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

Method and system for automatic screening of reference grids in road condition detection images

A technology for detecting images and grids, which is applied in the field of image processing, can solve problems such as missing disease area identification, achieve logical and reasonable results, avoid misjudgment, and simplify complexity

Active Publication Date: 2022-07-15
HUNAN ZHONGDA CONSTR ENG TESTING TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the actual operation process, due to the limitation of image resolution and the ability to distinguish with the naked eye, manual identification of diseased areas can easily lead to more omissions.

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
  • Method and system for automatic screening of reference grids in road condition detection images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0018] This embodiment discloses an automatic screening method for a reference grid in a road condition detection image, such as figure 1 shown, including the following steps:

[0019] Step S1, calibrating the range of colors and line widths corresponding to at least part of the road marking lines in a single image collected by the image acquisition terminal mounted on the detection vehicle; and building a filter model library in which at least one manhole cover model, At least one bridge expansion joint model and at least one speed bump model.

[0020] In this step, the length and width of the road corresponding to a single image collected by the image collecting terminal on the vehicle usually need to be synchronously calibrated. The length of the road corresponding to a single image mainly refers to the mileage length corresponding to the single image; then, taking the length of the road as the minimum division unit of the measured road, the continuous images of the measur...

Embodiment 2

[0041] Corresponding to the above method embodiments, this embodiment discloses an image processing system in a highway technical condition assessment system, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the When the processor executes the computer program, the steps corresponding to the above method embodiments are implemented.

[0042] To sum up, the methods and systems for automatic screening of reference grids in road condition detection images disclosed in the above embodiments of the present invention confirm that the logic of potential reference grids is scientific and reasonable, so as to improve the universality and reliability of intelligent screening of diseased areas. Reliability is guaranteed.

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 discloses an automatic screening method and system for a reference grid in a road condition detection image, so as to improve the universality and reliability of intelligent screening of diseased areas. The method includes: acquiring a road condition detection image, extracting an area within the color range of the road marking line in the image area outside the contour of the corresponding manhole cover, bridge expansion joint and deceleration belt, and then judging whether there is a line width in the area. The line width range calibrated by the road marking is a straight line segment within the set range. If it is, the corresponding area is judged as the marking area; the road condition detection image is divided into grids, and the marking area, manhole cover and bridge are screened out. The grids outside the outlines of expansion joints and speed bumps are clustered by the grayscale sequence of the selected pixels in each grid, and the class with the most elements in the same cluster is selected. The grid corresponding to the grayscale sequence of the pixel with the smallest variance is confirmed as the reference grid.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for automatic screening of reference grids in a road condition detection image. Background technique [0002] In the daily maintenance of highways, it is usually necessary to carry out technical condition assessment every year. In the existing road detection, the image data of road conditions is usually collected by the detection vehicle, and then the user visually demarcates the disease area and marks the disease type of the disease area. However, in the actual operation process, due to the limitation of image resolution and the ability of the naked eye to distinguish, manual identification of the diseased area is likely to lead to more omissions. If the intelligent screening of diseased areas is automatically performed by image processing technology, it is easy to be interfered by road markings, bridge expansion joints, manhole covers and speed bum...

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 Patents(China)
IPC IPC(8): G06T7/12G06T7/13G06T7/90G06T7/00G06V10/762G06K9/62
CPCG06T7/12G06T7/13G06T7/90G06T7/0004G06T2207/30132G06T2207/20021G06F18/23
Inventor 王朝扣陈跃欣刘泽亮
Owner HUNAN ZHONGDA CONSTR ENG TESTING TECH
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