CN115880299B - Quality detection system of light concrete composite self-insulation external wall panel - Google Patents
Quality detection system of light concrete composite self-insulation external wall panel Download PDFInfo
- Publication number
- CN115880299B CN115880299B CN202310193337.8A CN202310193337A CN115880299B CN 115880299 B CN115880299 B CN 115880299B CN 202310193337 A CN202310193337 A CN 202310193337A CN 115880299 B CN115880299 B CN 115880299B
- Authority
- CN
- China
- Prior art keywords
- pixel point
- gray
- value
- pixel
- neighborhood
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 239000002131 composite material Substances 0.000 title claims abstract description 18
- 238000009413 insulation Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000004321 preservation Methods 0.000 claims abstract description 25
- 230000000739 chaotic effect Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000010606 normalization Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 4
- 210000003195 fascia Anatomy 0.000 claims 1
- 238000007689 inspection Methods 0.000 claims 1
- 238000012372 quality testing Methods 0.000 claims 1
- 230000008859 change Effects 0.000 description 15
- 230000000875 corresponding effect Effects 0.000 description 8
- 230000007547 defect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 239000010410 layer Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000011162 core material Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000002002 slurry Substances 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/90—Passive houses; Double facade technology
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a quality detection system of a light concrete composite self-heat-preservation external wall panel, which relates to the field of image processing and comprises: and an image acquisition module: the method comprises the steps of acquiring gray images of an inner panel and an outer panel of the thermal insulation external wall panel to be detected; and a pretreatment module: the method comprises the steps of obtaining a chaotic degree parameter of each pixel point; determining seed points by using the chaotic degree parameters; and a data processing module: acquiring an edge characteristic value of each pixel point; obtaining a region growth judgment value of each pixel point by using the gray value and the edge characteristic value of each pixel point; region growing module: the method comprises the steps of using a region growth judgment value of a pixel point which is grown and a pixel point to be grown as a region growth condition, and using seed points in a gray level image to perform region growth to obtain a plurality of regions; and a judging module: and the detection device is used for determining the damage area of the thermal insulation external wall panel to be detected according to the edge characteristic value. The invention improves the accuracy of quality detection of the self-heat-preservation external wall panel.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a quality detection system of a lightweight concrete composite self-heat-preservation external wall panel.
Background
The light concrete composite self-heat-insulating external wall panel not only can exert the heat-insulating effect on the wall body, but also has the advantages of fire resistance, corrosion resistance and light weight, and gradually develops into a main flow form of the building external wall. The existing self-heat-preservation external wall panel is a sandwich heat-preservation external wall panel which clamps a composite heat-preservation board in the middle by using concrete, and is adhered to a wall surface through concrete layers on two sides. If the surface of the self-heat-preservation external wall panel is damaged, the external wall panel is uneven in structure, and the self-heat-preservation external wall panel can fall off, so that the quality detection of the self-heat-preservation external wall panel is particularly important.
Because the detection efficiency of manual spot check is lower and the qualification standard of human factor influence is not clear enough, the quality detection result of the self-insulation external wall panel is not accurate enough, and in order to obtain the quality detection results of all self-insulation external wall panels more efficiently and accurately, a computer vision detection method with higher identification accuracy and detection efficiency, which is used for introducing most of defect detection, is considered. According to the gray level difference of the edge part in the image, a region growing algorithm is carried out to obtain a defect region and a normal region in the image, but the inner surface and the outer surface of the self-heat-insulation external wall panel are made of concrete, the surface of the concrete is rough, the gray level distribution is disordered, a large number of rough interference pixel points exist to influence the region growing algorithm when region division is carried out, when region growth based on gray level values is carried out, the gray level average value of the grown region can be changed along with the change of growing gray level, and along with the addition of the interference points, the two regions with large gray level and gradient difference are easily combined into one region, so that the subsequent distinguishing and identification of a damaged region and a normal region are influenced, and the quality detection result of the self-heat-insulation external wall panel is inaccurate.
Disclosure of Invention
The invention provides a quality detection system of a light concrete composite self-heat-preservation external wall panel, which aims to solve the problem that the quality detection result of the obtained self-heat-preservation external wall panel is inaccurate due to interference of the existing rough concrete surface on an area growth algorithm based on gray scale.
