CN115908411A - Concrete curing quality analysis method based on visual detection - Google Patents
Concrete curing quality analysis method based on visual detection Download PDFInfo
- Publication number
- CN115908411A CN115908411A CN202310014998.XA CN202310014998A CN115908411A CN 115908411 A CN115908411 A CN 115908411A CN 202310014998 A CN202310014998 A CN 202310014998A CN 115908411 A CN115908411 A CN 115908411A
- Authority
- CN
- China
- Prior art keywords
- edge line
- edge
- crack
- line
- lines
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 title abstract description 6
- 230000000007 visual effect Effects 0.000 title description 4
- 238000011179 visual inspection Methods 0.000 claims abstract description 14
- 238000005452 bending Methods 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 8
- 238000005336 cracking Methods 0.000 claims description 6
- 230000007547 defect Effects 0.000 abstract description 14
- 238000000034 method Methods 0.000 abstract description 7
- 238000013441 quality evaluation Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000001723 curing Methods 0.000 description 20
- 230000035699 permeability Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 2
- 108091034117 Oligonucleotide Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036571 hydration Effects 0.000 description 1
- 238000006703 hydration reaction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002985 plastic film Substances 0.000 description 1
- 229920006255 plastic film Polymers 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005507 spraying Methods 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a concrete curing quality analysis method based on visual inspection, which relates to the field of image processing and comprises the following steps: acquiring an edge line in a gray level image of the surface of the concrete to be detected; obtaining the crack possibility of each edge line according to the gray average value and the bending degree of each edge line; obtaining a first edge line and a second edge line by utilizing crack possibility; acquiring a target edge line and a target end point of each first edge line; recalculating the crack probability for the extended first edge line; determining the crack edge lines according to the crack possibility of the first edge lines and the extended first edge lines and the number of the second edge lines in the minimum circumscribed rectangle, and evaluating the curing quality of the concrete according to the area ratio of the crack edge lines in the gray level image. The method improves the accuracy of crack defect detection, and further ensures that the obtained concrete curing quality evaluation result is more accurate.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a concrete curing quality analysis method based on visual inspection.
Background
The concrete curing method is a sub-project which consumes the longest time and has the greatest influence on the quality of concrete in the whole concrete project. The concrete curing is generally performed by watering natural curing, spraying film curing and plastic film wrapping curing to keep the concrete moist and avoid water loss so as to achieve the curing purpose. However, many projects are too careless to maintain, so that the final concrete hydration effect is not good, cracks appear, and the service life of the project can be seriously influenced. Therefore, maintenance quality inspection is required to be continuously carried out in the concrete maintenance process and immediately after the maintenance is finished, and whether cracks appear is mainly detected.
In the prior art, the crack defect is usually obtained by edge detection, but the concrete surface also has a groove mark with a shape similar to the crack defect, the crack is generated due to the damage of the concrete quality and performance, and the groove mark is surface change caused by misoperation and has little influence on the quality; therefore, only a crack region with defects needs to be obtained, but the groove mark and the crack defect are in a slender curve form in a gray image, so that the groove mark and the crack defect on the surface of the concrete are similar to edge lines of the crack defect during edge detection, are difficult to distinguish, and the accurate crack defect cannot be obtained, so that the maintenance quality of the concrete cannot be accurately analyzed.
Disclosure of Invention
The invention provides a concrete curing quality analysis method based on visual inspection, which aims to solve the problem that the defects of groove marks and cracks on the surface of concrete are difficult to distinguish in the existing edge inspection process.
The concrete curing quality analysis method based on visual inspection adopts the following technical scheme:
acquiring a gray image of the surface of the concrete to be detected;
acquiring edge lines in the gray level image and non-edge pixel points in the middle of double thresholds during edge detection as candidate pixel points;
obtaining the curvature of each edge line according to the number of the pixel points on each edge line and the coordinates of the pixel points; obtaining the crack possibility of each edge line according to the gray average value and the bending degree of each edge line;
dividing the edge line into a first edge line and a second edge line according to the crack possibility, wherein the crack possibility of the first edge line is greater than that of the second edge line;
obtaining a target edge line with the shortest distance between each first edge line by using the distance between the end point of each first edge line and the end points of other first edge lines, and taking the end point with the shortest distance between each first edge line and the target edge line as a target end point;
determining whether the first edge line is extended or not according to whether candidate pixel points exist in the target end point neighborhood of each first edge line and the distance between the candidate pixel points when the candidate pixel points exist and the end points of the corresponding target edge lines, and recalculating the crack possibility of the extended first edge line;
and marking the first edge lines which are not extended and the first edge lines which are extended as third edge lines, determining crack edge lines according to the number of second edge lines in the minimum circumscribed rectangle of each third edge line and the crack possibility of the third edge lines, and evaluating the maintenance quality of the concrete according to the area occupation ratio of the crack edge lines in the gray level image.
