Remote sensing data asset management system and method based on full life cycle management

Abstract

The invention discloses a remote sensing data asset management system and method based on full life cycle management, and belongs to the field of data asset management, and the method and the system comprise the steps of data acquisition, data processing and storage, data analysis and extraction, data application and service, data auditing and updating, risk monitoring, safety protection and the like. The data acquisition comprises acquisition of satellite remote sensing data, such as optical remote sensing data, infrared remote sensing data, radar remote sensing data and the like, and acquisition of terrain, weather, ocean, agriculture and environment information. And the data processing and storage comprises the steps of preprocessing remote sensing data, and carrying out data backup and security monitoring. Data analysis and extraction are carried out by adopting a deep learning method. Data application and service generation include various remote sensing data products and services. And data auditing and updating ensure the accuracy and real-time performance of the data. Risk monitoring and safety protection ensure the safety of data in the whole life cycle.

Description

Technical Field

[0001] The present invention belongs to the field of data asset management, and more specifically relates to a remote sensing data asset management system and method based on full life cycle management. Background Art

[0002] Data assets refer to data resources that are legally owned or controlled by a specific subject, can be measured in monetary terms, and can bring direct or indirect economic benefits. With the advancement of science and technology, my country's satellite remote sensing technology has been widely used in many fields. As an important strategic data asset, the standardized management and use of satellite remote sensing data is of great significance to promoting economic and social development.

[0003] In today's information society, data has become an indispensable and important resource for all walks of life, especially in the field of remote sensing. Remote sensing data, with its unique advantages, not only provides important decision-making basis for decision-makers and decision-making departments, but also plays an irreplaceable role in various fields such as agriculture, forestry, hydrology, meteorology, environmental protection, urban planning, disaster prevention and mitigation. However, with the development of remote sensing technology, the volume of remote sensing data continues to expand and the content continues to enrich, but it also brings about data management and service issues. There are many problems in the acquisition and distribution, storage and backup, processing and analysis, service and application of data.

[0004] Data asset management is a method that can help enterprises extract business value from a large amount of data and provide strong support for enterprise decision-making by managing and optimizing these data. As an important branch of data asset management, remote sensing data asset management also faces challenges in data collection, quality control, security, and utilization efficiency. Summary of the invention

[0005] The technical problem to be solved by the present invention is mainly how to effectively manage and utilize large-scale, multi-source, heterogeneous remote sensing data, especially in various links such as data acquisition, preprocessing, in-depth analysis, application and service, data audit update, risk monitoring and data security protection, to open up the entire life cycle of remote sensing data and realize comprehensive, systematic, source-to-end asset management of remote sensing data, aiming to improve the quality, utilization efficiency and security of remote sensing data, and ultimately maximize the value of remote sensing data.

[0006] In order to realize the above solution, the present invention is implemented by adopting the following technical solution: the method comprises:

[0007] Data collection: satellite remote sensing data collection, including optical remote sensing data, infrared remote sensing data, and radar remote sensing data;

[0008] Data processing and storage: pre-processing of remote sensing data, including radiation correction and geometric correction, regular data backup and security monitoring to ensure data security;

[0009] Data analysis and extraction, using deep learning to analyze remote sensing data;

[0010] Data applications and services, generating remote sensing data products and services;

[0011] Data review and update: regularly review and update the data in the system to ensure the accuracy and timeliness of the data;

[0012] Risk monitoring and security protection ensure the security of data throughout the entire life cycle and promptly detect and handle risks.

[0013] In one solution, the data collection includes the collection of topographic, meteorological, marine, agricultural and environmental information, and the data collection method is optical remote sensing, infrared remote sensing and radar remote sensing;

[0014] After data collection is completed, it is transmitted back to the ground station via remote sensing signals. After receiving the data, detailed inspection and verification are carried out to check whether the data has packet loss or bit errors; the new data received replaces the old data to keep the data up to date.

[0015] In one embodiment, the preprocessing includes radiation correction and geometric correction.

[0016] The purpose of radiation correction is to convert the digital value of the pixel into actual radiation brightness or reflectivity. The mathematical formula is as follows:

[0017]

[0018] Where L is the radiance, DN is the digitized pixel value, DNmin and DNmax are the minimum and maximum pixel values, Lmin and Lmax are the minimum and maximum radiances, respectively.

