Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A road crack image recognition and processing method

A technology of image recognition and processing methods, applied in image data processing, neural learning methods, image analysis, etc., can solve problems such as rapid detection of road conditions, evaluation development, subjectivity and insecurity, and high work intensity, etc., to avoid Artificially judge the effect of heavy workload, rich features, and improved work efficiency

Active Publication Date: 2021-10-12
山东高速工程检测有限公司 +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The traditional road pavement crack detection method is to manually detect the road surface through the visual inspection of engineers. The results of this manual detection are not only time-consuming, high cost, low efficiency, high work intensity, slow speed, but also highly subjective. sex and insecurities
With the rapid growth of highway mileage in our country, the maintenance tasks of highways are bound to become more and more onerous. The current treatment methods for road surface cracks obviously cannot meet the needs of rapid detection and evaluation of road conditions.

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
  • A road crack image recognition and processing method
  • A road crack image recognition and processing method
  • A road crack image recognition and processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0096] A road crack image recognition and processing method, such as figure 1 shown, including the following steps:

[0097] Step1: The road inspection vehicle takes photos of cracks on the road to form an initial picture of cracks;

[0098] Step2: Perform image preprocessing on the initial crack image to form a crack preprocessing image set;

[0099] Step3: Based on the VAE algorithm, automatically encode and decode the crack preprocessing image set to obtain the processed decoded image;

[0100] Step4: Based on the pixel difference algorithm, mark the crack area and non-crack area in the decoded picture;

[0101] Step5: Based on the crack damage grade formula, the damage degree of the crack area is distinguished, and preliminary suggestions for crack repair methods are automatically given.

[0102] Wherein, the image preprocessing in Step2 includes image flipping, image rotation, and image interpolation, and may also include other preprocessing methods, such as adjusting ...

Embodiment 2

[0114] Embodiment 2: The difference between embodiment 2 and embodiment 1 is that a specific method is provided for the preprocessing process of pictures.

[0115] Specifically, such as Figure 2-Figure 4 As shown, the image rotation adopts 180 degree rotation, the image flipping is left-right flipping, and the image interpolation adopts the following formula for pixel adjustment:

[0116]

[0117] Among them, both u and v are constants between 0 and 1, and C(i+u, j+v) represents row i, column j in the crack preprocessing picture and line i+1 and j in the crack preprocessing picture Between +1 columns, and the gray value of the pixel point whose horizontal displacement is u and the vertical displacement is v in the i-th row and j-th column in the crack preprocessing picture, A(i, j) represents the first crack on the initial crack picture The gray value of the pixel in row i and column j, A(i+1, j) represents the gray value of the pixel in row i+1 and column j on the initia...

Embodiment 3

[0120] Embodiment 3: The difference between Embodiment 3 and Embodiment 1 is that a specific evaluation method for road repair is provided.

[0121] Specifically, step4 includes the following steps:

[0122] Step4.1: Store all pixels on the decoded picture in the initial non-mutant set X 0 middle,;

[0123] Step4.2: In the initial non-mutation set X 0 Extract a pixel point x and store it in the mutation set Y to form a non-mutation set X 1 ;

[0124] Step4.3: Calculate the non-mutation set X 1 and the pixel difference D(X 1 ) and D(X 0 ), when D(X 1 )≤D(X 0 ), store the pixel point x in the mutation set Y, otherwise, store the pixel point x in the initial non-mutation set X 0 middle;

[0125] Step4.4: Repeat steps 4.2-4.3 until all pixels are extracted, and all pixels are only extracted in order to form

[0126] Final non-mutated set X* and final mutated set Y*;

[0127] Step4.5: Mark the final mutation set Y* on the decoded picture to form one or more continuous b...

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 present invention provides a road crack image identification and processing method, comprising the following steps: Step 1: road inspection vehicle photographs and collects road crack photos to form an initial crack image; Step 2: performs image preprocessing on the initial crack image to form a crack preprocessing image set; Step3: Automatically encode and decode the crack preprocessing image set based on the VAE algorithm to obtain the processed decoded image; Step4: Mark the crack area and non-crack area in the decoded image based on the pixel difference algorithm; Step5: Based on the crack destruction The grade formula distinguishes the degree of damage in the crack area, and automatically gives preliminary suggestions for crack repair methods. This application is suitable for road detection, especially for asphalt roads. Image enhancement is performed through VAE, cracks and non-cracks are identified through the pixel difference algorithm, and crack treatment suggestions are automatically given through the crack damage level formula, which can automatically identify cracks and give Repair suggestions greatly reduce the workload of staff and improve work efficiency.

Description

technical field [0001] The invention relates to the field of road detection, in particular to a road crack image recognition and processing method. Background technique [0002] In my country, asphalt concrete pavement is the most common pavement structure type for current highways. It has smooth surface, solidity, no joints, comfortable driving, wear resistance, low noise, short construction period, easy maintenance and repair, and can absorb water. Generally, it is well maintained. The service life under certain conditions is relatively long, and it is suitable for phased construction and other advantages, and has been widely used. However, due to the differences in asphalt concrete material itself, coupled with the influence of design level and construction quality, various forms of cracks will inevitably occur in the initial stage of asphalt pavement construction. Due to climate, heavy traffic and illegal driving during highway operation, cracks are inevitable, and the d...

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): G06T7/00G06T9/00G06T3/60G06T3/40G06T7/62G06N3/08
CPCG06N3/08G06T3/4007G06T3/60G06T7/0004G06T9/00G06T2207/20081G06T2207/20084G06T7/62
Inventor 刘宪明辛公锋张文武汲平朱振祥陈铮姜涛夏晗
Owner 山东高速工程检测有限公司
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
Eureka Blog
Learn More
PatSnap group products