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

Robust lane 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 the problems of low robustness, poor real-time performance, low visibility, etc., to improve algorithm accuracy, reduce requirements, and robustness The effect of tracking

Active Publication Date: 2019-03-01
HUIZHOU DESAY SV AUTOMOTIVE
View PDF4 Cites 18 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 detection method based on dynamic region of interest
  • Robust lane 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 regions of interest, such as figure 1 shown. attached figure 1 Introduce an overall flow process of the present invention, comprising the following steps:

[0052] S10. Obtain the image data to be recognized in the current frame, and initialize the area of ​​interest of the lane. During the initialization process, during the initialization of the area of ​​interest of the lane line, the initial detection area of ​​the image preprocessing is based on the line width of the lane line, the solid line of the lane line, and the dashed 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 identify dynamic ROIs more accurately, firstly, the ROI of the lane line in the current frame is divided into connected first area DROI1 , second area DROI2 and third area DROI3 from near to far. It can be understood that,...

Embodiment 2

[0077] As an optimization of embodiment 1, the difference between this embodiment and embodiment 1 is that in order to verify the accuracy of the calculated lane lines, this embodiment also includes the following sub-steps before performing step S40: judging the solved lane lines, Whether the vanishing point and the mean value of the curve radius meet all the following conditions, if the conditions are met, output the relevant parameters and perform Kalman filter prediction calculation; if not, do not output, and return to step S10 to process the next frame of image.

[0078] Specific conditions include:

[0079] 1) Judging that in the fitted lane line, 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 trapezoidal shape. If the slope product of the left and right lane lines is greater than 0, it obviously does not conform to the image recognition. lane line characteristics. ...

Embodiment 3

[0083] As an optimization of Embodiment 1, the difference between this embodiment and Embodiment 2 is that in order to prevent the painted lane line from “flying” or obviously not fitting the actual lane line, in this implementation, in step S30, the drawn lane line is Verification steps are also included before the joint lane line:

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

[0085] S322. Judging whether the mean values ​​of the curvature radii of the current frame are 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 judged according to the image pixel distance, and the fifth ...

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 robust lane line detection method based on a dynamic region of interest, comprising the following steps: S10, initializing a dynamic region of interest of the lane; S20, dividing the lane line interested region in the current frame from near to far into a straight line identifying region and a curve identifying region; S30, pre-extracting that characteristic point of thelane line edge for the straight line recognition area and the curve recognition area, obtaining the straight line lane parameter of the straight line recognition area and the curve lane parameters ofthe curve recognition area through a fitting algorithm, and drawing a fitting lane line; S40, according to the fitting lane line parameters of the current frame, the dynamic region of interest DROI in the next frame image is predicted by using the Kalman filter. The invention is based on DROI, adopts RANSAC algorithm, can effectively extract lane line inner side edge information under complex working conditions, and the anti-jamming performance and accuracy of the method are obviously improved and improved. At the same time, the real-time and robust lane tracking can be realized by using Kalman prediction and inter-frame correlation constraint.

Description

technical field [0001] The invention relates to the field of intelligent driving and ADAS intelligent assisted driving system, 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 (Intelligent Transportation System, ITS) and Advanced Driver Assistance System (Advanced Driver Assistance System, ADAS) has provided an important guarantee for the driving safety of drivers. As a key technology in the ADAS system, lane 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 obstacles, it still has problems such as low robustness and poor real-time performance. [0003] Therefore, proposing a fast and robust lane line detection method will help impro...

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): G06K9/00G06K9/46
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