A method and system for visualizing dust accumulation on pipe surface

Abstract

The present invention relates to the field of image processing technology, and in particular to a method and system for visualizing dust accumulation on the surface of a tube body. The method comprises the steps of: obtaining two target areas of each frame of a tube body image, obtaining the directional characteristics and aggregation degree of each target area of ​​each frame of the tube body image based on the target areas, and obtaining the shadow area characteristics of each target area of ​​each frame of the tube body image according to the directional characteristics and aggregation degree; obtaining the expression degree of each edge point of each target area of ​​each frame of the tube body image, obtaining the edge strength of each target area of ​​each frame of the tube body image based on the expression degree, obtaining the dust accumulation area characteristics of each target area of ​​each frame of the tube body image based on the edge strength and aggregation degree, obtaining the dust accumulation area of ​​each frame of the tube body image according to the dust accumulation area characteristics and shadow area characteristics, and obtaining the dust accumulation situation of the tube body according to the dust accumulation area of ​​each frame of the tube body image. The present invention can accurately identify the dust accumulation area.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for visualizing dust accumulation on a pipe surface. Background Art

[0002] In many industrial applications, such as petroleum, chemical, and electric power industries, the normal operation of the pipeline system is crucial. Dust accumulation may affect the heat exchange efficiency of the pipeline and cause equipment failure, so effective monitoring and evaluation methods are needed. Traditional manual inspections and simple sensor monitoring may not be comprehensive or accurate enough to conduct detailed and real-time evaluations of dust distribution on the pipeline surface. With the development of image processing and computer vision technology, it has become more feasible and efficient to use advanced visual technology to monitor and analyze dust accumulation on the pipeline surface. Through visualization technology, the speed and accuracy of identifying dust accumulation on the pipeline surface can be improved, thereby reducing maintenance costs and improving the safety of equipment operation.

[0003] The patent application document with the publication number CN113870182A currently discloses an Otsu thresholding method with a mask. First, the number of masks and the number of permeable areas in the masks are determined, and a template of equal size is made according to the original image. The shielding area and the permeable area in the template are filled with grayscale shielding factors and permeability factors respectively; then the Hadamard product of the image and the mask is used as the target area to be extracted; then, the maximum between-class variance in the target area is calculated to obtain the threshold of the target area thresholding operation; finally, the threshold is binarized with the obtained threshold.

[0004] When segmenting the dusty area on the tube body, since the tube body is not built horizontally or vertically, but has turns or even stacks, the projection of part of the tube body under light is mapped onto the remaining tube bodies, resulting in shadow areas on the remaining tube bodies. This shadow area is very close to the dusty area on the tube body in grayscale. At this time, although the Otsu threshold method in the above method can be used to divide the tube body image into two categories, since the grayscales of the two are relatively close, it is impossible to distinguish whether the grayscale level greater than the threshold belongs to the dusty area, or the grayscale level less than the threshold belongs to the dusty area. Summary of the invention

[0005] In order to solve the technical problem that the shadow area and the dust accumulation area on the tube body are very close in grayscale, and the dust accumulation area cannot be confirmed after the tube body image is divided into two categories using the Otsu threshold method, the present invention provides a dust accumulation visualization method and system on the tube body surface.

[0006] In a first aspect, the present invention provides a method for visualizing dust accumulation on a pipe surface, which adopts the following technical solution:

[0007] A method for visualizing dust accumulation on a pipe surface, comprising the steps of:

[0008] Obtain each frame of the tube body image, perform threshold segmentation on each frame of the tube body image, and obtain several target areas of each frame of the tube body image; obtain the directional characteristics of each target area of ​​each frame of the tube body image; obtain the degree of aggregation of each target area of ​​each frame of the tube body image; obtain the shadow area characteristics of each target area of ​​each frame of the tube body image ; In the formula, Represents the shadow area feature of the zth target area of ​​the i-th frame tube image; Represents the directional features of the zth target area of ​​the i-th frame tube image; Represents the aggregation degree of the zth target area of ​​the i-th frame tube image;

[0009] Obtain the edge strength of each target area of ​​each frame of the tube image; obtain the dust accumulation area characteristics of each target area of ​​each frame of the tube image ; Represents the dust accumulation area feature of the zth target area of ​​the i-th frame tube image; Represents the aggregation degree of the zth target area of ​​the i-th frame tube image; Represents the edge strength of the zth target area of ​​the i-th tube body image;

[0010] The dust accumulation area features of each target area of ​​each frame of the tube body image are compared with the shadow area features to obtain the dust accumulation area of ​​each frame of the tube body image; and the dustiness of the tube body is obtained according to the dust accumulation area of ​​each frame of the tube body image.

