Remote sensing image dynamic data processing system and method based on data analysis

Abstract

The invention discloses a remote sensing image dynamic data processing system and method based on data analysis, and belongs to the technical field of traffic. A display device database is constructed; road condition information of the inspection robot arriving at the display device is obtained, and the optimal route is selected to run to the position of the display device; constructing a multiple linear regression model, updating the acquisition frequency of the display equipment, and acquiring a remote sensing image of an image displayed by the display equipment; extracting a display image, and calculating an error value between the remote sensing image and the display image; when the error value is greater than or equal to an error threshold value, the position information of the display equipment is sent to a control center, a feedback detection result is abnormal, and a maintainer is pre-warned to carry out maintenance evaluation on site; when the inspection robot does not receive the maintenance assessment feedback within the specified time, secondary early warning is triggered to remind an administrator that the display equipment is not subjected to maintenance assessment; therefore, the inspection time is saved, and early warning of abnormal conditions is realized.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a remote sensing image dynamic data processing system and method based on data analysis. Background Art

[0002] Remote sensing images are image data of objects on the earth's surface or in the atmosphere obtained through remote sensing technology, mainly through sensors on remote sensing platforms. With the development of remote sensing technology, remote sensing images are applied to all aspects of people's lives. Remote sensing images are used to monitor environmental issues such as surface cover changes, water pollution, and air quality; remote sensing images are used to find natural resources such as mineral resources and water resources; to evaluate crop growth conditions, monitor pests and diseases, and plan farmland irrigation; to analyze urban planning elements such as urban expansion, transportation networks, and green space distribution; to quickly obtain image information of disaster sites to provide support for disaster relief and assessment, etc.

[0003] In the field of transportation, the inspection of display equipment is often carried out by staff at fixed times to check and maintain the display equipment. This inspection method consumes a lot of manpower and material resources. Therefore, how to combine remote sensing imaging technology to improve inspection efficiency and reduce the loss of manpower and material resources has become a problem we need to study. Summary of the invention

[0004] The purpose of the present invention is to provide a remote sensing image dynamic data processing system and method based on data analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A remote sensing image dynamic data processing method based on data analysis, the method comprising the following steps:

[0007] Step S1: constructing a display device database, wherein the display device database includes display device data and display device environment data;

[0008] Step S2: Obtaining the road condition information of the inspection robot to the display device, selecting the best route to run to the location of the display device, and collecting the remote sensing image of the display device through the remote sensing platform;

[0009] Step S3: before the remote sensing platform collects the remote sensing image of the display device display image, construct a multivariate linear regression model, update the collection frequency of the display device, and collect the remote sensing image of the display device display image;

[0010] Step S4: extract the display image, map the pixels at the same position on the remote sensing image, and calculate the error value between the remote sensing image and the display image; when the error value is greater than or equal to the error threshold, send the location information of the display device to the control center, feedback the abnormal detection result, and warn the maintenance personnel to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, it triggers a secondary warning to remind the administrator that the display device has not been evaluated for maintenance.

[0011] Furthermore, the specific implementation process of step S1 includes:

[0012] Construct a display device database, the display device database is used to store display device data and display device environment data; the display device data includes display device display image and location information; the display device environment data includes temperature and light intensity; the display device is fixedly set on the side of the traffic route to display traffic information.

[0013] Furthermore, the specific implementation process of step S2 includes:

[0014] Step S2.1: Based on the location information of the display device, connect to the Internet of Vehicles to obtain the road condition information of the inspection robot reaching the display device, the road condition information is the average speed of vehicles in each road section, the inspection robot is externally equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor, the remote sensing platform is used to collect remote sensing images of the display device display image, the temperature sensor is used to collect the real-time temperature of the environment at the display device location, and the light intensity sensor is used to collect the real-time light intensity at the display device location;

[0015] Step S2.2: Construct route set S = {s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes;

[0016] Step S2.3: route s according to the intersection n Segment and build segment set l m represents the length of the mth road segment, M represents the route s n The total number of segments;

[0017] Step S2.4: Based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v maxIndicates the maximum operating speed of the inspection robot. represents the average speed of vehicles on the mth road section;

[0018] Step S2.5: Calculate the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

[0019] The choice of the route determines the length of the inspection time. Choosing the best route can save inspection time and increase the utilization rate of the inspection robot, so that the inspection robot can complete the designated task in the shortest time. Since the lane width, number of lanes, road conditions and speed limits at different intersections are different, the traffic capacity of different intersections is also different. Therefore, it is necessary to connect to the Internet of Vehicles to obtain road condition information for the inspection robot to reach the display device, such as the average vehicle speed of each section of the road.

[0020] Furthermore, the specific implementation process of step S3 includes:

[0021] Step S3.1: Before the remote sensing platform collects the remote sensing image displayed by the display device, the real-time temperature and the real-time light intensity are normalized. Wherein, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the best ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the best ambient light intensity collected;

[0022] Step S3.2: Construct a multivariate linear regression model to dynamically analyze the clarity of remote sensing images and perform iterative processing. The expression formula is: p = α1e c +α2e -F +α3e -g +α4, where P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, and α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency;

[0023] Let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, preset the clarity threshold, and if the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform collects the remote sensing image of the display device display image according to the collection frequency during the iterative update.

[0024] The clarity of the captured image is closely related to the ambient temperature, light intensity and acquisition frequency. In a high temperature environment, the image will produce more noise points; the image acquisition device will increase its activity under high temperature, generating more random signals, which will interfere with the image signal and cause the image clarity to decrease; the light intensity directly affects the brightness and contrast of the image; proper lighting can ensure that the image is bright and clear. Under strong light conditions, the image acquisition device receives more light signals, and the converted electrical signals are also stronger, thus obtaining a brighter image, but too strong light may cause the image to be oversaturated, that is, the pixel value reaches or exceeds the maximum range of the image acquisition device, resulting in loss of image details and color distortion; the image acquisition frequency is an important indicator for measuring image clarity. The higher the acquisition frequency, the more image frames the image acquisition device collects per second, which means that more detailed information can be captured; in scenes with rich details, a high acquisition frequency can ensure that the details of the image are fully preserved, thereby improving the clarity of the image; and among the ambient temperature, light intensity and acquisition frequency, the ambient temperature and light intensity are uncontrollable, so the clarity can be improved by changing the acquisition frequency.

[0025] Furthermore, the specific implementation process of step S4 includes:

[0026] Step S4.1: retrieve the display image, and capture the pixel point (i, j) on the display image, where i and j represent the horizontal coordinate value and the vertical coordinate value of the pixel point respectively, and obtain the pixel value at the pixel point (i, j) on the display image, which is recorded as Y2(i, j); based on the pixel point (i, j), map the pixel point at the same position on the remote sensing image, and record the pixel value at the mapped pixel point on the remote sensing image as Y1(i, j);

[0027] Step S4.2: Calculate the error value between the remote sensing image and the display image: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image;

[0028] A preset error threshold is set. When the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment. When the inspection robot does not receive maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0029] The purpose of calculating the error value between the remote sensing image and the display image is to determine whether there is any abnormality in the display image of the display device. For example, the missing display image and the presence of abnormal spots in the display image will cause the error value between the remote sensing image and the display image to become larger. When the inspection robot does not receive maintenance assessment feedback within the specified time, it is necessary to warn the maintenance personnel again to prevent the maintenance personnel from missing the detection results.

[0030] A remote sensing image dynamic data processing system based on data analysis, the system comprising: a data storage module, a route planning module, an image acquisition module and an early warning module;

[0031] The data storage module is used to store display device data and display device environment data;

[0032] The route planning module includes a route planning unit and an optimal route selection unit, which is used to select the optimal route to reach the display device location;

[0033] The image acquisition module is used to calculate the acquisition frequency of the display device, acquire images from the display device, and pre-process the images;

[0034] The early warning module includes an error unit and an early warning unit. By extracting the display image, mapping the pixels at the same position on the remote sensing image, and calculating the error value between the remote sensing image and the display image, when the error value is greater than or equal to the error threshold, the position information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0035] Furthermore, the data storage module is used to construct a display device database, and the display device database is used to store display device data and display device environment data; the display device data includes display device display images, location information and operating status data; the display device environment data includes temperature and light intensity.

[0036] Further, the route planning module includes a route planning unit and an optimal route selection unit;

[0037] The route planning unit is connected to the Internet of Vehicles through the location information of the display device to obtain the road condition information of the inspection robot reaching the display device, wherein the road condition information is the average speed of vehicles in each road section. The inspection robot is externally equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor. The remote sensing platform is used to collect remote sensing images of the display device display image, the temperature sensor is used to collect the real-time temperature of the environment at the display device location, and the light intensity sensor is used to collect the real-time light intensity at the display device location. Construct a route set s={s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes;

[0038] The optimal route selection unit selects the route s according to the intersection n Segment and build segment set lm represents the length of the mth road segment, M represents the route s n The total number of segments; based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v max Indicates the maximum operating speed of the inspection robot. Represents the average speed of vehicles on the mth road section; calculates the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

[0039] Furthermore, the image acquisition module normalizes the real-time temperature and the real-time light intensity before the remote sensing platform acquires the remote sensing image displayed by the display device. Among them, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the optimal ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the optimal ambient light intensity collected; a multivariate linear regression model is constructed to dynamically analyze the clarity of remote sensing images and perform iterative processing. The expression formula is: p = α1e c +α2e -F +α3e -g +α4, where P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, and α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency; let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, and preset the clarity threshold. If the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform acquires the remote sensing image of the display device according to the acquisition frequency during the iterative update.

[0040] Further, the early warning module includes an error unit and an early warning unit;

[0041] The error unit retrieves the display image and captures the pixel point (i, j) on the display image, where i and j represent the horizontal coordinate value and the vertical coordinate value of the pixel point respectively, obtains the pixel value at the pixel point (i, j) on the display image, and records it as Y2(i, j); based on the pixel point (i, j), maps the pixel point at the same position on the remote sensing image, and records the pixel value at the mapped pixel point on the remote sensing image as Y1(i, j); calculates the error value between the remote sensing image and the display image: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image;

[0042] The early warning unit presets an error threshold. When the error value is greater than or equal to the error threshold, the early warning unit sends the location information of the display device to the control center, feedback that the detection result is abnormal, and warns the maintenance personnel to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary early warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a remote sensing image dynamic data processing system and method based on data analysis provided by the present invention, a display device database is constructed; road condition information for the inspection robot to reach the display device is obtained, and the best route is selected to run to the location of the display device; a multivariate linear regression model is constructed, the acquisition frequency of the display device is updated, and the remote sensing image of the display device display image is acquired; the display image is extracted, and the error value between the remote sensing image and the display image is calculated; when the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, the detection result is fed back to be abnormal, and the maintenance personnel are warned to go to the site for maintenance evaluation; when the inspection robot does not receive the maintenance evaluation feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance; thereby saving inspection time and realizing early warning of abnormal situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a structural schematic diagram of a remote sensing image dynamic data processing system based on data analysis of the present invention;

[0046] Figure 2 It is a schematic diagram of the steps of a remote sensing image dynamic data processing method based on data analysis of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0049] A remote sensing image dynamic data processing method based on data analysis, the method comprising the following steps:

[0050] Step S1: constructing a display device database, the display device database including display device data and display device environment data;

[0051] Step S2: Obtaining the road condition information of the inspection robot to the display device, selecting the best route to run to the location of the display device, and collecting the remote sensing image of the display device through the remote sensing platform;

[0052] Step S3: before the remote sensing platform collects the remote sensing image of the display device display image, construct a multivariate linear regression model, update the collection frequency of the display device, and collect the remote sensing image of the display device display image;

[0053] Step S4: extract the display image, map the pixels at the same position on the remote sensing image, and calculate the error value between the remote sensing image and the display image; when the error value is greater than or equal to the error threshold, send the location information of the display device to the control center, feedback the abnormal detection result, and warn the maintenance personnel to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, it triggers a secondary warning to remind the administrator that the display device has not been evaluated for maintenance.

[0054] Preferably, the specific implementation process of step S1 includes:

[0055] Construct a display device database, which is used to store display device data and display device environment data; the display device data includes display device display images and location information; the display device environment data includes temperature and light intensity; the display device is fixedly set on the side of the traffic route to display traffic information.

[0056] Preferably, the specific implementation process of step S2 includes:

[0057] Step S2.1: Based on the location information of the display device, connect to the Internet of Vehicles to obtain the road condition information of the inspection robot reaching the display device. The road condition information is the average speed of vehicles in each road section. The inspection robot is externally equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor. The remote sensing platform is used to collect remote sensing images of the display device display image. The temperature sensor is used to collect the real-time temperature of the environment at the display device location. The light intensity sensor is used to collect the real-time light intensity at the display device location.

[0058] Step S2.2: Construct route set S = {s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes;

[0059] Step S2.3: route s according to the intersection n Segment and build segment set l m represents the length of the mth road segment, M represents the route s n The total number of segments;

[0060] Step S2.4: Based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v max Indicates the maximum operating speed of the inspection robot. represents the average speed of vehicles on the mth road section;

[0061] Step S2.5: Calculate the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

[0062] For example, the maximum running speed vmax of the inspection robot is preset to be 20km / h, and the route set S of the inspection robot to reach the display device is S={s1, s2, s3}, where Ls1={12km, 18km, 48km}, Then vs1 = {10km / h, 20km / h, 20km / h}, ts1 = (12 / 10 + 18 / 20 + 48 / 20) h = 4.5 h;

[0063] Ls2 = {3km, 8km, 6km}, Then vs1 = {10km / h, 20km / h, 15km / h}, ts2 = (3 / 10 + 8 / 20 + 6 / 15) h = 1.1 h;

[0064] Ls3 = {12km, 1km, 7km}, vs1={8km / h, 10km / h, 7km / h}, ts3=(12 / 8+1 / 10+7 / 7)h=2.5h;

[0065] The shortest route is tmin=ts2=1.1h, that is, route s2 is the best route.

[0066] Preferably, the specific implementation process of step S3 includes:

[0067] Step S3.1: Before the remote sensing platform collects the remote sensing image displayed by the display device, the real-time temperature and the real-time light intensity are normalized. Wherein, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the best ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the best ambient light intensity collected;

[0068] Step S3.2: Construct a multivariate linear regression model to dynamically analyze the clarity of remote sensing images and perform iterative processing. The expression formula is: p = α1e c +α2e -F +α3e -g +α4, where P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, and α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency;

[0069] Let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, preset the clarity threshold, and if the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform collects the remote sensing image of the display device display image according to the collection frequency during the iterative update.

[0070] Preferably, the specific implementation process of step S4 includes:

[0071] Step S4.1: retrieve the display image, and capture the pixel point (i, j) on the display image, where i and j represent the horizontal coordinate value and the vertical coordinate value of the pixel point respectively, and obtain the pixel value at the pixel point (i, j) on the display image, which is recorded as Y2(i, j); based on the pixel point (i, j), map the pixel point at the same position on the remote sensing image, and record the pixel value at the mapped pixel point on the remote sensing image as Y1(i, j);

[0072] Step S4.2: Calculate the error value between the remote sensing image and the display image: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image;

[0073] A preset error threshold is set. When the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment. When the inspection robot does not receive maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0074] A remote sensing image dynamic data processing system based on data analysis, the system includes: a data storage module, a route planning module, an image acquisition module and an early warning module;

[0075] The data storage module is used to store display device data and display device environment data;

[0076] The route planning module includes a route planning unit and an optimal route selection unit, which is used to select the optimal route to reach the display device location;

[0077] An image acquisition module is used to calculate the acquisition frequency of the display device, acquire images from the display device, and pre-process the images;

[0078] The early warning module includes an error unit and an early warning unit. It extracts the display image, maps the pixels at the same position on the remote sensing image, and calculates the error value between the remote sensing image and the display image. When the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment. When the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0079] Preferably, the data storage module is used to construct a display device database, which is used to store display device data and display device environment data; the display device data includes display device display images, location information and operating status data; the display device environment data includes temperature and light intensity.

[0080] Preferably, the route planning module includes a route planning unit and an optimal route selection unit;

[0081] The route planning unit connects to the Internet of Vehicles through the location information of the display device to obtain the road condition information of the inspection robot to the display device. The road condition information is the average speed of vehicles in each section. The inspection robot is equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor. The remote sensing platform is used to collect remote sensing images of the display device display image, the temperature sensor is used to collect the real-time temperature of the environment at the display device location, and the light intensity sensor is used to collect the real-time light intensity at the display device location; construct a route set S = {s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes;

[0082] The best route selection unit selects the route s according to the intersection n Segment and build segment set l m represents the length of the mth road segment, M represents the route s n The total number of segments; based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v max Indicates the maximum operating speed of the inspection robot. Represents the average speed of vehicles on the mth road section; calculates the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

[0083] Preferably, the image acquisition module normalizes the real-time temperature and the real-time light intensity before the remote sensing platform acquires the remote sensing image for displaying the image on the display device. Among them, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the optimal ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the optimal ambient light intensity collected; a multivariate linear regression model is constructed to dynamically analyze the clarity of remote sensing images and perform iterative processing. The expression formula is: p = α1e c +α2e -F +α3e -g +α4, where P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, and α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency; let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, and preset the clarity threshold. If the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform acquires the remote sensing image of the display device according to the acquisition frequency during the iterative update.

