Brick content analysis method based on microscope image of brick-mixed powder and related equipment

Abstract

The present application discloses a brick content analysis method based on a microscope image of brick-concrete powder and related equipment, wherein the method includes: for a target brick-concrete powder, obtaining a target microscope image corresponding to each shooting dimension, wherein the shooting dimensions include: magnification and shooting area; performing background image area processing on the target microscope image to obtain an image to be analyzed; performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; performing brick content analysis based on each of the color segmentation data corresponding to the target brick-concrete powder to obtain a brick content analysis result. By determining the brick content analysis result based on the target microscope image of the target brick-concrete powder, there is no need to separate bricks from other powders, no need for large equipment and complex technology, which simplifies the operation process and improves the speed of detecting the brick content in the brick-concrete aggregate.

Description

Technical Field

[0001] The invention relates to the technical field of image processing and resource processing of construction waste, and in particular to a brick content analysis method based on a microscope image of brick-concrete powder and related equipment. Background Art

[0002] Converting construction waste into recycled coarse and fine aggregates (i.e., brick-concrete aggregates) for use in fresh concrete can not only promote the resource reuse of construction waste, but also reduce the impact on the natural environment caused by the exploitation of natural aggregates. At present, red bricks and other bricks account for a large proportion of construction waste, which leads to a high brick content in brick-concrete aggregates. Relevant studies have shown that the higher the proportion of bricks in brick-concrete aggregates, the worse the performance of the recycled concrete made from them. Therefore, the brick content in brick-concrete aggregates can be used as an important indicator to evaluate the quality of brick-concrete aggregates, which is of great significance to the recycling of brick-concrete aggregates.

[0003] In the current method of detecting the brick content in brick-concrete aggregate, random sampling is first performed, and then the bricks in the sample are separated from other particles by mechanical or manual methods. Finally, the brick content in the sample is weighed and calculated. The operation process is complicated and it is impossible to quickly detect the brick content in the brick-concrete aggregate. Summary of the invention

[0004] Based on this, it is necessary to propose a brick content analysis method and related equipment based on microscope images of brick-concrete powder to address the technical problems of the existing technology in detecting the brick content in brick-concrete aggregate, which has complicated operating procedures and cannot quickly detect the brick content in brick-concrete aggregate.

[0005] In a first aspect, a method for analyzing brick content based on a microscope image of brick-mixed powder is provided, the method comprising:

[0006] For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the shooting dimension includes: magnification and shooting area;

[0007] Performing background image region processing on the target microscope image to obtain an image to be analyzed;

[0008] Performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0009] Brick content analysis is performed according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0010] Furthermore, the step of obtaining a target microscope image corresponding to each shooting dimension for the target brick-concrete powder includes:

[0011] Obtain a test microscope image corresponding to the sampled brick-concrete powder;

[0012] According to the test microscope image, judging whether the spacing of the brick-concrete powder meets the unqualified spacing condition, or judging whether the brick-concrete powder is stacked;

[0013] If any one of them is yes, then based on the sampled brick-concrete powder after the distribution is adjusted, jump to the step of obtaining the test microscope image corresponding to the sampled brick-concrete powder and continue to execute;

[0014] If both are negative, the sampled brick-concrete powder is used as the target brick-concrete powder;

[0015] For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the target microscope image is a microscope image obtained by shooting the target brick-concrete powder based on the target configuration and the shooting dimension, and the target configuration adopts a target light source and a target microscope setting, the target light source adopts natural light or white light, and the target microscope is set to not add a filter.

[0016] Furthermore, the step of performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data includes:

[0017] Based on a preset color space, performing color distribution analysis on the image to be analyzed to obtain color distribution data;

[0018] According to the preset replacement color data and the threshold range data corresponding to the color space type corresponding to the preset color space, the color distribution data is segmented into brick and concrete colors to obtain initial segmentation data;

[0019] The color segmentation data is determined according to the initial segmentation data.

[0020] Furthermore, the step of determining the color segmentation data according to the initial segmentation data includes:

[0021] Inputting the image to be analyzed into a pre-trained brick segmentation model to perform brick powder segmentation to obtain a brick powder mask;

[0022] Performing segmentation difference data identification on the brick powder mask and the initial segmentation data;

[0023] The color segmentation data is determined according to the image to be analyzed, the initial segmentation data and the segmentation difference data.

[0024] Furthermore, the preset color space adopts the HSL color space, and the preset replacement color data adopts the color data corresponding to black;

[0025] The threshold range data corresponding to the color space type corresponding to the HSL color space includes: H[0,85], S[32,255], L[68,255].

[0026] Furthermore, the step of performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result includes:

[0027] Performing brick content analysis on each of the color segmentation data to obtain a first result;

[0028] Calculate the average value of each of the first results corresponding to the same magnification factor to obtain a second result;

[0029] The weighted sum of each of the second results corresponding to the target brick-mixed powder is performed to obtain the brick content analysis result.

