Municipal construction dust fall system and equipment based on image processing

Abstract

The invention relates to the technical field of image processing, in particular to a municipal construction dust fall system and equipment based on image processing. The method comprises the following steps: acquiring a time sequence grayscale image of a construction site, analyzing the grayscale change and motion condition of pixel points, and accurately dividing a particulate matter area in the grayscale image; according to the method, the difference of motion performance of dust and water mist particles in an image is considered, the conditions of gray level distribution, number distribution, motion modes and the like of pixel points are integrated, and the dust falling characteristic value of a particle area is analyzed to reflect the dust falling effect in the current image. And on the basis, the system adaptively adjusts the initial water mist concentration based on the dust falling characteristic value to obtain the final water mist concentration, and dust falling is carried out on the construction site according to the final water mist concentration. According to the comprehensive evaluation system, the image of the construction site is analyzed, the dust raising condition of the construction site can be comprehensively reflected, a scientific basis is provided for formulating a targeted dust falling strategy, and the dust falling effect is remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly relates to a dust reduction system and equipment for municipal construction based on image processing. Background Art

[0002] During the process of municipal construction, a large amount of dust is often generated at the construction site, which not only affects the air quality of the construction environment, but may also have an adverse impact on the living environment and health of the surrounding residents. Therefore, dust reduction measures in municipal construction are very important. Usually, a high-pressure spray system is used to generate fine water mist. When the water mist contacts the dust particles in the air, the fine water mist particles will adhere to the dust, making the dust particles heavier and thus reducing the ability of the dust to suspend in the air, thereby reducing the dust concentration in the air.

[0003] During the dust reduction process, the water mist concentration is an important indicator, which is closely related to the dust reduction efficiency. In order to improve the dust reduction effect and efficiency, the prior art usually uses gray-scale information to identify the dust in the current construction scene, so as to determine the final required water mist concentration; however, since the construction site usually has a complex background, these backgrounds may be similar to the gray scale and texture of the dust, resulting in an increase in the difficulty of dust identification, and the water mist generated by the fog cannon machine may cause the dust to be dispersed. These problems will increase the difficulty of identifying the dust only using gray-scale information, and thus affect the subsequent dust reduction efficiency and effect. Summary of the Invention

[0004] In order to solve the technical problems that the construction site usually has a complex background, these backgrounds may be similar to the gray scale and texture of the dust, resulting in an increase in the difficulty of dust identification, and the water mist generated by the fog cannon machine may cause the dust to be dispersed. These problems will increase the difficulty of identifying the dust only using gray-scale information, and thus affect the subsequent dust reduction efficiency and effect, the purpose of the present invention is to provide a dust reduction system and equipment for municipal construction based on image processing, and the specific technical solutions adopted are as follows: A dust reduction system for municipal construction based on image processing, comprising: A data acquisition module, configured to acquire two adjacent gray-scale images in time series of the construction site, and use the previous gray-scale image in time series as the target image; A particulate matter region division module, configured to determine the atomization coefficient of each pixel point according to the gray-scale fluctuation characteristics of the pixel points within a local range in the target image; in two adjacent gray-scale images, analyze the movement situation and gray-scale change situation of the pixel points, and combine the atomization coefficient of each pixel point to divide the target image into regions to obtain particulate matter regions; The dust fall situation analysis module is used to obtain the dust fall characteristic value of the particulate matter area in the particulate matter area according to the number distribution of pixel points, the atomization coefficient of pixel points, and analyze the motion mode of pixel points; The water mist concentration adjustment and dust fall module is used to adjust the initial water mist concentration according to the dust fall characteristic value of the particulate matter area to obtain the final water mist concentration; and perform dust fall on the construction site based on the final water mist concentration.

[0005] Further, the method for obtaining the atomization coefficient includes: In the target image, based on the gray value of pixel points, select the maximum value points; With each pixel point as the center, construct a preset second neighborhood; In the preset second neighborhood corresponding to each pixel point, randomly select one maximum value point as the measurement point, and in the remaining maximum value points, select the maximum value point with the smallest Euclidean distance from the measurement point as the comparison point, calculate the average gray value between the measurement point and the comparison point as the first gray average value, calculate the average gray value of the pixel points whose gray values exist between the measurement point and the comparison point as the second gray average value, and use the Euclidean distance between the measurement point and the comparison point as the distance factor; Take the absolute value of the difference between the first gray average value and the second gray average value between the measurement point and the comparison point as the gray fluctuation factor, and use the normalized value of the ratio of the gray fluctuation factor to the distance factor as the atomization factor corresponding to the measurement point; In the preset second neighborhood corresponding to each pixel point, use the normalized sum value of the atomization factors corresponding to all maximum value points as the atomization coefficient of each pixel point.

[0006] Further, the method for obtaining the maximum value points includes: In the target image, determine the preset first neighborhood of each pixel point, and in the preset first neighborhood corresponding to each pixel point, take the pixel point with the largest gray value as the maximum value point; Among them, the preset first neighborhood is smaller than the preset second neighborhood.

[0007] Further, the method for obtaining the particulate matter area includes: Take two gray images as the input of the optical flow method, so as to output the optical flow vector corresponding to the pixel points in the target image; In the target image, determine the particle factor of each pixel point according to the atomization coefficient, optical flow vector corresponding to each pixel point, and the gray chaos situation of pixel points in the corresponding preset second neighborhood; Segment the target image based on the Otsu threshold segmentation method to obtain two regions, which are divided into the foreground region and the background region; In each region, calculate the mean of the particle factors of all pixel points as the particulate matter index corresponding to each region; Take the region with the largest particulate matter index as the particulate matter region.

