A geographic information surveying and mapping system based on remote sensing images

Abstract

The application discloses a kind of geographic information surveying and mapping systems based on remote sensing image, it is related to geographic surveying and mapping technical field, including data acquisition module, pre-processing module, information extraction and evaluation module, data output and application module, data acquisition module includes remote sensing image acquisition unit and data storage unit, remote sensing image data include longitude and latitude T, wave band B, image resolution P, radiation value S, cloud cover C and data level L, data applicability CPL, pre-processing module includes radiation calibration unit, atmospheric correction unit, geometric correction unit and image enhancement unit, information extraction and evaluation module includes feature extraction unit, classification processing unit and evaluation unit, with the space coverage range and data applicability of these parameters calculation by high-precision remote sensing image data acquisition, simultaneously utilize feature extraction algorithm and classification processing algorithm, effectively handle the nonlinear relationship in remote sensing image, improve the effect of classification accuracy.

Description

Technical Field

[0001] This invention relates to the field of geographic surveying and mapping technology, specifically to a geographic information surveying and mapping system based on remote sensing imagery. Background Technology

[0002] Remote sensing imagery geospatial mapping is a scientific method that utilizes remote sensing technology to acquire, process, and analyze information on surface and subsurface features. It is not only applied in traditional fields such as topographic mapping, resource exploration, and environmental monitoring, but also plays a vital role in urban planning, disaster management, and military reconnaissance. Remote sensing imagery refers to digital images of the Earth's surface features acquired through remote sensing technology.

[0003] Currently, the data acquisition methods of traditional remote sensing image geographic information mapping systems are relatively outdated. For example, they only collect spectral and textural features. Due to the diversity and complexity of land cover types, it is difficult to accurately describe all the information of the target land cover. In addition, they usually rely on manually designed feature extractors and classifiers to classify remote sensing images, which cannot effectively handle the nonlinear relationships in remote sensing images, resulting in inaccurate classification results and affecting the mapping effect. Summary of the Invention

[0004] The purpose of this invention is to provide a geographic information mapping system based on remote sensing imagery, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a geographic information mapping system based on remote sensing imagery, comprising a data acquisition module, a preprocessing module, an information extraction and evaluation module, and a data output and application module;

[0006] The data acquisition module includes a remote sensing image acquisition unit and a data storage unit;

[0007] The remote sensing image acquisition unit acquires remote sensing image data of the target area through satellites, aircraft, or drones;

[0008] The data storage unit receives and stores remote sensing image data acquired from the remote sensing image acquisition unit. The remote sensing image data includes latitude and longitude T, band B, image resolution P, radiometric value, cloud coverage C, and data level L. The remote sensing image data is combined and analyzed to obtain the spatial coverage range TP, which reflects the geographic area information covered by the remote sensing image, the spectral feature signature BA, which reflects the spectral characteristics of different land features or phenomena in the remote sensing image, and the data applicability CPL, which evaluates the data quality.

[0009] The preprocessing module includes a radiometric calibration unit, an atmospheric correction unit, a geometric correction unit, and an image enhancement unit;

[0010] The information extraction and evaluation module includes a feature extraction unit, a classification processing unit, and an evaluation unit.

[0011] Optionally, the latitude and longitude T includes longitude T1 and latitude T2 in the remote sensing image, band B is the spectral band in the remote sensing image, image resolution P is the ground resolution of the remote sensing image, usually in meters, radiance S is the minimum radiance difference that the sensor can detect, and data level L is the quality of the remote sensing image data.

[0012] Optionally, the spatial coverage area TP is obtained by combining the latitude and longitude T with the image resolution P. The calculation process for the spatial coverage area TP is as follows:

[0013]

[0014] Where T1 is longitude and T2 is latitude;

[0015] E is the angle conversion function, and cos(E(TI)) is the longitude correction function;

[0016] Calculating the spatial coverage area (TP) ensures the comprehensiveness and continuity of data in geospatial space.

[0017] The data suitability CPL is composed of the cloud coverage rate C, the image resolution P, and the data level L. The data suitability CPL algorithm unit is:

[0018] CPL=(C*R1)+(P*R2)+(L*R3)

[0019] Wherein, R1 is the fraction of the cloud coverage rate C;

[0020] R2 is a fraction of the image resolution P, where R2 changes according to the quality of the image resolution P;

[0021] R3 is the score for the data level L, where R3 varies depending on the specific level of the data level L;

[0022] The Data Applicability (CPL) score comprehensively evaluates the cloud coverage rate (C), the image resolution (P), and the data level (L), facilitating staff's understanding of the reliability and applicability of remote sensing data. A higher CPL score indicates stronger reliability and applicability of the remote sensing data, enabling the staff to make reasonable application decisions and avoid using irrelevant or low-quality data.