[0030] Furthermore, the step of calculating the average value of each of the first results corresponding to the same magnification factor to obtain the second result includes:

[0031] Deleting the maximum and minimum values ​​of the first results corresponding to the same magnification factor;

[0032] The second result is obtained by calculating the average value of each of the first results corresponding to the same magnification factor after the deletion process.

[0033] In a second aspect, a brick content analysis device based on a microscope image of a brick-mixed powder is provided, the device comprising:

[0034] A data acquisition module is used to acquire a target microscope image corresponding to each shooting dimension for a target brick-concrete powder, wherein the shooting dimension includes: a magnification and a shooting area;

[0035] A background processing module, used for performing background image area processing on the target microscope image to obtain an image to be analyzed;

[0036] A color segmentation module, used for performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0037] The brick content analysis module is used to perform brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0038] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned brick content analysis method based on microscope images of brick-concrete powder when executing the computer program.

[0039] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned brick content analysis method based on the microscope image of brick-concrete powder are implemented.

[0040] The brick content analysis method and related equipment based on the microscope image of brick-concrete powder of the present application obtain the target microscope image corresponding to each shooting dimension for the target brick-concrete powder, wherein the shooting dimension includes: magnification and shooting area; the target microscope image is processed with the background image area to obtain the image to be analyzed; the image to be analyzed is color segmented between brick and concrete to obtain color segmentation data; brick content analysis is performed according to each color segmentation data corresponding to the target brick-concrete powder to obtain the brick content analysis result. The present application determines the brick content analysis result based on the target microscope image of the target brick-concrete powder, does not need to separate bricks from other powders, does not require large equipment and complex technology, simplifies the operation process, and improves the speed of detecting the brick content in the brick-concrete aggregate; the existing technology is all for the brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes the brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, realizing non-destructive testing; the shooting dimension includes magnification and shooting area, thereby realizing the brick content analysis of images from at least one perspective, further improving the accuracy of the brick content analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0042] in:

[0043] Figure 1 A diagram showing an application environment of a brick content analysis method based on a microscope image of brick-mixed powder in one embodiment;

[0044] Figure 2 is a flow chart of a brick content analysis method based on a microscope image of brick-mixed powder in one embodiment;

[0045] Figure 3 is a structural block diagram of a brick content analysis device based on a microscope image of brick-concrete powder in one embodiment;

[0046] Figure 4 is a structural block diagram of a computer device in one embodiment;

[0047] Figure 5 Another structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The brick content analysis method based on the brick-mix powder microscope image provided by the embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client 110 communicates with the server 120 through the network.

[0050] The server 120 can obtain the target microscope image corresponding to each shooting dimension for the target brick-concrete powder through the client 110, wherein the shooting dimension includes: magnification and shooting area. The server 120 is used to: perform background image area processing on the target microscope image to obtain the image to be analyzed; perform color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; perform brick content analysis according to each of the color segmentation data corresponding to the target brick-concrete powder to obtain a brick content analysis result. The present application determines the brick content analysis result based on the target microscope image of the target brick-concrete powder, without the need to separate bricks from other powders, without requiring large equipment and complex technology, thus simplifying the operation process and improving the speed of detecting the brick content in the brick-concrete aggregate; the existing technology is all for the brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes the brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, thus realizing non-destructive testing; the shooting dimension includes magnification and shooting area, thereby realizing the brick content analysis of images from at least one perspective, further improving the accuracy of the brick content analysis.

[0051] In another embodiment of the present application, the server 120 obtains a target microscope image corresponding to each shooting dimension for the target brick-concrete powder from a preset storage space, wherein the shooting dimensions include: magnification and shooting area; performs background image area processing on the target microscope image to obtain an image to be analyzed; performs color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; performs brick content analysis based on each of the color segmentation data corresponding to the target brick-concrete powder to obtain a brick content analysis result.

[0052] In another embodiment of the present application, the client 110 obtains a target microscope image corresponding to each shooting dimension for the target brick-concrete powder from a preset storage space, wherein the shooting dimensions include: magnification and shooting area; performs background image area processing on the target microscope image to obtain an image to be analyzed; performs color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; performs brick content analysis according to each of the color segmentation data corresponding to the target brick-concrete powder to obtain a brick content analysis result.

[0053] The client 110 may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server 120 may be implemented by an independent server or a server cluster consisting of multiple servers.

[0054] The present invention is described in detail below through specific embodiments.

