is a core part of advanced driver assistance systems. Due to the low cost of vision sensors and the ease of system construction, machine vision-based lane line detection methods are widely used. The lane detection methods based on machine vision can generally be divided into two categories: methods based on image features and methods based on model recognition. [0003] The method based on image features is mainly to recognize the gray edge in the gray image, while the method based on the model is to establish a mathematical model to represent the boundary of the lane. Model-based recognition methods are usually used on urban streets and highways. Commonly used lane line detection models include straight line models, hyperbolic models, parabol...

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 成剑沙涛
Owner NANJING UNIV OF SCI & 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

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