[0023] Optionally, the feature extraction unit is used to extract features from remote sensing image data, and the feature extraction algorithm unit includes spatial coverage feature F1, band radiation average value feature F2, and data applicability feature F3;

[0024] F1 = TP * W1;

[0025]

[0026] F3 = CPL * W3;

[0027] Where B1 is band one, S1 is radiation value one, and each group of B1 and S1 is combined into B1S1, B1S1 is the radiation value of band one, and n is the number of bands B and radiation values ​​S.

[0028] This represents the average radiation value across the band.

[0029] W1 is the weight of the spatial coverage area TP;

[0030] W2 is the weight of the average radiation value of the band;

[0031] W3 is the weight of the data suitability CPL;

[0032] By performing the aforementioned F1, F2, and F3 feature extractions on remote sensing image data, a comprehensive feature vector F is obtained. This comprehensive feature vector can represent the information of the target ground features and can be used for subsequent classification, detection, and change monitoring tasks.

[0033] Optionally, the classification processing unit classifies the comprehensive feature vector F, and the classification algorithm unit is:

[0034] V=∑(M i *F i )+∑(M Ai *A i )+∑(M ii *(F i ) 2 )+K

[0035] Where V is the classification score, i ranges from 1 to 3, and F... i This represents the i-th eigenvalue in the composite eigenvector F;

[0036] M i For F i The weight of the i-th feature value in the equation;

[0037] A i As an auxiliary feature, M Ai The weights of auxiliary feature A;

[0038] M ii It is a nonlinear term (F) i ) 2 The weights are used to capture the nonlinear effects of features;

[0039] K is a bias term used to adjust the classification boundary;

[0040] Auxiliary feature A i This includes performing mathematical transformations on the original features to improve the distribution of the data or highlight certain specific patterns;

[0041] The classification result is determined based on the classification score V. A threshold is set, and different feature values ​​F are classified according to the threshold.

[0042] Optionally, the radiometric calibration unit in the preprocessing module is used to convert the grayscale values ​​of the remote sensing image into the actual reflectance or emissivity of the land surface, eliminating the error of the sensor itself; the atmospheric correction unit is used to eliminate the influence of the atmosphere on the remote sensing image, including scattering and absorption, so that the image is closer to the real situation of the land surface; the geometric correction unit is used to perform geometric correction on the image to eliminate distortion; and the image enhancement unit is used to perform histogram equalization and filtering on the remote sensing image to improve the visual effect of the image and improve the accuracy of information extraction.

[0043] Optionally, before acquiring remote sensing image data, it is necessary to clarify the specific area, scope, and purpose of the survey, and select a remote sensing image data source according to the survey purpose, including satellite images, aerial photographs, or images collected by UAVs, and prepare GIS software, image processing software, and computer hardware equipment for processing and analyzing remote sensing images.

[0044] Optionally, the data output and application module includes a data visualization unit and a results application unit. The data visualization unit generates various thematic maps, including land use maps and vegetation cover maps, based on the classification results of the comprehensive feature vector F. The results application unit applies the surveying and mapping results to urban planning, environmental monitoring, and disaster early warning, providing support for decision-making.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] This invention utilizes high-precision remote sensing image data acquisition, including latitude and longitude (T), band (B), image resolution (P), radiometric value (S), cloud cover (C), and data level (L). This system acquires high-quality, accurate remote sensing image data and combines these parameters to calculate spatial coverage (TP) and data suitability (CPL), avoiding the use of irrelevant or low-quality data and improving the accuracy and reliability of the analysis results. Simultaneously, by employing feature extraction and classification algorithms, the system can quickly extract useful geographic information from remote sensing image data and perform classification processing, effectively handling nonlinear relationships in remote sensing images and improving classification accuracy. This also enhances the efficiency and automation of geographic information mapping. The aforementioned computing units collectively constitute a complete geographic information mapping system, forming a closed loop from data acquisition to processing, analysis, and application, with close connections and dependencies between them, thus improving the overall performance and accuracy of the mapping system. Attached Figure Description

[0047] Figure 1 This is a system framework diagram of the present invention. Detailed Implementation

[0048] This geographic information mapping system based on remote sensing imagery differs from existing systems. Existing systems rely on a single method for acquiring remote sensing image data, and due to various factors during acquisition, such as cloud cover and sensor performance, the acquired data quality varies significantly, directly impacting the accuracy of subsequent information extraction and classification. This system not only considers the spectral characteristics of remote sensing images but also analyzes data from other remote sensing images to provide a more comprehensive description of target features. It can capture nonlinear relationships and complex patterns in remote sensing images, improving classification accuracy.

