A method, device and product for monitoring leakage position of underground pipe network

Abstract

The present invention relates to a monitoring method, a monitoring device, a computer program product and an electronic device for underground pipe network leakage positions, and belongs to the field of remote sensing monitoring. The present invention uses remote sensing means to detect underground pipe network leakage positions within a large urban area. The monitoring method involved in the present invention comprises: determining the bare soil backscattering coefficient of the area to be monitored; inputting the bare soil backscattering coefficient into a target soil moisture identification model, and determining the soil mass moisture content of the area to be monitored through the target soil moisture identification model; comparing the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored, and determining the leakage point of the pipeline in the area to be monitored. The monitoring method involved in the present invention has the advantages of low cost, low construction cost, low loss, and rapid, non-destructive and automatic detection of pipe network leakage points within a large area.

Description

Technical Field

[0001] The present invention relates to the field of remote sensing monitoring technology, and in particular to a method, a monitoring device, a computer program product and an electronic device for monitoring leakage positions of underground pipe networks. Background Art

[0002] Underground pipelines used to transport liquids such as water (for example, underground sewage discharge systems) are an important part of urban infrastructure. Urban underground pipelines undertake the important tasks of collecting, transporting, treating and discharging a large amount of production and domestic water. They also affect urban planning, ecological protection and public health. Their safe and stable operation can ensure the daily life and production safety of urban residents.

[0003] The problems existing in the prior art are explained below by taking the underground sewage discharge system as an example.

[0004] When a city encounters extreme weather such as short-term heavy rainfall, a reasonable and normal sewage discharge system can also timely and effectively divert precipitation, thereby effectively preventing accidents and urban waterlogging, and playing a very positive role in the sustainable development of urban water resources. However, due to factors such as the deep burial of the urban sewage discharge system, large scale, and complex environment, coupled with the unscientific design of some underground sewage discharge systems, long service life, and the increase in water volume caused by the demand for water and drainage from all walks of life, the pressure on the pipeline has increased, which is higher than the design pressure at the time. The resulting leakage of underground sewage pipe networks has become increasingly serious. In addition, due to various reasons such as pipeline aging, engineering construction, major accidents, man-made damage, natural disasters, and poor management, the underground sewage pipe network will also suffer from serious leakage problems, which will bring huge challenges to the utilization of urban water resources and increase the high maintenance costs of local government management departments in the later stage. In addition, if the defects and leakage locations in the urban underground sewage pipe network cannot be checked in time, it will inevitably cause urban waterlogging and sewage backflow into rivers, bringing a series of disasters such as disease transmission and environmental pollution to the city, seriously affecting the operation of the city and the normal life of residents, and threatening people's lives and property safety. Therefore, it is very urgent to select a suitable underground sewage discharge pipe network leakage monitoring method and improve the underground sewage discharge pipe network inspection capability.

[0005] Up to now, the main monitoring methods for urban underground sewage pipe network leakage include manual monitoring, instrument monitoring, water balance testing, etc., which mainly rely on technical personnel to conduct on-site inspections along the water supply network to observe whether there are obvious leakage points, and use radar, ultrasound and other special monitoring instruments to assist in checking whether there are hidden leakage points, and judge the leakage situation and specific location by the sound of water leakage. However, the traditional leakage monitoring method requires a lot of manpower and time to continue, and has high professional and quality requirements for practitioners. It also has insufficient detection capabilities for non-metallic pipes and limited applicability. In addition, high-density electrical method can also be used to detect leakage in urban underground sewage pipe networks. This method targets the location of local abnormalities and judges the location and degree of damage of abnormal points by feedback on the changes in underground resistivity. However, this method is mostly used for detailed investigation, and is more used for confirmation and fixed-point monitoring of suspected leakage areas, and cannot be used to find leakage locations in large areas of cities. Summary of the invention

[0006] In view of the shortcomings of the traditional urban underground sewage pipe network leakage monitoring method, the present invention provides a method and a monitoring device for underground pipe network leakage location, which uses remote sensing means to detect the leakage location of underground pipe networks within a large area of ​​the city. Exemplarily, the monitoring method and the monitoring device are described using an underground sewage pipe network as an example. Those skilled in the art should understand that the monitoring method and the monitoring device of the present invention can also be used to monitor the damage points of other similar underground pipe networks.

[0007] The basic principle of this method is that when the underground sewage pipe network is damaged, the sewage in the pipe network will infiltrate and diffuse into the soil. The leaked water is often adsorbed on the surface of soil particles or stored between soil pores. Through the capillary action of soil particles, the soil moisture will change. The condition of soil surface moisture can also directly reflect the degree of pipeline damage. In bare soil areas, the soil moisture content will increase significantly, and the backscattering coefficient of the ground objects obtained by microwave radar images is particularly sensitive to soil moisture. It can be used for accurate inversion of soil mass moisture content, thereby further determining the leakage location of the underground sewage pipe network. Therefore, the detection of the leakage location of the urban underground sewage pipe network based on satellite remote sensing can achieve full coverage from source control of pollution sources to pollution control at the end.