[0008] Furthermore, the method for obtaining the particle factor includes: Within the preset second neighborhood corresponding to each pixel point, take the mean of the gray gradients of all pixel points as the gray change factor of each pixel point; Calculate the magnitude of the optical flow vector corresponding to each pixel point as the motion intensity corresponding to each pixel point; For any pixel point, take the product of the atomization coefficient of the pixel point and the gray change factor as the gray change coefficient, and normalize the absolute value of the difference between the ratio of the gray change coefficient of the pixel point and the motion intensity and a preset first constant to obtain the particle factor of the pixel point.

[0009] Furthermore, the method for obtaining the dust reduction eigenvalue includes: Divide the particulate matter region based on the superpixel segmentation method to obtain a plurality of superpixel blocks; Based on the number distribution, motion condition, and atomization coefficient of the pixel points in all superpixel blocks in the particulate matter region, determine the water mist factor of each superpixel block and the water mist combination index of the particulate matter region; In the particulate matter region, analyze the motion diffusion condition of the pixel points, and combine the water mist factors of all superpixel blocks in the particulate matter region to determine the dust diffusion coefficient of the particulate matter region; Take the normalized value of the ratio of the water mist combination index to the dust diffusion coefficient as the dust reduction eigenvalue of the particulate matter region.

[0010] Furthermore, the step of determining the water mist factor of each superpixel block and the water mist combination index of the particulate matter region based on the number distribution, motion condition, and atomization coefficient of the pixel points in all superpixel blocks in the particulate matter region includes: In each superpixel block, take the mean of the atomization coefficients of all pixel points as the atomization mean; Preset the number of iterations. At each iteration, randomly select a certain number of pixel points as water mist pixel points in each superpixel block; Calculate the ratio of the number of water mist pixel points in each superpixel block to the number of all pixel points as the water mist density, and take the variance of the magnitudes of the optical flow vectors of all water mist pixel points in each superpixel block as the chaos factor of each superpixel block; The absolute value of the difference between the ratio of the atomization mean value and the water mist density corresponding to each superpixel block and a preset second constant is used as a true factor, and the value obtained by performing negative correlation mapping and normalization on the ratio of the true factor to the chaos factor is used as the water mist loss factor corresponding to each superpixel block in each iteration. The sum value of the water mist loss factors corresponding to all superpixel blocks is used as the water mist loss value corresponding to the particulate matter region in each iteration. Among all the iteration times, at the minimum water mist loss value, the water mist density corresponding to each superpixel block is used as the water mist factor of each superpixel block; the value obtained by normalizing the difference between the maximum water mist density and the minimum water mist density among all superpixel blocks is used as the water mist combination index of the particulate matter region.

[0011] Further, the method for obtaining the dust diffusion coefficient includes: In each superpixel block, calculate the mean value of the optical flow vectors of all pixel points as the comprehensive vector. Decompose the comprehensive vector, remove the vertically downward component and then synthesize it to obtain the diffusion vector. The ratio of the magnitude of the diffusion vector corresponding to each superpixel block to the water mist factor is used as the diffusion factor corresponding to each superpixel block. The value obtained by normalizing the mean value of the diffusion factors of all superpixel blocks is used as the dust diffusion coefficient of the particulate matter region.

[0012] Further, the method for obtaining the final water mist concentration includes: The difference between a preset third constant and the dust fall eigenvalue is used as the adjustment coefficient. The product of the adjustment coefficient and the initial water mist concentration is used as the final water mist concentration.

[0013] A municipal construction dust reduction device based on image processing includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory. When at least one instruction, at least one program, the code set or the instruction set is loaded and executed by the processor, the steps of the municipal construction dust reduction system based on image processing are implemented.

[0014] The present invention has the following beneficial effects: First, obtain the sequential grayscale images of the construction site to provide immediate and accurate environmental data. Since dust usually appears in the form of smoke, there will be an alternating phenomenon of light and dark in the images. Therefore, in the particulate matter area division module, the atomization coefficient of each pixel point is determined by analyzing the grayscale changes of the pixel points in detail, which is used to reflect the grayscale changes around the pixel point and prepare for subsequent judgment of whether it is a dust particle pixel point. Dust particles of different sizes will have different movement patterns at the construction site, so the atomization coefficient is combined with the movement and grayscale distribution of the pixel points to more accurately divide the particulate matter area in the image. There are water mist particles generated by the fog cannon machine in the obtained particulate matter part. Therefore, in order to more accurately judge the dust reduction situation at the current construction site, it is necessary to analyze the diffusion and combination of the particulate matter and the water mist. Given that the water mist particles produced by the industrial fog cannon machine are small, evenly distributed, and have a relatively consistent movement pattern, in the particulate matter area, the number distribution, movement pattern, and atomization coefficient of the pixel points are analyzed to obtain the dust reduction characteristic value of the particulate matter area, which is used to reflect the dust reduction effect in the current image. Finally, in the water mist concentration adjustment and dust reduction module, the initial water mist concentration is adaptively adjusted based on the dust reduction characteristic value to obtain the final water mist concentration, and the construction site is dusted according to the final water mist concentration. This comprehensive evaluation system can more comprehensively reflect the dust and dust situation at the construction site, provide a scientific basis for formulating targeted dust reduction strategies, and significantly enhance the dust reduction effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 System block diagram of a municipal construction dust reduction system based on image processing provided by an embodiment of the present invention; Figure 2 Method flowchart of a method for obtaining a particulate matter area provided by an embodiment of the present invention; Figure 3 Method flowchart of a method for obtaining a dust reduction characteristic value provided by an embodiment of the present invention; Figure 4 Structural schematic diagram of a municipal construction dust reduction device based on image processing provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details a dust reduction system and equipment for municipal construction based on image processing according to the present invention, including its specific implementation manner, structure, features and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solution of a dust reduction system and equipment for municipal construction based on image processing provided by the present invention with reference to the accompanying drawings.

