CN112669286A - Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall - Google Patents
Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall Download PDFInfo
- Publication number
- CN112669286A CN112669286A CN202011602263.1A CN202011602263A CN112669286A CN 112669286 A CN112669286 A CN 112669286A CN 202011602263 A CN202011602263 A CN 202011602263A CN 112669286 A CN112669286 A CN 112669286A
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- binary image
- damage degree
- thermal insulation
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 68
- 238000009413 insulation Methods 0.000 title claims abstract description 41
- 238000003384 imaging method Methods 0.000 title description 2
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000003708 edge detection Methods 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 238000001931 thermography Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 20
- 238000012216 screening Methods 0.000 claims abstract description 14
- 230000005764 inhibitory process Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000001629 suppression Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 21
- 238000011156 evaluation Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000009422 external insulation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement 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
- 238000004321 preservation Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Abstract
The invention discloses a method for identifying defects and evaluating damage degree of an external thermal insulation system based on infrared thermography, and relates to a method for identifying defects and evaluating damage degree of an external thermal insulation system. The invention aims to solve the problems of low efficiency and poor accuracy caused by the fact that detection personnel are required to participate in detection judgment during detection of the external thermal insulation defect of the external wall by the existing infrared thermal imaging method. The process is as follows: firstly, carrying out image denoising processing on an acquired infrared thermograph, then converting the image subjected to denoising processing into a gray level image, and drawing a gray level histogram; secondly, calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image; thirdly, obtaining a binary image after contour extraction and outlining; fourthly, threshold segmentation is carried out on the binary image after contour extraction and delineation, and defects and the background of the binary image are segmented; and fifthly, calculating the defect area and the damage degree. The invention relates to the field of external thermal insulation system evaluation of external walls.
Description
Technical Field
The invention relates to a method for identifying defects and evaluating damage degree of an external thermal insulation system of an external wall.
Background
The external thermal insulation system of the building external wall can effectively improve the thermal insulation performance of the wall body and protect the main structure, and is one of important technical means for realizing the energy-saving goal of the building in China. The most widely applied organic benzene board type external heat insulation system at present. Due to the influence of raw materials, construction quality, system complexity and other factors, the quality of the external wall external insulation system is uneven, and the phenomenon that an external insulation layer falls off frequently occurs in a structure with the external wall external insulation system installed, so that great challenge is brought to the safety of urban buildings. How to carry out efficient and accurate quality monitoring and evaluation on a finished external thermal insulation system of an external wall and a newly-built external thermal insulation project and find out system defects in time to avoid causing personnel and property losses is one of the problems which need to be solved urgently by workers in the industry at present. The defect detection of the traditional external heat insulation system mainly adopts modes of manual hammering and the like, so that the efficiency is low, the cost is high, and the detection effect is unsatisfactory. According to the temperature-sensitive characteristic of the external thermal insulation system of the external wall, researchers provide a method for positioning and representing the defects of the external thermal insulation system of the external wall by using an infrared thermal imaging method. The infrared thermography is a detection method using an infrared image as a representation means as the name implies. The infrared thermograph shows the temperature distribution of the target surface, and the outer heat-insulating layer without defects can be regarded as a homogeneous material, and the surface temperature of the homogeneous material can be regarded as uniform distribution; when a defect occurs, the heat conductivity coefficient of the system changes, the temperature changes, and a temperature difference is generated. By analyzing the infrared thermograph, the temperature change can be captured, and then the information such as the position and the type of the defect can be obtained through inference, and further the defect detection can be realized.
At present, although the infrared thermal imaging method is more applied to the detection of the external thermal insulation defect of the external wall, the qualitative detection is mainly adopted, detection personnel are required to participate in detection and judgment, and the efficiency is low. Therefore, a defect detection method with high automation degree and high precision is needed.
Disclosure of Invention
The invention aims to solve the problems of low efficiency and poor accuracy caused by the fact that detection personnel are required to participate in detection judgment when the external thermal insulation defect of an external wall is detected by the existing infrared thermal imaging method, and provides an external thermal insulation system defect identification and damage degree evaluation method based on infrared thermal imaging.