[0008] In a first aspect, an embodiment of the present invention provides a method for monitoring leakage locations of an underground pipe network, the method comprising:

[0009] Acquire a radar remote sensing image of the area to be monitored, wherein the radar remote sensing image includes: a vertical polarization radar component image, a cross-polarization radar component image, and a radar signal incident angle component image;

[0010] Acquire an optical remote sensing image of the area to be monitored, wherein the optical remote sensing image includes: a red light band component image, a near infrared band component image, a short wave infrared band component image, and a mid infrared band component image;

[0011] Acquire ground data of the area to be monitored, wherein the ground data includes: location information of soil sampling points, soil mass water content of soil sampling points, underground pipe network distribution map and location information of historical leakage points;

[0012] Extracting the backscattering coefficient and the radar signal incident angle of the radar remote sensing image, and extracting the reflectivity value of each band of the optical remote sensing image;

[0013] Calculating the soil backscattering coefficient of the area to be monitored according to the backscattering coefficient, the incident angle of the radar signal, and the reflectivity values ​​of each band, and calculating the normalized building index of the area to be monitored according to the reflectivity values ​​of each band;

[0014] Determining a bare soil backscatter coefficient of the area to be monitored based on the soil backscatter coefficient and the normalized building index;

[0015] Extracting bare soil backscattering coefficients and radar signal incident angle information of soil sampling points in the area to be monitored;

[0016] Using the soil sampling points in the to-be-monitored area as training sample points of a soil moisture recognition model, and training the soil moisture recognition model to obtain a target soil moisture recognition model;

[0017] Inputting the bare soil backscattering coefficient into the target soil moisture identification model, and determining the soil mass moisture content of the to-be-monitored area through the target soil moisture identification model;

[0018] Compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored;

[0019] The step of calculating the soil backscatter coefficient of the area to be monitored includes:

[0020] Calculate the normalized water index image of the area to be monitored; calculate the remote sensing component image of vegetation moisture content in the area to be monitored based on the normalized water index image; calculate the radar signal attenuation factor of the area to be monitored based on the remote sensing component image of vegetation moisture content; calculate the vegetation backscatter coefficient of the area to be monitored based on the radar signal attenuation factor; calculate the soil backscatter coefficient of the area to be monitored based on the vegetation backscatter coefficient.

[0021] In some embodiments, before comparing the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored, the monitoring method further includes:

[0022] The leakage soil mass moisture content threshold of the area to be monitored is determined according to the soil mass moisture content at the historical leakage point position in the area to be monitored and the soil mass moisture content at the random position point in the area to be monitored.

[0023] In a second aspect, an embodiment of the present invention provides a monitoring device used in the aforementioned underground pipe network leakage location monitoring method, the device comprising:

[0024] A bare soil backscatter coefficient determination module is used to determine the bare soil backscatter coefficient of the area to be monitored;

[0025] A soil moisture inversion module is used to input the bare soil backscattering coefficient into a target soil moisture identification model, and determine the soil mass moisture content of the area to be monitored through the target soil moisture identification model;

[0026] The suspected leakage point determination module is used to compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored.

[0027] In some embodiments, the suspected leakage point determination module further comprises:

[0028] The leakage soil mass moisture content threshold determination module is used to determine the leakage soil mass moisture content threshold of the area to be monitored based on the soil mass moisture content of the historical leakage points in the area to be monitored and the soil mass moisture content of random positions in the area to be monitored.

[0029] In a third aspect, some embodiments of the present invention provide a computer program product, comprising computer program instructions, wherein when the computer program instructions are read and executed by a processor, the method described in any one of the embodiments of the first aspect is executed.

[0030] In a fourth aspect, some embodiments of the present invention provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the embodiments included in the first aspect can be implemented.

[0031] The solution involved in the present invention can solve the shortcomings of traditional methods of pipe network detection, such as being time-consuming, labor-intensive, and requiring high professional quality of practitioners. At the same time, it can solve the problems of special tools and instruments being time-consuming, labor-intensive, sensitive, and expensive. It can also break through the limitation of existing methods that cannot realize the location investigation of underground pipe network leakage in a large area, and finally realize the large-scale, accurate, rapid, non-destructive, and automated screening of urban underground pipe network leakage locations using multi-source remote sensing image data. The advantage of the present invention is that the underground pipe network leakage monitoring method based on multi-source remote sensing images can not only greatly improve the screening accuracy of underground pipe network leakage locations, but also save detection time, facilitate dynamic observation and comparison of leakage location points at different times and spaces, and greatly reduce the cost of leakage location detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flow chart of a method for monitoring leakage locations of underground pipe networks provided by an embodiment of the present invention;

[0034] Figure 2 A flow chart for determining the bare soil backscatter coefficient of the area to be monitored provided by an embodiment of the present invention;

[0035] Figure 3 A flow chart for determining the soil quality moisture content image of the area to be monitored provided by an embodiment of the present invention;

[0036] Figure 4 A block diagram of the composition of a device for monitoring leakage positions of underground pipe networks provided by an embodiment of the present invention;

[0037] Figure 5 A schematic diagram of the composition of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the embodiments of the present invention will be further described below. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein. Obviously, the embodiments in the specification are only some embodiments of the present invention, not all embodiments.

[0040] The terms and explanations involved in the present invention are as follows:

[0041] Backscatter coefficient: The backscatter coefficient is an index extracted from radar remote sensing images, which is used to measure the scattered energy returned to the sensor after the radar wave encounters the surface target (such as vegetation, soil or water body). The value of the backscatter coefficient depends on the incident angle of the radar and the physical characteristics of the surface, such as roughness and water content.

[0042] Radar signal incident angle: The incident angle refers to the angle between the radar beam and the surface normal. It is a key parameter of radar observation and is usually recorded in the metadata of the image. The incident angle affects the scattering pattern and intensity of the radar wave, and also determines the interaction between the beam and the surface. It is an important reference when analyzing the backscatter coefficient.

[0043] Normalized Difference Water Index (NDWI): It is a normalized ratio index based on the green band and the near-infrared band. It is usually used to extract water information from images, and is often calculated based on the ratio of the reflectance of the shortwave infrared (SWIR) and near-infrared (NIR) bands.

