Remote mining area image processing method and system

Abstract

The invention provides a remote mining area image processing method and system, and belongs to the technical field of image processing, and the method comprises the steps: inputting a target environment parameter into a target model, and determining a noise reduction parameter; determining a target noise reduction algorithm based on the noise reduction parameters; processing the target data based on a target noise reduction algorithm to obtain mining area data, and sending the mining area data to display equipment of a mining area monitoring center; wherein the target environment parameter is an environment parameter of a target area corresponding to the target data, and the target data comprises monitoring image data of the target area. According to the remote mining area image processing method and system provided by the invention, the mining area image processing effect can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of image processing, and more particularly, relates to a method and system for remote mining area image processing. Background Art

[0002] In the modern mining industry, remote mining area monitoring systems have become an important means to ensure production safety and improve operational efficiency. Through monitoring devices deployed throughout the mining area, a large amount of monitoring image and video data can be collected in real time, providing key basis for the management and decision-making of the mining area. However, due to the characteristics of the mining area itself, the environmental differences in different regions of the mining area are relatively large. Secondly, the progress and operation types in different regions are different, further resulting in the ever-changing environment in each region of the mining area.

[0003] In this regard, traditional image processing algorithms use fixed parameter settings when processing images. However, in the complex and ever-changing mining area environment, the image noise characteristics at different times and positions vary greatly. The noise reduction algorithm with fixed parameters cannot automatically adjust the parameters according to the environmental changes, resulting in poor processing effects of mining area monitoring images.

[0004] Therefore, a mining area image processing method with good effects and high reliability is needed. Summary of the Invention

[0005] The purpose of the present disclosure is to provide a method and system for remote mining area image processing, so as to improve the processing effect of mining area images by adjusting the parameters of image processing according to environmental parameters.

[0006] In the first aspect of the embodiments of the present disclosure, a method for remote mining area image processing is provided, including: Inputting target environmental parameters into a target model to determine noise reduction parameters; Determining a target noise reduction algorithm based on the noise reduction parameters; Processing target data based on the target noise reduction algorithm to obtain mining area data, and sending the mining area data to a display device of a mining area monitoring center; wherein, the target environmental parameters are the environmental parameters of the target area corresponding to the target data, and the target data includes monitoring image data of the target area.

[0007] In the second aspect of the embodiments of the present disclosure, a system for remote mining area image processing is provided, including: A parameter determination module, configured to input target environmental parameters into a target model to determine noise reduction parameters; An algorithm determination module, configured to determine a target noise reduction algorithm based on the noise reduction parameters; A data processing module is configured to process target data based on a target noise reduction algorithm to obtain mine area data, and send the mine area data to a display device of a mine area monitoring center; wherein, the target environmental parameter is the environmental parameter of the target area corresponding to the target data, and the target data includes monitoring image data of the target area.

[0008] In a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned remote mine area image processing method are implemented.

[0009] In a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned remote mine area image processing method are implemented.

[0010] The beneficial effects of the remote mine area image processing method and system provided by the embodiments of the present disclosure are as follows: By introducing target environmental parameters to determine noise reduction parameters, the present disclosure can perform adaptive adjustment for the mine area environments in different regions and at different times, improving the accuracy and practicability of image processing. By dynamically selecting the most suitable noise reduction algorithm for the current environment, the present disclosure can reduce image noise and improve the effect and reliability of remote mine area image processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of a remote mine area image processing method provided by an embodiment of the present disclosure; Figure 2 It is a structural block diagram of a remote mine area image processing system provided by an embodiment of the present disclosure; Figure 3 It is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should clearly understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0014] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0015] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a remote mining area image processing method provided for an embodiment of the present disclosure. The method includes: S101: Input the target environmental parameters into the target model to determine the noise reduction parameters.

[0016] In this embodiment, the target environmental parameters are the environmental parameters of the target area corresponding to the target data. The target data is the monitoring image data of the target area, and the target area is an area in the mining area. Since the environmental differences in each area of the mining area are relatively large, and secondly, due to the different construction operation environments and operation types in different mining area areas, the environmental difference degree in each area of each mining area is further exacerbated. For example, in some mine areas, due to the relative enclosure of the underground operation space, the dust concentration is extremely likely to rise sharply during the mining process, and at the same time, the humidity will also vary depending on the underground water source and ventilation conditions; the light intensity will also vary depending on the window opening conditions in each mining area area. The higher the dust concentration, the more noise in the collected data, and the worse the data quality.

