Coal mine underground video monitoring method

Abstract

The invention relates to the technical field of image denoising, in particular to a coal mine underground video monitoring method, which comprises the following steps of: acquiring a coal mine underground video image by using an explosion-proof camera; calculating the spatial proximity between each pixel point in the search window and the current pixel point; calculating the dust influence degree and the illumination influence degree of the similar window of each pixel point, and further analyzing the similarity of the direction dispersion degrees of the similar windows of any two pixel points; and calculating the weight of each pixel point to the current pixel point in the search window by combining the spatial proximity, and performing weighted summation on the pixel values of all the pixel points in the search window to obtain the denoised pixel value of the current pixel point so as to construct the denoised image. The method aims at eliminating adverse effects of dust, illumination and distance on similarity calculation under the condition that image details and edge information are not lost, reducing coal mine underground monitoring video image noise and enabling the monitoring process to be more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of image denoising, and in particular to a method for underground video monitoring in a coal mine. Background Art

[0002] Coal occupies an important position in the development of our country, so the safe mining of coal mines is of great significance to the social and economic development of our country. With the rapid development of the computer industry, the use of intelligent devices to monitor the mining of coal mines and the safety of employees' lives has made great progress.

[0003] However, due to insufficient lighting and excessive dust underground, the collected video image information contains a large amount of noise, which has an adverse effect on subsequent image processing tasks. The application results of using artificial intelligence for target recognition and detection are not very ideal. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a coal mine underground video monitoring method to solve the existing problems.

[0005] The present invention discloses a method for underground video monitoring in a coal mine using the following technical solutions: An embodiment of the present application provides a method for underground video monitoring in a coal mine, the method comprising the following steps: S1, using explosion-proof cameras to collect video images of underground coal mines; S2, defining a similarity window and a search window for each pixel point in the underground coal mine video image; for each pixel point in the search window of the current pixel point, using a Gaussian function to analyze the distance between each pixel point and the current pixel point, and calculating the spatial proximity between each pixel point in the search window and the current pixel point; S3, obtaining the dark channel value of each pixel in the image and constructing a dark channel image; dividing all dark channel values ​​in the similarity window of each pixel in the dark channel image into orders, and analyzing the connected areas of different sizes and their occurrence times under each order of division, as well as the distance between the centroid of each connected area and the center of the similarity window, to construct the dust influence degree of the similarity window; S4, obtaining the illumination component of each pixel in the image and constructing an illumination image; calculating the illumination influence of the similar window of each pixel in the illumination image according to the same calculation method as the dust influence of the similar window of each pixel in the dark channel image; S5, based on the dust influence and the illumination influence, determine the value of the central pixel point corresponding to the similar window position in the comprehensive distribution image; calculate the directional dispersion of the similar window by using the dispersion of the gradient amplitude of the value in the similar window of each pixel point in the comprehensive distribution image in different direction ranges; and analyze the similarity of the directional dispersion of the similar windows of any two pixel points in the comprehensive distribution image; S6, combining the spatial proximity of each pixel point in the search window to the current pixel point, and the similarity of the directional dispersion of the similarity windows of the two corresponding pixel points in the comprehensive distribution image, calculate the weight of each pixel point in the search window to the current pixel point; based on the weight, perform weighted summation on the pixel values ​​of all pixels in the search window to obtain the denoised pixel value of the current pixel point, thereby constructing a denoised image.

[0006] Preferably, in step S2, the similarity window and the search window are respectively a square window centered on any pixel point, and the similarity window is smaller than the search window, and the similarity window slides in the search window.

[0007] Preferably, in step S3, the dark channel value of each pixel is determined by the minimum value of the minimum values ​​of each pixel in each channel in the similarity window corresponding to the pixel.

[0008] Preferably, in step S4, the illumination component of each pixel in the illumination image is obtained by convolving the pixel value with a preset Gaussian kernel.

[0009] Preferably, in step S3, the method for constructing the dust influence degree of the similar window is: The dust influence degree of the similar window is recorded as , the calculation formula is: Where P is the number of dark channel value orders in the similar window, Q is the maximum size of the connected area with the same dark channel order in the similar window, M is the maximum number of connected areas with the same size in the similar window, p is the order p, q is the size of the connected area q, It represents the number of occurrences of the connected region with dark channel order p and size q in the similarity window. It represents the distance between the centroid of the mth connected region with dark channel order p and size q in the similarity window and the center of the similarity window.

