Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Robust Lane Line Detection Method Based on Dynamic Region of Interest

A lane line detection and area of ​​interest technology, applied in the field of intelligent driving and ADAS intelligent assisted driving system, can solve problems such as low visibility, low robustness, and poor real-time performance, so as to improve accuracy, solve "shake, reduce required effect

Active Publication Date: 2022-06-24
HUIZHOU DESAY SV AUTOMOTIVE
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for lane line detection under complex conditions such as low visibility at night, shadows, lights, and obstacles, it still has low robustness and poor real-time performance.

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
  • Robust Lane Line Detection Method Based on Dynamic Region of Interest
  • Robust Lane Line Detection Method Based on Dynamic Region of Interest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A robust lane line detection method based on dynamic region of interest, such as figure 1 shown. attached figure 1 An overall flow of the present invention is introduced, including the following steps:

[0052] S10: Obtain the image data of the current frame to be recognized, and initialize the area of ​​interest of the lane. During the initialization process, the area of ​​interest of the lane line is initialized, and the initial detection area of ​​the image preprocessing is based on the width of the lane line, the solid line of the lane line, and the dotted line. The type and the distribution characteristics of the straight line and curve of the lane line are determined.

[0053] S20, such as figure 2 As shown, in order to more accurately identify the dynamic region of interest, the region of interest of the lane line in the current frame is firstly divided into connected first region DROI1, second region DROI2 and third region DROI3 from near to far. Understand...

Embodiment 2

[0077] As the optimization of Embodiment 1, the difference between this embodiment and Embodiment 1 is that in order to perform accuracy authentication on the calculated lane lines, this embodiment further includes the following sub-steps before executing step S40: judging the solved lane lines, Whether the mean value of the vanishing point and the radius of the curve meets all the following conditions, if the conditions are met, the relevant parameters are output and Kalman filter prediction calculation is performed;

[0078] Specific conditions include:

[0079] 1) In the fitting lane line, determine whether the slope product of the fitted straight lines on both sides of the lane is less than 0, and determine whether the fitted lane line conforms to a typical trapezoid shape. lane line characteristics.

[0080] 2) The width difference between the calculated lane width and the actual lane width is smaller than the first threshold. Preferably, in this embodiment, the first t...

Embodiment 3

[0083] As the optimization of Embodiment 1, the difference between this embodiment and Embodiment 2 is that: in order to prevent the painted lane lines from being "flipped" or obviously not fitting the actual lane lines, in this implementation, in step S30, in the painting simulation Before merging lanes, it also includes verification steps:

[0084] S321, judge whether the distance between the vanishing point of the predicted next frame and the vanishing point of the current frame is less than the fourth threshold, if so, execute step S322, otherwise output the result but do not execute the lane line drawing step;

[0085] S322: Determine whether the average value of the radius of curvature of the current frame is greater than the fifth threshold, if so, output the result and execute the lane line drawing step, otherwise output the result but not execute the lane line drawing step.

[0086] Wherein, the fourth threshold is determined according to the pixel distance of the ima...

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 present invention relates to a robust lane line detection method based on a dynamic region of interest, comprising the following steps: S10, initializing the dynamic region of interest of the lane; S20, dividing the region of interest of the lane line in the current frame from near to far into a straight line recognition area and a curve recognition area; S30, perform pre-extraction of lane line edge feature points for the straight line recognition area and curve recognition area, and then obtain straight line lane parameters in the straight line recognition area and curved lanes in the curve recognition area through a fitting algorithm Parameters, draw the fitted lane line; S40, according to the fitted lane line parameters of the current frame, use Kalman filter to predict the dynamic region of interest DROI in the image of the next frame. The present invention is based on DROI, adopts RANSAC algorithm, can effectively extract the inner edge information of the lane line under complex working conditions, and the anti-interference and accuracy of the method have obvious improvement and improvement; at the same time, Kalman prediction and inter-frame correlation are used constraints for real-time, robust lane line tracking.

Description

technical field [0001] The invention relates to the field of intelligent driving and ADAS intelligent assisted driving systems, in particular to a robust lane line detection method based on a dynamic region of interest. Background technique [0002] The rapid development of Intelligent Transportation System (ITS) and Advanced Driver Assistance System (ADAS) provides an important guarantee for the driving safety of drivers. As a key technology in ADAS system, lane line detection plays an indispensable role in assisting driving safety, which has attracted domestic and foreign scholars to conduct in-depth research on it. However, for lane line detection under complex conditions such as low visibility at night, shadows, lights, and obstacle interference, there are still problems such as low robustness and poor real-time performance. [0003] Therefore, a fast and robust lane line detection method is proposed, which will help improve the driving safety of drivers and passengers ...

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 Patents(China)
IPC IPC(8): G06V20/58G06V10/44
CPCG06V20/588G06V10/44
Inventor 胡坤福罗作煌
Owner HUIZHOU DESAY SV AUTOMOTIVE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com