A Multi-Source Satellite Data Fusion Arbitration and Intelligent Analysis System

Abstract

The present invention belongs to the technical field of satellite data analysis. The present invention discloses a multi-source satellite data fusion arbitration and intelligent analysis system, which includes obtaining corresponding satellite remote sensing data in each target area within a geographical monitoring area. The satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data. The satellite remote sensing data is fused through data to generate a satellite fusion image with a timestamp. The satellite fusion image includes using the satellite image data as a carrier and the time series data as retrieval information, and integrating the spectral induction data and meteorological data on the satellite image data. The satellite fusion images corresponding to each target area in the geographical monitoring area are superimposed to obtain a geographical monitoring panoramic view, and whether there is an abnormal pixel area in the satellite fusion image is identified. The ratio corresponding to the abnormal pixel area is arbitrated and judged to obtain the satellite fusion effect.

Description

Technical Field

[0001] The present invention relates to the technical field of satellite data analysis, and more specifically, to a multi-source satellite data fusion arbitration and intelligent analysis system. Background Art

[0002] With the new progress made by major scientific research institutions in the field of data intelligent fusion, it is necessary to integrate data from different satellites and different sensors, eliminate factors such as sensor differences and atmospheric effects, and weaken the differentiation of remote sensing information to obtain more comprehensive remote sensing information. However, as the amount of remote sensing information data increases, the fusion efficiency of satellite remote sensing data is relatively low. If a preliminary identification and judgment are to be carried out, arbitration of the fusion data is required. For example, the architecture and device for advanced arbitration in embedded control disclosed in the authorized patent number: CN107229238B record the execution data of tasks executed by each controller in the redundant control system;

[0003] In practical applications, when receiving and processing remote sensing data from different satellites and different types during data fusion, it is very difficult to solve the problem of heterogeneity in aspects such as format, accuracy, and time resolution of multi-source data for fusion. Most of the data collected by satellites mainly relies on image data. However, when the original data can still be retained during fusion, the space storage is reduced. When conflicting results occur in the fusion data, on the one hand, the intelligent analysis ability needs to be improved, and the dependence on prior knowledge also needs to be reduced. If some satellite remote sensing data is misjudged due to external factors or accidental failures, the accuracy of satellite remote sensing data cannot be objectively obtained, which is extremely likely to cause operators to wrongly fuse satellite remote sensing data and even obtain opposite analysis results; thus affecting the fairness of arbitration and analysis.

[0004] In view of this, the present invention provides a multi-source satellite data fusion arbitration and intelligent analysis system. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-source satellite data fusion arbitration and intelligent analysis system.

[0006] In a first aspect, the present invention provides a multi-source satellite data fusion arbitration and intelligent analysis system, including a data receiving module, a data fusion module, and a data arbitration module. The above-mentioned each module is connected by wired and / or wireless connection methods to realize data transmission between each module;

[0007] The data receiving module acquires the corresponding satellite remote sensing data in each target area within the regional monitoring area. The satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data; and transmits the satellite remote sensing data to the data fusion module;

[0008] Data fusion module, the satellite remote sensing data generates a satellite fusion image with a timestamp through data fusion. The satellite fusion image includes satellite image data as the carrier and time series data as the retrieval information, integrating spectral sensing data and meteorological data on the satellite image data; sending the satellite fusion image to the data arbitration module and the historical data storage module;

[0009] Data arbitration module, superimposing the satellite fusion images corresponding to each target area in the regional monitoring area to obtain a panoramic view of the regional monitoring, and identifying whether there is an abnormal pixel area in the satellite fusion image, and arbitrating and evaluating the occupancy ratio corresponding to the abnormal pixel area to obtain the satellite fusion effect.

[0010] As a preferred solution of the first aspect of the present invention, the acquisition logic of the satellite remote sensing data is as follows:

[0011] S101: Obtain the original data of the remote sensing satellite, perform frame synchronization, deinterleaving, descrambling, CRC check, decoding and sub-packeting on the input of the original data of the remote sensing satellite, and extract the list of remote sensing data supporting the target monitoring environment in the original data of the remote sensing satellite;

[0012] S102: Determine the environmental assessment impact factor of the remote sensing data in the remote sensing data list relative to the target monitoring environment, mark the remote sensing data with an environmental assessment impact factor exceeding the expectation as satellite remote sensing data, assign a value to the satellite remote sensing data, and update according to the size of the assignment.