[0011] The innovation of the present invention lies in obtaining the shadow area features and the dust accumulation area features of each target area of ​​each frame of the tube body image according to the features of the shadow area and the dust accumulation area, and finally comparing the shadow area features with the dust accumulation area features of each target area of ​​each frame of the tube body image to obtain the dust accumulation area of ​​each frame of the tube body image to evaluate the dust accumulation situation, confirm the dust accumulation area, reduce the misjudgment caused by the grayscale overlap between the shadow area and the dust accumulation area, and make the subsequent dust accumulation situation evaluation more accurate.

[0012] Preferably, the threshold segmentation is performed on each frame of the tube body image to obtain a plurality of target areas of each frame of the tube body image, including:

[0013] The i-th frame tube body image is segmented using the Otsu threshold segmentation method to obtain the i-th frame initial segmentation image, and the two regions in the i-th frame initial segmentation image are recorded as the two target regions of the i-th frame tube body image.

[0014] Preferably, the step of obtaining the directional features of each target area of ​​each frame of the tube body image includes:

[0015] ;

[0016] In the formula, Represents the directional features of the zth target area of ​​the i-th frame tube image; Represents the number of pixels in the zth target area of ​​the i-th frame tube image; Represents the gradient direction of the jth pixel point in the zth target area of ​​the i-th frame tube image; Represents the variance of the gradient direction of all pixels in the zth target area of ​​the i-th tube body image; Represents the maximum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube image; Represents the minimum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube image; exp() represents an exponential function with a natural constant as the base, and || represents an absolute value function.

[0017] This facilitates the subsequent acquisition of shadow area features of each target area of ​​each frame of the tube body image based on the directional features.

[0018] Preferably, the step of obtaining the concentration degree of each target area in each frame of the tube body image includes:

[0019] The number of clusters k is preset, and each target area of ​​each frame of the tube body image is clustered using the k-means clustering algorithm, and the cluster center is used as the central pixel point of each target area of ​​each frame of the tube body image;

[0020] The mean of the Euclidean distances from all pixels in the zth target area of ​​the i-th tube body image to its central pixel is obtained and recorded as the first mean. The reciprocal of the first mean is recorded as the aggregation degree of the zth target area of ​​the i-th tube body image.

[0021] This facilitates the subsequent acquisition of shadow area features and dust accumulation area features of each target area of ​​each frame of the tube body image according to the degree of aggregation.

[0022] Preferably, the step of obtaining the edge strength of each target area of ​​each frame of the tube body image includes:

[0023] Obtain the expression level of each edge point of each target area of ​​each frame of the tube body image;

[0024] ;

[0025] In the formula, Represents the edge strength of the zth target area of ​​the i-th tube body image; Represents the number of edge points of the zth target area of ​​the i-th frame tube image; Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the mean value of the performance of all edge points in the zth target area of ​​the i-th tube image.

[0026] This facilitates the subsequent acquisition of dust accumulation area features of each target area of ​​each frame of the tube body image based on edge strength.

[0027] Preferably, the step of obtaining the expression level of each edge point of each target area of ​​each frame of the tube body image includes:

[0028] Use the canny edge detection algorithm to obtain the edge points of each target area in each frame of the tube image;

[0029] ;

[0030] In the formula, Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the difference in the gradient direction between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point; Represents the difference in grayscale value between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point.

[0031] Preferably, obtaining the dust accumulation area of ​​each frame of the tube body image includes:

[0032] If the dust accumulation area feature of the first target area of ​​the i-th frame tube body image is greater than the shadow area feature and the dust accumulation area feature of the second target area is less than the shadow area feature, then the first target area of ​​the i-th frame tube body image is the dust accumulation area; if the dust accumulation area feature of the first target area of ​​the i-th frame tube body image is less than the shadow area feature and the dust accumulation area feature of the second target area is greater than the shadow area feature, then the second target area of ​​the i-th frame tube body image is the dust accumulation area.

[0033] It can accurately identify dust accumulation areas and reduce misjudgment caused by grayscale overlap between shadow areas and dust accumulation areas.

