Real-time detection method of digital image correlation method based on SIFT improvement

A digital image, real-time detection technology, applied in the direction of character and pattern recognition, instruments, computer components, etc., can solve the problems of complicated measuring instrument lines, complicated deployment of strain gauges, and inapplicability, and achieve strong scalability and high environmental protection The effect of improving adaptability and efficiency

Inactive Publication Date: 2021-07-09
NANCHANG INST OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Bond the strain gauge to the surface of the component under test. When the force deforms, the strain gauge deforms along with the component. At this time, the resistance value of the strain gauge changes accordingly. The resistance change in the strain gauge is measured and converted by the resistance strain gauge. The instruments used to measure strain mainly include linear displacement sensors and extensometers, etc., but the circuits of the measuring instruments are complicated and can only be used for single-point one-way measurement and precise devices are required before obtaining complete results
Since the strain gauges commonly used to measure strain need to be patched and deployed in advance, and the measurement is often the average strain in a certain area, it is not suitable for some occasions where direct contact is not possible

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
  • Real-time detection method of digital image correlation method based on SIFT improvement
  • Real-time detection method of digital image correlation method based on SIFT improvement
  • Real-time detection method of digital image correlation method based on SIFT improvement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0064] Embodiment: a kind of real-time detection method based on SIFT improved digital image correlation method, see Figure 2-4 As shown, it includes the following steps:

[0065] 1. Obtain the grayscale image before and after deformation:

[0066] The CDD camera can directly capture the grayscale image, or input the RGB color image, and obtain the grayscale image of the sub-region through computer conversion. The grayscale formula of the color image is shown in formula (1);

[0067] Formula 1)

[0068] In formula (1) is the red color intensity of the color image, is the green color intensity of the color image, is the blue color intensity of the color image;

[0069] 2. Compute subpixel surface fitting:

[0070] The surface fitting shape function expression is constructed, and the coefficients in the surface fitting formula can be calculated by using the Newton iterative method. The surface fitting expression is shown in formula (2):

[0071] Formula (2)

[...

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 real-time detection method of a digital image correlation method based on SIFT improvement, and relates to a deformation detection method. The method comprises the following steps: 1, obtaining gray level images before and after deformation; 2, calculating sub-pixel curved surface fitting; 3, calculating a sub-pixel interpolation; 4, establishing different Gaussian scale spaces to construct a continuous scale image pyramid; 5, searching and screening feature points from the continuous scale space; 6, constructing analysis sub-regions in combination with the selected feature points; 7, calculating the displacement of the deformation sub-region; and 8, using a displacement feature vector to represent deformation. According to the method, the continuity of the displacement field is ensured, the adjustment of the calculation speed and precision is more concise and convenient, the two parameters are balanced, the improved algorithm does not increase the calculation complexity, the pretreatment time is saved, the method has better adaptability to complex boundaries, and higher calculation precision can be achieved under the condition of the same calculation speed.

Description

technical field [0001] The invention relates to a deformation detection method, in particular to a real-time detection method based on a SIFT-improved digital image correlation method. Background technique [0002] Civil engineering materials such as sand, concrete, rock, etc. are mixed with various materials. These different materials are very easy to form rough and uneven surfaces. These surfaces will have certain differences in the reflection effect of light, and these differences are random and non-uniform. Therefore, capturing these differences can be described in the digital image correlation method A characteristic of the surface of a material. [0003] The current geotechnical material deformation monitoring methods generally use the sensor method, ultrasonic method, etc., and the sensor method is more common. Paste or embed many transformers on the surface or inside of the stress test pieces, such as buildings and experimental materials, and monitor the voltage ch...

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): G06K9/32G06K9/46G06K9/62
CPCG06V10/25G06V10/462G06F18/2411
Inventor 万琪伟甘建军张渴望张世乐张思聪
Owner NANCHANG INST OF TECH
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