[0019] Geometric correction is to correct the geometric distortion of the image so that the pixels correspond more accurately to the actual position on the ground. The mathematical formula is as follows:

[0020] (X,Y)=T(x,y)

[0021] Among them, (X, Y) is the actual coordinate of the ground, (x, y) is the image coordinate of the pixel, and T is the conversion function from the pixel coordinate to the ground coordinate;

[0022] The data backup and security monitoring described above back up the data to the blockchain. Each data modification will form a new block and be added to the original blockchain. This not only tracks each data modification, but also effectively prevents data tampering.

[0023] In one embodiment, the data analysis and extraction uses generative adversarial networks (GANs), including:

[0024] Data preprocessing includes invalid value processing, data standardization and data enhancement;

[0025] Build a generator (G), the goal of which is to learn to generate images that are increasingly similar to real images from noise signals;

[0026] Construct a discriminator (D). The task of the discriminator is to distinguish whether the input image is a real image, that is, a binary classification problem.

[0027] Training GANs: During the training process, the generator and the discriminator are trained adversarially;

[0028] After training, the generator G generates images that are increasingly similar to real remote sensing data, and the discriminator D distinguishes whether the input image is a real image, thus completing the classification and recognition task of remote sensing data.

[0029] In one solution, the remote sensing data product generates remote sensing images of customized size, resolution, and area according to application requirements, including original remote sensing images and processed remote sensing images;

[0030] include:

[0031] Land use / land cover classification products generate land use / land cover maps by classifying remote sensing data, providing important information for urban planning and resource development;

[0032] Environmental monitoring products are used for monitoring environmental changes, forest coverage, lake area changes, desert expansion, and climate change monitoring and research;

[0033] Disaster assessment products: after earthquakes, floods, fires and other disasters occur, remote sensing data can be used to assess disaster losses and provide a basis for post-disaster reconstruction;

[0034] Agriculture and forestry monitoring products, used for crop growth monitoring and forest coverage monitoring;

[0035] The services described include:

[0036] Consulting services, providing consulting services on remote sensing application solutions to related industries and enterprises;.

[0037] Data API service, providing data API for developers;

[0038] Cloud processing services, providing online remote sensing data processing services;

[0039] Customized services, providing customized remote sensing products and services according to customer needs.

[0040] In one embodiment, the data review and update

[0041] Data review includes content review and quality review;

[0042] The quality review is performed using the Gaussian distribution check algorithm to check whether the data conforms to the normal distribution. The mathematical formula is as follows:

[0043]

[0044] Among them, x is the input data, μ is the mean of the data, σ is the standard deviation of the data, and p(x) is the output value of the probability density function, whose value reflects the fraction of x in the sample population;

[0045] Data updates are accomplished by implementing regular data capture tasks or system-triggered events.

[0046] In one solution, the risk monitoring monitors risk factors that threaten data security and protects data security by setting up firewalls and virus scanning security protection mechanisms.

[0047] In another aspect, a remote sensing data asset management system based on full life cycle management is provided, wherein the management system is applicable to the method described above, and the system comprises:

[0048] Data acquisition module, for collecting satellite remote sensing data, including optical remote sensing data, infrared remote sensing data, and radar remote sensing data;

[0049] The data processing and storage module pre-processes remote sensing data, including radiation correction and geometric correction, and performs regular data backup and security monitoring to ensure data security;

[0050] Data analysis and extraction module, which uses deep learning to analyze remote sensing data;

[0051] Data application and service module, generating remote sensing data products and services;

[0052] Data review and update module, which regularly reviews and updates the data in the system to ensure the accuracy and timeliness of the data;

[0053] The risk monitoring and security protection module ensures the security of data throughout the entire life cycle and promptly detects and handles risks.

[0054] On the other hand, the data acquisition module also includes the acquisition of UAV remote sensing data;

[0055] In the data analysis and extraction module, Generative Adversarial Networks (GANs) are used to improve the accuracy and efficiency of remote sensing data analysis;

[0056] In the data application and service module, data visualization services are also provided, allowing users to intuitively view and understand remote sensing data.

