Satellite real-time information monitoring method and device, storage medium and electronic equipment

Abstract

The invention discloses a satellite real-time information monitoring method and device, a storage medium and electronic equipment, and relates to the technical field of satellite remote sensing. The method comprises the following steps: acquiring original remote sensing images shot by a satellite sensor at each time node based on a satellite-borne platform; extracting an information monitoring area to obtain remote sensing image slices; transmitting the remote sensing image slices to a satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal during transit; wherein the ground terminal is used for performing multi-source fusion on the remote sensing image slices shot by different types of satellites according to the remote sensing image slices shot by each satellite, and performing multi-temporal fusion on the remote sensing image slices shot by different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; and performing information monitoring according to the multi-source fusion image and the multi-temporal fusion image, and determining a target information monitoring result. The timeliness of information monitoring is ensured.

Description

Technical Field

[0001] The present application relates to the field of satellite remote sensing technology, and in particular to a satellite real-time intelligence monitoring method, device, storage medium and electronic equipment. Background Art

[0002] With the improvement of satellite manufacturing and launch technology, the deployment of large-scale low earth orbit (LEO) satellite constellations has become possible. Its most basic and common application is to build satellite Internet and provide communication services in remote areas. In terms of low-orbit remote sensing, based on the large-scale, wide coverage and high-frequency revisit capabilities of satellites, more frequent and continuous monitoring of ground targets can be achieved, especially in emergency rescue, military intelligence and other aspects, which can significantly improve the update frequency and information value of remote sensing observation images.

[0003] At present, when satellites are in orbit, they transmit the original remote sensing image data they take to the ground station for processing, thereby realizing intelligence monitoring. However, this method requires a large amount of original remote sensing image data to be transmitted to the ground for processing, but the bandwidth between the satellite and the ground is limited, so the data needs to be transmitted multiple times, and analysis and processing can only be performed on the ground after all data transmission is completed. In addition, this method can only transmit data when the satellite passes over the ground station, so it is difficult to ensure the timeliness of intelligence monitoring. Summary of the invention

[0004] In view of this, the present application provides a satellite real-time intelligence monitoring method, device, storage medium and electronic equipment, the main purpose of which is to ensure the timeliness of intelligence monitoring.

[0005] According to a first aspect of the present application, a satellite real-time intelligence monitoring method is provided, which is applied to an edge computing unit of each satellite in a satellite constellation, wherein the satellite constellation includes satellites of different types, and the method includes: Obtain original remote sensing images taken by satellite sensors at various time points; Extracting the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice; The remote sensing image slices are transmitted to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; wherein the ground terminal is used to perform multi-source fusion of the remote sensing image slices taken by the different types of satellites according to the remote sensing image slices taken by each satellite at each time node, and perform multi-temporal fusion of the remote sensing image slices taken at different time nodes to obtain multi-source fusion images and multi-temporal fusion images; intelligence monitoring is performed based on the multi-source fusion images and the multi-temporal fusion images to determine the target intelligence monitoring results corresponding to the intelligence monitoring area.

[0006] According to a second aspect of the present application, another satellite real-time intelligence monitoring method is provided, which is applied to a ground terminal, and the method comprises: Receive remote sensing image slices transmitted by the edge computing unit of each satellite in the satellite constellation, wherein the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain the original remote sensing images taken by the satellite sensor at each time node; extract the intelligence monitoring area in the original remote sensing image to obtain the remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; Based on the remote sensing image slices taken by each satellite at each time node, multi-source fusion is performed on the remote sensing image slices taken by the different types of satellites, and multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; Intelligence monitoring is performed based on the multi-source fusion image and the multi-temporal fusion image to determine the target intelligence monitoring result corresponding to the intelligence monitoring area.

[0007] According to a third aspect of the present application, a satellite real-time intelligence monitoring device is provided, which is applied to an edge computing unit of each satellite in a satellite constellation, wherein the satellite constellation includes satellites of different types, and the device includes: An acquisition unit, used to acquire original remote sensing images taken by satellite sensors at various time points; An extraction unit, used for extracting the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice; A transmission unit is used to transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; wherein the ground terminal is used to perform multi-source fusion of the remote sensing image slices taken by the different types of satellites according to the remote sensing image slices taken by each satellite at each time node, and perform multi-temporal fusion of the remote sensing image slices taken at different time nodes to obtain multi-source fusion images and multi-temporal fusion images; intelligence monitoring is performed based on the multi-source fusion images and the multi-temporal fusion images to determine the target intelligence monitoring results corresponding to the intelligence monitoring area.

[0008] According to a fourth aspect of the present application, another satellite real-time intelligence monitoring device is provided, which is applied to a ground terminal, and the device includes: A receiving unit is used to receive remote sensing image slices transmitted by an edge computing unit of each satellite in a satellite constellation, wherein the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain original remote sensing images taken by satellite sensors at various time nodes; extract intelligence monitoring areas in the original remote sensing images to obtain remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing through; A fusion unit is used to perform multi-source fusion on the remote sensing image slices taken by the different types of satellites based on the remote sensing image slices taken by each satellite at each time node, and to perform multi-temporal fusion on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; A determination unit is used to perform intelligence monitoring based on the multi-source fusion image and the multi-temporal fusion image, and determine the target intelligence monitoring result corresponding to the intelligence monitoring area.

[0009] According to the fifth aspect of the present application, a storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the above-mentioned satellite real-time intelligence monitoring method applied to the edge computing unit is implemented.

[0010] According to the sixth aspect of the present application, another storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned satellite real-time intelligence monitoring method applied to a ground terminal is implemented.

