Land utilization dynamic change monitoring method and system based on multi-modal remote sensing data

Abstract

The invention discloses a land utilization dynamic change monitoring method and system based on multi-modal remote sensing data, and relates to the technical field of multi-modal remote sensing data analysis. The system comprises a data acquisition and preprocessing module, a consistency baseline construction module, a real-time data analysis module and an abnormality diagnosis and processing module. The data acquisition and preprocessing module realizes space-time alignment of multi-source data; the consistency baseline construction module divides land utilization types based on geographic features and establishes a baseline database; the real-time data analysis module screens suspected abnormal areas through difference indexes; the abnormity diagnosis and processing module distinguishes data quality abnormity and emergency abnormity based on the characteristic association relation, the data quality abnormity triggers data restoration and verification, and the emergency abnormity marks a high-priority area and outputs position information. According to the system, through multi-modal data fusion and correlation analysis, high-precision monitoring and abnormal intelligent classification of land utilization changes are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal remote sensing data analysis, and specifically to a method and system for monitoring the dynamic changes of land use based on multimodal remote sensing data. Background Technique

[0002] The monitoring of dynamic changes in land use is an important research direction in the application field of remote sensing technology, and is widely used in multiple fields such as urban planning, resource management, and environmental protection. With the development of remote sensing technology, more and more sensors and satellite platforms are used to obtain multimodal remote sensing data, including optical remote sensing data, radar remote sensing data (such as synthetic aperture radar SAR), thermal infrared remote sensing data, etc. These multimodal remote sensing data provide different perspectives and information sources, and can effectively monitor land use changes, especially in the aspects of large-scale, high timeliness, and continuity monitoring, with significant advantages.

[0003] However, in practical applications, remote sensing data is often affected by various factors, such as cloudy and foggy weather, sensor failures, data transmission errors, etc., resulting in fluctuations in data quality and affecting the accuracy of monitoring dynamic changes in land use. In addition, during the process of land use changes, some abnormal events may also occur, such as forest fires, sudden changes during the urbanization process, etc. These changes may be different from normal seasonal changes or fluctuations in ground attributes, and may have a profound impact on the environment. Therefore, how to accurately identify and classify data anomalies, and how to use the physical relationships and consistencies between multimodal remote sensing data to detect and correct these anomalies have become a key issue in remote sensing data processing. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for monitoring the dynamic changes of land use based on multimodal remote sensing data to solve the problems raised in the above background technique.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] A method for monitoring the dynamic changes of land use based on multimodal remote sensing data includes the following steps:

[0007] Step S100. Obtain the multimodal remote sensing historical data within the monitoring period, as well as the geographical information data of the monitoring area, and divide the monitoring area into different land use types according to the geographical information data; and based on the division results of the monitoring area, correspond the corresponding multimodal remote sensing historical data, and establish a consistency baseline database for different land use types in a stable state.

[0008] Step S200. Obtain the multi-modal remote sensing real-time data of different land use types within the monitoring area, compare the multi-modal remote sensing real-time data with the corresponding consistency baseline database to obtain the corresponding difference index; based on the difference index, initially screen out the areas with a deviation degree from the consistency baseline database greater than the threshold and mark them as suspected abnormal areas;

[0009] Step S300. For the suspected abnormal areas, analyze the correlation relationship of the corresponding multi-modal remote sensing real-time data, and identify the abnormal diagnosis results of the suspected abnormal areas according to the correlation relationship; among them, the abnormal diagnosis results are divided into data quality anomalies and emergency anomalies;

[0010] Step S400. Mark the areas identified as data quality anomalies as unreliable data areas, repair the corresponding multi-modal remote sensing real-time data, compare the repaired multi-modal remote sensing real-time data with the corresponding consistency baseline database, and output the corresponding prompt information according to the comparison result; mark the areas identified as emergency anomalies as high-priority change areas, obtain the location information of the high-priority change areas and output it to the relevant personnel for corresponding processing.

[0011] Further, step S100 includes:

[0012] S101. Obtain the multi-modal historical remote sensing data during the monitoring period, including optical remote sensing, synthetic aperture radar data, and infrared data, etc.; and the geographical information data of the monitoring area, including land use status data, vegetation coverage, soil type, terrain elevation, etc., preprocess the multi-modal historical remote sensing data, including radiometric calibration, geometric correction, and atmospheric correction; perform format unification and spatial registration on the geographical information data to make the geographical information data and the multi-modal historical remote sensing data consistent in the spatial and temporal dimensions;

[0013] S102. Divide the monitoring area into several sub-areas according to the preset minimum area unit; for each sub-area, obtain the geographical information data of the corresponding sub-area, extract the corresponding geographical data features from the geographical information data, and the geographical data features include terrain features, soil features, vegetation features, and hydrological features, etc.; perform normalization processing on the extracted geographical data features to form the corresponding geographical data feature vector V, and V = [v1, v2,..., vn], where v1 represents the geographical data feature of the first dimension, v2 represents the geographical data feature of the second dimension, and so on, vn represents the geographical data feature of the nth dimension; summarize the geographical data feature vectors V of all sub-areas and calculate the average value to obtain the corresponding geographical data feature average vector V0; identify the land use type of each sub-area according to the geographical data feature vector V;