[0057] Beneficial effects of the present invention:

[0058] First, it adopts a full life cycle management approach, covering the collection, processing and storage, analysis and extraction, application services, review and update, and risk monitoring of remote sensing data, to complete the comprehensive management and utilization of remote sensing data. Secondly, by adopting radiation correction and geometric correction in the data processing and storage stage, the accuracy of the data is enhanced, and blockchain technology is used to enhance the transparency and security of the data. In addition, in the data analysis and extraction stage, the accuracy and efficiency of remote sensing data recognition are effectively improved by applying deep learning technology, especially generative adversarial networks (GANs). In terms of risk monitoring and security protection, the security protection of remote sensing data throughout the life cycle is strengthened, greatly reducing the risks caused by data leakage, tampering, etc. In addition, the present invention also provides various types of products and services to meet the needs of different industries and enterprises, and provides data visualization services so that users can understand and use remote sensing data more intuitively. In the data review and update stage, the accuracy and real-time nature of data assets are ensured by implementing Gaussian distribution check algorithms and regular data capture or system trigger events. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of the method of the present invention;

[0060] Figure 2 The data analysis and extraction flow chart of the method of the present invention is as follows;

[0061] Figure 3 This is a system block diagram of the present invention. DETAILED DESCRIPTION

[0062] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0063] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0064] Embodiment 1:

[0065] like Figure 1 As shown, the remote sensing data asset management method based on full life cycle management includes:

[0066] S1. Data collection: collect satellite remote sensing data, including optical remote sensing data, infrared remote sensing data, and radar remote sensing data.

[0067] Data collection, automatic data collection. This includes the collection of various information such as terrain, weather, ocean, agriculture, environment, etc. There are many ways to collect data, such as optical remote sensing, infrared remote sensing, radar remote sensing, etc.

[0068] After data collection is completed, it is transmitted back to the ground station through remote sensing signals. Including signal transmission, reception, decoding and other equipment and technologies to ensure that the data can be transmitted back accurately and in a timely manner.

[0069] After receiving the data, detailed inspection and verification are carried out to ensure the quality and integrity of the data, such as checking whether there are packet loss, bit errors, etc., and whether the data quality meets the preset standards.

[0070] S2. Data processing and storage: pre-processing of remote sensing data, including radiation correction and geometric correction, regular data backup and security monitoring to ensure data security.

[0071] After receiving the remote sensing data, the first thing to do is to preprocess the data, which mainly includes radiation correction and geometric correction.

[0072] The purpose of radiation correction is to convert the digital value of the pixel into actual radiation brightness or reflectivity. The mathematical formula is as follows:

[0073]

[0074] Where L is the radiance, DN is the digitized pixel value, DNmin and DNmax are the minimum and maximum pixel values, Lmin and Lmax are the minimum and maximum radiances, respectively.

[0075] The purpose of geometric correction is to correct the geometric distortion of the image so that the pixels correspond more accurately to the actual position on the ground. The mathematical formula is as follows:

[0076] (X,Y)=T(x,y)

[0077] Among them, (X, Y) is the actual coordinate of the ground, (x, y) is the image coordinate of the pixel, and T is the conversion function from the pixel coordinate to the ground coordinate;

[0078] The preprocessed remote sensing data needs to be stored in a certain format, which is usually determined by the characteristics of the data and the usage requirements. The general process of data storage includes selecting a suitable data model and storage structure, encoding the data, and then writing the data to a database or file system.

[0079] The data backup and security monitoring described above back up the data to the blockchain. Each data modification will form a new block and be added to the original blockchain. This not only tracks each data modification, but also effectively prevents data tampering.

[0080] The detailed process of data backup and security monitoring using blockchain technology can be achieved as follows:

[0081] After the remote sensing data is preprocessed, it is stored in a new block as a transaction record. Each block contains one or more transactions and a pointer to the previous block.

[0082] In order to be added to the blockchain, new blocks are verified through a process called "generating a new blockchain". The main task of generating a new blockchain is to find a value such that the hash value of the block (determined by the block content) meets certain conditions. For a normal computer, finding such a value requires a lot of calculations. If such a value is found, the block is added to the blockchain, and this process is called a successful generation of a new blockchain.