[0044] Soil mass moisture content: Soil mass moisture content is the percentage of water in the soil to the total mass of the soil. It is related to the dielectric properties of the soil and significantly affects the backscattering of radar waves. The higher the moisture content, the greater the intensity of radar scattering.

[0045] Vegetation moisture content: refers to the proportion of water in vegetation, usually expressed as a percentage. Vegetation moisture content has a greater attenuation effect on radar waves, especially for microwave bands, where higher vegetation moisture content will significantly reduce backscattered signals.

[0046] Radar signal attenuation factor: The attenuation factor describes the energy loss caused by absorption and scattering when the radar wave penetrates the surface medium (such as atmosphere, vegetation or soil). This factor is a key parameter in model calculation, especially in the water cloud model to reflect the impact of vegetation or atmosphere on radar signals.

[0047] Vegetation backscatter coefficient: Vegetation backscatter coefficient refers to the energy intensity returned to the antenna after the radar wave interacts with the vegetation. Its size is affected by the type, density, structure and water content of the vegetation, and is an important indicator for evaluating vegetation characteristics.

[0048] Soil backscatter coefficient: Soil backscatter coefficient refers to the energy intensity returned after the radar wave interacts with the soil surface. This coefficient is affected by the type, moisture content and surface roughness of the soil and is used to monitor soil moisture and physical properties.

[0049] Normalized difference building index (NDBI): It is a remote sensing index used to evaluate the distribution of urban buildings and the degree of urbanization. It is an effective tool for extracting urban building information. NDBI is usually calculated based on the ratio of short-wave infrared (SWIR) and near-infrared (NIR) bands. This index is mainly used to enhance building features and identify building areas in images.

[0050] Bare soil backscatter coefficient: The bare soil backscatter coefficient represents the energy intensity of the radar wave returning to the sensor after interacting with the bare soil surface. It is mainly used to evaluate the roughness and moisture content of the soil. The bare soil backscatter coefficient excludes the influence of vegetation and other covering materials and is usually used for bare soil moisture monitoring.

[0051] In the present invention, the monitoring method and monitoring device of the underground pipe network leakage position are described by way of example by taking the underground sewage pipe network as an example. Those skilled in the art should understand that the monitoring method and monitoring device of the present invention can also be applied to monitor the damage points of other similar underground pipe networks.

[0052] In actual scenarios, when the underground sewage pipe network is damaged, the sewage in the pipe network will infiltrate and diffuse into the soil. The leaked water is often adsorbed on the surface of soil particles or stored between soil pores. Through the capillary action of soil particles, the soil moisture will change. The condition of soil surface moisture can also directly reflect the degree of pipe damage. In bare soil areas, the soil moisture content will increase significantly, and the backscattering coefficient of the ground object obtained by microwave radar images is particularly sensitive to soil moisture, which can be used for the accurate inversion of soil mass moisture content, thereby further determining the leakage location of the underground sewage pipe network.

[0053] Figure 1 A method for monitoring the leakage position of an underground pipe network provided by an embodiment of the present invention comprises the following steps:

[0054] Step S1, obtaining the bare soil backscattering coefficient of the area to be monitored;

[0055] Step S2, inputting the bare soil backscattering coefficient into a target soil moisture identification model, and determining the soil mass moisture content of the to-be-monitored area through the target soil moisture identification model;

[0056] Step S3: Compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored.

[0057] The target soil moisture identification model in this embodiment is a machine learning model, which can be implemented by a random forest machine learning model. Those skilled in the art should understand that the target soil moisture identification model of the present invention can also be implemented by other types of machine learning models that can achieve corresponding functions.

[0058] In this embodiment, the bare soil backscattering coefficient of the area to be monitored is input into the target soil moisture identification model to invert the soil mass moisture content of the area to be monitored, and the soil mass moisture content of the area to be monitored is compared with the leakage soil mass moisture content threshold of the area to be monitored, so as to determine the leakage point of the underground pipeline located in the area to be monitored.

[0059] like Figure 2 As shown, in some embodiments of the present invention, step S1 exemplarily includes steps S11 to S15:

[0060] Step S11, obtaining radar remote sensing images, optical remote sensing images and ground data of the area to be monitored.

[0061] Among them, step S11 can be further decomposed into three sub-steps: step S111, step S112 and step S113.

[0062] Step S111: Acquire radar remote sensing images.

[0063] Exemplarily, in this embodiment, the space-borne aerospace radar remote sensing image of the area to be monitored is downloaded on the Google Earth Engine (GEE) platform. In order to ensure the scope and accuracy of the subsequent soil mass water content inversion and increase the inversion depth of the soil mass water content, the present invention intends to obtain a synthetic aperture radar remote sensing image P with a wavelength greater than the C band and a radar signal with vertical polarization and cross polarization. The synthetic aperture radar remote sensing image P includes a vertically polarized radar component image P vv , cross-polarization radar component image P vh , and the radar signal incident angle component image A. Among them, the synthetic aperture radar remote sensing image P, the vertical polarization radar component image P vv , cross-polarization radar component image P vh , and the image size of the radar signal incident angle component image A are both m rows and n columns.

[0064] Step S112: Acquire optical remote sensing images.

[0065] For example, in this embodiment, a multispectral optical remote sensing image with high spatial resolution of the monitored area is downloaded from the GEE platform. The spectral band of the optical remote sensing image needs to include a band range from the visible light band to the mid-infrared band, and the optical remote sensing image is recorded as L. Among them, the red light band component image of the optical remote sensing image is recorded as L red The near-infrared band component image of the optical remote sensing image is recorded as L vir The short-wave infrared band component image of the optical remote sensing image is recorded as L sir The mid-infrared band component image of the optical remote sensing is recorded as L mir .

