CN114689246B - Curtain wall door and window airtight performance evaluation method and system based on machine vision - Google Patents
Curtain wall door and window airtight performance evaluation method and system based on machine vision Download PDFInfo
- Publication number
- CN114689246B CN114689246B CN202210289301.5A CN202210289301A CN114689246B CN 114689246 B CN114689246 B CN 114689246B CN 202210289301 A CN202210289301 A CN 202210289301A CN 114689246 B CN114689246 B CN 114689246B
- Authority
- CN
- China
- Prior art keywords
- air leakage
- point
- pixel
- points
- window
- 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000001931 thermography Methods 0.000 claims abstract description 7
- 238000001228 spectrum Methods 0.000 claims abstract description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 5
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0066—Radiation pyrometry, e.g. infrared or optical thermometry for hot spots detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to the field of machine vision, in particular to a curtain wall door and window airtight performance evaluation method and system based on machine vision, wherein the method comprises the following steps: acquiring door and window images by using a thermal imaging double-spectrum camera; determining a plurality of air leakage points based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows; for each adjacent area corresponding to each air leakage point, searching for a pixel point influenced by the air leakage point in the adjacent area; determining three-dimensional points corresponding to each found pixel point based on the position and temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptic conical surface; for each air leakage point, acquiring an elliptical cone corresponding to each adjacent area of the air leakage point, and calculating the air leakage degree of the air leakage point according to the distance between the air leakage point and each elliptical cone; and evaluating the airtight performance of the curtain wall doors and windows according to the air leakage degree of each air leakage point. The door and window air tightness evaluation result obtained by the method is accurate, and the evaluation result is not influenced by a complex door and window structure.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a curtain wall door and window airtight performance evaluation method and system based on machine vision.
Background
If the curtain wall doors and windows are not installed correctly, cold air leakage and hot air backflow can be caused in summer, cold air backflow and heating leakage can be caused in winter, and therefore, the load of a heating or refrigerating system can be increased, the running cost is increased, and the problem is called building air tightness defect.
The existing method for evaluating the air tightness of the door and the window is to process thermal imaging of the curtain wall door and window based on a deep neural network, determine a cold area and evaluate the air tightness of the door and window according to the area occupation ratio of the cold area; the method has the advantages that the resolution of the heated imaging equipment and other structures of the doors and windows are greatly influenced, so that the evaluation result of the air tightness of the doors and windows is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a curtain wall door and window airtight performance evaluation method and system based on machine vision, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for evaluating airtight performance of a curtain wall door and window based on machine vision, the method comprising the following specific steps:
acquiring door and window images by using a thermal imaging double-spectrum camera; determining a plurality of air leakage points based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows;
for each adjacent area corresponding to each air leakage point, searching for a pixel point influenced by the air leakage point in the adjacent area; determining three-dimensional points corresponding to each found pixel point based on the pixel position and temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptic conical surface; each adjacent area corresponds to an elliptic conical surface;
for each air leakage point, acquiring an elliptical cone corresponding to each adjacent area of the air leakage point, and calculating the air leakage degree of the air leakage point according to the distance between the air leakage point and each elliptical cone;
and evaluating the airtight performance of the curtain wall doors and windows according to the air leakage degree of each air leakage point.
Further, a plurality of air leakage points are determined based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows, specifically:
P i scoring the ith pixel point; g i The temperature of the ith pixel point is represented, and Max (g) represents the maximum value of the temperature of the pixel point in the door and window image; d, d i Representing the shortest distance between the ith pixel point and the edge of the door and window;
and determining the air leakage point according to the scores of the pixel points.
Further, for an adjacent area corresponding to one air leakage point, searching the pixel point affected by the air leakage point in the adjacent area specifically includes:
the distance and the temperature difference between each pixel point and the air leakage point in the adjacent area are respectively the abscissa d and the ordinate T d Obtaining a plurality of points, clustering the plurality of points, and leading the points to a straight line T d The pixel point corresponding to the point in the cluster having the smallest average distance of =d is the pixel point affected by the air leakage point.