[0083] When a new block is successfully generated into a new blockchain, it can be added to the blockchain. Each new block contains a link to the previous block, forming a chain from the latest block to the initial block. Every modification of data will form a new block and be added to the blockchain.

[0084] From then on, every query, modification, and deletion of data must follow the rules of the blockchain, that is, all operations must be made public in the entire blockchain network, which ensures the transparency and traceability of the data and is conducive to the security monitoring of the data.

[0085] like Figure 2 As shown, S3, data analysis and extraction,remote sensing data analysis using deep learning.

[0086] The data analysis and extraction uses generative adversarial networks (GANs), including:

[0087] S301. Data preprocessing includes invalid value processing, data standardization and data enhancement.

[0088] The preprocessing of remote sensing data mainly includes invalid value processing, data standardization and data enhancement. Among them, data standardization requires calculating the mean μ and standard deviation σ of the remote sensing image, so that the standardized data obeys a normal distribution with a mean of 0 and a standard deviation of 1. Among them, the standardization formula is:

[0089] X'=(X-μ) / σ

[0090] S302, build a generator (G). The goal of the generator is to learn how to generate images that are increasingly similar to real images from noise signals. Its network structure may include a fully connected layer (FC), batch normalization (BN), ReLU activation function, etc. The loss function of the generator is L G = -log(D(G(z))), the goal is to make the generated image able to "fool" the discriminator as much as possible.

[0091] S303, construct a discriminator (D). The task of the discriminator is to distinguish whether the input image is a real image, that is, a binary classification problem. The network structure may include a fully connected layer (FC), a LeakyReLU activation function, a Sigmoid activation function, etc. The loss function of the discriminator is L D =-[log(D(x))+log(1-D(G(z)))], which can correctly identify real images and images generated by the generator.

[0092] S304, training GANs: During the training process, the generator and the discriminator are trained adversarially. First, the generator G is fixed, and the discriminator D is updated to minimize L D ; Then fix the discriminator D and update the generator G to minimize L G .

[0093] S305. After training, the generator G can generate images that are increasingly similar to real remote sensing data, and the discriminator D can distinguish whether the input image is a real image, that is, the classification and recognition tasks of remote sensing data are completed.

[0094] The above are the detailed steps for using GANs for remote sensing data classification and recognition. This is a method for remote sensing data classification and recognition by simulating the image generation process and optimizing the difference between the generated image and the real image.

[0095] S4, Data Applications and Services, generate remote sensing data products and services. Use these data products to provide services such as customized reports, consulting services, or data APIs. In addition, data products can be iteratively improved based on user feedback.

[0096] The remote sensing data products described above generate remote sensing images of customized size, resolution, and area according to application requirements, including original remote sensing images and processed remote sensing images.

[0097] Remote sensing image products: Based on application requirements, remote sensing images of customized size, resolution, and area can be generated, including original remote sensing images and processed remote sensing images (such as cropped, geometrically corrected, and radiation-corrected images).

[0098] Land use / land cover classification products: By classifying remote sensing data, land use / land cover maps can be generated to provide important information for urban planning, resource development, etc.

[0099] Environmental monitoring products: Remote sensing data can be used to monitor environmental changes, such as forest coverage, lake area changes, desert expansion, climate change, etc.

[0100] Disaster assessment products: After earthquakes, floods, fires and other disasters occur, remote sensing data can be used to assess disaster losses and provide a basis for post-disaster reconstruction.

[0101] Agricultural and forestry monitoring products: Remote sensing data can be used to monitor crop growth and tree cover, which helps farm management and forestry planning.

[0102] The services described include:

[0103] Consulting services: Provide consulting services on remote sensing application solutions to related industries and enterprises, including solution design, implementation and training.

[0104] Data API service: Provides data APIs to developers so that they can integrate and use these remote sensing data and products in their own systems and applications.

[0105] Cloud processing service: Provides online remote sensing data processing services. Users can complete various data processing tasks on the cloud platform without downloading data.

[0106] Customized services: Provide customized remote sensing products and services according to customer needs, such as remote sensing data acquisition, processing and analysis of specific areas, specific times and specific topics.

[0107] S5. Data review and update: Regularly review and update the data in the system to ensure the accuracy and timeliness of the data.

