Multi-source remote sensing geographic data-based urban mixed functional area identification method and system

Abstract

The invention discloses an urban mixed functional area identification method and system based on multi-source remote sensing geographic data, and belongs to the technical field of remote sensing image identification. The method comprises the following steps: acquiring remote sensing image data and road network data of a research area, and performing preprocessing and data superposition to obtain a basic block unit of the research area; obtaining POI data of a research area, preprocessing the POI data, and extracting a first data set from the basic block unit by using a POI distribution information entropy guided sample extraction method; acquiring AOI data of a research area, preprocessing the AOI data, and extracting a third data set from the basic block unit through a multi-view difference information learning method; combining the first data set with the third data set to obtain a comprehensive data set; and training a neural network model through the comprehensive data set, wherein the neural network model is used for urban functional area classification. According to the invention, the recognition precision of the single functional area is improved, and the real layout of each mixed functional area can be accurately captured in a complex urban environment.

Description

Technical Field

[0001] The present invention belongs to the technical field of remote sensing image processing and recognition, and in particular relates to a method and system for identifying urban mixed functional areas based on multi-source remote sensing geographic data. Background Art

[0002] With the rapid development of urbanization in my country, fully identifying the current status of urban development is crucial to promoting economic development, improving people's quality of life, and promoting comprehensive and balanced high-quality development of cities. Different from the urban regional divisions such as urban centers and suburban areas, urban functional areas emphasize the cohesion and improvement of the main functions in the region, such as industrial areas, residential areas, and commercial areas. As an important part of urban planning, urban functional areas can not only help urban planners and managers to rationally plan urban construction and promote balanced development in different regions, but also coordinate the functional layout of mixed areas, thereby achieving healthy development of cities. In addition, identifying urban functional areas helps to understand their spatial distribution characteristics, intensively save land resources, improve urban land utilization, and optimize resource allocation, which plays an important role in the scientific planning of cities and the optimization of living environment.

[0003] The purpose of urban functional areas is not always single, and mixed-use is also common. Such areas contain multiple functions, such as mixed residential and commercial types, and communities with both public services and commercial functions. The advantages of mixed-function areas are very obvious: they can provide a diverse living and working environment and improve the flexibility of the city; the coexistence of multiple functions can promote the vitality of the community and improve the quality of life of residents; reasonable layout can optimize the allocation of urban resources and improve land use efficiency; more importantly, mixed-function areas can better adapt to changes in urban development needs and enhance the city's sustainable development capabilities. Therefore, it is crucial to accurately identify mixed urban functional areas.

[0004] In recent years, remote sensing images have attracted widespread attention because they can objectively reflect the characteristics of ground objects. They contain rich information and have strong recognition capabilities. It is particularly worth mentioning that the development of deep learning technology has provided a powerful tool for urban functional area identification. This technology can not only improve the accuracy of identification, but also process large-scale data sets. On the other hand, the AOI data of crowd-sourced geographic information provides detailed geographic boundaries and rich category labels, which supplements the lack of remote sensing images in the details of ground object classification. The combination of the two significantly improves the accuracy and meticulousness of urban functional area identification.

[0005] At present, the recognition of urban functional areas focuses on a single type of area, while relatively insufficient attention is paid to mixed functional areas. Most traditional urban functional area recognition methods are based on supervised classification ideas and rely on a large amount of manually labeled data, which not only increases the workload but also limits the efficiency and breadth of recognition. Some urban functional area recognition methods combine the advantages of POI data and remote sensing images to achieve urban functional area recognition. However, due to the significant differences between POIs of different categories, it is difficult to effectively reveal the main categories of urban functional areas by relying solely on the density of POIs. For example, the number of commercial POIs usually far exceeds that of other categories, which may cause some areas to be misjudged as commercial areas.

[0006] Therefore, the recognition accuracy of mixed-functional areas by existing technologies needs to be improved, especially in complex urban environments, where it is difficult to accurately capture the true layout of each functional area. Summary of the invention

[0007] In view of this, the present invention proposes a method and system for identifying urban mixed functional areas based on multi-source remote sensing geographic data, which are used to solve the problem that it is difficult to accurately identify urban mixed functional areas in a complex urban environment.