[0020] Please refer to Figure 1 , which shows a system block diagram of a dust reduction system for municipal construction based on image processing provided by an embodiment of the present invention. The system includes a data acquisition module 101, a particulate matter area division module 102, a dust reduction situation analysis module 103, and a water mist concentration adjustment and dust reduction module 104.

[0021] The data acquisition module 101 is used to acquire two adjacent grayscale images in time sequence at the construction site, and use the previous grayscale image in time sequence as the target image.

[0022] In order to perform dust reduction treatment on the municipal construction site, an industrial fog cannon is used to spray water mist; the industrial fog cannon consists of a high-pressure pump, a nozzle, and a control unit, etc. The high-pressure pump extracts water from the water storage tank and pressurizes it, and the high-pressure water is released through the nozzle to form fine water mist, and the type and design of the nozzle determine the particle size and spraying range of the water mist; the control unit can adjust the water mist concentration, etc., and the control unit can be a microprocessor or a microcontroller.

[0023] In order to efficiently perform dust reduction treatment on the dust in the construction site, it is necessary to analyze the dust density in the air. Therefore, in this embodiment of the present invention, a high-resolution industrial camera is installed at the bottom of the industrial fog cannon to collect video images of the construction site, and a professional video processing software is used to extract video images from the recorded video images at a set time interval. Since color space is not required for dust analysis, the collected video images of the construction site are all grayscale processed to obtain grayscale images. Then, in the video image sequence, two adjacent grayscale images in time sequence are selected, for example, the nth frame and the n + 1th frame are selected, and in the two adjacent grayscale images, the previous grayscale image (the nth frame) in time sequence is used as the target image.

[0024] It should be noted that the time interval for extracting video images can be set to 1 second, and the specific time interval can be adjusted according to the implementation scenario, which is not limited herein; it should be noted that the method for obtaining grayscale images can adopt methods such as average grayscale conversion, maximum value method, or weighted grayscale conversion, etc., and these are all well-known technical means to those skilled in the art, which are not limited and elaborated herein.

[0025] The particulate matter region division module 102 is used to determine the atomization coefficient of each pixel point according to the grayscale fluctuation characteristics of pixel points within a local range in the target image; in two adjacent grayscale images, analyze the movement situation and grayscale change situation of pixel points, and combine the atomization coefficient of each pixel point to divide the target image into regions to obtain the particulate matter region.

[0026] Since the dust in the construction site will float and move in the air, the dust part in the image will appear smoky and may present a grayscale fluctuation characteristic of alternating light and dark. Therefore, in the target image, based on the grayscale fluctuation situation of pixel points within a local range, the atomization coefficient of each pixel point can be obtained to reflect the grayscale change situation around the pixel point. Further, since the movement patterns of dust with different particle sizes will be different in the construction site. For example, small-particle dust is not easy to settle when lifted due to its small mass, so the movement change situation is weak, and because of its small volume, the grayscale change around it will be more obvious; on the contrary, large-particle dust is more likely to settle after being lifted due to its large mass, so the movement change situation is more obvious, but because of its large volume, the grayscale change around it will be weak. Therefore, based on this feature, on the basis of the atomization coefficient calculated above, the present invention analyzes the movement situation and grayscale change situation of pixel points between two adjacent grayscale images, so as to more accurately quantify the possibility that each pixel point in the target image is particulate matter dust, and then divide the target image into regions, and a more accurate particulate matter region can be obtained, providing support for subsequent analysis processes.

[0027] First, in the target image, based on the grayscale fluctuation characteristics of pixel points within a local range, determine the atomization coefficient of each pixel point.

[0028] Preferably, in an embodiment of the present invention, the method for obtaining the atomization coefficient includes: The maximum value points are usually the peaks of local grayscale changes, and these points may correspond to features such as the edges and corners of particulate matter in the target image. Therefore, in the target image, based on the grayscale values of pixel points, screen the maximum value points: determine the preset first neighborhood of each pixel point, and within the preset first neighborhood corresponding to each pixel point, take the pixel point with the largest grayscale value as the maximum value point.

[0029] So far, all the maximum points in the target image can be screened out, that is, the pixel points where the gray level changes abruptly.

[0030] Then, in order to analyze the gray level changes around each pixel point more comprehensively, a local range larger than the preset first neighborhood is constructed, that is, with each pixel point as the center, a preset second neighborhood is constructed.

[0031] In the preset second neighborhood corresponding to each pixel point, any one of the maximum points is selected as the point to be measured, and the maximum point with the smallest Euclidean distance from the point to be measured among the remaining maximum points is used as the comparison point.