The invention discloses a quality detection system of a light concrete composite self-heat-preservation external wall panel, which comprises the following components:
and an image acquisition module: the method comprises the steps of acquiring gray images of an inner panel and an outer panel of the thermal insulation external wall panel to be detected;
and a pretreatment module: the method comprises the steps of obtaining gray fluctuation degree of each pixel according to gray values of each pixel and a neighborhood pixel in a gray image, and obtaining chaotic degree parameters of each pixel by using the gray fluctuation degree of each pixel and the neighborhood pixel;
taking a pixel point with the chaotic degree parameter larger than a preset parameter threshold as a seed point;
and a data processing module: the method comprises the steps of obtaining an edge characteristic value of each pixel point according to a gray gradient value of each pixel point in a gray image and gray values of neighbor pixel points of the gray gradient value;
obtaining a region growth judgment value of each pixel point by using the gray value and the edge characteristic value of each pixel point;
region growing module: performing region growth by using seed points in the gray level image, and taking the region growth judgment values of the grown pixel points and the pixel points to be grown as region growth conditions, wherein the grown pixel points refer to the pixel points subjected to region growth;
and a judging module: and the detection device is used for determining the damaged area of the thermal insulation external wall panel to be detected according to the edge characteristic value of the pixel point in each area.
Further, in the region growing module, performing region growing using the seed points in the grayscale image includes:
subtracting the average value of the area growth judgment values of the grown pixel points from the area growth judgment value of the pixel points to be grown to obtain a difference value;
if the absolute value of the obtained difference value is smaller than the set judging threshold value, performing region growth, and updating the corresponding pixel point to be grown into a grown pixel point;
if the absolute value of the obtained difference value is not smaller than the set judgment threshold value, the corresponding pixel point to be grown is not updated.
Further, the method for obtaining the area growth judgment value of each pixel point comprises the following steps:
multiplying the duty ratio of the gray value of each pixel point in the total gray value by the preset weight of the gray value to obtain the gray characteristic of each pixel point;
multiplying the edge characteristic value of each pixel point by the preset weight of the edge characteristic value to obtain the edge characteristic of each pixel point;
and combining the gray characteristic and the edge characteristic of each pixel point to obtain the region growth judgment value of each pixel point.
Further, in the preprocessing module, the square of the gray difference value between each pixel point and each neighborhood pixel point is obtained, and the average value of the squares of the gray difference values of a plurality of neighborhood pixel points obtained by each pixel point is obtained to obtain the gray fluctuation degree of each pixel point.
Further, in the preprocessing module, the method for acquiring the chaotic degree parameter of each pixel point is as follows:
acquiring the average value of the difference value between the gray level fluctuation degree of each pixel point and the gray level fluctuation degree of the adjacent pixel point;
and carrying out negative correlation mapping on the value obtained by the mean normalization of each pixel point to obtain the chaotic degree parameter of each pixel point.
Further, the method for obtaining the edge characteristic value of each pixel point comprises the following steps:
obtaining the maximum gray difference value between the neighborhood pixel points of each pixel point;
acquiring gray distribution characteristic values of each neighborhood pixel point in the neighborhood of each pixel point;
taking the product of the gray gradient value of each pixel point and the maximum gray difference value between the adjacent pixel points as a molecule;
taking the average value of the gray distribution characteristic values of the neighborhood pixel points of each pixel point as a denominator;
and normalizing the ratio of the numerator to the denominator corresponding to each pixel point to obtain the edge characteristic value of each pixel point.
Further, the method for obtaining the gray distribution characteristic value of each neighborhood pixel point in the neighborhood of each pixel point comprises the following steps:
obtaining a gray level distribution characteristic value of each neighborhood pixel point in the neighborhood according to the gray level value difference value of each neighborhood pixel point and the adjacent pixel point in the neighborhood of each pixel point;
the expression for obtaining the gray distribution characteristic value of each neighborhood pixel point in the neighborhood of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
In-neighborhood of each pixel point
Gray level distribution characteristic values of the adjacent pixel points;
represent the first
In-neighborhood of each pixel point
Gray values of the neighboring pixel points;
，
respectively represent the first
In-neighborhood and the first pixel point
Adjacent first adjacent pixel points of each neighborhood
A plurality of neighborhood pixel points and a first pixel point
Gray values of the neighboring pixels.
Further, the method for obtaining the damaged area of the thermal insulation external wall panel to be detected comprises the following steps:
acquiring the average value of the edge characteristic values of the pixel points in each region;
and taking the area, the average value of the edge characteristic values of which is smaller than the preset damage threshold value, as the damage area of the thermal insulation external wall panel to be detected.
Further, in the region growing module, when any seed point is selected to perform the first step of region growth, the grown pixel point refers to the seed point selected initially.