[0013] As a preferred solution of the first aspect of the present invention, the acquisition logic of the environmental assessment impact factor is as follows:

[0014] Used to pre-collect the original data of historical remote sensing satellites in each target monitoring environment; use the original data of historical remote sensing satellites as the sample set; divide the sample set into a training set and a test set;

[0015] Construct a computer learning model, input the training set into the computer learning model for training, obtain the environmental assessment impact factor to be verified; determine the satellite remote sensing data based on the environmental assessment impact factor; the satellite remote sensing data includes satellite image data, spectral sensing data, meteorological data and time series data;

[0016] Testing and validating the impact factors and satellite remote sensing data for the environment to be verified according to the test set, and using the satellite remote sensing data determined at the current moment as the input end of the computer learning model; the computer learning model outputs satellite predicted remote sensing data based on the environmental assessment impact factors, using the satellite remote sensing data corresponding to the next moment of the current moment as the prediction target, and taking the difference between the satellite predicted remote sensing data and the satellite remote sensing data corresponding to the next moment as the prediction accuracy; continuously optimizing and training the environmental assessment impact factors based on the prediction accuracy until the training stops when the prediction accuracy is greater than or equal to the preset accuracy threshold.

[0017] As a preferred solution of the first aspect of the present invention, the update logic of the remote sensing data list:

[0018] The initialization state of the remote sensing data list is based on the remote sensing data list corresponding to the most recent target monitoring environment, and based on prior knowledge, determining the important demarcation line of the environmental assessment impact factor relative to the satellite remote sensing data.

[0019] If the environmental assessment impact factor is less than or equal to the important demarcation line, the remote sensing data that does not exceed the expectation is removed from the remote sensing data list.

[0020] If the environmental assessment impact factor is greater than the important demarcation line, the remote sensing data that exceeds the expectation is marked as satellite remote sensing data and added to the remote sensing data list; and a sorting assignment is generated according to the environmental assessment impact factor, and the remote sensing data list is updated in real time from large to small according to the sorting assignment.

[0021] As a preferred solution of the first aspect of the present invention, the acquisition logic of the satellite fusion image is as follows:

[0022] The satellite image data includes visible light images and SAR terrain data; the visible light images and SAR terrain data are overlapped and simulated, and the overlapping points are marked as reference points.

[0023] Taking the visible light image as a reference object, correcting the SAR terrain data, constructing a three-dimensional space system based on the SAR terrain data, marking the terrain data with actual longitude and latitude, and marking the normalized spectral induction data and meteorological data in the three-dimensional space system to form the corrected SAR terrain data.

[0024] Overlaying the corrected SAR terrain data and the visible light image to generate a satellite fusion image, taking any reference point in the three-dimensional space system of the satellite fusion image as a reference point, and extracting the position information of the reference point; storing the satellite fusion image with a timestamp using the time series data as index information.

[0025] As a preferred solution of the first aspect of the present invention, the acquisition logic of the regional monitoring panoramic view:

[0026] Perform zoning processing according to the relative position labels of the target areas. The overlapping part between two adjacent target areas is the transition area. Select the transition area with high clarity and label it as target area A, and label the other target area sharing the same transition area as target area B;

[0027] Take target area A as the starting node 1, label target area B as node 2, and sequentially obtain N nodes according to the positional relationship between node 1 and node 2. The Nth node N is adjacent to the starting node 1;

[0028] Match the brightness of target area B with that of target area A, extract the feature points of target area A and target area B based on the algorithm, then analyze the feature points using the RANSAC algorithm, calculate the transformation matrix H of the best match, and perform a projection transformation on target area B using the transformation matrix H to obtain the coordinate parameters of target area B in target area A;

[0029] Evaluate whether target area B meets the requirements according to the transformed coordinate parameters. If it meets the requirements, continue with the splicing. The overlapping part is fused using the weighted average method, and the fused image is labeled as target area A; otherwise, label target area B as an abnormal pixel area, retain the image integrity of target area A, and update target area B to target area A;

[0030] Repeat the above operations. After completing the splicing of all adjacent target areas, perform head-to-tail alignment and remove the overlapping parts; then crop the blank areas according to the maximum boundary value to generate a panoramic map of regional monitoring.

[0031] As a preferred solution of the first aspect of the present invention, the method for evaluating the satellite fusion effect:

[0032] Count the number of abnormal pixel areas, obtain the ratio of the number of abnormal pixel areas to all target areas, divide the satellite fusion effect into M levels, and determine the ratio interval corresponding to each level based on the fuzzy function,

[0033] Compare the ratio value with the ratio interval to obtain the satellite fusion effect corresponding to the current regional monitoring area.