[0108] Data auditing usually includes content review and quality review. Content review mainly checks whether the data content is true and accurate. Quality review checks whether the quality of the data meets the requirements, such as whether it contains too much noise, missing values ​​or outliers. Quality review is performed through the Gaussian distribution check algorithm to check whether the data conforms to the normal distribution. Its mathematical formula is expressed as follows:

[0109]

[0110] Among them, x is the input data, μ is the mean of the data, σ is the standard deviation of the data, and p(x) is the output value of the probability density function, whose value reflects the fraction of x in the sample population.

[0111] Data updates can be accomplished by implementing regular data capture tasks or system-triggered events, such as recollecting remote sensing data and deleting obsolete data.

[0112] S6. Risk monitoring and security protection ensure the security of data throughout the entire life cycle and promptly detect and handle risks.

[0113] Risk monitoring is mainly to monitor risk factors that may threaten data security, such as hacker attacks, system crashes, etc. Generally, data security can be protected by setting up firewalls, data encryption, virus scanning and other security protection mechanisms.

[0114] Embodiment 2:

[0115] According to the first embodiment, a remote sensing data asset management system based on full life cycle management is constructed. The management system is applicable to the method described. The system includes:

[0116] The first is the data acquisition module, which is responsible for collecting satellite remote sensing data, including optical remote sensing data, infrared remote sensing data and radar remote sensing data. This is the primary link in the management system's work and provides raw data for subsequent work.

[0117] The second is the data processing and storage module, which pre-processes remote sensing data, including radiation correction and geometric correction, to ensure the accuracy of the data. At the same time, the module also regularly performs data backup and security monitoring to ensure data security and prevent information loss or leakage.

[0118] Next is the data analysis and extraction module, which uses deep learning to analyze remote sensing data to extract valuable information and features and provide data support for decision-making. The data acquisition module also includes the acquisition of remote sensing data from drones, which is an additional data acquisition method that can supplement the acquisition of remote sensing data in specific situations and environments to improve the integrity of the data. In the data analysis and extraction module, the system uses generative adversarial networks (GANs) to improve the accuracy and efficiency of remote sensing data analysis, effectively improving the quality of data analysis. In the data application and service module, data visualization services are also provided, allowing users to intuitively view and understand remote sensing data, helping users better understand and use data.

[0119] Then comes the data application and service module, which generates remote sensing data products and services. This is the main output link of the system and provides users with directly usable data products.

[0120] There is also a data review and update module, which regularly reviews and updates the data in the system to ensure the accuracy and real-time nature of the data and keep the data fresh.

[0121] The last one is the risk monitoring and security protection module, which ensures the security of data throughout the entire life cycle, detects and handles risks in a timely manner, and prevents data leakage and damage.

[0122] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0123] It should be understood that the detailed description of the technical solutions of the present invention by means of the preferred embodiments is illustrative rather than restrictive. A person skilled in the art may modify the technical solutions described in the embodiments, or replace some of the technical features by equivalents, based on reading the specification of the present invention; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote sensing data asset management method based on full life cycle management, characterized by: The method includes: Data collection: satellite remote sensing data collection, including optical remote sensing data, infrared remote sensing data, and radar remote sensing data; Data processing and storage: pre-processing of remote sensing data, including radiation correction and geometric correction, regular data backup and security monitoring to ensure data security; Data analysis and extraction, using deep learning to analyze remote sensing data; Data applications and services, generating remote sensing data products and services; Data review and update: regularly review and update the data in the system to ensure the accuracy and timeliness of the data; Risk monitoring and security protection ensure the security of data throughout the entire life cycle and promptly detect and handle risks.

2. A remote sensing data asset management method based on full life cycle management according to claim 1, characterized in that: The data collection includes the collection of terrain, meteorology, ocean, agriculture, and environmental information, and the data collection methods are optical remote sensing, infrared remote sensing, and radar remote sensing; After data collection is completed, it is transmitted back to the ground station via remote sensing signals. After receiving the data, detailed inspection and verification are carried out to check whether the data has packet loss or bit errors; the new data received replaces the old data to keep the data up to date.

3. The remote sensing data asset management method based on full life cycle management according to claim 1 is characterized in that: The preprocessing includes radiation correction and geometric correction; The purpose of radiation correction is to convert the digital value of the pixel into actual radiation brightness or reflectivity. The mathematical formula is as follows: Where L is the radiance, DN is the digitized pixel value, DNmin and DNmax are the minimum and maximum pixel values, Lmin and Lmax are the minimum and maximum radiances, respectively. Geometric correction is to correct the geometric distortion of the image so that the pixels correspond more accurately to the actual position on the ground. The mathematical formula is as follows: (X,Y)=T(x,y) Among them, (X, Y) is the actual coordinate of the ground, (x, y) is the image coordinate of the pixel, and T is the conversion function from the pixel coordinate to the ground coordinate; The data backup and security monitoring described above back up the data to the blockchain. Each data modification will form a new block and be added to the original blockchain. This not only tracks each data modification, but also effectively prevents data tampering.

4. The remote sensing data asset management method based on full life cycle management according to claim 1 is characterized in that: The data analysis and extraction uses generative adversarial networks (GANs), including: Data preprocessing includes invalid value processing, data standardization and data enhancement; Build a generator (G), the goal of which is to learn to generate images that are increasingly similar to real images from noise signals; Construct a discriminator (D). The task of the discriminator is to distinguish whether the input image is a real image, that is, a binary classification problem. Training GANs: During the training process, the generator and the discriminator are trained adversarially; After training, the generator G generates images that are increasingly similar to real remote sensing data, and the discriminator D distinguishes whether the input image is a real image, thus completing the classification and recognition task of remote sensing data.

5. The remote sensing data asset management method based on full life cycle management according to claim 1 is characterized in that: The remote sensing data products described above generate remote sensing images of customized size, resolution, and area according to application requirements, including original remote sensing images and processed remote sensing images; include: Land use / land cover classification products generate land use / land cover maps by classifying remote sensing data, providing important information for urban planning and resource development; Environmental monitoring products are used for monitoring environmental changes, forest coverage, lake area changes, desert expansion, and climate change monitoring and research; Disaster assessment products: after earthquakes, floods, and fires occur, remote sensing data can be used to assess disaster losses and provide a basis for post-disaster reconstruction; Agriculture and forestry monitoring products, used for crop growth monitoring and forest coverage monitoring; The services described include: Consulting services: providing consulting services on remote sensing application solutions to relevant industries and enterprises; Data API service, providing data API for developers; Cloud processing services, providing online remote sensing data processing services; Customized services, providing customized remote sensing products and services according to customer needs.

6. The remote sensing data asset management method based on full life cycle management according to claim 1 is characterized in that: Data review and update as described Data review includes content review and quality review; The quality review is performed using the Gaussian distribution check algorithm to check whether the data conforms to the normal distribution. The mathematical formula is as follows: Among them, x is the input data, μ is the mean of the data, σ is the standard deviation of the data, and p(x) is the output value of the probability density function, whose value reflects the fraction of x in the sample population; Data updates are accomplished by implementing regular data capture tasks or system-triggered events.

7. The remote sensing data asset management method based on full life cycle management according to claim 1 is characterized in that: The risk monitoring described above monitors the risk factors that threaten data security and protects data security by setting up firewalls and virus scanning security protection mechanisms.

8. A remote sensing data asset management system based on full life cycle management, the management system being applicable to the method according to any one of claims 1 to 7, characterized in that: The system comprises: Data acquisition module, for collecting satellite remote sensing data, including optical remote sensing data, infrared remote sensing data, and radar remote sensing data; The data processing and storage module pre-processes remote sensing data, including radiation correction and geometric correction, and performs regular data backup and security monitoring to ensure data security; Data analysis and extraction module, which uses deep learning to analyze remote sensing data; Data application and service module, generating remote sensing data products and services; Data review and update module, which regularly reviews and updates the data in the system to ensure the accuracy and timeliness of the data; The risk monitoring and security protection module ensures the security of data throughout the entire life cycle and promptly detects and handles risks.

9. A remote sensing data asset management system based on full life cycle management, characterized by: The data acquisition module also includes the acquisition of UAV remote sensing data; In the data analysis and extraction module, Generative Adversarial Networks (GANs) are used to improve the accuracy and efficiency of remote sensing data analysis; In the data application and service module, data visualization services are also provided, allowing users to intuitively view and understand remote sensing data.

Images