The beneficial effects of the invention are as follows: according to the quality detection system of the lightweight concrete composite self-heat-preserving external wall panel, the chaotic degree parameter of each pixel point is obtained according to the gray distribution condition of the pixel points around the pixel point, namely the gray fluctuation degree of the pixel points, and the chaotic degree parameter is used for determining the seed points for regional growth. The edge characteristic value is determined through the gray gradient value of the pixel point and the gray value of the neighborhood pixel point, and then the edge characteristic value and the gray value of the pixel point are used for judging the region growth, so that compared with the conventional algorithm, the gray average value judgment of the grown region is more accurate, the influence of the gray average value of the grown pixel point generated by the gray change in the gradient region on the growth rule in the conventional algorithm is avoided, the obtained region is more accurate, and the condition that the damaged region and the normal region are divided into the same region is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic structural diagram of a quality detection system of a lightweight concrete composite self-insulating external wall panel according to the present invention;
FIG. 2 is a gray scale image of the inner and outer panels of the self-insulating exterior wall panel;
fig. 3 is an edge image of a gray scale image of the inner and outer panels of the self-insulating exterior wall panel.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
An embodiment of a quality detection system for a lightweight concrete composite self-insulating external wall panel of the present invention, as shown in fig. 1, comprises: the device comprises an image acquisition module 10, a preprocessing module 11, a data processing module 12, a region growing module 13 and a judging module 14.
Image acquisition module 10: the method is used for acquiring gray images of the inner panel and the outer panel of the thermal insulation external wall panel to be detected.
The light concrete composite self-heat-preservation external wall board is of a sandwich structure and mainly comprises an inner panel, a core material and an outer panel, the appearance quality of the sandwich heat-preservation external wall board is required to meet the requirements of durability of prefabricated components and integral attractive appearance of an assembled concrete structural engineering, the surface of the panel is required to be smooth and flat, the inner panel is required to be adhered with a structural layer (wall body) by coating an interface agent, and the outer layer is required to be fixed on an outer wall decorative surface layer through an inner bolt fixing steel wire mesh or fixed on the outer wall decoration by using the interface agent. In the production process of the self-heat-preservation external wall panel, uneven templates, inaccurate slab joints, water seepage and slurry leakage or uneven filling of steel wire meshes can occur, and if the inner panel structure of the self-heat-preservation external wall panel is uneven, the self-heat-preservation external wall panel can be caused to fall off; if the outer panel structure of the self-heat-preservation external wall panel is uneven, the possibility of falling off and breakage of the external wall decoration can be caused.
Therefore, the inner side and the outer side of the self-heat-preservation external wall board are required to be guaranteed to be free of defects, and the self-heat-preservation external wall board is prevented from falling off or the external wall is prevented from being decorated and falling off, so that quality detection is required to be carried out on the inner panel and the outer panel of the self-heat-preservation external wall board.
Specifically, a camera is arranged above the production line of the self-heat-preservation external wall panel and is used for collecting images of an inner panel and an outer panel of the self-heat-preservation external wall panel, and the inner panel and the outer panel are made of the same material, so that the images of the inner panel and the outer panel are not distinguished under the condition of no damage defect, the collected images of the inner panel and the outer panel are processed in the same manner, and the images of the inner panel and the outer panel are subjected to gray processing to obtain gray images of the inner panel and the outer panel.
Pretreatment module 11: the method comprises the steps of obtaining gray fluctuation degree of each pixel according to gray values of each pixel and a neighborhood pixel in a gray image, and obtaining chaotic degree parameters of each pixel by using the gray fluctuation degree of each pixel and the neighborhood pixel; and taking the pixel points with the chaotic degree parameters larger than the preset parameter threshold as seed points.
The traditional region growing algorithm classifies the pixel points with similar characteristics into one type by calculating the positions, gray scale relations and the like of the pixel points and the seed points, but the seed point selection of the traditional algorithm determines the advantages and disadvantages of the dividing effect, and if the pixel points at the two characteristic boundaries are used as the seed points, the two characteristics are divided into the same region, the two characteristic boundaries are the boundaries of a damaged region and a normal region, and the damaged region and the normal region on the inner panel and the outer panel cannot be accurately distinguished in the follow-up process. Thus, in this scheme, the selected seed points need to be able to properly reflect the region characteristics.
The surface of the panel of the concrete heat-insulating board belongs to a rough surface, and the internal raw materials are likely to be clustered due to insufficient stirring and the like, so that the surface of the concrete is rough, the gray level change of a rough area is frequent but the change degree is approximate, and the gray level change frequency of the abnormal area, namely the internal gray level change frequency of a damaged area is reduced and the change degree is smaller, and the gray level gradient of the edge of the abnormal area is larger. Therefore, the pixel points of the normal area of the inner panel and the outer panel are displayed as the pixel points which change frequently but have similar change degrees in the gray level image, and the seed points in the area growth need to be selected to reflect the characteristics of the area.