[0034] In the second aspect, the present invention provides a multi-source satellite data fusion arbitration and intelligent analysis method, based on the implementation of the first aspect, including the following steps:

[0035] Obtain the satellite remote sensing data corresponding to each target area in the regional monitoring area. The satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data;

[0036] The satellite remote sensing data generates a satellite fusion image with a timestamp through data fusion. The satellite fusion image includes satellite image data as the carrier and time series data as the retrieval information, integrating spectral sensing data and meteorological data on the satellite image data.

[0037] Overlay the satellite fusion images corresponding to each target area in the regional monitoring area to obtain a panoramic regional monitoring map, identify whether there are abnormal pixel areas in the satellite fusion images, and arbitrate and evaluate the proportion corresponding to the abnormal pixel areas to obtain the satellite fusion effect.

[0038] In a third aspect, the present invention provides an electronic device, including: a processor and a memory, wherein a computer program that can be called by the processor is stored in the memory;

[0039] The processor executes the first aspect by calling the computer program stored in the memory.

[0040] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which when run on a computer cause the computer to execute the first aspect.

[0041] The technical effects and advantages of a multi-source satellite data fusion arbitration and intelligent analysis system according to the present invention:

[0042] Combined with the analysis of the panoramic regional monitoring map, the present invention plays a role in optimizing resource allocation and decision support, providing favorable support for more scientifically planning urban development, optimizing resource allocation, and formulating environmental protection policies; concentrating multi-source data on the remote sensing fusion image reduces information loss or misjudgment caused by the limitations of a single data source and provides more accurate and comprehensive monitoring information; in addition, with the remote sensing fusion image as the carrier, the computing pressure on the computer is greatly reduced, the response speed is increased, and when natural disasters or emergencies occur, abnormal areas can be quickly identified to provide timely and accurate information support. And based on the time series, long-term and continuous environmental change monitoring data is provided, providing a scientific basis for environmental protection and ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of satellite data transmission according to the present invention;

[0044] Figure 2 It is a framework diagram of a multi-source satellite data fusion arbitration and intelligent analysis system according to the present invention;

[0045] Figure 3 It is a flowchart of a multi-source satellite data fusion arbitration and intelligent analysis method according to the present invention;

[0046] Figure 4 It is a schematic diagram of the stitching effect of the panoramic regional monitoring map according to the present invention;

[0047] Figure 5 This is a schematic structural diagram of an electronic device according to the present invention. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] Embodiment 1: The present invention provides a multi-source satellite data fusion arbitration and intelligent analysis system as shown in Figure 2 which includes a data receiving module 100, a data fusion module 200, a data arbitration module 300, and a historical data storage module 400. The above-mentioned each module is connected by wired and / or wireless connection methods to realize data transmission between each module;

[0050] The data receiving module 100 acquires the corresponding satellite remote sensing data in each target area within the geographical monitoring area. The satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data; and transfers the satellite remote sensing data to the data fusion module 200 and the historical data storage module 400;

[0051] It should be noted that: the target monitoring environment is screened based on the actual application scenario. For example, when the satellite monitors the change of forest vegetation cover, forest health status, or forest fire risk, the target monitoring environment includes geographical information system data, historical remote sensing data, and ground observation data. As shown in Figure 1 multiple satellites are configured on the satellite orbit to collect the original remote sensing satellite data corresponding to the target monitoring environment from different angles. Based on the target monitoring environment, a representative and important forest area is selected as the geographical monitoring area, and the geographical monitoring area is divided into target areas corresponding to different visual angles. In this way, it can be ensured that under the same time series, different satellites obtain the original remote sensing satellite data corresponding to the target area from different visual angles, and multiple target areas of the same geographical monitoring area are analyzed simultaneously, weakening the influence of uncertain factors on the monitoring of the change of forest cover and health status, thereby affecting the evaluation of satellite remote sensing data.

[0052] Specifically, the acquisition logic of the satellite remote sensing data is as follows:

[0053] S101: Acquire the original remote sensing satellite data, perform frame synchronization, deinterleaving, descrambling, CRC check, decoding, and packet splitting on the input of the original remote sensing satellite data, and extract the list of remote sensing data in the original remote sensing satellite data that supports the target monitoring environment;

[0054] S102: Determine the environmental assessment impact factors of the remote sensing data in the remote sensing data list with respect to the target monitoring environment, mark the remote sensing data with environmental assessment impact factors exceeding the expectation as satellite remote sensing data, assign values to the satellite remote sensing data, and update according to the assigned value size.