[0010] Preferably, in step S5, the product of the dust influence degree of the similar window of each pixel point in the dark channel image and the illumination influence degree of the similar window of the corresponding pixel point in the illumination image is used as the value of the corresponding pixel point in the comprehensive distribution image.

[0011] Preferably, in step S5, the method for calculating the directional dispersion of the similarity window is: Obtain the gradient direction and gradient amplitude of each pixel in the comprehensive distribution map; The gradient direction is divided into several gradient direction ranges; the gradient amplitudes belonging to the same gradient direction range are accumulated and counted to obtain a gradient direction histogram; The square sum of the accumulated gradient amplitudes in all gradient direction ranges in the gradient direction histogram is taken as the directional dispersion of the similarity window.

[0012] Preferably, in step S5, the similarity of the directional dispersion of similar windows of any two pixels in the comprehensive distribution image is determined by the result of negative correlation mapping of the difference in the directional dispersion of the similar windows of the two pixels.

[0013] Preferably, in step S6, the weight of each pixel in the search window to the current pixel is calculated as follows: The spatial proximity of each pixel in the search window to the current pixel is added to the similarity of the directional dispersion of the similar windows of the two corresponding pixels in the comprehensive distribution image to obtain the weight of each pixel in the search window to the current pixel.

[0014] Preferably, the method further comprises performing target recognition and tracking processing on the denoised image.

[0015] This application has at least the following beneficial effects: The present application utilizes the redundant information in the video images of underground coal mines, and according to the characteristics of high dust content and weak illumination in underground coal mines, takes the search window in the image as a unit, analyzes the distribution characteristics of dust and illumination in all similar windows inside, considers the influence of dust and illumination on different pixel points, and estimates each pixel value in the image by combining the spatial proximity of the image, the proximity of the dark channel value, and the proximity of the illumination condition. Without losing the image details and edge information, the application eliminates the adverse effects of dust, illumination, and distance on the similarity calculation, reduces the noise of underground coal mine monitoring video images, and makes the monitoring process more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flow chart of a method for underground video monitoring in a coal mine provided in this application; Figure 2 A flowchart is provided for constructing an indicator of the weight of each pixel point in the search window to the current pixel point. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of a method for underground video monitoring in a coal mine proposed in accordance with the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0020] The specific scheme of the underground video monitoring method of a coal mine provided by the present application is described in detail below with reference to the accompanying drawings.

[0021] An embodiment of the present application provides a method for underground video monitoring in a coal mine.

[0022] Specifically, the following method for underground video monitoring in coal mines is provided. Figure 1 , the method comprises the following steps: S1, using explosion-proof cameras to collect video images underground in coal mines.

[0023] This application requires denoising of underground coal mine video images, and requires first using an explosion-proof camera to capture images.

[0024] Cameras are needed for daily inspections, documentary filming, geological surveys, etc. in coal mines. However, there are flammable and explosive gases and substances such as gas and coal dust in coal mines. Underground equipment will produce electric sparks, arcs, hot surfaces and hot particles when operating normally or when there is a fault. They all have thermal energy and may become the ignition source and heat source for igniting mine gas and coal dust. Ordinary cameras have not been improved with explosion-proof technology and may produce sparks with flammable gases underground, thereby causing the risk of explosion. Explosion-proof cameras can be used in dangerous places in coal mines, mainly for coal mine disaster accident investigation and evidence collection and daily geological cataloging, recording production safety conditions, operating status of electromechanical equipment, roof support conditions and geological characteristics underground.

[0025] Accordingly, this application uses explosion-proof cameras to collect video images underground in coal mines. Among them, the explosion-proof camera must meet the explosion-proof standards of coal mines and is used to safely collect video images in an environment containing gas or coal dust. The specific explosion-proof camera model is set by the implementer.

[0026] S2, define a similarity window and a search window for each pixel point in the underground coal mine video image; for each pixel point in the search window of the current pixel point, use the Gaussian function to analyze the distance between each pixel point and the current pixel point, and calculate the spatial proximity between each pixel point in the search window and the current pixel point.

