Material pile internal temperature analysis method and device, computer equipment and storage medium

Abstract

The invention relates to a material pile internal temperature analysis method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring visible light image information and infrared image information of a material pile; according to the visible light image information and the infrared image information, respective temperature information of different areas on the surface of the material pile is determined; carrying out heat transfer attribute analysis on the material pile based on the infrared image information, and determining the heat transfer attribute of the material pile; and determining respective temperature information of different areas in the material pile according to the respective temperature information of different areas on the surface of the material pile and the heat transfer attribute of the material pile. By adopting the method, the accuracy of the internal temperature analysis result of the material pile can be improved, and the implementation process of the method does not need to depend on a sensor installed in the material pile, so that the method can adapt to application requirements in different scenes, and the application scenes of the internal temperature analysis method of the material pile can be expanded.

Description

Technical Field

[0001] The present application relates to the technical field of material pile temperature prediction, and in particular to a material pile internal temperature analysis method, device, computer equipment, computer readable storage medium and computer program product. Background Art

[0002] The interior of a chemical raw material pile may overheat due to chemical reactions, self-heating, or external heat sources, leading to safety accidents such as fire and explosion, causing huge economic losses. Therefore, it is necessary to predict the temperature inside the pile.

[0003] Traditional technologies usually use sensors for detection. When the pile is in a tightly stacked state, it may be difficult to install the sensor. Even if the sensor is successfully installed inside the pile, it can only detect the internal temperature of the pile at the sensor installation location. It can be seen that traditional technologies can only be applied to application scenarios where the pile is not tightly stacked and only the internal temperature of the pile at a specific installation location needs to be detected, which has the disadvantage of limited application scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for analyzing the internal temperature of a pile of materials that can expand the application scenarios in order to address the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for analyzing the internal temperature of a pile of materials. The method comprises:

[0006] Obtain visible light image information and infrared image information of the stockpile;

[0007] Determining temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information;

[0008] Performing heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile;

[0009] The temperature information of different regions on the surface of the pile of materials is combined with the heat transfer properties of the pile of materials to determine the temperature information of different regions inside the pile of materials.

[0010] In one embodiment, determining the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information includes:

[0011] fusing the visible light image information and the infrared image information to obtain fused image information of the stockpile;

[0012] The temperature information of different areas on the surface of the pile is determined according to the fused image information.

[0013] In one embodiment, the step of fusing the visible light image information and the infrared image information to obtain the fused image information of the stockpile includes:

[0014] Based on the first type of filter and the second type of filter, the image information of the pile is filtered to obtain a first filtered image and a second filtered image; the image information includes visible light image information and infrared image information;

[0015] Determine a fusion weight coefficient of the image information according to the first filtered image and the second filtered image respectively corresponding to each of the image information; the fusion weight coefficient is positively correlated with the information difference between the first filtered image and the second filtered image;

[0016] The visible light image information and the infrared image information are fused according to their respective fusion weight coefficients to obtain fused image information of the stockpile.

[0017] In one embodiment, the heat transfer property includes material information; and the heat transfer property analysis of the material pile based on the infrared image information to determine the heat transfer property of the material pile includes:

[0018] According to the multiple bands corresponding to the infrared image information, the infrared image information is converted into hyperspectral image information;

[0019] Performing feature image extraction on the hyperspectral image information to obtain feature image information of the stockpile;

[0020] The characteristic image information is input into a material recognition model, and the material information of the material pile is determined based on the output of the material recognition model.

[0021] In one embodiment, extracting characteristic images from the hyperspectral image information to obtain characteristic image information of the stockpile includes:

[0022] Performing background noise reduction processing on the hyperspectral image information to obtain a hyperspectral noise reduction image;

[0023] Based on a segmentation result obtained by performing superpixel segmentation on the hyperspectral denoised image, characteristic image information of the stockpile is determined.

[0024] In one of the embodiments, the infrared image information includes infrared images acquired respectively at at least two image acquisition positions; the heat transfer property includes a three-dimensional form;

[0025] The performing heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile includes:

[0026] Performing morphological analysis on the material pile based on each of the infrared image information to determine the two-dimensional morphology of the material pile corresponding to each of the image acquisition postures;

[0027] The three-dimensional shape of each of the two-dimensional shapes is reconstructed in three dimensions according to each of the image acquisition postures to determine the three-dimensional shape of the stockpile.

[0028] In one embodiment, the heat transfer properties include material information and three-dimensional shape;

[0029] The determining the temperature information of different regions inside the pile of materials by combining the temperature information of different regions on the surface of the pile of materials and the heat transfer property of the pile of materials comprises:

[0030] Determining a three-dimensional model that matches the three-dimensional shape of the material pile and heat transfer parameters that match material information of the material pile;

[0031] Setting the physical field of the three-dimensional model based on the heat transfer parameters to obtain a heat transfer model of the pile;

[0032] The temperature information of different regions inside the material pile is determined according to the temperature information of different regions on the surface of the material pile and the heat transfer model.

[0033] In one embodiment, the obtaining of visible light image information and infrared image information of the stockpile includes:

[0034] Obtain visible light images and infrared images collected for the stockpile storage point;

[0035] The visible light image and the infrared image are respectively segmented to obtain visible light image information and infrared image information of the material pile stored at the material pile storage point.