Further, the step of obtaining the curvature of each edge line includes:
obtaining the absolute value of the slope of the connecting line of the starting point and the end point of each edge line according to the coordinates of the starting point and the end point of the pixel point on each edge line in the gray level image, and using the absolute value as a reference slope;
obtaining the slope absolute value of the connecting line of each pixel point and the starting point according to the coordinates of each pixel point and the starting point on each edge line;
and calculating the average value of the absolute value of the difference value between the slope absolute value of each pixel point on each edge line and the starting point connecting line and the reference slope, and normalizing the obtained average value to obtain the curvature of each edge line.
Further, the step of determining whether to extend the first edge line includes:
taking a target endpoint of the first edge line as a seed point, and if no candidate pixel point exists in the neighborhood of the seed point, not extending the first edge line;
if candidate pixel points exist in the neighborhood of the seed point, acquiring the candidate pixel point with the maximum gradient in the neighborhood as a target candidate point;
and if the minimum distance between the target candidate point and the corresponding target edge line end point is not less than the distance between the target end point and the target edge line end point, not extending the first edge line, if the minimum distance is less than the distance, extending the first edge line to the target candidate pixel point, and continuously taking the target candidate pixel point as a new seed point to determine whether to extend the first edge line.
Further, the formula for obtaining the crack probability of each edge line is as follows:
wherein ,
denotes the first
The possibility of cracking of the edge lines;
is shown as
Curvature of a border line;
is shown as
Curvature of a border line;
representing the total number of edge lines in the grayscale image;
representing bends of all edge lines in a grayscale imageA curvature mean value;
denotes the first
Normalizing the gray level mean value of the edge line;
denotes the first
Normalizing the gray level mean value of the edge line of the strip;
expressing the mean value of the normalized values of the gray mean values of all the edge lines in the gray image;
is a normalization function.
Further, the step of determining the crack edge line comprises the following steps:
the formula for obtaining the final fracture possibility of each third edge line is as follows:
wherein ,
denotes the first
The ultimate crack potential of the third edge line of the strip;
is shown as
Splitting of the third edge lineThe possibility of seams;
is shown as
The area of the minimum circumscribed rectangle of the third edge line;
is shown as
The number of second edge lines in the minimum circumscribed rectangle of the third edge line;
is an exponential function with a natural constant e as a base;
and determining a third edge line with the final crack possibility larger than a preset crack threshold value as a crack edge line.
Further, the step of obtaining the target edge line with the closest distance to each first edge line comprises:
acquiring the minimum distance between the end point of each first edge line and the end points of other first edge lines;
selecting a minimum value from all the minimum distances obtained from each first edge line;
and taking the first edge line corresponding to the minimum value as the target edge line with the shortest distance from the first edge line.
Further, the step of evaluating the curing quality of the concrete according to the area ratio of the crack edge line in the gray level image comprises the following steps:
if the area ratio of the crack edge line in the gray level image is smaller than a preset first area threshold value, the maintenance quality of the concrete is qualified;
if the area proportion of the crack edge line in the gray-scale image is larger than or equal to the first area threshold value and smaller than the preset second area threshold value, the concrete curing quality is poor;
and if the area ratio of the crack edge line in the gray level image is greater than or equal to the second area threshold value, the maintenance quality of the concrete is unqualified.
Further, the dividing of the edge line into a first edge line and a second edge line according to the crack probability includes:
setting a crack possibility threshold value, and taking an edge line with the crack possibility larger than the crack possibility threshold value as a first edge line;
and taking the edge line with the crack possibility smaller than or equal to the crack possibility threshold value as a second edge line.
The invention has the beneficial effects that: according to the concrete curing quality analysis method based on visual detection, the crack possibility of each edge line is obtained through the curvature and the gray average value of each edge line, the edge line of the crack is more bent and has larger curvature relative to the edge line of the groove mark, the directions of the edge lines of the groove mark are consistent, and the brightness of the crack and the brightness of the groove mark in a gray image are different, namely the gray values are different, so that the crack possibility can be obtained by combining the curvature and the gray average value of the edge lines for preliminary distinction, and a first edge line closer to crack defects and a second edge line closer to the groove mark are obtained; because some tiny crack edges can not be obtained by conventional edge detection, extending the first edge line through the distance between a non-edge pixel point in a double-threshold interval and the nearest target edge line during edge detection to obtain a complete extended first edge line; and because the number of the grooves around the concrete surface crack defect is less than that around the groove, the crack edge line is further determined by combining the characteristic and the crack possibility of the first edge line, so that the crack edge line is more accurate, and the obtained quality evaluation result of the concrete surface is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart illustrating the general steps of an embodiment of a visual inspection-based concrete curing quality analysis method according to the present invention;
fig. 2 is a grayscale image of a concrete surface.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
An embodiment of the method for analyzing concrete curing quality based on visual inspection of the present invention is shown in fig. 1, and the method includes:
s1, acquiring a gray image of the surface of concrete to be detected; and acquiring edge lines in the gray level image and non-edge pixel points in the middle of double thresholds during edge detection as candidate pixel points.