[0027] Taking into account the self-similar nature of images, the redundant information in the image can be used to denoise the image, while retaining the detailed features of the image to the greatest extent possible.

[0028] Firstly, a similarity window and a search window are defined for each pixel in the image to analyze the distribution of similarities between pixels in a local range, so as to facilitate the subsequent accurate denoising of the pixel value of the central pixel.

[0029] It should be noted that the similarity window and the search window are respectively a square window centered at any pixel point, and the similarity window is smaller than the search window, and the similarity window slides in the search window.

[0030] Among them, the similarity window size is In this embodiment, the value of f is 4, that is, the size of the similarity window is 9×9; the search window size In this embodiment, s takes a value of 6, that is, the size of the search window is 13×13.

[0031] It is worth noting that when the pixels in the similarity window or search window exceed the image range, zero padding operation is performed on them.

[0032] Assume that the x coordinate of the current pixel is (k, l), and the y coordinate of a pixel in the search window of the current pixel is (i, j). The similarity between the two points is Depends on spatial proximity, dark channel value proximity, and lighting condition proximity.

[0033] When a pixel is far away from another pixel, the impact on the other pixel is small. Spatial proximity describes the difference in spatial position between two pixels. The distance between pixels can be analyzed by Gaussian function. The spatial proximity of the current pixel x and the pixel y in the search window is used to calculate the distance between the pixels. To express: Wherein, e is a natural constant, h is a smoothing parameter, which is used to control the attenuation degree of the Gaussian function. The larger the h is, the smoother the change of the Gaussian function is, and the higher the influence of the pixel point y on the denoising level of the current pixel point x is, but it will also cause image blur; the smaller the h is, the lower the influence of the pixel point y on the denoising level of the current pixel point x is, and the more edge detail components are retained, but too many noise points will remain. In this embodiment, the value of h is 1.

[0034] S3, obtaining the dark channel value of each pixel in the image and constructing a dark channel image; dividing all dark channel values ​​in the similarity window of each pixel in the dark channel image into orders, and analyzing the connected areas of different sizes and their occurrence times under each order of division, as well as the distance between the centroid of each connected area and the center of the similarity window, to construct the dust influence degree of the similarity window.

[0035] In real life, the images observed or collected are often not the true color of the object due to the influence of light intensity, dust, etc. When processing images, it is necessary to consider and eliminate the influence of these external factors, and then calculate the similarity between different pixels.

[0036] Considering that the observed or collected images are affected by dust and light, the similarity between two pixels can be judged by the similarity of the dark channel value and the light intensity of the image.

[0037] Color images all contain three channels, namely R, G, and B. In a clear, fog-free image, pixels in any local area except the sky area have at least one channel value that is very low. This is because dust, shadows, etc. have an impact on the object. The value of this channel is the dark channel value. The dark channel value of a pixel is equal to the minimum value of the minimum values ​​of each pixel in its local window in each channel, which is used to reflect the extent to which the pixel is affected by dust.

[0038] Accordingly, based on the dark channel prior theory, for any pixel in the image, the minimum value of the minimum values ​​of each pixel in each channel in the similarity window of any pixel is obtained as the dark channel value of any pixel.

[0039] The dark channel value of each pixel in the image is calculated according to the above formula to obtain a dark channel image.

[0040] Dust often appears in pieces and has certain regional characteristics. For the similarity window of each pixel in the dark channel image, the dark channel area size matrix and dark channel distance size matrix are constructed.

[0041] The size of the dark channel region size matrix is ​​P×Q, where P is the number of dark channel value orders in the similarity window. In this embodiment, the value is 32, that is, pixel values ​​0-255 are grouped into 8 pixels each and evenly mapped to dark channel orders 1-32. For example, 0-7 is mapped to order 1, 8-15 is mapped to order 2, and 248-255 is mapped to order 32. Q is the maximum size of the connected region with the same dark channel order in the similarity window, which is the size of the connected region with the same order. The elements in the dark channel region size matrix It represents the number of occurrences of connected regions with dark channel order p and size q in the similarity window.