[0036] In a second aspect, the present application also provides a device for analyzing the internal temperature of a pile of materials. The device comprises:

[0037] An acquisition module, used to acquire visible light image information and infrared image information of the stockpile;

[0038] A surface temperature determination module, used to determine the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information;

[0039] a heat transfer property determination module, configured to perform heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile;

[0040] The internal temperature determination module is used to determine the temperature information of different areas inside the pile of materials by combining the temperature information of different areas on the surface of the pile of materials and the heat transfer properties of the pile of materials.

[0041] In one of the embodiments, the surface temperature determination module includes: an information fusion unit, used to fuse the visible light image information and the infrared image information to obtain fused image information of the pile of materials; and a surface temperature determination unit, used to determine the temperature information of different areas on the surface of the pile of materials based on the fused image information.

[0042] In one of the embodiments, the information fusion unit is specifically used to: filter the image information of the pile of materials based on a first type of filter and a second type of filter, respectively, to obtain a first filtered image and a second filtered image; the image information includes visible light image information and infrared image information; determine a fusion weight coefficient of the image information according to the first filtered image and the second filtered image corresponding to each of the image information; the fusion weight coefficient is positively correlated with the information difference between the first filtered image and the second filtered image; and fuse the visible light image information and the infrared image information according to their respective fusion weight coefficients to obtain fused image information of the pile of materials.

[0043] In one embodiment, the heat transfer property includes material information. In this embodiment, the heat transfer property determination module includes: an information conversion unit, which is used to convert the infrared image information into hyperspectral image information according to the multiple bands corresponding to the infrared image information; a feature extraction unit, which is used to extract feature images from the hyperspectral image information to obtain feature image information of the pile; and a material information determination unit, which is used to input the feature image information into a material recognition model, and determine the material information of the pile based on the output of the material recognition model.

[0044] In one of the embodiments, the feature extraction unit is specifically used to: perform background noise reduction processing on the hyperspectral image information to obtain a hyperspectral noise reduction image; and determine characteristic image information of the stockpile based on a segmentation result obtained by superpixel segmentation of the hyperspectral noise reduction image.

[0045] In one embodiment, the infrared image information includes infrared images collected by at least two image acquisition postures; the heat transfer property includes a three-dimensional form. In the case of this embodiment, the heat transfer property determination module is specifically used to: perform a morphological analysis on the material pile based on each of the infrared image information to determine the two-dimensional form of the material pile corresponding to each of the image acquisition postures; perform a three-dimensional reconstruction of each of the two-dimensional forms according to each of the image acquisition postures to determine the three-dimensional form of the material pile.

[0046] In one embodiment, the heat transfer attribute includes material information and three-dimensional form. In the case of this embodiment, the internal temperature determination module is specifically used to: determine a three-dimensional model that matches the three-dimensional form of the material pile and heat transfer parameters that match the material information of the material pile; set the physical field of the three-dimensional model based on the heat transfer parameters to obtain the heat transfer model of the material pile; determine the temperature information of different areas inside the material pile according to the temperature information of different areas on the surface of the material pile and the heat transfer model.

[0047] In one of the embodiments, the acquisition module is specifically used to: acquire visible light images and infrared images collected at a material pile storage point; perform image segmentation on the visible light image and the infrared image respectively to obtain visible light image information and infrared image information of the material pile stored at the material pile storage point.

[0048] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0050] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0051] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for analyzing the temperature inside the pile obtain visible light image information and infrared image information of the pile; determine the temperature information of different areas on the surface of the pile based on the visible light image information and the infrared image information; perform heat transfer property analysis on the pile based on the infrared image information to determine the heat transfer properties of the pile; and determine the temperature information of different areas inside the pile based on the temperature information of different areas on the surface of the pile and the heat transfer properties of the pile. By adopting the above-mentioned method, it is possible to determine the temperature information of different areas inside the pile based on the heat transfer properties of the pile, based on the determination of the temperature information of different areas on the surface of the pile based on the infrared image, thereby improving the accuracy of the temperature information inside the pile. Since the implementation process of the method does not have to rely on sensors installed inside the pile, the above-mentioned method can adapt to application requirements in different scenarios, which is conducive to expanding the application scenarios of the method for analyzing the temperature inside the pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A diagram showing an application environment of a method for analyzing temperature inside a pile in one embodiment;

[0053] FIG2 is a schematic diagram of a process flow of a method for analyzing temperature inside a pile of materials in one embodiment;

[0054] Figure 3 is a structural block diagram of a device for analyzing the internal temperature of a pile of materials in one embodiment;

[0055] Figure 4 A block diagram of a device for predicting the internal temperature of a pile of materials in one embodiment;

[0056] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] In one embodiment, the internal temperature analysis method of the pile provided by the present application can be applied to Figure 1In the application environment shown. Among them, the visible light image acquisition device 102 and the infrared image acquisition device 104 can communicate with the processor 106 through a network. The communication network can be a wired network or a wireless network. Therefore, the visible light image acquisition device 102 and the processor 106 can be directly or indirectly connected through wired or wireless communication. For example, the visible light image acquisition device 102 can be indirectly connected to the processor 106 through a wireless access point, or the visible light image acquisition device 102 is directly connected to the processor 106 through the Internet, and this application is not limited here.