Specifically, the square of the gray difference value between each pixel point and each adjacent pixel point is obtained, the square of the gray difference value between a plurality of adjacent pixel points obtained by each pixel point is averaged to obtain the gray fluctuation degree of each pixel point, and the expression for obtaining the gray fluctuation degree of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
The gray level fluctuation degree of each pixel point refers to the fluctuation degree of the gray level value of the pixel point relative to the gray level value of the neighborhood pixel point;
representing the first in a gray scale image
Gray values of the individual pixels;
representing the first in a gray scale image
In-neighborhood of each pixel point
Gray values of the neighboring pixel points; the gray level fluctuation degree of each pixel point is represented by the gray level difference of the pixel points in 8 neighborhoods of each pixel point, namely, the average value of the squares of the gray level values of each pixel point and the pixel points in the neighborhood of 8 pixel points is taken as the gray level fluctuation degree of the corresponding pixel point; the larger the gray scale fluctuation degree of the pixel point is, the larger the gray scale distribution difference around the pixel point is.
Acquiring the average value of the difference value between the gray level fluctuation degree of each pixel point and the gray level fluctuation degree of the adjacent pixel point; carrying out negative correlation mapping on the value obtained by the mean normalization of each pixel point to obtain a chaotic degree parameter of each pixel point, wherein the expression for obtaining the chaotic degree parameter of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
A chaotic degree parameter of each pixel point;
representing the first in a gray scale image
Gray scale fluctuation degree of each pixel point;
represent the first
In-neighborhood of each pixel point
Gray scale fluctuation degree of each neighborhood pixel point;
the value range is [0,1 ] as the existing normalization function]。
Determining the confusion degree around the pixel point by the difference between each neighborhood pixel point in 8 neighborhood around the pixel point and the gray level fluctuation degree of the pixel point and utilizing a normalization function
The average value of the difference of the obtained gray level fluctuation degrees is normalized, the obtained normalized value is subjected to negative correlation mapping by using a numerical value 1, the larger the chaotic degree parameter of a pixel point is, the more similar the gray level fluctuation degree of the pixel point around the pixel point is, namely the more likely that the pixel point and 8 neighborhood pixel points belong to the same area, the more likely that the pixel point and the 8 neighborhood pixel points belong to the normal area or all belong to the damaged area, the more suitable the pixel point is used for carrying out area growth, namely the less the possibility that two features are divided into the same area is generated, and the more accurate the division result is.
Empirically given parameter thresholds for chaotic degree parametersIs that
When the chaotic degree parameter of a certain pixel point in the gray level image
When the pixel point and 8 neighborhood pixel points are more likely to belong to the same region, namely the pixel point can be used for growing and dividing the pixel point region in the region.
Acquiring all chaotic degree parameters in gray level image
The pixel points of (a) are used as seed points to form a seed point set.
The data processing module 12: the method comprises the steps of obtaining an edge characteristic value of each pixel point according to a gray gradient value of each pixel point in a gray image and gray values of neighbor pixel points of the gray gradient value; and obtaining the region growth judgment value of each pixel point by using the gray value and the edge characteristic value of each pixel point.
Because of the difference of the pouring process of the concrete surface, the gray scale image of the inner and outer wallboards presents gray scale area blocking, wherein the blocks are mostly changed gradually, and no obvious boundary exists in the gradual change area, so when the area grows to the gradual change area by utilizing the traditional area growth algorithm based on the gray scale average value and the pixel point distance, the gray scale average value of the grown area is changed along with the gray scale value of the pixel point to be grown, when the gray scale average value of the grown area is changed to a certain extent, the gray scale value of a certain pixel point to be grown is possibly larger than the initial average value, and compared with the current gray scale average value, the gray scale average value of the grown area is smaller than the growth threshold value, and the possibility of growth error is generated, namely the gray scale average value of the grown area is changed along with the change of the growth gray scale, and the two areas with large gradient change are possibly combined into one area.
Because the manufacturing process of the inner panel and the outer panel of the self-heat-preservation external wall panel is concrete pouring, the surfaces of the inner panel and the outer panel are rough, a large number of interference pixel points exist in a gray level image, detection of an abnormal area can be interfered, the gray level image of the inner panel and the outer panel is shown in fig. 2, and the edge image obtained by detecting the edges of the gray level image of the inner panel and the outer panel is shown in fig. 3. The gray level difference between the interference pixel point and the neighborhood pixel point in the edge image is larger, but the gray level difference value is approximate, namely the gray level difference between the neighborhood pixel points of the pixel points is not obvious, and the gray level difference between the neighborhood pixel points of the pixel points at the edges of the two areas is obvious, namely the gray level values of the pixel points in the areas at the two sides of the edge pixel point fluctuate in different mean value ranges, and the image is segmented according to the characteristics.