[0014] S103. Based on the classified land use types, correspond the corresponding multi-modal historical remote sensing data to each sub-region; for all sub-regions of the same land use type, obtain the corresponding multi-modal historical remote sensing data and the stable state marking period, where the stable state marking period is obtained by the analysis of relevant personnel; based on the stable state marking period, intercept the multi-modal historical remote sensing data of all sub-regions of the same land use type, perform time series analysis on the intercepted multi-modal remote sensing historical data, so as to obtain the multi-modal remote sensing historical data characteristics of each sub-region within the stable state marking period, and use the principal component analysis method to reduce the dimension of the multi-modal remote sensing historical data characteristics, so as to obtain the main feature vector Z; calculate the feature mean and standard deviation of the main feature vector Z of each land use type, so as to construct a consistency baseline database. Among them, the database includes the key features of each land use type in the stable state, such as vegetation index, soil moisture, surface temperature, etc., and its stable patterns at different time periods. The stable state data of each sub-region will be integrated to form a high-dimensional feature space, ensuring that the database can comprehensively reflect the stable state characteristics of various land use types.

[0015] Further, in S102, according to the geographical data feature vector V, identify the land use type of each sub-region, and the specific analysis process is as follows:

[0016] For each sub-region, represent the corresponding geographical data feature vector V and the geographical data feature average vector V0 in the same radar chart, and the number of number axes corresponding to the radar chart is n; on each number axis in the radar chart, mark the elements where the geographical data feature vector V is greater than the geographical data feature average vector V0 as key features, and summarize the key features to form the key feature set G of the corresponding sub-region; obtain the key feature set Gi corresponding to each land use type in the database, where i represents the number of land use types; compare the key feature set G of each sub-region with the key feature set Gi corresponding to each land use type in turn, calculate the corresponding matching coefficient Pi, and Pi = N(G∩Gi) / N(Gi), where N(G∩Gi) represents the number of key features in the intersection of the key feature set G and the key feature set Gi, and N(Gi) represents the number of key features corresponding to the i-th land use type; summarize the matching coefficients Pi corresponding to all land use types, and select the land use type with the largest matching coefficient as the land use type of the corresponding sub-region.

[0017] Further, step S200 includes:

[0018] S201. Obtain the multi-modal remote sensing real-time data of sub-regions with different land use types in the monitoring area, analyze the multi-modal remote sensing real-time data in the same way as the analysis of multi-modal historical data, so as to obtain the real-time data feature vector S with the same dimension as the consistency baseline database; according to the land use type of the corresponding sub-region, obtain the corresponding consistency baseline database, calculate the feature mean and standard deviation of the real-time data feature vector S of the current sub-region and the main feature vector Z corresponding to the consistency baseline database, so as to obtain the corresponding difference index R, and ,

[0019] where S k represents the k-th eigenvalue of the real-time data feature vector, μ_Z k represents the mean of the k-th eigenvalue of the main feature vector Z in the consistency baseline database, σ_Z k represents the standard deviation of the k-th eigenvalue of the main feature vector Z in the consistency baseline database;

[0020] S202. Compare the difference index R of sub-regions with different land use types in the monitoring area with the preset threshold R0. If there is a sub-region where the difference index R is greater than the preset threshold R0, mark the corresponding sub-region as a suspected abnormal area.

[0021] Further, step S300 includes:

[0022] S301. For the suspected abnormal area, obtain the real-time data feature vector S of the corresponding multi-modal remote sensing real-time data, analyze the correlation relationship between different elements in the real-time data feature vector S of the multi-modal remote sensing real-time data, so as to form a correlation relationship matrix A m×m , and each element aij in the correlation relationship matrix A m×m represents the correlation between the i-th feature and the j-th feature, and the Pearson correlation coefficient is used to calculate the linear correlation between feature elements; obtain the consistency baseline database of the land use type corresponding to the suspected abnormal area, and analyze the correlation relationship between different elements in the main feature vector Z in the consistency baseline database in the same way as the analysis of the real-time data feature vector S, so as to obtain a baseline correlation relationship matrix B m×m ;

[0023] S302. Calculate the correlation relationship matrix A m×m of the suspected abnormal area and the corresponding baseline correlation relationship matrix B m×mThe difference between them, extract the elements whose values are not 0 and are greater than or equal to the preset threshold, and obtain the corresponding number N of real-time data features according to the elements; if 0 < N < N1 is satisfied, output an abnormal diagnosis result of abnormal data quality; if N ≥ N1, output an abnormal diagnosis result of abnormal emergency; where N1 represents the threshold of the number of characteristic elements whose correlation does not meet the consistency baseline database, and the value is less than m, which is obtained by relevant personnel through specific situation analysis.