[0055] See also Figure 2 As shown, Figure 2 A flow chart of a brick content analysis method based on a microscope image of brick-mixed powder provided by an embodiment of the present invention includes the following steps:

[0056] S1: For the target brick-concrete powder, obtain a target microscope image corresponding to each shooting dimension, wherein the shooting dimension includes: magnification and shooting area;

[0057] Specifically, the target microscope image may be obtained by a user input, may be obtained from a preset storage space, or may be obtained from a third-party application.

[0058] The target brick-mix powder is the brick-mix powder for which brick content analysis is desired. Optionally, the particle size of the powder particles in the brick-mix powder is less than 0.15 mm.

[0059] The target microscope image is a digital image taken of the target brick-concrete powder.

[0060] It can be understood that at least one shooting area is set for the target brick-concrete powder.

[0061] Optionally, the magnification can be 10 times, 20 times, 30 times, 40 times, 50 times, or 60 times.

[0062] S2: performing background image region processing on the target microscope image to obtain an image to be analyzed;

[0063] Optionally, an image processing tool is called to replace the background image area in the target microscope image with a preset background color, and the target microscope image after the replacement is used as the image to be analyzed.

[0064] Optionally, the default background color is white.

[0065] Optionally, the image processing tool uses Photoshop, which mainly processes digital images composed of pixels.

[0066] Optionally, a pre-trained background segmentation model is used to perform background image segmentation on the target microscope image, and the background image area in the target microscope image is replaced with a preset background color based on the mask obtained by the segmentation, so that only the image area corresponding to the brick-concrete powder is retained, and the target microscope image with the background image area replaced is used as the image to be analyzed.

[0067] Optionally, the background segmentation model is a model obtained by training based on the target detection network. The model structure and model training method of the background segmentation model can be selected from the prior art and will not be described in detail here.

[0068] The background segmentation model outputs a binary mask, in which the value of the mask point is 1 or 0; if the value of the mask point is 1, the type of the pixel point corresponding to the mask point in the target microscope image is determined to be background; if the value of the mask point is 0, the type of the pixel point corresponding to the mask point in the target microscope image is determined to be brick-concrete powder.

[0069] It can be understood that by processing the background image region, the background image region is prevented from affecting the accuracy of color segmentation.

[0070] S3: performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0071] Specifically, the image to be analyzed is drawn in a preset color space, and then a color distribution analysis is performed. The color segmentation of bricks and concrete is performed based on the result of the color distribution analysis and the threshold range data, and the segmented data is used as color segmentation data.

[0072] Optionally, a GUI (Graphical User Interface, also known as graphical user interface) desktop program that can be applied to actual engineering projects is designed through Qt5 to draw the distribution of the image to be analyzed in a preset color space, and then the color space of the brick-concrete powder is distinguished according to a default reference threshold (that is, threshold range data), and the color segmentation data is determined based on the data of the brick space (that is, the distribution area of ​​the brick color in the preset color space) composed of each channel threshold (for example, the H channel, S channel and L channel in the HSL color space).

[0073] Optionally, the color segmentation data is determined based on the brick space composed of the threshold values ​​of each channel, which can be replaced by marking the pixel points in the brick space composed of the threshold values ​​of each channel as preset replacement color data for easy distinction, and using the data of the marked brick space as color segmentation data.

[0074] Optionally, the preset replacement color data uses black.

[0075] Optionally, the pixel points in the brick space composed of each channel threshold are marked as black for easy distinction, and the data of the brick space that has been marked is used as color segmentation data, which can be replaced by: marking the pixel points in the brick space composed of each channel threshold as black for easy distinction, and then obtaining the user to manually fine-tune the threshold of each channel, re-distinguishing the color space of the brick-mixed powder through the adjusted threshold of each channel, and marking the pixel points in the brick space composed of each channel threshold as preset replacement color data for easy distinction, and using the data of the brick space that has been marked as color segmentation data. By manually fine-tuning the threshold of each channel, the brick space can cover the brick powder, thereby improving the accuracy of the color segmentation data.

[0076] The preset color space can be any of the HSL color space, RGB color space and HSV color space. HSL is a method of representing points in the RGB color model in a cylindrical coordinate system. The RGB color space is defined by the chromaticity of the three primary colors of red, green and blue, which can be used to define the corresponding color triangle to generate other colors. HSV (Hue, Saturation, Value) is a color space created based on the intuitive characteristics of color, also known as the Hexcone Model l.

[0077] Threshold range data, used to describe the channel threshold corresponding to the brick.

[0078] Optional, color segmentation data, used to describe the data corresponding to the brick space.

[0079] Optionally, color segmentation data is used to describe data corresponding to the brick space and data of areas corresponding to powder particles outside the brick space.

[0080] Qt5 is a popular C++ framework for developing cross-platform applications.

[0081] S4: performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0082] Specifically, according to the color segmentation data, the number of pixels of the brick powder is calculated as the first number; the number of pixels in the color segmentation data is calculated as the second number; the first number is divided by the second number to obtain a first result; and the brick content analysis result is determined according to all first results corresponding to the target brick-mixed powder.

[0083] Optionally, a weighted sum is performed on all first results corresponding to the target brick-mixed powder, and the data obtained by the weighted sum is used as the brick content analysis result.

[0084] Optionally, an average value is calculated for all first results corresponding to the target brick-mixed powder, and the calculated data is used as the brick content analysis result.

[0085] It can be understood that each of the color segmentation data corresponding to the target brick-concrete powder includes at least one color segmentation data.

[0086] This embodiment determines the brick content analysis result based on the target microscope image of the target brick-concrete powder. There is no need to separate bricks from other powders, and no large equipment and complex technology are required. The operation process is simplified and the speed of detecting the brick content in the brick-concrete aggregate is improved. The prior art is all for brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, thus realizing non-destructive testing. The shooting dimensions include magnification and shooting area, thereby realizing brick content analysis of images from at least one perspective, further improving the accuracy of brick content analysis.

[0087] In one embodiment, the step of obtaining a target microscope image corresponding to each shooting dimension for the target brick-concrete powder includes:

[0088] S11: Obtain a test microscope image corresponding to the sampled brick-concrete powder;

[0089] Specifically, take a sample from the brick-concrete powder as the sampling brick-concrete powder, spread the sampling brick-concrete powder evenly and flatly on a microscope glass slide. There can be a small amount of gaps between the powder particles, but it is best not to stack them. Then cover them with a cover glass. Use the glass slide, the sampling brick-concrete powder and the cover glass as test samples. Put the test samples under a microscope, obtain a microscope image through the microscope, and use the microscope image as a test microscope image.

[0090] Optionally, a microscope image of the sampled brick-concrete powder is captured based on the target configuration and the shooting dimensions to obtain a test microscope image.

[0091] S12: judging whether the spacing of the brick-concrete powder meets the unqualified spacing condition according to the test microscope image, or judging whether the brick-concrete powder is stacked;

[0092] Specifically, the spacing between the powder particles of the brick-concrete powder should not be too large, and the transitional and scattered powder is difficult to identify. The powder particles of the brick-concrete powder should not be stacked, and the powder particles will produce a large number of shadows, which will have a negative impact on the color recognition of the powder particles. In order to solve this problem, this embodiment determines whether the spacing of the brick-concrete powder meets the unqualified spacing condition based on the test microscope image, or determines whether the brick-concrete powder is stacked based on the test microscope image.

[0093] Optionally, the spacing failure condition is that the spacing is greater than a preset spacing threshold.

[0094] The test microscope image is input into a pre-trained stacking classification model to perform classification prediction on whether stacking exists, and whether stacking exists is determined based on the predicted data.

[0095] The pre-trained stacked classification model is a pre-trained binary classification model.

[0096] S13: If any one of the answers is yes, then based on the sampled brick-concrete powder after the distribution is adjusted, jump to the step of obtaining a test microscope image corresponding to the sampled brick-concrete powder and continue to execute;

[0097] Specifically, if any one of them is yes, that is, the spacing of the brick-concrete powder meets the unqualified spacing condition, or there is stacking of the brick-concrete powder, it means that the sampled brick-concrete powder does not meet the tiling requirements. Therefore, the distribution of the sampled brick-concrete powder in the test sample is adjusted, and then jump to step S11 (that is, obtain the test microscope image corresponding to the sampled brick-concrete powder) and continue to execute step S11 to re-evaluate whether the sampled brick-concrete powder meets the tiling requirements.

[0098] S14: If the answer is no, the sampled brick-concrete powder is used as the target brick-concrete powder;

[0099] Specifically, if the answer is no, that is, the spacing of the brick-concrete powder does not meet the unqualified spacing condition, and there is no stacking of the brick-concrete powder, then it means that the sampled brick-concrete powder meets the paving requirements. Therefore, the sampled brick-concrete powder is used as the target brick-concrete powder.

[0100] S15: For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the target microscope image is a microscope image obtained by shooting the target brick-concrete powder based on the target configuration and the shooting dimension, the target configuration is to adopt a target light source and a target microscope setting, the target light source adopts natural light or white light, and the target microscope is set to not add a filter.

[0101] Specifically, for the test sample corresponding to the target brick-concrete powder, a microscope image corresponding to each shooting dimension is obtained through a microscope, and the obtained microscope image is used as the target microscope image.

[0102] Optionally, at a certain magnification, different shooting areas of the test sample corresponding to the target brick-concrete powder are photographed separately, and each microscope image obtained is used as a target microscope image. The specific operation is to change the recognition area in the eyepiece of the microscope by slowly moving the stage forward and backward / left and right. The images taken multiple times can more comprehensively identify the brick content in the sample.

[0103] In this embodiment, the target light source adopts natural light or white light, and the target microscope is set to not add filters, so as to prevent large errors in subsequent color recognition; relative to the camera, the microscope magnifies the recycled brick-concrete powder that the camera cannot clearly display to a recognizable size and then shoots it, so as to more accurately capture the image of the powder. This application performs brick content analysis based on the target microscope image, thereby improving the accuracy of brick content analysis; the target brick-concrete powder corresponding to the target microscope image has a spacing between brick-concrete powders that does not meet the spacing unqualified condition and there is no stacking of brick-concrete powders, thereby preventing the boundaries between powder particles from being blurred or the color of some powders from being distorted due to shadows, avoiding large errors in color segmentation, and helping to improve the accuracy of brick content analysis.

[0104] In one embodiment, the step of performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data includes:

[0105] S31: performing color distribution analysis on the image to be analyzed based on a preset color space to obtain color distribution data;

[0106] Specifically, the image to be analyzed is drawn in a preset color space, a color distribution analysis is performed on the drawing result, and the data obtained by the analysis is used as color distribution data.

[0107] S32: performing color segmentation of brick and concrete on the color distribution data according to preset replacement color data and threshold range data corresponding to a color space type corresponding to the preset color space to obtain initial segmentation data;

[0108] Specifically, according to the threshold range data corresponding to the color space type corresponding to the preset color space, the color space of the brick-mixed powder is distinguished, and the data of the brick space composed of each channel threshold is replaced or marked as the preset replacement color data, and the color segmentation data is determined according to the data corresponding to the brick space. By replacing the preset replacement color data, it is beneficial to improve the accuracy of brick content analysis.

[0109] S33: Determine the color segmentation data according to the initial segmentation data.

[0110] Optionally, the initial segmentation data is directly used as the color segmentation data.

[0111] Optionally, the initial segmentation data and the image to be analyzed are sent to the target audit end, and the color segmentation data sent by the target audit end is obtained. The user modifies the initial segmentation data according to the image to be analyzed through the target audit end, clicks submit after the modification is completed, and the target audit end uses the initial segmentation data modified by the user as the color segmentation data. Through the adjustment of the target audit end, the accuracy of the determined color segmentation data is improved.

[0112] Optionally, the initial segmentation data and the image to be analyzed are sent to the target audit end, the adjusted threshold range data sent by the target audit end is obtained, the initial segmentation data is regenerated, and "the initial segmentation data → obtaining the adjusted threshold range data → regenerating the initial segmentation data" is repeated until the user feels that the requirements are met. At this time, the user will click submit, and the target audit end will use the initial segmentation data corresponding to the adjusted threshold range data corresponding to the user's click submission as the color segmentation data. By combining the adjustment of the target audit end, the accuracy of the determined color segmentation data is improved.

[0113] In one embodiment, the step of determining the color segmentation data according to the initial segmentation data includes:

[0114] S331: Inputting the image to be analyzed into a pre-trained brick segmentation model to perform brick powder segmentation to obtain a brick powder mask;

[0115] Specifically, the image to be analyzed is input into a pre-trained brick segmentation model to perform brick powder segmentation, and a binary mask obtained by segmentation is used as a brick powder mask.

[0116] Each mask point in the brick powder mask corresponds to a pixel point in the image to be analyzed. The value of each mask point in the brick powder mask is 0 or 1; if the mask point in the brick powder mask is 1, the powder particle corresponding to the pixel point corresponding to the mask point is brick powder; if the mask point in the brick powder mask is 0, the powder particle corresponding to the pixel point corresponding to the mask point is not brick powder.

[0117] S332: performing segmentation difference data identification on the brick powder mask and the initial segmentation data;

[0118] Specifically, the brick powder mask and the initial segmentation data are compared pixel by pixel, and the data corresponding to all pixels with differences (at least including the positions of the pixels) are used as segmentation difference data. For example, if the value of the mask point in the 3rd row and 8th column of the brick powder mask is 1, and the pixel in the 3rd row and 8th column of the initial segmentation data is brick powder, then the pixel is a normal pixel. For example, if the value of the mask point in the 3rd row and 8th column of the brick powder mask is 1, and the pixel in the 3rd row and 8th column of the initial segmentation data is not brick powder, then the pixel is an abnormal pixel.

[0119] S333: Determine the color segmentation data according to the image to be analyzed, the initial segmentation data and the segmentation difference data.

[0120] Specifically, the image to be analyzed, the initial segmentation data and the segmentation difference data are sent to the target audit end, the audit result sent by the target audit end is obtained, the initial segmentation data is corrected according to the audit result, and the corrected initial segmentation data is used as the color segmentation data.

[0121] This embodiment determines the color segmentation data according to the image to be analyzed, the initial segmentation data and the segmentation difference data, which is conducive to improving the accuracy of the color segmentation data and further improving the accuracy of brick content analysis.

[0122] In one embodiment, the preset color space adopts the HSL color space, and the preset replacement color data adopts the color data corresponding to black;

[0123] The threshold range data corresponding to the color space type corresponding to the HSL color space includes: H[0,85], S[32,255], L[68,255].

[0124] Specifically, H[0,85], that is, H channel 0 to 85 of the HSL color space, can be 0, 85, or a value between 0 and 85.

[0125] Specifically, S[32,255], that is, the S channel 32 to 255 of the HSL color space, can be 32, 255, or a value between 32 and 255.

[0126] Specifically, L[68,255], that is, the L channel 68 to 255 of the HSL color space, can be 68, 255, or a value between 68 and 255.

[0127] This embodiment provides a basis for eliminating the need to mechanically separate bricks from other parts of the brick-concrete powder by using the threshold range data corresponding to the color space type corresponding to the HSL color space, thereby reducing the time in batch processing of a large amount of image information.

[0128] In one embodiment, the step of performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result includes:

[0129] S41: Perform brick content analysis on each color segmentation data to obtain a first result;

[0130] Specifically, according to the color segmentation data, the number of pixels of the brick powder is calculated as the first number; the number of pixels in the color segmentation data is calculated as the second number; the first number is divided by the second number to obtain a first result.

[0131] S42: Calculating the average value of each of the first results corresponding to the same magnification factor to obtain a second result;

[0132] Specifically, an average value is calculated for each of the first results corresponding to the same magnification factor, and the calculated data is used as the second result.

[0133] S43: Perform weighted summation on each of the second results corresponding to the target brick-mixed powder to obtain the brick content analysis result.

[0134] Specifically, a weighted sum is performed on each of the second results corresponding to the target brick-mixed powder, and the data obtained by the weighted sum is used as the brick content analysis result.

[0135] Optionally, the weight of the weighted summation is determined according to the magnification factor.

[0136] This embodiment first calculates the average value of each of the first results corresponding to the same magnification factor to obtain the second result, and then performs weighted summation on each of the second results corresponding to the target brick-mixed powder to obtain the brick content analysis result. The adverse effects caused by accidental errors are minimized through average value calculation, thereby improving the accuracy of brick content analysis.

[0137] In one embodiment, the step of calculating the average value of each of the first results corresponding to the same magnification factor to obtain the second result includes:

[0138] S421: Deleting the maximum value and the minimum value of each of the first results corresponding to the same magnification factor;

[0139] S422: Calculate the average value of each of the first results corresponding to the same magnification after the deletion process to obtain the second result.

[0140] This embodiment calculates the average value of each of the first results corresponding to the same amplification factor after the maximum value and the minimum value are deleted to obtain the second result, thereby reducing the influence of noise data (that is, the maximum value and the minimum value among each of the first results corresponding to the same amplification factor), thereby improving the accuracy of the second result.

[0141] See also Figure 3 As shown, in one embodiment, a brick content analysis device based on a microscope image of brick-mixed powder is provided, the device comprising:

[0142] The data acquisition module 801 is used to acquire a target microscope image corresponding to each shooting dimension for the target brick-concrete powder, wherein the shooting dimension includes: magnification and shooting area;

[0143] A background processing module 802 is used to perform background image area processing on the target microscope image to obtain an image to be analyzed;

[0144] A color segmentation module 803 is used to perform color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0145] The brick content analysis module 804 is used to perform brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0146] This embodiment determines the brick content analysis result based on the target microscope image of the target brick-concrete powder. There is no need to separate bricks from other powders, and no large equipment and complex technology are required. The operation process is simplified and the speed of detecting the brick content in the brick-concrete aggregate is improved. The prior art is all for brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, thus realizing non-destructive testing. The shooting dimensions include magnification and shooting area, thereby realizing brick content analysis of images from at least one perspective, further improving the accuracy of brick content analysis.

[0147] In one embodiment, the step of acquiring the target microscope image corresponding to each shooting dimension for the target brick-concrete powder in the data acquisition module 801 includes:

[0148] Obtain a test microscope image corresponding to the sampled brick-concrete powder;

[0149] According to the test microscope image, judging whether the spacing of the brick-concrete powder meets the unqualified spacing condition, or judging whether the brick-concrete powder is stacked;

[0150] If any one of them is yes, then based on the sampled brick-concrete powder after the distribution is adjusted, jump to the step of obtaining the test microscope image corresponding to the sampled brick-concrete powder and continue to execute;

[0151] If both are negative, the sampled brick-concrete powder is used as the target brick-concrete powder;

[0152] For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the target microscope image is a microscope image obtained by shooting the target brick-concrete powder based on the target configuration and the shooting dimension, and the target configuration adopts a target light source and a target microscope setting, the target light source adopts natural light or white light, and the target microscope is set to not add a filter.