[0034] Preferably, the step of obtaining the tube volume ash situation includes:

[0035] ;

[0036] Where, N represents the dust content of the tube; The number of pixels representing the gray area of ​​the first frame of the tube body image; Represents the number of pixels in the gray area of ​​the last frame of the tube image; Represents the grayscale mean value in the gray area of ​​the tube body image of the vth frame; represents the grayscale mean in the gray area of ​​the tube body image of the v+1th frame; || represents the absolute value sign; V represents the frame number of the tube body image.

[0037] In a second aspect, the present invention provides a system for visualizing dust accumulation on a pipe surface, which adopts the following technical solution:

[0038] A pipe surface dust visualization system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned pipe surface dust visualization method is implemented.

[0039] By adopting the above technical solution, the above-mentioned method for visualizing dust accumulation on the surface of a pipe is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0040] The present invention has the following technical effects: the purpose of the present invention is to obtain the shadow area features and the dust accumulation area features of each target area of ​​each frame of the tube body image according to the features of the shadow area and the dust accumulation area, and finally compare the shadow area features with the dust accumulation area features of each target area of ​​each frame of the tube body image to obtain the dust accumulation area of ​​each frame of the tube body image to evaluate the dust accumulation situation, confirm the dust accumulation area, reduce the misjudgment caused by the grayscale overlap of the shadow area and the dust accumulation area, and make the subsequent dust accumulation situation evaluation more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0042] Figure 1 The present invention is a flowchart of a method for visualizing dust accumulation on the surface of a pipe according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0044] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0045] The embodiment of the present invention discloses a method for visualizing dust accumulation on the surface of a pipe body, referring to Figure 1 , comprising steps S1 to S4:

[0046] S1: Acquire each frame of the tube body image.

[0047] In an embodiment of the present invention, a camera is installed above the tube body to collect a video of the tube body surface, and the FFmpeg software is used to decompose the tube body surface video into several frames of tube body RGB images. In order to facilitate subsequent analysis, each frame of the tube body RGB image is grayed to obtain each frame of the tube body image.

[0048] S2: Obtain two target areas of each frame of the tube body image, and based on the target areas, obtain the directional characteristics and aggregation degree of each target area of ​​each frame of the tube body image, and according to the directional characteristics and aggregation degree of each target area of ​​each frame of the tube body image, obtain the shadow area characteristics of each target area of ​​each frame of the tube body image.

[0049] It should be noted that when the dust accumulation area on the tube body is segmented, since the tube body is not built horizontally and vertically, but has turns or even stacked, this causes the projection of part of the tube body under light to be mapped onto the remaining tube bodies, resulting in shadow areas on the remaining tube bodies. This shadow area is very close to the dust accumulation area on the tube body in grayscale. At this time, although the Otsu method can be used to divide the tube body image into two categories, since the grayscales of the two are relatively close, it is impossible to distinguish whether the grayscale level greater than the threshold belongs to the dust accumulation area, or the grayscale level less than the threshold belongs to the dust accumulation area. Therefore, the present invention first needs to use the Otsu threshold method to segment each frame of the tube body image to obtain an initial segmented image, and then analyze the two areas in the initial segmented image to determine which one belongs to the dust accumulation area.

[0050] In an embodiment of the present invention, the Otsu threshold segmentation method is used to segment the i-th frame tube body image to obtain the i-th frame initial segmentation image and the segmentation threshold of the i-th frame tube body image, and the two areas in the i-th frame initial segmentation image are recorded as the two target areas of the i-th frame tube body image.

[0051] It should be noted that two target areas are obtained for each frame of the tube body image, so it is necessary to analyze each target area of ​​each frame of the tube body image according to the characteristics of the dust accumulation area and the shadow area. It is known that the grayscale of the dust accumulation area and the shadow area are relatively low, so they cannot be distinguished by the grayscale value. Since the shadow area caused by the pipe being blocked is a regular area, the direction of the shadow area is consistent with the direction of light, but the dust accumulation area is caused by the continuous accumulation of dust, so the edge of the dust accumulation area is blurred; and because the shadow area caused by the pipe being blocked will divide the dust accumulation area, the aggregation degree of the pixel point distribution in the dust accumulation area is relatively low, while the aggregation degree of the pixel point distribution in the shadow area is relatively high, that is, the shadow area has directional characteristics and the pixel point distribution is concentrated, the edge of the dust accumulation area is relatively blurred and the pixel point distribution is relatively dispersed, so the unique characteristics of the two different areas are combined to obtain the shadow area characteristics and dust accumulation area characteristics of each target area of ​​each frame of the tube body image, and then judge whether each target area of ​​each frame of the tube body image is a dust accumulation area or a shadow area through the size of the shadow area characteristics and the dust accumulation area characteristics of each target area of ​​each frame of the tube body image.