[0059] Among them, the visible light image acquisition device 102 and the infrared image acquisition device 104 can be, but are not limited to, hardware devices with image data acquisition functions, such as cameras, video cameras, scanners, or laser radars, or various desktop computers, laptops, smart phones, tablet computers, Internet of Things devices, and portable wearable devices integrated with image acquisition devices, among which the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The processor 106 can be integrated with the visible light image acquisition device 102 and the infrared image acquisition device 104 in the same device, or can be separately set, which is not limited in this application.

[0060] The processor 106 refers to a hardware device with data processing functions, and the processor 106 can be integrated into a computer device or a separate processing device. The computer device can be a terminal or a server. Among them, the terminal includes but is not limited to a desktop computer, a laptop computer, a smart phone, a tablet computer, an Internet of Things device and a portable wearable device. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart car device, etc.; the portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0061] Specifically, the visible light image acquisition device 102 is used to acquire visible light image information, and the infrared image acquisition device 104 is used to acquire infrared image information. In the process of analyzing the temperature inside the pile, the processor 106: obtains visible light image information and infrared image information of the pile; determines the temperature information of different areas on the surface of the pile based on the visible light image information and the infrared image information; performs heat transfer property analysis on the pile based on the infrared image information to determine the heat transfer property of the pile; and determines the temperature information of different areas inside the pile based on the temperature information of different areas on the surface of the pile and the heat transfer property of the pile.

[0062] In one embodiment, as shown in FIG2 , a method for analyzing the internal temperature of a pile is provided. In this embodiment, the method comprises the following steps:

[0063] Step S202, obtaining visible light image information and infrared image information of the stockpile.

[0064] Among them, the chemical raw material pile refers to the raw material aggregation pile formed by stacking various chemical raw materials according to certain methods and standards in the chemical production process. When collecting images of the same pile, different image information can be obtained due to the use of different light. Among them, the visible light image information of the pile refers to the image of the pile collected under visible light irradiation; the infrared image information of the pile refers to the image of the pile collected under infrared irradiation. Exemplarily, the image acquisition equipment can deploy a visible light lighting system and an infrared light lighting system to collect visible light image information and infrared image information for the same pile. Furthermore, the visible light image and the infrared image can be color images or grayscale images, which are not limited here.

[0065] Specifically, the image acquisition device can perform image acquisition, and the processor can obtain image information of the pile in the acquired image, which can include visible light image information and infrared image information of the pile. The specific way for the processor to obtain the pile image information can be active acquisition or passive reception.

[0066] In an optional embodiment, obtaining visible light image information and infrared image information of a material pile includes: obtaining visible light images and infrared images collected at a material pile storage point; and performing image segmentation on the visible light image and infrared image respectively to obtain visible light image information and infrared image information of the material pile stored at the material pile storage point.

[0067] Among them, the stockpile storage point is used to store various chemical raw material stockpiles. When chemical raw material stockpiles undergo chemical reactions or self-heating, safety accidents may occur. Therefore, it is necessary to accurately monitor the internal temperature of the stockpile.

[0068] Specifically, the image acquisition device can perform image acquisition on the material pile storage point to obtain an infrared image and a visible light image of the material pile storage point. Since there are other objects in the material pile storage point, and the present application only needs to predict the temperature inside the material pile, the processor can perform image segmentation on the infrared image and the visible light image of the material pile storage point to obtain visible light image information and infrared image information of the material pile, and perform further processing to analyze the internal temperature distribution of the material pile.

[0069] Furthermore, the algorithm for performing image segmentation on the visible light image and infrared image of the stockpile storage point is not unique, and it may be, for example, a threshold-based image segmentation method, a deep learning-based image segmentation method, etc., which is not limited in this application.

[0070] It should be noted that when there are multiple material piles stored at a material pile storage point, the processor can perform image segmentation on the infrared image and visible light image of the material pile storage point to obtain visible light image information and infrared image information corresponding to each material pile, so as to subsequently perform internal temperature analysis on each material pile.

[0071] In this embodiment, the visible light image information and infrared image information of the pile are extracted through image segmentation, which can effectively reduce the amount of data processing and improve the work efficiency of temperature analysis.

[0072] Step S204: determining the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information.

[0073] In practical applications, visible light images have better image clarity, but are greatly affected by ambient light, especially the image edges, which may produce more noise due to the influence of ambient light. Infrared images, on the other hand, are not easily affected by the surrounding environment. Therefore, the processor can use the characteristics of infrared image information that can characterize the surface temperature of an object, combined with the high definition of visible light images, to determine the temperature information of different areas on the surface of the pile.

[0074] In an optional embodiment, the processor can divide the surface of the pile into a plurality of different regions based on the visible light image information. These regions can be divided by grids or by pixels, which is not limited here. Then, based on the correspondence between the visible light image information and the infrared image information, the temperature represented by the infrared image information of each region is determined, thereby obtaining the temperature information of different regions on the surface of the pile.

[0075] In an optional embodiment, the processor can fuse the visible light image information and the infrared image information to obtain fused image information of the pile. It can be understood that the fused image information has both high image clarity and the ability to characterize the surface temperature of the pile. Then, the processor divides the pile surface into multiple different areas based on the fused image information, and further determines the temperature information of the different areas on the pile surface.