[0084] Preferably, the early warning module includes an error unit and an early warning unit;

[0085] The error unit retrieves the display image and captures the pixel point (i, j) on the display image, where i and j represent the horizontal and vertical coordinate values ​​of the pixel point, respectively, to obtain the pixel value at the pixel point (i, j) on the display image, recorded as Y2(i, j); based on the pixel point (i, j), the pixel point at the same position is mapped on the remote sensing image, and the pixel value at the mapped pixel point on the remote sensing image is recorded as Y1(i, j); the error value between the remote sensing image and the display image is calculated: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image;

[0086] The early warning unit presets an error threshold. When the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, feedback is abnormal in the detection result, and the maintenance personnel are warned to go to the site for maintenance assessment. When the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

[0087] 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.

[0088] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A remote sensing image dynamic data processing method based on data analysis, characterized in that: The method comprises the following steps: Step S1: constructing a display device database, wherein the display device database includes display device data and display device environment data; Step S2: Obtaining the road condition information of the inspection robot to the display device, selecting the best route to run to the location of the display device, and collecting the remote sensing image of the display device through the remote sensing platform; Step S3: before the remote sensing platform collects the remote sensing image of the display device display image, construct a multivariate linear regression model, update the collection frequency of the display device, and collect the remote sensing image of the display device display image; Step S4: extract the display image, map the pixels at the same position on the remote sensing image, and calculate the error value between the remote sensing image and the display image; when the error value is greater than or equal to the error threshold, send the location information of the display device to the control center, feedback the abnormal detection result, and warn the maintenance personnel to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, it triggers a secondary warning to remind the administrator that the display device has not been evaluated for maintenance.

2. A remote sensing image dynamic data processing method based on data analysis according to claim 1, characterized in that: The specific implementation process of step S1 includes: Construct a display device database, the display device database is used to store display device data and display device environment data; the display device data includes display device display image and location information; the display device environment data includes temperature and light intensity; the display device is fixedly set on the side of the traffic route to display traffic information.

3. A remote sensing image dynamic data processing method based on data analysis according to claim 2, characterized in that: The specific implementation process of step S2 includes: Step S2.1: Based on the location information of the display device, connect to the Internet of Vehicles to obtain the road condition information of the inspection robot reaching the display device, the road condition information is the average speed of vehicles in each road section, the inspection robot is externally equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor, the remote sensing platform is used to collect remote sensing images of the display device display image, the temperature sensor is used to collect the real-time temperature of the environment at the display device location, and the light intensity sensor is used to collect the real-time light intensity at the display device location; Step S2.2: Construct route set S = {s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes; Step S2.3: route s according to the intersection n Segment and build segment set l m represents the length of the mth road segment, M represents the route s n The total number of segments; Step S2.4: Based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v max Indicates the maximum operating speed of the inspection robot. represents the average speed of vehicles on the mth road section; Step S2.5: Calculate the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

4. A remote sensing image dynamic data processing method based on data analysis according to claim 3, characterized in that: The specific implementation process of step S3 includes: Step S3.1: Before the remote sensing platform collects the remote sensing image displayed by the display device, the real-time temperature and the real-time light intensity are normalized. Wherein, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the best ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the best ambient light intensity collected; Step S3.2: construct a multivariate linear regression model, dynamically analyze the clarity of the remote sensing image, and perform iterative processing. The expression formula is: p = α1ec + α2e-F + α3e-g + α4, where P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency; Let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, preset the clarity threshold, and if the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform collects the remote sensing image of the display device display image according to the collection frequency during the iterative update.

5. A remote sensing image dynamic data processing method based on data analysis according to claim 4, characterized in that: The specific implementation process of step S4 includes: Step S4.1: retrieve the display image, and capture the pixel point (i, j) on the display image, where i and j represent the horizontal coordinate value and the vertical coordinate value of the pixel point respectively, and obtain the pixel value at the pixel point (i, j) on the display image, which is recorded as Y2(i, j); based on the pixel point (i, j), map the pixel point at the same position on the remote sensing image, and record the pixel value at the mapped pixel point on the remote sensing image as Y1(i, j); Step S4.2: Calculate the error value between the remote sensing image and the display image: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image; A preset error threshold is set. When the error value is greater than or equal to the error threshold, the location information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment. When the inspection robot does not receive maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

6. A remote sensing image dynamic data processing system based on data analysis, characterized in that: The system includes: a data storage module, a route planning module, an image acquisition module and an early warning module; The data storage module is used to store display device data and display device environment data; The route planning module includes a route planning unit and an optimal route selection unit, which is used to select the optimal route to reach the display device location; The image acquisition module is used to calculate the acquisition frequency of the display device, acquire images from the display device, and pre-process the images; The early warning module includes an error unit and an early warning unit. By extracting the display image, mapping the pixels at the same position on the remote sensing image, and calculating the error value between the remote sensing image and the display image, when the error value is greater than or equal to the error threshold, the position information of the display device is sent to the control center, the abnormal detection result is fed back, and the maintenance personnel are warned to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

7. A remote sensing image dynamic data processing system based on data analysis according to claim 6, characterized in that: The data storage module is used to construct a display device database, and the display device database is used to store display device data and display device environment data; the display device data includes display device display images, location information and operating status data; the display device environment data includes temperature and light intensity.

8. The remote sensing image dynamic data processing system based on data analysis according to claim 7, characterized in that: The route planning module includes a route planning unit and an optimal route selection unit; The route planning unit is connected to the Internet of Vehicles through the location information of the display device to obtain the road condition information of the inspection robot reaching the display device, wherein the road condition information is the average speed of vehicles in each road section. The inspection robot is externally equipped with a remote sensing platform, a temperature sensor, and a light intensity sensor. The remote sensing platform is used to collect remote sensing images of the display device display image, the temperature sensor is used to collect the real-time temperature of the environment at the display device location, and the light intensity sensor is used to collect the real-time light intensity at the display device location. Construct a route set S = {s n |n∈(1,N)},s n represents the nth route, and N represents the total number of routes; The optimal route selection unit selects the route s according to the intersection n Segment and build segment set l m represents the length of the mth road segment, M represents the route s n The total number of segments; based on route s n The road condition information is used to calculate the running speed of the inspection robot passing through the mth road section. Calculate the time required for the inspection robot to pass the mth road section Calculate the inspection robot's route s n Duration Among them, v max Indicates the maximum operating speed of the inspection robot. Represents the average speed of vehicles on the mth road section; calculates the shortest route The route is recorded as the best route. The inspection robot runs to the location of the display device according to the best route, and collects the remote sensing image of the display device through the remote sensing platform.

9. A remote sensing image dynamic data processing system based on data analysis according to claim 8, characterized in that: The image acquisition module normalizes the real-time temperature and the real-time light intensity before the remote sensing platform acquires the remote sensing image displayed by the display device. Wherein, F represents the normalized temperature value, f represents the real-time temperature, f0 represents the optimal ambient temperature collected, g represents the normalized light intensity value, G represents the real-time light intensity, and G0 represents the optimal ambient light intensity collected; a multivariate linear regression model is constructed to dynamically analyze the clarity of the remote sensing image and perform iterative processing, and the expression formula is: p=α1ec+α2e-F+α3e-g+α4, wherein P represents the clarity of the remote sensing image, c represents the acquisition frequency, α1, α2, α3 represent the preset regression coefficients, and α4 represents the random error under the influence of the preset acquisition frequency; let c=c+1, return to the multivariate linear regression model, iteratively update the clarity P, preset the clarity threshold, if the updated clarity is greater than or equal to the clarity threshold, the iteration stops, and the remote sensing platform collects the remote sensing image of the display device display image according to the acquisition frequency during the iterative update.

10. A remote sensing image dynamic data processing system based on data analysis according to claim 9, characterized in that: The early warning module includes an error unit and an early warning unit; The error unit retrieves the display image and captures the pixel point (i, j) on the display image, where i and j represent the horizontal coordinate value and the vertical coordinate value of the pixel point respectively, obtains the pixel value at the pixel point (i, j) on the display image, and records it as Y2(i, j); based on the pixel point (i, j), maps the pixel point at the same position on the remote sensing image, and records the pixel value at the mapped pixel point on the remote sensing image as Y1(i, j); calculates the error value between the remote sensing image and the display image: Wherein, M represents the length of the displayed image, and N represents the width of the displayed image; The early warning unit presets an error threshold. When the error value is greater than or equal to the error threshold, the early warning unit sends the location information of the display device to the control center, feedback that the detection result is abnormal, and warns the maintenance personnel to go to the site for maintenance assessment; when the inspection robot does not receive the maintenance assessment feedback within the specified time, a secondary early warning is triggered to remind the administrator that the display device has not been evaluated for maintenance.

Images