[0052] It should be further explained that the shadow area feature of each target area in each frame of the tube body image is obtained based on the directional feature and the degree of aggregation of each target area. Since the direction of the shadow area caused by the obstruction of the tube is consistent with the direction of illumination, the gradient direction of the pixel points in the shadow area is approximate, and the variance of the gradient direction of the pixel points is small. The directional feature of each target area in each frame of the tube body image is obtained based on this feature. Since the pixel points in the shadow area are distributed in a relatively concentrated manner, the central pixel point of the target area is obtained. According to the Euclidean distance from each pixel point in the target area to its central pixel point, the degree of aggregation of each target area in each frame of the tube body image is quantified.

[0053] In the embodiment of the present invention, the directional features of each target area of ​​the tube body image of the i-th frame are obtained:

[0054] ;

[0055] In the formula, Represents the directional features of the zth target area of ​​the i-th frame tube image; Represents the number of pixels in the zth target area of ​​the i-th frame tube image; Represents the gradient direction of the jth pixel point in the zth target area of ​​the i-th frame tube image; Represents the variance of the gradient direction of all pixels in the zth target area of ​​the i-th tube body image; Represents the maximum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube image; Represents the minimum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube body image; exp() represents an exponential function with a natural constant as the base. The larger its value is, the greater the directional feature of the zth target area of ​​the i-th frame tube body image is, which means that the zth target area of ​​the i-th frame tube body image is more likely to be a shadow area.

[0056] The number of clusters k is preset to 1. In other embodiments, the implementer may preset the value of k according to the specific implementation method, use the k-means clustering algorithm to cluster each target area of ​​each frame of the tube body image, and use the cluster center as the central pixel point of each target area of ​​each frame of the tube body image;

[0057] The mean of the Euclidean distances from all pixels in the zth target area of ​​the i-th tube body image to its central pixel is obtained and recorded as the first mean. The reciprocal of the first mean is recorded as the aggregation degree of the zth target area of ​​the i-th tube body image.

[0058] Get the shadow area features of each target area in each frame of the tube image:

[0059] ;

[0060] In the formula, Represents the shadow area feature of the zth target area of ​​the i-th frame tube image; Represents the directional features of the zth target area of ​​the i-th frame tube image; Represents the degree of aggregation of the zth target area of ​​the i-th frame tube body image; when the directional characteristics of the zth target area of ​​the i-th frame tube body image are more obvious and the degree of aggregation is greater, the zth target area will express the shadow area more.

[0061] S3: Obtain the expression degree of each edge point of each target area of ​​each frame of the tube body image, obtain the edge strength of each target area of ​​each frame of the tube body image based on the expression degree, obtain the dust accumulation area characteristics of each target area of ​​each frame of the tube body image based on the edge strength and aggregation degree of each target area of ​​each frame of the tube body image, and obtain the dust accumulation area of ​​each frame of the tube body image according to the dust accumulation area characteristics and shadow area characteristics of each target area of ​​each frame of the tube body image.

[0062] It should be noted that it is known that the dust accumulation area is caused by the continuous accumulation of dust, so the edge of the dust accumulation area is blurred. Therefore, it is necessary to first obtain the edge points of each target area of ​​each frame of the tube body image, and obtain the degree of expression of each edge point to the edge according to the gradient direction difference and grayscale value difference between each edge point and its nearest edge point. If the gradient direction difference is smaller and the grayscale value difference is smaller, the edge point has a higher degree of expression of the edge, that is, the edge point has a higher degree of expression; then, according to the variance of the expression degree of all edge points in each target area of ​​each frame of the tube body image, the edge strength of each target area of ​​each frame of the tube body image is obtained.

[0063] It should be further explained that, when the edge strength of each target area in each frame of the tube body image is more obvious and the degree of aggregation is smaller, the target area will be more representative of the dust accumulation area. Therefore, the dust accumulation area characteristics of each target area in each frame of the tube body image are obtained by combining the edge strength and degree of aggregation of each target area in each frame of the tube body image.