[0008] In a first aspect, the present invention discloses a method for identifying urban mixed functional areas based on multi-source remote sensing geographic data, the method comprising:

[0009] Obtain remote sensing image data and road network data of the study area and preprocess them, then overlay the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area;

[0010] Acquire POI data of the study area and perform preprocessing, calculate the mixed degree of the functional category to which the basic block unit belongs according to the preprocessed POI data, and extract a first data set from the basic block unit according to the mixed degree; the first data set includes a first single functional area sample and a first mixed functional area sample;

[0011] Obtaining and preprocessing the AOI data of the study area, and extracting the second single functional area sample according to the preprocessed AOI data;

[0012] Merging the first single functional area sample with the second single functional area sample to obtain a second data set;

[0013] Performing multi-view difference information learning based on the second data set, and performing voting prediction on the basic block units to obtain a third data set;

[0014] Combining the first data set with the third data set to obtain a comprehensive data set;

[0015] The neural network model is trained by the comprehensive data set to obtain an urban functional area recognition model, and the urban functional area recognition model is used to classify the urban functional areas of the study area.

[0016] On the basis of the above technical solution, preferably, the calculation of the mixed degree of the functional category to which the basic block unit belongs specifically includes:

[0017] Construct a Voronoi diagram based on POI data, and use the Voronoi diagram to calculate the average area of ​​each type of POI data;

[0018] The weighted area ratio of each type of POI data is calculated by the average area of ​​each type of POI data and the number of each type of POI data;

[0019] According to the area weighted ratio, the POI distribution information entropy is used to calculate the mixing degree of the functional category to which any basic block unit in the study area belongs.

[0020] On the basis of the above technical solution, preferably, the formula for calculating the area weighted ratio of each type of POI data is:

[0021]

[0022] Among them, r represents any area in the study area, AP r (k) is the area weighted proportion of the k-th POI in region r, T k represents the total number of POI types of the kth category, k is the type number of a single category, k = 1,...,5; A(i,k) is the average area of ​​the kth category and the ith POI type; nr(i,k) is the number of the kth category and the ith POI type in region r; i = 1,2,…,T k .

[0023] On the basis of the above technical solution, preferably, the formula for calculating the mixed degree of the functional category to which any basic block unit in the study area belongs by using POI distribution information entropy is:

[0024]

[0025] Among them, MD r is the mixing degree of region r corresponding to any basic block unit, AP r (k) is the area weighted proportion of the k-th type of POI in region r.

[0026] Based on the above technical solution, preferably, extracting the first data set from the basic block unit according to the mixing degree specifically includes:

[0027] Set a mixed degree threshold. If the mixed degree of area r corresponding to a basic block unit in the study area is less than the mixed degree threshold, then area r is a single functional area, and the category with the largest area weighted ratio in area r is used as the category label of area r;

[0028] If the mixed degree of area r corresponding to a basic block unit in the study area is greater than or equal to the mixed degree threshold, then area r is a mixed functional area, and the category with a weighted area ratio in area r greater than the preset threshold is used as the category label of area r;

[0029] The first data set is constructed according to each basic block unit and the corresponding category label.

[0030] On the basis of the above technical solution, preferably, multi-view difference information learning is performed according to the second data set, and voting prediction is performed on the basic block unit, and the third data set is obtained, which specifically includes:

[0031] Dividing the second data set into N data subsets, and training N neural network models respectively by using the N data subsets;

[0032] The trained N neural network models are used to perform voting prediction on the basic block units to obtain a third data set.

[0033] Based on the above technical solution, preferably, the voting prediction of the basic block unit is performed by the trained N neural network models to obtain the third data set specifically including:

[0034] The trained N neural network models are used to vote and predict each basic block unit, and the final label of each image is determined by the majority voting mechanism;

[0035] In the case where the prediction results show mixed labels, statistics are taken based on the prediction results of the N trained neural network models, and the label combination supported by most models is selected as the final mixed label of the corresponding image.

[0036] In a second aspect, the present invention discloses a system for identifying mixed-function urban areas based on multi-source remote sensing geographic data, the system comprising:

[0037] Data overlay module: used to obtain remote sensing image data and road network data of the study area and preprocess them, and overlay the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area;

[0038] The first data set module is used to obtain and preprocess the POI data of the study area, calculate the mixed degree of the functional category to which the basic block unit belongs according to the preprocessed POI data, and extract the first data set from the basic block unit according to the mixed degree; the first data set includes a first single functional area sample and a first mixed functional area sample;

[0039] The second data set module is used to obtain and preprocess the AOI data of the study area, extract the second single functional area sample according to the preprocessed AOI data; merge the first single functional area sample with the second single functional area sample to obtain a second data set;

[0040] A third data set module: used to perform multi-view difference information learning based on the second data set, and perform voting prediction on the basic block unit to obtain a third data set;

[0041] Functional area classification module: used to merge the first data set and the third data set to obtain a comprehensive data set; train a neural network model through the comprehensive data set to obtain an urban functional area recognition model, and classify the urban functional areas of the study area through the urban functional area recognition model.

[0042] In a third aspect of the present invention, an electronic device is disclosed, comprising: at least one processor, at least one memory, a communication interface and a bus;

[0043] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0044] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method according to the first aspect of the present invention.

[0045] According to a fourth aspect of the present invention, a computer-readable storage medium is disclosed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method described in the first aspect of the present invention.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1) The present invention combines deep learning, remote sensing images, AOI data and POI data to form multi-source geographic data. Based on the single-type functional area labels provided by the multi-source geographic data, a sample extraction method based on the mixed degree of regional functional categories is proposed. The single functional area samples of the multi-source data are combined to perform multi-view difference information learning, effectively and automatically screen reliable samples containing single function and mixed function labels, thereby using remote sensing images to identify mixed urban functional areas, further improving the ability to identify urban functional areas.

[0048] 2) The present invention proposes a sample extraction method guided by POI distribution information entropy. This method uses area-weighted ratio to measure the land use ratio of different functional areas, and introduces the concept of POI distribution information entropy to quantify the mixing degree of functional categories in a region. The mixing degree of the region reflects the distribution of POIs of different functional categories in the region. According to the value of the mixing degree, the dominant type of each functional area and its mixed components can be evaluated and assisted in identifying, thereby more accurately guiding the extraction of urban functional area samples. This method can not only accurately reflect the actual use and complexity of each functional area, but also provide a data basis for subsequent analysis.

[0049] 3) The present invention uses a multi-view difference information learning method, uses single functional area samples extracted from multi-source data to perform multi-model training respectively, and uses a multi-model voting mechanism to predict labels for basic block units, which not only fills the potential data gaps, but also increases the number of samples in mixed functional areas.

[0050] 4) The present invention combines the sample extraction method guided by the POI distribution information entropy with the multi-view difference information learning method, which not only improves the accuracy of single functional area recognition, but also ensures that the true layout of various mixed functional areas is accurately captured in complex urban environments, thereby providing strong support for urban planning and management. By analyzing a large amount of spatiotemporal data, the spatial distribution characteristics of urban functional areas and their changing trends can be revealed. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A flow chart of a method for identifying mixed-functional urban areas based on multi-source remote sensing geographic data is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The present invention is committed to identifying mixed urban functional areas on the basis of solving the problem of identifying single urban functional areas. The present invention combines deep learning, remote sensing images, AOI data and POI data, and uses the detailed geographic boundaries and rich category labels provided by AOI data to supplement the deficiencies of remote sensing images in the classification details of objects, and uses the POI area weighted ratio to more accurately reveal the functional characteristics of urban areas, so as to improve the ability to identify mixed urban functional areas.

[0055] It is understandable that before using the method of the present invention, the urban functional area classification system is first determined. The present invention divides urban functional areas into five single functional area categories and two mixed functional area categories, namely, residential land, commercial service facility land, industrial land, public management and public service land, green land and square land, commercial and residential mixed land, and residential public mixed land, a total of seven categories.

[0056] Table 1 Functional area classification system

[0057]

[0058]

[0059] See also Figure 1 The present invention discloses a method for identifying urban mixed functional areas based on multi-source remote sensing geographic data, the method comprising:

[0060] S1. Obtain remote sensing image data and road network data of the study area and preprocess them, and superimpose the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area.

[0061] In the embodiment of the present invention, remote sensing data collection and processing are performed on the Google Earth Engine (GEE) platform. Sentinel-2 10m and 20m resolution band data are selected, and all images are resampled to 10m. Multi-view images are spliced ​​using ENVI to cover the entire study area.

[0062] In the embodiment of the present invention, the road network data is derived from the Open Street Map (OSM). First, the road network data is precisely clipped according to the scope of the study area. Then, internal and invalid roads are removed, and the topological check of the roads is performed to ensure that all block boundaries are closed and overlap between plots is eliminated. Finally, the processed road network layer is accurately superimposed with the remote sensing image to form the basic block unit Sample for functional area mapping. Block_ori .

[0063] S2. Acquire POI data of the study area and perform preprocessing, calculate the mixing degree of the functional category to which the basic block unit belongs based on the preprocessed POI data, and extract a first data set from the basic block unit based on the mixing degree.