[0011] According to the seventh aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the program, the above-mentioned satellite real-time intelligence monitoring method applied to an edge computing unit is implemented.

[0012] According to the eighth aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the program, the above-mentioned satellite real-time intelligence monitoring method applied to a ground terminal is implemented.

[0013] By means of the above technical scheme, the present application provides a satellite real-time intelligence monitoring method, device, storage medium and electronic device. Compared with the prior art, by processing the original remote sensing image on the satellite, extracting the remote sensing image slices of the intelligence monitoring area in the original remote sensing image and transmitting them to the ground, it is possible to eliminate invalid and useless remote sensing data, and only transmit valid data to the ground, thereby reducing the bandwidth pressure and storage pressure of satellite-to-ground transmission, achieving a reduction in the amount of transmitted data and an improvement in efficiency, and ensuring the timeliness of intelligence monitoring. In addition, the remote sensing image data taken by any satellite in the present application can be quickly transmitted through the intersatellite link, without waiting for the satellite to pass before transmitting, so it can further improve the data transmission efficiency and ensure the timeliness of intelligence monitoring. At the same time, the present application can perform intelligence monitoring in multiple dimensions by performing multi-source fusion and multi-phase fusion on the remote sensing image data, and determining the final intelligence monitoring results based on the multi-source fusion image and the multi-phase fusion image, thereby ensuring the accuracy of the intelligence monitoring results.

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of a process flow of a satellite real-time intelligence monitoring method provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of an efficient data processing architecture applicable to a communication and remote control integrated constellation provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of a process flow of another satellite real-time intelligence monitoring method provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of multi-source fusion provided by an embodiment of the present application is shown; Figure 5 A schematic diagram of multi-temporal fusion provided by an embodiment of the present application is shown; Figure 6 A schematic diagram of the structure of a satellite real-time intelligence monitoring device provided in an embodiment of the present application is shown; Figure 7 A schematic diagram of the structure of another satellite real-time intelligence monitoring device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0017] Existing technologies require a large amount of raw remote sensing image data to be transmitted to the ground for processing, which makes it difficult to ensure the timeliness of intelligence monitoring.

[0018] In order to solve the above problems, an embodiment of the present invention provides a satellite real-time intelligence monitoring method, which is applied to the edge computing unit of each satellite in the satellite constellation, such as Figure 1 As shown, the method includes: Step 101: Acquire original remote sensing images taken by satellite sensors at various time points.

[0019] Among them, the satellite constellation includes satellites of different types and may also include satellites of the same type. The number of satellites in the satellite constellation is at least two. Satellites of different types carry different types of sensors, and satellites of the same type carry the same type of sensors. The sensor types include visible light sensors, hyperspectral sensors, SAR (Synthetic ApertureRada, synthetic aperture radar) sensors and infrared sensors, etc. Visible light sensors, hyperspectral sensors and infrared sensors are collectively referred to as optical sensors. It should be noted that the types of sensors installed on the satellites in the embodiments of the present invention are not limited to the above, and may also be other types of sensors. The original remote sensing image is image data taken of the intelligence monitoring area by each satellite during its in-orbit operation.

[0020] For the embodiments of the present invention, during the on-orbit operation, each satellite in the satellite constellation will continuously capture original remote sensing images, which carry latitude and longitude information. Based on the geographical location of the intelligence monitoring area, the original remote sensing images for the intelligence monitoring area can be screened out.

[0021] In order to solve the timeliness problem of intelligence monitoring, the embodiment of the present invention provides an efficient data processing architecture suitable for integrated communication and remote sensing constellations, such as Figure 2As shown in the figure, the data processing architecture mainly includes a satellite constellation and a ground terminal. The satellite constellation includes satellite A, satellite B and satellite C. Each satellite has an edge computing unit and edge computing power, and can perform on-board processing. The data processing flow of this data processing architecture mainly involves the following processes: high-frequency revisit of low-orbit constellations, on-board processing, inter-satellite transfer, satellite-to-ground data transmission and ground terminal processing. Among them, for high-frequency revisit of low-orbit constellations, satellites A, satellite B and satellite C can continuously observe during their in-orbit operation. Satellites A, satellite B and satellite C include satellites of different types, and may also include satellites of the same type. For example, satellites A and satellite C are both optical satellites, and satellite B is a SAR satellite. This enables multi-source and multi-phase observations of intelligence monitoring areas. For on-board processing, after the sensors of satellites A and satellite B complete data collection, based on high Performance edge computing technology directly performs real-time data processing on the satellite, including imaging, intelligence monitoring area extraction, etc. A large amount of invalid data will be eliminated in this process, thereby improving the efficiency of downlink data and reducing data transmission pressure; for inter-satellite transfer, since the data still needs to be downlinked to the ground terminal via the transit satellite, and satellite A and satellite B are not necessarily above the ground receiving device connected to the ground terminal, the embodiment of the present invention uses the inter-satellite communication link to transmit the data processed on the satellite to the satellite C closest to the ground terminal; for satellite-to-ground data transmission, the low-orbit constellation satellite-to-ground high-bandwidth and low-latency data transmission link is used for data transmission. Figure 2 Satellite C is closer to the ground receiving device, and data is transmitted when satellite C passes by. Since this application is based on transit transmission, satellites A and B do not need to wait for transit and can transmit data at the fastest speed; for ground terminal processing, the ground terminal is connected to a portable satellite receiving device. After receiving the data, the ground terminal runs an artificial intelligence fusion algorithm based on the ground terminal computing power to comprehensively process the multi-satellite, multi-source, and multi-phase data obtained, thereby completing intelligence area monitoring in real time. Since this application does not go through ground fixed stations and servers for processing, it can realize portable field scene work.