Specifically, obtaining the maximum gray difference value between the neighborhood pixel points of each pixel point; acquiring gray distribution characteristic values of each neighborhood pixel point in the neighborhood of each pixel point; taking the product of the gray gradient value of each pixel point and the maximum gray difference value between the adjacent pixel points as a molecule; taking the average value of the gray distribution characteristic values of the neighborhood pixel points of each pixel point as a denominator; and normalizing the ratio of the numerator to the denominator corresponding to each pixel point to obtain the edge characteristic value of each pixel point. The formula for obtaining the edge characteristic value of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
The edge feature values of the individual pixel points,
represent the first
The gray gradient value of each pixel point,
represent the first
Neighborhood gray scale range of each pixel point, namely the difference value between the maximum gray scale value and the minimum gray scale value of the neighborhood pixel point in 8 neighborhood of the pixel point;
representing the first in a gray scale image
In-neighborhood of each pixel point
Gray level distribution characteristic values of the adjacent pixel points;
the value range is [0,1 ] as the existing normalization function]。
Optionally, the sobel operator is used to calculate the gray gradient value of each pixel point. Obtaining a gray level distribution characteristic value of each neighborhood pixel point in the neighborhood according to the gray level value difference value of each neighborhood pixel point and the adjacent pixel point in the neighborhood of the pixel point; the expression for acquiring the gray distribution characteristic value of each neighborhood pixel point in the neighborhood of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
In-neighborhood of each pixel point
Gray level distribution characteristic values of the adjacent pixel points;
represent the first
In-neighborhood of each pixel point
Gray values of the neighboring pixel points;
，
respectively represent the first
In-neighborhood and the first pixel point
Adjacent first adjacent pixel points of each neighborhood
A plurality of neighborhood pixel points and a first pixel point
Gray values of the neighboring pixels. Each neighborhood pixel point has two adjacent pixel points, the first
And
the adjacent pixel points may be any one of the two pixel points, and are not particularly limited. The gray distribution characteristic value of each neighborhood pixel point is calculated to represent the gray difference between the neighborhood pixel points, and the larger the gray difference between the neighborhood pixel points is, the more likely the center pixel point corresponding to the neighborhood pixel point is considered to belong to the boundary of two areas, the smaller the probability that the neighborhood pixel point of the pixel point belongs to the same area is.
In the formula for calculating the edge feature value of each pixel point, the first
The larger the gray gradient value of each pixel point is, the two pixels belong toThe larger the probability of the boundary of each region is, the smaller the gray gradient value is, and the probability that the pixel belongs to the inside of the region is larger;
represent the first
The larger the neighborhood gray scale range of each pixel point is, the more likely the neighborhood pixel point of the pixel point belongs to two areas, namely the more likely the pixel point is positioned at the boundary of the two areas; first, the
The smaller the average value of the gray distribution characteristic values of the neighborhood pixel points of the pixel points is, the greater the possibility that the neighborhood pixel points of the pixel points belong to the same area is, the greater the possibility that the pixel points belong to the inside of the area is, and the lower the possibility that the pixel points belong to the boundary of the two areas is; therefore, the gray gradient value and the neighborhood gray range of the pixel point are positively correlated with the edge characteristic value of the pixel point, and the gray distribution characteristic value of the neighborhood pixel point of the pixel point is negatively correlated with the edge characteristic value of the pixel point. And normalizing the obtained numerical value by using a normalization function, so that subsequent calculation is facilitated.
Thus, the edge characteristic value of each pixel point is obtained. And the edge characteristic value is used for carrying out region growth on the gray image, so that the influence of the gray average value of the grown pixel points generated by gray change in the gradient region in the traditional algorithm on the growth rule is avoided.
And acquiring a region growth judgment value of each pixel point according to the edge characteristic value and the gray value of each pixel point, and using the region growth judgment value for a subsequent region growth algorithm.
Specifically, the gray characteristic of each pixel point is obtained by multiplying the duty ratio of the gray value of each pixel point in the total gray value by the preset weight of the gray value; multiplying the edge characteristic value of each pixel point by the preset weight of the edge characteristic value to obtain the edge characteristic of each pixel point; and combining the gray characteristic and the edge characteristic of each pixel point to obtain the region growth judgment value of each pixel point. The grown pixel points are pixel points which have been subjected to region growth, and the formula for obtaining the region growth judgment value of each pixel point is as follows:
wherein ,
representing the first in a gray scale image
A region growing judgment value of each pixel point;
the first in the gray scale image
Gray values of the individual pixels;
represent the first
Edge feature values of the pixel points;
a weight value representing a gray scale characteristic of the pixel point;
a weight value representing an edge feature of the pixel point; when the regional growth is carried out in the scheme, because more interference pixel points and gradient regions exist in the gray level image, the influence of gray level values on the growth judgment should be reduced, the influence of edge characteristic values on the growth judgment is improved, the obtained regional growth result can be more accurate, therefore, the weight value is given,
，
. The more approximate the gray value and the edge characteristic value of the two pixel points are, the more approximate the region growth judgment value is, and the more approximate the region growth judgment value isCan be grown to the same region.
Region growing module 13: and carrying out region growth by using seed points in the gray level image, and taking the region growth judging values of the grown pixel points and the pixel points to be grown as region growth conditions, wherein the grown pixel points are pixel points subjected to region growth.