Specifically, an unmanned aerial vehicle provided with a professional camera is used for acquiring images of the surface of concrete in a flying manner, and the images are influenced by mechanical noise in the process of acquiring the images, so that noise points exist in the acquired images, and the acquired images are subjected to Gaussian filtering to obtain the noise-reduced images.
The image after noise reduction is grayed to obtain a grayscale image of the concrete surface, as shown in fig. 2.
And carrying out edge detection on the gray level image by using a Canny operator to obtain edge lines in the gray level image, wherein the obtained edge lines comprise edge lines of cracks and furrow marks on the surface of the concrete.
When the Canny operator carries out edge detection, double thresholds, namely an upper bound threshold and a lower bound threshold, are set, and if the gradient of the pixel point is greater than the upper bound threshold, the pixel point is regarded as a boundary inevitably and is called as a strong edge pixel point; if the pixel value is smaller than the lower bound threshold value, the pixel is regarded as a non-edge pixel point; and if the pixel points between the upper and lower bound thresholds belong to the eight neighborhoods of the strong edge pixel points, the pixel points are judged to be weak edge pixel points, and if the pixel points do not belong to the eight neighborhoods of the strong edge pixel points, the pixel points are judged to be non-edge pixel points. However, in this scheme, since the crack region has permeability, it is necessary to further analyze the pixels not belonging to the eight neighborhoods of edge pixels, and obtain non-edge pixels between the upper and lower bound thresholds as candidate pixels for subsequent analysis.
S2, obtaining the curvature of each edge line according to the number of the pixel points on each edge line and the coordinates of the pixel points.
The cracks are generated from inside to outside when the concrete is damaged, the groove marks are scratches on the surface of the concrete, the edge lines of the defects of the cracks are more bent and have larger curvature, and the edge lines of the groove marks have stronger direction consistency, so that the cracks and the groove marks can be preliminarily distinguished according to the curvature of the edge lines.
Specifically, the number of pixel points and the coordinates of the pixel points on each edge line in the gray-scale image are obtained.
Obtaining the absolute value of the slope of the connecting line of the starting point and the end point of each edge line as a reference slope according to the coordinates of the starting point and the end point of the pixel point on each edge line; obtaining the slope absolute value of the connecting line of each pixel point and the starting point according to the coordinates of each pixel point and the starting point on each edge line; and calculating the average value of the absolute value of the difference value between the slope absolute value of each pixel point on each edge line and the starting point connecting line and the reference slope, and normalizing the obtained average value to obtain the curvature of each edge line. The formula for specifically calculating the curvature of each edge line is as follows:
wherein ,
denotes the first
Curvature of a border line;
denotes the first
The number of pixel points on the edge line;
is as follows
The coordinates of the start point of the edge line,
is as follows
The coordinates of the end point of the edge line,
is as follows
On the strip edge line
The coordinates of each pixel point, the starting point and the end point of the edge line are any end points of the edge line;
is a normalization function;
is shown as
Absolute value of slope of connection line between start point and end point of edge line, and slope of connection line between start point and end pointThe absolute value is used as a reference slope; second pixel from edge line
Starting to traverse (the first pixel point is the starting point), respectively calculating the first
A pixel
And a starting point
And calculating the mean value of the absolute values of all the difference values and normalizing to obtain the curvature of the edge line. The absolute value of the slope obtained by each pixel point is compared with the reference slope, because the starting point and the end point on the edge line are connected to determine a reference direction, if the edge line is a straight line, the difference between the direction of any one pixel point on the edge line and the connecting line of the starting point and the reference direction is not large, and if the difference is larger, the edge line is considered to deviate from the straight line more, namely the curvature is larger. The difference results are normalized to facilitate calculation of crack probabilities for the gray values of subsequent bond edge lines.
S3, obtaining the crack possibility of each edge line according to the gray average value and the bending degree of each edge line; the edge lines are divided into first edge lines and second edge lines according to crack probability, and the crack probability of the first edge lines is greater than that of the second edge lines.
The bending degree of the edge line of the crack is large, but the edge of a local section of the crack is not obvious, so that a continuous crack edge line is divided into a plurality of sections of edge lines during edge detection, and the bending degree of each local section of the edge line is not high, so that the edge line can be detected as a groove mark. Therefore, it is necessary to distinguish the crack from the groove in gray scale, the gray scale of the groove in the gray scale image is brighter than the gray scale of the crack, and if the gray scale of the pixel in the gray scale image is divided into three levels, i.e., low, medium and high, the crack mainly appears in two levels, and the groove mainly appears in two levels, i.e., medium and high, so that the possibility that the edge line is the crack edge line is further determined by combining the gray scale value and the curvature.