Further, after searching the pixel points affected by the air leakage points in the adjacent area, calculating the reliability of the found pixel points:
based on the distance and the temperature difference between the found pixel points and the air leakage point, the distribution direction of the found pixel points is obtained by utilizing a principal component analysis method, and the credibility is calculated based on the distribution direction, specifically:
r is the credibility of the found pixel point, and when r is larger than or equal to a preset credibility threshold value, the found pixel point is credible; lambda (lambda) 1 And lambda (lambda) 2 For the eigenvalues based on principal component analysis, (u, v) is max (λ 1 ,λ 2 ) Corresponding feature vectors.
Further, when r is smaller than a preset credibility threshold, the clustering parameters need to be adjusted for re-clustering.
Further, the obtaining of the air leakage degree specifically includes: each elliptical cone corresponds to one credibility, the credibility is a weight, and the air leakage degree of the air leakage point is obtained after the distances between the air leakage point and each elliptical cone are weighted and averaged.
In a second aspect, another embodiment of the present invention provides a system for evaluating the airtight performance of a curtain wall door and window based on machine vision, which specifically includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the computer program when executed by the processor implements the steps of a method for evaluating the airtight performance of a curtain wall door and window based on machine vision.
The embodiment of the invention has at least the following beneficial effects: according to the invention, the door and window air tightness is evaluated based on the influence range of the air leakage points, the evaluation result is accurate, and the evaluation result is not influenced by a complex door and window structure.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof for a curtain wall door and window airtight performance evaluation method and system based on machine vision according to the invention in combination with a preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment of the invention is illustrated by taking the following application scenarios as examples:
the application scene is as follows: after the installation of the curtain wall door and window is finished or the curtain wall door and window is used for a plurality of years, the heat insulation performance of the curtain wall door and window is determined, and whether the curtain wall door and window is installed correctly or whether the curtain wall door and window needs to be repaired or replaced is judged.
The invention provides a machine vision-based curtain wall door and window airtight performance evaluation method, which comprises the following steps of:
step S1, acquiring door and window images by using a thermal imaging double-spectrum camera; and determining a plurality of air leakage points based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows.
Specifically, in an indoor environment, a thermal imaging dual-spectrum camera is used for acquiring door and window images, the optical axis of the camera is perpendicular to the plane of a curtain wall door and window as much as possible, and the thermal imaging dual-spectrum camera means that the camera can acquire four channels of a color image (comprising three channels of RGB) and an infrared heat image (one channel) of the door and window at the same time.
If the time for acquiring the door and window image is summer, executing the subsequent steps based on the originally acquired infrared heat map; if the time for acquiring the door and window image is in winter, carrying out reverse phase processing on the infrared heat image to obtain a new infrared heat image, namely, the pixel value of each pixel point in the new infrared heat image is the difference value between the pixel value of the corresponding pixel point in the original infrared heat image and the maximum possible pixel value, the maximum possible pixel value is generally 255, and the subsequent steps are carried out based on the new infrared heat image.
Preferably, a plurality of air leakage points are determined based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows, specifically:
P i scoring the ith pixel point; g i The temperature of the ith pixel point is represented, max (g) represents the maximum value of the temperature of the pixel point in the door and window image, and the temperature of the pixel point is obtained based on an infrared heat map; d, d i Representing the shortest distance between the ith pixel point and the edges of the doors and windows, specifically, processing a color image of the doors and windows, namely an RGB image by using an edge detection algorithm to obtain edges of the doors and windows in the image, and performing edge detection by using a Canny operator in the embodiment to obtain an edge image of the doors and windows, wherein the value of the pixels of the edges of the doors and windows in the image is 1, and the values of the other pixels are 0; wherein d i Is the minimum value of the distance between the ith pixel point and each door and window edge pixel.