[0064] In an embodiment of the present invention, a canny edge detection algorithm is used to obtain edge points of each target area of ​​each frame of the tube body image; the Euclidean distance between the bth edge point of the zth target area of ​​the i-th frame of the tube body image and each edge point except the bth edge point is obtained, and the edge point corresponding to the minimum Euclidean distance is recorded as the nearest edge point of the bth edge point of the zth target area of ​​the i-th frame of the tube body image.

[0065] Get the performance level of each edge point of each target area in each frame of the tube image:

[0066] ;

[0067] In the formula, Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the difference in the gradient direction between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point; Represents the difference in grayscale value between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point.

[0068] Get the edge strength of each target area in each frame of the tube image:

[0069] ;

[0070] In the formula, Represents the edge strength of the zth target area of ​​the i-th tube body image; Represents the number of edge points of the zth target area of ​​the i-th frame tube image; Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the mean value of the performance of all edge points in the zth target area of ​​the i-th tube image.

[0071] Get the dust accumulation area features of each target area in each frame of the tube image:

[0072] ;

[0073] In the formula, Represents the dust accumulation area feature of the zth target area of ​​the i-th frame tube image; Represents the aggregation degree of the zth target area of ​​the i-th frame tube image; Represents the edge strength of the zth target area of ​​the i-th frame tube body image; when the edge strength of the zth target area of ​​the i-th frame tube body image is more obvious and the degree of aggregation is smaller, the zth target area will show a greater degree of gray area.

[0074] If the dust accumulation region feature of the first target region of the i-th frame tube body image is greater than the shadow region feature and the dust accumulation region feature of the second target region is less than the shadow region feature, then the first target region of the i-th frame tube body image is a dust accumulation region; if the dust accumulation region feature of the first target region of the i-th frame tube body image is less than the shadow region feature and the dust accumulation region feature of the second target region is greater than the shadow region feature, then the second target region of the i-th frame tube body image is a dust accumulation region;

[0075] If the dust accumulation area features of the first target area and the second target area of ​​the i-th frame tube body image are both greater than the shadow area features, or the dust accumulation area features of the first target area and the second target area of ​​the i-th frame tube body image are both smaller than the shadow area features, the segmentation threshold of the i-th frame tube body image is increased by one gray value and used as the new segmentation threshold of the i-th frame tube body image to analyze the two target areas obtained after segmenting the i-th frame tube body image. If the above situation still exists, the segmentation threshold of the i-th frame tube body image is reduced by one gray value and used as the new segmentation threshold of the i-th frame tube body image to analyze the two target areas obtained after segmenting the i-th frame tube body image until the dust accumulation area obtained in the i-th frame tube body image exists and is unique. It should be noted that when adjusting the threshold, it is adjusted in the order of increasing one gray value, decreasing one gray value, increasing two gray values, decreasing two gray values, and increasing three gray values.

[0076] S4: Obtain the dust accumulation status of the tube body according to the dust accumulation area of ​​each frame of the tube body image.

[0077] It should be noted that after obtaining the dust accumulation area in each frame of the tube body image, the dust accumulation situation during this period of time is obtained based on the changes in the number of pixels and the grayscale changes in the dust accumulation area of ​​the continuous frame tube body image. Among them, the greater the changes in the number of pixels and the grayscale changes in the dust accumulation area of ​​the continuous frame tube body image, the more serious the dust accumulation situation during this period of time.

[0078] In the embodiment of the present invention, the dust level of the tube volume is obtained:

[0079] ;

[0080] Where, N represents the dust content of the tube; The number of pixels representing the gray area of ​​the first frame of the tube body image; Represents the number of pixels in the gray area of ​​the last frame of the tube image; Represents the grayscale mean value in the gray area of ​​the tube body image of the vth frame; Represents the grayscale mean in the dusty area of ​​the tube body image in the v+1th frame; || represents the absolute value symbol; V represents the frame number of the tube body image. The larger the value, the more serious the dust accumulation situation of the tube body during this period.

[0081] An embodiment of the present invention further discloses a system for visualizing dust accumulation on a pipe surface, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for visualizing dust accumulation on a pipe surface according to the present invention is implemented.