[0032] Calculate the average gray level value between the point to be measured and the comparison point as the first gray level average value, which reflects the average gray level between these two points; calculate the average gray level value of the pixel points whose gray level values exist between the point to be measured and the comparison point as the second gray level average value, and the second gray level average value reflects the average gray level of the pixel points whose gray level values exist between these two points; take the Euclidean distance between the point to be measured and the comparison point as the distance factor.

[0033] Take the absolute value of the difference between the first gray level average value and the second gray level average value between the point to be measured and the comparison point as the gray level fluctuation factor. The larger the gray level fluctuation factor, the more obvious the gray level fluctuation of the pixel point, and the smaller the distance factor, the faster the gray level value of the pixel point can be regarded as changing, which also indicates that the gray level change is more obvious. Therefore, the value obtained by normalizing the ratio of the gray level fluctuation factor to the distance factor is used as the fogging factor corresponding to the point to be measured. At this time, the larger the fogging factor, the more significant the gray level change around the pixel point. Among them, normalization is a technical means well-known to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0034] So far, the fogging factors of all the maximum points in the preset second neighborhood corresponding to each pixel point can be obtained.

[0035] Finally, in the preset second neighborhood corresponding to each pixel point, the value obtained by normalizing the sum of the fogging factors corresponding to all the maximum points is used as the fogging coefficient of each pixel point. The larger the fogging coefficient, the more obvious the gray level change characteristics in the local range where the pixel point is located. Among them, normalization is a technical means well-known to those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0036] It should be noted that in this embodiment of the present invention, when calculating the Euclidean distance, a two-dimensional coordinate system can be constructed in the target image to obtain the position coordinates of each pixel point for calculating the Euclidean distance; the preset first neighborhood is 3×3, and the preset second neighborhood is 5×5.

[0037] After obtaining the atomization coefficient, since particles of different sizes have different motion patterns, in order to obtain the particle region in the target image, further, in two adjacent grayscale images, the motion of pixel points and the change in grayscale are analyzed, and combined with the atomization coefficient of each pixel point, so as to divide the region of the target image to obtain an accurate particle region.

[0038] Preferably, in an embodiment of the present invention, the method for obtaining the particle region includes: Please refer to Figure 2 , which shows a flowchart of the method for obtaining the particle region in an embodiment of the present invention. The method includes the following steps: Step S201: Use two grayscale images as the input of the optical flow method, so as to output the optical flow vectors corresponding to the pixel points in the target image.

[0039] The optical flow method is a technique for detecting and analyzing the motion of objects in a video or image sequence. It can estimate the motion of objects based on the change in the grayscale values of pixel points in the image, and the obtained optical flow vectors can reflect the motion direction and motion distance of the objects in the image between adjacent frames. This is important for subsequent analysis of the motion pattern of particles to determine the particle region. Therefore, in this embodiment of the present invention, two grayscale images are used as the input of the optical flow method, so as to output the optical flow vectors corresponding to the pixel points in the target image.

[0040] It should be noted that the optical flow method is a well-known technology, and the specific process will not be elaborated here.

[0041] Step S202: In the target image, determine the particle factor of each pixel point according to the atomization coefficient, optical flow vector corresponding to each pixel point, and the grayscale chaos of the pixel points in the corresponding preset second neighborhood.

[0042] Given that the volume of large particle dust is relatively large, the degree of grayscale chaos of pixel points in a local range may be relatively small; on the contrary, the volume of small particle dust is relatively small, so the degree of grayscale chaos of pixel points in a local range may be relatively large.

[0043] Therefore, in the preset second neighborhood corresponding to each pixel point, the mean value of the grayscale gradient of all pixels is used as the grayscale change factor of each pixel point. The larger the grayscale change factor, the more drastic the grayscale change in the preset second neighborhood of the pixel point, and the more likely it is a pixel point of small dust particles. The smaller the grayscale change factor, the smaller the grayscale change in the preset second neighborhood of the pixel point, and the more likely it is a pixel point of large dust particles. Large dust particles are more likely to settle faster at the construction site due to their large mass, so the movement will be more obvious; on the contrary, small dust particles are more likely to be suspended in the air at the construction site due to their small mass, so the movement characteristics are less obvious.

[0044] Therefore, the modulus of the optical flow vector corresponding to each pixel is calculated as the motion intensity corresponding to each pixel. At this time, the greater the motion intensity, the more obvious the motion feature, and the more likely it is to represent large dust particles. The smaller the motion intensity, the less obvious the motion feature, and the more likely it is to represent small dust particles.

[0045] Finally, for any pixel, the product of the fog coefficient of the pixel and the grayscale change factor is used as the grayscale change coefficient. The larger the grayscale change coefficient, the more obvious the grayscale change feature in the local range of the pixel, and the higher the possibility of representing small dust particles; the smaller the grayscale change coefficient, the weaker the grayscale change feature in the local range of the pixel, and the higher the possibility of representing large dust particles; based on the above analysis, it can be seen that the greater the motion intensity, the more likely it is large dust particles, and the smaller the motion intensity, the more likely it is small dust particles, so the ratio of the grayscale change coefficient of the pixel to the motion intensity is calculated. At this time, the greater the difference between the denominator and the numerator in the fraction, the more likely it is that the pixel is a dust pixel, so the absolute value of the difference between the ratio and the preset first constant is calculated for normalization to obtain the particle factor of the pixel. At this time, the larger the absolute value of the difference, the more the pixel can represent the particulate matter part in the target image, so the larger the particle factor, the more likely the pixel is a particulate matter pixel. Normalization is a technical means well known to those skilled in the art, and the normalization function may be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0046] It should be noted that the preset first constant is set to 1 here for the purpose of facilitating comparison and calculation; the grayscale gradient acquisition method can be based on the Canny operator, and the specific process is not described here.

