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

A landslide trailing edge crack displacement image recognition method

An image recognition and trailing edge technology, applied in the field of image recognition, can solve the problems of easily damaged or even buried ground equipment, affecting the accuracy of monitoring data, increasing monitoring costs, etc., to avoid the danger of installing sensors, and to visualize the details of landslide disasters. , the effect of reducing errors

Active Publication Date: 2019-04-05
CHENGDU UNIVERSITY OF TECHNOLOGY
View PDF10 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current traditional monitoring method is to deploy various ground monitoring equipment in the landslide area, such as sensor terminals, GPS stations, etc. The disadvantages of this monitoring method are: the traditional instrument monitoring method is highly dependent on The degree determines the monitoring precision and accuracy
In addition, it is easy to damage or even bury ground equipment during the crack development process, which not only increases the monitoring cost, but also seriously affects the accuracy of monitoring data
In addition, the data collected by the sensor also needs various integrations, which requires a large amount of computation.

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 landslide trailing edge crack displacement image recognition method
  • A landslide trailing edge crack displacement image recognition method
  • A landslide trailing edge crack displacement image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] Embodiment 1: see figure 1 , a method for image recognition of crack displacement at the trailing edge of a landslide, comprising the following steps:

[0066] (1) Obtain the color CCD image of the landslide site. The CCD image contains the original crack curve of the landslide, and the color CCD image is grayscaled, and the multi-channel color image is converted into a single-channel grayscale image; the grayscale image in this embodiment The degreeization process is weighted average method, using the following formula to carry out weighted average method on the three-channel components of the color image to obtain the grayscale image:

[0067] f=0.299R+0.587G+0.114B

[0068] Where f is the gray value of a pixel, and R, G, and B represent the red sub-channel value, green channel value and blue channel value of the pixel respectively;

[0069] (2) Use the histogram equalization method to process the grayscale image to enhance the contrast of the grayscale image;

[0...

Embodiment 2

[0077] Embodiment 2: In order to illustrate the present invention better, we choose a color CCD image of a landslide site, in this image, its foreground pixel area is exposed rock and soil, and the background area is green vegetation. The present invention comprises the following steps:

[0078] (1) Get as figure 2 In the grayscale image, the CCD image includes the original crack curve of the landslide, the color CCD image is grayscaled, and the multi-channel color image is converted into a single-channel grayscale image;

[0079] (2) Use the histogram equalization method to process the grayscale image to enhance the contrast of the grayscale image. After processing, the effect is as follows image 3 ;

[0080] (3) The image processed in step (2) is denoised by median filter, and the effect after processing is as follows Figure 4 ;

[0081] (4) Convert the image processed in step (3) into a binarized image using the OTSU Otsu algorithm, and the binarized image consists o...

Embodiment 3

[0090] Assume that in step (4), temporarily select the threshold value as 100, and the obtained graph can be found in Figure 6a-Figure 6f . From Figure 6a-Figure 6f It can be seen from the figure that when the binarization threshold is 100, because the binarization threshold is low, that is, there are few pixels with a pixel value of 255 in the foreground area in the figure, the foreground area is blurred and the outline is intermittent, resulting in the final recognition result Most of the crack curves at the trailing edge of the landslide are lost, and there are errors in the identification effect.

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 landslide trailing edge crack displacement image recognition method, which comprises the following steps: firstly, converting an original color image into a single-channel gray image by using a graying method on the basis that mountain surface vegetation is clearly compared with landslide bare rock soil for an existing crack zone of a landslide trailing edge; Performing noise reduction and filtering processing by using a histogram and median filtering; Determining an optimal binarization threshold value by using an OTSU Otsu algorithm, and giving a binarization image;Performing corrosion and expansion processing through image morphology, and smoothing image details; And finally, using a Canny operator method to draw an image boundary, and relying on feature recognition to retain the solved landslide trailing edge crack curve. According to the identification method provided by the invention, an existing landslide crack monitoring mode is effectively optimized,detail information of landslide cracks is reserved to the maximum extent, and a more reliable material is provided for research of geologists.

Description

technical field [0001] The invention relates to an image recognition method, in particular to an image recognition method for crack displacement at the trailing edge of a landslide. Background technique [0002] As a common type of disaster in geological disasters, the proportion of landslides is increasing year by year. According to the 2016 National Geological Disaster Notification, a total of 7,403 landslides occurred across the country in 2016, accounting for 76.2% of the total number of geological disasters, posing a huge threat to the safety of people's lives and property. Therefore, the detection and monitoring of landslides become very important. The landslide itself has the following characteristics: there is a crack zone at the trailing edge of the landslide, and the color difference between the exposed rock and soil of the landslide and the vegetation on the mountain surface is obvious. [0003] The current traditional monitoring method is to deploy various grou...

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): G06T7/00G06T5/00G06T5/30G06T7/136G06T7/194
CPCG06T5/30G06T7/0002G06T7/136G06T7/194G06T2207/10024G06T2207/20032G06T2207/30184G06T5/70
Inventor 王洪辉聂东林庹先国赵宇周全儒王翔孟令宇
Owner CHENGDU UNIVERSITY OF TECHNOLOGY
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