Specifically, subtracting the average value of the area growth judgment values of the grown pixel points from the area growth judgment value of the pixel points to be grown to obtain a difference value; if the absolute value of the obtained difference value is smaller than the set judging threshold value, performing region growth, and updating the corresponding pixel point to be grown into a grown pixel point; if the absolute value of the obtained difference value is not smaller than the set judgment threshold value, the corresponding pixel point to be grown is not updated. And if the grown pixel points meet the following formula, continuing growing:
wherein ,
representing pixel points to be grown in gray scale image
Is a region growth judgment value;
representing grown pixel points in gray scale images
Is determined by the region growing judgment value of (a),
representing the number of grown pixels in the gray scale image,
representing the average value of the area growth judgment values of the grown pixel points, wherein the average value of the area growth judgment values of the pixel points to be grown and the area growth judgment values of the grown pixel points are more connectedThe more likely that the pixel point to be grown and the grown region belong to the same region is considered to be, the growth should be continued; thus setting the judgment threshold
The judgment threshold value can be set according to specific situations.
When any seed point is selected to perform the first step of region growth, the grown pixel point refers to the seed point which is initially selected. And updating the pixel points to be grown into the pixel points to be grown when the difference between the regional growth judgment value of the pixel points to be grown and the regional growth judgment value mean value of the pixel points to be grown is smaller than a set judgment threshold value, continuing regional growth until the pixel points to be grown meeting the condition do not exist, ending regional growth, and obtaining a region. And then optionally carrying out region growth on the seed points according to the same mode, and finally obtaining a plurality of regions in the gray level image.
The judgment module 14: and the detection device is used for determining the damaged area of the thermal insulation external wall panel to be detected according to the edge characteristic value of the pixel point in each area.
In the inner and outer panels of the self-heat-insulating external wall panel, the normal heat-insulating panel surface belongs to a rough surface, compared with the normal area made of concrete, the damaged area has smaller roughness, and fewer interference points are displayed in the edge image of the gray level image, so that the edge characteristic values of the pixel points in the damaged area
Is relatively small, and thus a broken region in the gray image is extracted by the edge feature value of each region.
Specifically, the average value of the edge characteristic values of all pixel points in each region in the gray image is obtained
When the mean value of the edge characteristic values of a certain area
Less than the set breakage threshold q=0.3, the region is brokenAn area.
In summary, the invention provides a quality detection system of a lightweight concrete composite self-insulation external wall panel, which obtains a chaotic degree parameter of each pixel point through the gray distribution condition of the pixels around the pixel point, namely the gray fluctuation degree of the pixels, and determines a seed point for regional growth by using the chaotic degree parameter. The edge characteristic value is determined through the gray gradient value of the pixel point and the gray value of the neighborhood pixel point, and then the edge characteristic value and the gray value of the pixel point are used for judging the region growth, so that compared with the conventional algorithm, the gray average value judgment of the grown region is more accurate, the influence of the gray average value of the grown pixel point generated by the gray change in the gradient region on the growth rule in the conventional algorithm is avoided, the obtained region is more accurate, and the condition that the damaged region and the normal region are divided into the same region is avoided.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (5)
1. The utility model provides a quality testing system of light concrete composite self preservation temperature side fascia which characterized in that includes:
and an image acquisition module: the method comprises the steps of acquiring gray images of an inner panel and an outer panel of the thermal insulation external wall panel to be detected;
and a pretreatment module: the method comprises the steps of obtaining gray fluctuation degree of each pixel according to gray values of each pixel and a neighborhood pixel in a gray image, and obtaining chaotic degree parameters of each pixel by using the gray fluctuation degree of each pixel and the neighborhood pixel;
the gray level fluctuation degree method for each pixel point is as follows:
obtaining squares of gray difference values of each pixel point and each neighborhood pixel point, and obtaining average value of squares of gray difference values of a plurality of neighborhood pixel points obtained by each pixel point to obtain gray fluctuation degree of each pixel point;
the method for obtaining the chaotic degree parameter of each pixel point comprises the following steps:
acquiring the average value of the difference value between the gray level fluctuation degree of each pixel point and the gray level fluctuation degree of the adjacent pixel point;
carrying out negative correlation mapping on the value obtained by the average normalization of each pixel point to obtain a chaotic degree parameter of each pixel point;