Specifically, the gray value of each pixel point on each edge line is obtained, and the gray regularity of each edge line is calculated according to the following formula:
wherein ,
denotes the first
The gray scale regularity of the edge lines;
is shown as
The number of pixel points on the edge line;
is shown as
On the strip edge line
The gray value of each pixel point;
is shown as
The gray average value of the pixel points on the edge line;
is a normalization function; the gray scale rule of the edge line is represented by the gray scale average value of the pixel points on each edge line, the larger the gray scale average value is, the brighter the gray scale in the gray scale image is, the more likely the gray scale is to be a groove mark edge line, the smaller the gray scale average value is, the more likely the gray scale is to be a crack edge line, and the normalization of the gray scale average value is to facilitate the calculation of the crack possibility in the follow-up process by combining the curvature of the edge line.
The crack probability of each edge line is calculated according to the following formula:
wherein ,
is shown as
The possibility of cracking of the edge lines;
is shown as
Curvature of a border line;
is shown as
Curvature of a border line;
representing the total number of edge lines in the grayscale image;
representing the curvature mean value of all edge lines in the gray level image;
denotes the first
Normalization of the mean value of the gray levels of the edge lines, i.e. second
The gray scale regularity of the edge lines;
is shown as
Normalization of the mean value of the gray levels of the edge lines, i.e. second
The gray scale regularity of the edge lines;
expressing the mean value of the normalized values of the gray mean values of all the edge lines in the gray image, namely the gray regularity mean value of all the edge lines;
is a normalization function.
The degree of curvature and the gray scale regularity are related to each other negatively, so that the obtained related coefficient is a negative number, and in order to conveniently represent the related degree, the absolute value of the related coefficient is taken, and the larger the absolute value is, the larger the negative related degree of the degree of curvature and the gray scale regularity is; the ratio of the two is weighted by the degree of negative correlation of the two, and the greater the curvature, the smaller the grayscale value, and the greater the degree of negative correlation of the two, the greater the probability that the edge line is considered to be a crack edge line. And normalizing the obtained result, so that a threshold value can be conveniently set to distinguish edge lines.
Setting a crack possibility threshold, wherein an edge line with the crack possibility greater than the crack possibility threshold is used as a first edge line, and an edge line with the crack possibility less than or equal to the crack possibility threshold is used as a second edge line, and the crack possibility threshold is set to be 0.45 in the embodiment of the invention. The first edge line is more likely to be a crack edge line and the second edge line is more likely to be a score edge line.
And S4, obtaining a target edge line with the shortest distance of each first edge line by using the distance between the end point of each first edge line and the end points of other first edge lines, and taking the end point with the shortest distance of each first edge line and the target edge line as a target end point.
The cracks have strong permeability, and the Canny edge detection cannot obtain some fine cracks, only analyzes the detected edge lines, and does not consider the undetected fine cracks, so that the obtained detection result is not accurate enough, and further analysis can be performed through pixel points around the first edge line which is closer to the crack edge line.
Specifically, because the crack has strong permeability, the probability that a fine crack exists between two first edge lines which are closest to each other is high, the minimum distance between the end point of each first edge line and the end points of other first edge lines is obtained, each edge line has two end points, when the distance between the two first edge lines is calculated, one end point is selected from the two edge lines to be matched for distance calculation, four calculation results are obtained in total, and the minimum value of the four calculation results is selected as the minimum distance between the two first edge lines; selecting a minimum value from all the minimum distances obtained from each first edge line; and taking other first edge lines corresponding to the selected minimum value as the nearest target edge line of the first edge line.
And taking the end point of each first edge line, which is closest to the end point of the target edge line, as a target end point.
S5, determining whether to extend the first edge line or not according to whether a candidate pixel point exists in the target end point neighborhood of each first edge line and the distance between the candidate pixel point when the candidate pixel point exists and the end point of the corresponding target edge line, and recalculating the crack possibility of the extended first edge line.
When the Canny operator carries out edge detection, partial non-edge pixel points between upper and lower bound thresholds exist, and the partial non-edge pixel points which are not judged as weak edges are taken as candidate pixel points for further analysis in consideration of the permeability of cracks.
Specifically, the target end point of the first edge line is used as a seed point, candidate pixel points are searched in 5 × 5 neighborhoods of the seed point (the size of the neighborhood can be adjusted according to specific implementation conditions), if no candidate pixel point exists in the neighborhoods of the seed point, it is indicated that no fine crack exists between the two first edge lines, and the first edge lines are not extended; if candidate pixel points exist in the neighborhood of the seed point, acquiring the candidate pixel point with the maximum gradient in the neighborhood as a target candidate point; and if the minimum distance between the target candidate point and the corresponding target edge line end point is not less than the distance between the target end point and the target edge line end point, indicating that no fine crack exists between the two first edge lines, not extending the first edge lines, and if the minimum distance is less than the distance, extending the first edge lines to the target candidate pixel points.
And continuing to use the target candidate pixel point as a new seed point to determine whether to extend the first edge line until no candidate pixel point exists in the neighborhood of the new seed point or the minimum distance between the target candidate pixel point and the corresponding target edge line end point is not less than the distance between the target end point and the target edge line end point, and stopping extension to obtain the complete first edge line after extension.
The crack probability is recalculated for all extended first edge lines according to steps S2-S3.
And S6, marking the first edge lines which are not extended and the first edge lines which are extended as third edge lines, determining the crack edge lines according to the number of the second edge lines in the minimum circumscribed rectangle of each third edge line and the crack possibility of the third edge lines, and evaluating the maintenance quality of the concrete according to the area ratio of the crack edge lines in the gray level image.
Since the grooves are distributed in clusters on the concrete surface, a plurality of second edges closer to the groove edge lines are arranged around the grooves, and the second edges closer to the groove edge lines around the cracks can calculate the final crack possibility of each first edge line and the extended first edge line according to the characteristics.
Specifically, the first edge line which is not extended and the first edge line which is extended are marked as third edge lines, each third edge line is subjected to minimum circumscribed rectangles, the number of second edge lines in the minimum circumscribed rectangles of each third edge line is obtained, and the final crack possibility of each third edge line is calculated according to the following formula:
wherein ,
is shown as
The ultimate crack potential of the third edge line of the strip;
is shown as
The likelihood of cracking of the third edge line of the strip;
is shown as
The area of the minimum circumscribed rectangle of the third edge line;
is shown as
The number of second edge lines in the minimum bounding rectangle of the third edge line;
is an exponential function with a natural constant e as a base;
representing the number of second edge lines per unit area in the minimum bounding rectangle, the greater the number of second edges per unit area, the more likely the edge line is to be a groove edge line, i.e. the
The greater the ratio of (A) is, the greater the ratio of (B) is
After negative correlation mapping, the final crack probability of the edge line is smaller, and the final crack probability is in the denominator
The larger the negative correlation map, the greater the likelihood of a final crack resulting in the edge line.
The negative correlation map is used to determine the fracture edge line from the third edge lines in order to select the fracture threshold.
In the embodiment of the invention, the crack threshold value is set to be 0.5, and the third edge line with the final crack possibility larger than the crack threshold value is determined as the crack edge line to obtain all crack edge lines in the gray level image. Meanwhile, the scheme can label the crack edge lines in the gray level image, and the gray level image with the labeled crack edge lines is displayed on the corresponding display, so that the abnormal condition of the concrete surface can be checked more visually.
The ratio of the number of the pixel points on all the crack edge lines to the total number of the pixel points in the gray level image is obtained, the larger the ratio is, the worse the quality of the concrete surface is, the worse the concrete curing quality is, and a concrete curing quality grade implementer can automatically set the threshold of the ratio according to actual conditions to obtain the ratio.
In this embodiment, if the area ratio of the crack edge line in the grayscale image is less than the preset first area threshold value of 0.3, the maintenance quality of the concrete is qualified, and only the local crack needs to be specifically processed; if the area ratio of the crack edge line in the gray level image is greater than or equal to the first area threshold value 0.3 and less than the preset second area threshold value 0.7, the maintenance quality of the concrete is poor, and the area where the crack is located needs to be repaired; and if the area ratio of the crack edge line in the gray-scale image is greater than or equal to 0.7 of the second area threshold, the curing quality of the concrete is unqualified, the crack penetrates through the whole concrete surface, and the curing quality is poor.