[0017] The target environmental parameters can be parameters such as dust concentration, humidity, or light intensity that affect the acquisition and processing of images. The target data can be images or videos collected through monitoring. The target area can be a coal storage area, a gangue stacking area, a mine, a beneficiation area, a production area, etc. The target model can be a machine learning model obtained through training. In this embodiment, the basic model of the target model can be a support vector machine model. The target model is trained with a dataset composed of a preset number of environmental parameters and their corresponding standard noise reduction parameters. The preset number refers to the number that can satisfy the support vector machine model for learning and verification, which can be set according to experience or determined according to the number of data in the training dataset when solving similar problems. The standard noise reduction parameters can be understood as the relatively optimal or optimal noise reduction parameters corresponding to the influence of this environmental parameter. The noise reduction parameters are the parameters in the noise reduction algorithm or noise reduction model, and the noise reduction algorithm can be a bilateral filtering algorithm.

[0018] It should be noted that in this embodiment, the target environmental parameters are the environmental parameters of the target area during the process of collecting target data, and the target data can be collected by the monitoring devices installed in various areas of the mining area.

[0019] S102: Determine the target noise reduction algorithm based on the noise reduction parameters.

[0020] In this embodiment, the noise reduction parameters can be some or all of the parameters in the bilateral filtering algorithm. In this embodiment, the noise reduction parameters are selected as the spatial domain kernel radius, the standard deviation of the gray value range, and the standard deviation of the spatial domain in the bilateral filtering algorithm parameters. The target noise reduction algorithm is the bilateral filtering algorithm.

[0021] Applied in this scenario, the reasons for selecting the above three parameters are as follows: The spatial domain kernel radius determines the pixel neighborhood range considered during filtering. In the mining area monitoring images, noise may be distributed in areas of different sizes. By adjusting the spatial domain kernel radius, the suppression ability of the filtering algorithm for different scale noises can be controlled. A larger radius can effectively remove large-area noises, but may blur the image details. A smaller radius can better preserve the edge and detail information of the image and is suitable for the case where the noise is more dispersed.

[0022] The standard deviation of the gray value range reflects the degree of change of the pixel gray values in the image. The gray values of the mining area monitoring images may vary due to factors such as lighting conditions and equipment characteristics. When the standard deviation of the gray value range is large, it indicates that the gray value change in the image is relatively intense. At this time, the algorithm will pay more attention to processing pixels with large gray value differences to balance the overall gray distribution of the image and reduce the noise impact caused by factors such as uneven lighting. When the standard deviation is small, the algorithm will tend to preserve the original gray details of the image and avoid losing image information due to excessive smoothing.

[0023] The standard deviation of the spatial domain describes the distribution of pixels in space. In the mining area environment, different regions of the image may have different spatial characteristics, such as equipment and terrain. A larger standard deviation of the spatial domain means that the algorithm will pay more attention to the spatial relationship between pixels and has a better suppression effect on noises widely distributed in space, and can repair some irregular noise areas in the image to a certain extent. A smaller standard deviation of the spatial domain makes the algorithm focus more on the processing of local pixels and helps to preserve the fine structure and texture information in the image.

[0024] Therefore, in this embodiment, the spatial domain kernel radius, the standard deviation of the gray value range, and the standard deviation of the spatial domain in the bilateral filtering algorithm parameters are selected as the noise reduction parameters. After obtaining the noise reduction parameters, substitute them into the bilateral filtering algorithm, and the remaining parameters can be set according to the reference values of the bilateral filtering algorithm, and finally the target noise reduction algorithm is obtained.

[0025] S103: Process the target data based on the target noise reduction algorithm to obtain mine area data, and send the mine area data to the display device of the mine area monitoring center; wherein, the target environmental parameter is the environmental parameter of the target area corresponding to the target data, and the target data is the monitoring image data of the target area.

[0026] In this embodiment, it can be known from the foregoing description that the noise reduction parameter of the target noise reduction algorithm is determined based on the target environmental parameter, and the target environmental parameter is the environmental parameter of the target area corresponding to the target data. Therefore, the target noise reduction algorithm is a processing algorithm applicable to the target data. The target data is the monitoring image data of the target area, such as a monitoring image or a monitoring video. The mine area data is the target data after noise reduction processing. Therefore, the mine area data can also be an image or a video. After obtaining the mine area data, send the mine area data to the display device of the mine area monitoring center so that relevant personnel can understand the real-time image data of each area in the mine area.

[0027] It can be concluded from the above that the present disclosure determines the noise reduction parameter by introducing the target environmental parameter, can perform adaptive adjustment for the mine area environment in different regions and at different times, and improves the accuracy and practicability of image processing. The present disclosure can reduce image noise and improve the effect and reliability of remote mine area image processing by dynamically selecting the most suitable noise reduction algorithm for the current environment.

