CN114596525A - Dynamic bridge form identification method based on computer vision - Google Patents
Dynamic bridge form identification method based on computer vision Download PDFInfo
- Publication number
- CN114596525A CN114596525A CN202210201036.0A CN202210201036A CN114596525A CN 114596525 A CN114596525 A CN 114596525A CN 202210201036 A CN202210201036 A CN 202210201036A CN 114596525 A CN114596525 A CN 114596525A
- Authority
- CN
- China
- Prior art keywords
- video
- amplification
- edge
- frame
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000004438 eyesight Effects 0.000 title claims abstract description 26
- 230000003321 amplification Effects 0.000 claims abstract description 45
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 45
- 230000008859 change Effects 0.000 claims abstract description 26
- 238000005070 sampling Methods 0.000 claims abstract description 13
- 238000003708 edge detection Methods 0.000 claims abstract description 5
- 238000006073 displacement reaction Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004456 color vision Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 abstract description 10
- 238000005259 measurement Methods 0.000 abstract description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration by non-spatial domain filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0008—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings of bridges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention is suitable for the technical field of vision measurement, and provides a dynamic bridge form identification method based on computer vision, which comprises the following steps: selecting a sensor with proper sampling frequency and resolution ratio for video acquisition; cutting the collected video; amplifying the structural deformation of the video by using an Euler video amplification algorithm; aiming at a target structure in each frame of image after motion amplification, preliminarily determining possible structure edge pixel points by using a Prewitt operator, and then calculating the position of the structure edge point in the region by using a space moment subpixel edge detection algorithm; obtaining a dynamic form recognition result of the structure according to the edge recognition point cloud result of each frame; and calibrating the structural deformation identified by the method by using the known distance between two pixel points on the surface of the object in the picture and the video motion amplification coefficient to obtain accurate dynamic form change. The invention realizes the vision non-contact measurement, does not need to install a sensor on the structure, does not interfere the normal operation of the structure and saves the test cost.
Description
Technical Field
The invention belongs to the technical field of vision measurement, and particularly relates to a dynamic bridge form identification method based on computer vision.
Background
In the operation stage of the bridge, the deformation of the main beam, the bridge tower, the inhaul cable and other members directly reflects the structural construction rigidity of the bridge, so that the form change of the bridge is an important index for evaluating the stress performance of the bridge. Compared with the existing deformation detection methods such as a contact displacement meter, a laser displacement meter, a photoelectric displacement meter and the like, the bridge form measurement method based on the digital image technology has certain development in recent years, obtains the displacement information of the structure by comparing the structural digital images at different times based on the computer vision technology, can measure in a long-distance non-contact manner without installing a sensor, and has the advantages of rapidness, easiness in use, high precision, small limitation, no influence on the normal operation of the structure and the like.
However, the dynamic form recognition of the bridge structure by using the vision sensor at present has the difficulty of recognizing the micro deformation when the sensor pixels are insufficient. When the target structure is large, if the whole camera structure is desired to be shot for form recognition, the resolution of the sensor is not increased, and the small deformation of the pixel capture structure is not enough, so that the cost of the sensor and the time for computer processing are greatly increased by increasing the resolution of the sensor. Therefore, a more accurate and effective dynamic bridge shape recognition method is needed.
Disclosure of Invention
The embodiment of the invention aims to provide a dynamic bridge form identification method based on computer vision, and aims to solve the problems in the background technology.
The embodiment of the invention is realized in such a way that a dynamic bridge form identification method based on computer vision comprises the following steps:
s1, selecting a sensor with proper sampling frequency and resolution to carry out video acquisition on the target structure;
s2, cutting the collected video to obtain the video of the target area;
s3, amplifying the structural deformation in the video by using an Euler video amplification algorithm based on brightness change;
s4, preliminarily determining possible structure edge pixel points by using a Prewitt operator according to a target structure in each frame of image after motion amplification, and then calculating the positions of the structure edge points in the region by using a space moment subpixel edge detection algorithm;
s5, obtaining a dynamic form recognition result of the structure according to the edge recognition point cloud result of each frame;
s6, the distance between two pixel points on the surface of the object and the video motion amplification coefficient which are known in the picture are used, and the structural deformation identified by the method can be calibrated to obtain the accurate dynamic form change of the structure.