The method for identifying the defects and evaluating the damage degree of the external thermal insulation system based on the infrared thermography comprises the following specific processes:
the external thermal insulation system of the external wall refers to an external wall enclosure structure which is widely used at present, has a plurality of different categories, and the external wall enclosure structure which plays a role in thermal insulation can be called as an external thermal insulation system.
The method comprises the following steps that firstly, an unmanned aerial vehicle collects an infrared thermograph of an outer wall of a building, carries out image denoising on the collected infrared thermograph, converts the denoised image into a gray level image, and draws a gray level histogram;
step two, calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image;
extracting the contour of the edge detection binary image by using a contour extraction algorithm to complete contour extraction; the extracted contour is sketched by using a contour sketching algorithm to obtain a binary image after contour extraction and sketching;
step four, performing threshold segmentation on the binary image after contour extraction and delineation, and segmenting the binary image defects and the background;
and step five, calculating the defect area and the damage degree based on the step four.
The invention has the beneficial effects that:
the method is accurate and efficient, and improves the efficiency and accuracy of the external thermal insulation defect identification and damage degree evaluation of the external wall. According to the invention, the judgment result can be obtained only by manually importing the pictures and the parameters, so that the automation degree of the external thermal insulation defect detection is greatly improved. The invention can realize real-time defect monitoring and provide guidance for external heat preservation and falling early warning. The invention improves the intellectualization, the automation and the accuracy of the external thermal insulation defect identification. The invention provides a solution for automatic identification and damage degree evaluation of the defects of the external thermal insulation system of the external wall. The defect identification and outline delineation, defect area calculation output and damage degree calculation output can be realized.
The invention aims to provide a method for identifying the thermal insulation defects and evaluating the damage degree of the outer wall of a building based on infrared thermography, which can realize the machine autonomous judgment of the defects through an infrared thermography acquired by an unmanned aerial vehicle and carry out the quantitative judgment of the damage degree of a system.
The qualitative analysis and the quantitative analysis are combined to carry out comprehensive analysis on the defects, the delineation marking of the defects is completed in the image by utilizing algorithms such as edge detection and the like, the calculation of the defect area and the damage degree is completed by utilizing threshold segmentation, and the detection efficiency is obviously improved;
the package software can realize parameter selection through man-machine interaction, and a user can adjust related parameters at any time according to an analysis result, so that the software operation is convenient and fast and is foolproof;
the defect detection only needs to manually input parameters, and compared with the traditional detection, the detection result is less influenced by the subjective judgment of detection personnel, and the judgment is more objective and more accurate.
Drawings
FIG. 1 is a flow chart of thermal insulation defect identification and damage degree evaluation outside a building outer wall based on infrared thermography;
FIG. 2 is a histogram of the acquired gray levels;
FIG. 3 is a binary image obtained by edge detection;
FIG. 4 is a sketch of a defect profile in an original IR thermograph;
FIG. 5 is a graph of adaptive threshold segmentation of a gray scale image after Gaussian denoising;
FIG. 6 is a global threshold segmentation graph of a gray scale image after Gaussian denoising.
Detailed Description
The first embodiment is as follows: the method for identifying the defects and evaluating the damage degree of the external thermal insulation system based on the infrared thermography comprises the following specific processes:
the external heat insulation system refers to an external wall enclosure structure which is widely used at present, and has a plurality of different categories, and the external wall enclosure structure with the heat insulation function can be called as the external heat insulation system.
The method comprises the following steps that firstly, an unmanned aerial vehicle collects an infrared thermograph of an outer wall of a building, carries out image denoising on the collected infrared thermograph, converts the denoised image into a gray level image, and draws a gray level histogram;
step two, calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image;
extracting the contour of the edge detection binary image by using a contour extraction algorithm to complete contour extraction; the extracted contour is sketched by using a contour sketching algorithm to obtain a binary image after contour extraction and sketching;
step four, performing threshold segmentation on the binary image after contour extraction and delineation, and segmenting the binary image defects and the background;
and step five, calculating the defect area and the damage degree based on the step four.