[0022] Step 102: extract the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice.

[0023] Among them, intelligence monitoring areas include natural disaster monitoring areas, military intelligence monitoring areas, etc.

[0024] In the embodiment of the present invention, each satellite can obtain the latitude and longitude range of the intelligence monitoring area when performing on-board processing, and then cut the original remote sensing image based on the latitude and longitude range using preset screenshot software to obtain remote sensing image slices corresponding to the intelligence monitoring area, wherein the preset screenshot software includes GIS software, etc. In this way, invalid image data can be eliminated, data transmission pressure can be reduced, and data transmission efficiency can be improved.

[0025] Step 103: Transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by.

[0026] The ground terminal is used to perform multi-source fusion of remote sensing image slices taken by different types of satellites and multi-temporal fusion of remote sensing image slices taken by different time nodes according to the remote sensing image slices taken by each satellite at each time node, so as to obtain multi-source fusion images and multi-temporal fusion images; perform intelligence monitoring according to the multi-source fusion images and the multi-temporal fusion images, and determine the target intelligence monitoring results corresponding to the intelligence monitoring area. The intelligence monitoring in the embodiment of the present invention includes natural disaster monitoring, military monitoring, etc.

[0027] For the embodiment of the present invention, the remote sensing image slices can also be compressed to obtain compressed remote sensing image slices, and then the compressed remote sensing image slices are transmitted to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the compressed remote sensing image slices to the ground terminal when passing by.

[0028] The embodiments of the present invention can further improve data transmission efficiency and reduce data transmission pressure by compressing remote sensing image data.

[0029] The embodiment of the present invention provides a satellite real-time intelligence monitoring method, which processes the original remote sensing image on the satellite, extracts the remote sensing image slices of the intelligence monitoring area in the original remote sensing image and transmits them to the ground, thereby eliminating invalid and useless remote sensing data and only transmitting valid data to the ground, thereby reducing the bandwidth pressure and storage pressure of satellite-to-ground transmission, reducing the amount of transmitted data and improving efficiency, and ensuring the timeliness of intelligence monitoring. In addition, the embodiment of the present invention can realize the rapid transmission of data through the intersatellite link, which can further improve the timeliness of intelligence monitoring.

[0030] Furthermore, the embodiment of the present invention provides another satellite real-time intelligence monitoring method, which is applied to a ground terminal, such as Figure 3 As shown, the method includes: Step 201: Receive remote sensing image slices transmitted by the edge computing unit of each satellite in the satellite constellation.

[0031] Among them, the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain the original remote sensing images taken by satellite sensors at various time nodes; extract the intelligence monitoring area in the original remote sensing image to obtain remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing through.

[0032] The ground terminal of the embodiment of the present invention is a portable device that is movable and connected to a satellite receiving device. The satellite receiving device is used to receive data transmitted from the satellite to the ground terminal. The ground terminal of the embodiment of the present invention is lightweight and portable. It can use an edge-end embedded high-computing GPU chip with low power consumption and small size. It has a high energy efficiency ratio and can realize a large amount of data processing under low power consumption. The peripheral design interface power board is connected to the GPU chip to realize multiple interface docking and 12-28V power supply. The high integration and low voltage operation ensure its portability and can work quickly in the field scene. The ground terminal of the embodiment of the present invention adds a cooling fan in the hardware design, designs system status monitoring and automatic speed regulation software, improves the heat dissipation ability, and the platform computing power performance can be better released. In terms of interface design, it is compatible with various high and low-speed communication interfaces, low-speed interfaces such as CAN, LVDS, RS422, RS485, GPIO, etc., and high-speed interfaces such as GTX, ETH (high-speed Ethernet), etc., through which other devices such as satellite antennas, vehicle-mounted communications, and command systems can be connected. In addition, compared with the onboard platform, HDMI, USB and other interfaces are designed to facilitate the external connection of various commonly used input and output peripherals on the ground, such as keyboards, cameras, monitors, various USB receivers and transmitters, etc.

[0033] For the embodiment of the present invention, after receiving the remote sensing image slices taken by each satellite at each time point, the remote sensing image slices need to be preprocessed, and the preprocessing process mainly includes correction and denoising. Specifically, the remote sensing image slices are first geometrically corrected. There are differences in the geometric correction methods of images taken by different types of sensors. For example, for optical image slices, orthorectification and polynomial correction methods are used, and for synthetic aperture radar image slices, orthorectification and geocoding methods are used. After that, the geometrically corrected remote sensing image slices continue to be processed by denoising, radiation correction, atmospheric correction, etc. For example, radiation correction and atmospheric correction are performed on the geometrically corrected optical image slices. Specifically, the dark pixel method or the radiation transfer model can be used to remove the speckle noise in the geometrically corrected synthetic aperture radar image slices. Specifically, Lee filtering, Frost filtering or non-local mean algorithm can be used. Thus, the processed remote sensing image slices can be obtained in the above manner.

[0034] After the remote sensing image slices are corrected and denoised, image registration is required to prepare for subsequent image fusion. During registration, based on the processed remote sensing image slices taken by each satellite at each time node, image registration can be performed on the processed remote sensing image slices taken by different types of satellites, and image registration can be performed on the processed remote sensing image slices taken at different time nodes, so as to obtain the registered remote sensing image slices taken by different types of satellites and the registered remote sensing image slices taken at different time nodes.

[0035] Specifically, feature matching algorithms (such as SIFT, SURF, or deep learning-based registration networks) are used to align processed remote sensing image slices (such as optical image slices and synthetic aperture radar image slices) taken by different types of satellites to ensure spatial consistency. At the same time, the processed remote sensing image slices taken at different time points are aligned to the same coordinate system, and the registration accuracy can be controlled within 1-2 pixels. Specifically, feature matching (such as SIFT) or regional cross-correlation methods can be used.

[0036] Step 202: Based on the remote sensing image slices taken by each satellite at each time node, multi-source fusion is performed on the remote sensing image slices taken by the different types of satellites, and multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image.

[0037] Among them, when performing multi-source fusion of remote sensing image slices taken by different types of satellites, there must be overlapping areas between the remote sensing image slices taken by different types of satellites; when performing multi-temporal fusion of remote sensing image slices taken at different time nodes, the remote sensing image slices taken at different time nodes can come from the same type of satellite or from different types of satellites.

[0038] For the embodiment of the present invention, after the remote sensing image slices are registered, multi-source fusion is performed on the registered remote sensing image slices taken by different types of satellites to obtain the multi-source fused image; multi-temporal fusion is performed on the registered remote sensing image slices taken at different time nodes to obtain the multi-temporal fused image.

[0039] The process of multi-source fusion of remote sensing image slices taken by different types of satellites is as follows: Figure 4 As shown, the fusion of optical image slices and synthetic aperture radar image slices is taken as an example.

[0040] When the registered remote sensing image slices taken by the different types of satellites include optical image slices and synthetic aperture radar image slices, wavelet transform is performed on the optical image slices and the synthetic aperture radar image slices respectively to obtain a first wavelet coefficient corresponding to the optical image slice and a second wavelet coefficient corresponding to the synthetic aperture radar image slice; the first wavelet coefficient and the second wavelet coefficient are fused to obtain fused wavelet coefficients; inverse wavelet transform is performed on the fused wavelet coefficients to obtain a fused multi-band image; the fused multi-band image and the synthetic aperture radar image slice are converted to IHS color space respectively to obtain first grayscale information corresponding to the fused multi-band image and second grayscale information corresponding to the synthetic aperture radar image slice; the first grayscale information and the second grayscale information are fused to obtain a fused IHS image; the fused IHS image is converted back to RGB color space to obtain the multi-source fused image.

[0041] Specifically, when performing wavelet transform on optical image slices and synthetic aperture radar image slices, discrete wavelet transform DWT or continuous wavelet transform CWT can be selected. When fusing the first wavelet coefficient and the second wavelet coefficient, the wavelet coefficient fusion can be performed by weighted averaging, maximum selection, etc., and the fused wavelet coefficient will retain the characteristic information of the image. In addition, when fusing the first grayscale information and the second grayscale information, the fusion can be performed by weighted averaging.

[0042] In addition to using the above wavelet transform method to obtain a multi-source fusion image, the U-Net deep learning model can also be used to fuse the multi-source fusion image. Specifically, the registered optical image slices and synthetic aperture radar image slices can be input into the U-Net deep learning model, and the multi-scale features of the optical image slices and synthetic aperture radar image slices can be extracted through the encoder, and then the cross-modal attention module is used to adaptively fuse the features, and then the decoder is used to reconstruct a high-resolution multi-source fusion image, which retains spectral fidelity and structural details.

[0043] It should be noted that the remote sensing image slices for multi-source fusion in the embodiment of the present invention are not limited to optical image slices and synthetic aperture radar image slices, but can also be remote sensing image slices taken by other types of satellites. Here, only the fusion of optical image slices and synthetic aperture radar image slices is used as an example.

[0044] At the same time, after the remote sensing image slices are registered, multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes.

[0045] For any two adjacent time nodes among different time nodes, if the remote sensing image slices taken at the any two adjacent time nodes are from the same type of satellite, the pixel values ​​of the remote sensing image slices taken at the any two adjacent time nodes are subtracted to obtain a difference image, and the difference image is determined as the multi-source fusion image.

[0046] For example, any two adjacent time nodes are time node 1 and time node 2. If the registered remote sensing image slices taken at time node 1 and time node 2 are both optical image slices, that is, the remote sensing image slices are all derived from visible light satellites, then the pixel values ​​of the optical image slice corresponding to time node 1 and the optical image slice corresponding to time node 2 can be directly subtracted to obtain a difference image, which is a multi-source fusion image.

[0047] In some embodiments, the pixel values ​​of the remote sensing image slices taken at any two adjacent time nodes can be added to obtain a value-added image, and the value-added image can be used as a multi-source fusion image. The pixel value ratio of the remote sensing image slices taken at any two adjacent time nodes can also be calculated to obtain a proportional image, and the proportional image can be used as a multi-source fusion image.

[0048] If the remote sensing image slices taken at any two adjacent time nodes are from different types of satellites, a preset edge detection algorithm is used to extract borders of the remote sensing image slices taken at any two adjacent time nodes; the border information extracted from the two remote sensing image slices is mapped to the same remote sensing image slice to obtain a mapping image, and the mapping image is determined as the multi-temporal fusion image.

[0049] Specifically, edge detection algorithms (such as Sobel, Canny, etc.) or target detection algorithms (such as YOLO, Faster R-CNN, etc.) can be used to extract the border information of remote sensing image slices. Then, the border information of the two remote sensing image slices is mapped to the same image slice. For example, the border information of one image slice can be directly superimposed on the other image slice to obtain a multi-temporal fusion image.

[0050] Step 203: Perform intelligence monitoring based on the multi-source fusion image and the multi-temporal fusion image to determine the target intelligence monitoring result corresponding to the intelligence monitoring area.

[0051] Among them, the intelligence monitoring of the embodiment of the present invention includes natural disaster monitoring, military intelligence monitoring, etc. Natural disaster monitoring includes intelligence monitoring of landslides, floods, mudslides, etc. Military intelligence monitoring includes intelligence monitoring of armed raids, military exercises, etc.

[0052] For the embodiment of the present invention, after obtaining the multi-source fusion image and the multi-temporal fusion image, the multi-source fusion image and the multi-temporal fusion image are comprehensively analyzed to determine the final target intelligence monitoring result. Specifically, intelligence monitoring is performed based on the multi-source fusion image to obtain a first intelligence monitoring result corresponding to the intelligence monitoring area; intelligence monitoring is performed based on the multi-temporal fusion image to obtain a second intelligence monitoring result corresponding to the intelligence monitoring area; and the target intelligence monitoring result is determined based on the first intelligence monitoring result and the second intelligence monitoring result.

[0053] For example, if both the first intelligence monitoring result and the second intelligence monitoring result believe that a natural disaster, such as a landslide, has occurred, it can be finally determined that a landslide has occurred; if a natural disaster has occurred in one of the first intelligence monitoring result and the second intelligence monitoring result, a further step is required to confirm the reliability of the monitoring result.

[0054] For another example, if both the first intelligence monitoring result and the second intelligence monitoring result believe that there is currently a military exercise, then it can be finally determined that there is a military exercise; if one of the first intelligence monitoring result and the second intelligence monitoring result believes that there is a military exercise, then a further step is required to confirm the reliability of the monitoring result.

[0055] Furthermore, when determining the first intelligence monitoring result, the multi-source fusion image is input into a preset intelligence monitoring model for intelligence monitoring to obtain the first intelligence monitoring result. The preset intelligence monitoring model may be a classification model, such as a multi-layer perceptron.

[0056] For example, by inputting multi-source fusion images into a multi-layer perceptron for classification, it is possible to determine whether a natural disaster has occurred in the intelligence monitoring area. For another example, by inputting multi-source fusion images into a multi-layer perceptron for classification, it is possible to determine whether a military exercise has occurred in the intelligence monitoring area.

[0057] Furthermore, when determining the second intelligence monitoring result, if the remote sensing image slices taken at any two adjacent time nodes originate from the same type of satellite, change detection is performed on the difference image (multi-source fusion image), the change area in the difference image is determined, and the change area is marked; based on the range of the marked change area, the second intelligence monitoring result is determined.

[0058] Specifically, when performing change detection, a preset detection threshold can be used to detect each pixel in the difference image. Pixels that exceed the preset detection threshold are considered abnormal, that is, there are changes. This makes it possible to determine the change area in the difference image, and ultimately the second intelligence monitoring result can be determined based on the size of the change area. If the change area is large, it is determined that a natural disaster has occurred or a military exercise is present; conversely, if the change area is small, it is determined that no natural disaster has occurred or there is no military exercise.

[0059] Furthermore, in order to ensure the reliability of the second intelligence monitoring result, the embodiment of the present invention can simultaneously perform change detection on the difference image, the value-added image and the ratio image to respectively determine the change areas corresponding to the difference image, the value-added image and the ratio image, and then determine whether a natural disaster or a military exercise has occurred based on the change area of ​​each image. Finally, the intelligence monitoring results of the three images are combined to obtain the second intelligence monitoring result, thereby ensuring the accuracy of the second intelligence monitoring result.

[0060] For example, by performing change detection on the difference image, the added image, and the ratio image respectively, it is determined that the conclusions drawn from these three images are all that a natural disaster has occurred or a military exercise has occurred. In this case, it can be determined that the second intelligence monitoring result is that a natural disaster has occurred or a military exercise has occurred.

[0061] Further, when determining the second intelligence monitoring result, if the remote sensing image slices taken at any two adjacent time nodes are from different types of satellites, then based on the mapping image, the border information difference between the two remote sensing image slices is determined; based on the border information difference, the second intelligence monitoring result is determined, such as Figure 5 shown.

[0062] Specifically, if the border information difference is too large, it is determined that a natural disaster has occurred or a military exercise has occurred; conversely, if the border information difference is not large, it is determined that no natural disaster has occurred or no military exercise has occurred.

[0063] A satellite real-time intelligence monitoring method provided by an embodiment of the present invention can eliminate invalid and useless remote sensing data by processing the original remote sensing image on the satellite, extracting the remote sensing image slices of the intelligence monitoring area in the original remote sensing image and transmitting them to the ground, thereby reducing the bandwidth pressure and storage pressure of satellite-to-ground transmission, reducing the amount of transmitted data and improving efficiency, and ensuring the timeliness of intelligence monitoring. In addition, the remote sensing image data taken by any satellite in the embodiment of the present invention can be quickly transmitted through the intersatellite link without waiting for the satellite to pass through before transmitting, so that the data transmission efficiency can be further improved and the timeliness of intelligence monitoring can be ensured. At the same time, the embodiment of the present invention can perform intelligence monitoring in multiple dimensions by performing multi-source fusion and multi-phase fusion on the remote sensing image data, and determining the final intelligence monitoring results based on the multi-source fusion image and the multi-phase fusion image, thereby ensuring the accuracy of the intelligence monitoring results.

[0064] Further, as Figure 1 The specific implementation of the method shown in the embodiment provides a satellite real-time intelligence monitoring device, such as Figure 6 As shown, the device includes: an acquisition unit 31, an extraction unit 32 and a transmission unit 33.

[0065] The acquisition unit 31 may be used to acquire original remote sensing images taken by satellite sensors at various time points.

[0066] The extraction unit 32 may be used to extract the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice.

[0067] The transmission unit 33 can be used to transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; wherein the ground terminal is used to perform multi-source fusion of the remote sensing image slices taken by the different types of satellites according to the remote sensing image slices taken by each satellite at each time node, and perform multi-phase fusion of the remote sensing image slices taken at different time nodes to obtain multi-source fusion images and multi-phase fusion images; intelligence monitoring is performed based on the multi-source fusion images and the multi-phase fusion images to determine the target intelligence monitoring results corresponding to the intelligence monitoring area.

[0068] In some embodiments, the extraction unit 32 can be specifically used to obtain the longitude and latitude range of the intelligence monitoring area; based on the longitude and latitude range, the original remote sensing image is cropped using preset screenshot software to obtain a remote sensing image slice corresponding to the intelligence monitoring area.

[0069] In some embodiments, the device further comprises: a compression unit.

[0070] The compression unit can be used to compress the remote sensing image slices to obtain compressed remote sensing image slices.

[0071] The transmission unit 33 can be specifically used to transmit the compressed remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the compressed remote sensing image slices to the ground terminal when passing by.

[0072] It should be noted that for other corresponding descriptions of the functional units involved in the satellite real-time intelligence monitoring device provided in this embodiment, reference can be made to Figure 1 The corresponding description in will not be repeated here.

[0073] Based on the above Figure 1 The method shown in the embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned Figure 1 The satellite real-time intelligence monitoring method shown.

[0074] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0075] Based on the above Figure 1 The method shown, and Figure 6 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, which can be a personal computer, a tablet computer, a server, or other network equipment, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 The satellite real-time intelligence monitoring method shown.

[0076] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0077] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0078] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0079] Further, as Figure 3 The specific implementation of the method shown in the embodiment provides a satellite real-time intelligence monitoring device, such as Figure 7 As shown, the device includes: a receiving unit 41, a fusion unit 42 and a determination unit 43.

[0080] The receiving unit 41 can be used to receive remote sensing image slices transmitted by the edge computing unit of each satellite in the satellite constellation, wherein the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain the original remote sensing images taken by the satellite sensor at each time node; extract the intelligence monitoring area in the original remote sensing image to obtain remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing through.

[0081] The fusion unit 42 can be used to perform multi-source fusion of remote sensing image slices taken by different types of satellites based on the remote sensing image slices taken by each satellite at each time node, and to perform multi-temporal fusion of remote sensing image slices taken at different time nodes to obtain multi-source fusion images and multi-temporal fusion images.

[0082] The determination unit 43 may be configured to perform intelligence monitoring based on the multi-source fusion image and the multi-temporal fusion image, and determine a target intelligence monitoring result corresponding to the intelligence monitoring area.

[0083] In some embodiments, the device further comprises: a processing unit.

[0084] The processing unit can be used to perform denoising and correction processing on the remote sensing image slices taken by each satellite at each time node to obtain the processed remote sensing image slices; based on the processed remote sensing image slices taken by each satellite at each time node, perform image registration on the processed remote sensing image slices taken by different types of satellites, and perform image registration on the processed remote sensing image slices taken at different time nodes to obtain the registered remote sensing image slices taken by different types of satellites and the registered remote sensing image slices taken at different time nodes.

[0085] The fusion unit 42 can be specifically used to perform multi-source fusion on the registered remote sensing image slices taken by different types of satellites to obtain the multi-source fused image; and perform multi-temporal fusion on the registered remote sensing image slices taken at different time nodes to obtain the multi-temporal fused image.

[0086] In some embodiments, the determination unit 43 includes: a monitoring module and a determination module.

[0087] The monitoring module can be used to perform intelligence monitoring based on the multi-source fusion image to obtain a first intelligence monitoring result corresponding to the intelligence monitoring area.

[0088] The monitoring module may also be used to perform intelligence monitoring based on the multi-temporal fusion image to obtain a second intelligence monitoring result corresponding to the intelligence monitoring area.

[0089] The determination module can be used to determine the target intelligence monitoring result based on the first intelligence monitoring result and the second intelligence monitoring result.

[0090] In some embodiments, the ground terminal comprises a movable portable device.

[0091] In some embodiments, when the registered remote sensing image slices taken by the different types of satellites include optical image slices and synthetic aperture radar image slices, the fusion unit 42 may also be specifically used to perform wavelet transform on the optical image slices and the synthetic aperture radar image slices respectively to obtain a first wavelet coefficient corresponding to the optical image slice and a second wavelet coefficient corresponding to the synthetic aperture radar image slice; fuse the first wavelet coefficient and the second wavelet coefficient to obtain fused wavelet coefficients; perform inverse wavelet transform on the fused wavelet coefficients to obtain a fused multi-band image; convert the fused multi-band image and the synthetic aperture radar image slice to IHS color space respectively to obtain first grayscale information corresponding to the fused multi-band image and second grayscale information corresponding to the synthetic aperture radar image slice; fuse the first grayscale information and the second grayscale information to obtain a fused IHS image; convert the fused IHS image back to RGB color space to obtain the multi-source fused image.

[0092] The monitoring module can be specifically used to input the multi-source fusion image into a preset intelligence monitoring model to perform intelligence monitoring and obtain the first intelligence monitoring result.

[0093] In some embodiments, the fusion unit 42 can also be specifically used to, for any two adjacent time nodes among the different time nodes, if the remote sensing image slices taken at the any two adjacent time nodes are from the same type of satellite, then subtract the pixel values ​​of the remote sensing image slices taken at the any two adjacent time nodes to obtain a difference image, and determine the difference image as the multi-source fusion image.

[0094] The monitoring module may also be specifically used to perform change detection on the difference image, determine the change area in the difference image, and mark the change area; and determine the second intelligence monitoring result based on the range of the marked change area.

[0095] In some embodiments, the fusion unit 42 can also be specifically used to extract the borders of any two adjacent time nodes among the different time nodes, if the remote sensing image slices taken at the any two adjacent time nodes are from different types of satellites, using a preset edge detection algorithm; map the border information extracted from the two remote sensing image slices to the same remote sensing image slice to obtain a mapping image, and determine the mapping image as the multi-temporal fusion image.

[0096] The monitoring module may also be specifically used to determine the border information difference between the two remote sensing image slices based on the mapping image; and determine the second intelligence monitoring result based on the border information difference.

[0097] It should be noted that for other corresponding descriptions of the functional units involved in the satellite real-time intelligence monitoring device provided in this embodiment, reference can be made to Figure 3 The corresponding description in will not be repeated here.

[0098] Based on the above Figure 3 The method shown in the embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned Figure 3 The satellite real-time intelligence monitoring method shown.

[0099] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0100] Based on the above Figure 3 The method shown, and Figure 7 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, which can be a personal computer, a tablet computer, a server, or other network equipment, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 3 The satellite real-time intelligence monitoring method shown.

[0101] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0102] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0103] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware.

[0105] The embodiment of the present invention processes the original remote sensing image on the satellite, extracts the remote sensing image slices of the intelligence monitoring area in the original remote sensing image, and transmits them to the ground, thereby eliminating invalid and useless remote sensing data and only transmitting valid data to the ground, thereby reducing the bandwidth pressure and storage pressure of satellite-to-ground transmission, achieving a reduction in the amount of transmitted data and an improvement in efficiency, and ensuring the timeliness of intelligence monitoring. In addition, the remote sensing image data taken by any satellite in the embodiment of the present invention can be quickly transmitted through the intersatellite link without waiting for the satellite to pass through before transmitting, thereby further improving the data transmission efficiency and ensuring the timeliness of intelligence monitoring. At the same time, the embodiment of the present invention performs multi-source fusion and multi-phase fusion on the remote sensing image data, and determines the final intelligence monitoring results based on the multi-source fusion image and the multi-phase fusion image, so as to perform intelligence monitoring in multiple dimensions, thereby ensuring the accuracy of the intelligence monitoring results.

[0106] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0107] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A satellite real-time intelligence monitoring method, characterized in that: An edge computing unit applied to each satellite in a satellite constellation, wherein the satellite constellation includes satellites of different types, and the method includes: Obtain original remote sensing images taken by satellite sensors at various time points; Extracting the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice; The remote sensing image slices are transmitted to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; wherein the ground terminal is used to perform multi-source fusion of the remote sensing image slices taken by the different types of satellites according to the remote sensing image slices taken by each satellite at each time node, and perform multi-temporal fusion of the remote sensing image slices taken at different time nodes to obtain multi-source fusion images and multi-temporal fusion images; intelligence monitoring is performed based on the multi-source fusion images and the multi-temporal fusion images to determine the target intelligence monitoring results corresponding to the intelligence monitoring area.

2. The method according to claim 1, characterized in that The step of extracting the intelligence monitoring area from the original remote sensing image to obtain a remote sensing image slice includes: Obtain the latitude and longitude range of the intelligence monitoring area; Based on the latitude and longitude range, the original remote sensing image is cropped using a preset screenshot software to obtain a remote sensing image slice corresponding to the intelligence monitoring area; and / or After extracting the intelligence monitoring area in the original remote sensing image to obtain the remote sensing image slice, the method further includes: Compressing the remote sensing image slices to obtain compressed remote sensing image slices; The step of transmitting the remote sensing image slice to the satellite closest to the ground terminal so that the satellite closest to the ground terminal transmits the remote sensing image slice to the ground terminal when passing through the satellite, comprises: The compressed remote sensing image slices are transmitted to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the compressed remote sensing image slices to the ground terminal when passing by.

3. A satellite real-time intelligence monitoring method, characterized in that: Applied to a ground terminal, the method comprises: Receive remote sensing image slices transmitted by the edge computing unit of each satellite in the satellite constellation, wherein the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain the original remote sensing images taken by the satellite sensor at each time node; extract the intelligence monitoring area in the original remote sensing image to obtain the remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; Based on the remote sensing image slices taken by each satellite at each time node, multi-source fusion is performed on the remote sensing image slices taken by the different types of satellites, and multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; Intelligence monitoring is performed based on the multi-source fusion image and the multi-temporal fusion image to determine the target intelligence monitoring result corresponding to the intelligence monitoring area.

4. The method according to claim 3, characterized in that After the remote sensing image slices transmitted by the edge computing unit of each satellite in the receiving satellite constellation, the method further includes: Performing denoising and correction processing on the remote sensing image slices taken by each satellite at each time node to obtain the processed remote sensing image slices; Based on the processed remote sensing image slices taken by each satellite at each time node, image registration is performed on the processed remote sensing image slices taken by the different types of satellites, and image registration is performed on the processed remote sensing image slices taken at different time nodes, to obtain registered remote sensing image slices taken by different types of satellites and registered remote sensing image slices taken at different time nodes; The method of performing multi-source fusion on the remote sensing image slices taken by the different types of satellites based on the remote sensing image slices taken by each satellite at each time node, and performing multi-temporal fusion on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image includes: Performing multi-source fusion on registered remote sensing image slices taken by different types of satellites to obtain the multi-source fused image; Multi-temporal fusion is performed on the registered remote sensing image slices taken at different time points to obtain the multi-temporal fused image.