Preferably, when the sensor is a color vision sensor, the video is converted to a grayscale color mode.
Preferably, the step S3 is to directly process the pixel gray scale of the video image by equating a slight motion in the video to a slight brightness change.
Preferably, the S3 specifically includes the following steps:
s31, assuming that the one-dimensional signal intensity of the pixel at the arbitrary position x of the video image at the time t is represented as I (x, t), delta (t) is a tiny displacement, and delta (t) is a tiny displacementk(t) denotes the change signal, δ (t) the kth frequency component at time t, γkRepresenting the attenuation multiple of the kth change signal at time t, where 0 < gammakLess than 1, the amplification factor of different frequencies in linear amplification environment is changed into gammakα, the amplification result at this time is expressed as:
s32, band-pass filtering is carried out on the frequency band range within the effective sampling frequency in the video according to the Shannon sampling law, and when the sampling frame rate of the video is 60fps, the motion within 0-30Hz is selected for amplification.
Preferably, the motion amplification process in S32 includes the following steps:
performing Laplacian pyramid multilayer decomposition on the video frame by frame to obtain image sub-bands under different resolutions, adopting different amplification factors according to the different resolutions, wherein the signal-to-noise ratio is lowest under the scale of the highest resolution, the smallest amplification factor can be selected, and the largest amplification factor is selected under the scale of the lowest resolution;
carrying out band-pass filtering on the sub-band obtained after the image multi-scale pyramid decomposition to obtain a change signal in a target frequency band for subsequent processing, wherein a wide-pass-band filter is adopted for vibration amplification, the amplified frequency band range is manually set, and the processing is directly carried out in a time domain;
carrying out Taylor series difference approximation on the interesting signals obtained by filtering, and multiplying the interesting signals by the set amplification factor to obtain a slightly-changed linearly-amplified image sequence;
and (4) reconstructing the amplified image sequence by using a pyramid, overlapping the image sequence with the input sequence, and outputting the amplified video.
Preferably, the S4 specifically includes the following steps:
s41, preliminarily determining the structural edge points at the pixel level through a Prewitt operator:
convolving each frame of image I by using transverse and longitudinal templates to obtain approximate gradients of the transverse and longitudinal directions
And
thereby obtaining a gradient magnitude matrix
After the set threshold value, the pixel points with the gradient amplitude value larger than the threshold value are possible edge points
S42, obtaining sub-pixel level edges of the structure by using space moments:
image I is matched with four space moment templates m with the size of 5 multiplied by 500、m01、m10、m20Is convoluted to obtainCorresponding moment A00、A01、A10、A20；
For in S41
The edge direction can be obtained by calculation
Distance from the centre of the form
Difference in gray scale
Optimizing final edge location coordinates by setting thresholds
Wherein
Preferably, in S5, the first frame of structural configuration point cloud is used as a reference, and the first frame of structural configuration point cloud is compared with the point clouds of other frames to select a stationary point in the point clouds for registration, so as to obtain the structural overall configuration change.
The dynamic bridge form identification method based on computer vision provided by the embodiment of the invention realizes vision non-contact measurement, does not need to install a sensor on a structure, does not interfere with the normal operation of the structure, and saves the test cost;
the overall form measurement of the target structure is realized, instead of measuring one point on the structural member like the traditional sensor, and the overall form change of the structure can be more conveniently obtained;
by using the Euler visual angle video amplification algorithm and the sub-pixel edge identification method, the whole micro morphological change of the structure can be accurately measured, and the method is suitable for the conditions of artificial excitation and environmental excitation, is economical and efficient, has low requirements on the parameters of a measuring instrument, and can be used for structural health monitoring.
