Lane line extraction method based on dynamic ROI and improved firefly algorithm

A technology of firefly algorithm and extraction method, which is applied in the field of lane line extraction based on dynamic ROI and improved firefly algorithm, can solve the problems of low accuracy rate of lane lines, poor robustness, false detection of noise as edges, etc., to improve accuracy and The effect of robustness

Active Publication Date: 2021-07-09
NANJING INST OF TECH
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The primary reason for the low accuracy and poor robustness of lane line detection is that the selected ROI range is too large, except that the lane line area contains too many interference factors, and because the Canny operator in the traditional method is too sensitive, it is easy to misdetect the noise as edge

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
  • Lane line extraction method based on dynamic ROI and improved firefly algorithm
  • Lane line extraction method based on dynamic ROI and improved firefly algorithm
  • Lane line extraction method based on dynamic ROI and improved firefly algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further explained below in conjunction with the accompanying drawings.

[0030] Such as figure 1 It is a flow chart of the lane line extraction method based on dynamic ROI and improved firefly algorithm of the present invention, the lane line extraction method specifically includes the following steps:

[0031] (1) Obtain the lane line video during the driving process of the vehicle in real time, and perform distortion correction, grayscale processing and Gaussian blur processing on the video frame to obtain the preprocessed video frame.

[0032] (2) For the first pre-processed video frame, select the lower 1 / 2 image of the pre-processed video frame as the ROI area.

[0033] (3) carry out edge detection to ROI region by improved firefly algorithm, obtain the edge coordinates of lane line; Step (3) comprises following sub-steps:

[0034] (3.1) Randomly select pixels in the ROI area as the distribution points of fireflies, and divide the fi...

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 lane line extraction method based on a dynamic ROI and an improved firefly algorithm, and relates to the field of lane line detection. The method comprises the following steps: (1) preprocessing a lane line video frame; (2) for the first video frame, selecting the lower 1 / 2 image of the video frame as an ROI; (3) carrying out edge detection on the ROI through an improved firefly algorithm to obtain an edge coordinate of a lane line; (4) carrying out probability Hough transformation on the edge coordinates of the lane line obtained in the step (3), finding out a straight line of the ROI, and fitting the detected straight line by using a least square method to obtain a lane line equation; and (5) dynamically adjusting the video frames after the second frame based on the ROI region of the previous frame to obtain the ROI region of the preprocessed video frame, and then repeating the steps (3)-(4) until the vehicle stops running, thereby completing the extraction of the lane line equation. The lane line extraction method improves the accuracy and robustness of lane line extraction.

Description

technical field [0001] The invention relates to the technical field of positioning, in particular to a lane line extraction method based on a dynamic ROI and an improved firefly algorithm. Background technique [0002] In recent years, driverless cars have become a research hotspot. The driverless car perceives the road environment through the on-board sensor system, and guides the vehicle according to the perceived environmental information, so that the vehicle can drive safely and reliably on the road. The correct detection of lane lines is the premise of realizing driverless driving. Through Detecting lane lines and adjusting vehicles in real time can greatly reduce the accident rate. [0003] The primary reason for the low accuracy and poor robustness of lane line detection is that the selected ROI range is too large, except that the lane line area contains too many interference factors, and because the Canny operator in the traditional method is too sensitive, it is ea...

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): G06K9/00G06K9/32G06K9/46G06N3/00
CPCG06N3/006G06V20/588G06V10/25G06V10/48G06V10/44Y02T10/40
Inventor 沈业辉毕云蕊杨振柴鑫波方英达张岩
Owner NANJING INST OF 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