Determining air leakage points according to the scores of the pixel points: setting a scoring threshold, preferably, in the embodiment, the scoring threshold is 0.78, setting the pixel value of the pixel point with the scoring larger than the scoring threshold as 1 in the RGB image, setting the pixel value of the other pixels as 0 to obtain a binary image, carrying out connected domain analysis on the binary image to obtain a plurality of connected domains, searching the pixel point with the largest scoring value in each connected domain by utilizing a soft-argmax algorithm, wherein the found pixel point is the air leakage point, and further, acquiring the position coordinates of each air leakage point in the RGB image.
Step S2, for each adjacent area corresponding to each air leakage point, searching for a pixel point influenced by the air leakage point in the adjacent area; determining three-dimensional points corresponding to each found pixel point based on the pixel position and temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptic conical surface; each adjacent area corresponds to an elliptic conical surface; and for each air leakage point, acquiring an elliptical cone corresponding to each adjacent area of the air leakage point, and calculating the air leakage degree of the air leakage point according to the distance between the air leakage point and each elliptical cone.
(a) Setting the value of a door pixel in the door and window edge graph to 0 and the value of the other pixels to 1, obtaining a door and window plane binary graph, carrying out connected domain analysis on the door and window plane binary graph, obtaining a plurality of connected domains, searching adjacent areas corresponding to each air leakage point in the plurality of connected domains, specifically, calculating the minimum distance between the pixel point in each connected domain and the air leakage point for each air leakage point, wherein the plane corresponding to the connected domain with the minimum distance smaller than a preset distance threshold is the adjacent area corresponding to the air leakage point, and preferably, setting the distance threshold to 20 in the embodiment.
(b) For an adjacent area corresponding to one air leakage point, searching the pixel points affected by the air leakage point in the adjacent area, specifically: the air leakage point is taken as an original point, the inter-point distance d is taken as a transverse axis, and the temperature difference T between the points is taken d Establishing a clustering coordinate system for a longitudinal axis; the distance and the temperature difference between each pixel point and the air leakage point in the adjacent area are respectively the abscissa d and the ordinate T d Obtaining a plurality of points, clustering the plurality of points, and leading the points to a straight line T d The pixel point corresponding to the point in the cluster with the smallest average distance of d is the pixel point affected by the air leakage point; preferably, in the embodiment, a DBSCAN algorithm is adopted, the cluster radius eps is 5, and the density threshold MinPts is 7.
(c) Determining three-dimensional points corresponding to each found pixel point based on the pixel position and temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptic conical surface; specifically, the position of the air leakage point is taken as an original point, the row number of the pixels is taken as an x axis, the column number of the pixels is taken as a y axis, the temperature of the pixels is taken as a z axis, a three-dimensional coordinate system is established, three-dimensional coordinates (x, y, z) corresponding to each searched pixel point can be obtained based on the pixel position and the temperature of the pixel point, the pixel position of the pixel point is represented by (x, y), the temperature of the pixel point is represented by z, and the three-dimensional points corresponding to each searched pixel point are fitted by using a least square method to obtain an elliptic conical surface.
So far, for each air leakage point, each adjacent area corresponds to one elliptical cone.
(d) For each air leakage point, an elliptical cone corresponding to each adjacent area of the air leakage point is obtained, the air leakage degree of the air leakage point is calculated according to the distance between the air leakage point and each elliptical cone, the larger the distance between the air leakage point and the elliptical cone is, the larger the influence range of the air leakage point is, and the more serious the air leakage degree of the air leakage point is, specifically, the distance average value is obtained based on each distance, and the distance average value represents the air leakage degree of the air leakage point.