Drawings
FIG. 1 is a flowchart of a dynamic bridge form recognition method based on computer vision according to an embodiment of the present invention;
fig. 2 is an initial frame of a test beam configuration change video acquired in a dynamic bridge configuration identification method based on computer vision according to an embodiment of the present invention;
fig. 3 is a flow chart of the video acquired in the dynamic bridge form identification method based on computer vision according to the embodiment of the present invention, which is amplified by the euler visual angle video amplification algorithm;
fig. 4 is a graph of an edge recognition result of a test beam obtained based on computer vision in the dynamic bridge form recognition method based on computer vision according to the embodiment of the present invention;
fig. 5 is a comparison graph of the reconstructed vibration time course and the mid-span point of the test beam measured by the eddy current displacement sensor in the dynamic bridge form identification method based on the computer vision according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Specific implementations of the present invention are described in detail below with reference to specific embodiments.
Example 1
As shown in fig. 1, a flowchart of a dynamic bridge form recognition method based on computer vision provided for an embodiment of the present invention includes the following steps:
s1, selecting a sensor with proper sampling frequency and resolution to carry out video acquisition on the target structure;
s2, cutting the collected video to obtain a video of the target area; when a color vision sensor is used, video can be converted into a gray-scale color mode to reduce the amount of computation for subsequent computer processing;
s3, amplifying the structural deformation in the video by using an Euler video amplification algorithm based on brightness change; the basic principle is mainly based on an optical flow method in the traditional video motion processing, the tiny motion in the video is equivalent to tiny brightness change by using the assumption of optical flow space consistency and constant brightness, and the indirect processing of the tiny motion in the video is realized by directly processing the pixel brightness (gray scale) of a video image, and the method specifically comprises the following steps:
s31, assuming that the one-dimensional signal intensity of the pixel at the arbitrary position x of the video image at the time t is represented as I (x, t), delta (t) is a tiny displacement, and delta (t) is a tiny displacementk(t) denotes the k-th frequency component of the change signal delta (t) at time t, gammakRepresents the attenuation multiple of the kth change signal at the time t (0 < gamma)kLess than 1), the amplification factor of different frequencies under the linear amplification environment is changed into gammakα, the amplification result at this time is expressed as:
s32, performing band-pass filtering on a frequency band range within the effective sampling frequency in the video according to the Shannon sampling law, for example, if the sampling frame rate of the video is 60fps, selecting motion within 0-30Hz for amplification to prevent amplification distortion;
the specific video motion amplification process comprises the following steps: firstly, performing Laplace pyramid multilayer decomposition on a video frame by frame to obtain image sub-bands under different resolutions (spatial scales), adopting different magnification factors according to the different resolutions, wherein the signal-to-noise ratio is lowest under the highest resolution scale, the smallest magnification factor can be selected, and the largest magnification factor is selected under the lowest resolution scale; secondly, carrying out band-pass filtering on the sub-bands obtained after the image multi-scale pyramid decomposition to obtain a change signal in a target frequency band for subsequent processing, wherein a wide-pass-band filter such as a Butterworth filter is generally adopted for vibration amplification, an amplified frequency band range is manually set, and the change signal is directly processed in a time domain; then, Taylor series difference approximation is carried out on the interesting signals obtained through filtering, and the interesting signals are multiplied by the set amplification factor to obtain a slightly-changed linearly-amplified image sequence; finally, the amplified image sequence is reconstructed by using a pyramid, and is superposed with the input sequence, and the amplified video is output;
s4, aiming at the target structure in each frame of image after motion amplification, preliminarily determining possible structure edge pixel points by using a Prewitt operator, and then calculating the positions of the structure edge points in the region by using a space moment subpixel edge detection algorithm, wherein the method specifically comprises the following steps:
s41, preliminarily determining the structural edge points at the pixel level through a Prewitt operator: convolving each frame of image I by using transverse and longitudinal templates to obtain approximate gradients of the transverse and longitudinal directions
And
thereby obtaining a gradient magnitude matrix
After the set threshold value, the pixel points with the gradient amplitude value larger than the threshold value are possible edge points
S42, obtaining a subpixel level edge of the structure by using the space moment; image I is matched with four space moment templates m with the size of 5 multiplied by 500、m01、m10、m20Convolution is carried out to obtain corresponding moment A00、A01、A10、A20(ii) a For in S41
The following can be obtained by calculation: direction of edge
Distance from the centre of the form
Difference in gray scale
Optimizing final edge location coordinates by setting thresholds
Wherein
S5, obtaining a dynamic form recognition result of the structure according to the edge recognition point cloud result of each frame, taking the first frame structure form point cloud as a reference, comparing the first frame structure form point cloud with the point clouds of other frames, selecting an immobile point in the point clouds for registration, and obtaining the surface deformation of the whole structure by integral monitoring;
s6, the distance between two pixel points on the surface of the object and the video motion amplification coefficient which are known in the picture are used, and the structural deformation identified by the method can be calibrated to obtain the accurate dynamic form change of the structure.