[0064] Considering that some functional areas in a city are composed of a mixture of multiple categories, in order to quantify this diversity, the present invention proposes a method for extracting urban functional area samples guided by POI distribution information entropy, extracting a first data set from the basic block unit, specifically comprising the following steps:

[0065] S21. POI data acquisition and preprocessing.

[0066] In an embodiment of the present invention, the original POI data is derived from existing map software. The GCJ-02 coordinates of the original POI data are converted to WGS-84 coordinates, and then the POI data is screened to remove missing, repeated, erroneous or non-uniform data, and some points with low public awareness, such as public toilets, are removed. The POI data is then reclassified into five categories: residential land, commercial service facility land, industrial land, public management and public service land, green land and square land, and the small category data of each point is retained, and finally POI data containing four attributes of name, large category, small category and longitude and latitude are obtained.

[0067] S22. Construct a Voronoi diagram based on the preprocessed POI data, and use the Voronoi diagram to count the average area of ​​each type of POI data.

[0068] Specifically, by constructing a Voronoi diagram, the average area of ​​each type of POI data is converted from the POI location information, so that each POI has an area attribute.

[0069] S23, calculating the area weighted proportion of each type of POI data according to the average area of ​​each type of POI data and the number of each type of POI data.

[0070] In the embodiment of the present invention, for any defined area, the area weighted ratio of each type of POI is determined by considering the total number of each type of POI in the area, the average area of ​​each POI, and the number of a specific type of POI in the area.

[0071] In the embodiment of the present invention, for any defined region r, the area weighted proportion APr(k) of the k-th type of POI can be calculated by the following formula:

[0072]

[0073] Where: T krepresents the total number of POI types of the kth category; A(i,k) is the average area of ​​the kth category and i-th POI type; this area can be converted from the POI location information by constructing a Voronoi diagram, so that each POI has an area attribute; nr(i,k) is the number of the kth category and i-th POI type in region r.

[0074] The above calculation formula can better reflect the actual influence of different types of POIs in the urban spatial layout, thereby helping to more accurately identify and define the functional areas of the city.

[0075] S24. According to the area weighted ratio, the POI distribution information entropy is used to calculate the mixing degree of the functional category to which any basic block unit in the study area belongs.

[0076] Some functional areas in the city are not composed of a single category, but show diverse characteristics due to the mixed existence of multiple categories. In order to quantify this diversity, the concept of POI distribution information entropy is introduced to quantify the mixed degree of functional categories in a region, namely, mixed diversity (MD). r ). Information entropy is a statistical concept used to describe the degree of disorder of a system or the uncertainty of information.

[0077] In the embodiment of the present invention, the formula for calculating the mixed degree of the functional category to which any basic block unit belongs in the study area is:

[0078]

[0079] Among them, MD r is the mixing degree of region r corresponding to any basic block unit, AP r (k) is the area weighted proportion of the k-th type of POI in region r, k is the type number of a single category, k = 1,...,5.

[0080] MD r The value range is [0,2.32]. When the area weighted ratio AP of all categories r (k) Equal (when both are 1 / 5,

[0081] S25. Extract a first data set from the basic block unit according to the mixing degree.

[0082] According to the mixed degree MD r The value of can determine the functional category characteristics of region r: when MD r When it is close to zero, it indicates that the functional category in region r is relatively simple and the uncertainty is low. At this time, the region mainly belongs to AP r(k) the category with the largest value; when MD r When the value is high, it means that the functional categories in the region are more diverse and the uncertainty is higher. In this case, region r can be considered to belong to the mixed category.

[0083] In the embodiment of the present invention, a mixed degree threshold is set to distinguish between a single-function area and a mixed-function area in the basic block unit, and the first data set is extracted. Block_ori The mixing degree of the data is statistically analyzed with an interval of 0.1, which can provide a detailed understanding of the number distribution of functional areas within different mixing degree ranges. Through further analysis, it is found that there is a significant change point when the mixing degree reaches a certain value. The mixing degree threshold is set according to the significant change point, and the sample is divided according to the mixing degree threshold and the area weighted ratio of each category. Block_ori The data is divided into single functional area samples Block_single and mixed ribbon sampleSample Block_mixed .

[0084] In an embodiment of the present invention, extracting the first data set from the basic block unit according to the mixing degree specifically includes:

[0085] If the mixing degree of area r corresponding to a basic block unit in the study area is less than the mixing degree threshold, then area r is a single functional area, and the category with the largest area weighted ratio in area r is used as the category label of area r; if the mixing degree of area r corresponding to a basic block unit in the study area is greater than or equal to the mixing degree threshold, then area r is a mixed functional area, and the two categories with area weighted ratios greater than the preset threshold in area r are used as mixed labels of area r; a first data set is constructed based on each basic block unit and the corresponding category label.

[0086] S3. Obtain the AOI data of the study area and perform preprocessing, and extract the second single functional area sample according to the preprocessed AOI data.

[0087] The initial sample of the urban functional area of ​​the present invention comes from the AOI data Sample provided by the Open Street Map OSM AOI_ori AOIs provide detailed geographic information and rich category labels that often cover multiple single-purpose categories.

[0088] According to the scope of the study area, cut out the AOI single functional area sample in the study area AOI_ori According to the research needs of this invention, the samples are reclassified into five categories, namely, residential land, commercial service facility land, industrial land, public administration and public service land, and green land and square land.

[0089] S4. Merge the first single functional area sample and the second single functional area sample to obtain a second data set, perform multi-view difference information learning based on the second data set, and perform voting prediction on the basic block unit to obtain a third data set.

[0090] Considering that there is no POI data distribution in some basic block units, in order to make up for the missing data and increase the number of samples in mixed functional areas, the present invention uses a multi-view difference information learning method to extract the third data set using single functional area samples.

[0091] Specifically, the second data set is divided into N data subsets, each of which is used to independently train a neural network model. N neural network models are trained using the N data subsets respectively; voting prediction is performed on the basic block units using the trained N neural network models to obtain a third data set. In an embodiment of the present invention, the neural network model adopts the SE-ResNet50 model.

[0092] In an embodiment of the present invention, the voting prediction of the basic block unit is performed by the trained N neural network models to obtain the third data set, which specifically includes:

[0093] The trained N neural network models are used to vote and predict each basic block unit, and the final label of each image is determined by the majority voting mechanism;

[0094] In the case where the prediction results show mixed labels, statistics are taken based on the prediction results of the N trained neural network models, and the label combination supported by most models is selected as the final mixed label of the corresponding image.

[0095] S5. Combine the first data set and the third data set to obtain a comprehensive data set, train a neural network model with the comprehensive data set to obtain an urban functional area recognition model, and classify the urban functional areas of the study area with the urban functional area recognition model.

[0096] The first data set and the third data set are merged to form a comprehensive data set, which includes 7 types of functional area samples. These reclassified data are then input into SE-ResNet50 for training to obtain the final urban functional area recognition model to achieve the classification of urban functional areas.

[0097] On the basis of the above method embodiment, the present invention further proposes a system for identifying urban mixed functional areas based on multi-source remote sensing geographic data, the system comprising:

[0098] Data overlay module: used to obtain remote sensing image data and road network data of the study area and preprocess them, and overlay the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area;

[0099] The first data set module is used to obtain and preprocess the POI data of the study area, calculate the mixed degree of the functional category to which the basic block unit belongs according to the preprocessed POI data, and extract the first data set from the basic block unit according to the mixed degree; the first data set includes a first single functional area sample and a first mixed functional area sample;

[0100] The second data set module is used to obtain and preprocess the AOI data of the study area, extract the second single functional area sample according to the preprocessed AOI data; merge the first single functional area sample with the second single functional area sample to obtain a second data set;

[0101] A third data set module: used to perform multi-view difference information learning based on the second data set, and perform voting prediction on the basic block unit to obtain a third data set;

[0102] Functional area classification module: used to merge the first data set and the third data set to obtain a comprehensive data set; train a neural network model through the comprehensive data set to obtain an urban functional area recognition model, and classify the urban functional areas of the study area through the urban functional area recognition model.

[0103] The above system embodiments and method embodiments correspond one to one, and for a brief description of the system embodiments, please refer to the method embodiments.

[0104] The present invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus; wherein the processor, memory, and communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the aforementioned method of the present invention.

[0105] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to implement all or part of the steps of the method described in the embodiment of the present invention. The storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk, and other media that can store program codes.

[0106] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be distributed to multiple network units. A person skilled in the art may select some or all of the modules according to actual needs to achieve the purpose of the solution of this embodiment without creative effort.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying urban mixed functional areas based on multi-source remote sensing geographic data, characterized in that: The method comprises: Obtain remote sensing image data and road network data of the study area and preprocess them, then overlay the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area; Acquire POI data of the study area and perform preprocessing, calculate the mixed degree of the functional category to which the basic block unit belongs according to the preprocessed POI data, and extract a first data set from the basic block unit according to the mixed degree; the first data set includes a first single functional area sample and a first mixed functional area sample; Obtaining and preprocessing the AOI data of the study area, and extracting the second single functional area sample according to the preprocessed AOI data; Merging the first single functional area sample with the second single functional area sample to obtain a second data set; Performing multi-view difference information learning based on the second data set, and performing voting prediction on the basic block units to obtain a third data set; Combining the first data set with the third data set to obtain a comprehensive data set; The neural network model is trained by the comprehensive data set to obtain an urban functional area recognition model, and the urban functional area recognition model is used to classify the urban functional areas of the study area.

2. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 1 is characterized in that: The step of calculating the mixed degree of the functional category to which the basic block unit belongs specifically includes: Construct a Voronoi diagram based on POI data, and use the Voronoi diagram to calculate the average area of ​​each type of POI data; The weighted area ratio of each type of POI data is calculated by the average area of ​​each type of POI data and the number of each type of POI data; According to the area weighted ratio, the POI distribution information entropy is used to calculate the mixing degree of the functional category to which any basic block unit in the study area belongs.

3. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 2 is characterized in that: The formula for calculating the area weighted ratio of each type of POI data is: Among them, r represents any area in the study area, AP r (k) is the area weighted proportion of the k-th POI in region r, T k represents the total number of POI types of the kth category, k is the type number of a single category, k = 1,...,5; A(i,k) is the average area of ​​the kth category and the ith POI type; nr(i,k) is the number of the kth category and the ith POI type in region r; i = 1,2,…,T k .

4. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 3 is characterized in that: The formula for calculating the mixed degree of the functional category to which any basic block unit in the study area belongs using POI distribution information entropy is: Among them, MD r is the mixing degree of region r corresponding to any basic block unit, AP r (k) is the area weighted proportion of the k-th type of POI in region r.

5. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 1 is characterized in that: The extracting the first data set from the basic block unit according to the mixing degree specifically includes: Set a mixed degree threshold. If the mixed degree of area r corresponding to a basic block unit in the study area is less than the mixed degree threshold, then area r is a single functional area, and the category with the largest area weighted ratio in area r is used as the category label of area r; If the mixed degree of area r corresponding to a basic block unit in the study area is greater than or equal to the mixed degree threshold, then area r is a mixed functional area, and the category with a weighted area ratio in area r greater than the preset threshold is used as the category label of area r; The first data set is constructed according to each basic block unit and the corresponding category label.

6. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 1, characterized in that: The multi-view difference information learning is performed according to the second data set, and voting prediction is performed on the basic block unit, so that the third data set is obtained, which specifically includes: Dividing the second data set into N data subsets, and training N neural network models respectively by using the N data subsets; The trained N neural network models are used to perform voting prediction on the basic block units to obtain a third data set.

7. The method for identifying urban mixed functional areas based on multi-source remote sensing geographic data according to claim 6 is characterized in that: The voting prediction of the basic block unit by the trained N neural network models is performed to obtain the third data set, which specifically includes: The trained N neural network models are used to vote and predict each basic block unit, and the final label of each image is determined by the majority voting mechanism; In the case where the prediction results show mixed labels, statistics are taken based on the prediction results of the N trained neural network models, and the label combination supported by most models is selected as the final mixed label of the corresponding image.

8. A system for identifying urban mixed functional areas based on multi-source remote sensing geographic data, characterized in that: The system comprises: Data overlay module: used to obtain remote sensing image data and road network data of the study area and preprocess them, and overlay the preprocessed remote sensing image data with the road network data to obtain the basic block units of the study area; The first data set module is used to obtain and preprocess the POI data of the study area, calculate the mixed degree of the functional category to which the basic block unit belongs according to the preprocessed POI data, and extract the first data set from the basic block unit according to the mixed degree; the first data set includes a first single functional area sample and a first mixed functional area sample; The second data set module is used to obtain and preprocess the AOI data of the study area, extract the second single functional area sample according to the preprocessed AOI data; merge the first single functional area sample with the second single functional area sample to obtain a second data set; A third data set module: used to perform multi-view difference information learning based on the second data set, and perform voting prediction on the basic block unit to obtain a third data set; Functional area classification module: used to merge the first data set and the third data set to obtain a comprehensive data set; train a neural network model through the comprehensive data set to obtain an urban functional area recognition model, and classify the urban functional areas of the study area through the urban functional area recognition model.

9. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; Wherein, the processor, memory, and communication interface communicate with each other via the bus; The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to any one of claims 1 to 7.

Images