taking a pixel point with the chaotic degree parameter larger than a preset parameter threshold as a seed point;
and a data processing module: the method comprises the steps of obtaining an edge characteristic value of each pixel point according to a gray gradient value of each pixel point in a gray image and gray values of neighbor pixel points of the gray gradient value;
the method for acquiring the edge characteristic value of each pixel point comprises the following steps:
obtaining the maximum gray difference value between the neighborhood pixel points of each pixel point;
acquiring gray distribution characteristic values of each neighborhood pixel point in the neighborhood of each pixel point;
taking the product of the gray gradient value of each pixel point and the maximum gray difference value between the adjacent pixel points as a molecule;
taking the average value of the gray distribution characteristic values of the neighborhood pixel points of each pixel point as a denominator;
normalizing the ratio of the numerator to the denominator corresponding to each pixel point to obtain an edge characteristic value of each pixel point;
the method for acquiring the gray distribution characteristic value of each neighborhood pixel point in the neighborhood of each pixel point comprises the following steps:
obtaining a gray level distribution characteristic value of each neighborhood pixel point in the neighborhood according to the gray level value difference value of each neighborhood pixel point and the adjacent pixel point in the neighborhood of each pixel point;
the expression for obtaining the gray distribution characteristic value of each neighborhood pixel point in the neighborhood of each pixel point is as follows:
wherein ,
representing the>
In the neighborhood of the individual pixel point +.>
Gray level distribution characteristic values of the adjacent pixel points;
indicate->
In the neighborhood of the individual pixel point +.>
Gray values of the neighboring pixel points; />
，/>
Respectively represent +.>
Adjacent area of each pixel point and +.>
The adjacent +.>
The pixel points of the neighborhood and +.>
Gray values of the neighboring pixel points;
obtaining a region growth judgment value of each pixel point by using the gray value and the edge characteristic value of each pixel point;
region growing module: performing region growth by using seed points in the gray level image, and taking the region growth judgment values of the grown pixel points and the pixel points to be grown as region growth conditions, wherein the grown pixel points refer to the pixel points subjected to region growth;
and a judging module: and the detection device is used for determining the damaged area of the thermal insulation external wall panel to be detected according to the edge characteristic value of the pixel point in each area.
2. The quality inspection system of a lightweight concrete composite self-insulating external wall panel according to claim 1, wherein in the area growth module, the area growth using seed points in the gray scale image comprises:
subtracting the average value of the area growth judgment values of the grown pixel points from the area growth judgment value of the pixel points to be grown to obtain a difference value;
if the absolute value of the obtained difference value is smaller than the set judging threshold value, performing region growth, and updating the corresponding pixel point to be grown into a grown pixel point;
if the absolute value of the obtained difference value is not smaller than the set judgment threshold value, the corresponding point to be grown is not updated.
3. The quality detection system of the lightweight concrete composite self-heat-preserving external wall panel according to claim 1, wherein the method for obtaining the area growth judgment value of each pixel point is as follows:
multiplying the duty ratio of the gray value of each pixel point in the total gray value by the preset weight of the gray value to obtain the gray characteristic of each pixel point;
multiplying the edge characteristic value of each pixel point by the preset weight of the edge characteristic value to obtain the edge characteristic of each pixel point;
and combining the gray characteristic and the edge characteristic of each pixel point to obtain the region growth judgment value of each pixel point.
4. The quality detection system of the lightweight concrete composite self-heat-preserving external wall panel according to claim 1, wherein the method for obtaining the damaged area of the heat-preserving external wall panel to be detected is as follows:
acquiring the average value of the edge characteristic values of the pixel points in each region;
and taking the area, the average value of the edge characteristic values of which is smaller than the preset damage threshold value, as the damage area of the thermal insulation external wall panel to be detected.
5. The system for detecting the quality of the lightweight concrete composite self-insulating external wall panel according to claim 1, wherein when any seed point is selected in the area growth module to perform the first step of area growth, the grown pixel point refers to the initially selected seed point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310193337.8A CN115880299B (en) | 2023-03-03 | 2023-03-03 | Quality detection system of light concrete composite self-insulation external wall panel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310193337.8A CN115880299B (en) | 2023-03-03 | 2023-03-03 | Quality detection system of light concrete composite self-insulation external wall panel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115880299A CN115880299A (en) | 2023-03-31 |
| CN115880299B true CN115880299B (en) | 2023-05-23 |
Family