[0066] In this embodiment, the platform for downloading radar remote sensing images and optical remote sensing images is exemplarily implemented by the GEE platform. Those skilled in the art should understand that the platform can also be implemented by other public data platforms with corresponding functions.

[0067] Step S113: Acquire ground data. In this embodiment, the ground data specifically includes:

[0068] (1) Location information of sampling points:

[0069] On Baidu Map, k sampling points are randomly selected in the monitoring area to ensure that all sampling points are evenly distributed in the entire monitoring area. The sampling points are numbered P. a (a=1, 2, 3...., k), each sampling point records its location information, including longitude information X a (a=1, 2, 3...., k) and latitude information Y a (a=1, 2, 3...., k).

[0070] (2) Soil mass moisture content at the sampling point:

[0071] Use the handheld GPS coordinates to find the location of each sampling point in the monitored area, use a circular knife and a shovel to collect soil samples at each location, the sampling depth of the soil sample is 0-10 cm, and the soil samples of each sampling point are placed in a plastic ziplock bag for sealing. Use an electronic scale to measure the total weight M of each soil sample and ziplock belt a (a=1, 2,3...., k), use an electronic scale to weigh the ziplock bag without any object and record the result as M0, dry each soil sample in the ziplock bag in an oven at 105 degrees Celsius for 12 hours, and consider all soil samples to be completely dry, then use an electronic scale to weigh the total weight of the dry samples in the ziplock bag again and record the weighing result as m a (a=1, 2, 3...., k). Using formula S a=(M a -m a ) / (M a -M0) calculate the soil mass moisture content S of the ath soil sample a (a=1, 2, 3...., k).

[0072] (3) Distribution map of underground pipeline network:

[0073] Collect the overall distribution map of the underground pipeline network in the area to be monitored from the urban planning department in the area, and record the overall distribution map of the pipeline network as G.

[0074] (4) Location information of historical leakage points:

[0075] Obtain q known historical leakage points P in the area to be monitored from the municipal management department b (b=1, 2, 3...., q) location information, including longitude information X b (b=1, 2, 3...., q) and latitude information Y b (b=1, 2, 3...., q).

[0076] It should be noted that, in this embodiment, there is no order requirement for the execution of the three sub-steps S111, S112 and S113, that is, the operations of obtaining radar remote sensing images of the area to be monitored, obtaining optical remote sensing images of the area to be monitored, and obtaining ground data of the area to be monitored can be performed simultaneously or in any order.

[0077] Step S12: extracting the backscattering coefficient and the radar signal incident angle of the radar remote sensing image of the area to be monitored, and the reflectivity value of each band of the optical remote sensing image.

[0078] Wherein, step S12 can be further decomposed into two sub-steps: step S121 and step S122. Step S121, extracting the backscatter coefficient of the radar remote sensing image and the radar signal incident angle.

[0079] In ArcGIS software, the radar remote sensing images are preprocessed by multi-view, geometric correction and radiation correction, and the preprocessing results of the radar remote sensing images are recorded as P ’ The preprocessed vertical polarization radar component image is recorded as P vv ’ , the preprocessed cross-polarization radar component image is recorded as P vh ’ The incident angle component image of the preprocessed radar signal is recorded as A ’ .

[0080] Among them, the preprocessed vertical polarization radar component image Pvv ’ Each pixel value in represents the backscatter coefficient value σ of the actual ground point corresponding to the pixel in the vertical polarization mode vv 0 (i, j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n. Preprocessed cross-polarization radar component image P vh ’ Each pixel value in represents the backscatter coefficient value σ of the actual ground point corresponding to the pixel in the cross-polarization mode vh 0 (i, j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n. Preprocessed radar signal incident angle component image A ’ Each pixel value in represents the incident angle θ(i,j) of the radar signal received by the actual ground point corresponding to the pixel, i is the row number of the image, and the value range of i is between 1 and m, and j is the column number of the image, and the value range of j is between 1 and n.

[0081] Step 122: extract the reflectivity value of each band of the optical remote sensing image.

[0082] In ArcGIS software, the optical remote sensing image is preprocessed by geometric correction and radiation correction, and resampled to the same spatial resolution as the radar remote sensing image. The preprocessed and resampled optical remote sensing image is recorded as L ’ , the red light band component image of the optical remote sensing image after preprocessing and resampling is recorded as L red ’ , the near infrared band component image of the optical remote sensing image after preprocessing and resampling is recorded as L vir ’ , the short-wave infrared band component image of the optical remote sensing image after preprocessing and resampling is recorded as L sir ’ , the infrared band component image of the optical remote sensing image after preprocessing and resampling is recorded as L mir ’ After resampling, the above-mentioned preprocessed and resampled optical remote sensing image L ’ Its component images include L red ’ , L vir ’ , L sir ’ , L mir ’ The sizes of are the same as those of radar remote sensing images, which are m rows and n columns.

[0083] Among them, the red light band component image L of the optical remote sensing image after preprocessing and resampling red ’ Each pixel value in represents the reflectance value R of the actual ground point of the pixel in the red light band red (i, j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n; the near-infrared band component image L of the optical remote sensing image after preprocessing and resampling vir ’ Each pixel value in represents the reflectance value R of the actual ground point of the pixel in the near-infrared band vir (i, j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n; the short-wave infrared band component image L of the optical remote sensing image after preprocessing and resampling sir ’ Each pixel value in represents the reflectivity value R of the actual ground point of the pixel in the short-wave infrared band sir (i, j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n; the infrared band component image L of the optical remote sensing image after preprocessing and resampling mir ’ Each pixel value in represents the reflectance value R of the actual ground point of the pixel in the mid-infrared band mir (i,j), i is the row number of the image, the value range of i is between 1 and m, j is the column number of the image, the value range of j is between 1 and n.

