A concrete quality detection method for water conservancy projects

Abstract

The present invention relates to the field of image processing technology, and more particularly to a concrete quality detection method for water conservancy projects, comprising: obtaining a weighted corrosion factor of each edge pixel on the concrete edge line based on the grayscale difference between the edge pixel and surrounding pixels on the concrete edge line, and the corrosion factor of the concrete edge line; obtaining the corrosion intensity of each concrete edge line based on the weighted corrosion factors of different edge pixels on the concrete edge line; performing corrosion enhancement on a grayscale image of a concrete sample to be detected based on the corrosion intensity to obtain an enhanced image of the concrete sample to be detected; obtaining the degree of unevenness of the concrete to be detected by analyzing the enhanced image of the concrete sample to be detected; and performing quality detection on the concrete to be detected based on the degree of unevenness of the concrete to be detected. The present invention obtains a more accurate degree of concrete unevenness, thereby improving the accuracy of concrete quality detection.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a concrete quality detection method for water conservancy projects. Background Art

[0002] In water conservancy projects, the quality of concrete is crucial to the stability and durability of the project. Using image processing technology to inspect concrete quality can provide a more intuitive means of quality assessment. For example, a high-resolution camera can be used to obtain images of concrete samples taken from inside a concrete mixer. Image processing technology can then be used to enhance the concrete sample images to obtain enhanced concrete sample images. The enhanced concrete sample images can be used to obtain more accurate concrete uniformity, allowing adjustments to be made to the concrete during the mixing process to ensure its final quality.

[0003] Because the conventional image enhancement algorithm, the morphological corrosion algorithm, performs grayscale corrosion on the entire image. Since its indifferent corrosion simply brightens the entire image, that is, the image tends to be distributed in blocks, resulting in serious loss of details and inaccurate degree of concrete unevenness; thus reducing the accuracy of concrete quality detection. Summary of the Invention

[0004] In order to solve the above problems, the present invention provides a concrete quality detection method for water conservancy projects, the method comprising:

[0005] Obtaining a grayscale image of the concrete sample to be tested;

[0006] The grayscale image of the concrete sample to be tested is divided into several concrete areas; the corrosion factor of the concrete edge line is obtained based on the position distribution of the edge pixel points on each concrete edge line in the concrete area; the weighted corrosion factor of each edge pixel point on the concrete edge line is obtained based on the grayscale difference between the edge pixel point and the surrounding pixels and the corrosion factor of the concrete edge line; the corrosion intensity of each concrete edge line is obtained based on the weighted corrosion factors of different edge pixels on the concrete edge line;

[0007] Corrosion enhancement is performed on the grayscale image of the concrete sample to be tested according to the corrosion intensity to obtain an enhanced image of the concrete sample to be tested; and the degree of unevenness of the concrete to be tested is obtained by analyzing the enhanced image of the concrete sample to be tested;

[0008] The quality of the concrete to be tested is tested according to the degree of unevenness of the concrete to be tested.

[0009] Preferably, the grayscale image of the concrete sample to be tested is divided into a plurality of concrete areas, including the following specific methods:

[0010] Preset a split parameter , using tile segmentation algorithm to segment the grayscale image of the concrete sample to be tested according to The tile size is divided and each tile is treated as an independent area and recorded as the concrete area.

[0011] Preferably, the method of obtaining the corrosion factor of the concrete edge line according to the position distribution of the edge pixel points on each concrete edge line in the concrete area includes the following specific methods:

[0012] For any concrete edge line in any concrete area, a chain code algorithm is used to obtain a chain code value of each edge pixel point on the concrete edge line to form a chain code sequence of the concrete edge line;

[0013] Obtaining the distribution clutter of the concrete edge line according to the position distribution of edge pixel points on the concrete edge line;

[0014] Place the first The chain code value of the edge pixel is The absolute value of the difference between the chain code values ​​of the edge pixels is recorded as The chain code difference value of each edge pixel point is calculated; the cumulative sum of the chain code difference values ​​of all edge pixel points on the concrete edge line is recorded as the morphological regularity of the concrete edge line;

[0015] The product of the reciprocal of the number of chain code value types in the chain code sequence of the concrete edge line, the distribution disorder of the concrete edge line, and the morphological regularity of the concrete edge line is used as the corrosion factor of the concrete edge line.