In summary, the invention provides a concrete curing quality analysis method based on visual detection, the crack possibility of each edge line is obtained through the curvature and the gray average of each edge line, because the edge line of the crack is more tortuous and has larger curvature relative to the groove edge line, the directions of the groove edge lines are consistent, and the brightness of the crack and the brightness of the groove in the gray image are different, namely the gray values are different, the crack possibility can be obtained by combining the curvature and the gray average of the edge lines for preliminary distinction, and a first edge line closer to the crack defect and a second edge line closer to the groove are obtained; because some fine crack edges can not be obtained by conventional edge detection, the first edge line is extended through the distance between the non-edge pixel point in the double-threshold interval and the nearest target edge line during the edge detection, and a complete extended first edge line is obtained; and because the number of the grooves around the concrete surface crack defect is less than that around the groove, the crack edge line is further determined by combining the characteristic and the crack possibility of the first edge line, so that the crack edge line is more accurate, and the obtained quality evaluation result of the concrete surface is more accurate.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The concrete curing quality analysis method based on visual inspection is characterized by comprising the following steps:
acquiring a gray image of the surface of the concrete to be detected;
acquiring edge lines in the gray level image and non-edge pixel points in the middle of double thresholds during edge detection as candidate pixel points;
obtaining the curvature of each edge line according to the number of pixel points on each edge line and the coordinates of the pixel points; obtaining the crack possibility of each edge line according to the gray average value and the bending degree of each edge line;
dividing the edge line into a first edge line and a second edge line according to the crack possibility, wherein the crack possibility of the first edge line is greater than that of the second edge line;
obtaining a target edge line with the shortest distance between each first edge line by using the distance between the end point of each first edge line and the end points of other first edge lines, and taking the end point with the shortest distance between each first edge line and the target edge line as a target end point;
determining whether the first edge line is extended or not according to whether candidate pixel points exist in the target end point neighborhood of each first edge line and the distance between the candidate pixel points when the candidate pixel points exist and the end points of the corresponding target edge lines, and recalculating the crack possibility of the extended first edge line;
and marking the first edge lines which are not extended and the first edge lines which are extended as third edge lines, determining crack edge lines according to the number of second edge lines in the minimum circumscribed rectangle of each third edge line and the crack possibility of the third edge lines, and evaluating the maintenance quality of the concrete according to the area occupation ratio of the crack edge lines in the gray level image.
2. The visual inspection-based concrete curing quality analysis method according to claim 1, wherein the step of obtaining the curvature of each edge line comprises:
obtaining an absolute value of a slope of a connecting line between the starting point and the end point of each edge line according to coordinates of the starting point and the end point of the pixel point on each edge line in the gray-scale image, and taking the absolute value as a reference slope;
obtaining the slope absolute value of the connection line of each pixel point and the starting point according to the coordinates of each pixel point and the starting point on each edge line;
and calculating the mean value of the absolute value of the difference value between the slope absolute value of each pixel point on each edge line and the connecting line of the starting point and the reference slope, and normalizing the obtained mean value to obtain the curvature of each edge line.
3. The visual inspection-based concrete curing quality analysis method of claim 1, wherein the step of determining whether to extend the first edge line comprises:
taking a target endpoint of the first edge line as a seed point, and if no candidate pixel point exists in the neighborhood of the seed point, not extending the first edge line;
if candidate pixel points exist in the neighborhood of the seed point, acquiring the candidate pixel point with the maximum gradient in the neighborhood as a target candidate point;
and if the minimum distance between the target candidate point and the corresponding target edge line end point is not less than the distance between the target end point and the target edge line end point, not extending the first edge line, if the minimum distance is less than the distance, extending the first edge line to the target candidate pixel point, and continuously taking the target candidate pixel point as a new seed point to determine whether to extend the first edge line.
4. The visual inspection-based concrete curing quality analysis method according to claim 1, wherein the formula for obtaining the crack probability of each edge line is as follows:
wherein ,
is shown as
The possibility of cracking of the edge lines;
denotes the first
Curvature of a border line;
denotes the first
Curvature of a border line;
representing the total number of edge lines in the grayscale image;
representing the curvature mean value of all edge lines in the gray level image;
denotes the first
Normalizing the gray level mean value of the edge line of the strip;
is shown as
Normalizing the gray level mean value of the edge line of the strip;
representing the mean of the grey levels of all edge lines in a grey-scale imageA mean of the normalized values;
is a normalization function.
5. The visual inspection-based concrete curing quality analysis method of claim 1, wherein the step of determining a crack edge line comprises:
the final crack probability of each third edge line is obtained by the following formula:
wherein ,
is shown as
The ultimate likelihood of cracking of the third edge line of the strip;
is shown as
The possibility of cracking of the third edge line of the strip;
is shown as
The area of the minimum circumscribed rectangle of the third edge line;
denotes the first
The number of second edge lines in the minimum circumscribed rectangle of the third edge line;
is an exponential function with a natural constant e as a base;
and determining a third edge line with the final crack possibility larger than a preset crack threshold value as a crack edge line.
6. The visual inspection-based concrete curing quality analysis method of claim 1, wherein the step of obtaining a target edge line with each first edge line closest to the target edge line comprises:
acquiring the minimum distance between the end point of each first edge line and the end points of other first edge lines;
selecting a minimum value from all the minimum distances obtained from each first edge line;
and taking the first edge line corresponding to the minimum value as the target edge line with the shortest distance from the first edge line.
7. The visual inspection-based concrete curing quality analysis method as claimed in claim 1, wherein the step of evaluating the curing quality of the concrete according to the area ratio of the crack edge lines in the gray-scale image comprises:
if the area proportion of the crack edge lines in the gray-scale image is smaller than a preset first area threshold value, the maintenance quality of the concrete is qualified;
if the area proportion of the crack edge line in the gray-scale image is larger than or equal to the first area threshold value and smaller than the preset second area threshold value, the concrete curing quality is poor;
and if the area ratio of the crack edge line in the gray-scale image is greater than or equal to the second area threshold value, the curing quality of the concrete is unqualified.