[0082] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0083] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0085] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for visualizing dust accumulation on a pipe surface, characterized in that: Includes steps: Obtain each frame of the tube body image, perform threshold segmentation on each frame of the tube body image, and obtain a number of target areas of each frame of the tube body image; obtain the directional features of each target area of ​​each frame of the tube body image; Obtain the concentration degree of each target area of ​​each frame of the tube body image; obtain the shadow area characteristics of each target area of ​​each frame of the tube body image ; In the formula, Represents the shadow area feature of the zth target area of ​​the i-th frame tube image; Represents the directional features of the zth target area of ​​the i-th frame tube image; Represents the aggregation degree of the zth target area of ​​the i-th frame tube image; Directional features of the zth target area of ​​the i-th tube image for: ； In the formula, Represents the number of pixels in the zth target area of ​​the i-th frame tube image; Represents the gradient direction of the jth pixel point in the zth target area of ​​the i-th frame tube image; Represents the variance of the gradient direction of all pixels in the zth target area of ​​the i-th tube body image; Represents the maximum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube image; represents the minimum value of the gradient direction of all pixels in the zth target area of ​​the i-th frame tube body image; exp() represents an exponential function with a natural constant as the base; Obtain the edge strength of each target area of ​​each frame of the tube image; obtain the dust accumulation area characteristics of each target area of ​​each frame of the tube image ; Represents the dust accumulation area feature of the zth target area of ​​the i-th frame tube image; Represents the edge strength of the zth target area of ​​the i-th tube body image; Comparing the dust accumulation area feature of each target area of ​​each frame of the tube body image with the shadow area feature to obtain the dust accumulation area of ​​each frame of the tube body image, including: if the dust accumulation area feature of the first target area of ​​the i-th frame of the tube body image is greater than the shadow area feature and the dust accumulation area feature of the second target area is less than the shadow area feature, then the first target area of ​​the i-th frame of the tube body image is the dust accumulation area; if the dust accumulation area feature of the first target area of ​​the i-th frame of the tube body image is less than the shadow area feature and the dust accumulation area feature of the second target area is greater than the shadow area feature, then the second target area of ​​the i-th frame of the tube body image is the dust accumulation area; according to the dust accumulation area of ​​each frame of the tube body image, obtaining the dustiness of the tube body, including: ; In the formula, N represents the dust content of the tube; The number of pixels representing the gray area of ​​the first frame of the tube body image; Represents the number of pixels in the gray area of ​​the last frame of the tube image; Represents the grayscale mean value in the gray area of ​​the tube body image of the vth frame; represents the grayscale mean in the gray area of ​​the tube body image of the v+1th frame; || represents the absolute value sign; V represents the frame number of the tube body image.

2. A method for visualizing dust accumulation on a pipe surface according to claim 1, characterized in that: The threshold segmentation is performed on each frame of the tube body image to obtain a plurality of target areas of each frame of the tube body image, including: The i-th frame tube body image is segmented using the Otsu threshold segmentation method to obtain the i-th frame initial segmentation image, and the two regions in the i-th frame initial segmentation image are recorded as the two target regions of the i-th frame tube body image.

3. A method for visualizing dust accumulation on a pipe surface according to claim 1, characterized in that: The step of obtaining the concentration degree of each target area of ​​each tube body image frame includes: The number of clusters k is preset, and each target area of ​​each frame of the tube body image is clustered using the k-means clustering algorithm, and the cluster center is used as the central pixel point of each target area of ​​each frame of the tube body image; The mean of the Euclidean distances from all pixels in the zth target area of ​​the i-th tube body image to its central pixel is obtained as the first mean, and the reciprocal of the first mean is recorded as the aggregation degree of the zth target area of ​​the i-th tube body image.

4. A method for visualizing dust accumulation on a pipe surface according to claim 1, characterized in that: The step of obtaining the edge strength of each target area of ​​each frame of the tube body image comprises: Obtain the expression level of each edge point of each target area of ​​each frame of the tube body image; ； In the formula, Represents the edge strength of the zth target area of ​​the i-th tube body image; Represents the number of edge points of the zth target area of ​​the i-th frame tube image; Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the mean value of the performance of all edge points in the zth target area of ​​the i-th tube image.

5. A method for visualizing dust accumulation on a pipe surface according to claim 4, characterized in that: The step of obtaining the expression level of each edge point of each target area in each frame of the tube body image includes: Use the canny edge detection algorithm to obtain the edge points of each target area in each frame of the tube image; ； In the formula, Represents the performance level of the bth edge point of the zth target area of ​​the i-th tube body image; Represents the difference in the gradient direction between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point; Represents the difference in grayscale value between the bth edge point of the zth target area of ​​the i-th tube body image and its nearest edge point.

6. A pipe surface dust visualization system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for visualizing dust accumulation on a pipe surface according to any one of claims 1 to 5 is implemented.

Images