[0024] Among them, if only a few features do not meet the requirements of the consistency baseline database in terms of correlation with other features, and the differences of these features are within the set tolerance range, it is classified as abnormal data quality; if the correlations among multiple features do not meet the requirements of the consistency baseline database, and the differences of these features are large, it is classified as abnormal emergency.

[0025] Further, step S400 includes:

[0026] S401. Mark the area identified as abnormal data quality as an unreliable data area, combine the multi-modal remote sensing historical data of the same area to repair the multi-modal remote sensing real-time data of the unreliable data area, and calculate the real-time difference index Rs according to the calculation formula of the difference index R for the repaired multi-modal remote sensing real-time data; if the real-time difference index Rs is less than or equal to the threshold R0, output a prompt message of "data repair successful"; if the real-time difference index Rs is greater than the threshold R0, output a prompt message of "abnormality still exists after data repair, please check further", and relevant personnel will perform corresponding processing;

[0027] S402. Mark the area identified as abnormal emergency as a high-priority change area, obtain the location information of the high-priority change area and output it to relevant personnel for corresponding processing.

[0028] A land use dynamic change monitoring system based on multi-modal remote sensing data, including: a data acquisition and preprocessing module, a consistency baseline construction module, a real-time data analysis module, and an abnormal diagnosis and processing module;

[0029] The data acquisition and preprocessing module acquires multi-modal remote sensing historical data during the monitoring period, as well as geographic information data of the monitoring area; preprocesses the multi-modal historical remote sensing data, and unifies the format and performs spatial registration on the geographic information data, so that the geographic information data and the multi-modal historical remote sensing data are consistent in spatial and temporal dimensions;

[0030] The consistency baseline construction module divides the monitoring area into multiple sub-areas, and identifies the land use types according to the geographic data characteristics of each sub-area; analyzes the stable state data of each land use type and establishes a consistency baseline database;

[0031] The real-time data analysis module obtains multi-modal remote sensing real-time data of different land use types within the monitoring area and compares it with the consistency baseline database; calculates the difference index between the characteristics of the real-time data and the characteristics of the baseline database, thereby preliminarily screening out and marking suspected abnormal areas;

[0032] The anomaly diagnosis and processing module analyzes the suspected abnormal areas to identify data quality anomalies or emergency anomalies; identifies the anomaly types by analyzing the characteristic correlation relationships of the multi-modal remote sensing real-time data; if it is diagnosed as a data quality anomaly, repairs the unreliable data and re-compares the repaired data; if it is diagnosed as an emergency anomaly, marks it as a high-priority change area and promptly provides the relevant location information to relevant personnel for processing.

[0033] Furthermore, the data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0034] The data acquisition unit obtains multi-modal remote sensing historical data within the monitoring period and geographical information data of the monitoring area; the data preprocessing unit preprocesses the multi-modal historical remote sensing data, unifies the format of the geographical information data and performs spatial registration, so that the geographical information data and the multi-modal historical remote sensing data are consistent in spatial and temporal dimensions.

[0035] Furthermore, the consistency baseline construction module includes a land use type analysis unit and a consistency baseline construction unit;

[0036] The land use type analysis unit divides the monitoring area into multiple sub-areas and identifies the land use type according to the geographical data characteristics of each sub-area; the consistency baseline construction unit analyzes the stable state data of each land use type and establishes a consistency baseline database.

[0037] Furthermore, the real-time data analysis module includes a consistency baseline database comparison unit and a suspected abnormal area identification unit;

[0038] The consistency baseline database comparison unit obtains multi-modal remote sensing real-time data of different land use types within the monitoring area and compares it with the consistency baseline database; the suspected abnormal area identification unit calculates the difference index between the characteristics of the real-time data and the characteristics of the baseline database, thereby preliminarily screening out and marking suspected abnormal areas;

[0039] The anomaly diagnosis and processing module includes an anomaly diagnosis unit and a prompt information output unit;

[0040] The anomaly diagnosis unit analyzes the suspected anomaly areas to identify data quality anomalies or emergency anomalies; by analyzing the feature correlation relationships of multi-modal remote sensing real-time data, it identifies the types of anomalies; if the prompt information output unit diagnoses a data quality anomaly, it repairs the unreliable data and re-compares the repaired data; if it diagnoses an emergency anomaly, it marks it as a high-priority change area and promptly provides the relevant location information to relevant personnel for handling.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining geographic information data and remote sensing data, the present invention accurately divides the monitoring area into different land use types and establishes a consistency baseline database based on the marked time periods of the stable states; this division method makes the monitoring more accurate and enables detailed analysis for different types of land use, ensuring that the monitoring results are more targeted. By establishing a consistency baseline database and comparing the differences in the characteristics of multi-modal remote sensing real-time data and historical data, the present invention can efficiently screen out anomaly areas and accurately diagnose the types of anomalies; this analysis method based on the difference index and the correlation relationship matrix can timely detect anomaly events such as forest fires and sudden changes during the urbanization process during the monitoring process, with high real-time performance and accuracy. For data quality anomaly areas, the present invention provides a data repair mechanism, repairs the unreliable data by comparing multi-modal historical data, and evaluates it through the difference index; the repaired data can be secondarily verified to ensure the reliability and accuracy of the data; compared with the prior art, the present invention can effectively avoid manual intervention when dealing with data anomalies, improving the automation level and data processing efficiency. For emergency anomalies, the present invention can prioritize the identification of relevant areas and promptly feedback the location information to relevant personnel for handling, ensuring a rapid response to emergencies; this feature is of great significance in practical applications in the fields of environmental protection, disaster monitoring, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0043] Figure 1 It is a schematic diagram of the modules of the land use dynamic change monitoring system based on multi-modal remote sensing data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0045] Please refer to Figure 1 , the present invention provides a technical solution:

[0046] A land use dynamic change monitoring system based on multi-modal remote sensing data, comprising: a data acquisition and preprocessing module, a consistency baseline construction module, a real-time data analysis module, and an anomaly diagnosis and processing module;

[0047] The data acquisition and preprocessing module acquires multi-modal remote sensing historical data within the monitoring period and geographic information data of the monitoring area; preprocesses the multi-modal historical remote sensing data, and unifies the format and spatially registers the geographic information data, so that the geographic information data and the multi-modal historical remote sensing data are consistent in spatial and temporal dimensions;

[0048] The consistency baseline construction module divides the monitoring area into multiple sub-areas, and identifies the land use types according to the geographic data characteristics of each sub-area; analyzes the stable state data of each land use type and establishes a consistency baseline database;

[0049] The real-time data analysis module acquires multi-modal remote sensing real-time data of different land use types within the monitoring area and compares it with the consistency baseline database; calculates the difference index between the real-time data characteristics and the baseline database characteristics, so as to preliminarily screen out and mark the suspected abnormal areas;

[0050] The anomaly diagnosis and processing module analyzes the suspected abnormal areas to identify data quality anomalies or emergency anomalies; identifies the anomaly types by analyzing the characteristic correlation relationship of the multi-modal remote sensing real-time data; if it is diagnosed as a data quality anomaly, repairs the unreliable data and re-compares the repaired data; if it is diagnosed as an emergency anomaly, marks it as a high-priority change area and timely provides the relevant location information to relevant personnel for processing.

[0051] The data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0052] The data acquisition unit acquires multi-modal remote sensing historical data within the monitoring period and geographic information data of the monitoring area; the data preprocessing unit preprocesses the multi-modal historical remote sensing data, and unifies the format and spatially registers the geographic information data, so that the geographic information data and the multi-modal historical remote sensing data are consistent in spatial and temporal dimensions.

[0053] The consistency baseline construction module includes a land use type analysis unit and a consistency baseline construction unit;

[0054] The land use type analysis unit divides the monitoring area into multiple sub-areas and identifies the land use type according to the geographical data characteristics of each sub-area; the consistency baseline construction unit analyzes the steady-state data of each land use type and establishes a consistency baseline database.

[0055] The real-time data analysis module includes a consistency baseline database comparison unit and a suspected abnormal area identification unit;

[0056] The consistency baseline database comparison unit obtains the multi-modal remote sensing real-time data of different land use types in the monitoring area and compares it with the consistency baseline database; the suspected abnormal area identification unit calculates the difference index between the real-time data characteristics and the baseline database characteristics, so as to initially screen out and mark the suspected abnormal areas;

[0057] The abnormal diagnosis and processing module includes an abnormal diagnosis unit and a prompt information output unit;

[0058] The abnormal diagnosis unit analyzes the suspected abnormal areas to identify data quality abnormalities or emergency abnormalities; by analyzing the characteristic correlation relationship of the multi-modal remote sensing real-time data, the abnormal type is identified; if the prompt information output unit diagnoses that it is a data quality abnormality, the unreliable data is repaired, and the repaired data is re-compared; if it is diagnosed as an emergency abnormality, it is marked as a high-priority change area, and the relevant location information is provided to relevant personnel in a timely manner for processing.

[0059] A method for monitoring land use dynamic changes based on multi-modal remote sensing data includes the following steps:

[0060] Step S100. Obtain the multi-modal remote sensing historical data during the monitoring period and the geographical information data of the monitoring area, divide the monitoring area into different land use types according to the geographical information data; and based on the division result of the monitoring area, correspond the corresponding multi-modal remote sensing historical data, and establish a consistency baseline database for different land use types in a steady state;

[0061] Step S200. Obtain the multi-modal remote sensing real-time data of different land use types in the monitoring area, compare the multi-modal remote sensing real-time data with the corresponding consistency baseline database, so as to obtain the corresponding difference index; based on the difference index, initially screen out the areas whose deviation from the consistency baseline database is greater than the threshold and mark them as suspected abnormal areas;

[0062] Step S300. Analyze the correlation relationship of the corresponding multimodal remote sensing real-time data for the suspected abnormal area, and identify the abnormal diagnosis results of the suspected abnormal area according to the correlation relationship; wherein the abnormal diagnosis results are divided into data quality abnormalities and emergency abnormalities;

[0063] Step S400. Mark the area identified as having abnormal data quality as an unreliable data area, repair the corresponding multimodal remote sensing real-time data, and compare the repaired multimodal remote sensing real-time data with the corresponding consistency baseline database, and output corresponding prompt information based on the comparison result; mark the area identified as having abnormal emergency events as a high-priority change area, obtain the location information of the high-priority change area and output it to relevant personnel, who will perform corresponding processing.