[0028] It can be known from S101 that the target model is trained by a data set composed of a preset number of environmental parameters and their corresponding standard noise reduction parameters. Specifically, it can be explained as: the target model is a support vector machine model; Before inputting the target environmental parameter into the target model to determine the noise reduction parameter, it further includes: Train the support vector machine model based on the first data set to obtain the target model; wherein, the data in the first data set is the historical environmental parameter and the corresponding standard noise reduction parameter, and the standard noise reduction parameter is determined by optimizing the initial noise reduction parameter based on the particle swarm optimization algorithm.

[0029] In this embodiment, the historical environmental parameter refers to the environmental parameter in the historical mine area. For example, the dust concentration, humidity and light intensity. The standard noise reduction parameter is part or all of the parameters in the relatively better or optimal noise reduction algorithm corresponding to this environmental parameter. Multiple historical environmental parameters and their corresponding standard noise reduction parameters form the first data set, and the quantity and quality of the data in the first data set should meet the requirements for training and verification of the support vector machine model.

[0030] Since the process of corresponding a standard noise reduction parameter to each combination of environmental parameters is time-consuming and laborious, in this embodiment, the particle swarm optimization algorithm is used to optimize the initial noise reduction parameters to obtain the standard noise reduction parameters. The essence of the initial noise reduction parameters is also the spatial domain kernel radius, the standard deviation of the gray value range, and the standard deviation of the spatial domain in the bilateral filtering algorithm. The initial parameter values can be the default values of the bilateral filtering algorithm.

[0031] Specifically, the process of determining the standard noise reduction parameters based on the particle swarm optimization algorithm includes: Determining the particle dimension of the particle swarm optimization algorithm based on the parameters of the noise reduction algorithm; Determining the fitness function of the particle swarm optimization algorithm based on the environmental parameters; Performing iterative calculations on the initial noise reduction parameters based on the particle dimension and the fitness function until the differences between consecutive fitness function values are all less than the first threshold or the number of iterations reaches the first number to obtain the standard noise reduction parameters.

[0032] In this embodiment, the particle dimension in the particle swarm optimization algorithm can be understood as the position coordinate dimension of the particle. The position of each particle corresponds to a solution. Therefore, the particle dimension should be consistent with the parameters of the noise reduction algorithm. The parameters of the selected noise reduction algorithm mentioned above are the spatial domain kernel radius, the standard deviation of the gray value range, and the standard deviation of the spatial domain. Therefore, in this embodiment, the particle dimension in the particle swarm optimization algorithm is three-dimensional and can be expressed as [spatial domain kernel radius, standard deviation of gray value range, standard deviation of spatial domain].

[0033] Since the environmental factors (dust concentration, humidity, light intensity) affect the image quality, the influence of the environmental factors should be added to the fitness function. For example, the fitness function is: , where represents the fitness function value, is the weight coefficient corresponding to the peak signal-to-noise ratio, is the weight coefficient corresponding to the structural similarity index, , is the peak signal-to-noise ratio, is the structural similarity index, is the weight coefficient corresponding to the th environmental parameter, is the th normalized value of the environmental parameter. For example, represents the normalized value corresponding to the dust concentration, represents the normalized value corresponding to the humidity, represents the normalized value corresponding to the light intensity. represents the weight corresponding to the dust concentration, represents the weight corresponding to the humidity, Represents the weight corresponding to the light intensity, , and The values can be determined based on experience or can be determined based on the degree of influence of each environmental parameter on the image quality.

[0034] Specifically, the scores of each environmental parameter can be calculated based on the random forest algorithm, and the scores of each environmental parameter are normalized to obtain the weights corresponding to each environmental parameter. Or the correlation can be determined by calculating the Pearson correlation coefficient and then normalized to obtain the weights corresponding to each environmental parameter. and Can be determined according to usage preferences, or can both be set to 0.5.

[0035] The logic of the fitness function is as follows: Calculate the basic quality score of the image. Among them, PSNR is used to measure the distortion degree of the image, and the higher it is, the better the denoising or enhancement effect; SSIM takes into account the brightness, contrast and structural information of the image, and the closer it is to 1, the higher the image quality and the more in line with the human eye's perception of the image quality.

[0036] Calculate the comprehensive influence of environmental factors on the image quality. Convert the actual values of environmental factors to the interval [0, 1] for unified measurement and comparison. Is used to adjust the basic image quality score, that is, if the environmental factors have a greater impact on the image quality, then The value will be close to 1, Will be smaller, thus reducing the basic image quality score. On the contrary, if the environmental factors are more ideal and have less impact on the image quality, Is close to 1, and the basic image quality score is less affected, so that the advantages and disadvantages of the image preprocessing algorithm parameters can be reasonably evaluated according to different environmental conditions, guiding the particle swarm algorithm to find the most suitable parameter combination in the current environment, making the fitness function more in line with the requirements of the application scenario in the mining area.

