Rapid measurement method for large motion of structure based on computer vision
A technology of computer vision and measurement method, which is applied in computer parts, calculation, image data processing, etc., can solve the problem of low efficiency of measurement structure, and achieve the effect of high measurement accuracy and high measurement efficiency
Active Publication Date: 2022-01-18
XI AN JIAOTONG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In order to solve the problem that the current template matching method uses a search area of the same global size, resulting in low efficiency when measuring large motions of structures, the present invention provides a fast measurement method for large structural motions based on computer vision. In order to achieve the above objectives, the present invention adopts The technical solution is:
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.
[0041] Such as figure 1 Shown, the present invention is a kind of fast measurement method of large motion of structure based on computer vision, comprises the following steps:
[0042] Step 1: Speckle processing is performed on the position to be measured on the structure, video recording of the motion of the structure is performed by the camera, and the initial frame image is divided into several sub-domains.
[0043] Step 2: If figure 2 As shown, select any sub-domain as a template, establish a zero-mean normalized cross-correlation function about the template, perform a global search on the next frame of image, calculate the correlation of the template at different positions in the next frame of image, and pass the correlation The largest position gets the integer pixel coordinates of the template in the next image frame.
[0044] In the ...
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
Login to View More Abstract
In order to solve the problem of low measurement efficiency of an existing template matching method during measurement of large motion of a structure, the invention discloses a rapid measurement method for large motion of the structure based on computer vision. According to the method, the size of a search area of a next frame is determined by utilizing the displacement of a current frame structure in the horizontal and vertical directions, and a template is matched in the search area to obtain the integer pixel displacement of the structure. The integer pixel displacement of the structure is fitted by adopting a curved surface fitting method, the sub-pixel displacement of the structure is calculated, and high-precision measurement is performed on the motion of the structure. According to the method provided by the invention, the size of the search area can be adjusted according to the actual motion size of the structure, and compared with a previous template matching strategy based on global search, the method provided by the invention can effectively improve the measurement efficiency of the template matching method in measuring the large motion of the structure.
Description
technical field [0001] The invention belongs to the technical field of structural vibration measurement, in particular to a computer vision-based fast measurement method for large structural motions. Background technique [0002] As a new type of non-contact structural motion measurement method, computer vision method is gradually applied in the industrial field, so it is of great significance to develop efficient and fast computer vision motion measurement method. [0003] The template matching method is a computer vision-based structural motion measurement method, which has the advantages of non-contact, spatial high resolution, and high precision. In this method, the speckle processing is performed on the surface of the structure, and the video image of the structure movement is acquired by the camera, and the correlation function and the template are established by using the gray information of the pixel of the video image, and the search area is set, and the template co...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06V10/75G06K9/62G06T7/00G06T7/20
CPCG06T7/0002G06T7/20G06T2207/10016
Inventor 徐自力辛存王珺闫松
Owner XI AN JIAOTONG UNIV