[0047] Step S203: performing image segmentation on the target image, and determining the particle area based on the particle factors of the pixels in the target image.

[0048] Otsu threshold segmentation is a method for automatically determining the optimal segmentation threshold, which can divide an image into two parts based on the grayscale histogram of the image. First, the target image is segmented based on the Otsu threshold segmentation method to obtain two regions, which are divided into a foreground region and a background region.

[0049] Then, in each region, calculate the mean value of the particle factors of all pixel points as the particulate matter index corresponding to each region. At this time, the larger the particulate matter index, the more concentrated the pixel points representing particulate matter in the region, and the higher the possibility that the pixel points in the region are particulate matter pixel points. Therefore, finally, in the two regions, the region with the largest particulate matter index is taken as the particulate matter region.

[0050] It should be noted that the Otsu threshold segmentation method is a well-known technology, and the specific process will not be elaborated here.

[0051] The dust fall situation analysis module 103 is used to obtain the dust fall characteristic value of the particulate matter region in the particulate matter region according to the number distribution of pixel points, the atomization coefficient of pixel points, and analyze the motion mode of pixel points.

[0052] For the particulate matter region obtained by the above operations, it is necessary to analyze the dust fall situation according to the particulate matter part therein. However, since the industrial fog cannon is operating for dust removal during the image acquisition process, there may be water mist particles in the obtained particulate matter region. Therefore, there will be deviations in directly analyzing the dust fall situation of the particulate matter part. In this embodiment of the present invention, in order to analyze and judge the dust fall situation of dust in the current image, it is necessary to analyze the diffusion situation of particulate matter and integrate the situation of water mist combination. Since the water mist ejected by the industrial fog cannon is to contact and adhere to the dust particles in the air, resulting in an increase in the mass of the dust particles to achieve the purpose of dust fall, the particles of the water mist ejected by the industrial fog cannon are small and have good suspension in the air. And because the water mist ejected by the industrial fog cannon is relatively uniform, the distribution of water mist in the air is relatively uniform and its motion mode is relatively consistent. However, the raised dust is disordered in distribution and motion mode in the air due to different particle sizes and dust-raising reasons. Therefore, in the particulate matter region, according to the number distribution situation, motion situation of pixel points, and the atomization coefficient of pixel points, the dust fall characteristic value of the particulate matter region can be obtained.

[0053] Preferably, in an embodiment of the present invention, the method for obtaining the dust fall characteristic value includes: Please refer to Figure 3 , which shows the method flow chart of the method for obtaining the dust fall characteristic value in an embodiment of the present invention. The method includes the following steps: Step S301: Divide the particulate matter region based on the superpixel segmentation method to obtain a plurality of superpixel blocks.

[0054] The superpixel segmentation method can divide pixel points with similar texture features or attributes into a superpixel block, reducing complexity while retaining key features, thus simplifying the subsequent analysis process. Therefore, based on the superpixel segmentation method, the particulate matter region is divided to obtain multiple superpixel blocks.

[0055] It should be noted that in the embodiment of the present invention, the number of superpixel blocks is set to 32, and the specific number can be adjusted according to the implementation scenario and is not limited herein; the superpixel segmentation method is a well-known technology, and the specific process will not be elaborated herein.

[0056] Step S302: Based on the number distribution, movement situation, and atomization coefficient of pixel points in all superpixel blocks in the particulate matter region, determine the water mist factor of each superpixel block and the water mist combination index of the particulate matter region.

[0057] In each superpixel block, the mean value of the atomization coefficients of all pixel points is used as the atomization mean value, which reflects the average gray change situation of all pixel points in the superpixel block.

[0058] In order to more accurately evaluate the water mist combination situation, in this embodiment of the present invention, a preset number of iterations is set. In each iteration, in each superpixel block, a certain number of pixel points are randomly selected as water mist pixel points, which can simulate the distribution of water mist in different situations, so as to screen out water mist pixel points that can better represent the real water mist and improve the accuracy of subsequent dust reduction situation analysis.

[0059] Calculate the ratio of the number of all water mist pixel points to the number of all pixel points in each superpixel block as the water mist density.

[0060] Based on the foregoing analysis, it can be seen that the water mist sprayed by the industrial fog cannon is relatively uniform, resulting in a relatively uniform distribution of water mist in the air and a relatively consistent movement pattern. Therefore, in order to evaluate whether the selection of water mist pixel points in each superpixel point is appropriate, the variance of the modulus length of the optical flow vector of the water mist pixel points in each superpixel block is used as the chaos factor of each superpixel block. At this time, the smaller the chaos factor, the more appropriate the selection of water mist pixel points and the more representative of the real water mist.

[0061] Under normal circumstances, the larger the atomization coefficient, that is, the greater the gray-scale change, the better the combination with water mist, and the real water mist density will decrease; conversely, when the atomization coefficient is smaller, it indicates that the combination with water mist is worse, and the real water mist density will increase. Therefore, calculate the ratio of the atomization mean value corresponding to each superpixel block to the water mist density. At this time, the greater the difference between the denominator and the numerator in the fraction, the more the selected water mist pixel points can represent the real water mist. Therefore, continue to calculate the absolute value of the difference between this ratio and the preset second constant as the real factor. The larger the real factor, the more the water mist pixel points can represent the real water mist.