[0064] Step S100 includes:

[0065] S101. Acquire multimodal historical remote sensing data within the monitoring period, including optical remote sensing, synthetic aperture radar data, and infrared data, etc.; and geographic information data of the monitoring area, including land use status data, vegetation coverage, soil type, terrain elevation, etc., pre-process the multimodal historical remote sensing data, including radiation calibration, geometric correction, and atmospheric correction; unify the format and spatially register the geographic information data, so that the geographic information data and the multimodal historical remote sensing data are consistent in spatial and temporal dimensions;

[0066] S102. Divide the monitoring area into several sub-areas according to the preset minimum area unit; for each sub-area, obtain the geographic information data of the corresponding sub-area, and extract the corresponding geographic data features from the geographic information data, wherein the geographic data features include terrain features, soil features, vegetation features, and hydrological features, etc.; normalize the extracted geographic data features to form a corresponding geographic data feature vector V, and V=[v1,v2,...,vn], wherein v1 represents the geographic data features of the first dimension, v2 represents the geographic data features of the second dimension, and so on, vn represents the geographic data features of the nth dimension; summarize the geographic data feature vectors V of all sub-areas and calculate the average value, thereby obtaining the corresponding geographic data feature average vector V0; identify the land use type of each sub-area according to the geographic data feature vector V;

[0067] S103. Based on the well - defined land use types, correspond the corresponding multi - modal historical remote sensing data to each sub - region; for all sub - regions of the same land use type, obtain the corresponding multi - modal historical remote sensing data and the stable state marking period, where the stable state marking period is obtained by the analysis of relevant personnel; based on the stable state marking period, intercept the multi - modal historical remote sensing data of all sub - regions of the same land use type, conduct time - series analysis on the intercepted multi - modal remote sensing historical data, so as to obtain the multi - modal remote sensing historical data characteristics of each sub - region within the stable state marking period, and use the principal component analysis method to reduce the dimension of the multi - modal remote sensing historical data characteristics, thereby obtaining the main feature vector Z; calculate the characteristic mean and standard deviation of the main feature vector Z of each land use type, thereby constructing a consistency baseline database. Among them, the database includes the key features of each land use type in the stable state, such as vegetation index, soil moisture, surface temperature, etc., and its stable patterns in different time periods. The stable state data of each sub - region will be integrated to form a high - dimensional feature space, ensuring that the database can comprehensively reflect the stable state characteristics of various land use types.

[0068] In S102, according to the geographical data feature vector V, identify the land use type of each sub - region, and the specific analysis process is as follows:

[0069] For each sub - region, represent the corresponding geographical data feature vector V and the geographical data feature average vector V0 in the same radar chart, and the number of number axes corresponding to the radar chart is n; on each number axis in the radar chart, mark the elements of the geographical data feature vector V that are greater than the geographical data feature average vector V0 as key features, and summarize the key features to form the key feature set G of the corresponding sub - region; obtain the key feature set Gi corresponding to each land use type in the database, where i represents the number of land use types; compare the key feature set G of each sub - region with the key feature set Gi corresponding to each land use type in turn, calculate the corresponding matching coefficient Pi, and Pi = N(G∩Gi) / N(Gi), where N(G∩Gi) represents the number of key features in the intersection of the key feature set G and the key feature set Gi, and N(Gi) represents the number of key features corresponding to the i - th land use type; summarize the matching coefficients Pi corresponding to all land use types, and select the land use type with the largest matching coefficient as the land use type of the corresponding sub - region.

[0070] In this embodiment, assume that the key feature set G of a certain sub - region is: G = {slope, vegetation coverage}; obtain the key feature sets corresponding to each land use type from the database, assume there are: G1, G2 and G3, and are expressed as: G1 = {slope, soil moisture, vegetation coverage}; G2 = {slope, soil moisture, water content}; G3 = {vegetation coverage, water content};

[0071] Calculate the corresponding matching coefficients Pi, which are in turn:

[0072] P1 = N(G ∩ G1) / N(G1) = 2 / 3; P2 = N(G ∩ G2) / N(G2) = 1 / 3; P3 = N(G ∩ G3) / N(G3) = 1 / 2;

[0073] Since P1 > P3 > P2, the land use type corresponding to this sub-region is the land use type corresponding to G1.

