Lane line detection method based on vanishing point estimation and semantic segmentation

A technology of lane line detection and semantic segmentation, applied in the field of image processing, can solve the problems of long time-consuming lane line detection and low detection accuracy, and achieve the effects of reducing parameters and calculations, suppressing noise, and good adaptability

Active Publication Date: 2020-08-25
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, lane line detection still has certain limitations: the increase of lane line with distance will lead to the problem of lower detection accuracy, and the time-consuming problem 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 based on vanishing point estimation and semantic segmentation
  • Lane line detection method based on vanishing point estimation and semantic segmentation
  • Lane line detection method based on vanishing point estimation and semantic segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] An embodiment of the present invention provides a lane line detection method based on vanishing point estimation and semantic segmentation. The overall flow chart is as follows figure 1 As shown, the specific steps are as follows:

[0053] Step 1. Collect images containing lane lines in different scenes, and mark the lane lines and road vanishing points of the images to form a data set. Divide the data set into a training set, a verification set, and a test set according to a certain proportion. Among them, training The set is used to train the deep convolutional network, the verification set is used to select the best training model, and the test set is used to test the performance of the designed model later.

[0054] Step 2. Design a classification convolutional neural network to estimate the coordinate position of the vanishing point, and send the marked image into the classification convolutional neural network to obtain the best training model, and obtain the coor...

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 the technical field of image processing, and provides a lane line detection method based on vanishing point estimation and semantic segmentation. The lane line detection method comprises the following steps: firstly, detecting a vanishing point through a convolutional neural network, secondly, performing inverse perspective transformation of self-parameter learning throughestimated vanishing point coordinates, and projecting an image into an overlooking view angle easy for network learning. In the top view, binary segmentation is carried out through a semantic segmentation network, then post-processing instantiation is carried out, and a lane line fitting equation is obtained and displayed in an original image. According to the method, the problem of lane line detection in different road scenes is solved by utilizing the strong feature extraction capability of the convolutional neural network, and the time of instantiation operation of a lane line detection algorithm is saved. According to the technical scheme, the edge of the fuzzy lane line can be effectively detected, noise is suppressed, time consumed for detection of vanishing points and straight lines is short, accuracy is high, and lane line recognition real-time performance is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a lane line detection method based on vanishing point estimation and semantic segmentation. Background technique [0002] With the popularity of automobiles, using sensors to improve the ability to identify road objects, giving drivers more safety warnings and assistance, thereby improving the active safety of vehicles has become an important direction for the development of intelligent transportation systems. Lane detection Tasks are an important part of it. In practical application scenarios, due to weather changes, lighting changes, different terrains, road conditions, etc., high-precision detection of lane lines is very challenging. Usually, the lane line detection algorithm needs to be run on the vehicle side, so the algorithm not only has certain requirements for accuracy, but also needs to ensure real-time performance. A good lane line detection algorithm can ef...

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): G06K9/00G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/588G06V10/267G06N3/045G06F18/2414G06F18/253Y02T10/40
Inventor 吴忻生向石方陈安刘海明陈纯玉
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap