Remote sensing image geological structure information extraction system

Abstract

The invention relates to the technical field of geological exploration, and discloses a remote sensing image geological structure information extraction system, which comprises an image acquisition module, a feature extraction module, a data integration module, a data calculation module, a data analysis module and a feedback module, according to the system, high-quality geological information can be extracted from a complex remote sensing image by integrating an image acquisition module, a feature extraction module, a data integration module, a data calculation module, a data analysis module, a feedback module and the like, and various errors in data are comprehensively corrected. Compared with a traditional method, the system has the advantages that data accuracy and reliability are improved, manual intervention is reduced, processing efficiency and result quality are improved, high consistency and precision can be kept when the system processes large-scale areas and complex geological structures due to the comprehensive correction and analysis capability, and the system can be widely applied to the field of geological engineering. Therefore, more effective support is provided for geological research and resource exploration.

Description

Technical Field

[0001] The invention relates to the technical field of geological exploration, and in particular to a remote sensing image geological structure information extraction system. Background Art

[0002] Remote sensing image geological structure information extraction systems are used to identify and analyze geological structural features, such as faults, folds, and lithologic boundaries. These systems can provide detailed geological structure information by processing remote sensing image data and combining geological models and algorithms, thereby providing support for mineral resource exploration, natural disaster assessment, environmental protection, and other work.

[0003] There are many shortcomings in the traditional process of extracting geological structure information. First, the quality of image data is unstable and is easily affected by noise, radiation and geometric distortion, resulting in low accuracy of the extracted geological information. Second, traditional layer generation and data correction methods rely on manual operations, which are inefficient and prone to human errors leading to deviations in information extraction results. Especially when dealing with large-scale and complex geological structures, the existing methods have limited computing power and lack an automated correction mechanism, and the processing speed and accuracy are difficult to meet actual needs. In addition, the system cannot automatically adapt to the characteristics of different image data, and the results are often imprecise.

[0004] Therefore, we proposed a remote sensing image geological structure information extraction system to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a remote sensing image geological structure information extraction system to solve the problem that the existing methods mentioned in the background art are difficult to maintain consistency and accuracy when dealing with complex geological structures or large-scale areas, and generally lack the ability to comprehensively correct different error sources.

[0006] To achieve the above object, the present invention provides the following technical solutions: a remote sensing image geological structure information extraction system, including an image acquisition module, a feature extraction module, a data integration module, a data calculation module, a data analysis module and a feedback module; The image acquisition module is used to capture regional geological images and generate a sample layer I; The feature extraction module is used to extract multi-source data of sample layer I; The data integration module is used to preprocess the multi-source data extracted by the feature extraction module, and organize the preprocessed multi-source data to generate a first data set, a second data set, and a third data set; The data calculation module integrates and calculates the first data set, the second data set and the third data set respectively, so as to generate a radiation calibration coefficient S1, a geometric calibration coefficient S2 and a noise calibration coefficient S3, and integrates and calculates the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 to generate a filtering reference coefficient GLC; The data analysis module integrates and calculates the sample layer I and the filtering reference coefficient GLC to generate the actual layer Ip, and compares the actual layer Ip with a preset threshold value Y to generate a first comparison result, and determines whether the actual layer Ip meets the usage requirements according to the comparison result; If the comparison result shows that the actual layer Ip does not meet the use requirements, the sample layer I is integrated and calculated with the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively, so as to generate several corrected samples In, and the several corrected samples In are respectively replaced with the sample layer I and the filtering reference coefficient GLC for integrated calculation, so as to generate a new actual layer Ip, and the generated new actual layer Ip is compared with the threshold value Y until the use requirements are met; The feedback module is used to feed back the final corrected actual layer IP to the operation page.

[0007] Preferably, the feature extraction module includes a first extraction unit, a second extraction unit and a third extraction unit; The first extraction unit is used to extract radiation parameters in the sample layer I, the second extraction unit is used to extract geometric parameters in the sample layer I, and the third extraction unit is used to extract noise parameters in the sample layer I; Radiation parameters, geometric parameters, and noise parameters are aggregated into multi-source data.

[0008] Preferably, the data integration module includes a data preprocessing unit and a data sorting unit, and the data preprocessing unit is used to preprocess the multi-source data extracted by the feature extraction module; The data sorting unit is used to perform dimensionless transformation on the multi-source data after preprocessing, and reorganize the dimensionless multi-source data into a first data set, a second data set, and a third data set.

[0009] Preferably, the first data set includes radiance FSL, spectral characteristic GPT, ground object reflectance DFS, ozone content CYH, whiteboard reflectance BFS and blackboard reflectance HFS; The second data set includes the height value GDZ, the accuracy value JDZ, the spread rate SBL, the shooting angle PSJ, the tilt angle QXJ, and the resolution FBL; The third data set includes the signal-to-noise ratio XZB, the dark current ADL, the spot intensity GBQ, the aerosol thickness QRJ, the water vapor content SJH and the atmospheric transmittance DQT.

[0010] Preferably, the data calculation module calculates and obtains the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively through the following formulas;

[0011] Among them, FSL is the radiation brightness, GPT is the spectral characteristics, DFS is the ground reflectance, CYH is the ozone content, BFS is the whiteboard reflectance, HFS is the blackboard reflectance, GDZ is the height value, JDZ is the accuracy value, SBL is the scatter rate, PSJ is the shooting angle, QXJ is the tilt angle, FBL is the resolution, XZB is the signal-to-noise ratio, ADL is the dark current, GBQ is the spot intensity, QRJ is the aerosol thickness, SJH is the water vapor content, and DQT is the atmospheric transmittance.

[0012] Preferably, the data calculation module calculates and obtains the filtering reference coefficient GLC through the following formula:

[0013] Among them, S1 is the radiation calibration coefficient, S2 is the geometric calibration coefficient, S3 is the noise calibration coefficient, and a1, a2 and a3 are weight values.

[0014] Preferably, the data analysis module calculates and generates the actual layer Ip by the following formula:

[0015] Among them, A is the reference function, I and In are filled in respectively, I is the sample layer, In is the correction sample, and GLC is the filtering reference coefficient.

[0016] Preferably, the data analysis module generates the corrected sample In by calculating through the following formula:

[0017] Where I is the sample layer, B is the reference function, and the radiation calibration coefficient S1, geometric calibration coefficient S2 and noise calibration coefficient S3 are filled in respectively.

[0018] Preferably, the comparison results are as follows: when , it means the layer can be used directly; when , it means the layer cannot be used directly; If the actual layer layer Ip cannot be used directly, set the radiation calibration coefficient S1 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate a new Ip, and re-perform the comparison; If the new actual layer Ip cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip, generate the actual layer Ip again, and re-perform the comparison; If the actual layer Ip generated again cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate the actual layer Ip, and re-execute the comparison. If the result is still not directly usable, repeat the cycle until the layer can be used.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. This system integrates modules such as image acquisition, feature extraction, data integration, data calculation, data analysis and feedback. The system can extract high-quality geological information from complex remote sensing images and comprehensively correct various errors in the data. Compared with traditional methods, this system improves the accuracy and reliability of data, reduces manual intervention, and improves processing efficiency and the quality of results. The comprehensive correction and analysis capabilities enable the system to maintain high consistency and accuracy when processing large-scale areas and complex geological structures, thereby providing more effective support for geological research and resource exploration.

[0020] 2. This system uses a step-by-step optimization approach to generate a usable actual layer Ip. If the initially generated layer Ip does not meet the preset requirements, the system will apply the radiation, geometry, and noise calibration coefficients S3 respectively for iterative correction. This step-by-step optimization process can ensure that the final layer meets the usage standards, improves the accuracy and reliability of processing, and processes layers that do not meet the requirements through an automated correction process without manual intervention. This automated correction mechanism improves the efficiency and accuracy of data processing, reduces human errors, and accelerates the generation process of the final layer. The system's correction process can adjust the calibration coefficient according to actual conditions, providing strong adaptability. By adjusting the radiation, geometry, and noise calibration coefficients S3, the system can optimize for different image data characteristics, making the processing results more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a system flow chart of the present invention.

[0022] In the figure: 1. Image acquisition module; 2. Feature extraction module; 21. First extraction unit; 22. Second extraction unit; 23. Third extraction unit; 3. Data integration module; 31. Data preprocessing unit; 32. Data sorting unit; 4. Data calculation module; 5. Data analysis module; 6. Feedback module. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example 1: Please refer to Figure 1 , a remote sensing image geological structure information extraction system, comprising an image acquisition module 1, a feature extraction module 2, a data integration module 3, a data calculation module 4, a data analysis module 5 and a feedback module 6; The image acquisition module 1 is used to capture regional geological images and generate a sample layer I; The feature extraction module 2 is used to extract multi-source data from the sample layer I; The data integration module 3 is used to preprocess the multi-source data extracted by the feature extraction module 2, and organize the preprocessed multi-source data to generate a first data set, a second data set, and a third data set; The data calculation module 4 integrates and calculates the first data set, the second data set and the third data set respectively, so as to generate a radiation calibration coefficient S1, a geometric calibration coefficient S2 and a noise calibration coefficient S3, and integrates and calculates the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 to generate a filtering reference coefficient GLC; The data analysis module 5 integrates and calculates the sample layer I and the filtering reference coefficient GLC to generate the actual layer Ip, and compares the actual layer Ip with the preset threshold value Y to generate a first comparison result, and determines whether the actual layer Ip meets the use requirements according to the comparison result; If the comparison result shows that the actual layer Ip does not meet the use requirements, the sample layer I is integrated and calculated with the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively, so as to generate several corrected samples In, and the several corrected samples In are respectively replaced with the sample layer I and the filtering reference coefficient GLC for integrated calculation, so as to generate a new actual layer Ip, and the generated new actual layer Ip is compared with the threshold value Y until the use requirements are met; The feedback module 6 is used to feed back the final corrected actual layer IP to the operation page.

[0025] In this embodiment: Image acquisition module 1 is the basis of the remote sensing image geological structure information extraction system, which is responsible for taking geological images of the target area and generating sample layer I. The effectiveness of this module directly affects the quality and accuracy of subsequent data processing. Through high-resolution image acquisition, this module can obtain detailed geological feature information, including faults, folds and lithology boundaries, and provide high-quality input data for the feature extraction module. This process ensures the basic quality of the data and lays a solid foundation for subsequent feature extraction and analysis.

[0026] Feature extraction module 2 extracts multi-source data from sample layer 1, which include various information of geological features, such as fault lines, fold morphology and rock types. Through efficient feature extraction algorithm, this module can identify and extract key geological structure features from complex remote sensing images. The extracted data provides multi-dimensional information support for data integration module 3, making subsequent data processing more accurate and comprehensive. The main task of this module is to convert raw image data into useful geological feature data, which improves the availability of data and the depth of analysis.

[0027] The data integration module 3 preprocesses and organizes the multi-source data extracted by the feature extraction module 2 to generate the first data set, the second data set, and the third data set. This module solves the inconsistency problem between different data sources by integrating and standardizing the data. The preprocessed data set helps to eliminate noise, correct errors, and integrate multi-source data into a standard format that can be used for further calculations. This process improves the overall quality and consistency of the data and provides a reliable foundation for subsequent data calculations.

[0028] The data calculation module 4 integrates and calculates the first data set, the second data set and the third data set to generate the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3, and integrates these coefficients to generate the filtering reference coefficient GLC. The main task of this module is to correct various errors in the data through comprehensive calculation, including radiation error, geometric distortion and noise influence. Through precise calibration and calculation, the module can generate high-quality filtering reference coefficients GLC, thereby significantly improving the accuracy and reliability of image data and providing an accurate basis for data analysis.

[0029] The data analysis module 5 integrates and calculates the sample layer I and the filtering reference coefficient GLC to generate the actual layer Ip, and compares Ip with the preset threshold value Y to generate the first comparison result. Through this process, the module can determine whether the actual layer Ip meets the usage requirements and make corresponding adjustments based on the comparison results. If the actual layer Ip does not meet the requirements, a corrected sample In will be further generated and integrated with the filtering reference coefficient GLC until it meets the requirements. The task of this module is to ensure that the generated actual layer has sufficient quality and accuracy by comparing with the threshold.

[0030] Feedback module 6 is responsible for feeding back the final corrected actual layer IP to the operation page. Through the feedback module, users can instantly obtain the corrected and optimized layer data, ensuring that the system output results can be applied to actual work in a timely manner. This module improves the user interaction experience and data processing efficiency of the system, so that the final geological structure information can be quickly and accurately delivered to users, supporting subsequent decision-making and application.

[0031] By integrating modules such as image acquisition, feature extraction, data integration, data calculation, data analysis and feedback, this system can extract high-quality geological information from complex remote sensing images and comprehensively correct various errors in the data. Compared with traditional methods, this system improves the accuracy and reliability of data, reduces manual intervention, and improves processing efficiency and the quality of results. The comprehensive correction and analysis capabilities enable the system to maintain high consistency and accuracy when processing large-scale areas and complex geological structures, thereby providing more effective support for geological research and resource exploration.

[0032] Example 2: Please refer to Figure 1 , the feature extraction module 2 includes a first extraction unit 21, a second extraction unit 22 and a third extraction unit 23; The first extraction unit 21 is used to extract radiation parameters in the sample layer I, the second extraction unit 22 is used to extract geometric parameters in the sample layer I, and the third extraction unit 23 is used to extract noise parameters in the sample layer; Radiation parameters, geometric parameters, and noise parameters are aggregated into multi-source data.

[0033] In this embodiment: the feature extraction module 2 is subdivided into three specialized units, so that each unit can focus on processing a specific type of parameters. This modular design improves the flexibility and maintainability of the system, so that each unit can be optimized and updated independently without affecting the functions of other units. The first extraction unit 21 focuses on extracting radiation parameters, the second extraction unit 22 processes geometric parameters, and the third extraction unit 23 extracts noise parameters. This parameter extraction method with a clear division of labor ensures that each type of data can be analyzed and processed more accurately, improves the accuracy and efficiency of data extraction, and by extracting and processing radiation, geometry and noise parameters separately, the impact of these parameters on geological images can be better identified and corrected. This method helps to reduce confusion and errors, thereby improving the quality and reliability of the final extracted data.

[0034] Example 3: Please refer to Figure 1 , the data integration module 3 includes a data preprocessing unit 31 and a data sorting unit 32, the data preprocessing unit 31 is used to preprocess the multi-source data extracted by the feature extraction module 2; The data sorting unit 32 is used to perform dimensionless transformation on the preprocessed multi-source data, and reorganize the dimensionless multi-source data into a first data set, a second data set, and a third data set.

[0035] The first data set includes radiance FSL, spectral characteristics GPT, ground reflectance DFS, ozone content CYH, whiteboard reflectance BFS and blackboard reflectance HFS; The second data set includes the height value GDZ, the accuracy value JDZ, the spread rate SBL, the shooting angle PSJ, the tilt angle QXJ, and the resolution FBL; The third data set includes the signal-to-noise ratio XZB, the dark current ADL, the spot intensity GBQ, the aerosol thickness QRJ, the water vapor content SJH and the atmospheric transmittance DQT.

[0036] In this embodiment: the data integration module 3 divides data processing into two stages: preprocessing and sorting. The data preprocessing unit 31 focuses on cleaning and preliminary processing of multi-source data to ensure the consistency and accuracy of the data; the data sorting unit 32 performs dimensionless processing and data sorting to improve the standardization of the data. This hierarchical processing method improves the systematicness and efficiency of data processing. Through dimensionless processing, the data sorting unit 32 eliminates the dimensional differences between different data sources, so that the data has a consistent scale during the analysis process. This processing method makes subsequent calculations and analyses more accurate and reduces errors caused by inconsistent dimensions. The preprocessed data is sorted into three specific data sets: the first data set, the second data set, and the third data set. Each data set contains detailed information on specific parameters. This structured sorting method improves the operability and manageability of the data, and facilitates subsequent integrated calculations and analysis.

[0037] Example 4: Please refer to Figure 1 The data calculation module 4 calculates and obtains the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively through the following formulas;

[0038] Among them, FSL is the radiation brightness, GPT is the spectral characteristics, DFS is the ground reflectance, CYH is the ozone content, BFS is the whiteboard reflectance, HFS is the blackboard reflectance, GDZ is the height value, JDZ is the accuracy value, SBL is the scatter rate, PSJ is the shooting angle, QXJ is the tilt angle, FBL is the resolution, XZB is the signal-to-noise ratio, ADL is the dark current, GBQ is the spot intensity, QRJ is the aerosol thickness, SJH is the water vapor content, and DQT is the atmospheric transmittance.

[0039] The data calculation module 4 calculates and obtains the filtering reference coefficient GLC through the following formula;

[0040] Among them, S1 is the radiation calibration coefficient, S2 is the geometric calibration coefficient, S3 is the noise calibration coefficient, and a1, a2 and a3 are weight values.

[0041] In this embodiment: by calculating the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively, the data calculation module 4 adopts a comprehensive correction mechanism to handle various errors in the remote sensing image data. Each coefficient is calculated based on specific parameters to ensure the comprehensiveness and pertinence of the correction. This method can effectively correct different types of errors and improve the overall quality of the image data. The radiation calibration, geometric calibration and noise calibration are calculated separately, and various errors can be handled modularly. This correction method with clear division of labor enables each calibration to be optimized independently, improving the flexibility and accuracy of the overall correction.

[0042] Through meticulous radiation, geometry and noise correction, the system can significantly improve the accuracy of remote sensing image data. These calibration coefficients effectively correct various errors in the image data, making the final geological information extraction results more reliable. The effects of radiation brightness, geometric distortion and noise on remote sensing images are systematically corrected, so that the image quality is comprehensively improved. This improvement enables the image data to show higher clarity and details when applied to geological structure analysis. The accurate calibration coefficient enables the data analysis module 5 to more effectively compare the actual layer with the reference coefficient, thereby generating more accurate geological structure information. This process enhances the system's ability to extract geological structure features and provides more valuable data support for geological research. Through automated calibration calculations, the system reduces its reliance on manual adjustment and intervention. The automated calibration process improves the efficiency of data processing and reduces the impact of human errors, making the overall system more efficient and reliable.

[0043] By weighting the radiation calibration coefficient S1, geometric calibration coefficient S2 and noise calibration coefficient S3, the formula combines different types of calibration coefficients into a filtering reference coefficient GLC. This weighted method can give different weights to each calibration coefficient according to its importance, thereby achieving more accurate and personalized data correction.

[0044] The weight values ​​in the formula provide a flexible adjustment mechanism, allowing users to adjust the influence of various calibration coefficients according to actual needs and data characteristics. This flexibility allows the system to better adapt to different application scenarios and data conditions.

[0045] By calculating different types of calibration coefficients into a filter reference coefficient GLC, the module can more comprehensively consider various error sources in the image data. The comprehensive correction effect improves the accuracy and stability of image data processing.

[0046] The weighted synthesis method can comprehensively consider the effects of radiation, geometry and noise correction, ensuring that the advantages of each coefficient are fully utilized during the correction process. This precise correction method improves the processing accuracy of image data and makes the extraction of geological structure information more reliable. By calculating the filter reference coefficient GLC, the system can more effectively integrate various calibration coefficients, thereby improving the overall data processing and analysis performance. The optimized data processing results can reduce errors and improve the quality and efficiency of data analysis. The setting of weight values ​​allows users to adjust the influence of each calibration coefficient according to specific needs, so that the system can support different types of application scenarios and data characteristics. The customized calibration solution improves the flexibility and adaptability of the system. By generating the filter reference coefficient GLC, the system can complete the data correction work in a comprehensive step, thereby reducing the workload of subsequent processing and adjustment. This process improves the simplicity and efficiency of the overall operation.

[0047] Example 5: Please refer to Figure 1 , the data analysis module 5 calculates and generates the actual layer Ip through the following formula;

[0048] Among them, A is the reference function, I and In are filled in respectively, I is the sample layer, In is the correction sample, and GLC is the filtering reference coefficient.

[0049] The data analysis module 5 generates the corrected sample In by calculating the following formula:

[0050] Where I is the sample layer, B is the reference function, and the radiation calibration coefficient S1, geometric calibration coefficient S2 and noise calibration coefficient S3 are filled in respectively.

[0051] The comparison results are as follows; when , it means the layer can be used directly; when , it means the layer cannot be used directly; If the actual layer layer Ip cannot be used directly, set the radiation calibration coefficient S1 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate a new Ip, and re-perform the comparison; If the new actual layer Ip cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip, generate the actual layer Ip again, and re-perform the comparison; If the actual layer Ip generated again cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate the actual layer Ip, and re-execute the comparison. If the result is still not directly usable, repeat the cycle until the layer can be used.

[0052] In this embodiment: the actual layer Ip and the correction sample In are generated by formula calculation, and data adjustment is performed based on the filter reference coefficient GLC, and the system can dynamically adjust and correct the image data. The dynamic correction mechanism ensures that the system can adapt to different correction requirements, further improving the accuracy and applicability of the image data.

[0053] The system uses a step-by-step optimization approach to generate the actual usable layer Ip. If the initially generated layer Ip does not meet the preset requirements, the system will apply the radiation, geometry, and noise calibration coefficients S3 for iterative corrections. This step-by-step optimization process ensures that the final layer meets the usage standards and improves the accuracy and reliability of the processing.

[0054] The system handles layers that do not meet the requirements through an automated correction process without manual intervention. This automated correction mechanism improves the efficiency and accuracy of data processing, reduces human errors, and speeds up the generation of the final layer.

[0055] The correction process of the system can adjust the calibration coefficient according to the actual situation, providing strong adaptability. By adjusting the calibration coefficients corresponding to radiation, geometry and noise, the system can be optimized for different image data characteristics, making the processing results more accurate and reliable.

[0056] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0057] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote sensing image geological structure information extraction system, characterized by: It includes an image acquisition module (1), a feature extraction module (2), a data integration module (3), a data calculation module (4), a data analysis module (5) and a feedback module (6); The image acquisition module (1) is used to capture regional geological images and generate a sample layer I; The feature extraction module (2) is used to extract multi-source data of the sample layer I; The data integration module (3) is used to pre-process the multi-source data extracted by the feature extraction module (2), and to sort the pre-processed multi-source data, thereby generating a first data set, a second data set, and a third data set; The data calculation module (4) integrates and calculates the first data set, the second data set and the third data set respectively, thereby generating a radiation calibration coefficient S1, a geometric calibration coefficient S2 and a noise calibration coefficient S3, and integrates and calculates the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 to generate a filtering reference coefficient GLC; The data analysis module (5) integrates and calculates the sample layer I and the filtering reference coefficient GLC to generate an actual layer Ip, and compares the actual layer Ip with a preset threshold value Y to generate a first comparison result, and determines whether the actual layer Ip meets the usage requirements based on the comparison result; If the comparison result shows that the actual layer Ip does not meet the use requirements, the sample layer I is integrated and calculated with the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively, so as to generate several corrected samples In, and the several corrected samples In are respectively replaced with the sample layer I and the filtering reference coefficient GLC for integrated calculation, so as to generate a new actual layer Ip, and the generated new actual layer Ip is compared with the threshold value Y until the use requirements are met; The feedback module (6) is used to feed back the final corrected actual layer IP to the operation page.

2. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The feature extraction module (2) comprises a first extraction unit (21), a second extraction unit (22) and a third extraction unit (23); The first extraction unit (21) is used to extract radiation parameters in the sample layer I, the second extraction unit (22) is used to extract geometric parameters in the sample layer I, and the third extraction unit (23) is used to extract noise parameters in the sample layer I; Radiation parameters, geometric parameters, and noise parameters are aggregated into multi-source data.

3. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The data integration module (3) comprises a data preprocessing unit (31) and a data sorting unit (32), wherein the data preprocessing unit (31) is used to preprocess the multi-source data extracted by the feature extraction module (2); The data sorting unit (32) is used to perform dimensionless transformation on the pre-processed multi-source data, and to re-organize the dimensionless multi-source data into a first data set, a second data set, and a third data set.

4. A remote sensing image geological structure information extraction system according to claim 3, characterized in that: The first data set includes radiance FSL, spectral characteristics GPT, ground object reflectance DFS, ozone content CYH, whiteboard reflectance BFS and blackboard reflectance HFS; The second data set includes the height value GDZ, the accuracy value JDZ, the spread rate SBL, the shooting angle PSJ, the tilt angle QXJ, and the resolution FBL; The third data set includes the signal-to-noise ratio XZB, the dark current ADL, the spot intensity GBQ, the aerosol thickness QRJ, the water vapor content SJH and the atmospheric transmittance DQT.

5. A remote sensing image geological structure information extraction system according to claim 4, characterized in that: The data calculation module (4) calculates and obtains the radiation calibration coefficient S1, the geometric calibration coefficient S2 and the noise calibration coefficient S3 respectively through the following formulas; Among them, FSL is the radiation brightness, GPT is the spectral characteristics, DFS is the ground reflectance, CYH is the ozone content, BFS is the whiteboard reflectance, HFS is the blackboard reflectance, GDZ is the height value, JDZ is the accuracy value, SBL is the scatter rate, PSJ is the shooting angle, QXJ is the tilt angle, FBL is the resolution, XZB is the signal-to-noise ratio, ADL is the dark current, GBQ is the spot intensity, QRJ is the aerosol thickness, SJH is the water vapor content, and DQT is the atmospheric transmittance.

6. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The data calculation module (4) calculates and obtains the filtering reference coefficient GLC through the following formula; Among them, S1 is the radiation calibration coefficient, S2 is the geometric calibration coefficient, S3 is the noise calibration coefficient, and a1, a2 and a3 are weight values.

7. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The data analysis module (5) calculates and generates the actual layer IP using the following formula; Among them, A is the reference function, I and In are filled in respectively, I is the sample layer, In is the correction sample, and GLC is the filtering reference coefficient.

8. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The data analysis module (5) generates a corrected sample In by calculating the following formula; Among them, I is the sample layer, B is the reference function, and the radiation calibration coefficient S1, geometric calibration coefficient S2 and noise calibration coefficient S3 are filled in respectively.

9. A remote sensing image geological structure information extraction system according to claim 1, characterized in that: The comparison results are as follows: when , it means the layer can be used directly; when , it means the layer cannot be used directly; If the actual layer layer Ip cannot be used directly, set the radiation calibration coefficient S1 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate a new Ip, and re-perform the comparison; If the new actual layer Ip cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip, generate the actual layer Ip again, and re-perform the comparison; If the actual layer Ip generated again cannot be used directly, set the geometric calibration coefficient S2 into the calculation formula of the corrected sample In, and input In into the calculation formula of the actual layer Ip to generate the actual layer Ip, and re-execute the comparison. If the result is still not directly usable, repeat the cycle until the layer can be used.

Images