[0074] Step S200 includes:

[0075] S201. Obtain the multi-modal remote sensing real-time data of the sub-regions with different land use types in the monitoring area, analyze the multi-modal remote sensing real-time data in the same way as the analysis of multi-modal historical data, so as to obtain the real-time data feature vector S with the same dimension as the consistency baseline database; according to the land use type of the corresponding sub-region, obtain the corresponding consistency baseline database, and calculate the feature mean and standard deviation of the real-time data feature vector S of the current sub-region and the main feature vector Z corresponding to the consistency baseline database, so as to obtain the corresponding difference index R, and ,

[0076] where S k represents the k-th eigenvalue of the real-time data feature vector, and μ_Z k represents the mean of the k-th eigenvalue of the main feature vector Z in the consistency baseline database, and σ_Z k represents the standard deviation of the k-th eigenvalue of the main feature vector Z in the consistency baseline database;

[0077] S202. Compare the difference index R of the sub-regions with different land use types in the monitoring area with a preset threshold R0. If there is a sub-region where the difference index R is greater than the preset threshold R0, mark the corresponding sub-region as a suspected abnormal area.

[0078] Step S300 includes:

[0079] S301. For the suspected abnormal area, obtain the real-time data feature vector S of the corresponding multi-modal remote sensing real-time data, analyze the correlation relationship between different elements in the real-time data feature vector S of the multi-modal remote sensing real-time data, so as to form a correlation relationship matrix A m×m , and the correlation relationship matrix A m×mEach element aij in it represents the correlation between the i-th feature and the j-th feature, and the Pearson correlation coefficient is used to calculate the linear correlation between feature elements; obtain the consistency baseline database of the land use type corresponding to the suspected abnormal area, and analyze the association relationship between different elements in the main feature vector Z in the consistency baseline database according to the analysis method of the real-time data feature vector S, so as to obtain the baseline association relationship matrix B m×m ;

[0080] S302. Calculate the association relationship matrix A of the suspected abnormal area m×m and the corresponding baseline association relationship matrix B m×m Calculate the difference between them, extract the elements whose values are not 0 and greater than or equal to the preset threshold, and obtain the corresponding real-time data feature quantity N according to the elements; if 0 < N < N1 is satisfied, output the abnormal diagnosis result of data quality abnormality; if N ≥ N1, output the abnormal diagnosis result of emergency abnormality; where N1 represents the threshold of the number of feature elements whose correlation does not meet the consistency baseline database, and the value is less than m, which is obtained by relevant personnel through specific situation analysis

[0081] Among them, if only a few features do not meet the requirements of the consistency baseline database in terms of the correlation with other features, and the differences of these features are within the set tolerance range, it is classified as data quality abnormality; if the correlations between multiple features do not meet the requirements of the consistency baseline database, and the differences of these features are large, it is classified as emergency abnormality

[0082] Step S400 includes:

[0083] S401. Mark the area identified as data quality abnormality as an unreliable data area, combine the multi-modal remote sensing historical data of the same area to repair the multi-modal remote sensing real-time data of the unreliable data area, and calculate the real-time difference index Rs according to the calculation formula of the difference index R for the repaired multi-modal remote sensing real-time data; if the real-time difference index Rs is less than or equal to the threshold R0, output the prompt information of "data repair successful"; if the real-time difference index Rs is greater than the threshold R0, output the prompt information of "abnormality still exists after data repair, please check further", and relevant personnel will perform corresponding processing

[0084] S402. Mark the area identified as emergency abnormality as a high-priority change area, obtain the location information of the high-priority change area and output it to relevant personnel for corresponding processing

[0085] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0086] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent substitution on some of the technical features. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for monitoring the dynamic changes of land use based on multi-modal remote sensing data, characterized in that: The method includes the following steps: Step S100. Obtain multi-modal remote sensing historical data within a monitoring period and geographic information data of the monitoring area. Divide the monitoring area into different land use types according to the geographic information data; and based on the division result of the monitoring area, correspond the corresponding multi-modal remote sensing historical data, and establish a consistency baseline database for different land use types in a stable state; Step S200. Obtain multi-modal remote sensing real-time data of different land use types within the monitoring area, compare the multi-modal remote sensing real-time data with the corresponding consistency baseline database to obtain corresponding difference indexes; based on the difference indexes, preliminarily screen out areas with a deviation degree greater than the threshold from the consistency baseline database and mark them as suspected abnormal areas; Step S300. For the suspected abnormal areas, analyze the correlation relationship of the corresponding multi-modal remote sensing real-time data, and identify the abnormal diagnosis results of the suspected abnormal areas according to the correlation relationship; where the abnormal diagnosis results are divided into data quality anomalies and emergency anomalies; Step S400. Mark the areas identified as data quality anomalies as unreliable data areas, repair the corresponding multi-modal remote sensing real-time data, compare the repaired multi-modal remote sensing real-time data with the corresponding consistency baseline database, and output corresponding prompt information according to the comparison result; mark the areas identified as emergency anomalies as high-priority change areas, obtain the location information of the high-priority change areas and output it to relevant personnel for corresponding processing by the relevant personnel.

2. The method for monitoring dynamic changes in land use based on multi-modal remote sensing data according to claim 1, wherein: The said step S100 includes: S101. Obtain multi-modal historical remote sensing data within a monitoring period and geographic information data of the monitoring area, and preprocess the multi-modal historical remote sensing data, including radiometric calibration, geometric correction, and atmospheric correction; unify the format and perform spatial registration on the geographic information data, so that the geographic information data and the multi-modal historical remote sensing data are consistent in spatial and temporal dimensions; S102. Divide the monitoring area into several sub-areas according to a preset minimum regional unit; for each sub-area, obtain the geographic information data of the corresponding sub-area, extract the corresponding geographic data features from the geographic information data; perform normalization processing on the extracted geographic data features to form the corresponding geographic data feature vector V, and V = [v1, v2,..., vn], where v1 represents the geographic data feature of the first dimension, v2 represents the geographic data feature of the second dimension, and so on, vn represents the geographic data feature of the nth dimension; summarize the geographic data feature vectors V of all sub-areas and calculate the average value to obtain the corresponding geographic data feature average vector V0; identify the land use type of each sub-area according to the geographic data feature vector V; S103. Based on the well - divided land use types, correspond the corresponding multi - modal historical remote sensing data to each sub - region; for all sub - regions of the same land use type, obtain the corresponding multi - modal historical remote sensing data and the stable - state marking time period, where the stable - state marking time period is obtained by the analysis of relevant personnel; based on the stable - state marking time period, intercept the multi - modal historical remote sensing data of all sub - regions of the same land use type, perform time - series analysis on the intercepted multi - modal remote sensing historical data, so as to obtain the multi - modal remote sensing historical data characteristics of each sub - region within the stable - state marking time period, and use the principal component analysis method to reduce the dimension of the multi - modal remote sensing historical data characteristics, so as to obtain the main feature vector Z; calculate the feature mean and standard deviation of the main feature vector Z of each land use type, so as to construct a consistency baseline database.

3. The method for monitoring land use dynamic changes based on multi-modal remote sensing data according to claim 2, wherein: In S102, according to the geographical data feature vector V, identify the land use type of each sub - region. The specific analysis process is as follows: For each sub - region, represent the corresponding geographical data feature vector V and the geographical data feature average vector V0 in the same radar chart, and the number of number axes corresponding to the radar chart is n; on each number axis in the radar chart, mark the elements where the geographical data feature vector V is greater than the geographical data feature average vector V0 as key features, and summarize the key features to form the key feature set G of the corresponding sub - region; obtain the key feature set Gi corresponding to each land use type in the database, where i represents the number of land use types; compare the key feature set G of each sub - region with the key feature set Gi corresponding to each land use type in turn, calculate the corresponding matching coefficient Pi, and Pi = N(G∩Gi) / N(Gi), where N(G∩Gi) represents the number of key features in the intersection of the key feature set G and the key feature set Gi, and N(Gi) represents the number of key features corresponding to the i - th land use type; summarize the matching coefficients Pi corresponding to all land use types, and select the land use type with the largest matching coefficient as the land use type of the corresponding sub - region.

4. The method for monitoring the dynamic changes of land use based on multi-modal remote sensing data according to claim 3, wherein: The step S200 includes: S201. Obtain the multi-modal remote sensing real-time data of sub-regions with different land use types within the monitoring area, analyze the multi-modal remote sensing real-time data in the same way as the analysis of multi-modal historical data, so as to obtain the real-time data feature vector S with the same dimension as the consistency baseline database; according to the land use type of the corresponding sub-region, obtain the corresponding consistency baseline database, calculate the feature mean and standard deviation of the real-time data feature vector S of the current sub-region and the main feature vector Z corresponding to the consistency baseline database, so as to obtain the corresponding difference index R, and , where S k represents the k-th eigenvalue of the real-time data feature vector, and μ_Z k represents the mean of the k-th eigenvalue of the main feature vector Z in the consistency baseline database, and σ_Z k represents the standard deviation of the k-th eigenvalue of the main feature vector Z in the consistency baseline database; S202. Compare the difference index R of the sub - regions of different land use types in the monitoring area with a preset threshold R0. If there is a sub - region where the difference index R is greater than the preset threshold R0, mark the corresponding sub - region as a suspected abnormal area.

5. The method for monitoring the dynamic change of land use based on multi-modal remote sensing data according to claim 4, wherein: The step S300 includes: S301. For the suspected abnormal area, obtain the real-time data feature vector S of the corresponding multi-modal remote sensing real-time data, analyze the correlation relationship between different elements in the real-time data feature vector S of the multi-modal remote sensing real-time data, so as to construct the correlation relationship matrix Am×m, and each element aij in the correlation relationship matrix Am×m represents the correlation between the i-th feature and the j-th feature, and the Pearson correlation coefficient is used to calculate the linear correlation between feature elements; obtain the consistency baseline database of the land use type corresponding to the suspected abnormal area, and analyze the correlation relationship between different elements in the main feature vector Z in the consistency baseline database in the same way as the analysis of the real-time data feature vector S, so as to obtain the baseline correlation relationship matrix Bm×m; S302. Calculate the difference between the correlation relationship matrix Am×m of the suspected abnormal area and the corresponding baseline correlation relationship matrix Bm×m, extract the elements with non-zero values greater than or equal to the preset threshold, and obtain the corresponding real-time data feature quantity N according to the elements; if 0 < N < N1, output the abnormal diagnosis result of data quality abnormality; if N ≥ N1, output the abnormal diagnosis result of sudden event abnormality; where N1 represents the threshold of the number of feature elements whose correlation does not meet the consistency baseline database, and the value is less than m.

6. The method for monitoring land use dynamic changes based on multi-modal remote sensing data according to claim 5, wherein: The step S400 includes: S401. Mark the area identified as data quality abnormal as an unreliable data area, combine the multi-modal remote sensing historical data of the same area to repair the multi-modal remote sensing real-time data of the unreliable data area, and calculate the real-time difference index Rs according to the calculation formula of the difference index R for the repaired multi-modal remote sensing real-time data; if the real-time difference index Rs is less than or equal to the threshold R0, output the prompt information of "data repair successful"; if the real-time difference index Rs is greater than the threshold R0, output the prompt information of "abnormality still exists after data repair, please check further", and the relevant personnel will carry out corresponding processing; S402. Mark the area identified as sudden event abnormal as a high-priority change area, obtain the location information of the high-priority change area and output it to the relevant personnel, and the relevant personnel will carry out corresponding processing.

7. A land use dynamic change monitoring system based on multi-modal remote sensing data, which is applied to the land use dynamic change monitoring method based on multi-modal remote sensing data according to any one of claims 1-6, and is characterized in that: The system includes: a data acquisition and preprocessing module, a consistency baseline construction module, a real-time data analysis module, and an abnormal diagnosis and processing module; The data acquisition and preprocessing module acquires the multi-modal remote sensing historical data within the monitoring period and the geographic information data of the monitoring area; preprocesses the multi-modal historical remote sensing data, and unifies the format and spatially registers the geographic information data, so that the geographic information data and the multi-modal historical remote sensing data are consistent in the spatial and temporal dimensions; The consistency baseline construction module divides the monitoring area into multiple sub-areas, and identifies its land use type according to the geographic data characteristics of each sub-area; analyzes the stable state data of each land use type and establishes a consistency baseline database; The real-time data analysis module obtains multi-modal remote sensing real-time data of different land use types in the monitoring area and compares it with the consistency baseline database; calculates the difference index between the characteristics of the real-time data and the characteristics of the baseline database, thereby initially screening out and marking suspected abnormal areas; The abnormal diagnosis and processing module analyzes the suspected abnormal areas to identify data quality abnormalities or emergency abnormalities; identifies the type of abnormality by analyzing the characteristic correlation relationship of the multi-modal remote sensing real-time data; if it is diagnosed as a data quality abnormality, repairs the unreliable data and re-compares the repaired data; if it is diagnosed as an emergency abnormality, marks it as a high-priority change area and promptly provides the relevant location information to relevant personnel for processing.

8. The land use dynamic change monitoring system based on multi-modal remote sensing data according to claim 7, characterized in that: The data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit obtains multi-modal remote sensing historical data during the monitoring period and geographical information data of the monitoring area; the data preprocessing unit preprocesses the multi-modal historical remote sensing data, unifies the format and performs spatial registration on the geographical information data, so that the geographical information data and the multi-modal historical remote sensing data are consistent in the spatial and temporal dimensions.

9. The land use dynamic change monitoring system based on multi-modal remote sensing data according to claim 7, characterized in that: The consistency baseline construction module includes a land use type analysis unit and a consistency baseline construction unit; The land use type analysis unit divides the monitoring area into multiple sub-areas and identifies the land use type of each sub-area according to the geographical data characteristics; the consistency baseline construction unit analyzes the stable state data of each land use type and establishes a consistency baseline database.

10. The land use dynamic change monitoring system based on multi-modal remote sensing data according to claim 7, characterized in that: The real-time data analysis module includes a consistency baseline database comparison unit and a suspected abnormal area identification unit; The consistency baseline database comparison unit obtains multi-modal remote sensing real-time data of different land use types in the monitoring area and compares it with the consistency baseline database; the suspected abnormal area identification unit calculates the difference index between the characteristics of the real-time data and the characteristics of the baseline database, thereby initially screening out and marking suspected abnormal areas; The abnormal diagnosis and processing module includes an abnormal diagnosis unit and a prompt information output unit; The abnormal diagnosis unit analyzes the suspected abnormal areas to identify data quality abnormalities or emergency abnormalities; identifies the type of abnormality by analyzing the characteristic correlation relationship of the multi-modal remote sensing real-time data; the prompt information output unit repairs the unreliable data and re-compares the repaired data for a diagnosed data quality abnormality; For a diagnosed emergency abnormality, marks it as a high-priority change area and promptly provides the relevant location information to relevant personnel for processing.

Images