[0084] It should be noted that, in this embodiment, there is no order requirement for the execution of the above two sub-steps S121 and S122, that is, the operations of extracting the backscattering coefficient and the incident angle of the radar signal of the area to be monitored and extracting the reflectivity value of each band of the optical remote sensing image can be performed simultaneously or in any order.

[0085] Step S13: Calculate the soil backscatter coefficient of the area to be monitored.

[0086] Wherein, step S13 further includes sub-steps S131 to S135.

[0087] Step S131, calculating a normalized water index image of the area to be monitored.

[0088] Using the formula NDWI(i,j)=(R vir (i,j)-R sir (i,j)) / (R vir (i,j)+R sir(i,j)) calculates the normalized water index NDWI(i,j) of each pixel in the monitored area, i is the row number of the image involved in the calculation, and the value range of i is between 1 and m, j is the column number of the image involved in the calculation, and the value range of j is between 1 and n. All pixels constitute the normalized water index image NDWI of the monitored area.

[0089] Step S132: Calculate the remote sensing component image of vegetation moisture content in the area to be monitored.

[0090] According to the normalized water index NDWI(i,j) of each pixel in the normalized water index image NDWI, the formula VWC(i,j)=1.44×NDWI(i,j) is used. 2 +1.36×NDWI(i,j)+0.34, calculate the vegetation water content VWC(i,j) in each pixel. The vegetation water content VWC(i,j) of all pixels constitutes the remote sensing component image VWC of the vegetation water content in the monitored area. i is the row number of the image involved in the calculation, and the value range of i is between 1 and m. j is the column number of the image involved in the calculation, and the value range of j is between 1 and n.

[0091] Step S133: Calculate the radar signal attenuation factor of the area to be monitored

[0092] Combined with the vegetation moisture content VWC(i, j) of each pixel in the vegetation moisture remote sensing component image VWC of the monitored area and the radar signal incident angle θ(i, j) of the pixel, the formula τ 2 =e (-0.182×VWC×secθ) Calculate vegetation coverage on preprocessed radar remote sensing image P ’ The radar signal attenuation factor τ of each pixel is 2 (i,j), i is the row number of the image involved in the calculation, and its value range is between 1 and m; j is the column number of the image involved in the calculation, and its value range is between 1 and n.

[0093] Step S134: Calculate the vegetation backscatter coefficient of the area to be monitored

[0094] Finally, combined with the preprocessed radar remote sensing image P ’ The radar signal attenuation factor τ of each pixel in 2 (i, j), the incident angle of the radar signal at each pixel point θ(i, j), the vegetation water content VWC(i, j) of each pixel, using the formula σ veg 0 =0.0012×VWC×cosθ×(1−τ 2 ) Calculate the preprocessed radar remote sensing image P in the area to be monitored ’ The vegetation backscatter coefficient σ of each radar pixel in veg0 (i,j), i is the row number of the image involved in the calculation, and its value range is between 1 and m; j is the column number of the image involved in the calculation, and its value range is between 1 and n.

[0095] Step S135: Calculate the soil backscatter coefficient of the area to be monitored

[0096] The backscatter coefficient value σ of each pixel point in the preprocessed radar vertical polarization component image is vv 0 (i, j), using the vegetation backscatter coefficient value σ extracted from the pixel point veg 0 (i, j), and the radar signal attenuation factor τ at the pixel position 2 (i,j), using the formula σ vv-soil 0 = σ vv 0 −σ veg 0 / τ 2 Calculate the soil backscattering coefficient σ of the pixel point under vertical polarization vv-soil 0 (i, j), i is the row number of the image involved in the calculation, and the value range of i is between 1 and m, j is the column number of the image involved in the calculation, and the value range of j is between 1 and n. The soil backscatter coefficient of all pixels in the monitored area under vertical polarization is saved as the soil backscatter coefficient component map P under vertical polarization vv ’’ .

[0097] The backscatter coefficient σ of each pixel point in the preprocessed radar cross-polarization component image is vh 0 (i, j), using the vegetation backscatter coefficient value σ extracted from the pixel point veg 0 (i, j), and the radar signal attenuation factor τ at the pixel position 2 (i,j), using the formula σ vh-soil 0 = σ vh 0 −σ veg 0 / τ 2 , calculate the soil backscattering coefficient σ of the pixel point under cross-polarization mode vh-soil 0(i, j), i is the row number of the image involved in the calculation, and the value range of i is between 1 and m, j is the column number of the image involved in the calculation, and the value range of j is between 1 and n. The soil backscatter coefficient of all pixels in the monitored area under the cross-polarization mode is saved as the soil backscatter coefficient component map P under the cross-polarization mode vh ’’ .

[0098] Step S14: Calculate the normalized building index of the area to be monitored.

[0099] For the optical remote sensing image L after preprocessing and resampling ’ , using the near infrared band component image L of the optical remote sensing image after preprocessing and resampling vir ’ The near-infrared band reflectance value R of each pixel in vir (i, j), and the infrared band component image L of the optical remote sensing image after preprocessing and resampling mir ’ The mid-infrared band reflectance value R of each pixel mir (i,j), using the formula NDBI(i,j)=(R mir (i,j)-R vir (i,j)) / (R mir (i,j)+R vir (i,j)) calculates the optical remote sensing image L after preprocessing and resampling in the area to be monitored ’ The normalized building index of each pixel in the image is plotted, and the building index image L of the area to be monitored is drawn. ’’ The building index image L in the area to be monitored ’’ In the figure, the value of each pixel is the normalized building index calculation result NDBI(i,j) of the pixel, i is the row number of the image involved in the calculation, and the value range of i is between 1 and m, and j is the column number of the image involved in the calculation, and the value range of j is between 1 and n.

[0100] It should be noted that, in this embodiment, there is no requirement for the execution order of step S13 and step S14, that is, step S13 and step S14 can be performed simultaneously or in any order.

[0101] Step S15, determining the bare soil backscatter coefficient map of the area to be monitored.

[0102] Draw a statistical histogram of the normalized building index NDBI (i, j) of all pixels. In this histogram, the horizontal axis represents the building index image L of the area to be monitored. ’’The calculation results of the various NDBI statistical values ​​(between -1 and 1) appearing in the graph, and the vertical axis represents the building index image L of the area to be monitored. ’’ The number of pixels corresponding to each NDBI statistical value in the NDBI statistical histogram. Since the NDBI statistical values ​​of buildings or hard surfaces are high, and the NDBI statistical values ​​of other features such as water bodies, vegetation, and soil are low, there are two significant peaks in the NDBI statistical histogram: one peak represents urban buildings or hard surface areas, and the other peak represents other non-building areas such as water bodies, vegetation, or soil.

[0103] The NDBI value of the horizontal coordinate corresponding to the lowest point of the curve shape between the two peaks in the histogram is determined as the NDBI threshold T1 for distinguishing buildings or hard ground from other types of ground objects. ’’ The brightness values ​​of all pixels with NDBI values ​​greater than T1 are uniformly set to 1, and the brightness values ​​of all pixels with NDBI values ​​less than T1 are uniformly set to 0, thereby generating a binary image L of the building index image of the area to be monitored. ’’’ .

[0104] Record the binary image L of the building index image of the area to be monitored ’’’ All pixel positions with brightness value 1 in .

[0105] Soil backscatter coefficient component diagram P under vertical polarization vv ’’ In the example, the binary image L of the building index image in all the monitored areas is ’’’ All points corresponding to the pixel positions with brightness values ​​of 1 in the image are deleted, so as to obtain the bare soil backscattering coefficient image P under vertical polarization mode. vv ’’’ , bare soil backscattering coefficient image P in vertical polarization mode vv ’’’ In the example, the value of each pixel is σ vv-soil 1 (i,j), i is the row number of the image involved in the calculation, and its value range is between 1 and m; j is the column number of the image involved in the calculation, and its value range is between 1 and n.

[0106] Soil backscatter coefficient component diagram P under cross-polarization mode vh ’’ In the example, the binary image L of the building index image in all the monitored areas is ’’’ All points corresponding to the pixel positions with brightness values ​​of 1 in the image are deleted, so as to obtain the bare soil backscattering coefficient image P under the cross-polarization mode. vh ’’’, bare soil backscatter coefficient image P in cross-polarization mode vh ’’’ In the example, the value of each pixel is σ vh-soil 1 (i,j), i is the row number of the image involved in the calculation, and its value range is between 1 and m; j is the column number of the image involved in the calculation, and its value range is between 1 and n.

[0107] like Figure 3 As shown, in some embodiments of the present invention, step S2 exemplarily includes steps S21 to S23:

[0108] Step S21, extracting bare soil backscattering coefficient image information and radar signal incident angle information of the soil sampling point.

[0109] For the bare soil backscattering coefficient image P under vertical polarization vv ’’’ and bare soil backscattering coefficient image P under cross polarization mode vh ’’’ , extract the following information:

[0110] Each soil sampling point P a (a=1,2,3...., k) Bare soil backscatter coefficient σ under vertical polarization of radar vv-soil 1 (a)

[0111] Each soil sampling point P a (a=1,2,3...., k) Bare soil backscatter coefficient σ in radar cross-polarization mode vh-soil 1 (a)

[0112] Each soil sampling point P a (a=1,2,3...., k) The difference between the bare soil backscattering coefficient under vertical polarization and the bare soil backscattering coefficient under cross polarization is σ vv-soil 1 (a)-σ vh-soil 1 (a)

[0113] Each soil sampling point P a (a=1,2,3...., k) The sum of the bare soil backscattering coefficient in vertical polarization mode and the bare soil backscattering coefficient in cross polarization mode σ vv-soil 1 (a)+σ vh-soil 1 (a)

[0114] Each soil sampling point P a(a=1,2,3...., k) The ratio of the bare soil backscattering coefficient under vertical polarization to the bare soil backscattering coefficient under cross polarization σ vv-soil 1 (a) / σ vh-soil 1 (a)

[0115] And each soil sampling point P a (a=1,2,3...., k) radar signal incident angle θ(a).

