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

Road lane detection method based on binarization CGAN

A lane detection and binarization technology, applied in the field of image recognition, can solve the problem that the target recognition network is difficult to run embedded terminals, and achieve the effect of promoting application and delicate results

Pending Publication Date: 2020-05-12
合肥湛达智能科技有限公司
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a highway lane detection method based on a binary CGAN network, which binarizes the CGAN network to solve the problem that the target recognition network is difficult to run on an embedded terminal

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
  • Road lane detection method based on binarization CGAN
  • Road lane detection method based on binarization CGAN
  • Road lane detection method based on binarization CGAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] A road lane detection method based on a binary CGAN network. Firstly, a network model is constructed and trained, and then the road lane is detected through the trained network model. figure 2 It is a schematic diagram of the network structure of the present invention, image 3 It is a schematic diagram of lane detection output through the present invention.

[0019] The construction and training of the network model mainly includes the following steps:

[0020] 1. Collect a large number of road scene pictures, preprocess and label the pictures to obtain a data set, and divide the data set into three parts: training set, test set and verification set.

[0021] Preprocessing mainly includes grayscale processing, smoothing processing, binarization processing, etc., and then CAD is used to mark the lane marking lines. In order to distinguish from the surrounding environment, the color that is quite different from the surrounding environment is selected for labeling, whi...

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 road lane detection method based on a binarization CGAN. The CGAN finally generates an extremely high resolution image. The details and textures of the image are the same asthose of a real picture, in the network training process, any manually defined loss function does not need to be relied on, and compared with a CNN and a SCNN, the CGAN has the advantages that the result is finer, smoother and more real, the network does not depend on more post-processing technologies and has great superiority; meanwhile, the CGAN is compressed, so that the CGAN can be possibly applied to the embedded terminal, and the application of a deep learning algorithm in movement is promoted.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a road lane detection method based on a binary CGAN network. Background technique [0002] At present, the research hotspot in the field of intelligent transportation is the safety driving assistance system, which mainly aims at how to reduce traffic accidents. By continuously developing advanced technologies to replace part of the driver's tasks, and constantly improving the car's assisted driving functions, a fully intelligent car will eventually be realized. In view of the increasing number of cars and the frequent occurrence of traffic accidents in recent years, many countries in the world have increased the research on the field of vehicle safety assisted driving. Vehicle departure warning is an important aspect of vehicle safety driving assistance system research, and it also plays an important role in intelligent system research. Lane detection and recognition ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/084G06V20/588G06N3/045
Inventor 吴善春张中
Owner 合肥湛达智能科技有限公司
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