Unlock instant, AI-driven research and patent intelligence for your innovation.

Road area identification method and system

A technology for area recognition and roads, applied in the field of image recognition, can solve the problems of non-universality, poor detection effect, and non-universal algorithms, etc., to reduce the calculation amount of algorithms, enhance real-time performance, and ensure effectiveness Effect

Pending Publication Date: 2021-08-27
浙江同善人工智能技术有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For practical applications, roads are a combination of structured roads and unstructured roads. Although structured road detection technology is becoming mature, the effect of applying to unstructured road area detection is not good, and the algorithm is not universal. Due to the diversity of unstructured roads, most of the proposed algorithms can only be applied to specific road types and are not universal

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 area identification method and system
  • Road area identification method and system
  • Road area identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A road area recognition method, installing a visual device above the vehicle, and collecting images through the visual device, such as figure 1 , methods include:

[0051] 1) Collect real-time images of the road;

[0052] 2) Determine whether the image brightness value of the road real-time image is within the optimal brightness range, if so, perform step 4), otherwise perform step 3);

[0053] 3) Determine whether the natural environmental factors affect the brightness of image acquisition, if so, adjust the brightness of the real-time image of the road through the brightness adjustment step, and perform step 2), otherwise, it means that external interference is encountered when collecting the real-time image of the road, such as leaves blocking the visual equipment. The road real-time image is invalid, go to step 1);

[0054] 4) Input the road real-time image into the trained road area segmentation network to obtain the road area image.

[0055] The optimal brightn...

Embodiment 2

[0065] A road area recognition system, in which a visual device is installed above a vehicle to collect images through the visual device, the system includes an image collection module, a brightness judgment module, an environment analysis module, an image adjustment module, an image segmentation module and a network training module;

[0066] The network training module collects road sample images to form a training set. The network training module uses the training set to pre-train the road area segmentation network to obtain the image brightness range with the best road area image segmentation effect, that is, the optimal brightness range.

[0067] The image acquisition module is used to collect real-time road images and generate brightness judgment instructions;

[0068] The brightness judgment module is used to receive the brightness judgment instruction, and judge whether the image brightness value of the real-time road image is within the optimal brightness range, if so, ...

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 road area identification method and system. The method comprises the following steps: 1) collecting a real-time image of a road; 2) judging whether the image brightness value of the road real-time image is within the optimal brightness range, if yes, executing the step 4), otherwise, executing the step 3); (3) judging whether the natural environment factors influence the image acquisition brightness, if yes, adjusting the brightness of the real-time road image through a brightness adjusting step, and executing the step (2), otherwise, executing the step (1); and 4) inputting the road real-time image into the trained road region segmentation network to obtain a road region image. Compared with the prior art, the method has the advantages of small calculation amount, high real-time performance, high accuracy and the like.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a road area recognition method and system. Background technique [0002] With the rapid development of sensing technology, computer technology and unmanned driving technology, research on vision-based unmanned vehicles has also developed rapidly. The prerequisite for ensuring the safe and reliable operation of unmanned vehicles lies in the accurate identification of road areas. [0003] Generally speaking, roads are divided into two categories: structured roads and unstructured roads. Structured roads are asphalt roads with standard lane lines and standard widths, such as common urban arterial roads, expressways, etc.; unstructured roads, on the contrary, have no fixed width, fuzzy or even no lane lines to determine the road boundary, and the road There are also various materials, such as gravel roads, cement roads, dirt roads, sand roads, etc., which increase the difficulty of...

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): G06K9/00G06K9/34G06K9/46G06K9/62G06N20/00
CPCG06N20/00G06V20/588G06V10/267G06V10/50G06F18/214
Inventor 赵晋燕付卫婷
Owner 浙江同善人工智能技术有限公司
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