The second embodiment is as follows: the first difference between the present embodiment and the specific embodiment is: in the first step, the unmanned aerial vehicle collects an infrared thermograph of an outer wall of a building, carries out image denoising on the collected infrared thermograph, converts the denoised image into a gray level image, and draws a gray level histogram; the specific process is as follows:
carrying out image denoising on the collected infrared thermograph by adopting Gaussian filtering;
image denoising is carried out by adopting Gaussian filtering, and the Gaussian filtering is divided into two steps:
1) calculating a Gaussian mask;
2) convolution (i.e. inner product of pixel matrix near each point and Gaussian mask)
The gaussian mask (mask) is a gaussian kernel, which is a matrix for convolution, and is calculated based on a gaussian distribution. A gaussian distribution, i.e., a normal distribution, has a probability density function as follows:
the gaussian mask is two-dimensional, in which case only x and μ in the above equation have to be replaced by the corresponding vectors, as follows:
(x, y) is the coordinate of any point in the mask
(x0,y0) The coordinates of the center of the mask.
Using a 3x3 Gaussian mask as an example, for an arbitrary point (x) in an image0,y0) The coordinates of the surrounding points are:
taking sigma as 1, calculating to obtain:
finally, the matrix in the above formula is normalized to obtain the Gaussian mask, as follows:
after the Gaussian mask is obtained, the Gaussian mask is convolved with the image to complete Gaussian filtering.
The value of the gaussian mask is only related to the size of the mask matrix, i.e. the size of the gaussian kernel and the value of σ, and the latter generally takes the default value of 1, so that only the size of the gaussian kernel needs to be adjusted, and in the developed detection software, a user can adjust the gaussian kernel to obtain different filtering effects.
And inputting the Gaussian kernel parameters in a given range or adopting default parameters to obtain the denoised gray level image and the gray level histogram.
Other steps and parameters are the same as those in the first embodiment.
The third concrete implementation mode: the present embodiment differs from the first or second embodiment in that: calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image; the specific process is as follows:
the Canny algorithm is used for edge detection, and the algorithm comprises four steps: image denoising, image gradient acquisition, non-maximum value inhibition and threshold value screening.
Image denoising
The noise has a great influence on the edge detection of the image, and in order to improve the detection effect, the image needs to be denoised firstly. Canny edge detection applies a gaussian filtering algorithm to perform noise reduction processing on an image. The specific process is as described above.
Step two, calculating the gray gradient of pixel points in the gray image;
secondly, carrying out non-maximum value suppression on pixel points in the gray level image after the gray level gradient is solved in the second step;
non-maxima suppression is to remove all unwanted pixels that may not constitute an edge. Judging whether the pixel point obtains the maximum value of the adjacent area in the gradient direction at each pixel point in the gray level image, if so, reserving the point for subsequent processing, and otherwise, setting the value of the point as 0 (inhibiting);
with non-maxima suppression, the resulting edge detection image will be a binary image with "thin edges".
And step two, performing threshold screening on pixel points in the gray level image obtained in the step two to obtain an edge detection binary image.
Other steps and parameters are the same as those in the first or second embodiment.
The fourth concrete implementation mode: the difference between this embodiment and the first to third embodiments is that, in the second step, the gray gradient of the pixel point in the gray image is calculated; the specific process is as follows:
the gray scale change at the edge of the image is obvious, and the change of the gray scale can be known through the gradient of the image. Therefore, in this step, the Sobel operator is used to filter the denoised gray level image in the horizontal and vertical directions to obtain the first derivatives Gx, Gy of each pixel point in the x and y directions, and the gray level gradient calculation formula of the pixel points in the gray level image is as follows:
to improve the operation efficiency, the above equation can be simplified as follows:
G＝|GX|+|GY|
in the formula, Gx and Gy are first derivatives of the denoised grayscale image in the horizontal and vertical directions obtained by filtering the denoised grayscale image with Sobel operator, respectively, where the x direction is a direction parallel to the rows of the grayscale image matrix, and the y direction is a direction parallel to the columns of the grayscale image matrix (in a computer, the image is composed of arrays (matrices), and the image matrix refers to the matrices constituting the grayscale image).
