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

Bottom plate bolt loss detection method based on image processing

An image processing and missing detection technology, which is applied in image data processing, image enhancement, image analysis, etc., can solve the problems of low detection accuracy and missing bottom plate bolts, and achieve the effect of improving image distortion and improving efficiency

Active Publication Date: 2021-02-05
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of low detection accuracy when using the existing method to detect the loss of truck floor bolts, and propose a method for detecting the loss of floor bolts based on image processing

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
  • Bottom plate bolt loss detection method based on image processing
  • Bottom plate bolt loss detection method based on image processing
  • Bottom plate bolt loss detection method based on image processing

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode 1. Combination figure 1 This embodiment will be described. A kind of base plate bolt missing detection method based on image processing of the present embodiment, it specifically is:

[0030] Step 1. Obtain the bottom image of the truck, and extract the bolt sub-image to be detected from the obtained image;

[0031] Step 2, performing definition enhancement on the intercepted bolt sub-picture to obtain a definition-enhanced image;

[0032] Step 3. Use the parameter control method to detect whether there is a bolt missing fault in the image after the definition is enhanced; the specific process is:

[0033] Step 31. According to the size of the bolt in the sharpness-enhanced image under normal circumstances, set the pixel block size to a×a, divide the a×a pixel area in the upper left corner of the sharpness-enhanced image into a pixel block, and the pixel block Sliding window movement is performed on the sharpness-enhanced image with a ste...

specific Embodiment approach 2

[0040] Specific implementation mode two, the difference between this implementation mode and specific implementation mode one is: the specific process of step two is:

[0041] Step 21. Perform particle removal on the intercepted bolt sub-image to obtain an image after particle removal;

[0042] Step 22: Traverse the intercepted bolt sub-image and the pixels of the image after particle removal to obtain the gray value of the pixel at the same position of the two images, and then calculate the average of the two gray values ​​at the same position, Multiply the average value by the coefficient weight r to get a new gray value;

[0043] Use the new gray value to replace the gray value of the pixel in the image after particle removal (that is, use the new gray value to replace the gray value of the same position in the image after particle removal), and after the replacement is completed, the definition is enhanced Image.

specific Embodiment approach 3

[0044] Specific implementation mode three, the difference between this implementation mode and specific implementation mode two is: the specific process of step 21 is:

[0045] Let f(x,y) be the intercepted bolt subgraph, x and y are the row and column coordinates of the intercepted bolt subgraph respectively, G(x,y) is a two-dimensional Gaussian function, E avr (x,y) is the image averaging function:

[0046]

[0047]

[0048] Where: e is the base of natural logarithm, σ is the standard deviation of the two-dimensional Gaussian function, μ f(x,y) is the average gray value of the pixel in f(x,y), W is the width of f(x,y), and H is the height of f(x,y);

[0049] f dis (x,y)=G(x,y)*E avr (x,y)

[0050] Among them, f dis (x,y) is the image after particle removal, and * represents multiplication.

[0051] E. avr The (x, y) average function, as can be seen from the formula, calculates the difference between the grayscale difference between adjacent pixels and the averag...

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 bottom plate bolt loss detection method based on image processing, and belongs to the technical field of wagon bottom plate bolt loss detection. According to the method, thelow detection accuracy when wagon bottom plate bolt loss fault detection is carried out by using the existing method is solved. According to the technical scheme, the method mainly comprises the following steps that 1, obtaining a wagon bottom image, and extracting a bolt sub-image needing to be detected from the obtained image; 2, performing definition enhancement on the extracted bolt sub-imageto obtain an image with enhanced definition; and 3, performing bolt loss fault detection on the image with the enhanced definition by a parameter control method. The method can be applied to wagon bottom plate bolt loss fault detection.

Description

technical field [0001] The invention belongs to the technical field of detecting missing bolts on the floor of railway wagons, and in particular relates to a method for detecting missing bolts on the bottom plate based on image processing. Background technique [0002] The existing monitoring method for the loss of bolts on the truck floor is visual judgment. This monitoring method is greatly affected by external factors, such as the photographed pictures are not clear, there are objective factors such as water interference; and artificial time-sharing fatigue, lack of concentration, etc. Concentration and other subjective factors. The existence of these objective factors and subjective factors will cause missed and false detections of component failures, which will affect the driving safety of trucks. [0003] Since the existing method for detecting the missing bolts of the floor is easy to cause missed detection and false detection, if the existing method is directly appl...

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): G06T7/00G06T5/00
CPCG06T5/00G06T7/0008G06T2207/10004G06T2207/20021G06T2207/20024
Inventor 张庆宇
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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