[0042] The size of the dark channel distance size matrix is ​​P×Q×M, where M is the maximum number of connected regions with the same size in the similarity window, and the elements It represents the distance between the centroid of the mth connected region with dark channel order p and size q in the similarity window and the center of the similarity window.

[0043] Furthermore, by analyzing the connected regions of different sizes and their occurrence times at each order of division, as well as the distance between the centroid of each connected region and the center of the similar window, the dust influence degree of the similar window is constructed. , the calculation formula is: Where P is the number of dark channel value orders in the similar window, Q is the maximum size of the connected area with the same dark channel order in the similar window, M is the maximum number of connected areas with the same size in the similar window, p is the order p, q is the size of the connected area q, It represents the number of occurrences of the connected region with dark channel order p and size q in the similarity window. It represents the distance between the centroid of the mth connected region with dark channel order p and size q in the similarity window and the center of the similarity window.

[0044] It should be understood that the larger the p, the larger the order of the dark channel, indicating that it is more affected by dust; the larger the q, the larger the connected area of ​​the dark channel. The larger it is, the more times the connected area appears, indicating that the range affected by dust is wider; The larger it is, the closer the connected area is to the central pixel, which means the central pixel is more affected by the dust area.

[0045] For the connected regions in the dark channel image with larger dark channel order, larger connected region area, and closer to the center of the similar window, they are more affected by dust and should be given greater weight.

[0046] S4, obtaining the illumination component of each pixel in the image and constructing an illumination image; calculating the illumination influence of the similar window of each pixel in the illumination image according to the same calculation method as the dust influence of the similar window of each pixel in the dark channel image.

[0047] In real life, the images observed or collected are composed of illumination images and reflection images, and the color of an object is determined by the object's ability to reflect light, rather than the absolute value of the light intensity. In order to obtain the true color of the object, it is necessary to eliminate the impact of different lighting on the collected image information.

[0048] Based on Retinex theory, the illumination component of ambient light The original image and the Gaussian kernel can be used to approximate the convolution of the original image, so that the illumination image can be obtained. The value of each pixel in the illumination image is obtained by convolving the pixel value of the corresponding pixel with the Gaussian kernel, which is recorded as the illumination component of the corresponding pixel. In this embodiment, the Gaussian kernel size is set to 5×5. The process of convolving the pixel value with the Gaussian kernel to obtain the illumination component in the Retinex theory is a well-known technology and will not be repeated.

[0049] Similarly, according to the illumination image, the dust influence of the similar window of each pixel in the dark channel image is calculated. The same calculation method is used to calculate the illumination influence of the similar window of each pixel in the illumination image. .

[0050] S5, based on the dust influence and the illumination influence, determine the value of the central pixel point corresponding to the similar window position in the comprehensive distribution image; calculate the directional dispersion of the similar window by using the dispersion of the gradient amplitude of the value within the similar window of each pixel point in the comprehensive distribution image in different directional ranges; and analyze the similarity of the directional dispersion of the similar windows of any two pixel points in the comprehensive distribution image.

[0051] By combining the influence of dust and light, we can get the comprehensive distribution influence of a certain pixel. , comprehensive distribution influence It is the product of the dust influence and the light influence in the similar window corresponding to the pixel point.

[0052] The comprehensive distribution influence degree is calculated for each pixel in the image, and then the comprehensive distribution influence degrees of all pixels are combined to form a comprehensive distribution image according to the corresponding positions of the pixels in the image.

[0053] Since each pixel is affected by dust and light in different directions and intensities, that is, the gradient direction and amplitude are different, the HOG operator can be used to count the local gradient amplitude and direction of the comprehensive distribution image to form a histogram based on gradient characteristics.

[0054] In order to obtain the gradient histogram, the present embodiment first uses the Sobel operator to obtain the gradient direction and gradient magnitude of each pixel in the comprehensive distribution map. The Sobel operator is a well-known technology and will not be described in detail. In other embodiments of the present application, the Prewitt operator, Canny edge detection, etc. may also be used to obtain the gradient direction and gradient magnitude.