Preferably, in order to obtain a more accurate air leakage degree, in one embodiment, the reliability of the pixel points found in each adjacent area corresponding to each air leakage point is also calculated, specifically: based on the distance and the temperature difference between the found pixel points and the air leakage point, the distribution direction of the found pixel points is obtained by utilizing a principal component analysis method, and the credibility is calculated based on the distribution direction, specifically:
r is the reliability of the found pixel, and when r is greater than or equal to a preset reliability threshold, the found pixel is reliable and is not affected by noise, and preferably, the reliability threshold is 0.8 in the embodiment; lambda (lambda) 1 And lambda (lambda) 2 For the eigenvalues based on principal component analysis, (u, v) is max (λ 1 ,λ 2 ) Corresponding feature vectors. Since the influence of the air leakage point on the temperature of other pixels is only related to the distance, the points in the cluster coordinate system should be linearly distributed, and ideally the distribution of the points in the cluster coordinate system is in a straight line T d The better the linearity, the higher the confidence that the pixel is found, i.e. max (λ 1 ,λ 2 )-min(λ 1 ,λ 2 ) The larger the value of (c), the better the linearity of the distribution of points in the cluster coordinate system; the smaller the difference between u and v, the more points in the cluster coordinate system are distributed in the straight line T d Near =d.
When r is smaller than a preset credibility threshold, the clustering parameters need to be adjusted for re-clustering; for convenience of subsequent description, the calculation formula of the credibility is written asa. b respectively represents a split function at the left side and an exponential function at the right side of the bracket plus sign in the original formula, and specifically, when a is smaller than a preset credibility threshold value, the density threshold value MinPts of the DBSCAN clustering algorithm is reduced; when b is smaller than a preset credibility threshold, reducing the clustering radius eps of the DBSCAN clustering algorithm; when a and b are smaller than the preset valueAnd when the reliability is threshold, reducing the cluster radius eps and the density threshold MinPts of the DBSCAN clustering algorithm at the same time.
The distribution direction of the found pixel points is specifically: for the pixel points found in an adjacent area corresponding to one air leakage point, the distance and the temperature difference between each found pixel point and the air leakage point form a matrix of 2 rows and n columns, n represents that n pixel points are found altogether, one row of elements in the matrix are the distances between n pixel points and the air leakage point respectively, and the other row of elements are the temperature differences between n pixel points and the air leakage point respectively; further, the step of acquiring the covariance matrix based on the matrix of 2 rows and n columns, and specifically acquiring the covariance matrix is not described in detail in the present invention; performing eigenvalue decomposition on the covariance matrix to obtain corresponding eigenvalue lambda 1 、λ 2 Eigenvalue vector xi corresponding to eigenvalue 1 、ξ 2 The method comprises the steps of carrying out a first treatment on the surface of the The characteristic value maximum max (lambda 1 ,λ 2 ) The corresponding feature vector represents the distribution direction of the found n pixel points in the cluster coordinate system.
In one embodiment, for each air leakage point, the air leakage degree of the air leakage point is specifically obtained as follows: each adjacent area of the air leakage point corresponds to an elliptic conical surface, each elliptic conical surface corresponds to a credibility, the credibility is a weight, and the air leakage degree of the air leakage point is obtained after the distances between the air leakage point and each elliptic conical surface are weighted and averaged.
It is noted that the method and the device acquire the air leakage degree of the air leakage point based on the shortest distance between the air leakage point and each elliptic conical surface, and compared with the method and the device for calculating the average or minimum distance between the air leakage point and the searched pixels to acquire the air leakage degree of the air leakage point, the method and the device eliminate the influence of the pose of the camera on the calculation result, so that the acquired air leakage degree of the air leakage point is more accurate.
Step S3, evaluating the airtight performance of curtain wall doors and windows according to the air leakage degree of each air leakage point, and specifically:
q represents the air tightness evaluation score of curtain wall door and window, alpha k And K represents K total air leakage points for the air leakage degree of the kth air leakage point, and s represents the area of the acquired door and window image.