8. The visual inspection-based concrete curing quality analysis method according to claim 1, wherein the step of dividing the edge line into a first edge line and a second edge line according to crack probability comprises:
setting a crack possibility threshold value, and taking an edge line with the crack possibility larger than the crack possibility threshold value as a first edge line;
and taking the edge line with the crack possibility smaller than or equal to the crack possibility threshold value as a second edge line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014998.XA CN115908411B (en) | 2023-01-06 | 2023-01-06 | Concrete curing quality analysis method based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310014998.XA CN115908411B (en) | 2023-01-06 | 2023-01-06 | Concrete curing quality analysis method based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115908411A true CN115908411A (en) | 2023-04-04 |
| CN115908411B CN115908411B (en) | 2023-05-30 |
Family
ID=85753627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310014998.XA Active CN115908411B (en) | 2023-01-06 | 2023-01-06 | Concrete curing quality analysis method based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115908411B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116228777A (en) * | 2023-05-10 | 2023-06-06 | 鱼台汇金新型建材有限公司 | Concrete stirring uniformity detection method |
| CN116645363A (en) * | 2023-07-17 | 2023-08-25 | 山东富鹏生物科技有限公司 | Vision-based starch production quality real-time detection method |
| CN116703907A (en) * | 2023-08-04 | 2023-09-05 | 合肥亚明汽车部件有限公司 | Machine vision-based method for detecting surface defects of automobile castings |
| CN116958182A (en) * | 2023-09-20 | 2023-10-27 | 广东华宸建设工程质量检测有限公司 | Quick concrete crack detection method based on image data |
| CN116993740A (en) * | 2023-09-28 | 2023-11-03 | 山东万世机械科技有限公司 | Concrete structure surface defect detection method based on image data |
| CN117095004A (en) * | 2023-10-20 | 2023-11-21 | 金成技术股份有限公司 | Excavator walking frame main body welding deformation detection method based on computer vision |
| CN117351021A (en) * | 2023-12-06 | 2024-01-05 | 东莞市南谷第电子有限公司 | Intelligent detection method for production quality of photovoltaic connecting wire |
| CN117423046A (en) * | 2023-12-19 | 2024-01-19 | 山东水利建设集团有限公司 | Visual detection method for cement mortar stirring process based on image processing |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008039594A (en) * | 2006-08-07 | 2008-02-21 | Yamaguchi Univ | Crack detection method for concrete foundation pile |
| CN108007355A (en) * | 2017-10-20 | 2018-05-08 | 西安电子科技大学 | Distress in concrete detection method based on Image distance transform |
| CN110175658A (en) * | 2019-06-26 | 2019-08-27 | 浙江大学 | A kind of distress in concrete recognition methods based on YOLOv3 deep learning |
| CN110390669A (en) * | 2019-06-26 | 2019-10-29 | 杭州电子科技大学 | The detection method in crack in a kind of bridge image |
| CN112785579A (en) * | 2021-01-26 | 2021-05-11 | 西京学院 | Concrete crack identification method based on image processing technology |
| CN114454325A (en) * | 2022-01-21 | 2022-05-10 | 四川农业大学 | Maintenance system and production method of prefabricated concrete component for assembly type building |
| CN115082419A (en) * | 2022-07-14 | 2022-09-20 | 江苏诺阳家居科技有限公司 | Blow-molded luggage production defect detection method |
| CN115082462A (en) * | 2022-08-22 | 2022-09-20 | 山东海鑫达石油机械有限公司 | Method and system for detecting appearance quality of fluid conveying pipe |
-
2023
- 2023-01-06 CN CN202310014998.XA patent/CN115908411B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008039594A (en) * | 2006-08-07 | 2008-02-21 | Yamaguchi Univ | Crack detection method for concrete foundation pile |
| CN108007355A (en) * | 2017-10-20 | 2018-05-08 | 西安电子科技大学 | Distress in concrete detection method based on Image distance transform |
| CN110175658A (en) * | 2019-06-26 | 2019-08-27 | 浙江大学 | A kind of distress in concrete recognition methods based on YOLOv3 deep learning |
| CN110390669A (en) * | 2019-06-26 | 2019-10-29 | 杭州电子科技大学 | The detection method in crack in a kind of bridge image |
| CN112785579A (en) * | 2021-01-26 | 2021-05-11 | 西京学院 | Concrete crack identification method based on image processing technology |
| CN114454325A (en) * | 2022-01-21 | 2022-05-10 | 四川农业大学 | Maintenance system and production method of prefabricated concrete component for assembly type building |
| CN115082419A (en) * | 2022-07-14 | 2022-09-20 | 江苏诺阳家居科技有限公司 | Blow-molded luggage production defect detection method |
| CN115082462A (en) * | 2022-08-22 | 2022-09-20 | 山东海鑫达石油机械有限公司 | Method and system for detecting appearance quality of fluid conveying pipe |