ID=85761818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310193337.8A Active CN115880299B (en) | 2023-03-03 | 2023-03-03 | Quality detection system of light concrete composite self-insulation external wall panel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115880299B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116152261B (en) * | 2023-04-24 | 2023-06-27 | 济南奥盛包装科技有限公司 | Visual inspection system for quality of printed product |
| CN116993716B (en) * | 2023-09-22 | 2023-12-19 | 山东力加力钢结构有限公司 | Visual inspection method for concrete stirring process |
| CN116993740B (en) * | 2023-09-28 | 2023-12-19 | 山东万世机械科技有限公司 | Concrete structure surface defect detection method based on image data |
| CN117011303B (en) * | 2023-10-08 | 2024-01-09 | 泰安金冠宏油脂工业有限公司 | Oil production quality detection method based on machine vision |
| CN117237338B (en) * | 2023-11-10 | 2024-01-30 | 山东天意高科技有限公司 | Defect identification method for building external heat-insulating layer hollowing |
| CN117351433B (en) * | 2023-12-05 | 2024-02-23 | 山东质能新型材料有限公司 | Computer vision-based glue-cured mortar plumpness monitoring system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447659A (en) * | 2016-09-27 | 2017-02-22 | 电子科技大学 | Region growth detection method based on multiple judgments |
| CN109102518A (en) * | 2018-08-10 | 2018-12-28 | 广东工业大学 | A kind of method of Image Edge-Detection, system and associated component |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2399245B (en) * | 2003-03-03 | 2005-07-27 | Motorola Inc | Method for segmenting an image and an image transmission system and image transmission unit therefor |
| CN105095846B (en) * | 2014-09-28 | 2019-07-30 | 航天恒星科技有限公司 | Region growing seed point extracting method and system towards the segmentation of remote sensing images sea land |
| CN107346545A (en) * | 2017-05-22 | 2017-11-14 | 沈阳工业大学 | Improved confinement growing method for the segmentation of optic cup image |
| CN108961291A (en) * | 2018-08-10 | 2018-12-07 | 广东工业大学 | A kind of method of Image Edge-Detection, system and associated component |
| CN110390669B (en) * | 2019-06-26 | 2021-03-30 | 杭州电子科技大学 | Method for detecting cracks in bridge image |
| CN112435208B (en) * | 2019-08-07 | 2022-09-13 | 河海大学常州校区 | Insulator region detection method for significant edge guidance |
| CN112233133B (en) * | 2020-10-29 | 2023-04-14 | 上海电力大学 | Power plant high-temperature pipeline defect detection and segmentation method based on OTSU and area growth method |
| CN112465852B (en) * | 2020-12-03 | 2024-01-30 | 国网山西省电力公司晋城供电公司 | Improved region growing method for infrared image segmentation of power equipment |
| CN115311290A (en) * | 2022-10-12 | 2022-11-08 | 南通市通州区精华电器有限公司 | Method for detecting defects of metal parts of precision instrument |
-
2023
- 2023-03-03 CN CN202310193337.8A patent/CN115880299B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447659A (en) * | 2016-09-27 | 2017-02-22 | 电子科技大学 | Region growth detection method based on multiple judgments |
| CN109102518A (en) * | 2018-08-10 | 2018-12-28 | 广东工业大学 | A kind of method of Image Edge-Detection, system and associated component |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115880299A (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115880299B (en) | Quality detection system of light concrete composite self-insulation external wall panel | |
| CN114359416B (en) | Building outer wall hollowing leakage abnormity detection and positioning method | |
| CN106468543B (en) | Blade area measuring method based on image processing | |
| CN115100171A (en) | Steel die welding defect detection method and system based on machine vision | |
| CN116934740B (en) | Plastic mold surface defect analysis and detection method based on image processing | |
| CN101256157B (en) | Method and apparatus for testing surface defect | |
| CN116168039A (en) | Environment-friendly energy-saving aluminum silicate plate quality detection method | |
| CN115641327B (en) | Building engineering quality supervision and early warning system based on big data | |
| CN113689426B (en) | Fire-fighting equipment defect detection method based on image processing | |
| CN117315289B (en) | Aeroengine blade contour edge detection method based on image processing | |
| CN116416252B (en) | Method for detecting sedimentation image of wastewater in boehmite production process | |
| CN117291937B (en) | Automatic plastering effect visual detection system based on image feature analysis | |
| CN115953409B (en) | Injection molding surface defect detection method based on image processing | |
| CN115761014A (en) | Ancient building intelligent monitoring analysis early warning system based on digital twins | |
| CN107657620A (en) | A kind of method and system of textured metal freezing region recognition | |
| CN117274240A (en) | Bearing platform foundation concrete surface crack identification method | |
| CN116993745B (en) | Method for detecting surface leakage of water supply pipe based on image processing | |
| CN111736156B (en) | Upwind area identification method and device based on weather radar | |
| CN117058137A (en) | Visual inspection method for production quality of laminated glass | |
| CN116304963B (en) | Data processing system suitable for geological disaster early warning | |
| CN115222735B (en) | Metal mold quality detection method based on pockmark defects | |
| CN116183622A (en) | Subway seepage water detection method based on point cloud information | |
| CN108898080A (en) | A kind of crack connection method based on ridge line neighborhood evaluation model | |
| CN114529536A (en) | Solid wood quality detection method | |
| CN113591737A (en) | Civil engineering construction risk management method and system based on artificial intelligence |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A quality inspection system for lightweight concrete composite self insulation exterior wall panels Granted publication date: 20230523 Pledgee: Shandong Chiping Rural Commercial Bank Co.,Ltd. Pledgor: Shandong times Plastic Co.,Ltd. Registration number: Y2024980015716 |