[0062] Then, the value obtained by performing negative correlation mapping and normalization on the ratio of the real factor to the chaos factor is used as the water mist loss factor corresponding to each superpixel block in each iteration. Based on the foregoing analysis, the smaller the chaos factor, the higher the correct degree of selection of water mist pixel points, and the larger the real factor, the higher the correct degree of selection of water mist pixel points. Therefore, the smaller the obtained water mist loss factor, it is considered that in this iteration, the water mist pixel points selected in the superpixel block can better represent the real water mist. The negative correlation mapping and normalization processing here can be carried out using the formula , where represents the exponential function with the natural constant e as the base, and x represents the independent variable.

[0063] Take the sum value of the water mist loss factors corresponding to all superpixel blocks as the water mist loss value corresponding to the particulate matter region in each iteration. Similarly, the smaller the water mist loss value, the higher the correct rate of the water mist pixel points selected in the particulate matter region in this iteration.

[0064] Finally, among all the iteration times, select the smallest water mist loss value. At this time, the more correct the selection of water mist pixel points, then on this basis, the actual water mist situation in the particulate matter region can be measured more accurately.

[0065] At the minimum water mist loss value, take the water mist density corresponding to each superpixel block as the water mist factor of each superpixel block, which is used to reflect the water mist distribution in each superpixel block; because when the water mist combination efficiency is better, the combination difference between different concentrations will be greater, so the value obtained by normalizing the difference between the maximum water mist density and the minimum water mist density in all superpixel blocks is used as the water mist combination index of the particulate matter region. This index reflects the uniformity or difference of the water mist distribution in the particulate matter region. When the difference is large, it indicates the uneven water mist distribution in the particulate matter region, indicating that the water mist combination efficiency is stronger.

[0066] It should be noted that the number of iterations is set to 20 times, and the specific value can be adjusted according to the implementation scenario and is not limited here; the preset second constant here is set to 1 for the purpose of facilitating comparison and calculation.

[0067] Step S303: In the particulate matter region, analyze the motion diffusion of pixel points, and combine the water mist factors of all superpixel blocks in the particulate matter region to determine the dust diffusion coefficient of the particulate matter region.

[0068] In each superpixel block, calculate the mean value of the optical flow vectors of all pixel points as the comprehensive vector, and the comprehensive vector can characterize the overall motion of the pixel points in each superpixel block.

[0069] Since the principle of dust fall is that water mist contacts and adheres to dust particles in the air, causing the dust mass to increase, thereby achieving the purpose of dust fall. Therefore, the comprehensive vector is decomposed, and after removing the vertically downward component and then synthesized to obtain the diffusion vector. At this time, the diffusion vector can characterize the diffusion of dust and weaken the influence of the dust fall process on its calculation.

[0070] Since the dust diffusion in the superpixel block with a smaller water mist factor is more serious, the ratio of the magnitude of the diffusion vector corresponding to each superpixel block to the water mist factor is used as the diffusion factor corresponding to each superpixel block. At this time, the larger the diffusion factor, the more serious the dust particle diffusion in the superpixel block.

[0071] Finally, the normalized value of the mean of the diffusion factors of all superpixel blocks is used as the dust diffusion coefficient of the particulate matter region. Similarly, the larger the diffusion coefficient, the more serious the dust particle diffusion in the particulate matter region. Normalization is a well-known technical means for those skilled in the art. The choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0072] Step S304: Combine the water mist combination index corresponding to the particulate matter region and the dust diffusion coefficient to obtain the dust fall characteristic value corresponding to the particulate matter region.

[0073] The dust fall characteristic value can be used to reflect the dust fall situation at the current construction site, which helps to adjust the water mist concentration in the subsequent process. The dust fall characteristic value can be quantified by the water mist combination index corresponding to the particulate matter region and the dust diffusion coefficient.

[0074] When the water mist combination index is larger, it indicates that the combination of water mist and dust in the particulate matter area is better, and then it can be regarded that the dust reduction effect is better. When the dust diffusion coefficient is smaller, it indicates that the diffusion of dust particles in the particulate matter area is weaker, and it can also be regarded that the dust reduction effect is better. Therefore, calculate the ratio of the water mist combination index to the dust diffusion coefficient, and use the value obtained by normalizing this ratio as the dust reduction characteristic value of the particulate matter area. At this time, the larger the dust reduction characteristic value, the better the corresponding dust reduction effect in the particulate matter area, that is, the better the dust reduction effect at the current construction site. Among them, normalization is a technical means well-known to those skilled in the art. The selection of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0075] The water mist concentration adjustment and dust reduction module 104 is used to adjust the initial water mist concentration according to the dust reduction characteristic value of the particulate matter area to obtain the final water mist concentration; and perform dust reduction on the construction site based on the final water mist concentration.

[0076] The dust reduction characteristic value of the current construction site calculated in module 103 can be used to reflect the dust reduction effect of the construction site. In this module, the initial water mist concentration can be adaptively adjusted according to the dust reduction characteristic value of the particulate matter area, so that the final water mist concentration better meets the actual dust reduction requirements in the current construction site and improves the dust reduction effect.