5. The method according to claim 3, characterized in that: The performing intelligence monitoring according to the multi-source fusion image and the multi-temporal fusion image to determine the target intelligence monitoring result corresponding to the intelligence monitoring area includes: Performing intelligence monitoring according to the multi-source fusion image to obtain a first intelligence monitoring result corresponding to the intelligence monitoring area; Performing intelligence monitoring according to the multi-temporal fusion image to obtain a second intelligence monitoring result corresponding to the intelligence monitoring area; Determine the target intelligence monitoring result according to the first intelligence monitoring result and the second intelligence monitoring result; and / or The ground terminal includes a movable portable device.

6. The method according to claim 5, characterized in that When the remote sensing image slices taken by the different types of satellites include optical image slices and synthetic aperture radar image slices, based on the remote sensing image slices taken by each satellite at each time node, multi-source fusion is performed on the remote sensing image slices taken by the different types of satellites to obtain a multi-source fused image, including: Performing wavelet transform on the optical image slice and the synthetic aperture radar image slice respectively to obtain a first wavelet coefficient corresponding to the optical image slice and a second wavelet coefficient corresponding to the synthetic aperture radar image slice; fusing the first wavelet coefficient and the second wavelet coefficient to obtain a fused wavelet coefficient; Performing inverse wavelet transform on the fused wavelet coefficients to obtain a fused multi-band image; Respectively converting the fused multi-band image and the synthetic aperture radar image slice into an IHS color space to obtain first grayscale information corresponding to the fused multi-band image and second grayscale information corresponding to the synthetic aperture radar image slice; Fusing the first grayscale information and the second grayscale information to obtain a fused IHS image; Converting the fused IHS image back to RGB color space to obtain the multi-source fused image; The performing intelligence monitoring according to the multi-source fusion image to obtain a first intelligence monitoring result corresponding to the intelligence monitoring area includes: The multi-source fusion image is input into a preset intelligence monitoring model to perform intelligence monitoring to obtain the first intelligence monitoring result.

7. The method according to claim 5, characterized in that Based on the remote sensing image slices taken by each satellite at each time node, multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes to obtain the multi-temporal fusion image, including: For any two adjacent time nodes among the different time nodes, if the remote sensing image slices taken at the any two adjacent time nodes are from the same type of satellite, subtract pixel values ​​of the remote sensing image slices taken at the any two adjacent time nodes to obtain a difference image, and determine the difference image as the multi-source fusion image; The performing intelligence monitoring according to the multi-temporal fusion image to obtain a second intelligence monitoring result corresponding to the intelligence monitoring area includes: Performing change detection on the difference image, determining a changed area in the difference image, and marking the changed area; Determining the second intelligence monitoring result according to the range of the marked change area; and / or Based on the remote sensing image slices taken by each satellite at each time node, multi-temporal fusion is performed on the remote sensing image slices taken at different time nodes to obtain the multi-temporal fusion image, including: For any two adjacent time nodes among the different time nodes, if the remote sensing image slices taken at the any two adjacent time nodes are from different types of satellites, a preset edge detection algorithm is used to extract borders of the remote sensing image slices taken at the any two adjacent time nodes; Mapping the frame information extracted from the two remote sensing image slices onto the same remote sensing image slice to obtain a mapping image, and determining the mapping image as the multi-temporal fusion image; The performing intelligence monitoring according to the multi-temporal fusion image to obtain a second intelligence monitoring result corresponding to the intelligence monitoring area includes: Based on the mapping image, determining the difference in border information between the two remote sensing image slices; Based on the border information difference, the second intelligence monitoring result is determined.

8. A satellite real-time intelligence monitoring device, characterized in that: An edge computing unit applied to each satellite in a satellite constellation, wherein the satellite constellation includes satellites of different types, and the device includes: An acquisition unit, used to acquire original remote sensing images taken by satellite sensors at various time points; An extraction unit, used for extracting the intelligence monitoring area in the original remote sensing image to obtain a remote sensing image slice; A transmission unit, used to transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; wherein the ground terminal is used to perform multi-source fusion of the remote sensing image slices taken by the different types of satellites according to the remote sensing image slices taken by each satellite at each time node, and perform multi-temporal fusion of the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; perform intelligence monitoring based on the multi-source fusion image and the multi-temporal fusion image to determine the target intelligence monitoring result corresponding to the intelligence monitoring area; and / or Applied to a ground terminal, the device comprises: A receiving unit is used to receive remote sensing image slices transmitted by an edge computing unit of each satellite in a satellite constellation, wherein the satellite constellation includes different types of satellites, and the edge computing unit is used to obtain original remote sensing images taken by satellite sensors at various time nodes; extract the intelligence monitoring area in the original remote sensing image to obtain remote sensing image slices; transmit the remote sensing image slices to the satellite closest to the ground terminal, so that the satellite closest to the ground terminal transmits the remote sensing image slices to the ground terminal when passing by; A fusion unit is used to perform multi-source fusion on the remote sensing image slices taken by the different types of satellites based on the remote sensing image slices taken by each satellite at each time node, and to perform multi-temporal fusion on the remote sensing image slices taken at different time nodes to obtain a multi-source fusion image and a multi-temporal fusion image; A determination unit is used to perform intelligence monitoring based on the multi-source fusion image and the multi-temporal fusion image, and determine the target intelligence monitoring result corresponding to the intelligence monitoring area.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method of any one of claims 1 to 2 and / or 3 to 7 is implemented.

10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 2 and / or 3 to 7 is implemented.

Images