Example 2
A specific dynamic bridge form identification method based on computer vision is provided:
s1, testing the beam structure under the condition of simple support boundary, wherein the tested beam is an aluminum beam with the length of 2.8m, the width of 100mm, the thickness of 20mm, the Young modulus of 70GPa, the Poisson ratio of 0.33, and the density of the beam of 2700kg/m3An eddy current displacement sensor is arranged for measuring the dynamic displacement across the middle position, and a video is acquired at a proper position to ensure that the whole test structure is positioned in a video acquisition visual field; a Sony IMX586 CMOS camera of a mobile phone Redmi K20 is used for video acquisition, the video acquisition parameter is 1080p @60fps, the intercepted video initial frame is shown in figure 2, and a random hammering excitation is used for vibrating a test beam;
s2, cutting the video to the required size and converting the video into gray colors;
s3, performing motion amplification on the video by using an Euler visual angle video amplification algorithm, wherein the amplification frequency band is 0-30Hz, the amplification factor is 10 times, and the amplification effect is shown in figure 3;
s4, performing sub-pixel edge detection by combining a Prewitt operator and the space moment to obtain the accurate morphological edge of the target structure, wherein the result of one frame is shown in FIG. 4;
s5, taking the first frame structural form point cloud as a reference, comparing the first frame structural form point cloud with point clouds of other frames, selecting an immobile point in the point clouds for registration, and obtaining the surface deformation of the whole structure by integral monitoring;
s6, calibrating the shape change of the test beam through the pixel distance of the beam with the thickness of 20mm in the video and the magnification factor of the Euler visual angle video amplification algorithm to obtain the accurate deformation of the test beam, selecting the vibration time course across the midpoint, and comparing the vibration time course with the vibration measured by the displacement sensor arranged on site, wherein the result is shown in figure 5, and the method has high identification precision.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (7)
1. A dynamic bridge form identification method based on computer vision is characterized by comprising the following steps:
s1, selecting a sensor with proper sampling frequency and resolution to carry out video acquisition on the target structure;
s2, cutting the collected video to obtain the video of the target area;
s3, amplifying the structural deformation in the video by using an Euler video amplification algorithm based on brightness change;
s4, preliminarily determining possible structure edge pixel points by using a Prewitt operator according to a target structure in each frame of image after motion amplification, and then calculating the positions of the structure edge points in the region by using a space moment subpixel edge detection algorithm;
s5, obtaining a dynamic form recognition result of the structure according to the edge recognition point cloud result of each frame;
s6, the distance between two pixel points on the surface of the object and the video motion amplification coefficient which are known in the picture are used, and the structural deformation identified by the method can be calibrated to obtain the accurate dynamic form change of the structure.
2. The dynamic bridge form recognition method based on computer vision as claimed in claim 1, wherein when the sensor is a color vision sensor, the video is converted into a gray scale color mode.
