An edge detection method for oil well casing damage images based on grey relational analysis and zernike moment

A grey relational analysis, image edge technology, applied in the field of image processing, can solve problems such as failure to achieve good recognition results, low edge accuracy, noise interference, etc.

Inactive Publication Date: 2016-07-13
XI'AN PETROLEUM UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the influence of some external factors, the image is easily disturbed by noise with a frequency close to the edge point during the acquisition and transmission process, resulting in false edges, noise interference, and low edge accuracy in the detected image edges. The edge detection of the object image failed to achieve a good recognition effect

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
  • An edge detection method for oil well casing damage images based on grey relational analysis and zernike moment
  • An edge detection method for oil well casing damage images based on grey relational analysis and zernike moment
  • An edge detection method for oil well casing damage images based on grey relational analysis and zernike moment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The image processing in this example can be divided into two parts. The first part uses the gray correlation analysis algorithm to detect the pixel-level edge of the casing damage image of the oil well pipe to realize the pixel-level edge location. The second part uses the Zernike moment operator to perform secondary subpixel-level edge positioning on the image in the previous step. Take the original image of M×N pixel size as an example to illustrate the implementation steps of this example:

[0033] (1) Use the gray correlation analysis algorithm to detect the edge of the preprocessed oil well casing damage image, and complete the rough positioning of the target edge;

[0034] 1. Determine the reference sequence and comparison sequence

[0035] For the convenience of calculation, for an image of M×N size, a 3×3 template with a value of 1 is used as a reference sequence, namely: x 0 =(1,1,1,1,1,1,1,1,1), the comparison sequence is composed of each pixel in the image ...

Embodiment 2

[0076] Take the video screenshot of the underground TV software system in a certain well depth as an example to illustrate the implementation steps of this example:

[0077] (1) Use the gray correlation analysis algorithm to detect the edge of the preprocessed oil well casing damage image, and complete the rough positioning of the target edge;

[0078] 1. Determine the reference sequence and comparison sequence

[0079] For the convenience of calculation, the 3×3 template with the value of 1 is used as the reference sequence, namely: x 0 =(1,1,1,1,1,1,1,1,1), the comparison sequence is composed of each pixel in the image and the surrounding 8 neighboring pixels, that is:

[0080] x ij =(x i-1,j-1 ,x i-1,j ,x i-1,j+1 ,x i,j-1 ,x i,j ,x i,j+1 ,x i+1,j-1 ,x i+1,j ,x i+1,j+1 )

[0081] Where i=1,2,...,M; j=1,2,...,N, when i,j=1 or i=M, j=N, repeat the corresponding pixel on the adjacent row or column value as the value of the point. For convenience of description, us...

Embodiment 3

[0122] Take the video screenshot of the underground TV software system in a certain well depth as an example to illustrate the implementation steps of this example:

[0123] (1) Use the gray correlation analysis algorithm to detect the edge of the preprocessed oil well casing damage image, and complete the rough positioning of the target edge;

[0124] 1. Determine the reference sequence and comparison sequence

[0125] For the convenience of calculation, the 3×3 template with the value of 1 is used as the reference sequence, namely: x 0 =(1,1,1,1,1,1,1,1,1), the comparison sequence is composed of each pixel in the image and the surrounding 8 neighboring pixels, that is:

[0126] x ij =(x i-1,j-1 ,x i-1,j ,x i-1,j+1 ,x i,j-1 ,x i,j ,x i,j+1 ,x i+1,j-1 ,x i+1,j ,x i+1,j+1 )

[0127] Where i=1,2,...,M; j=1,2,...,N, when i,j=1 or i=M, j=N, repeat the corresponding pixel on the adjacent row or column value as the value of the point. For convenience of description, us...

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 edge detection method of oil well casing damage image based on gray correlation analysis and Zernike moment, for the intercepted oil well casing damage image, the gray correlation analysis algorithm is used to roughly locate the edge of the image, and then the Zernike moment operator is used to realize the edge detection of the image Sub-pixel level positioning, the present invention uses a fast edge detection method that combines gray correlation analysis and Zernike moments, gray correlation analysis can detect continuous effective image edges and retain a large number of image details through threshold adjustment, and has a wide range of applications In sub-pixel edge detection, Zernike can effectively reduce the number of templates required for sub-pixel edge detection, reduce the order of functions, enhance anti-interference ability, and improve edge positioning accuracy. In this method, the gray correlation analysis is used to roughly locate the edge of the casing damage image, and then the edge of the casing damage image is accurately positioned to the sub-pixel level by using the Zernike moment operator with high positioning accuracy and good noise resistance.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an edge detection method for casing damage images of oil well pipes based on gray correlation analysis and Zernike moments. Background technique [0002] At present, there are more than 20,000 oil and gas wells with damaged casings in various oil fields in my country, and the number of wells is still increasing by nearly 1,000 every year, which seriously affects the safe production and development benefits of oil fields. The basis for the implementation of casing repair work during oil well casing damage detection is crucial to accurately evaluating the degree of oil well casing damage, reasonably analyzing formation stress, and timely repairing of casing. Traditional classic edge detection operators such as Sobel, Priwitt, Canny, etc. are all pixel-level detection operators, that is, the detection accuracy can reach the pixel level at most. Due to the influence of some external ...

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): G06T7/00
Inventor 爨莹薛继军赵洋
Owner XI'AN PETROLEUM UNIVERSITY
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