[0055] In order to facilitate the statistics of the gradient direction and gradient amplitude of the comprehensive distribution of the pixels in the similar window, the gradient direction range of 0-180 degrees is divided into N equal parts, that is, divided into N gradient direction ranges. In this embodiment, the value of N is 9, which are 0, 20, 40, ..., 160, respectively corresponding to [0, 20) degrees, [20, 40) degrees, ..., [160-180) degrees, and then the gradient amplitudes belonging to the same gradient direction range are accumulated and counted to obtain a gradient direction histogram, that is, a vector composed of 9 values. , n takes values ​​from 1 to 9, indicating a range of 9 gradient directions, Represents the gradient amplitude and value of the nth angle range, and normalizes it to , the directional dispersion of the similarity window can be expressed as LR: The LR value represents the comprehensive distribution, that is, the degree of dispersion of the distribution directions of dust and light. When there are more distribution directions, that is, the distribution of dust and light is more dispersed, the LR is larger; when the distribution direction is more singular, that is, the distribution of dust and light is more concentrated, the LR is smaller.

[0056] The result of negative correlation mapping of the difference in directional dispersion of similar windows of any two pixels in the comprehensive distribution image is used as the similarity F of similar windows of any two pixels in the comprehensive distribution image. It should be understood that the larger the result of negative correlation mapping, the more uniform the dust and light distribution directions in the similar windows of the two pixels are, which means that the surroundings of the two pixels have more similar features, and the higher the similarity of the similar windows of the two pixels.

[0057] Optionally, the negative correlation mapping can be implemented by negative linear mapping, negative exponential mapping, or setting adjustment parameters. Specifically, in this embodiment, the opposite number of the absolute value of the difference between the directional dispersions of the similarity windows of the two pixel points is used as the exponent of an exponential function with the natural constant e as the base, and the calculation result of the exponential function is used as the similarity of the similarity windows of the two pixel points.

[0058] S6, combining the spatial proximity of each pixel point in the search window to the current pixel point, and the similarity of the directional dispersion of the similarity windows of the two corresponding pixel points in the comprehensive distribution image, calculate the weight of each pixel point in the search window to the current pixel point; based on the weight, perform weighted summation on the pixel values ​​of all pixels in the search window to obtain the denoised pixel value of the current pixel point, thereby constructing a denoised image.

[0059] In this embodiment, the spatial proximity between the current pixel point x and the pixel point y in the search window of the current pixel point in the image is used to determine the spatial proximity between the current pixel point x and the pixel point y in the search window. , and the similarity of the similarity windows of the two corresponding pixels in the comprehensive distribution image , calculate the similarity between the pixel y in the search window and the current pixel x , That is, the similarity between the pixel y in the search window and the current pixel x is analyzed by the distance information between the two pixels and the similar features distributed around the two pixels.

[0060] Furthermore, after calculating the similarity between each pixel in the search window and the current pixel, normalization can be performed to perform a weighted summation on the pixel values ​​of each pixel. Based on this, the weight of the pixel y in the search window to the current pixel x is calculated. ; ; In the formula, is the sum of the similarities between all pixels in the search window and the current pixel x. The larger the weight, the greater the influence of pixel y on the denoising of the current pixel x.

[0061] At this point, the weight of each pixel in the search window to the current pixel can be calculated.

[0062] In this application, the index construction flow chart of the weight of each pixel point in the search window to the current pixel point is as shown in the attached figure. Figure 2 shown.

[0063] Then, based on the weight of each pixel in the search window to the current pixel, the pixel values ​​of all pixels in the search window are weighted summed to obtain the pixel value of the current pixel after denoising. The pixel values ​​of all pixels in the image after denoising are calculated to construct the denoised image.

[0064] The pixel value of each pixel in the image is determined by the weighted sum of all pixel values ​​in its search window, and its weight is not unique. It is determined by the similarity between two pixels. The pixel values ​​around the current pixel are used to determine the final output value of this pixel, thereby completing the denoising of the image.

[0065] After removing noise such as dust and light from the image, the denoised image is further processed for target recognition and tracking. By identifying specific targets (such as miners and equipment) and continuously tracking them through multi-target tracking (MOT), abnormal behaviors or potential dangerous areas can be accurately detected, thereby improving the safety and standardization of production. The specific multi-target tracking (MOT) can be implemented by combining Kalman filtering with Hungarian algorithms (such as SORT, DeepSORT algorithms, etc.), and the above algorithms are all well-known technologies and will not be repeated here. The specific settings are set by the implementers.