Non-Patent Citations (2)
| Title |
|---|
| YUSUKE FUJITA ET AL: "A Method for Crack Detection on a Concrete Structure", 《18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR\'06)》, pages 1 - 4 * |
| 丁威等: "基于深度学习和无人机的混凝土结构裂缝检测方法", 《土木工程学报》, vol. 64, pages 1 - 12 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116228777A (en) * | 2023-05-10 | 2023-06-06 | 鱼台汇金新型建材有限公司 | Concrete stirring uniformity detection method |
| CN116645363A (en) * | 2023-07-17 | 2023-08-25 | 山东富鹏生物科技有限公司 | Vision-based starch production quality real-time detection method |
| CN116645363B (en) * | 2023-07-17 | 2023-10-13 | 山东富鹏生物科技有限公司 | Vision-based starch production quality real-time detection method |
| CN116703907A (en) * | 2023-08-04 | 2023-09-05 | 合肥亚明汽车部件有限公司 | Machine vision-based method for detecting surface defects of automobile castings |
| CN116703907B (en) * | 2023-08-04 | 2023-10-27 | 合肥亚明汽车部件有限公司 | Machine vision-based method for detecting surface defects of automobile castings |
| CN116958182B (en) * | 2023-09-20 | 2023-12-08 | 广东华宸建设工程质量检测有限公司 | Quick concrete crack detection method based on image data |
| CN116958182A (en) * | 2023-09-20 | 2023-10-27 | 广东华宸建设工程质量检测有限公司 | Quick concrete crack detection method based on image data |
| CN116993740A (en) * | 2023-09-28 | 2023-11-03 | 山东万世机械科技有限公司 | Concrete structure surface defect detection method based on image data |
| 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 |
| CN117095004A (en) * | 2023-10-20 | 2023-11-21 | 金成技术股份有限公司 | Excavator walking frame main body welding deformation detection method based on computer vision |
| CN117095004B (en) * | 2023-10-20 | 2024-01-12 | 金成技术股份有限公司 | Excavator walking frame main body welding deformation detection method based on computer vision |
| CN117351021A (en) * | 2023-12-06 | 2024-01-05 | 东莞市南谷第电子有限公司 | Intelligent detection method for production quality of photovoltaic connecting wire |
| CN117351021B (en) * | 2023-12-06 | 2024-03-26 | 东莞市南谷第电子有限公司 | Intelligent detection method for production quality of photovoltaic connecting wire |
| CN117423046A (en) * | 2023-12-19 | 2024-01-19 | 山东水利建设集团有限公司 | Visual detection method for cement mortar stirring process based on image processing |
| CN117423046B (en) * | 2023-12-19 | 2024-03-01 | 山东水利建设集团有限公司 | Visual detection method for cement mortar stirring process based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115908411B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115908411A (en) | Concrete curing quality analysis method based on visual detection | |
| CN108629775B (en) | Thermal state high-speed wire rod surface image processing method | |
| CN110276754B (en) | Surface defect detection method, terminal device and storage medium | |
| CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
| CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
| CN108960237B (en) | Reading identification method for pointer type oil level indicator | |
| CN111652213A (en) | Ship water gauge reading identification method based on deep learning | |
| CN109215009B (en) | Continuous casting billet surface image defect detection method based on deep convolution neural network | |
| CN109409290B (en) | Thermometer verification reading automatic identification system and method | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN113643276B (en) | Textile texture defect automatic detection method based on statistical analysis | |
| CN109658391B (en) | Circle radius measuring method based on contour merging and convex hull fitting | |
| CN115049669A (en) | Metal defect identification method | |
| CN107798293A (en) | A kind of crack on road detection means | |
| CN115578389A (en) | Defect detection method of groove MOS device | |
| CN115063400B (en) | Musical instrument production defect detection method using visual means | |
| CN115861307B (en) | Fascia gun power supply driving plate welding fault detection method based on artificial intelligence | |
| CN112884746A (en) | Character defect intelligent detection algorithm based on edge shape matching | |
| CN116993742A (en) | Nickel alloy rolling defect detection method based on machine vision | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN109359653B (en) | Cotton leaf adhesion lesion image segmentation method and system | |
| CN117173661A (en) | Asphalt road quality detection method based on computer vision | |
| CN110751687B (en) | Apple size grading method based on computer vision minimum and maximum circle | |
| CN111126371B (en) | Coarse pointer dial reading method based on image processing | |
| CN115082444B (en) | Copper pipe weld defect detection method and system based on image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |