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

Lane line recognition method, apparatus and device, and computer readable storage medium

A lane line recognition and lane line technology, applied in the field of image recognition, can solve the problems of inaccurate recognition of subtleties and low recognition accuracy.

Inactive Publication Date: 2020-02-14
HUMAN HORIZONS (SHANGHAI) AUTONOMOUS TECH CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The image recognition model is affected by the image resolution, and it is often inaccurate to recognize the subtleties in the image. Therefore, the image recognition model is not very accurate in recognizing the lane lines in the distance.

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 recognition method, apparatus and device, and computer readable storage medium
  • Lane line recognition method, apparatus and device, and computer readable storage medium
  • Lane line recognition method, apparatus and device, and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 2

[0071] Example 2: According to the position information of the horizon in the lane line image of the first frame, the position information of the second sub-image corresponding to the lane line image of the first frame is determined. The position information of the horizon can be obtained by camera calibration. In some embodiments, before processing the lane line image, the coordinate system in the image should be set, and the zero point of the vertical axis of the coordinate system can be determined according to the horizon in the image. Therefore, in the process of setting the coordinate system in the image, the position information of the horizon can be determined. In this example, a point on the horizon can be selected as the center position of the second sub-image. For example, the center point of the horizon is selected as the center position of the second sub-image.

[0072] Among them, step S303 can have multiple implementation manners.

[0073] For example, the disappea...

Embodiment approach

[0078] As an exemplary embodiment, step 301, acquiring the corresponding first sub-image from the lane line image of the current frame may include: acquiring from the lane line image of the current frame according to predetermined second size information and predetermined position information The corresponding first sub-image. The real-world ROI corresponding to the first sub-image may include the entire lane line, occupying a larger image in the lane line image. In the process of processing consecutive multiple frames of lane lines, the relative position of the first sub-image in the lane line image is different. There will be too much change, and the processing speed can be improved by pre-setting the size information and position information of the first sub-image. It should be understood that the position and size of the first sub-image can also be adaptively adjusted according to the recognition result of the recognized image to obtain the first sub-image.

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 recognition method, apparatus and device, and a computer readable storage medium. The lane line recognition method comprises the steps of obtaining a lane line image; obtaining a first subimage and a second subimage from the lane line image, wherein a real scene region of interest corresponding to the first subimage is greater than a real scene region of interestcorresponding to the second subimage; and inputting the first sub-image and the second sub-image into an image recognition model, and recognizing the lane line in the lane line image. According to the embodiment of the invention, the image recognition model can recognize the complete lane line, and the accuracy of recognizing the remote lane line can be improved.

Description

Technical field [0001] This application relates to the field of image recognition, and in particular to a lane line recognition method, device, equipment and computer-readable storage medium. Background technique [0002] In the field of intelligent driving, lane line information is an important environmental perception information. After shooting the lane line image, the image recognition model can be used to identify the lane line in the image, so as to obtain the lane line information. For example, use a deep learning neural network model to recognize lane lines in an image. The image recognition model is affected by the resolution of the image, and it is often inaccurate to recognize the subtle points in the image. Therefore, the recognition accuracy of the image recognition model to the distant lane line is not high. Summary of the invention [0003] The embodiments of the present application provide a lane line recognition method, device, device, and computer-readable stor...

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): G06K9/00G06K9/32
CPCG06V20/588G06V10/25
Inventor 丁磊赵磊赵岩峰柴丽颖
Owner HUMAN HORIZONS (SHANGHAI) AUTONOMOUS TECH CO LTD
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