[0153] In one embodiment, the step of performing color segmentation of brick and concrete on the image to be analyzed to obtain color segmentation data in the color segmentation module 803 includes:

[0154] Based on a preset color space, performing color distribution analysis on the image to be analyzed to obtain color distribution data;

[0155] According to the preset replacement color data and the threshold range data corresponding to the color space type corresponding to the preset color space, the color distribution data is segmented into brick and concrete colors to obtain initial segmentation data;

[0156] The color segmentation data is determined according to the initial segmentation data.

[0157] In one embodiment, the step of determining the color segmentation data according to the initial segmentation data in the color segmentation module 803 includes:

[0158] Inputting the image to be analyzed into a pre-trained brick segmentation model to perform brick powder segmentation to obtain a brick powder mask;

[0159] Performing segmentation difference data identification on the brick powder mask and the initial segmentation data;

[0160] The color segmentation data is determined according to the image to be analyzed, the initial segmentation data and the segmentation difference data.

[0161] In one embodiment, the preset color space adopts the HSL color space, and the preset replacement color data adopts the color data corresponding to black;

[0162] The threshold range data corresponding to the color space type corresponding to the HSL color space includes: H[0,85], S[32,255], L[68,255].

[0163] In one embodiment, the step of performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result in the brick content analysis module 804 includes:

[0164] Performing brick content analysis on each of the color segmentation data to obtain a first result;

[0165] Calculate the average value of each of the first results corresponding to the same magnification factor to obtain a second result;

[0166] The weighted sum of each of the second results corresponding to the target brick-mixed powder is performed to obtain the brick content analysis result.

[0167] In one embodiment, the step of calculating the average value of each of the first results corresponding to the same magnification to obtain the second result in the brick content analysis module 804 includes:

[0168] Deleting the maximum and minimum values ​​of the first results corresponding to the same magnification factor;

[0169] The second result is obtained by calculating the average value of each of the first results corresponding to the same magnification factor after the deletion process.

[0170] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of a service-side method for analyzing the content of bricks based on a microscope image of brick-mixed powder.

[0171] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of the client side of a brick content analysis method based on a microscope image of brick-mixed powder.

[0172] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0173] For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the shooting dimension includes: magnification and shooting area;

[0174] Performing background image region processing on the target microscope image to obtain an image to be analyzed;

[0175] Performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0176] Brick content analysis is performed according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0177] This embodiment determines the brick content analysis result based on the target microscope image of the target brick-concrete powder. There is no need to separate bricks from other powders, and no large equipment and complex technology are required. The operation process is simplified and the speed of detecting the brick content in the brick-concrete aggregate is improved. The prior art is all for brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, thus realizing non-destructive testing. The shooting dimensions include magnification and shooting area, thereby realizing brick content analysis of images from at least one perspective, further improving the accuracy of brick content analysis.

[0178] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0179] For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the shooting dimension includes: magnification and shooting area;

[0180] Performing background image region processing on the target microscope image to obtain an image to be analyzed;

[0181] Performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data;

[0182] Brick content analysis is performed according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result.

[0183] This embodiment determines the brick content analysis result based on the target microscope image of the target brick-concrete powder. There is no need to separate bricks from other powders, and no large equipment and complex technology are required. The operation process is simplified and the speed of detecting the brick content in the brick-concrete aggregate is improved. The prior art is all for brick content analysis of the particles of the brick-concrete aggregate, while the present application realizes brick content analysis for the brick-concrete powder, and the whole process will not cause any damage to the brick-concrete powder, thus realizing non-destructive testing. The shooting dimensions include magnification and shooting area, thereby realizing brick content analysis of images from at least one perspective, further improving the accuracy of brick content analysis.