[0037] The iteration termination condition of the particle swarm optimization algorithm can be that the difference between consecutive multiple fitness function values is less than the first threshold or the number of iterations reaches the first number. The specific values of the first number and consecutive multiple can be determined based on experience. Generally, the first number can be set to 150 - 250 times, and multiple can be set to 3 - 6. When the iterative calculation ends, the noise reduction parameters corresponding to the global optimal position are the standard noise reduction parameters.

[0038] In the iterative optimization process of the particle swarm optimization algorithm, its inertia weight and learning factor are parameters that control the iterative calculation direction of each particle. In this embodiment, the inertia weight of the particle swarm optimization algorithm can be determined based on the number of iterations. That is, the inertia weight of the particle swarm optimization algorithm is determined based on the number of iterations; the iterative calculation direction of the particle swarm optimization algorithm is controlled based on the inertia weight and the learning factor.

[0039] Specifically, the inertia weight of the particle swarm optimization algorithm is determined based on the first formula and the number of iterations. The first formula can be: , where is the inertia weight at the -th iteration. is the maximum value of the inertia weight, which can generally be set to 0.9, giving the particles a relatively large global search ability at the beginning of the iteration. is the minimum value of the inertia weight, usually set to 0.4, making the particles focus on local search in the later stage of the iteration. is the first number, is the current number of iterations, represents the natural constant.

[0040] The logic of the first formula is: The cosine function is used to control the basic change trend of the inertia weight. At the beginning of the iteration , , and at this time the inertia weight is close to , and the particles have a relatively strong global search ability. As the number of iterations increases, the value of the cosine function gradually decreases, and the inertia weight also decreases accordingly. When the iteration reaches half , , and the inertia weight is at the intermediate value. In the later stage of the iteration, the inertia weight continues to decrease and approaches , and the particles are more inclined to local search.

[0041] is an exponential decay function used to fine-tune the above basic change trend. At the beginning of the iteration, the value of the exponential function is close to 0, which will make the decrease rate of the inertia weight relatively slow, ensuring that the particles have enough time for global search. As the number of iterations increases, the value of the exponential function gradually increases, and the decrease rate of the inertia weight accelerates, so as to turn to local search faster in the later stage of the iteration.

[0042] The inertia weight can be determined according to the number of iterations through the first formula. The learning factor includes a swarm learning factor and an individual learning factor. The swarm learning factor and the individual learning factor can be set according to the reference values of the particle swarm optimization algorithm. For example, both can be set to 2.

[0043] It can be concluded from the above that by introducing a support vector machine model and training based on historical environmental parameters and corresponding standard noise reduction parameters, the present disclosure can determine the noise reduction parameters applicable to different mining area environments. The standard noise reduction parameters are optimized by the particle swarm optimization algorithm, ensuring the accuracy of the noise reduction algorithm in different environments and improving the efficiency and accuracy of remote mining area image processing. By adjusting the inertia weight, the present disclosure further optimizes the search performance of the particle swarm optimization algorithm, making the optimization process more reliable, and thus obtaining more accurate standard noise reduction parameters, thereby improving the training effect of the support vector machine model and enhancing the effect and reliability of mining area image processing.

[0044] The purpose of the foregoing particle swarm optimization algorithm is to determine the standard noise reduction parameters corresponding to the historical environmental parameters, that is, the better or optimal noise reduction parameters corresponding to each environmental parameter combination. The target model can be obtained by training the support vector machine model based on the data set (the first data set) composed of the historical environmental parameters and the corresponding standard noise reduction parameters. The process of training the support vector machine model in this embodiment is described as follows: In an embodiment of the present disclosure, the kernel function of the support vector machine model is a Gaussian kernel function; Training the support vector machine model based on the first data set includes: In response to the concentration value of the standard noise reduction parameters being less than the first concentration value, reducing the reference value of the penalty parameter based on the first penalty step size to obtain the target penalty parameter of the Gaussian kernel function; In response to the concentration value of the standard noise reduction parameters being greater than the second concentration value, increasing the reference value of the penalty parameter based on the second penalty step size to obtain the target penalty parameter of the Gaussian kernel function; Training the support vector machine model based on the Gaussian kernel function with the determined target penalty parameter and the first data set; Wherein, the first concentration value is less than the second concentration value.

[0045] In this embodiment, the support vector machine model uses a Gaussian kernel function as the kernel function to map the input data to a high-dimensional space for better processing of non-linear problems.