[0055] Further explanation: The acquisition logic of the environmental assessment impact factors is as follows:

[0056] Pre-collect the original historical remote sensing satellite data in each target monitoring environment; use the original historical remote sensing satellite data as the sample set; divide the sample set into a training set and a test set;

[0057] Construct a computer learning model, input the training set into the computer learning model for training, and obtain the environmental assessment impact factors to be verified; determine the satellite remote sensing data based on the environmental assessment impact factors; the satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data;

[0058] Test and verify the environmental assessment impact factors to be verified and the satellite remote sensing data according to the test set, and use the satellite remote sensing data determined at the current moment as the input end of the computer learning model; the computer learning model outputs the predicted satellite remote sensing data based on the environmental assessment impact factors, use the satellite remote sensing data corresponding to the next moment of the current moment as the prediction target, and use the difference between the predicted satellite remote sensing data and the satellite remote sensing data corresponding to the next moment as the prediction accuracy; continuously optimize and train the environmental assessment impact factors based on the prediction accuracy until the training stops when the prediction accuracy is greater than or equal to the preset accuracy threshold.

[0059] It should be noted that: The computer learning model is used to analyze the influence degree of the environmental assessment impact factors on the satellite remote sensing data in the target monitoring environment; and sort the influence degrees from large to small to determine the priority. Its accuracy is higher, but the disadvantage is that the computing power is large and the speed is slow.

[0060] More specifically, the update logic of the remote sensing data list:

[0061] The initial state of the remote sensing data list is the remote sensing data list corresponding to the most recent target monitoring environment, and based on prior knowledge, determine the important demarcation line of the environmental assessment impact factors relative to the satellite remote sensing data.

[0062] If the environmental assessment impact factor is less than or equal to the important demarcation line, the remote sensing data that does not exceed the expectation, delete the remote sensing data that does not exceed the expectation from the remote sensing data list.

[0063] If the environmental assessment impact factor is greater than the important demarcation line, the remote sensing data exceeding the expectation is marked as satellite remote sensing data and added to the remote sensing data list; and a sorting assignment is generated according to the environmental assessment impact factor, and the remote sensing data list is updated in real time from large to small according to the sorting assignment.

[0064] Specifically, the acquisition method of the satellite remote sensing data is as follows:

[0065] Satellite image data includes visible light images and SAR terrain data;

[0066] Visible light image: Captured by the camera equipment on the satellite in the visible light band, used to obtain the intuitive image of the surface.

[0067] SAR terrain data: Collected by the synthetic aperture radar (SAR) sensor, capable of generating three-dimensional information of the surface; the advantage of SAR data is that it can penetrate clouds and vegetation and provide all-weather surface monitoring.

[0068] Spectral induction data: Capturing continuous spectral bands through the spectral sensor on the satellite, thus providing detailed information about the surface material composition. Hyperspectral data is particularly suitable for fields such as agricultural monitoring, vegetation classification, and mineral exploration.

[0069] Meteorological data: Includes atmospheric temperature, atmospheric humidity, atmospheric pressure, wind speed, and wind direction information, which is crucial for weather forecasting, climate research, and environmental monitoring.

[0070] Time series data: The data collected at different time points forms a time series, which helps to analyze the change trends of the surface and the atmosphere, and is used for monitoring environmental changes, disaster response, and long-term climate change.

[0071] Data fusion module 200, the satellite remote sensing data is fused to generate a satellite fusion image with a timestamp. The satellite fusion image includes the satellite image data as the carrier and the time series data as the retrieval information, integrating the spectral induction data and the meteorological data on the satellite image data; the satellite fusion image is sent to the data arbitration module 300 and the historical data storage module 400;

[0072] Specifically, as Figure 4 shown, the acquisition logic of the satellite fusion image is:

[0073] Satellite image data includes visible light images and SAR terrain data; the visible light image and the SAR terrain data are overlapped and simulated, and the overlapping points are marked as reference points;

[0074] Taking the visible light image as a reference object, correcting the SAR terrain data, constructing a three-dimensional space system based on the SAR terrain data, marking the terrain data with actual longitude and latitude, and marking the normalized spectral induction data and meteorological data in the three-dimensional space system to form the corrected SAR terrain data;

[0075] Overlaying the corrected SAR terrain data and the visible light image to generate a satellite fusion image, taking any reference point in the three-dimensional space system of the satellite fusion image as a reference point, and extracting the position information of the reference point; Storing the satellite fusion image with a timestamp using the time series data as index information.

[0076] The data arbitration module 300 overlays the satellite fusion images corresponding to each target area in the regional monitoring area to obtain a panoramic regional monitoring map, identifies whether there are abnormal pixel areas in the satellite fusion images, and arbitrates and judges the occupancy ratio corresponding to the abnormal pixel areas to obtain the satellite fusion effect.

[0077] The acquisition logic of the panoramic regional monitoring map:

[0078] Perform zoning processing according to the relative position labels of the target areas. The overlapping part of two adjacent target areas is a transition area. Select the transition area with high clarity and mark it as target area A, and mark the other target area sharing the same transition area as target area B;

[0079] Taking target area A as the starting node 1, marking target area B as node 2, and sequentially obtaining N nodes according to the positional relationship between node 1 and node 2. The Nth node N is adjacent to the starting node 1;

[0080] Match the brightness of target area B with that of target area A, extract the feature points of target area A and target area B based on an algorithm, then analyze the feature points using the RANSAC algorithm, calculate the optimal matching transformation matrix H, and perform a projection transformation on target area B using the transformation matrix H to obtain the coordinate parameters of target area B in target area A;

[0081] Evaluate whether target area B meets the requirements according to the transformed coordinate parameters. If it meets the requirements, continue with the splicing. The overlapping part is fused using the weighted average method, and the fused image is marked as target area A; Otherwise, mark target area B as an abnormal pixel area, retain the image integrity of target area A, and update target area B to target area A;

[0082] Repeat the above operations. After completing the splicing of all adjacent target areas, align the head and tail and remove the overlapping parts; Then crop the blank area according to the maximum boundary value to generate a panoramic regional monitoring map.

[0083] The method for judging the satellite fusion effect:

[0084] Count the number of abnormal pixel regions, obtain the ratio of the number of abnormal pixel regions to all target regions, divide the satellite fusion effect into M levels, and determine the ratio interval corresponding to each level based on the fuzzy function.

[0085] Compare the ratio value with the ratio interval to obtain the satellite fusion effect corresponding to the current regional monitoring area.

[0086] It should be noted that under normal circumstances, satellites and satellite monitoring equipment are fixed, so the satellite fusion effect generally does not change significantly. Abnormal pixel regions may be due to deviations between satellite acquisition devices, resulting in poor data fusion effects. This can be solved by adjusting the equipment or correcting the satellite fusion image of the target area based on software; if there is a large deviation in the satellite fusion effect, it indicates that the satellite acquisition data is abnormal, and the satellite monitoring equipment needs to be repaired in time; therefore, different control strategies are generated based on comparing the satellite fusion effects corresponding to different times based on timestamps, and the satellite is adjusted and corrected based on the control strategies.

[0087] Embodiment 2: On the basis of Embodiment 1, this embodiment regularly stores satellite remote sensing data based on the historical data storage module 400, and based on the regional monitoring panoramic map and satellite fusion effect corresponding to the target monitoring environment, tracks the changes in the target monitoring environment based on the regional monitoring panoramic map, and integrates the ground verification data and user feedback into the multi-source satellite data fusion arbitration and intelligent analysis system to improve the accuracy and reliability of the evaluation.

[0088] Exemplarily, taking the use of multi-source satellite data for forest environment monitoring as an example, the satellite analyzes the forest vegetation coverage images corresponding to different time periods, marks the forest vegetation coverage images as satellite remote sensing images, marks the image features in the satellite remote sensing images, and divides the image features into SAR terrain data and vegetation image data; among them, the SAR terrain data is the boundary information of the forest vegetation coverage information obtained based on the target environment, a three-dimensional coordinate system is constructed based on the SAR terrain data, and the position changes and pixel changes of the vegetation image data in the three-dimensional coordinate system can identify illegal logging and forest degradation; in addition, based on the spectral characteristics corresponding to the forest vegetation, under different lighting conditions, the states of the forest vegetation are different, and the health status of the forest vegetation is analyzed based on the state changes.

[0089] Similarly, multi-source satellite data is applicable to agriculture. It can estimate the planting area and potential yield of crops based on floating information, monitor the health status of crops, help detect and control pests and diseases in a timely manner; evaluate soil moisture, guide irrigation activities, and improve the utilization efficiency of water resources; it can also be combined with GPS and other sensors to achieve precise fertilization, sowing and harvesting, and improve agricultural production efficiency.

[0090] Embodiment 3

[0091] As Figure 3 shown, the present invention provides a multi-source satellite data fusion arbitration and intelligent analysis method, including the following steps:

[0092] S1: Obtain the corresponding satellite remote sensing data in each target area within the regional monitoring area. The satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data;

[0093] The acquisition logic of the satellite remote sensing data is as follows:

[0094] S101: Obtain the original data of the remote sensing satellite, perform frame synchronization, deinterleaving, descrambling, CRC check, decoding, and packet splitting on the input of the original data of the remote sensing satellite, and extract the list of remote sensing data in the original data of the remote sensing satellite that supports the target monitoring environment;

[0095] S102: Determine the environmental assessment impact factors of the remote sensing data in the remote sensing data list relative to the target monitoring environment, mark the remote sensing data with environmental assessment impact factors exceeding the expectation as satellite remote sensing data, assign values to the satellite remote sensing data, and update according to the assigned values.