[0077] Preferably, in an embodiment of the present invention, the method for obtaining the final water mist concentration includes: When the dust reduction characteristic value is smaller, it indicates that the dust reduction effect at the current construction site is poor. Then it is necessary to increase the water mist concentration so that the water mist can better adhere to the dust particles to improve the dust reduction effect. Therefore, use the difference between the preset third constant and the dust reduction characteristic value as the adjustment coefficient. At this time, the larger the adjustment coefficient, the greater the degree to which the water mist concentration needs to be increased. Finally, use the product of the adjustment coefficient and the initial water mist concentration as the final water mist concentration.

[0078] After obtaining the final water mist concentration, the control unit can be used to adjust the water mist concentration of the industrial fog cannon to perform dust reduction on the construction site.

[0079] It should be noted that the preset third constant here is set to 2, aiming to ensure that the final water mist concentration is greater than the initial water mist concentration but not too large, so as to ensure the dust reduction effect.

[0080] In summary, first, the sequential grayscale images of the construction site are obtained to provide immediate and accurate environmental data. Since dust usually appears in the form of smoke, there will be an alternating phenomenon of light and dark in the image. Therefore, in the particulate matter area division module, the atomization coefficient of each pixel is determined by analyzing the grayscale change of the pixel in detail, which is used to reflect the grayscale change around the pixel and prepare for subsequent judgment of whether it is a dust particle pixel. Dust particles of different sizes will have different motion patterns at the construction site, so the atomization coefficient is combined with the motion and grayscale distribution of the pixel, so as to more accurately divide the particulate matter area in the image. There are water mist particles generated by the fog cannon machine in the particulate matter part obtained by the foregoing operation. Therefore, in order to more accurately judge the dust reduction situation at the construction site, it is necessary to analyze the diffusion situation of the particulate matter and the combination with the water mist. Given that the water mist particles ejected by the industrial fog cannon machine are small, evenly distributed, and have a relatively consistent motion pattern, in the particulate matter area, the number distribution, motion pattern, and atomization coefficient of the pixels are analyzed to obtain the dust reduction characteristic value of the particulate matter area, which is used to reflect the dust reduction effect in the current image. Finally, in the water mist concentration adjustment and dust reduction module, the initial water mist concentration is adaptively adjusted based on the dust reduction characteristic value to obtain the final water mist concentration, and the construction site is dust-reduced according to the final water mist concentration. This comprehensive evaluation system can more comprehensively reflect the dust and dust situation at the construction site, provide a scientific basis for formulating targeted dust reduction strategies, and significantly enhance the dust reduction effect.

[0081] An embodiment of the present invention also provides a municipal construction dust reduction device based on image processing. Please refer to Figure 4 , which shows a schematic structural diagram of a municipal construction dust reduction device based on image processing provided by an embodiment of the present invention, including a processor 400, a memory 401, a bus 402, and a communication interface 403. The processor 400, the communication interface 403, and the memory 401 are connected through the bus 402. Among them, the memory 401 may include a high-speed random access memory. The bus 402 may be an ISA bus, a PCI bus, an EISA bus, etc. The processor 400 may be an integrated circuit chip with signal processing capabilities. At least one instruction, at least one program, a code set, or an instruction set is stored in the memory 401. When at least one instruction, at least one program, a code set, or an instruction set is loaded and executed by the processor, the steps in a municipal construction dust reduction system based on image processing are implemented.

[0082] It should be noted that the above-mentioned order of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized respectively.

Claims

1. A dust reduction system for municipal construction based on image processing, characterized in that, The system includes: A data acquisition module, configured to acquire two adjacent grayscale images in time series at the construction site, and use the previous grayscale image in time series as the target image; A particulate matter region division module, configured to, in the target image, determine the atomization coefficient of each pixel according to the grayscale fluctuation characteristics of pixel points within a local range; in two adjacent grayscale images, analyze the movement and grayscale change of pixel points, and combine the atomization coefficient of each pixel point to divide the target image into regions to obtain the particulate matter region; A dust reduction situation analysis module, configured to, in the particulate matter region, obtain the dust reduction characteristic value of the particulate matter region according to the number distribution of pixel points and the atomization coefficient of pixel points, and analyze the movement pattern of pixel points; A water mist concentration adjustment and dust reduction module, configured to adjust the initial water mist concentration according to the dust reduction characteristic value of the particulate matter region to obtain the final water mist concentration; and perform dust reduction on the construction site based on the final water mist concentration.

2. The dust suppression system for municipal construction based on image processing according to claim 1, characterized in that, The method for obtaining the atomization coefficient includes: In the target image, based on the grayscale value of pixel points, screen out the maximum value points; Taking each pixel point as the center, construct a preset second neighborhood; In the preset second neighborhood corresponding to each pixel point, randomly select one maximum value point as the measurement point, and use the maximum value point with the smallest Euclidean distance from the measurement point among the remaining maximum value points as the comparison point, calculate the average grayscale value between the measurement point and the comparison point as the first grayscale average value, calculate the average grayscale value of pixel points whose grayscale values exist between the measurement point and the comparison point as the second grayscale average value, and use the Euclidean distance between the measurement point and the comparison point as the distance factor; Taking the absolute value of the difference between the first grayscale average value and the second grayscale average value between the measurement point and the comparison point as the grayscale fluctuation factor, and taking the value obtained by normalizing the ratio of the grayscale fluctuation factor to the distance factor as the atomization factor corresponding to the measurement point; In the preset second neighborhood corresponding to each pixel point, taking the value obtained by normalizing the sum of the atomization factors corresponding to all maximum value points as the atomization coefficient of each pixel point.