Acquiring the air tightness grade of the curtain wall door and window according to the air tightness performance evaluation score of the curtain wall door and window, and if Q is more than or equal to S3, the air tightness grade of the door and window is three-level; if Q is smaller than S3 and larger than or equal to S2, the air tightness grade of the door and window is two-grade; if Q is smaller than S2 and larger than or equal to S1, the air tightness grade of the door and window is one level; if Q is smaller than S1, the air tightness grade of the door and window is zero grade; in the examples, the value of S3 was 0.3, the value of S2 was 0.2, the value of S2 was 0.1, and the value of S1 was 0.05. The larger the Q value, the higher the corresponding air tightness grade, and the worse the air tightness of the door and window.
Based on the same inventive concept as the above method embodiments, one embodiment of the present invention provides a machine vision-based curtain wall door and window air tightness evaluation system, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the steps of a machine vision-based curtain wall door and window air tightness evaluation method.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (5)
1. The method for evaluating the airtight performance of the curtain wall door and window based on the machine vision is characterized by comprising the following steps of:
acquiring door and window images by using a thermal imaging double-spectrum camera; determining a plurality of air leakage points based on the temperature of the pixel points and the distance between the pixel points and the edges of the doors and windows;
for each adjacent area corresponding to each air leakage point, searching for a pixel point influenced by the air leakage point in the adjacent area; determining three-dimensional points corresponding to each found pixel point based on the pixel position and temperature of the pixel point, and fitting the three-dimensional points to obtain an elliptic conical surface; each adjacent area corresponds to an elliptic conical surface;
for each air leakage point, acquiring an elliptical cone corresponding to each adjacent area of the air leakage point, and calculating the air leakage degree of the air leakage point according to the distance between the air leakage point and each elliptical cone;
evaluating the airtight performance of curtain wall doors and windows according to the air leakage degree of each air leakage point;
searching the pixel points affected by the air leakage points in the adjacent areas, wherein the specific steps are as follows:
the distance and the temperature difference between each pixel point and the air leakage point in the adjacent area are respectively the abscissa d and the ordinate T d Obtaining a plurality of points, clustering the plurality of points, and leading the points to a straight line T d The pixel point corresponding to the point in the cluster with the smallest average distance of d is the pixel point affected by the air leakage point;
after searching the pixel points affected by the air leakage points in the adjacent areas, calculating the reliability of the searched pixel points:
based on the distance and the temperature difference between the found pixel points and the air leakage point, the distribution direction of the found pixel points is obtained by utilizing a principal component analysis method, and the credibility is calculated based on the distribution direction, specifically:
r is the credibility of the found pixel point, and when r is larger than or equal to a preset credibility threshold value, the found pixel point is credible; lambda (lambda) 1 And lambda (lambda) 2 For the eigenvalues based on principal component analysis, (u, v) is max (λ 1 ,λ 2 ) Corresponding feature vectors.
2. The method of claim 1, wherein the plurality of air leakage points are determined based on the temperature of the pixel points and the distance between the pixel points and the edges of the door and window, specifically:
P i scoring the ith pixel point; g i The temperature of the ith pixel point is represented, and Max (g) represents the maximum value of the temperature of the pixel point in the door and window image; d, d i Representing the shortest distance between the ith pixel point and the edge of the door and window;
and determining the air leakage point according to the scores of the pixel points.
3. The method of claim 1, wherein r is less than a predetermined confidence threshold, the clustering parameters are adjusted to re-cluster.
4. A method according to claim 3, wherein the air leakage degree is obtained specifically by: each elliptical cone corresponds to one credibility, the credibility is a weight, and the air leakage degree of the air leakage point is obtained after the distances between the air leakage point and each elliptical cone are weighted and averaged.