[0016] Preferably, the method of obtaining the distribution disorder of the concrete edge line according to the position distribution of the edge pixel points on the concrete edge line includes:

[0017] In the concrete area, the coordinate positions of all edge pixel points on the concrete edge line are curve fitted using the least squares method to obtain a fitted curve; the variance of the curvature of all edge pixel points in the fitted curve is used as the distribution clutter of the concrete edge line.

[0018] Preferably, the method of obtaining the weighted corrosion factor of each edge pixel on the concrete edge line according to the grayscale difference between the edge pixel and the surrounding pixels on the concrete edge line and the corrosion factor of the concrete edge line includes the following specific methods:

[0019] Preset a neighborhood window parameter , for the first edge pixels, with the The edge pixel point is used as the window center, and the window size is obtained as and record this window as The neighborhood reference range of edge pixels;

[0020] According to The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. Grayscale correction factor of edge pixels;

[0021] The first The product of the grayscale correction factor of the edge pixel and the corrosion factor of the concrete edge line is used as the The weighted corrosion factor of each edge pixel.

[0022] Preferably, the The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. Grayscale correction factor of edge pixels, including the specific method is:

[0023] The first The edge pixel point in the neighborhood reference range The gray value of the pixel is The absolute value of the difference between the grayscale values ​​of the edge pixels is recorded as The grayscale difference value of the pixel points; The inverse proportional value of the sum of the grayscale difference values ​​of all pixels within the reference range of the edge pixel is recorded as Grayscale correction factor of edge pixels.

[0024] Preferably, the method of obtaining the corrosion intensity of each concrete edge line according to the weighted corrosion factors of different edge pixels on the concrete edge line includes the following specific methods:

[0025] The first The reciprocal of the absolute value of the difference between the weighted corrosion factor of the edge pixel and the mean of the weighted corrosion factors of all edge pixels on the concrete edge line is recorded as The first inverse of the edge pixel; The weighted corrosion factor of the edge pixel is The product of the first reciprocal of the edge pixels is recorded as The corrosion intensity factor of each edge pixel;

[0026] The normalized value of the accumulated corrosion factors of all edge pixels on the concrete edge line is used as the corrosion intensity of the concrete edge line.

[0027] Preferably, the corrosion enhancement is performed on the grayscale image of the concrete sample to be inspected according to the corrosion intensity to obtain the enhanced image of the concrete sample to be inspected, and the specific method includes:

[0028] Preset a structural element parameter For any concrete edge line, the corrosion intensity of the concrete edge line is compared with the structural element parameter The integer value of the product of is used as the size of the corrosion structure element of the concrete edge line;

[0029] In the concrete area, the corrosion structural element of each concrete edge line is used to corrode each pixel on the concrete edge line to obtain the corroded concrete area; the image fusion algorithm is used to fuse all the corroded concrete areas to obtain the enhanced image of the concrete sample to be tested.

[0030] Preferably, the method of obtaining the degree of unevenness of the concrete to be tested by analyzing the enhanced image of the concrete sample to be tested includes the following specific methods:

[0031] The enhanced image of the concrete sample to be tested is analyzed using the connected domain analysis method to obtain several connected domains;

[0032] The ratio of the total number of all pixels in all connected domains in the enhanced concrete sample image to be detected to the number of all pixels in the enhanced concrete sample image to be detected is used as the unevenness degree of the concrete to be detected.

[0033] Preferably, the quality inspection of the concrete to be inspected according to the degree of unevenness of the concrete to be inspected includes the following specific methods:

[0034] Preset a threshold parameter , if the unevenness of the concrete to be tested is greater than or equal to the threshold parameter , the quality of the concrete to be tested will be recorded as failing.

[0035] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains a weighted corrosion factor of each edge pixel on the concrete edge line according to the grayscale difference between the edge pixel and the surrounding pixel points on the concrete edge line, and the corrosion factor of the concrete edge line; obtains the corrosion intensity of each concrete edge line according to the weighted corrosion factors of different edge pixel points on the concrete edge line; performs corrosion enhancement on the grayscale image of the concrete sample to be detected according to the corrosion intensity to obtain an enhanced image of the concrete sample to be detected; thereby adaptively corrosion enhancement is performed on different concrete areas; obtains the degree of unevenness of the concrete to be detected by analyzing the enhanced image of the concrete sample to be detected; performs quality inspection on the concrete to be detected according to the degree of unevenness of the concrete to be detected; thereby obtaining a more accurate degree of concrete unevenness, thereby improving the accuracy of concrete quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a flow chart of the steps of a concrete quality detection method for water conservancy projects according to the present invention;

[0038] Figure 2 The figure is a characteristic relationship flow chart of a concrete quality detection method for water conservancy projects according to the present invention. DETAILED DESCRIPTION

[0039] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of a concrete quality testing method for water conservancy projects proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The following describes in detail a concrete quality detection method for water conservancy projects provided by the present invention in conjunction with the accompanying drawings.

[0042] See also Figure 1, which shows a flowchart of a method for detecting the quality of concrete for water conservancy projects provided by one embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Obtain a grayscale image of a concrete sample to be tested.

[0044] Specifically, we first need to collect the grayscale image of the concrete sample to be tested. The specific process is as follows:

[0045] After the mixer stops running, a concrete sampler is used to take multiple samples of the concrete to be tested in the mixer; the concrete sample to be tested is placed in a sealed container, and a high-resolution camera is used to clearly obtain an image of the concrete sample to be tested in the sealed container. The image of the concrete sample to be tested is subjected to median filtering, denoising, and grayscale operations to obtain a grayscale image of the concrete sample to be tested.

[0046] Among them, the median filtering denoising and grayscale operations are existing technologies and are not described in detail in this embodiment.

[0047] So far, the grayscale image of the concrete sample to be tested is obtained through the above method.

[0048] Step S002: Divide the grayscale image of the concrete sample to be tested into several concrete areas; obtain the corrosion factor of the concrete edge line according to the position distribution of the edge pixel points on each concrete edge line in the concrete area; obtain the weighted corrosion factor of each edge pixel point on the concrete edge line according to the grayscale difference between the edge pixel point on the concrete edge line and the surrounding pixels, and the corrosion factor of the concrete edge line; obtain the corrosion intensity of each concrete edge line according to the weighted corrosion factors of different edge pixels on the concrete edge line.

[0049] It should be noted that the uniformity of the concrete area is mainly reflected in the number of stones with different color differences in the concrete area. The more the number, the more edge lines there are in the concrete area, and the greater the degree of unevenness. However, due to the texture characteristics of the stone, there will be a large number of edge lines on the stone surface under light and shadow conditions, which will cause errors in the unevenness of the concrete area. Adaptive grayscale corrosion can eliminate the edge lines on the stone surface in the concrete area, thereby amplifying the edge lines between stones with different color differences, thereby highlighting the uneven mixing of the concrete. Therefore, the corrosion factor of each edge line is obtained by the edge line type of the edge pixel point in the concrete area. The corrosion intensity of each edge line is obtained according to the corrosion factor of the edge pixel line and the difference in grayscale value with the surrounding pixels.

[0050] Preset a split parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation;

[0051] The tile segmentation algorithm is used to segment the grayscale image of the concrete sample to be tested into The tile size is divided and each tile is treated as an independent area and recorded as the concrete area;

[0052] The specific operation of segmenting the grayscale image is: using the preset size The sliding window is used to perform a step size of The sliding window operation is performed, and each sliding window is regarded as a tile.

[0053] 1. Obtain the corrosion factor of the concrete edge line.

[0054] It should be noted that due to the texture characteristics of stone, there will be a large number of edge lines on the stone surface under light and shadow conditions. By analyzing the position arrangement of edge pixels in the concrete area, the type of edge line to which it belongs is determined, so as to obtain the corrosion factor of each concrete edge line.

[0055] Preferably, for any concrete area, the Canny edge detection algorithm is used to obtain all concrete edge lines in the concrete area.

[0056] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the corrosion factor of the concrete edge line according to the position distribution of the edge pixel points on each concrete edge line in the concrete area is:

[0057] For any concrete edge line in the concrete area, a chain code algorithm is used to obtain a chain code value of each edge pixel point on the concrete edge line to form a chain code sequence of the concrete edge line;

[0058] Obtaining the distribution clutter of the concrete edge line according to the position distribution of edge pixel points on the concrete edge line;

[0059] Place the first The chain code value of the edge pixel is The absolute value of the difference between the chain code values ​​of the edge pixels is recorded as The chain code difference value of each edge pixel point is calculated; the cumulative sum of the chain code difference values ​​of all edge pixel points on the concrete edge line is recorded as the morphological regularity of the concrete edge line;

[0060] The product of the reciprocal of the number of chain code values ​​in the chain code sequence of the concrete edge line, the distribution disorder of the concrete edge line, and the morphological regularity of the concrete edge line is used as the corrosion factor of the concrete edge line;

[0061] The specific formula is:

[0062]

[0063] Where, Indicates the corrosion factor of the concrete edge line; Represents the number of all edge pixels on the concrete edge line; The number of types of chain code values ​​in the chain code sequence representing the concrete edge line; Indicates the first The chain code value of edge pixels; Indicates the first The chain code value of edge pixels; Indicates the chaotic distribution of concrete edge lines; Indicates taking the absolute value; Indicates the regularity of the concrete edge line.

[0064] It should be noted that if the chain code value types in the chain code sequence of the concrete edge line are more, it means that the shape of the concrete edge line is closer to the closed edge line, and the concrete edge line is more likely to be the edge between stones of different color differences, and its corrosion factor is smaller; if the difference between the chain code values ​​in the chain code sequence of the concrete edge line is greater, it means that the shape of the concrete edge line is closer to the chaotic and irregular internal edge line of the stone, and its corrosion factor is greater; and because the curvature of the closed edge of the stone is usually smoother and more continuous than the curvature of the jagged and chaotic edge inside the stone, the disorder of the edge can also be reflected by the variance of the curvature.

[0065] Preferably, in some implementations of the embodiments of the present invention, a specific method for obtaining the distribution clutter of the concrete edge line according to the position distribution of edge pixel points on the concrete edge line is:

[0066] In the concrete area, the coordinate positions of all edge pixel points on the concrete edge line are curve fitted using the least squares method to obtain a fitted curve; the variance of the curvature of all edge pixel points in the fitted curve is used as the distribution clutter of the concrete edge line.

[0067] Among them, the least squares method, the chain code algorithm and the Canny edge detection algorithm are existing technologies and will not be described in detail in this embodiment.

[0068] At this point, the corrosion factor of the concrete edge line is obtained.

[0069] 2. Obtain the weighted corrosion factor of each edge pixel on the concrete edge line.

[0070] It should be noted that since the internal edge line of the stone may be a closed shape, there will be a large error in distinguishing it simply by the shape of the edge line; and when the concrete edge line is the edge between stones of different color differences, there will be a large grayscale difference between the pixels around the concrete edge line. Therefore, by analyzing the grayscale difference between the edge pixel points on the concrete edge line and the surrounding pixels, and correcting the corrosion factor of the edge line, the weighted corrosion factor of each edge pixel point on the concrete edge line is obtained.

[0071] Preferably, in some implementations of the embodiments of the present invention, based on the grayscale difference between the edge pixel and the surrounding pixels on the concrete edge line and the corrosion factor of the concrete edge line, a specific method for obtaining the weighted corrosion factor of each edge pixel on the concrete edge line is as follows:

[0072] Preset a neighborhood window parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation;

[0073] For the concrete edge line edge pixels, with the The edge pixel point is used as the window center, and the window size is obtained as and record this window as The neighborhood reference range of edge pixels;

[0074] According to The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. Grayscale correction factor of edge pixels;

[0075] The first The product of the grayscale correction factor of the edge pixel and the corrosion factor of the concrete edge line is used as the The weighted corrosion factor of each edge pixel;

[0076] The specific formula is:

[0077]

[0078] Where, Indicates the The weighted corrosion factor of each edge pixel; Indicates the corrosion factor of the concrete edge line; Indicates the Grayscale correction factor of edge pixels.

[0079] Preferably, in some implementations of the embodiments of the present invention, according to The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. The specific method of grayscale correction factor of edge pixels is:

[0080] The first The edge pixel point in the neighborhood reference range The gray value of the pixel is The absolute value of the difference between the grayscale values ​​of the edge pixels is recorded as The grayscale difference value of the pixel points; The inverse proportional value of the sum of the grayscale difference values ​​of all pixels within the reference range of the edge pixel is recorded as Grayscale correction factor of edge pixels;

[0081] The specific formula is:

[0082]

[0083] Where, Indicates the Grayscale correction factor of edge pixels; Indicates the The number of all pixels within the reference neighborhood of an edge pixel; Indicates the The edge pixel point in the neighborhood reference range Gray value of each pixel; Indicates the Gray value of edge pixels; Indicates taking the absolute value; Represents an exponential function with a natural constant as its base.

[0084] At this point, the weighted corrosion factor of each edge pixel on the concrete edge line is obtained.

[0085] 3. Obtain the corrosion intensity of the concrete edge line.

[0086] It should be noted that if there is a large difference between the weighted corrosion factor of the edge pixel points on the concrete edge line and the average of the weighted corrosion factors of the edge pixel points on the concrete edge line, it means that the concrete edge line may be a situation where the internal edge line of the stone is adhered to the edge of the stone. At this time, the concrete edge line should be retained, so the corrosion intensity should be reduced.

[0087] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the corrosion intensity of each concrete edge line according to the weighted corrosion factors of different edge pixels on the concrete edge line is:

[0088] The first The reciprocal of the absolute value of the difference between the weighted corrosion factor of the edge pixel and the mean of the weighted corrosion factors of all edge pixels on the concrete edge line is recorded as The first inverse of the edge pixel; The weighted corrosion factor of the edge pixel is The product of the first reciprocal of the edge pixels is recorded as The corrosion intensity factor of each edge pixel;

[0089] The normalized value of the accumulated corrosion factors of all edge pixels on the concrete edge line is used as the corrosion intensity of the concrete edge line;

[0090] The specific formula is:

[0091]

[0092] Where, Indicates the corrosion intensity of the concrete edge line; Represents the number of all edge pixels on the concrete edge line; Indicates the first The weighted corrosion factor of each edge pixel; Represents the mean value of the weighted corrosion factors of all edge pixels on the concrete edge line; Indicates taking the absolute value; Indicates the The corrosion intensity factor of each edge pixel; Represents the preset hyperparameters. This implementation presets , used to prevent the denominator from being 0.

[0093] At this point, the corrosion intensity of the concrete edge line is obtained through the above method.

[0094] Step S003: performing corrosion enhancement on the grayscale image of the concrete sample to be inspected according to the corrosion intensity to obtain an enhanced image of the concrete sample to be inspected; and obtaining the degree of unevenness of the concrete to be inspected by analyzing the enhanced image of the concrete sample to be inspected.

[0095] Preferably, in some implementations of the embodiments of the present invention, the grayscale image of the concrete sample to be inspected is subjected to corrosion enhancement according to the corrosion intensity, and the specific method for obtaining the enhanced image of the concrete sample to be inspected is:

[0096] Preset a structural element parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation;

[0097] For any concrete edge line, the corrosion intensity of the concrete edge line is compared with the structural element parameter The integer value of the product of is used as the size of the corrosion structure element of the concrete edge line;

[0098] The specific formula is:

[0099] Where, Indicates the size of the corrosion structural element at the concrete edge line; Indicates preset structural element parameters; Indicates the corrosion intensity of the concrete edge line; Indicates rounding up;

[0100] In the concrete area, the corrosion structural element of each concrete edge line is used to corrode each pixel on the concrete edge line to obtain the corroded concrete area; the image fusion algorithm is used to fuse all the corroded concrete areas to obtain the enhanced image of the concrete sample to be tested.