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Example 1, please refer to Figure 1 This embodiment provides a geographic information mapping system based on remote sensing imagery, including a data acquisition module, a preprocessing module, an information extraction and evaluation module, and a data output and application module;

[0051] The data acquisition module includes a remote sensing image acquisition unit and a data storage unit;

[0052] The remote sensing image acquisition unit acquires remote sensing image data of the target area through satellites, aircraft, or drones;

[0053] The data storage unit receives and stores remote sensing image data acquired from the remote sensing image acquisition unit. The remote sensing image data includes latitude and longitude T, band B, image resolution P, radiometric value, cloud coverage C, and data level L. The remote sensing image data is combined and analyzed to obtain the spatial coverage range TP, which reflects the geographic area information covered by the remote sensing image, the spectral feature signature BA, which reflects the spectral characteristics of different land features or phenomena in the remote sensing image, and the data applicability CPL, which evaluates the data quality.

[0054] The preprocessing module includes a radiometric calibration unit, an atmospheric correction unit, a geometric correction unit, and an image enhancement unit;

[0055] The information extraction and evaluation module includes a feature extraction unit, a classification processing unit, and an evaluation unit.

[0056] More specifically, in this embodiment: by collecting and calculating the latitude and longitude T, band B, image resolution P, radiance S, cloud cover C, and data level L from the remote sensing impact data, and combining them into spatial coverage TP and data applicability CPL, a comprehensive feature vector F is formed. Compared with single remote sensing image data, it can more comprehensively describe the information of the target ground objects. By setting a preprocessing module to process the collected remote sensing image data, data cleaning can remove invalid, duplicate, and erroneous data, ensuring the accuracy and reliability of the data, thereby improving the effect of subsequent remote sensing image data analysis and improving the quality of remote sensing images. At the same time, the classification processing unit in the information extraction and evaluation module is used to classify the remote sensing image data, effectively handling nonlinear relationships and complex patterns in remote sensing images, and improving the accuracy of classification results.

[0057] Furthermore, latitude and longitude T includes longitude T1 and latitude T2 in the remote sensing image, band B is the spectral band in the remote sensing image, image resolution P is the ground resolution of the remote sensing image, usually in meters, radiometric value S is the minimum radiometric difference that the sensor can detect, and data level L is the data quality of the remote sensing image.

[0058] Data level L can be specifically divided into level 0, level 1 and level 2. Level 0 is the raw remote sensing image data without any correction. Level 1 is the remote sensing image data after preliminary radiometric correction. This level has already performed radiometric correction, converting the raw radiometric data into radiance or radiative reflectance. Level 2 performs geometric correction on the raw data based on parameters such as satellite orbit and attitude, as well as relevant parameters in the ground system. This includes removing the effects of Earth curvature, atmospheric diffusion and satellite attitude factors, so that the remote sensing image has better geometric accuracy.

[0059] Specifically, by collecting different types of remote sensing image data, it is possible to more accurately describe all the information of the target ground objects, so as to facilitate subsequent feature extraction and result classification of remote sensing image data.

[0060] Furthermore, the spatial coverage area TP is obtained by combining latitude and longitude T with image resolution P. The algorithm unit for spatial coverage area TP is:

[0061]

[0062] Where T1 is longitude and T2 is latitude;

[0063] E is the angle conversion function, and cos(E(TI)) is the longitude correction function;

[0064] The angle conversion function E is commonly used to convert angles from one unit to another. The formula for converting degrees to radians is:

[0065] radians are in radians, degrees are in degrees;

[0066] The longitude correction function cos(E(TI)) is commonly used to handle longitude distortion in map projections. The longitude correction formula is:

[0067] cl = ol * (1 - df) + offset

[0068] Where ol is the original longitude, df is a factor representing the degree of deformation, usually between 0 and 1, and offset is the possible offset;

[0069] Calculating the spatial coverage area (TP) ensures the comprehensiveness and continuity of data in geospatial space, facilitating an understanding of the characteristics and differences of different regions, as well as their interactions and connections.

[0070] Data suitability CPL is composed of cloud coverage C, image resolution P, and data level L. The data suitability CPL algorithm unit is:

[0071] CPL=(C*R1)+(P*R2)+(L*R3)

[0072] R1 is the score of cloud coverage C. When calculating, cloud coverage C can be set to greater than 10%, 20%, ... 90%. If cloud coverage C is greater than 10% and less than 20%, then R1 is 10 points, and so on. The higher the cloud coverage C, the worse the image data is, and the lower the R1 score is.

[0073] R2 is the score for image resolution P. R2 changes according to the quality of image resolution P and classifies the resolution, such as 360P, 480P, 720P and 1080P. The higher the image resolution P value, the higher the R2 score, and vice versa.

[0074] R3 is the score for data level L. R3 varies depending on the specific level of data level L. As mentioned above, data level L is divided into level 0, level 1, and level 2. Level 0 is the raw remote sensing image data without any correction. Level 1 is the remote sensing image data after preliminary radiometric correction, which converts the raw radiometric data into radiance or radiance reflectance. Level 2 performs geometric correction on the raw data based on parameters such as satellite orbit and attitude, as well as relevant parameters in the ground system. This includes removing the effects of Earth curvature, atmospheric diffusion, and satellite attitude factors. The higher the data level L, the higher the R3 score, and vice versa.

[0075] Furthermore, spatial coverage (TP) datasets with extensive spatial coverage can provide high-precision geographic location information, making it easier for staff to more accurately identify and locate target areas or objects, improving the accuracy and reliability of remote sensing image data analysis. TP can provide strong support for geospatial decision-making. Fields such as urban planning, environmental assessment, and disaster early warning all need to consider TP in the data to ensure the relevance and effectiveness of decision-making.

[0076] The Data Suitability Probability (CPL) comprehensively evaluates the cloud coverage rate (C), image resolution (P), and data level (L), facilitating staff understanding of the reliability and applicability of remote sensing data. A higher CPL score indicates stronger reliability and applicability of the remote sensing data, enabling more informed application decisions and avoiding the use of irrelevant or low-quality data. This improves the accuracy and reliability of analysis results and increases the efficiency of processing remote sensing image data. By understanding the applicability and limitations of remote sensing image data, staff can develop more reasonable and effective strategies. Furthermore, CPL can identify potential data quality issues, such as data bias, incompleteness, or inconsistency, reducing analytical errors and risks caused by data quality problems.

[0077] Furthermore, the feature extraction unit is used to extract features from the remote sensing image data, and the feature extraction algorithm unit is as follows:

[0078] The feature extraction unit is used to extract features from remote sensing image data. The feature extraction algorithm unit includes spatial coverage feature F1, band radiation average value feature F2, and data applicability feature F3.

[0079] F1 = TP * W1;

[0080]

[0081] F3 = CPL * W3;

[0082] Where B1 is band one, S1 is radiation value one, and each group of B1 and S1 is combined into B1S1, B1S1 is the radiation value of band one, and n is the number of bands B and radiation values ​​S.

[0083] This represents the average radiation value across the band.

[0084] W1 is the weight of the spatial coverage area TP;

[0085] W2 is the weight of the average radiation value of the band;

[0086] W3 is the weight of the data suitability CPL;

[0087] By performing the aforementioned F1, F2, and F3 feature extractions on remote sensing image data, a comprehensive feature vector F is obtained. This comprehensive feature vector can represent the information of the target ground features and can be used for subsequent classification, detection, and change monitoring tasks.

[0088] Specifically, by calculating the comprehensive feature vector F, an efficient data representation method can be provided. By converting remote sensing image data into feature vectors, the processing and analysis of remote sensing image data can be simplified while retaining the key information of the remote sensing image data. The comprehensive feature vector F can represent the information of target ground objects and can be used for subsequent remote sensing image data classification, detection or change monitoring tasks.

[0089] Furthermore, the classification processing unit classifies the comprehensive feature vector F. The classification algorithm unit is as follows:

[0090] V=∑(M i *F i )+Σ(M Ai *A i )+Σ(M ii *(F i ) 2 )+K

[0091] Where V is the classification score, i ranges from 1 to 3, and F... i This represents the i-th eigenvalue in the composite eigenvector F;

[0092] M i For F i The weight of the i-th feature value in the equation;

[0093] A i As an auxiliary feature, M Ai The weights of auxiliary feature A;

[0094] M ii It is a nonlinear term (F) i ) 2 The weights are used to capture the nonlinear effects of features;

[0095] K is a bias term used to adjust the classification boundary;

[0096] Auxiliary feature A i This includes performing mathematical transformations on the original features to improve the distribution of the data or highlight certain specific patterns, such as auxiliary features A. i This includes A1, which is the reflectance in the near-infrared band, and A2, which is the reflectance in the red band. The ratio of A1 to A2 is used to measure the density of vegetation, which is convenient for subsequent classification.

[0097] Specifically, the classification result is determined by the classification score V. Multiple thresholds are set, and different feature values ​​in F are classified according to the thresholds. The specific categories include Category 1 Forest, Category 2 Farmland, Category 3 Residential Area, Category 4 Industrial Area, Category 5 Desert, and Category 6 Lake. The threshold range for Category 1 Forest is greater than 80, for Category 2 Farmland it is 50 to 80, for Category 3 Residential Area it is 20 to 49, for Category 4 Industrial Area it is 10 to 19, for Category 5 Desert it is 1 to 9, and for Category 6 Lake it is less than 1. The F1(TP*W1) feature value is used for classification. For example, if the classification score V is 82, it belongs to Category 1 Forest. Classification helps managers to better understand the surface information, which is convenient for subsequent decision-making.

[0098] This application is merely an example of implementation; the specific classification can be determined based on the actual situation of remote sensing images as understood by those skilled in the art.

[0099] Example 2, based on the above examples:

[0100] Please see Figure 1 The radiometric calibration unit in the preprocessing module is used to convert the grayscale values ​​of remote sensing images into the actual reflectance or emissivity of the Earth's surface, eliminating the errors of the sensor itself. The atmospheric correction unit is used to eliminate the influence of the atmosphere on remote sensing images, including scattering and absorption, making the images closer to the real situation of the Earth's surface. The geometric correction unit is used to perform geometric correction on the images to eliminate distortion. The image enhancement unit is used to perform histogram equalization, filtering and other processing on remote sensing images to improve the visual effect of the images and improve the accuracy of information extraction.

[0101] Specifically, by standardizing remote sensing image data, data from different sources can be converted into a unified standard, reducing the differences between data and making the data easier to compare and analyze. Data cleaning and integration can eliminate duplicate and erroneous data, reducing the workload of subsequent data analysis, thereby saving time and resources and improving the efficiency of remote sensing image data processing.

[0102] Furthermore, before acquiring remote sensing image data, it is necessary to clarify the specific area, scope, and purpose of the survey, and select the remote sensing image data source according to the survey purpose, including satellite images, aerial photographs, or images collected by drones, and prepare GIS software, image processing software, and hardware equipment such as computers for processing and analyzing remote sensing images.

[0103] Specifically, by clearly defining the specific area, scope, and purpose of the survey, such as environmental monitoring, urban planning, disaster assessment, and resource management, different purposes may require different types of remote sensing image data and resolutions. This avoids collecting a large amount of useless data, delaying surveying efficiency, and ensuring the quality of remote sensing image data.

[0104] Furthermore, the data output and application module includes a data visualization unit and a results application unit. The data visualization unit generates various thematic maps, including land use maps and vegetation cover maps, based on the classification results of the comprehensive feature vector F. The results application unit applies the surveying and mapping results to fields such as urban planning, environmental monitoring, and disaster early warning, providing support for decision-making.

[0105] Specifically, the data visualization unit can present large amounts of complex data in an intuitive way through graphics, images, animations, etc., thereby reducing the time and effort required for data processing. This helps users quickly understand the basic characteristics and distribution of the data and conduct better data analysis. The results application unit can transform the results of data visualization into practical applications, providing users with practical operational suggestions or solutions, and applying the results of data analysis to actual work to improve work efficiency and decision-making effectiveness.

[0106] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A geographic information mapping system based on remote sensing imagery, characterized in that, It includes a data acquisition module, a preprocessing module, an information extraction and evaluation module, and a data output and application module; The data acquisition module includes a remote sensing image acquisition unit and a data storage unit; The remote sensing image acquisition unit acquires remote sensing image data of the target area through satellites, aircraft, or drones; The data storage unit receives and stores remote sensing image data acquired from the remote sensing image acquisition unit. The remote sensing image data includes latitude and longitude T, band B, image resolution P, radiometric value S, cloud coverage C, and data level L. The remote sensing image data is combined and analyzed to obtain the spatial coverage range TP, which reflects the geographic area information covered by the remote sensing image, the spectral feature signature BA, which reflects the spectral characteristics of different land features or phenomena in the remote sensing image, and the data applicability CPL, which evaluates the data quality. The preprocessing module includes a radiometric calibration unit, an atmospheric correction unit, a geometric correction unit, and an image enhancement unit; The information extraction and evaluation module includes a feature extraction unit, a classification processing unit, and an evaluation unit; The latitude and longitude T includes longitude T1 and latitude T2 in the remote sensing image, band B is the spectral band in the remote sensing image, image resolution P is the ground resolution of the remote sensing image, usually in meters, radiometric value S is the minimum radiometric difference that the sensor can detect, and data level L is the quality of the remote sensing image data. The spatial coverage area TP is obtained by combining the latitude and longitude T with the image resolution P. The calculation process for the spatial coverage area TP is as follows: ； Where T1 is longitude and T2 is latitude; E is the angle conversion function, and cos(E(TI)) is the longitude correction function; Calculating the spatial coverage area (TP) ensures the comprehensiveness and continuity of data in geospatial space. The data suitability CPL is composed of the cloud coverage rate C, the image resolution P, and the data level L. The calculation process of the data suitability CPL is as follows: ； in, The fraction of the cloud coverage rate C; The fraction of the image resolution P, where It changes according to the quality of the image resolution P; The score for the data level L, where It changes according to the specific level of the data level L; The Data Applicability (CPL) score comprehensively evaluates the cloud coverage rate (C), the image resolution (P), and the data level (L), facilitating staff's understanding of the reliability and applicability of remote sensing data. A higher CPL score indicates stronger reliability and applicability of the remote sensing data, enabling the staff to make reasonable application decisions and avoid using irrelevant or low-quality data.

2. The geographic information mapping system based on remote sensing imagery according to claim 1, characterized in that: The feature extraction unit is used to extract features from remote sensing image data, and the feature extraction algorithm unit includes spatial coverage features. Characteristics of average band radiation Data applicability characteristics ; ； ； ； in, For band one, For a radiation value of one, each group and Corresponding combination , denoted as band B, and n represents the number of bands B and radiance values ​​S. This represents the average radiation value across the band. The weight of the spatial coverage area TP; The weight of the average value of the band radiation; Weights for CPL data suitability; By performing the above-mentioned analysis on remote sensing image data , , Feature extraction yields a comprehensive feature vector F, which represents the information of the target ground features and is used for subsequent classification, detection, and change monitoring tasks.

3. A geographic information mapping system based on remote sensing imagery according to claim 2, characterized in that: The classification processing unit classifies the comprehensive feature vector F, and the classification algorithm unit is as follows: ； Where V is the classification score, and i ranges from 1 to 3. This represents the i-th eigenvalue in the composite eigenvector F; for The weight of the i-th feature value in the equation; As an auxiliary feature, The weights of auxiliary feature A; It is a nonlinear term The weights are used to capture the nonlinear effects of features; K is a bias term used to adjust the classification boundary; auxiliary features This includes performing mathematical transformations on the original features to improve the distribution of the data; The classification result is determined based on the classification score V. A threshold is set, and the comprehensive feature vector F is classified according to the threshold.

4. A geographic information mapping system based on remote sensing imagery according to claim 1, characterized in that: The radiometric calibration unit in the preprocessing module is used to convert the grayscale values ​​of the remote sensing image into the actual reflectance of the ground surface, eliminating the error of the sensor itself. The atmospheric correction unit is used to eliminate the influence of the atmosphere on the remote sensing image, including scattering and absorption, so that the image is closer to the real situation of the ground surface. The geometric correction unit is used to perform geometric correction on the image to eliminate distortion. The image enhancement unit is used to perform histogram equalization and filtering on the remote sensing image to improve the visual effect of the image and improve the accuracy of information extraction.

5. A geographic information mapping system based on remote sensing imagery according to claim 1, characterized in that: Before acquiring remote sensing image data, it is necessary to clarify the specific area, scope and purpose of the survey, and select the remote sensing image data source according to the survey purpose, including satellite images, aerial photographs or images collected by UAVs, and prepare GIS software, image processing software and computer hardware equipment for processing and analyzing remote sensing images.

6. A geographic information mapping system based on remote sensing imagery according to claim 3, characterized in that: The data output and application module includes a data visualization unit and a results application unit. The data visualization unit generates various thematic maps, including land use maps and vegetation cover maps, based on the classification results of the comprehensive feature vector F. The results application unit applies the surveying and mapping results to urban planning, environmental monitoring, and disaster early warning, providing support for decision-making.

Images