Lane line detection method based on ORB feature extraction

A technology for lane line detection and feature extraction, applied in instruments, character and pattern recognition, computer parts, etc., can solve problems such as inability to obtain accurate detection results, achieve good application prospects, ensure minimal computational overhead, and ensure real-time performance. Effect

Inactive Publication Date: 2017-03-22
BEIJING UNION UNIVERSITY
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The feature method is based on some characteristics of the road (such as lane line color, width, and edge features, etc.) to mark all points of the road image as lane line points and non-lane line points. This method requires that the lane line color of the road is more obvious, and the edge It is relatively clear, otherwise the test result cannot be obtained accurately

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 detection method based on ORB feature extraction
  • Lane line detection method based on ORB feature extraction
  • Lane line detection method based on ORB feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] like figure 1 As shown, an embodiment of the present invention provides a lane line detection method based on ORB feature extraction, which includes the following steps:

[0031] Step 1: Image acquisition;

[0032] Configure the on-board camera of the smart car to set the parameters (exposure, white balance, etc.), make the quality of the collected images reach the optimal state, and collect road and lane images in real time;

[0033] Step 2: Grayscale the image;

[0034] Convert the image captured by the camera into a grayscale image;

[0035] Step 3: Region of interest extraction;

[0036] After the camera acquires the image, it is necessary to extract the region of interest from the original image to exclude the interference of non-lane features. The region of interest is a trapezoidal region, and the region of interest must contain all the features of the front lane. We set the trapezoidal region as (X1, X2, X3, X4, Y1, Y2), wherein (X1, Y1), (X2, Y1), (X3, Y2),...

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 lane line detection method based on ORB feature extraction. A camera mounted under a rearview mirror in an intelligent vehicle is used to obtain real-time images; a region of interest (ROI) is extracted from the obtained image, and the image is preprocessed; a candidate lane line feature point set is extracted rapidly from the preprocessed image by utilizing an ORB feature; K-MEANS clustering is carried out according to the candidate lane line feature point set, and left and right lane line feature point sets are obtained; RANSAC fitting is carried out on the left and right lane line feature point sets; and lane lines are tracked to ensure the stability of lane line detection. The candidate lane line feature point set is extracted rapidly by utilizing the ORB feature, lane lines are classified, the instantaneity and accuracy of lane line detection can be improved effectively, and the robustness of the algorithm can be ensured.

Description

technical field [0001] The invention belongs to the technical field of unmanned driving and intelligent assisted driving, and in particular relates to a lane line detection method based on ORB feature extraction. Background technique [0002] Lane line detection is a key aspect of the research on intelligent assisted driving systems and unmanned driving systems. With the popularization of automobiles and the development of unmanned vehicles, safe driving and intelligent transportation have attracted more and more attention and attention. Lane line detection methods Research has become a hot issue at home and abroad. At present, lane line detection algorithms can be mainly divided into two categories: feature-based and model-based lane detection methods. The feature method is to mark all points of the road image as lane line points and non-lane line points based on some features of the road (such as lane line color, width, and edge features, etc.) It is relatively clear, ot...

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): G06K9/00G06K9/32G06K9/46
CPCG06V20/588G06V10/25G06V10/44
Inventor 鲍泓张飞飞王迪阳钧韩向敏乔良
Owner BEIJING UNION UNIVERSITY
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