3. The dust suppression system for municipal construction based on image processing according to claim 2, wherein, The method for obtaining the maximum value points includes: In the target image, determine the preset first neighborhood of each pixel point, and within the preset first neighborhood corresponding to each pixel point, take the pixel point with the largest grayscale value as the maximum value point; Wherein, the preset first neighborhood is smaller than the preset second neighborhood.

4. The dust reduction system for municipal construction based on image processing according to claim 2, wherein The method for obtaining the particulate matter region includes: Taking two grayscale images as the input of the optical flow method, so as to output the optical flow vector corresponding to the pixel points in the target image; In the target image, determine the particle factor of each pixel point according to the atomization coefficient, optical flow vector corresponding to each pixel point, and the grayscale chaos situation of pixel points within the corresponding preset second neighborhood; Segmenting the target image based on the Otsu threshold segmentation method to obtain two regions, and the regions are divided into a foreground region and a background region; In each region, calculate the average value of the particle factors of all pixel points as the particulate matter index corresponding to each region; Taking the region with the largest particulate matter index as the particulate matter region.

5. The dust suppression system for municipal construction based on image processing according to claim 4, characterized in that, The method for obtaining the particle factor includes: Within the preset second neighborhood corresponding to each pixel, take the mean of the gray gradients of all pixel points as the gray change factor for each pixel point; Calculate the magnitude of the optical flow vector corresponding to each pixel point as the motion intensity corresponding to each pixel point; For any pixel point, take the product of the fogging coefficient and the gray change factor of this pixel point as the gray change coefficient, and normalize the absolute value of the difference between the ratio of the gray change coefficient and the motion intensity of this pixel point and a preset first constant to obtain the particle factor of this pixel point.

6. The dust reduction system for municipal construction based on image processing according to claim 4, characterized in that, The method for obtaining the dust reduction eigenvalue includes: Divide the particulate matter region based on the superpixel segmentation method to obtain multiple superpixel blocks; Based on the number distribution, motion conditions, and fogging coefficients of the pixel points in all superpixel blocks in the particulate matter region, determine the water mist factor of each superpixel block and the water mist combination index of the particulate matter region; In the particulate matter region, analyze the motion diffusion of the pixel points, and combine the water mist factors of all superpixel blocks in the particulate matter region to determine the dust diffusion coefficient of the particulate matter region; Take the normalized value of the ratio of the water mist combination index to the dust diffusion coefficient as the dust reduction eigenvalue of the particulate matter region.

7. An urban construction dust suppression system based on image processing according to claim 6, characterized in that, The determining of the water mist factor of each superpixel block and the water mist combination index of the particulate matter region based on the number distribution, motion conditions, and fogging coefficients of the pixel points in all superpixel blocks in the particulate matter region includes: In each superpixel block, take the mean of the fogging coefficients of all pixel points as the fogging mean value; Preset the number of iterations. At each iteration, in each superpixel block, randomly select a certain number of pixel points as water mist pixel points; Calculate the ratio of the number of water mist pixel points in each superpixel block to the number of all pixel points as the water mist density, and take the variance of the magnitudes of the optical flow vectors of all water mist pixel points in each superpixel block as the chaos factor of each superpixel block; Take the absolute value of the difference between the ratio of the fogging mean value and the water mist density corresponding to each superpixel block and a preset second constant as the true factor, and take the value obtained by performing a negative correlation mapping and normalization on the ratio of the true factor to the chaos factor as the water mist loss factor corresponding to each superpixel block at each iteration; Take the sum of the water mist loss factors corresponding to all superpixel blocks as the water mist loss value corresponding to the particulate matter region at each iteration; Among all the iteration times, at the minimum water mist loss value, take the water mist density corresponding to each superpixel block as the water mist factor of each superpixel block; take the normalized value of the difference between the maximum water mist density and the minimum water mist density among all superpixel blocks as the water mist combination index of the particulate matter region.

8. The dust reduction system for municipal construction based on image processing according to claim 6, characterized in that, The method for obtaining the dust diffusion coefficient includes: In each superpixel block, calculate the mean of the optical flow vectors of all pixel points as the comprehensive vector; Decompose the comprehensive vector, remove the vertically downward component and then synthesize it to obtain the diffusion vector; Take the ratio of the magnitude of the diffusion vector corresponding to each superpixel block to the water mist factor as the diffusion factor corresponding to each superpixel block; The value obtained by normalizing the mean of the diffusion factors of all superpixel blocks is used as the dust diffusion coefficient of the particulate matter area.

9. The dust suppression system for municipal construction based on image processing according to claim 1, wherein, The method for obtaining the final water mist concentration includes: Taking the difference between a preset third constant and the dust removal eigenvalue as an adjustment coefficient; Taking the product of the adjustment coefficient and the initial water mist concentration as the final water mist concentration.

10. A dust reduction device for municipal construction based on image processing, characterized in that, It includes a processor and a memory. At least one instruction, at least one program, a code set or an instruction set is stored in the memory. When at least one instruction, at least one program, the code set or the instruction set is loaded and executed by the processor, the steps of a municipal construction dust removal system based on image processing as described in any one of claims 1-9 are implemented.

Images