5. A machine vision based curtain wall door and window air tightness evaluation system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210289301.5A CN114689246B (en) | 2022-03-23 | 2022-03-23 | Curtain wall door and window airtight performance evaluation method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210289301.5A CN114689246B (en) | 2022-03-23 | 2022-03-23 | Curtain wall door and window airtight performance evaluation method and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114689246A CN114689246A (en) | 2022-07-01 |
| CN114689246B true CN114689246B (en) | 2023-11-14 |
Family
ID=82139142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210289301.5A Active CN114689246B (en) | 2022-03-23 | 2022-03-23 | Curtain wall door and window airtight performance evaluation method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114689246B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102636313A (en) * | 2012-04-11 | 2012-08-15 | 浙江工业大学 | Leakage source detecting device based on infrared thermal imaging processing |
| CN103557996A (en) * | 2013-11-14 | 2014-02-05 | 河北科技大学 | Device and method for visually detecting leakproofness of four-station bearing part |
| CN109211483A (en) * | 2018-08-23 | 2019-01-15 | 江苏省建筑科学研究院有限公司 | A kind of combined exterior wall plate static air pressure waterproof performance detection method |
| CN109520671A (en) * | 2018-11-22 | 2019-03-26 | 南京工业大学 | Cold-hot wind infiltration capacity method for quantitative measuring based on infrared thermal imaging technique |
-
2022
- 2022-03-23 CN CN202210289301.5A patent/CN114689246B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102636313A (en) * | 2012-04-11 | 2012-08-15 | 浙江工业大学 | Leakage source detecting device based on infrared thermal imaging processing |
| CN103557996A (en) * | 2013-11-14 | 2014-02-05 | 河北科技大学 | Device and method for visually detecting leakproofness of four-station bearing part |
| CN109211483A (en) * | 2018-08-23 | 2019-01-15 | 江苏省建筑科学研究院有限公司 | A kind of combined exterior wall plate static air pressure waterproof performance detection method |
| CN109520671A (en) * | 2018-11-22 | 2019-03-26 | 南京工业大学 | Cold-hot wind infiltration capacity method for quantitative measuring based on infrared thermal imaging technique |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114689246A (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100405828C (en) | Method and system for visual object detection | |
| CN109272520B (en) | Self-adaptive infrared focal plane non-uniform correction method combining motion guidance and edge detection | |
| CN107014294A (en) | A kind of contact net geometric parameter detection method and system based on infrared image | |
| CN111008991B (en) | Background-aware related filtering target tracking method | |
| CN107680113A (en) | The image partition method of multi-layer segmentation network based on Bayesian frame edge prior | |
| CN111429485B (en) | Cross-modal filtering tracking method based on self-adaptive regularization and high-reliability updating | |
| CN106570886B (en) | A kind of method for tracking target based on super-resolution rebuilding | |
| CN105469408A (en) | Building group segmentation method for SAR image | |
| CN111611907A (en) | Image-enhanced infrared target detection method | |
| CN101957993A (en) | Adaptive infrared small object detection method | |
| CN109446978B (en) | Method for tracking moving target of airplane based on staring satellite complex scene | |
| CN112150386B (en) | SAR image speckle non-local average inhibition method based on contrast mean value | |
| CN112288758B (en) | Infrared and visible light image registration method for power equipment | |
| CN111161324B (en) | Target tracking method based on self-adaptive multimode updating strategy | |
| CN114689246B (en) | Curtain wall door and window airtight performance evaluation method and system based on machine vision | |
| CN110296705B (en) | Visual SLAM loop detection method based on distance metric learning | |
| CN115937231A (en) | Infrared image iterative denoising method and system based on spectrum structure constraint | |
| CN106339693A (en) | Positioning method of face characteristic point under natural condition | |
| CN117314912A (en) | Visual detection method and system for welding defects on surface of welded pipe | |
| CN111738396A (en) | Self-adaptive grid granularity ant colony algorithm applied to submarine path planning | |
| CN102005050A (en) | Gaussian log model single-side curvature threshold fitting method used for change detection | |
| CN116543238B (en) | Image detection method for cable insulating layer | |
| CN108629227A (en) | The method and system on left and right vehicle wheel boundary are determined in the picture | |
| CN111462180A (en) | Object tracking method based on AND-OR graph AOG | |
| CN116258705A (en) | Window opening detection method based on image processing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |