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

A lane line detection method in a complex driving scene

A lane line detection and driving scene technology, applied in the field of lane line detection, can solve the problems of difficult lane line recognition methods and limited information, and achieve the effects of overcoming road shadows, high-precision detection, and improving adaptability

Active Publication Date: 2019-06-14
WUHAN UNIV
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the information contained in a single image is limited. When faced with complex driving scenes, such as road shadows, lane line wear, vehicle body occlusion and other disturbances, the lane line recognition method based on a single image often encounters serious difficulties.

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
  • A lane line detection method in a complex driving scene
  • A lane line detection method in a complex driving scene
  • A lane line detection method in a complex driving scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The traditional method mainly uses a single image to detect lane lines. When faced with complex driving scenes such as high curvature of lane lines, strong shadows on the road surface, and lane lines blocked by car bodies, the detection effect is poor. The invention proposes a lane line detection method in a complex driving scene. This method uses continuous multi-frame driving scene images to detect lane lines in the current frame, and uses a deep learning network to construct a lane line semantic segmentation model to achieve stable and accurate lane line detection.

[0032] The method provided by the present invention designs a novel deep learning network model, and its overall structure can be found in figure 1 . Its specific embodiment comprises the following steps:

[0033] Step S1, constructing an image data set, each sample in the data set includes N frames of continuous road scene images. The specific implementation process is described as follows:

[0034]...

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 identification method in a complex driving scene. According to the method, the continuous multi-frame driving scene images are used for lane line detection; a modeof combining a deep convolutional neural network and a recurrent neural network is adopted to construct an end-to-end deep learning model, the lane line detection is carried out on an inputted continuous driving scene image, and a road line probability graph is outputted, so that the problem of high-precision lane line recognition under the complex conditions of road surface shadow, lane line abrasion, vehicle body shielding and the like is effectively solved.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and automatic driving, in particular to a lane line detection method in complex driving scenes. Background technique [0002] With the advancement of artificial intelligence technology, automatic driving has been extensively studied in academia and industry. Lane detection, as an important module in automatic driving technology, has always been a research hotspot. Traditional lane line detection is mostly processed for a single image. However, the information contained in a single image is limited. When faced with complex driving scenes, such as road shadows, lane line wear, vehicle body occlusion and other interferences, the lane line recognition method based on a single image often encounters serious difficulties. [0003] In recent years, the rise of deep learning technology has brought extensive and profound impact on the field of computer vision, which has enabled more and more visual...

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): G06K9/00G06K9/62
Inventor 邹勤
Owner WUHAN UNIV
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