[0066] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0067] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0068] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not invented by the present application.

[0069] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A video monitoring method for underground coal mines, characterized in that: The method comprises the following steps: A similarity window and a search window are defined for each pixel point in the video image of the underground coal mine; for each pixel point in the search window of the current pixel point, the distance between each pixel point and the current pixel point is analyzed by using a Gaussian function, and the spatial proximity between each pixel point in the search window and the current pixel point is calculated; Obtain the dark channel value of each pixel in the image and construct a dark channel image; divide all dark channel values ​​in the similarity window of each pixel in the dark channel image into orders, and analyze the connected areas of different sizes and their occurrence times under each order of division, as well as the distance between the centroid of each connected area and the center of the similarity window, to construct the dust influence degree of the similarity window; Obtain the illumination component of each pixel in the image and construct an illumination image; calculate the illumination influence of the similar window of each pixel in the illumination image in the same way as the dust influence of the similar window of each pixel in the dark channel image; Based on the dust influence and the illumination influence, the value of the central pixel point corresponding to the similar window position in the comprehensive distribution image is determined; the directional dispersion of the similar window is calculated by using the dispersion of the gradient amplitude of the value in the similar window of each pixel point in the comprehensive distribution image in different direction ranges; and the similarity of the directional dispersion of the similar windows of any two pixel points in the comprehensive distribution image is analyzed; The weight of each pixel in the search window to the current pixel is calculated by combining the spatial proximity of each pixel in the search window to the current pixel and the similarity of the directional dispersion of the similar windows of the two corresponding pixels in the comprehensive distribution image; based on the weight, the pixel values ​​of all pixels in the search window are weighted summed to obtain the denoised pixel value of the current pixel, thereby constructing a denoised image.

2. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S2, the similarity window and the search window are respectively a square window centered on any pixel point, and the similarity window is smaller than the search window, and the similarity window slides in the search window.

3. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S3, the dark channel value of each pixel is determined by the minimum value of the minimum values ​​of each pixel in each channel in the similarity window corresponding to the pixel.

4. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S4, the illumination component of each pixel in the illumination image is obtained by convolving the pixel value with a preset Gaussian kernel.

5. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S3, the dust influence degree of the similar window is constructed by: The dust influence degree of the similar window is recorded as , the calculation formula is: Where P is the number of dark channel value orders in the similar window, Q is the maximum size of the connected area with the same dark channel order in the similar window, M is the maximum number of connected areas with the same size in the similar window, p is the order p, q is the size of the connected area q, It represents the number of occurrences of the connected region with dark channel order p and size q in the similarity window. It represents the distance between the centroid of the mth connected region with dark channel order p and size q in the similarity window and the center of the similarity window.

6. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S5, the product of the dust influence degree of the similar window of each pixel point in the dark channel image and the illumination influence degree of the similar window of the corresponding pixel point in the illumination image is used as the value of the corresponding pixel point in the comprehensive distribution image.

7. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S5, the calculation method of the directional dispersion of the similarity window is: Obtain the gradient direction and gradient amplitude of each pixel in the comprehensive distribution map; The gradient direction is divided into several gradient direction ranges; the gradient amplitudes belonging to the same gradient direction range are accumulated and counted to obtain a gradient direction histogram; The square sum of the accumulated gradient amplitudes in all gradient direction ranges in the gradient direction histogram is taken as the directional dispersion of the similarity window.

8. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S5, the similarity of the directional dispersion of similar windows of any two pixels in the comprehensive distribution image is determined by the result of negative correlation mapping of the difference in the directional dispersion of the similar windows of the two pixels.

9. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: In step S6, the weight of each pixel in the search window to the current pixel is calculated as follows: The spatial proximity of each pixel in the search window to the current pixel is added to the similarity of the directional dispersion of the similar windows of the two corresponding pixels in the comprehensive distribution image to obtain the weight of each pixel in the search window to the current pixel.

10. A method for underground video monitoring in a coal mine according to claim 1, characterized in that: The method further includes performing target recognition and tracking processing on the denoised image.

Images