[0101] The image fusion algorithm used in this embodiment is a wavelet transform algorithm, which is a prior art and will not be described in detail in this embodiment.

[0102] At this point, the enhanced image of the concrete sample to be tested is obtained.

[0103] It should be noted that the more connected domains of the closed area in the enhanced image of the concrete sample to be tested, the more stones there are in the concrete, and the greater the degree of unevenness. Therefore, the degree of unevenness of the enhanced image of the concrete sample to be tested is obtained by analyzing the area ratio of the connected domains of the closed area.

[0104] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the degree of unevenness of the concrete to be inspected by analyzing the enhanced image of the concrete sample to be inspected is:

[0105] The enhanced image of the concrete sample to be tested is analyzed using the connected domain analysis method to obtain several connected domains;

[0106] The ratio of the total number of all pixels in all connected domains in the enhanced concrete sample image to be detected to the number of all pixels in the enhanced concrete sample image to be detected is used as the unevenness degree of the concrete to be detected.

[0107] The connected domain analysis method is an existing technology and will not be described in detail in this embodiment.

[0108] So far, the unevenness of the concrete to be tested is obtained through the above method.

[0109] Step S004: Performing a quality inspection on the concrete to be inspected according to the degree of unevenness of the concrete to be inspected.

[0110] Preferably, in some implementations of the embodiments of the present invention, the specific method for performing quality inspection on the concrete to be inspected is as follows, based on the degree of unevenness of the concrete to be inspected:

[0111] Preset a threshold parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation;

[0112] If the unevenness of the concrete to be tested is greater than or equal to the threshold parameter , the quality of the concrete to be tested will be recorded as failing.

[0113] See also Figure 2 , which shows a characteristic relationship flow chart of a concrete quality detection method for water conservancy projects;

[0114] At this point, this embodiment is completed.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A concrete quality detection method for water conservancy projects, characterized in that: The method comprises the following steps: Obtaining a grayscale image of the concrete sample to be tested; The grayscale image of the concrete sample to be tested is divided into several concrete areas; the corrosion factor of the concrete edge line is obtained based on the position distribution of the edge pixel points on each concrete edge line in the concrete area; the weighted corrosion factor of each edge pixel point on the concrete edge line is obtained based on the grayscale difference between the edge pixel point and the surrounding pixels and the corrosion factor of the concrete edge line; the corrosion intensity of each concrete edge line is obtained based on the weighted corrosion factors of different edge pixels on the concrete edge line; Corrosion enhancement is performed on the grayscale image of the concrete sample to be tested according to the corrosion intensity to obtain an enhanced image of the concrete sample to be tested; and the degree of unevenness of the concrete to be tested is obtained by analyzing the enhanced image of the concrete sample to be tested; Conduct quality inspection on the concrete to be inspected based on the degree of unevenness of the concrete to be inspected; The method of obtaining the corrosion factor of the concrete edge line according to the position distribution of the edge pixel points on each concrete edge line in the concrete area includes: For any concrete edge line in any concrete area, a chain code algorithm is used to obtain a chain code value of each edge pixel point on the concrete edge line to form a chain code sequence of the concrete edge line; Obtaining the distribution clutter of the concrete edge line according to the position distribution of edge pixel points on the concrete edge line; Place the first The chain code value of the edge pixel is The absolute value of the difference between the chain code values ​​of the edge pixels is recorded as The chain code difference value of each edge pixel point is calculated; the cumulative sum of the chain code difference values ​​of all edge pixel points on the concrete edge line is recorded as the morphological regularity of the concrete edge line; The product of the reciprocal of the number of chain code values ​​in the chain code sequence of the concrete edge line, the distribution disorder of the concrete edge line, and the morphological regularity of the concrete edge line is used as the corrosion factor of the concrete edge line; The method of obtaining the distribution disorder of the concrete edge line according to the position distribution of the edge pixel points on the concrete edge line includes: In the concrete area, the coordinate positions of all edge pixel points on the concrete edge line are curve fitted using the least squares method to obtain a fitted curve; the variance of the curvature of all edge pixel points in the fitted curve is used as the distribution clutter of the concrete edge line.