[0076] Step S206: analyzing the heat transfer properties of the material pile based on the infrared image information to determine the heat transfer properties of the material pile.

[0077] The heat transfer property refers to the pile property parameters that affect heat transfer. The heat transfer property may include the material information, shape information, etc. of the pile. Specifically, different materials have different heat transfer parameters, and different shapes have different heat dissipation areas, which in turn affect the heat transfer speed.

[0078] Specifically, the processor can perform heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile. Exemplarily, the processor can perform material analysis on the material pile based on the infrared image information to determine the material information of the material pile; the processor can also perform three-dimensional morphology analysis on the material pile based on the infrared image information to determine the morphology information of the material pile.

[0079] In an optional embodiment, the processor may combine the infrared image information and visible light image information of the pile to perform a three-dimensional morphological analysis of the pile, so as to improve the accuracy of the pile morphological analysis results by combining the advantages of higher clarity of visible light images and less environmental impact of infrared images.

[0080] Step S208, combining the temperature information of different areas on the surface of the pile and the heat transfer properties of the pile, to determine the temperature information of different areas inside the pile.

[0081] Specifically, the processor can determine the heat transfer model of the pile according to the heat transfer properties of the pile. The heat transfer model is used to characterize the law followed by the interior of the pile and the surface of the pile during the heat transfer process. Then, the processor analyzes the temperature inside the pile based on the heat transfer model based on the temperature information of different areas on the surface of the pile, and determines the temperature information of different areas inside the pile.

[0082] The above-mentioned method for analyzing the temperature inside a pile of materials obtains visible light image information and infrared image information of the pile of materials; determines the temperature information of different areas on the surface of the pile of materials based on the visible light image information and the infrared image information; performs heat transfer property analysis on the pile of materials based on the infrared image information to determine the heat transfer properties of the pile of materials; and determines the temperature information of different areas inside the pile of materials based on the temperature information of different areas on the surface of the pile of materials and the heat transfer properties of the pile of materials. By adopting the above-mentioned method, it is possible to determine the temperature information of different areas inside the pile of materials based on the temperature information of different areas on the surface of the pile of materials based on the infrared image, combined with the heat transfer properties of the pile of materials, thereby improving the accuracy of the temperature information inside the pile of materials. Since the implementation process of the method does not have to rely on sensors installed inside the pile of materials, the above-mentioned method can adapt to application needs in different scenarios, which is conducive to expanding the application scenarios of the method for analyzing the temperature inside the pile of materials.

[0083] In an optional embodiment, the temperature information of different areas on the surface of the pile is determined based on the visible light image information and the infrared image information, including: fusing the visible light image information and the infrared image information to obtain fused image information of the pile; and determining the temperature information of different areas on the surface of the pile based on the fused image information.

[0084] Among them, image information fusion is to integrate multiple types of image information together to improve information quality. Specifically, the processor can fuse visible light image information and infrared image information to obtain fused image information of the pile, and then, based on the pixel value of the red channel in the fused image information, the temperature information of different areas on the surface of the pile can be determined. Taking the case where the surface of the pile is divided into multiple areas according to pixels as an example, for each area, the processor can read the red channel pixel value of each pixel contained in the area, and determine the temperature information of the area through statistics. The statistical method of the red channel pixel value can be, for example, the average value or the median, which is not limited here.

[0085] Furthermore, there is no unique way to fuse infrared image information with visible light image information. For example, it can include multi-scale transformation, sparse representation, saliency detection, subspace method, etc., and image fusion can also be performed based on deep learning methods.

[0086] In the above embodiment, the temperature information of different areas on the surface of the pile is determined based on the fused image information obtained by fusing the visible light image information and the infrared image information, so as to improve the accuracy of the temperature information on the surface of the pile.

[0087] In an optional embodiment, visible light image information and infrared image information are fused to obtain fused image information of the material pile, including: filtering the image information of the material pile based on a first type of filter and a second type of filter respectively to obtain a first filtered image and a second filtered image; determining a fusion weight coefficient of the image information according to the first filtered image and the second filtered image corresponding to each piece of image information; and fusing the visible light image information and the infrared image information according to their respective fusion weight coefficients to obtain fused image information of the material pile.

[0088] The image information includes visible light image information and infrared image information; and the fusion weight coefficient is positively correlated with the information difference between the first filtered image and the second filtered image. The first type filter and the second type filter refer to two filters of different types. For example, the first type filter may be one of a mean filter and a median filter, and the second type filter may be the other of the mean filter and the median filter.

[0089] In one possible implementation, the first type of filter is a mean filter, and the second type of filter is a termination filter. By processing the image information of the pile based on the first type of filter, a smoothed first filtered image can be obtained; and by processing the image information of the pile based on the second type of filter, a denoised second filtered image can be obtained.

[0090] Specifically, the processor can process the visible light image information of the pile based on the first type of filter to obtain a first visible light filtered image, and process the infrared image information of the pile to obtain a first infrared filtered image; based on the second type of filter, the visible light image information of the pile is processed to obtain a second visible light filtered image, and the infrared image information of the pile is processed to obtain a second infrared filtered image. Then, the processor performs a difference processing on the first visible light filtered image and the second visible light filtered image to determine the information difference corresponding to the visible light image information; and performs a difference processing on the first infrared filtered image and the second infrared filtered image to determine the information difference corresponding to the infrared image information.

[0091] When the information difference between the visible light image information and the infrared image information is determined, the processor can determine the fusion weight coefficients of the visible light image information and the infrared image information according to the principle that the fusion weight coefficient is positively correlated with the information difference, and then fuse the visible light image information and the infrared image information according to each fusion weight coefficient to obtain the fused image information of the stockpile. The information difference may include the difference between the statistical values ​​of information parameters of one or more dimensions. The information parameter may include at least one of information quantity, brightness, grayscale or pixel value.

[0092] In a possible implementation, the processor can linearly fuse the detail layers of the visible light image information and the infrared image information according to each fusion weight coefficient to obtain a fused detail layer image, fuse the base layer of the visible light image information and the infrared image information using the average fusion rule (i.e., the fusion weights of the visible light image information and the infrared image information are the same) to obtain a fused base layer image, and finally, fuse the base layer image and the detail layer image to obtain fused image information of the pile.

[0093] It can be understood that for the same image information, the greater the information difference between the filtered images obtained under different filtering processing methods, the less redundant information contained in the image information (because the more redundant information, the more similar the results after filtering by different filtering methods), which means that the image contains more unique information and details, that is, the stronger the image information expression ability. In this case, fusing the image information in a way that the fusion weight coefficient is positively correlated with the information difference can improve the quality of the obtained fused image, and thus improve the accuracy of the temperature information determined based on the fused image.

[0094] In an optional embodiment, the heat transfer property includes material information. In the case of this embodiment, the heat transfer property analysis of the material pile is performed based on the infrared image information to determine the heat transfer property of the material pile, including: converting the infrared image information into hyperspectral image information according to multiple bands corresponding to the infrared image information; extracting feature images from the hyperspectral image information to obtain feature image information of the material pile; inputting the feature image information into a material recognition model, and determining the material information of the material pile based on the output of the material recognition model.

[0095] Among them, hyperspectral image (HSI) is a type of remote sensing data containing rich spectral information, which can reflect the spatial characteristics and internal components of the sample. Infrared images mainly use the difference in thermal radiation of objects to form images, reflecting the brightness and contour characteristics of objects. Hyperspectral images obtain the spectral and spatial information of objects by measuring the reflection, absorption and scattering characteristics of the same object at different wavelengths. Therefore, converting infrared images into hyperspectral images requires adding spectral information while maintaining the spatial characteristics of infrared images.

[0096] Specifically, the processor can segment the infrared image information to obtain sub-information corresponding to multiple waves, and then arrange and combine the sub-information in the order of the bands to construct a multi-band data cube to obtain hyperspectral image information, thereby completing the conversion from infrared image information to hyperspectral image information. Optionally, the processor can also align the sub-information based on pre-configured graphic information to obtain the sub-information of different bands after alignment, and then construct a multi-band data cube based on the aligned self-information.

[0097] After obtaining the hyperspectral image information, the processor can perform feature image extraction on the hyperspectral image information to obtain feature image information of the material pile, and input the feature image information into the material recognition model, and determine the material information of the material pile based on the output of the material recognition model. Among them, the material information of the material pile may include the material information of different components in the material pile. In other words, in the case where materials of different materials are mixed in a material pile, the material and location of each material in the material pile can be identified through the scheme of the present application. Furthermore, the material recognition model can be a pre-trained neural network model that has the ability to determine the physical material based on image feature information.

[0098] In the above embodiment, the infrared image information is converted into hyperspectral image information for identifying the material of the stockpile, without using expensive hyperspectral acquisition equipment, thus reducing costs.

[0099] In an optional embodiment, feature image extraction is performed on the hyperspectral image information to obtain feature image information of the stockpile, including: background noise reduction processing is performed on the hyperspectral image information to obtain a hyperspectral noise reduction image; based on a segmentation result obtained by superpixel segmentation of the hyperspectral noise reduction image, the feature image information of the stockpile is determined.

[0100] Specifically, the processor can preprocess the hyperspectral image to reduce the background noise of the image and obtain a hyperspectral denoised image. Then, the hyperspectral denoised image is superpixel segmented to generate first feature image information, which includes a first-layer global structure topology map and a second-layer global structure topology map. In combination, the processor fuses the first-layer global structure topology map and the second-layer global structure topology map to obtain second feature image information, and sends the second feature image information to the material recognition model to obtain material information corresponding to the pile of materials. Among them, the use of superpixel segmentation to process hyperspectral images is a technical solution well known to those skilled in the art, so it will not be repeated here.

[0101] Since the material of the pile affects the temperature of the pile, it is necessary to first determine the material of the pile, and then further predict the temperature inside the pile based on the temperature of the pile surface. At the same time, the same pile may contain materials of different materials, and the materials of different materials have different effects on the temperature. In this embodiment, the materials of different materials that may be mixed in the pile are confirmed based on the image information of the pile, which can improve the accuracy of the prediction of the temperature inside the pile.

[0102] In an optional embodiment, the infrared image information includes infrared images respectively acquired at least two image acquisition postures; and the heat transfer property includes a three-dimensional form. In the case of this embodiment, the heat transfer property analysis of the pile is performed based on the infrared image information to determine the heat transfer property of the pile, including: performing a form analysis on the pile based on each infrared image to determine the two-dimensional form corresponding to the pile in each image acquisition posture; performing three-dimensional reconstruction of each two-dimensional form according to each image acquisition posture to determine the three-dimensional form of the pile.

[0103] Specifically, the processor can obtain infrared image information collected for the pile in multiple image acquisition postures. Then, the pile is subjected to morphological analysis based on each infrared image information to determine the two-dimensional morphology of the pile in each image acquisition posture. Optionally, the processor can pre-train a morphological recognition model and input each infrared image information into the morphological recognition model to determine the two-dimensional morphology of the pile.

[0104] During the training of the morphological recognition model, sample infrared images of multiple sample stockpiles can be obtained, and then these sample infrared images can be clustered to determine multiple sample morphological categories corresponding to each sample stockpile, and each sample stockpile can be labeled according to the clustering results to obtain a training set. These sample morphological categories can include cuboids, cones, tall narrow cylinders, short wide cylinders, and the like. Then, the initial neural network model is trained using the training set to obtain a morphological recognition model with the ability to recognize the stockpile morphology. By clustering each sample infrared image, rapid labeling can be achieved, which is conducive to improving the work efficiency of the model training process.

[0105] After determining the two-dimensional shapes corresponding to the pile of materials under multiple image acquisition postures, the processor can perform three-dimensional reconstruction of each two-dimensional shape according to each image acquisition posture to determine the three-dimensional shape of the pile of materials. There is no unique way to perform three-dimensional reconstruction of multiple two-dimensional shapes, which is not limited here. For example, the conversion from two-dimensional shape to three-dimensional shape can be achieved by combining deep learning and computer graphics methods; the two-dimensional image can also be projected into three-dimensional space through projection transformation to achieve conversion.

[0106] In this embodiment, the shape of the pile has an impact on the heat transfer of the pile. For example, the speed at which heat dissipates from the surface of a tall and narrow pile may be different from that of a short and wide pile. For a tall and narrow pile, heat is more likely to accumulate in the center because the surface heat dissipation area is relatively small; while for a short and wide pile, the surface heat dissipation area is large and the heat dissipation is relatively fast. Therefore, it is necessary to identify the shape of the pile for subsequent modeling to ensure the accuracy of the internal temperature prediction of the pile.

[0107] In an optional embodiment, the heat transfer property includes material information and three-dimensional form. In the case of this embodiment, the temperature information of different regions inside the pile is determined in combination with the temperature information of different regions on the surface of the pile and the heat transfer property of the pile, including: determining a three-dimensional model matching the three-dimensional form of the pile and heat transfer parameters matching the material information of the pile; setting the physical field of the three-dimensional model based on the heat transfer parameters to obtain a heat transfer model of the pile; and determining the temperature information of different regions inside the pile according to the temperature information of different regions on the surface of the pile and the heat transfer model.

[0108] Specifically, on the one hand, the processor can match the preset three-dimensional model template according to the three-dimensional shape of the material pile to achieve rapid modeling and determine the three-dimensional model that matches the three-dimensional shape of the material pile. On the other hand, the heat transfer parameters of each physical contained in the material pile can be determined based on the material information of the material pile. The heat transfer parameters may include specific heat capacity, density, thermal conductivity, etc. Then, the processor can set the physical field of the three-dimensional model based on each heat transfer parameter to obtain the heat transfer model of the material pile. Finally, the processor can determine the temperature information of different areas inside the material pile based on the temperature information of different areas on the surface of the material pile and the heat transfer model.

[0109] Optionally, the control equation of the three-dimensional model of the stockpile after setting the physical field is:

[0110]

[0111] In the above formula, Indicates the material density, represents the specific heat capacity of the material, T represents the temperature information, Q represents the heat source term per unit volume, represents the heat flux density per unit volume, k represents the thermal conductivity of the material, It represents the temperature gradient. It should be noted that the heat transfer parameters of each grid in the three-dimensional model of the stockpile are not necessarily the same. When there are materials of various materials in the stockpile, the heat transfer characteristic information in the grid needs to be modified accordingly to ensure the accuracy of the temperature prediction inside the stockpile.

[0112] In an optional embodiment, the processor can also obtain characteristic parameters that affect temperature changes, standardize the characteristic parameters, and obtain standardized parameter information. Then, gray correlation analysis is performed on the standardized parameter information to obtain the gray correlation degree of each characteristic parameter, and the closeness between the sequences is measured according to the size of the gray correlation degree, and the target parameter as the main influencing factor is determined from each characteristic parameter. Finally, the temperature characteristic information corresponding to the target parameter of each grid and the temperature information of each grid inside the pile are sent to the BP neural network for prediction to obtain the temperature information of the next state of each grid.

[0113] The characteristic parameters include, but are not limited to, temperature information within the storage point, humidity information within the storage point, temperature information outside the storage point, humidity information outside the storage point, wind direction information, wind speed information, average temperature of the storage point, surface temperature, etc. Standardization processing may include averaging processing and initialization processing. The basic principle of grey correlation analysis is to use a series of curves formed by an existing data set to determine the difference and correlation between a reference series and a comparison series. In this embodiment, grey correlation analysis is performed to determine the main influencing factors affecting the temperature of the stockpile.

[0114] The temperature characteristic information that affects the temperature change and the temperature information of each grid inside the pile are sent to the BP neural network for prediction, and the temperature information of each grid changing over time can be output, so as to accurately obtain the temperature inside the pile and the temperature change. It should be noted that since the temperature change has the characteristics of time series, the BP neural network used in this application is more likely to capture the characteristics of time series, thereby improving the accuracy of the prediction of the temperature inside the pile.

[0115] In the above embodiment, the temperature transfer process between the inside and outside of the pile can be simulated by setting the three-dimensional model of the pile after the physical field and the temperature information of each grid on the surface of the pile, thereby realizing the prediction of the temperature inside the pile.

[0116] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0117] Based on the same inventive concept, the embodiment of the present application also provides a material pile internal temperature analysis device for implementing the material pile internal temperature analysis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the material pile internal temperature analysis device provided below can refer to the limitations of the material pile internal temperature analysis method above, and will not be repeated here.

[0118] In one embodiment, Figure 3As shown, a device for analyzing the internal temperature of a pile is provided, comprising: an acquisition module 301, a surface temperature determination module 302, a heat transfer property determination module 303 and an internal temperature determination module 304, wherein:

[0119] An acquisition module 301 is used to acquire visible light image information and infrared image information of the stockpile;

[0120] The surface temperature determination module 302 is used to determine the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information;

[0121] A heat transfer property determination module 303 is used to analyze the heat transfer properties of the pile based on the infrared image information to determine the heat transfer properties of the pile;

[0122] The internal temperature determination module 304 is used to determine the temperature information of different regions inside the pile in combination with the temperature information of different regions on the surface of the pile and the heat transfer properties of the pile.

[0123] In one embodiment, the surface temperature determination module 302 includes: an information fusion unit, which is used to fuse visible light image information and infrared image information to obtain fused image information of the pile; and a surface temperature determination unit, which is used to determine the temperature information of different areas on the surface of the pile based on the fused image information.

[0124] In one of the embodiments, the information fusion unit is specifically used to: filter the image information of the pile based on the first type of filter and the second type of filter respectively to obtain the first filtered image and the second filtered image; the image information includes visible light image information and infrared image information; determine the fusion weight coefficient of the image information according to the first filtered image and the second filtered image corresponding to each image information; the fusion weight coefficient is positively correlated with the information difference between the first filtered image and the second filtered image; according to the respective fusion weight coefficients of the visible light image information and the infrared image information, fuse the visible light image information and the infrared image information to obtain the fused image information of the pile.

[0125] In one embodiment, the heat transfer property includes material information. In this embodiment, the heat transfer property determination module 303 includes: an information conversion unit, which is used to convert the infrared image information into hyperspectral image information according to the multiple bands corresponding to the infrared image information; a feature extraction unit, which is used to extract feature images from the hyperspectral image information to obtain feature image information of the pile; and a material information determination unit, which is used to input the feature image information into a material recognition model, and determine the material information of the pile based on the output of the material recognition model.

[0126] In one of the embodiments, the feature extraction unit is specifically used to: perform background noise reduction processing on the hyperspectral image information to obtain a hyperspectral noise reduction image; and determine characteristic image information of the stockpile based on a segmentation result obtained by superpixel segmentation of the hyperspectral noise reduction image.

[0127] In one embodiment, the infrared image information includes infrared images collected respectively at least two image acquisition postures; the heat transfer property includes a three-dimensional form. In the case of this embodiment, the heat transfer property determination module 303 is specifically used to: perform a morphological analysis on the pile based on each infrared image information, determine the two-dimensional form corresponding to the pile in each image acquisition posture; perform a three-dimensional reconstruction of each two-dimensional form according to each image acquisition posture, and determine the three-dimensional form of the pile.

[0128] In one embodiment, the heat transfer attribute includes material information and three-dimensional shape. In the case of this embodiment, the internal temperature determination module 304 is specifically used to: determine a three-dimensional model matching the three-dimensional shape of the pile and heat transfer parameters matching the material information of the pile; set the physical field of the three-dimensional model based on the heat transfer parameters to obtain a heat transfer model of the pile; determine the temperature information of different areas inside the pile according to the temperature information of different areas on the surface of the pile and the heat transfer model.

[0129] In one embodiment, the acquisition module 301 is specifically used to: acquire visible light images and infrared images collected at a material pile storage point; perform image segmentation on the visible light image and infrared image respectively to obtain visible light image information and infrared image information of the material pile stored at the material pile storage point.

[0130] Each module in the above-mentioned material pile internal temperature analysis device can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0131] Corresponding to the above method embodiment, this embodiment also provides a material pile internal temperature prediction device based on infrared thermal imaging. The material pile internal temperature prediction device based on infrared thermal imaging described below and the material pile internal temperature prediction method based on infrared thermal imaging described above can refer to each other.

[0132] Figure 4 4 is a block diagram of a material pile internal temperature prediction device 400 based on infrared thermal imaging according to an exemplary embodiment. Figure 3As shown, the material pile internal temperature prediction device 400 based on infrared thermal imaging may include: a processor 401 and a memory 402. The material pile internal temperature prediction device 400 based on infrared thermal imaging may also include one or more of a multimedia component 403, an I / O interface 404, and a communication component 405.

[0133] The processor 401 is used to control the overall operation of the material pile internal temperature prediction device 400 based on infrared thermal imaging to complete all or part of the steps in the above-mentioned material pile internal temperature prediction method based on infrared thermal imaging. The memory 402 is used to store various types of data to support the operation of the material pile internal temperature prediction device 400 based on infrared thermal imaging, and these data may include, for example, instructions for any application or method operating on the material pile internal temperature prediction device 400 based on infrared thermal imaging, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 403 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 402 or sent via the communication component 405. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 404 provides an interface between the processor 401 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 405 is used for wired or wireless communication between the internal temperature prediction device 400 of the pile based on infrared thermal imaging and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 405 can include: Wi-Fi module, Bluetooth module, NFC module.

[0134] In an exemplary embodiment, the material pile internal temperature prediction device 400 based on infrared thermal imaging can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned material pile internal temperature analysis method.

[0135] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a palmprint depth analysis method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0136] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method for analyzing the internal temperature of a pile when executing the computer program.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method for analyzing the internal temperature of a pile of materials are implemented.

[0139] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above-mentioned material pile internal temperature analysis method when executed by a processor.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for analyzing the internal temperature of a pile, characterized in that: The method comprises: Obtain visible light image information and infrared image information of the stockpile; Determining temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information; Performing heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile; The temperature information of different regions on the surface of the pile of materials is combined with the heat transfer properties of the pile of materials to determine the temperature information of different regions inside the pile of materials.

2. The method according to claim 1, characterized in that Determining the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information includes: fusing the visible light image information and the infrared image information to obtain fused image information of the stockpile; The temperature information of different areas on the surface of the pile is determined according to the fused image information.

3. The method according to claim 2, characterized in that The fusing the visible light image information and the infrared image information to obtain the fused image information of the stockpile includes: Based on the first type of filter and the second type of filter, the image information of the pile is filtered to obtain a first filtered image and a second filtered image; the image information includes visible light image information and infrared image information; Determine a fusion weight coefficient of the image information according to the first filtered image and the second filtered image respectively corresponding to each of the image information; the fusion weight coefficient is positively correlated with the information difference between the first filtered image and the second filtered image; The visible light image information and the infrared image information are fused according to their respective fusion weight coefficients to obtain fused image information of the stockpile.

4. The method according to claim 1, characterized in that: The heat transfer property includes material information; and the heat transfer property analysis of the material pile based on the infrared image information to determine the heat transfer property of the material pile includes: According to the multiple bands corresponding to the infrared image information, the infrared image information is converted into hyperspectral image information; Performing feature image extraction on the hyperspectral image information to obtain feature image information of the stockpile; The characteristic image information is input into a material recognition model, and the material information of the material pile is determined based on the output of the material recognition model.

5. The method according to claim 4, characterized in that The step of extracting characteristic images from the hyperspectral image information to obtain characteristic image information of the stockpile includes: Performing background noise reduction processing on the hyperspectral image information to obtain a hyperspectral noise reduction image; Based on a segmentation result obtained by performing superpixel segmentation on the hyperspectral denoised image, characteristic image information of the stockpile is determined.

6. The method according to claim 1, characterized in that The infrared image information includes infrared images respectively acquired at at least two image acquisition positions; the heat transfer properties include three-dimensional morphology; The step of analyzing the heat transfer properties of the material pile based on the infrared image information to determine the heat transfer properties of the material pile includes: Performing morphological analysis on the material pile based on each of the infrared image information to determine the two-dimensional morphology of the material pile corresponding to each of the image acquisition postures; The three-dimensional shape of each of the two-dimensional shapes is reconstructed in three dimensions according to each of the image acquisition postures to determine the three-dimensional shape of the stockpile.

7. The method according to any one of claims 1 to 6, characterized in that: The heat transfer properties include material information and three-dimensional shape; The determining the temperature information of different regions inside the pile of materials by combining the temperature information of different regions on the surface of the pile of materials and the heat transfer property of the pile of materials comprises: Determining a three-dimensional model that matches the three-dimensional shape of the material pile and heat transfer parameters that match material information of the material pile; Setting the physical field of the three-dimensional model based on the heat transfer parameters to obtain a heat transfer model of the stockpile; The temperature information of different regions inside the material pile is determined according to the temperature information of different regions on the surface of the material pile and the heat transfer model.

8. The method according to any one of claims 1 to 6, characterized in that: The step of obtaining visible light image information and infrared image information of the stockpile includes: Obtain visible light images and infrared images collected for the stockpile storage point; The visible light image and the infrared image are respectively segmented to obtain visible light image information and infrared image information of the material pile stored at the material pile storage point.

9. A device for analyzing the internal temperature of a pile, characterized in that: The device comprises: An acquisition module, used to acquire visible light image information and infrared image information of the stockpile; A surface temperature determination module, used to determine the temperature information of different areas on the surface of the pile according to the visible light image information and the infrared image information; a heat transfer property determination module, configured to perform heat transfer property analysis on the material pile based on the infrared image information to determine the heat transfer property of the material pile; The internal temperature determination module is used to determine the temperature information of different areas inside the pile of materials by combining the temperature information of different areas on the surface of the pile of materials and the heat transfer properties of the pile of materials.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images