Check patentability & draft patents in minutes with Patsnap Eureka AI!

Lane line detection method and device based on combination of SegNet and U-Net networks

A lane line detection and lane line technology, applied in the field of lane line detection, can solve problems such as single feature, and achieve the effect of robust structure and good robustness

Active Publication Date: 2020-12-29
HUAQIAO UNIVERSITY
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to overcome the above-mentioned defects in the prior art, propose a lane line detection method combining SegNet and U-Net networks, overcome the problem that the features extracted by the original SegNet model are too single, and improve the accuracy of lane line detection

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 and device based on combination of SegNet and U-Net networks
  • Lane line detection method and device based on combination of SegNet and U-Net networks
  • Lane line detection method and device based on combination of SegNet and U-Net networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Embodiment, the present invention provides a kind of lane detection method combining SegNet and U-Net network, such as figure 1 It is a schematic flow chart of an embodiment of the present invention, specifically:

[0050] S10, making data sets and labels

[0051]Select images from the video that include straight lines, curves, and driving scenes under various conditions (night and day, shadows, rain and sunshine); remove blur, hidden lines, incorrect data format, and too similar problems in the video image; rotate and horizontally flip the filtered driving scene image, expand and generate more images, set these images uniformly as a 3-channel image with a size of 160*80, and use this as a data set; then, set The image in the data set is converted into a binary image, and the maximum between-class variance method (OTSU) is used to find the pixel corresponding to the lane line in the image, and its gray value is assigned to 255, while the rest of the pixel points The g...

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 combination of SegNet and UNet networks. The lane line detection method comprises the following steps: making a data set and a label; constructing a lane line detection network based on the SegNet; adding the jump connection structure of the UNet network into the lane line detection network based on the SegNet to obtain a lane line detection network combining the SegNet and the UNet; and detecting a driving scene image to be identified by using the lane line detection network combining the SegNet network and the UNet network to obtain a detection result. According to the lane line detection method provided by the invention, the problem that features extracted by an original SegNet model are too single is solved, and the lane linedetection precision is improved.

Description

technical field [0001] The present invention relates to the field of lane line detection, in particular to a lane line detection method and device combining SegNet and U-Net models. Background technique [0002] At present, the lane detection technology is mainly divided into two types: traditional lane detection technology and deep learning-based lane detection technology. [0003] Lane line detection was first implemented by traditional methods, generally consisting of five steps: distortion correction, inverse perspective transformation (IPMTransform), feature extraction, curve fitting and tracking, of which the first and fifth steps can be regarded as non-essential steps . However, since the traditional lane line recognition model is completely based on computer vision, lane lines are detected through image processing, threshold setting, etc. This model is single and has strong limitations. Usually the same threshold can only identify lane lines in a specific environm...

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): G06K9/00G06K9/42G06K9/46G06K9/54G06N3/04G06T3/40
CPCG06T3/4038G06T2200/32G06V20/46G06V20/588G06V10/32G06V10/20G06V10/56G06N3/045Y02T10/40
Inventor 朱显丞黄德天陈健吴娇绿于耀博
Owner HUAQIAO UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com