Other steps and parameters are the same as those in one of the first to third embodiments.
The fifth concrete implementation mode: the difference between this embodiment and one of the first to fourth embodiments is: in the second step, threshold screening is carried out on pixel points in the gray level image obtained in the second step to obtain an edge detection binary image; the specific process is as follows:
and finally screening the edges by using threshold screening.
Setting two thresholds, minValue and maxValue, aiming at the gray gradient of each pixel point, and dividing the pixel points into three parts;
points with a gray gradient greater than maxValue must be edge points;
points whose gray scale gradient is less than minValue are necessarily non-edge points;
the point between the two points needs to be judged according to connectivity, if the point is connected with the edge point, the point is the edge point, otherwise, the point is a non-edge point;
and obtaining an edge detection binary image according to the edge points.
Other steps and parameters are the same as in one of the first to fourth embodiments.
The sixth specific implementation mode: the difference between this embodiment and one of the first to fifth embodiments is: in the third step, extracting the contour of the edge detection binary image by using a contour extraction algorithm to complete contour extraction; the extracted contour is sketched by using a contour sketching algorithm (the contour extraction and the sketching algorithm are provided in OpenCV and can be considered as known), and a binary image after contour extraction and sketching is obtained; the specific process is as follows:
and extracting the contour of the edge detection binary image by using a contour extraction algorithm findContours in OpenCV to finish contour extraction, and outlining the extracted contour by using a drawContours algorithm in OpenCV to obtain the contour-extracted and outlined binary image.
Other steps and parameters are the same as those in one of the first to fifth embodiments.
The seventh embodiment: the difference between this embodiment and one of the first to sixth embodiments is: in the fourth step, threshold segmentation is carried out on the binary image after contour extraction and delineation, and defects of the binary image and the background are segmented; the specific process is as follows:
there may be two implementation ways for this step: global threshold segmentation and adaptive threshold segmentation; a user can complete self-adaptive threshold segmentation to obtain a binary image, if the requirement is not met, a proper global threshold can be selected according to the gray level histogram, parameters in a given range are input, and the binary image is obtained; if the requirement is not met, the global threshold value can be changed, and the process is repeated until a threshold value segmentation binary image meeting the requirement is obtained;
the pixel value calculation formula of each pixel point in the threshold segmentation binary image is as follows:
in the formula, f (x, y) represents the pixel value of a pixel point with coordinates (x, y) in the gray level image after Gaussian denoising, g (x, y) represents the pixel value of a pixel point with coordinates (x, y) in a binary image obtained after threshold segmentation, T is a threshold, for global threshold segmentation, T is a global threshold, and for adaptive threshold segmentation, T is a local threshold;
other steps and parameters are the same as those in one of the first to sixth embodiments.
The specific implementation mode is eight: the present embodiment differs from one of the first to seventh embodiments in that: calculating the defect area and the damage degree in the fifth step based on the fourth step; the specific process is as follows:
when the unmanned aerial vehicle collects images, the optical axis is perpendicular to the object distance, so that the defect area and the damage degree can be estimated approximately through the actual size of the wall body; and segmenting the defect and the background by using a threshold segmentation binary image, counting the number of pixel points corresponding to the defect to obtain the defect area ratio, namely the damage degree, obtaining the defect area according to the actual area, and outputting a result.
Other steps and parameters are the same as those in one of the first to seventh embodiments.