[0096] The acquisition logic of the environmental assessment impact factors is as follows:

[0097] Pre-collect the historical original data of remote sensing satellites in each target monitoring environment; use the historical original data of remote sensing satellites as a sample set; divide the sample set into a training set and a test set;

[0098] Construct a computer learning model, input the training set into the computer learning model for training to obtain the environmental assessment impact factors to be verified; determine the satellite remote sensing data based on the environmental assessment impact factors; the satellite remote sensing data includes satellite image data, spectral induction data, meteorological data, and time series data;

[0099] Test and verify the environmental assessment impact factors to be verified and the satellite remote sensing data according to the test set, use the satellite remote sensing data determined at the current moment as the input end of the computer learning model; the computer learning model outputs the predicted satellite remote sensing data based on the environmental assessment impact factors, use the satellite remote sensing data corresponding to the next moment of the current moment as the prediction target, and use the difference between the predicted satellite remote sensing data and the satellite remote sensing data corresponding to the next moment as the prediction accuracy; continuously optimize and train the environmental assessment impact factors based on the prediction accuracy until the prediction accuracy is greater than or equal to the preset accuracy threshold and then stop training.

[0100] The update logic of the remote sensing data list:

[0101] The initialization state of the remote sensing data list is the remote sensing data list corresponding to the most recent target monitoring environment, and based on prior knowledge, the important demarcation line of the environmental assessment impact factor relative to the satellite remote sensing data is determined.

[0102] If the environmental assessment impact factor is less than or equal to the important demarcation line, the remote sensing data that does not exceed the expectation will be removed from the remote sensing data list.

[0103] If the environmental assessment impact factor is greater than the important demarcation line, the remote sensing data that exceeds the expectation is marked as satellite remote sensing data and added to the remote sensing data list; and a sorting assignment is generated according to the environmental assessment impact factor, and the remote sensing data list is updated in real time from large to small according to the sorting assignment.

[0104] S2: The satellite remote sensing data generates a satellite fusion image with a timestamp through data fusion. The satellite fusion image includes satellite image data as the carrier and time series data as the retrieval information, and integrates spectral induction data and meteorological data on the satellite image data.

[0105] The acquisition logic of the satellite fusion image is as follows:

[0106] The satellite image data includes visible light images and SAR terrain data; the visible light images and SAR terrain data are overlapped and simulated, and the overlapping points are marked as reference points.

[0107] Taking the visible light image as a reference, the SAR terrain data is corrected, a three-dimensional space system is constructed based on the SAR terrain data, the terrain data is marked with actual longitude and latitude, and the normalized spectral induction data and meteorological data are marked in the three-dimensional space system to form corrected SAR terrain data.

[0108] The corrected SAR terrain data and the visible light image are superimposed to generate a satellite fusion image. Taking any reference point in the three-dimensional space system of the satellite fusion image as a reference point, the position information of the reference point is extracted; the satellite fusion image with a timestamp is stored using the time series data as index information.

[0109] S3: The satellite fusion images corresponding to each target area in the regional monitoring area are superimposed to obtain a regional monitoring panoramic view, and it is identified whether there is an abnormal pixel area in the satellite fusion image, and the occupation ratio corresponding to the abnormal pixel area is arbitrated and judged to obtain the satellite fusion effect.

[0110] The acquisition logic of the regional monitoring panoramic view:

[0111] Perform line-by-line partitioning processing according to the relative position labels of the target areas. The overlapping part between two adjacent target areas is the transition area. Select the transition area with high clarity and label it as target area A, and label the other target area sharing the same transition area as target area B;

[0112] Take target area A as the starting node 1, label target area B as node 2, and sequentially obtain N nodes according to the positional relationship between node 1 and node 2. The Nth node N is adjacent to the starting node 1;

[0113] Match the brightness of target area B with that of target area A, extract the feature points of target area A and target area B based on the algorithm, then analyze the feature points using the RANSAC algorithm, calculate the transformation matrix H for the best match, and perform a projective transformation on target area B using the transformation matrix H to obtain the coordinate parameters of target area B in target area A;

[0114] Evaluate whether target area B meets the requirements according to the transformed coordinate parameters. If it meets the requirements, continue with the splicing. The overlapping part is fused using the weighted average method, and the fused image is labeled as target area A; otherwise, label target area B as an abnormal pixel area, retain the image integrity of target area A, and update target area B to target area A;

[0115] Repeat the above operations. After completing the splicing of all adjacent target areas, perform head-to-tail alignment and remove the overlapping parts; then crop the blank areas according to the maximum boundary value to generate a panoramic map of regional monitoring.

[0116] The method for evaluating the satellite fusion effect:

[0117] Count the number of abnormal pixel areas, obtain the ratio of the number of abnormal pixel areas to all target areas, divide the satellite fusion effect into M levels, and determine the ratio interval corresponding to each level based on the fuzzy function,

[0118] Compare the ratio value with the ratio interval to obtain the satellite fusion effect corresponding to the current regional monitoring area.

[0119] Example 4: An electronic device shown according to an exemplary embodiment includes: a processor and a memory, where a computer program that can be called by the processor is stored in the memory;

[0120] The processor executes the above-mentioned multi-source satellite data fusion arbitration and intelligent analysis system by calling the computer program stored in the memory.

[0121] Figure 5FIG. 0 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may vary greatly due to different configurations or performances, and may include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the stock algorithm trading method based on a deep neural network provided by each of the above method embodiments. The electronic device may further include other components for implementing the functions of the device. For example, the electronic device may further have components such as a wired or wireless network interface and an input / output interface for input and output. Details thereof are not described in this embodiment of the present application.

[0122] Embodiment 5: A computer-readable storage medium according to an exemplary embodiment, on which a rewritable computer program is stored;

[0123] When the computer program runs on a computer device, the computer device is caused to execute the above multi-source satellite data fusion arbitration and intelligent analysis system.

[0124] The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center including one or more available medium sets. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state drive.

[0125] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0126] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0127] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the present invention.

[0129] In addition, the functional units in each embodiment of this application can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0130] If the above-mentioned functions are implemented in the form of software function units 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 this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0131] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0132] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, 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 multi-source satellite data fusion arbitration and intelligent analysis system, characterized by: It includes a data receiving module, a data fusion module and a data arbitration module, and the above modules are connected by wired and / or wireless connection to achieve data transmission between the modules; A data receiving module, which obtains satellite remote sensing data corresponding to each target area in the regional monitoring area, wherein the satellite remote sensing data includes satellite image data, spectral sensing data, meteorological data and time series data; Transfer satellite remote sensing data to the data fusion module; Extract the latest remote sensing data list based on satellite remote sensing data, and the update logic of the remote sensing data list is as follows: The initialization state of the remote sensing data list is based on the remote sensing data list corresponding to the most recent target monitoring environment, and based on prior knowledge, determines the important dividing line of the environmental assessment influencing factor relative to the satellite remote sensing data. If the environmental assessment impact factor is less than or equal to the important dividing line, the remote sensing data that did not exceed expectations will be deleted from the remote sensing data list; If the environmental assessment impact factor is greater than the important dividing line, the remote sensing data exceeding the expectation is marked as satellite remote sensing data and added to the remote sensing data list; And generate ranking assignments based on environmental assessment impact factors, and update the remote sensing data list in real time from large to small; A data fusion module, wherein the satellite remote sensing data generates a satellite fusion image with a time stamp through data fusion, wherein the satellite fusion image includes satellite image data as a carrier and time series data as retrieval information, and integrates spectral sensing data and meteorological data on the satellite image data; and sends the satellite fusion image to a data arbitration module and a historical data storage module; The data arbitration module superimposes the satellite fusion images corresponding to each target area in the regional monitoring area to obtain a regional monitoring panorama, and identifies whether there are abnormal pixel areas in the satellite fusion images, and arbitrates and judges the proportion values ​​corresponding to the abnormal pixel areas to obtain the satellite fusion effect.

2. A multi-source satellite data fusion arbitration and intelligent analysis system according to claim 1, characterized in that: The acquisition logic of the satellite remote sensing data is: S101: acquiring remote sensing satellite raw data, performing frame synchronization, deinterleaving, descrambling, CRC checking, decoding and packetization on the remote sensing satellite raw data input, and extracting a remote sensing data list supporting a target monitoring environment from the remote sensing satellite raw data; S102: Determine the environmental assessment impact factor of the remote sensing data in the remote sensing data list relative to the target monitoring environment, mark the remote sensing data with an environmental assessment impact factor exceeding the expected value as satellite remote sensing data, assign a value to the satellite remote sensing data, and update it according to the assigned value size.

3. A multi-source satellite data fusion arbitration and intelligent analysis system according to claim 2, characterized in that: The logic for obtaining the environmental assessment impact factors is: Used to collect historical remote sensing satellite raw data in each target monitoring environment in advance; use the historical remote sensing satellite raw data as a sample set; divide the sample set into a training set and a test set; Constructing a computer learning model, inputting the training set into the computer learning model for training, and obtaining the environmental assessment influencing factors to be verified; Determining satellite remote sensing data based on environmental assessment impact factors; the satellite remote sensing data includes satellite image data, spectral sensing data, meteorological data and time series data; The environmental assessment influencing factors and satellite remote sensing data to be verified are tested and verified according to the test set, and the satellite remote sensing data determined at the current moment is used as the input end of the computer learning model; the computer learning model outputs satellite predicted remote sensing data based on the environmental assessment influencing factors, and the satellite remote sensing data corresponding to the next moment of the current moment is used as the prediction target, and the difference between the satellite predicted remote sensing data and the satellite remote sensing data corresponding to the next moment is used as the prediction accuracy; the training environmental assessment influencing factors are continuously optimized based on the prediction accuracy, and the training is stopped when the prediction accuracy is greater than or equal to a preset accuracy threshold.

4. The multi-source satellite data fusion arbitration and intelligent analysis system according to claim 3, characterized in that: The acquisition logic of the satellite fusion image is: The satellite image data includes visible light images and SAR terrain data; the visible light images and SAR terrain data are overlapped and simulated, and the overlap points are marked as reference points; Using visible light images as reference, SAR terrain data is corrected, a three-dimensional space system is constructed based on SAR terrain data, terrain data is marked with actual longitude and latitude, and the normalized spectral sensing data and meteorological data are marked in the three-dimensional space system to form corrected SAR terrain data; The corrected SAR terrain data and the visible light image are superimposed to generate a satellite fusion image, and a reference point in the three-dimensional space system of the satellite fusion image is selected as a reference point to extract the position information of the reference point; The satellite fusion images with timestamps are stored using time series data as index information.

5. A multi-source satellite data fusion arbitration and intelligent analysis system according to claim 4, characterized in that: The logic for obtaining the regional monitoring panorama: The target area is partitioned according to its relative position label. The overlapping part of two adjacent target areas is the transition area. The transition area with higher definition is selected as target area A, and the other target area sharing the same transition area is marked as target area B. Take target area A as the starting node 1, target area B as node 2, and obtain N nodes in sequence according to the position relationship between nodes 1 and 2. The Nth node N is adjacent to the starting node 1. Match the brightness of target area B with that of target area A, extract the feature points of target area A and target area B based on the algorithm, analyze the feature points using the RANSAC algorithm, calculate the best matching transformation matrix H, and use the transformation matrix H to perform a projection transformation on target area B to obtain the coordinate parameters of target area B in target area A; According to the transformed coordinate parameters, whether the target area B meets the requirements is evaluated. If it meets the requirements, the stitching is continued, and the overlapping parts are fused using the weighted average method, and the fused image is marked as the target area A; Otherwise, target region B is marked as an abnormal pixel region, the image integrity of target region A is preserved, and target region B is updated to target region A; Repeat the above steps, align the ends after all adjacent target regions are joined, and remove the duplicated parts. Then, the blank area is cut off according to the maximum boundary value to generate a regional monitoring panorama.

6. A multi-source satellite data fusion arbitration and intelligent analysis system according to claim 5, characterized in that: The evaluation method of the satellite fusion effect is as follows: Count the number of abnormal pixel areas, obtain the proportion of the number of abnormal pixel areas to all target areas, divide the satellite fusion effect into M levels, and determine the proportion interval corresponding to each level based on the fuzzy function. Compare the proportion value with the proportion interval to obtain the satellite fusion effect corresponding to the current regional monitoring area.

7. A multi-source satellite data fusion arbitration and intelligent analysis method, characterized in that: The method is based on the implementation of a multi-source satellite data fusion arbitration and intelligent analysis system according to any one of claims 1 to 6, and is characterized in that it includes the following steps: Acquire satellite remote sensing data corresponding to each target area in the regional monitoring area, wherein the satellite remote sensing data includes satellite image data, spectral sensing data, meteorological data and time series data; The satellite remote sensing data generates a satellite fusion image with a time stamp through data fusion, wherein the satellite fusion image includes satellite image data as a carrier and time series data as retrieval information, and integrates spectral sensing data and meteorological data on the satellite image data; The satellite fusion images corresponding to each target area in the regional monitoring area are superimposed to obtain a regional monitoring panorama, and it is identified whether there are abnormal pixel areas in the satellite fusion images. The proportion value corresponding to the abnormal pixel area is arbitrated and judged to obtain the satellite fusion effect.

8. A computer program product stored on a computer readable medium, characterized in that: The invention comprises a computer readable program, which, when executed on an electronic device, provides a user input interface to implement a multi-source satellite data fusion arbitration and intelligent analysis system as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a multi-source satellite data fusion arbitration and intelligent analysis system as described in any one of claims 1 to 6.

Images