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

Lane detection method under poor illumination condition

A technology for lane detection and lighting conditions, applied in the field of lane line detection, can solve the problem of low detection accuracy in high exposure scenes, and achieve the effect of saving computing work, improving lane detection performance, and saving computing resources.

Pending Publication Date: 2022-04-22
FUZHOU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can effectively enhance the detection performance of the lane model in low-light conditions, but in real traffic scenes there are also glare scenes due to direct sunlight, and this method has low detection accuracy for high-exposure scenes

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 detection method under poor illumination condition
  • Lane detection method under poor illumination condition
  • Lane detection method under poor illumination condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0050] The invention provides a lane detection method under bad lighting conditions, and proposes a two-stage network model, namely, an exposure consistency generation model and a lane detection model;

[0051] Image exposure consistency generation model: Based on the retinex theory, a reflectance estimation network is designed; the reflectance of the image is calculated through the reflectance estimation network, and then combined with exposure consistency processing to obtain an enhanced image;

[0052] Lane detection model: train the enhanced image as a new data set to obtain a lane detection model; the lane detection model uses ERFNet as the backbone network, and additionally adds a lane presence prediction branch to improve the accuracy of lane detection.

[0053] The following is the specific implementation process of the present in...

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 lane detection method under a poor illumination condition. According to the method, the adaptability of the lane model under a poor illumination condition is improved. According to the invention, an image enhancement network is designed for calculating the reflectivity of the image, modifying the exposure of the image and generating the image with consistent exposure. And the enhanced images are used for training a lane detection model. According to the method, verification is carried out on a CULane data set, and the result shows that the method can improve the detection performance of a lane model, especially on data sets related to illumination, such as night, shadow and dazzle light scenes.

Description

technical field [0001] The invention relates to the field of lane line detection, and specifically relates to a lane detection method under bad lighting conditions. Background technique [0002] Now there are two mainstream technologies used in the field of lane line detection, namely the traditional image processing method and the method based on deep learning. [0003] Traditional methods are based on handcrafted features, and these methods rarely take into account the impact of illumination on lane detection. Their main idea is to use visual cues to perform image processing and extract shape information in HSI color space. In addition to shape features and color features, edge features are also used for lane detection. The method is to preprocess the image first, and then use the edge detection operator to detect the edge of the lane line. At the same time, Hough transform and Kalman filter are usually applied to lane line detection. [0004] In recent years, some rese...

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): G06V20/58G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/214
Inventor 杨明静魏英东
Owner FUZHOU 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