The following examples were used to demonstrate the beneficial effects of the present invention:
the first embodiment is as follows:
as shown in FIG. 1, a set of thermal insulation defect identification and damage degree evaluation method based on infrared thermography for the exterior wall of a building comprises the following steps:
step one, obtaining a gray level histogram: performing image Gaussian denoising processing on an input infrared image by adopting default parameters, and then converting the image into a gray level image to obtain a gray level histogram, as shown in FIG. 2;
step two, edge detection: after the gray histogram is obtained, calculating the gray gradient of the pixel point, wherein the formula is as follows:
G＝|GX|+|GY|
in the formula, Gx and Gy are gradients in x and y directions obtained by using a Sobel operator, respectively, where the x direction is a direction parallel to rows of an image matrix, and the y direction is a direction parallel to columns of the image matrix.
Then, non-maximum value suppression is carried out, a minimum threshold value and a maximum threshold value are input, threshold value screening is carried out, and an edge detection binary image is obtained, as shown in fig. 3;
step three, contour extraction and delineation: after the edge detection binary image is obtained, extracting the contour by using a contour extraction algorithm; then, finishing contour delineation by using a contour delineation algorithm, wherein the delineated defect contour is shown as a figure 4;
step four, threshold segmentation: firstly, completing adaptive threshold segmentation to obtain a binary image, as shown in fig. 5, obviously, the segmentation effect does not meet the requirement; selecting and inputting a proper global threshold according to the gray level histogram to obtain a binary image, as shown in fig. 6; the pixel value calculation formula of each pixel point in the threshold segmentation binary image is as follows:
in the formula, f (x, y) represents a pixel value of a pixel point with coordinates (x, y) in the gray image after gaussian denoising, g (x, y) represents a pixel value of a pixel point with coordinates (x, y) in a binary image obtained after threshold segmentation, T is a threshold, for global threshold segmentation, T is a global threshold, and for adaptive threshold segmentation, T is a local threshold.
Step five, calculating the defect area and the damage degree: the defect and background pixel values in the threshold segmentation binary image are different, the defect area ratio is obtained through the statistics of pixel points, the damage degree is 0.4853%, and the actual area of the wall body obtained through actual measurement calculation is 228cm2Calculating the defect area to be 1.1064cm2。
The present invention is capable of other embodiments and its several details are capable of modifications in various obvious respects, all without departing from the spirit and scope of the present invention.
Claims (8)
1. The method for identifying the defects and evaluating the damage degree of the external thermal insulation system based on the infrared thermography is characterized by comprising the following steps of: the method comprises the following specific processes:
the method comprises the following steps that firstly, an unmanned aerial vehicle collects an infrared thermograph of an outer wall of a building, carries out image denoising on the collected infrared thermograph, converts the denoised image into a gray level image, and draws a gray level histogram;
step two, calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image;
extracting the contour of the edge detection binary image by using a contour extraction algorithm to complete contour extraction; the extracted contour is sketched by using a contour sketching algorithm to obtain a binary image after contour extraction and sketching;
step four, performing threshold segmentation on the binary image after contour extraction and delineation, and segmenting the binary image defects and the background;
and step five, calculating the defect area and the damage degree based on the step four.
2. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 1, wherein: in the first step, the unmanned aerial vehicle collects an infrared thermograph of an outer wall of a building, carries out image denoising on the collected infrared thermograph, converts the denoised image into a gray level image, and draws a gray level histogram; the specific process is as follows:
and carrying out image denoising on the collected infrared thermograph by adopting Gaussian filtering.
3. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 1 or 2, wherein: calculating the gray gradient of pixel points in the gray image, then carrying out non-maximum value inhibition, and finally carrying out threshold value screening to obtain an edge detection binary image; the specific process is as follows:
step two, calculating the gray gradient of pixel points in the gray image;
secondly, carrying out non-maximum value suppression on pixel points in the gray level image after the gray level gradient is solved in the second step;
and step two, performing threshold screening on pixel points in the gray level image obtained in the step two to obtain an edge detection binary image.
4. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 3, wherein: in the second step, the gray gradient of the pixel points in the gray image is calculated; the specific process is as follows:
filtering the denoised gray level image in the horizontal and vertical directions by using a Sobel operator to obtain first derivatives Gx and Gy of each pixel point in the x and y directions, wherein a gray level gradient calculation formula of the pixel points in the gray level image is as follows:
the above equation is simplified as follows:
G＝GX|+|GY|
in the formula, Gx and Gy are first derivatives of the denoised gray image in the x and y directions obtained by filtering the denoised gray image in the horizontal and vertical directions by using a Sobel operator, respectively, where the x direction is a direction parallel to a gray image matrix row, and the y direction is a direction parallel to a gray image matrix column.
5. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 4, wherein: in the second step, threshold screening is carried out on pixel points in the gray level image obtained in the second step to obtain an edge detection binary image; the specific process is as follows:
setting two thresholds, minValue and maxValue, aiming at the gray gradient of each pixel point, and dividing the pixel points into three parts;
points with a gray gradient greater than maxValue must be edge points;
points whose gray scale gradient is less than minValue are necessarily non-edge points;
the point between the two points needs to be judged according to connectivity, if the point is connected with the edge point, the point is the edge point, otherwise, the point is a non-edge point;
and obtaining an edge detection binary image according to the edge points.
6. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 5, wherein: in the third step, extracting the contour of the edge detection binary image by using a contour extraction algorithm to complete contour extraction; the extracted contour is sketched by using a contour sketching algorithm to obtain a binary image after contour extraction and sketching; the specific process is as follows:
and extracting the contour of the edge detection binary image by using a contour extraction algorithm findContours in OpenCV to finish contour extraction, and outlining the extracted contour by using a drawContours algorithm in OpenCV to obtain the contour-extracted and outlined binary image.
7. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 6, wherein: in the fourth step, threshold segmentation is carried out on the binary image after contour extraction and delineation, and defects of the binary image and the background are segmented; the specific process is as follows:
the pixel value calculation formula of each pixel point in the threshold segmentation binary image is as follows:
in the formula, f (x, y) represents the pixel value of a pixel point with coordinates (x, y) in the gray image after gaussian denoising, g (x, y) represents the pixel value of a pixel point with coordinates (x, y) in a binary image obtained after threshold segmentation, and T is a threshold.
8. The method for identifying the defects and evaluating the damage degree of the thermal insulation system outside the outer wall based on the infrared thermography as claimed in claim 7, wherein: calculating the defect area and the damage degree in the fifth step based on the fourth step; the specific process is as follows:
and counting the number of pixels corresponding to the defect to obtain the defect area ratio, namely the damage degree, obtaining the defect area according to the actual area, and outputting a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011602263.1A CN112669286A (en) | 2020-12-29 | 2020-12-29 | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011602263.1A CN112669286A (en) | 2020-12-29 | 2020-12-29 | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112669286A true CN112669286A (en) | 2021-04-16 |
Family
ID=75410607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011602263.1A Pending CN112669286A (en) | 2020-12-29 | 2020-12-29 | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669286A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052833A (en) * | 2021-04-20 | 2021-06-29 | 东南大学 | Non-vision field imaging method based on infrared thermal radiation |
| CN113588090A (en) * | 2021-07-05 | 2021-11-02 | 东莞市鑫泰仪器仪表有限公司 | Human body searching method and system based on thermal imaging of unmanned aerial vehicle |
| CN114018946A (en) * | 2021-10-20 | 2022-02-08 | 武汉理工大学 | OpenCV-based high-reflectivity bottle cap defect detection method |
| CN114359416A (en) * | 2022-03-17 | 2022-04-15 | 山东水利建设集团有限公司 | Building outer wall hollowing leakage abnormity detection and positioning method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108414526A (en) * | 2018-02-02 | 2018-08-17 | 江苏方建质量鉴定检测有限公司 | A kind of sloughing of exterior wall detecting system |