[0184] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0185] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0186] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0187] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A brick content analysis method based on a microscope image of brick-mixed powder, the method comprising: For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the shooting dimension includes: magnification and shooting area; Performing background image region processing on the target microscope image to obtain an image to be analyzed; Performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; Perform brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result; The step of obtaining a target microscope image corresponding to each shooting dimension for the target brick-concrete powder comprises: Obtain a test microscope image corresponding to the sampled brick-concrete powder; According to the test microscope image, judging whether the spacing of the brick-concrete powder meets the unqualified spacing condition, or judging whether the brick-concrete powder is stacked; If any one of them is yes, then based on the sampled brick-concrete powder after the distribution is adjusted, jump to the step of obtaining the test microscope image corresponding to the sampled brick-concrete powder and continue to execute; If both are negative, the sampled brick-concrete powder is used as the target brick-concrete powder; For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the target microscope image is a microscope image obtained by shooting the target brick-concrete powder based on a target configuration and the shooting dimension, the target configuration is to use a target light source and a target microscope setting, the target light source is natural light or white light, and the target microscope is set to not add a filter; The step of performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data comprises: Based on a preset color space, performing color distribution analysis on the image to be analyzed to obtain color distribution data; According to the preset replacement color data and the threshold range data corresponding to the color space type corresponding to the preset color space, the color distribution data is segmented into brick and concrete colors to obtain initial segmentation data; Determining the color segmentation data according to the initial segmentation data; The step of determining the color segmentation data according to the initial segmentation data comprises: Inputting the image to be analyzed into a pre-trained brick segmentation model to perform brick powder segmentation to obtain a brick powder mask; Performing segmentation difference data identification on the brick powder mask and the initial segmentation data; Determining the color segmentation data according to the image to be analyzed, the initial segmentation data and the segmentation difference data; The preset color space adopts the HSL color space, and the preset replacement color data adopts the color data corresponding to black; The threshold range data corresponding to the color space type corresponding to the HSL color space includes: H[0,85], S[32,255], L[68,255]; The step of performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result comprises: Performing brick content analysis on each of the color segmentation data to obtain a first result; Calculate the average value of each of the first results corresponding to the same magnification factor to obtain a second result; Performing weighted summation on each of the second results corresponding to the target brick-mixed powder to obtain the brick content analysis result; The step of calculating the average value of each of the first results corresponding to the same magnification factor to obtain the second result comprises: Deleting the maximum and minimum values ​​of the first results corresponding to the same magnification factor; The second result is obtained by calculating the average value of each of the first results corresponding to the same magnification factor after the deletion process.

2. A brick content analysis device based on a microscope image of brick-mixed powder, characterized in that: The device comprises: A data acquisition module is used to acquire a target microscope image corresponding to each shooting dimension for a target brick-concrete powder, wherein the shooting dimension includes: a magnification and a shooting area; A background processing module, used for performing background image area processing on the target microscope image to obtain an image to be analyzed; A color segmentation module, used for performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data; A brick content analysis module, used to perform brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder, to obtain a brick content analysis result; The step of obtaining a target microscope image corresponding to each shooting dimension for the target brick-concrete powder comprises: Obtain a test microscope image corresponding to the sampled brick-concrete powder; According to the test microscope image, judging whether the spacing of the brick-concrete powder meets the unqualified spacing condition, or judging whether the brick-concrete powder is stacked; If any one of them is yes, then based on the sampled brick-concrete powder after the distribution is adjusted, jump to the step of obtaining the test microscope image corresponding to the sampled brick-concrete powder and continue to execute; If both are negative, the sampled brick-concrete powder is used as the target brick-concrete powder; For the target brick-concrete powder, a target microscope image corresponding to each shooting dimension is obtained, wherein the target microscope image is a microscope image obtained by shooting the target brick-concrete powder based on a target configuration and the shooting dimension, the target configuration is to use a target light source and a target microscope setting, the target light source is natural light or white light, and the target microscope is set to not add a filter; The step of performing color segmentation of bricks and concrete on the image to be analyzed to obtain color segmentation data comprises: Based on a preset color space, performing color distribution analysis on the image to be analyzed to obtain color distribution data; According to the preset replacement color data and the threshold range data corresponding to the color space type corresponding to the preset color space, the color distribution data is segmented into brick and concrete colors to obtain initial segmentation data; Determining the color segmentation data according to the initial segmentation data; The step of determining the color segmentation data according to the initial segmentation data comprises: Inputting the image to be analyzed into a pre-trained brick segmentation model to perform brick powder segmentation to obtain a brick powder mask; Performing segmentation difference data identification on the brick powder mask and the initial segmentation data; Determining the color segmentation data according to the image to be analyzed, the initial segmentation data and the segmentation difference data; The preset color space adopts the HSL color space, and the preset replacement color data adopts the color data corresponding to black; The threshold range data corresponding to the color space type corresponding to the HSL color space includes: H[0,85], S[32,255], L[68,255]; The step of performing brick content analysis according to each of the color segmentation data corresponding to the target brick-mixed powder to obtain a brick content analysis result comprises: Performing brick content analysis on each of the color segmentation data to obtain a first result; Calculate the average value of each of the first results corresponding to the same magnification factor to obtain a second result; Performing weighted summation on each of the second results corresponding to the target brick-mixed powder to obtain the brick content analysis result; The step of calculating the average value of each of the first results corresponding to the same magnification factor to obtain the second result comprises: Deleting the maximum and minimum values ​​of the first results corresponding to the same magnification factor; The second result is obtained by calculating the average value of each of the first results corresponding to the same magnification factor after the deletion process.

3. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the brick content analysis method based on the microscope image of brick-mixed powder as claimed in claim 1 are implemented.

4. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the brick content analysis method based on the microscope image of brick-mixed powder as claimed in claim 1 are implemented.

Images