2. A method for detecting the quality of concrete for water conservancy projects according to claim 1, characterized in that: The specific method of dividing the grayscale image of the concrete sample to be tested into a plurality of concrete areas includes: Preset a split parameter , using tile segmentation algorithm to segment the grayscale image of the concrete sample to be tested according to The tile size is divided and each tile is treated as an independent area and recorded as the concrete area.

3. The method for detecting the quality of concrete for water conservancy projects according to claim 1, wherein: The method of obtaining the weighted corrosion factor of each edge pixel on the concrete edge line according to the grayscale difference between the edge pixel and the surrounding pixels on the concrete edge line and the corrosion factor of the concrete edge line includes the following specific steps: Preset a neighborhood window parameter , for the first edge pixels, with the The edge pixel point is used as the window center, and the window size is obtained as and record this window as The neighborhood reference range of edge pixels; According to The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. Grayscale correction factor of edge pixels; The first The product of the grayscale correction factor of the edge pixel and the corrosion factor of the concrete edge line is used as the The weighted corrosion factor of each edge pixel.

4. A method for detecting the quality of concrete for water conservancy projects according to claim 3, characterized in that: According to the The grayscale difference between the edge pixel and the pixel in its neighborhood reference range is obtained. Grayscale correction factor of edge pixels, including the specific method is: The first The edge pixel point in the neighborhood reference range The gray value of the pixel is The absolute value of the difference between the grayscale values ​​of the edge pixels is recorded as The grayscale difference value of the pixel points; The inverse proportional value of the sum of the grayscale difference values ​​of all pixels within the reference range of the edge pixel is recorded as Grayscale correction factor of edge pixels.

5. A method for detecting the quality of concrete for water conservancy projects according to claim 1, characterized in that: The method of obtaining the corrosion intensity of each concrete edge line according to the weighted corrosion factors of different edge pixels on the concrete edge line includes the following specific methods: The first The reciprocal of the absolute value of the difference between the weighted corrosion factor of the edge pixel and the mean of the weighted corrosion factors of all edge pixels on the concrete edge line is recorded as The first inverse of the edge pixel; The weighted corrosion factor of the edge pixel is The product of the first reciprocal of the edge pixels is recorded as The corrosion intensity factor of each edge pixel; The normalized value of the accumulated corrosion factors of all edge pixels on the concrete edge line is used as the corrosion intensity of the concrete edge line.

6. A method for detecting the quality of concrete for water conservancy projects according to claim 1, characterized in that: The method of performing corrosion enhancement on the grayscale image of the concrete sample to be inspected according to the corrosion intensity to obtain the enhanced image of the concrete sample to be inspected includes the following specific methods: Preset a structural element parameter For any concrete edge line, the corrosion intensity of the concrete edge line is compared with the structural element parameter The integer value of the product of is used as the size of the corrosion structure element of the concrete edge line; In the concrete area, the corrosion structural element of each concrete edge line is used to corrode each pixel on the concrete edge line to obtain the corroded concrete area; the image fusion algorithm is used to fuse all the corroded concrete areas to obtain the enhanced image of the concrete sample to be tested.

7. A method for detecting the quality of concrete for water conservancy projects according to claim 1, characterized in that: The method of obtaining the unevenness of the concrete to be tested by analyzing the enhanced image of the concrete sample to be tested includes the following specific methods: The enhanced image of the concrete sample to be tested is analyzed using the connected domain analysis method to obtain several connected domains; The ratio of the total number of all pixels in all connected domains in the enhanced concrete sample image to be detected to the number of all pixels in the enhanced concrete sample image to be detected is used as the unevenness degree of the concrete to be detected.

8. A method for detecting the quality of concrete for water conservancy projects according to claim 1, characterized in that: The concrete to be tested is subjected to quality inspection based on the degree of unevenness of the concrete to be tested, including the following specific methods: Preset a threshold parameter , if the unevenness of the concrete to be tested is greater than or equal to the threshold parameter , the quality of the concrete to be tested will be recorded as failing.

Images