| WO2018216629A1 (en) * | 2017-05-22 | 2018-11-29 | キヤノン株式会社 | Information processing device, information processing method, and program |
| CN109658376A (en) * | 2018-10-24 | 2019-04-19 | 哈尔滨工业大学 | A kind of surface defect recognition method based on image recognition |
| CN110044964A (en) * | 2019-04-25 | 2019-07-23 | 湖南科技大学 | Architectural coating layer debonding defect recognition methods based on unmanned aerial vehicle thermal imaging video |
| CN110555345A (en) * | 2018-06-01 | 2019-12-10 | 北京深鉴智能科技有限公司 | Intelligent image analysis system and method |
| CN111260616A (en) * | 2020-01-13 | 2020-06-09 | 三峡大学 | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization |
-
2020
- 2020-12-29 CN CN202011602263.1A patent/CN112669286A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018216629A1 (en) * | 2017-05-22 | 2018-11-29 | キヤノン株式会社 | Information processing device, information processing method, and program |
| CN108414526A (en) * | 2018-02-02 | 2018-08-17 | 江苏方建质量鉴定检测有限公司 | A kind of sloughing of exterior wall detecting system |
| CN110555345A (en) * | 2018-06-01 | 2019-12-10 | 北京深鉴智能科技有限公司 | Intelligent image analysis system and method |
| CN109658376A (en) * | 2018-10-24 | 2019-04-19 | 哈尔滨工业大学 | A kind of surface defect recognition method based on image recognition |
| CN110044964A (en) * | 2019-04-25 | 2019-07-23 | 湖南科技大学 | Architectural coating layer debonding defect recognition methods based on unmanned aerial vehicle thermal imaging video |
| CN111260616A (en) * | 2020-01-13 | 2020-06-09 | 三峡大学 | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052833A (en) * | 2021-04-20 | 2021-06-29 | 东南大学 | Non-vision field imaging method based on infrared thermal radiation |
| CN113588090A (en) * | 2021-07-05 | 2021-11-02 | 东莞市鑫泰仪器仪表有限公司 | Human body searching method and system based on thermal imaging of unmanned aerial vehicle |
| CN114018946A (en) * | 2021-10-20 | 2022-02-08 | 武汉理工大学 | OpenCV-based high-reflectivity bottle cap defect detection method |
| CN114018946B (en) * | 2021-10-20 | 2023-02-03 | 武汉理工大学 | OpenCV-based high-reflectivity bottle cap defect detection method |
| CN114359416A (en) * | 2022-03-17 | 2022-04-15 | 山东水利建设集团有限公司 | Building outer wall hollowing leakage abnormity detection and positioning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112669286A (en) | Infrared thermal image-based method for identifying defects and evaluating damage degree of external thermal insulation system of external wall | |
| CN108038883B (en) | Crack detection and identification method applied to highway pavement video image | |
| CN109978839B (en) | Method for detecting wafer low-texture defects | |
| CN108827181B (en) | Vision-based plate surface detection method | |
| CN110033431B (en) | Non-contact detection device and detection method for detecting corrosion area on surface of steel bridge | |
| JP6099479B2 (en) | Crack detection method | |
| JP5852919B2 (en) | Crack detection method | |
| CN113109368A (en) | Glass crack detection method, device, equipment and medium | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN116664559B (en) | Machine vision-based memory bank damage rapid detection method | |
| CN111489337A (en) | Method and system for removing false defects through automatic optical detection | |
| CN111060442A (en) | Oil particle detection method based on image processing | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN111476712B (en) | Trolley grate image shooting and detecting method and system of sintering machine | |
| CN114549441A (en) | Sucker defect detection method based on image processing | |
| CN113506246A (en) | Concrete 3D printing component fine detection method based on machine vision | |
| CN115841633A (en) | Power tower and power line associated correction power tower and power line detection method | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN113205494B (en) | Infrared small target detection method and system based on adaptive scale image block weighting difference measurement | |
| CN108765463B (en) | Moving target detection method combining region extraction and improved textural features | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| CN108898080B (en) | Ridge line neighborhood evaluation model-based crack connection method | |
| CN114758139B (en) | Method for detecting accumulated water in foundation pit | |
| CN113643290B (en) | Straw counting method and device based on image processing and storage medium | |
| CN115601379A (en) | Surface crack accurate detection technology based on digital 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |
|
| RJ01 | Rejection of invention patent application after publication |