[0116] Step S22: All sampling points are used as training sample points of the random forest machine learning model to train the random forest machine learning model. The independent variables of the machine learning model include the following:

[0117] Training sample point P a (a=1,2,3...., k) Bare soil backscatter coefficient σ under vertical polarization of radar vv-soil 1 (a)

[0118] Training sample point P a (a=1,2,3...., k) Bare soil backscatter coefficient σ in radar cross-polarization mode vh-soil 1 (a)

[0119] Training sample point P a (a=1,2,3...., k) The difference between the bare soil backscatter coefficient under the vertical polarization mode of the radar and the bare soil backscatter coefficient under the cross polarization mode σ vv-soil 1 (a)-σ vh-soil 1 (a)

[0120] Training sample point P a (a=1,2,3...., k) The sum of the bare soil backscatter coefficient under the vertical polarization mode of the radar and the bare soil backscatter coefficient under the cross polarization mode σ vv-soil 1 (a)+σ vh-soil 1 (a)

[0121] Training sample point P a (a=1,2,3...., k) The ratio of the bare soil backscatter coefficient under the vertical polarization mode of the radar to the bare soil backscatter coefficient under the cross polarization mode σ vv-soil 1 (a) / σ vh-soil 1 (a)

[0122] And the training sample point P a (a=1,2,3...., k) radar signal incident angle θ(a).

[0123] Each training sample point P a The soil mass moisture content of (a=1,2,3...., k) was used as the dependent variable to train a random forest machine learning model for soil mass moisture content inversion.

[0124] The random forest machine learning model consists of multiple decision trees, and the data of each decision tree is composed of different data subsets randomly extracted from the training data set. As the number of decision trees increases, the overall prediction accuracy of the random forest machine learning model gradually improves. The prediction results of each decision tree are averaged by ensemble learning, and the inversion value of soil mass moisture content is finally output. The random forest machine learning model belongs to supervised training. During the training process, a set of known label data is used, that is, the soil mass moisture content of the training sample points, that is, the sampling points. These label data are used as the output parameters of the model, and are used together with the input independent variables to train and optimize the model, so that when new input data is given, the trained random forest machine learning model can realize the inversion of all soil mass moisture content in the entire monitored area.

[0125] Step S23, applying the random forest machine learning model to the entire monitored area to realize the inversion of the soil quality water content in the entire monitored area. The inversion result image of all soil quality water content in the entire monitored area is recorded as I, and in the inversion result image I of all soil quality water content in the monitored area, the soil quality water content value of each pixel is recorded as IW(i,j), i is the image row number involved in the calculation, and the value range of i is between 1 and m, and j is the image column number involved in the calculation, and the value range of j is between 1 and n.

[0126] Further, in some embodiments of the present invention, step S3 exemplarily includes steps S31-S32:

[0127] Step S31, determining the moisture content threshold of the leaked soil mass in the area to be monitored.

[0128] For the q known historical leakage points P in the monitored area obtained from the municipal management department b (b=1, 2,3...., q) longitude information x b (b=1, 2, 3...., q) and latitude information y b (b=1, 2, 3...., q), extract the historical leakage point P bSoil mass water content machine learning model inversion results IWQS b (b=1, 2, 3...., q), calculate the mean IWQS of the inversion results of the soil mass moisture content machine learning model for all historical leakage points.

[0129] Next, in the soil quality moisture content image I of the entire monitoring area, s random position points U are randomly selected again c (c=1, 2, 3...., s), extract the soil mass water content machine learning model inversion result IWNS at each random location c (c=1, 2, 3...., s), calculate the mean IWNS of the soil mass water content machine learning model inversion results of all random locations.

[0130] According to the formula T2=(IWQS+IWNS) / 2, the leakage soil mass moisture content threshold T2 for extracting the leakage point is determined.

[0131] Step S32: determine the leakage point of the underground pipeline in the area to be monitored.

[0132] Select a square sliding window with a side length of 100 pixels, use this window to traverse all soil mass water content images I in the entire monitored area, calculate the mean IW(u) of the soil mass water content IW(i,j) of all pixels in the traversal window, record and mark the total number of windows f in the entire image whose mean soil mass water content IW(u) is greater than the leakage soil mass water content threshold T2, where u is the window sequence number, u=1,2,3...f. The window area where the mean soil mass water content IW(u) of the pixels in all windows is greater than T2 is saved as the traversal window area image Z, and the windows where the mean soil mass water content of the pixels in other windows is less than or equal to T2 are discarded. The image is composed of the above f windows.

[0133] Taking each pipeline in the overall distribution map G of the pipeline network as the center point, a linear pipeline network buffer image G with a width of 100 pixels is established in the monitored area. ’ , and the linear pipe network buffer image G ’ Overlay with the marked traversal window area image Z and select the linear pipe network buffer image G ’ All complete window areas within the range will fall on the linear pipe network buffer image G ’ The number of window regions within the range is recorded as t.

[0134] Finally, the intersection of the center point of each buffer zone window area and the vertical line of the underground pipeline network is taken as the final suspected underground pipeline network leakage location point, and the location information of all t predicted leakage points is recorded, including the longitude information xd (d=1, 2, 3...., t) and latitude information y d (d=1, 2, 3...., t).

[0135] Figure 4 The present invention provides an underground pipe network leakage location monitoring device 400, which is similar to the above-mentioned Figure 1 The device 400 for monitoring the leakage position of underground pipe network includes the following modules:

[0136] A bare soil backscatter coefficient determination module 410 is used to determine the bare soil backscatter coefficient of the area to be monitored;

[0137] A soil moisture inversion module 420 is used to input the bare soil backscattering coefficient into a target soil moisture identification model, and determine the soil mass moisture content of the to-be-monitored area through the target soil moisture identification model;

[0138] The suspected leakage point determination module 430 is used to compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored.

[0139] Furthermore, in some embodiments of the present invention, the suspected leakage point determination module 430 further includes:

[0140] The leakage soil mass moisture content threshold determination module 440 is used to determine the leakage soil mass moisture content threshold of the area to be monitored by combining the soil mass moisture content of the historical leakage points in the area to be monitored and the soil mass moisture content of the random points in the area to be monitored;

[0141] The suspected leakage point determination module 430 further determines the leakage point of the underground pipeline located in the area to be monitored based on the leakage soil mass moisture content threshold determined by the leakage soil mass moisture content threshold determination module 440.

[0142] Those skilled in the art should understand that the device provided in the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for the parts not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the aforementioned devices and modules can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0143] The devices or modules described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0144] Some embodiments of the present invention provide a computer program product, including computer program instructions, which, when read and executed by a processor, execute a method in any one of the embodiments included in the above-mentioned method for monitoring leakage locations of underground pipe networks.

[0145] like Figure 5 As shown, some embodiments of the present invention provide an electronic device 500, including a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520, wherein the processor 520 can implement a method in any one of the embodiments included in the above-mentioned method for monitoring the leakage location of an underground pipeline network when reading and executing the program through a bus 530.

[0146] Processor 520 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 520 can be a microprocessor.

[0147] The memory 510 may be used to store instructions executed by the processor 520 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some functions or all functions of one or more modules described in the embodiments of the present invention. The processor 520 of the embodiment of the present invention may be used to execute instructions in the memory 510 to implement the methods shown in the foregoing embodiments. The memory 510 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memories known to those skilled in the art.

[0148] In the embodiment of the present invention, based on the highly sensitive characteristics of the backscatter coefficient of the radar remote sensing image under different polarization modes to the soil mass water content, remote sensing means are used to accurately and quickly invert the soil moisture content of the monitored area, and the soil surface mass water content threshold affected by the leakage point is determined in combination with the municipal underground pipe network distribution data and the abnormal condition of the soil surface mass water content, and the position of the leakage point in the entire monitored area is further located and checked in combination with the threshold. The monitoring method of the underground pipe network leakage position involves clear model parameter relationships, clear theoretical principles, practical solutions, fast monitoring process, large monitoring area, and high monitoring result accuracy.

[0149] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0150] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0151] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0152] The above description is only an embodiment of the present invention and is not intended to limit the scope of protection of the present invention. For those skilled in the art, the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0153] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0154] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for monitoring the leakage position of an underground pipe network, characterized in that: The method comprises: Acquire a radar remote sensing image of the area to be monitored, wherein the radar remote sensing image includes: a vertical polarization radar component image, a cross-polarization radar component image, and a radar signal incident angle component image; Acquire an optical remote sensing image of the area to be monitored, wherein the optical remote sensing image includes: a red light band component image, a near infrared band component image, a short wave infrared band component image, and a mid infrared band component image; Acquire ground data of the area to be monitored, wherein the ground data includes: location information of soil sampling points, soil mass water content of soil sampling points, underground pipe network distribution map and location information of historical leakage points; Extracting the backscattering coefficient and the radar signal incident angle of the radar remote sensing image, and extracting the reflectivity value of each band of the optical remote sensing image; Calculating the soil backscattering coefficient of the area to be monitored according to the backscattering coefficient, the incident angle of the radar signal, and the reflectivity values ​​of each band, and calculating the normalized building index of the area to be monitored according to the reflectivity values ​​of each band; Determining a bare soil backscatter coefficient of the area to be monitored based on the soil backscatter coefficient and the normalized building index; Extracting bare soil backscattering coefficients and radar signal incident angle information of soil sampling points in the area to be monitored; Using the soil sampling points in the to-be-monitored area as training sample points of a soil moisture recognition model, and training the soil moisture recognition model to obtain a target soil moisture recognition model; Inputting the bare soil backscattering coefficient into the target soil moisture identification model, and determining the soil mass moisture content of the to-be-monitored area through the target soil moisture identification model; Compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored; The step of calculating the soil backscatter coefficient of the area to be monitored includes: Calculate the normalized water index image of the area to be monitored; calculate the remote sensing component image of vegetation moisture content in the area to be monitored based on the normalized water index image; calculate the radar signal attenuation factor of the area to be monitored based on the remote sensing component image of vegetation moisture content; calculate the vegetation backscatter coefficient of the area to be monitored based on the radar signal attenuation factor; calculate the soil backscatter coefficient of the area to be monitored based on the vegetation backscatter coefficient.

2. The monitoring method according to claim 1, characterized in that: Before comparing the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored, the method further includes: The leakage soil mass moisture content threshold of the area to be monitored is determined according to the soil mass moisture content at the historical leakage point position in the area to be monitored and the soil mass moisture content at the random position point in the area to be monitored.

3. A monitoring device used in the method for monitoring the leakage position of an underground pipe network according to any one of claims 1 to 2, characterized in that: The device comprises: A bare soil backscatter coefficient determination module is used to determine the bare soil backscatter coefficient of the area to be monitored; A soil moisture inversion module is used to input the bare soil backscattering coefficient into a target soil moisture identification model, and determine the soil mass moisture content of the area to be monitored through the target soil moisture identification model; The suspected leakage point determination module is used to compare the soil mass moisture content of the area to be monitored with the leakage soil mass moisture content threshold of the area to be monitored to determine the leakage point of the underground pipeline in the area to be monitored.

4. The monitoring device according to claim 3, characterized in that: The suspected leakage point determination module further includes: The leakage soil mass moisture content threshold determination module is used to determine the leakage soil mass moisture content threshold of the area to be monitored based on the soil mass moisture content of the historical leakage points in the area to be monitored and the soil mass moisture content of random positions in the area to be monitored.

5. A computer program product, characterized in that The method comprises computer program instructions, which can implement the method according to any one of claims 1 to 2 when the computer program instructions are read and executed by a processor.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 2 can be implemented.

Images