[0046] The concentration value can be determined by calculating the variance or information entropy of the data. Taking the variance as an example, the variance can measure the dispersion degree of the data. The smaller their values are, the more concentrated the data is. Therefore, the variance and the concentration value should be related but opposite. Therefore, the concentration value can be obtained through a simple mapping relationship or a linear formula, which will not be elaborated here.

[0047] When the concentration value of the standard noise reduction parameter is less than the first concentration value, it means that the distribution of the standard noise reduction parameter in the data space is relatively dispersed. In this case, in order to prevent the model from overly emphasizing the accurate classification of each sample (because there are some outliers or noise points due to the dispersed data), the reference value of the penalty parameter can be reduced based on the first penalty step size, so as to obtain the target penalty parameter of the Gaussian kernel function. A smaller penalty parameter will make the model more tolerant of errors in the training data, pay more attention to the generalization ability, and avoid overfitting.

[0048] Conversely, when the concentration value of the standard noise reduction parameter is greater than the second concentration value, it indicates that the distribution of the standard noise reduction parameter in the data space is relatively concentrated. At this time, the reference value of the penalty parameter is increased based on the second penalty step size to obtain the target penalty parameter. A larger penalty parameter will make the model more strictly require the accurate classification of each sample, minimize the training error, and improve the accuracy of model training. The first penalty step size and the second penalty step size can be determined based on experience or based on the concentration value. Specifically, the first penalty step size and the second penalty step size can be determined based on the second formula: , where represents the first penalty step size or the second penalty step size. When , represents the first penalty step size. When , represents the second penalty step size. represents the concentration value. is the first concentration value. The second concentration value. is the preset minimum step size. is the preset maximum step size. The first concentration value and the second concentration value can be preset based on experience.

[0049] When is less than , the second formula tends to produce a smaller step size, approaching . When is greater than , the second formula tends to produce a larger step size, approaching . Through the above description, the first penalty step size or the second penalty step size can be obtained. If the concentration value of the standard noise reduction parameter is between the first concentration value and the second concentration value, then the reference value of the penalty parameter can be not adjusted. That is, in response to the concentration value of the standard noise reduction parameter being greater than or equal to the second concentration value and the concentration value of the standard noise reduction parameter being less than or equal to the first concentration value, the reference value of the penalty parameter is used as the penalty parameter of the Gaussian kernel function. The reference value of the penalty parameter can be the default value of the support vector machine model.

[0050] As can be seen from the above, the present disclosure evaluates the distribution state of the standard noise reduction parameters by introducing the concentration value, and dynamically adjusts the penalty parameter of the Gaussian kernel function in the support vector machine model according to its distribution state. This enables the support vector machine model to better adapt to the characteristics of different data sets, improves the performance and stability of the model, and further enhances the effect and reliability of mine area image processing.

[0051] In an embodiment of the present disclosure, the kernel function of the support vector machine model is a Gaussian kernel function; Training the support vector machine model based on the first data set includes: Identifying the first scatter plot based on the first neural network model; In response to the distribution of the standard noise reduction parameters in the data space satisfying the first condition, reducing the reference value of the kernel coefficient based on the first kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; In response to the distribution of the standard noise reduction parameters in the data space satisfying the second condition, increasing the reference value of the kernel coefficient based on the second kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; Training the support vector machine model based on the Gaussian kernel function with the determined target kernel coefficient and the first data set; Wherein, the first neural network model is determined based on a certain number of scatter plots and their corresponding distribution results, the first scatter plot is the scatter plot of the distribution of the standard noise reduction parameters in the data space, and the first condition and the second condition are different.

[0052] In this embodiment, in addition to the foregoing penalty parameter, the support vector machine model also has a kernel function. The kernel coefficient determines the distribution of data in the high-dimensional space. If the data distribution of the noise reduction algorithm parameters presents a complex non-linear structure in the low-dimensional space, a larger kernel coefficient may be required to map the data to a higher-dimensional space so that the support vector machine model can better perform classification or regression; if the data distribution is relatively simple and has good linear separability, a smaller kernel coefficient may enable the support vector machine model to achieve better results.

[0053] Therefore, in this embodiment, the first neural network model can be used to identify and process the scatter plot of the distribution of the standard noise reduction parameters in the data space, and determine whether the distribution of the standard noise reduction parameters in the data space satisfies the first condition, and whether the distribution of the standard noise reduction parameters in the data space satisfies the second condition; the first condition is the appearance of complex non-linear features, and the second condition is the appearance of simple linear or simple non-linear features.

[0054] The first neural network model is determined based on a certain number of scatter plots and their corresponding distribution results. The certain number refers to the amount of data sufficient for training the first neural network model, which can be a preset value. The first kernel coefficient step size and the second kernel coefficient step size can be determined based on experience or during the experimental process. The reference value of the kernel coefficient is the default value of the support vector machine model.

[0055] If the first scatter plot satisfies neither the first condition nor the second condition, the reference value of the kernel coefficient may not be adjusted. That is, in response to the distribution of the standard noise reduction parameter in the data space not satisfying the first condition and the second condition, the reference value of the kernel coefficient is used as the target kernel coefficient of the Gaussian kernel function.

[0056] It can be concluded from the above that the present disclosure improves the classification and regression performance of the support vector machine model by introducing the first neural network model to identify the scatter plot of the distribution of the standard noise reduction parameter in the data space and dynamically adjusting the kernel coefficient of the Gaussian kernel function in the support vector machine model according to the identification result, thereby improving the effect and reliability of mine area image processing.

[0057] In an embodiment of the present disclosure, the monitored image data includes: monitored images and monitored videos; The remote mine area image processing method further includes: In response to the target data being a monitored image of the target area, the environmental parameters of the target area when the target data is collected are used as the target environmental parameters; In response to the target data being a monitored video of the target area and the change rate of the environmental parameters of the target area within the target time period being less than the first threshold, the environmental parameters at any moment within the target time period are used as the target environmental parameters; In response to the target data being a monitored video of the target area and the change rate of the environmental parameters of the target area within the target time period being greater than or equal to the first threshold, the environmental parameters at each moment within the target time period are used as the target environmental parameters; Wherein, the start time of the target time period is the start time of collecting the target data, and the end time of the target time period is the end time of collecting the target data.

[0058] In this embodiment, the change rate of the environmental parameters can be determined by calculating the ratio of the change amount of each environmental parameter within the target time period to the duration of the target time period. The change rate can be calculated separately for each environmental parameter and weighted, and the weights can be evenly distributed or set according to preferences.

[0059] Considering the actual application scenarios in the mining area, the target data collected exists in two forms, namely single surveillance images and continuous surveillance videos. Due to the emphasis on safety in the mining area (such as clearly monitoring the operation status of equipment and personnel activities in the mining area to prevent accidents) and the high requirements for data visibility (ensuring that the images or videos are clear for staff to accurately judge the situation), different processing methods need to be set according to different situations of the target data to determine the target environmental parameters, so as to better perform image processing.

[0060] When the target data is a surveillance image of the target area, the processing method is relatively simple. The environmental parameters of the target area when this surveillance image is collected, such as the dust concentration, humidity, light intensity, etc. at that time, are directly used as the target environmental parameters. Because a single image only corresponds to a specific acquisition moment, the environmental parameters at this moment can reflect the environmental conditions affecting the image quality at that time, and based on this, the parameters required for subsequent image processing are determined.

[0061] If the target data is a surveillance video of the target area, and within the target time period (that is, from the start time to the end time of collecting the surveillance video), the change rate of the environmental parameters of the target area is less than a pre-set first threshold. That is, during this video collection period, the environment is relatively stable and changes little. Therefore, at this time, the environmental parameters at any moment within the target time period can be used as the target environmental parameters. This is because in the case of a stable environment, the environmental parameters at any moment can represent the environmental conditions of the entire time period. Selecting the parameters at any moment can not only meet the requirements of image processing but also simplify the processing process and reduce the amount of calculation.

[0062] When the target data is a surveillance video, and the change rate of the environmental parameters of the target area within the target time period is greater than or equal to the first threshold, it indicates that the environment changes significantly during the video collection process. In this case, in order to more accurately process each frame of the video (because the environmental changes at different times will have different impacts on the image quality), the environmental parameters at each moment within the target time period need to be used as the target environmental parameters. This can perform more precise image processing for the specific environmental conditions of each frame of the image (such as determining appropriate noise reduction parameters, etc.) to ensure the overall quality and visibility of the video, meeting the high requirements of the mining area for safety and data visibility. The target time period can be preset according to the actual needs of the mining area, and the first threshold is determined during the experiment or set according to experience.

[0063] From the above, it can be concluded that the present disclosure introduces the environmental parameter change rate and the determination method of the target environmental parameters, enhancing the adaptability and accuracy of image processing, optimizing the processing process, improving the calculation efficiency, meeting the high requirements of the mining area for safety and data visibility, and enhancing the effect of remote mining area image processing.

[0064] The remote mining area image processing method corresponding to the above embodiment Figure 2 is a structural block diagram of a remote mining area image processing system provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 , the remote mining area image processing system 20 includes: a parameter determination module 21, an algorithm determination module 22, and a data processing module 23.

[0065] Among them, the parameter determination module 21 is configured to input target environmental parameters into a target model to determine noise reduction parameters; The algorithm determination module 22 is configured to determine a target noise reduction algorithm based on the noise reduction parameters; The data processing module 23 is configured to process target data based on the target noise reduction algorithm to obtain mining area data, and send the mining area data to a display device of a mining area monitoring center; wherein, the target environmental parameters are environmental parameters of a target area corresponding to the target data, and the target data includes monitoring image data of the target area.

[0066] In an embodiment of the present disclosure, the target model is a support vector machine model; The remote mining area image processing system 20 further includes: a model training module, configured to train the support vector machine model based on a first data set to obtain a target model before inputting the target environmental parameters into the target model to determine the noise reduction parameters; wherein, the data in the first data set are historical environmental parameters and corresponding standard noise reduction parameters, and the standard noise reduction parameters are determined by optimizing initial noise reduction parameters based on a particle swarm optimization algorithm.

[0067] In an embodiment of the present disclosure, the remote mining area image processing system 20 further includes: a standard noise reduction parameter determination module, configured to determine the particle dimension of the particle swarm optimization algorithm based on the parameters of the noise reduction algorithm; Determine the fitness function of the particle swarm optimization algorithm based on the environmental parameters; Perform iterative calculation on the initial noise reduction parameters based on the particle dimension and the fitness function until the difference between consecutive fitness function values is less than a first threshold or the number of iterations reaches a first number to obtain the standard noise reduction parameters.

[0068] In an embodiment of the present disclosure, the remote mining area image processing system 20 further includes: an iterative calculation control module, configured to determine the inertia weight of the particle swarm optimization algorithm based on the number of iterations; Control the iterative calculation direction of the particle swarm optimization algorithm based on the inertia weight and the learning factor.

[0069] In an embodiment of the present disclosure, the kernel function of the support vector machine model is a Gaussian kernel function; The model training module is specifically configured to, in response to the concentration value of the standard noise reduction parameter being less than the first concentration value, reduce the reference value of the penalty parameter based on the first penalty step size to obtain the target penalty parameter of the Gaussian kernel function; In response to the concentration value of the standard noise reduction parameter being greater than the second concentration value, increase the reference value of the penalty parameter based on the second penalty step size to obtain the target penalty parameter of the Gaussian kernel function; Train the support vector machine model based on the Gaussian kernel function with the determined target penalty parameter and the first data set; Wherein, the first concentration value is less than the second concentration value.

[0070] In an embodiment of the present disclosure, the kernel function of the support vector machine model is a Gaussian kernel function; The model training module is specifically further configured to identify the first scatter plot based on the first neural network model; In response to the distribution of the standard noise reduction parameter in the data space satisfying the first condition, reduce the reference value of the kernel coefficient based on the first kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; In response to the distribution of the standard noise reduction parameter in the data space satisfying the second condition, increase the reference value of the kernel coefficient based on the second kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; Train the support vector machine model based on the Gaussian kernel function with the determined target kernel coefficient and the first data set; Wherein, the first neural network model is determined based on a certain number of scatter plots and their corresponding distribution results, the first scatter plot is the scatter plot of the distribution of the standard noise reduction parameter in the data space, and the first condition and the second condition are different.

[0071] In an embodiment of the present disclosure, the monitored image data includes: monitored images and monitored videos; The remote mining area image processing system 20 further includes: a target environmental parameter determination module, configured to, in response to the target data being a monitored image of the target area, use the environmental parameters of the target area when the target data is collected as the target environmental parameters; In response to the target data being a monitored video of the target area and the environmental parameter change rate of the target area within the target time period being less than the first threshold, use the environmental parameters at any moment within the target time period as the target environmental parameters; In response to the target data being a monitored video of the target area and the environmental parameter change rate of the target area within the target time period being greater than or equal to the first threshold, use the environmental parameters at each moment within the target time period as the target environmental parameters; Wherein, the start time of the target time period is the start time of collecting the target data, and the end time of the target time period is the end time of collecting the target data.

[0072] SeeFigure 3 , Figure 3 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 3 shown, the electronic device 300 in this embodiment may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store computer programs, and the computer programs include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, for example Figure 2 shown, the functions of the parameter determination module 21, the algorithm determination module 22, and the data processing module 23.

[0073] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0074] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0075] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0076] In specific implementation, the processors 301, input devices 302, and output devices 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of the remote mining area image processing method provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated herein.

[0077] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing related hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0078] The computer-readable storage medium can be the internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk equipped on the electronic device, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0079] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0080] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0081] In several embodiments provided by this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each other can be an indirect coupling or communication connection through some interfaces or units, and can also be in the form of electrical, mechanical or other connections.

[0082] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0083] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0084] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for processing remote mining area images, characterized in that, Including: Input the target environmental parameters into the target model to determine the noise reduction parameters; Determine the target noise reduction algorithm based on the noise reduction parameters; Process the target data based on the target noise reduction algorithm to obtain the mining area data, and send the mining area data to the display device of the mining area monitoring center; wherein, the target environmental parameters are the environmental parameters of the target area corresponding to the target data, and the target data is the monitoring image data of the target area.

2. The remote mining area image processing method according to claim 1, wherein, The target model is a support vector machine model; Before inputting the target environmental parameters into the target model to determine the noise reduction parameters, it further includes: Train the support vector machine model based on the first data set to obtain the target model; wherein, the data in the first data set are historical environmental parameters and corresponding standard noise reduction parameters, and the standard noise reduction parameters are determined by optimizing the initial noise reduction parameters based on the particle swarm optimization algorithm.

3. The remote mining area image processing method according to claim 2, wherein The process of determining the standard noise reduction parameters based on the particle swarm optimization algorithm includes: Determine the particle dimension of the particle swarm optimization algorithm based on the parameters of the noise reduction algorithm; Determine the fitness function of the particle swarm optimization algorithm based on the environmental parameters; Perform iterative calculation on the initial noise reduction parameters based on the particle dimension and the fitness function until the difference between consecutive multiple fitness function values is less than the first threshold or the number of iterations reaches the first number to obtain the standard noise reduction parameters.

4. The remote mining area image processing method according to claim 3, wherein, It also includes: Determine the inertia weight of the particle swarm optimization algorithm based on the number of iterations; Control the iterative calculation direction of the particle swarm optimization algorithm based on the inertia weight and learning factor.

5. The remote mining area image processing method according to claim 2, characterized in that, The kernel function of the support vector machine model is a Gaussian kernel function; The training of the support vector machine model based on the first data set includes: In response to the concentration value of the standard noise reduction parameters being less than the first concentration value, reduce the reference value of the penalty parameter based on the first penalty step size to obtain the target penalty parameter of the Gaussian kernel function; In response to the concentration value of the standard noise reduction parameters being greater than the second concentration value, increase the reference value of the penalty parameter based on the second penalty step size to obtain the target penalty parameter of the Gaussian kernel function; Train the support vector machine model based on the Gaussian kernel function with the determined target penalty parameter and the first data set; wherein, the first concentration value is less than the second concentration value.

6. The remote mining area image processing method according to claim 2, characterized in that, The kernel function of the support vector machine model is a Gaussian kernel function; The training of the support vector machine model based on the first data set includes: Identify the first scatter plot based on the first neural network model; In response to the distribution of the standard noise reduction parameters in the data space satisfying the first condition, reduce the reference value of the kernel coefficient based on the first kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; In response to the distribution of the standard noise reduction parameters in the data space satisfying the second condition, increase the reference value of the kernel coefficient based on the second kernel coefficient step size to obtain the target kernel coefficient of the Gaussian kernel function; Train the support vector machine model based on the Gaussian kernel function with the determined target kernel coefficient and the first data set; Among them, the first neural network model is determined based on a certain number of scatter plots and their corresponding distribution results. The first scatter plot is the scatter plot of the distribution of the standard noise reduction parameters in the data space, and the first condition is different from the second condition.

7. The remote mining area image processing method according to claim 1, characterized in that, The monitored image data includes: monitored images and monitored videos; The remote mining area image processing method further includes: In response to the target data being a monitored image of the target area, the environmental parameters of the target area when the target data is collected are used as the target environmental parameters; In response to the target data being a monitored video of the target area and the change rate of the environmental parameters of the target area within the target time period being less than the first threshold, the environmental parameters at any moment within the target time period are used as the target environmental parameters; In response to the target data being a monitored video of the target area and the change rate of the environmental parameters of the target area within the target time period being greater than or equal to the first threshold, the environmental parameters at each moment within the target time period are used as the target environmental parameters; Among them, the start time of the target time period is the start time when the target data is collected, and the end time of the target time period is the end time when the target data is collected.

8. A remote mining area image processing system, characterized in that, It includes: A parameter determination module, configured to input the target environmental parameters into the target model to determine the noise reduction parameters; An algorithm determination module, configured to determine the target noise reduction algorithm based on the noise reduction parameters; A data processing module, configured to process the target data based on the target noise reduction algorithm to obtain mining area data, and send the mining area data to the display device of the mining area monitoring center; among them, the target environmental parameters are the environmental parameters of the target area corresponding to the target data, and the target data includes the monitored image data of the target area.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images