3. The method for identifying a dynamic bridge form according to claim 1, wherein S3 is a method for directly processing the pixel gray scale of the video image by equating a slight motion in the video to a slight brightness change.
4. The dynamic bridge form recognition method based on computer vision of claim 3, wherein the step S3 specifically comprises the following steps:
s31, assuming that the one-dimensional signal intensity of the pixel at the arbitrary position x of the video image at the time t is represented as I (x, t), delta (t) is a tiny displacement, and delta (t) is a tiny displacementk(t) denotes the change signal, δ (t) the kth frequency component at time t, γkRepresenting the attenuation multiple of the kth change signal at time t, where 0 < gammakLess than 1, the amplification factor of different frequencies in linear amplification environment is changed into gammakα, the amplification result at this time is expressed as:
and S32, performing band-pass filtering on the frequency band range within the effective sampling frequency in the video according to the Shannon sampling law, and selecting the motion within 0-30Hz for amplification when the sampling frame rate of the video is 60 fps.
5. The dynamic bridge form recognition method based on computer vision of claim 4, wherein the motion amplification process in S32 comprises the following steps:
performing Laplacian pyramid multilayer decomposition on the video frame by frame to obtain image sub-bands under different resolutions, adopting different magnification factors according to different resolutions, selecting the minimum magnification factor when the signal-to-noise ratio is lowest under the highest resolution scale, and selecting the maximum magnification factor under the lowest resolution scale;
carrying out band-pass filtering on the sub-band obtained after the image multi-scale pyramid decomposition to obtain a change signal in a target frequency band for subsequent processing, wherein a wide-pass-band filter is adopted for vibration amplification, the amplified frequency band range is manually set, and the processing is directly carried out in a time domain;
carrying out Taylor series difference approximation on the interesting signals obtained by filtering, and multiplying the interesting signals by the set amplification factor to obtain a slightly-changed linearly-amplified image sequence;
and (4) reconstructing the amplified image sequence by using a pyramid, overlapping the image sequence with the input sequence, and outputting the amplified video.
6. The dynamic bridge form recognition method based on computer vision of claim 1, wherein the S4 specifically comprises the following steps:
s41, preliminarily determining the structural edge points at the pixel level through a Prewitt operator:
convolving each frame of image I by using transverse and longitudinal templates to obtain approximate gradients of the transverse and longitudinal directions
And
thereby obtaining a gradient magnitude matrix
After the set threshold value, the pixel points with the gradient amplitude value larger than the threshold value are possible edge points
S42, obtaining sub-pixel level edges of the structure by using space moments:
image I is matched with four space moment templates m with the size of 5 multiplied by 500、m01、m10、m20Convolution is carried out to obtain corresponding moment A00、A01、A10、A20；
For those in S41
The edge direction can be obtained by calculation
Distance from the centre of the form
Difference in gray scale
Optimizing final edge location coordinates by setting thresholds
Wherein
7. The method of claim 1, wherein in step S5, the point cloud of the structural form of the first frame is used as a reference, and compared with the point clouds of other frames to select a stationary point in the point cloud for registration, so as to obtain the overall structural form change.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210201036.0A CN114596525A (en) | 2022-03-03 | 2022-03-03 | Dynamic bridge form identification method based on computer vision |
| GB2215178.1A GB2616322B (en) | 2022-03-03 | 2022-10-14 | Computer vision-based dynamic bridge shape recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210201036.0A CN114596525A (en) | 2022-03-03 | 2022-03-03 | Dynamic bridge form identification method based on computer vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114596525A true CN114596525A (en) | 2022-06-07 |
Family
ID=81815156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210201036.0A Pending CN114596525A (en) | 2022-03-03 | 2022-03-03 | Dynamic bridge form identification method based on computer vision |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114596525A (en) |
| GB (1) | GB2616322B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5070401A (en) * | 1990-04-09 | 1991-12-03 | Welch Allyn, Inc. | Video measurement system with automatic calibration and distortion correction |
| WO2015167537A2 (en) * | 2014-04-30 | 2015-11-05 | Halliburton Energy Services, Inc. | Subterranean monitoring using enhanced video |
| CN106530285B (en) * | 2016-10-21 | 2019-04-09 | 国网山东省电力公司电力科学研究院 | A kind of transmission line part recognition methods based on GPU and the processing of CPU blended data |
| CN109559323A (en) * | 2018-11-16 | 2019-04-02 | 重庆邮电大学 | A method of picture edge characteristic is enhanced based on improved prewitt operator |
| CN109580137B (en) * | 2018-11-29 | 2020-08-11 | 东南大学 | Bridge structure displacement influence line actual measurement method based on computer vision technology |
| CN110595601B (en) * | 2019-04-26 | 2021-10-15 | 深圳市豪视智能科技有限公司 | Bridge vibration detection method and related device |
| CN110599510A (en) * | 2019-08-02 | 2019-12-20 | 中山市奥珀金属制品有限公司 | Picture feature extraction method |
| CN114841965B (en) * | 2022-04-30 | 2023-08-01 | 中建三局第一建设工程有限责任公司 | Steel structure deformation detection method and device, computer equipment and storage medium |
-
2022
- 2022-03-03 CN CN202210201036.0A patent/CN114596525A/en active Pending
- 2022-10-14 GB GB2215178.1A patent/GB2616322B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| GB202215178D0 (en) | 2022-11-30 |
| GB2616322A (en) | 2023-09-06 |
| GB2616322B (en) | 2024-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110108348B (en) | Thin-wall part micro-amplitude vibration measurement method and system based on motion amplification optical flow tracking | |
| CN103994724B (en) | Structure two-dimension displacement and strain monitoring method based on digital image processing techniques | |
| CN111277833B (en) | Multi-passband filter-based multi-target micro-vibration video amplification method | |
| CN108106541A (en) | A kind of bridge cable force measuring method based on video image identification | |
| CN111083365B (en) | Method and device for rapidly detecting optimal focal plane position | |
| CN111174961A (en) | Modal analysis-based cable force optical measurement method and measurement system thereof | |
| CN104200457A (en) | Wide-angle camera shooting based discrete type canopy leaf area index detection system and method | |
| Lee et al. | A new image-quality evaluating and enhancing methodology for bridge inspection using an unmanned aerial vehicle | |
| CN106022354B (en) | Image MTF measurement methods based on SVM | |
| CN111242884B (en) | Image dead pixel detection and correction method and device, storage medium and camera equipment | |
| CN114596525A (en) | Dynamic bridge form identification method based on computer vision | |
| CN108364274B (en) | Nondestructive clear reconstruction method of optical image under micro-nano scale | |
| CN111445435A (en) | No-reference image quality evaluation method based on multi-block wavelet transform | |
| CN116579959A (en) | Fusion imaging method and device for hyperspectral image | |
| CN113870150B (en) | Method for inverting spacecraft low-frequency vibration parameters based on continuous multiple remote sensing images | |
| CN115683431A (en) | Method, device and equipment for determining cable force of inhaul cable based on linear tracking algorithm | |
| Chen et al. | Modal frequency identification of stay cables with ambient vibration measurements based on nontarget image processing techniques | |
| CN112816120B (en) | Cable force measuring method | |
| CN114993452A (en) | Structure micro-vibration measurement method and system based on broadband phase motion amplification | |
| CN109035162A (en) | A kind of picture drift correction method and system based on pixel reconstruction | |
| CN110930447A (en) | Android-based unattended snow depth measurement method | |
| Zheng et al. | Bridge vibration virtual sensor based on eulerian video magnification and gray mean difference | |
| CN107218918B (en) | A kind of single camera distance measuring method | |
| CN111060437A (en) | Detection equipment and detection method for 3D printing sand box | |
| CN115638731B (en) | Super-resolution-based vibrating table test computer vision displacement measurement method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |