A method for urban land planning analysis based on remote sensing images

Abstract

The present invention provides an urban land planning analysis method based on remote sensing images, comprising: determining temporary construction land blocks and temporary construction land types of a target city; determining the geospatial change degree of the temporary construction land blocks based on first historical geospatial data and second historical geospatial data of the temporary construction land blocks; determining whether the temporary construction land blocks are abnormal land blocks based on historical remote sensing images and current remote sensing images of the target city at a second historical time node; and performing an association analysis on the temporary construction land blocks and land blocks corresponding to the same land type as the temporary construction land blocks. By analyzing the current remote sensing images of the target city, the temporary construction land blocks and the corresponding temporary construction land types of the target city can be determined, and the attribute information of the temporary construction land blocks marked as abnormal land blocks can be used as an analysis reference for the same land types.

Description

[0001] This application is a divisional application of patent number "2024112183416", application date "2024-09-02", and name "A GIS-based urban land planning analysis method and system". Technical Field

[0002] The present invention relates to the technical field of urban land planning, and in particular to an urban land planning analysis method based on remote sensing images. Background Art

[0003] GIS (Geographic Information System) data is the foundation of GIS technology. It encompasses both geospatial and attribute data and is used to store, analyze, and display geographic information. GIS technology enables the collection and integration of geographic information such as topography and land types, providing foundational data for land use planning. It can analyze the spatial relationships between plots of land with different uses and simulate land planning scenarios through modeling. GIS technology enables rapid and accurate analysis and comprehensive evaluation of land spatial distribution and characteristics, providing a scientific basis and decision support for land planning.

[0004] Land use patterns are considered a significant factor influencing the balance between employment and housing, which in turn impacts urban residents' transportation, carbon emissions, and the urban environment. Related technologies analyze urban land use vector data from different time periods using software such as ArcGIS, thereby determining overall land characteristics, regional differentiation patterns, and changes in major land use types. Traditional urban planning often differs from the actual urban spatial situation. Traditional land survey data typically covers permanent construction land, but lacks investigation and analysis of temporary construction land. This makes it difficult to accurately reflect the true urban spatial situation and influence urban land planning and analysis. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide an urban land planning analysis method based on remote sensing images, which solves the problem that the existing technology lacks investigation and analysis of temporary construction land, making it difficult to better reflect the most realistic urban space status and affect urban land planning and analysis.

[0006] First, this application provides an urban land planning analysis method based on remote sensing images, including:

[0007] Determining, based on a current remote sensing image of a target city, a temporary construction land block of the target city and a temporary construction land type of the temporary construction land block;

[0008] Retrieving historical planning data of the temporary construction land block and determining at least one target planning time interval for the temporary construction land block based on the historical planning data; the target planning time interval includes a time segment between a first historical time node and a second historical time node located after the first historical time node;

[0009] determining a geospatial change degree of the temporary construction land block based on first historical geospatial data of the temporary construction land block at the first historical time node and second historical geospatial data at the second historical time node;

[0010] When the geographic space change degree is lower than a preset geographic space change threshold, determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image of the target city at the second historical time node and the current remote sensing image;

[0011] When it is determined that the temporary construction land block is an abnormal land block, the temporary construction land block is subjected to association analysis with land blocks corresponding to the same land type as the temporary construction land block.

[0012] In one embodiment, determining the temporary construction land block and the land type of the temporary construction land block of the target city based on the current remote sensing image of the target city specifically includes:

[0013] Assigning pixels of the current remote sensing image of the target city to preset land categories, and dividing the target city into a plurality of land units; the land categories include land cover categories and land use categories;

[0014] Performing spatial analysis on each of the land units to determine attribute information corresponding to each of the land units and a first matching degree between the attribute information and a preset temporary building land attribute;

[0015] Marking a land unit whose first matching degree exceeds a preset first matching degree threshold as a reference land unit, merging at least another adjacent land unit with the reference land unit as the center to generate a land block to be determined, and determining a second matching degree between the land block to be determined and the land attribute of the temporary building;

[0016] The undetermined land block whose second matching degree exceeds the preset second matching degree threshold is marked as a temporary construction land block, and the temporary construction land type of the temporary construction land block is determined according to the land category of the land units contained in the temporary construction land block.

[0017] In one embodiment, allocating pixels of the current remote sensing image of the target city to preset land categories and dividing the target city into a plurality of land units specifically includes:

[0018] Based on the spectral band corresponding to the preset land category, the current remote sensing image is subjected to spectral analysis, and pixels of the current remote sensing image that match the spectral analysis are assigned to the land category;

[0019] Merge connected pixels belonging to the same land category into the same land unit.

[0020] In one embodiment, performing spatial analysis on each of the land units to determine the attribute information corresponding to each of the land units specifically includes:

[0021] extracting geometric features of each of the land units;

[0022] Superimposing the land unit with a preset human factor layer based on the geometric features, and marking the land unit whose intersection area after superposition is greater than a preset intersection area threshold with a corresponding artificial structure label;

[0023] Attribute information corresponding to each of the land units is determined based on the query index corresponding to the man-made structure tag.

[0024] In one embodiment, determining at least one target planning time interval for the temporary construction land block based on the historical planning data specifically includes:

[0025] The planning project of the temporary building land block in the historical planning data is determined, and the start and end times of the planning project are used as the target planning time interval.

[0026] In one embodiment, determining the geospatial change degree of the temporary construction land block based on first historical geospatial data of the temporary construction land block at the first historical time node and second historical geospatial data at the second historical time node specifically includes:

[0027] The geospatial change degree between the first historical geospatial data and the second historical geospatial data is determined according to a preset loss function.

[0028] In one embodiment, the historical remote sensing image and the current remote sensing image include the temporary construction land block and a land block adjacent to the temporary construction land block; and determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image and the current remote sensing image of the target city at the second historical time node specifically includes:

[0029] In the historical remote sensing image, taking the boundary line of the temporary construction land block as a reference, performing negative buffer processing on the temporary construction land block with a preset distance to obtain a negative buffer area, and performing masking processing on the negative buffer area to obtain a masked historical remote sensing image of the temporary construction land block;

[0030] Inputting the masked historical remote sensing image into a preset image restoration model for restoration, thereby obtaining a restored remote sensing image;

[0031] When the similarity between the restored remote sensing image and the current remote sensing image is less than a preset similarity threshold, the temporary building land block is determined to be an abnormal land block.

[0032] In one embodiment, before inputting the masked historical remote sensing image into a preset image restoration model for restoration to obtain a restored remote sensing image, the method further includes:

[0033] Constructing an image restoration sample data set; the image restoration sample data set includes remote sensing images of multiple temporary buildings that have not been demolished at different time nodes and non-demolished planning information of the temporary buildings that have not been demolished;

[0034] Based on the image restoration sample data set, the image restoration model is trained by a neural network model.

[0035] In the second aspect, the present application provides a GIS-based urban land planning analysis system, comprising a processor and a memory; wherein the memory stores a computer program, and the computer program is used by the processor to load and execute an urban land planning analysis method based on remote sensing images as described in any one of the first aspects.

[0036] In a third aspect, the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores instructions, and the instructions are used by a processor to load and execute an urban land planning analysis method based on remote sensing images as described in any one of the first aspects.

[0037] In an urban land planning analysis method and system based on remote sensing images of the present embodiment, by analyzing the current remote sensing images of the target city, the temporary construction land blocks and the corresponding temporary construction land types of the target city can be determined, and combined with the historical planning data and historical geographic spatial data of the temporary construction land blocks, it can be determined whether the temporary construction land blocks are land blocks where temporary buildings have not been demolished under abnormal circumstances, so that the attribute information of the temporary construction land blocks marked as abnormal land blocks can be used as an analysis reference for the same land type. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 Schematic diagram of the process of urban land planning analysis method based on remote sensing images in an embodiment of the present application. DETAILED DESCRIPTION

[0040] Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the described embodiments are merely some, and not all, of the embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the description of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0041] In the description of the present invention, unless otherwise specified or limited, the terms "disposed," "installed," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; and direct or indirect connections through an intermediary. Those skilled in the art will understand the specific meanings of these terms based on the specific circumstances.

[0042] The directions or positional relationships indicated by terms such as "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inside" and "outside" are based on the directions or positional relationships shown in the accompanying drawings, or are the directions or positional relationships in which the inventive product is usually placed when in use. They are only for the convenience and simplification of description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0043] The terms "first," "second," "third," etc. are merely used to distinguish elements of similar nature and do not indicate or imply relative importance or a particular order.

[0044] The terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than the listed elements and may also include additional elements not specifically listed.

[0045] like Figure 1 As shown, this embodiment provides an urban land planning analysis method based on remote sensing images, including:

[0046] Step S100: determining a temporary construction land block of the target city and a temporary construction land type of the temporary construction land block based on a current remote sensing image of the target city;

[0047] Step S200: Retrieving historical planning data of the temporary construction land block, and determining at least one target planning time interval for the temporary construction land block based on the historical planning data; the target planning time interval includes a time segment between a first historical time node and a second historical time node located after the first historical time node;

[0048] Step S300: determining the geospatial change degree of the temporary construction land block according to the first historical geospatial data of the temporary construction land block at the first historical time node and the second historical geospatial data at the second historical time node;

[0049] Step S400: When the geographic space change degree is lower than a preset geographic space change threshold, determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image of the target city at the second historical time node and the current remote sensing image;

[0050] Step S500: When it is determined that the temporary construction land block is an abnormal land block, the temporary construction land block is subjected to association analysis with land blocks corresponding to the same land type as the temporary construction land block.

[0051] In an urban land planning analysis method based on remote sensing images in this embodiment, by analyzing the current remote sensing images of the target city, the temporary building land blocks and the corresponding temporary building land types of the target city can be determined, and combined with the historical planning data and historical geographic spatial data of the temporary building land blocks, it can be determined whether the temporary building land blocks are land blocks where temporary buildings have not been demolished under abnormal circumstances, so that the attribute information of the temporary building land blocks marked as abnormal land blocks can be used as an analysis reference for the same land type.

[0052] Step S100: Based on a current remote sensing image of a target city, determining a temporary construction land block of the target city and a temporary construction land type of the temporary construction land block.

[0053] In step S100, the target city refers to the designated or selected city. Remote sensing images refer to surface images acquired by remote sensing satellites (such as Landsat remote sensing satellites, Sentinel remote sensing satellites), aircraft or UAV platforms. The current remote sensing images of the target city can be acquired through satellite map tools such as USGS and Google Earth Engine. The current remote sensing image records the spectral information, spatial information, texture information, shape information, and location information of the target city in the current state. The spectral information includes multiple spectral bands, and different land objects (such as vegetation, water bodies, soil, man-made structures, etc.) have different reflection characteristics in different spectral bands; spatial information records surface features in the form of spatial resolution; shape information records the shape and layout of surface features; and location information records the relationship between points on the remote sensing image and actual geographic location coordinates.

[0054] Temporary construction land parcels refer to parcels of land containing temporary structures, including tents, prefabricated houses, container homes, temporary fences, temporary bridges, temporary roads, and other spatial structures. Because temporary structures are designed for short-term use or for a specific period of time, they can be quickly erected, cost-effectively, and easily disassembled and moved. Land planning analysis typically focuses on land used for long-term permanent structures, while analysis of land used for temporary structures is less frequent or absent.

[0055] Determining a temporary construction land block and a land type of the temporary construction land block in the target city based on a current remote sensing image of the target city specifically includes:

[0056] Step S101: assigning pixels of the current remote sensing image of the target city to preset land categories, and dividing the target city into a plurality of land units; the land categories include land cover categories and land use categories;

[0057] Step S102: performing spatial analysis on each of the land units to determine attribute information corresponding to each of the land units and a first matching degree between the attribute information and the preset temporary building land attribute;

[0058] Step S103: marking a land unit whose first matching degree exceeds a preset first matching degree threshold as a reference land unit, merging at least another adjacent land unit with the reference land unit as the center to generate a land block to be determined, and determining a second matching degree between the land block to be determined and the land attribute of the temporary building;

[0059] Step S104: Mark the undetermined land block whose second matching degree exceeds the preset second matching degree threshold as a temporary construction land block, and determine the temporary construction land type of the temporary construction land block according to the land category of the land units contained in the temporary construction land block.

[0060] By dividing the current land use types of the target city, the target city can be divided into multiple land units, and the attribute information of each land unit can be determined through spatial analysis. The attribute information of each land unit is matched with the preset temporary building land attributes, and the land unit with a large difference from the preset land type can be identified as the benchmark land unit. It is further determined whether the land units near the benchmark land unit have similar characteristics to the benchmark land unit, thereby determining a collection of land units with a large deviation from the preset attribute information as the temporary building land block.

[0061] Step S101: Allocate pixels of the current remote sensing image of the target city to preset land categories, and divide the target city into a plurality of land units; the land categories include land cover categories and land use categories.

[0062] In step S101, since different land objects (such as forests, water bodies, soil, man-made structures, etc.) have different reflective characteristics in different spectral bands, the current remote sensing image can be spectrally analyzed using the spectral bands corresponding to different land objects to determine which pixels in the current remote sensing image have a higher matching degree, and multiple land units can be divided according to the set of pixels.

[0063] Remote sensing images include raster data, which is a data format that divides space into a regular grid, with each grid cell being called a unit. Each unit cell is assigned a corresponding attribute value to represent an entity. In a raster dataset, each grid cell is called a pixel, and each pixel has a value that represents the phenomenon being depicted, such as category, height, magnitude, or spectrum. Categories can be land use types such as grassland, forest, or road; height (distance) can represent surface elevation above mean sea level and can be used to derive slope, aspect, and watershed attributes; magnitude can represent gravity, noise pollution, or rainfall percentage; and spectrum can represent light reflectance and color in satellite imagery and aerial photography.

[0064] The method of allocating pixels of the current remote sensing image of the target city to a preset land category and dividing the target city into multiple land units specifically includes: performing spectral analysis on the current remote sensing image based on the spectral band corresponding to the preset land category, and allocating pixels of the current remote sensing image matched by the spectral analysis to the land category; and merging connected pixels belonging to the same land category into the same land unit.

[0065] Among them, the current remote sensing image can be spectrally analyzed by the maximum likelihood classification method. First, the spectral information under each preset land category is used to construct a corresponding data set; then, based on the normal distribution assumption, the mean vector and covariance matrix of each data set are calculated respectively, and the probability density function corresponding to the spectral information under each land category is constructed according to the mean variance and covariance matrix; then, for each pixel in the current remote sensing image, the likelihood value of its belonging to each land category is calculated respectively, and the corresponding pixel of the current remote sensing image is matched according to the likelihood value.

[0066] The probability density function is as follows:

[0067]

[0068] Among them, X is the spectral information, μ is the mean vector of X, Y is the covariance matrix of X, det(Y) is the determinant of the covariance matrix Y, and Y -1 is the inverse matrix of the covariance matrix Y.

[0069] Step S102: performing spatial analysis on each of the land units to determine attribute information corresponding to each of the land units and a first matching degree between the attribute information and the preset temporary building land attribute.

[0070] In step S102, spatial analysis is performed on each of the land units to determine the attribute information corresponding to each of the land units, specifically including: extracting the geometric features of each of the land units; superimposing the land units with a preset human factor layer based on the geometric features, and marking the land units whose intersection area after superposition is greater than a preset intersection area threshold with the corresponding artificial structure label; and determining the attribute information corresponding to each of the land units based on the query index corresponding to the artificial structure label.

[0071] Geometric features can include information such as the shape (such as rectangle, circle, irregular shape, etc.), area size, perimeter, direction, etc. of the land unit. Then, based on these geometric features, the land unit is superimposed with the preset human factor layer. Assuming that the preset human factor layer contains the planned building range in a specific area, when the geometric range of a land unit overlaps with these building ranges, it is necessary to further determine the size of the intersection area. If the superimposed intersection area is larger than the preset intersection area threshold, the land unit is marked as the corresponding artificial structure label. For example, the preset intersection area threshold is 50% of the land unit area. When the intersection area of ​​a land unit and the building range reaches 60% of its own area, it will be marked as an artificial structure label.

[0072] Man-made structure tags include urban infrastructure buildings (such as residences, shopping malls, hospitals, schools, etc.), transportation buildings (such as airports, train stations, ports, etc.), entertainment buildings (such as cinemas, museums, parks, stadiums, etc.), infrastructure buildings (such as roads, bridges, tunnels, etc.), agricultural buildings (such as greenhouses, livestock sheds, barns, etc.), administrative buildings (such as courts, police stations, city halls, etc.) and religious buildings (such as temples, churches, etc.), as well as some other types of man-made structure tags.

[0073] Correspondingly, the human factor layer includes urban basic building layer, transportation building layer, entertainment building layer, infrastructure building layer, agricultural building layer, administrative building layer and religious building layer, etc.

[0074] After determining the man-made structure label for each land unit, the corresponding attribute information can be extracted based on the query indicators corresponding to each land type. For example, for the urban infrastructure layer, query indicators may include building density and building height; for the transportation layer, indicators may include road grade and traffic flow; for the entertainment layer, the focus may be on building scale and service scope; for the infrastructure layer, the coverage and service capacity of the facilities may be considered; for the agricultural layer, the focus may be on the scale and type of breeding or planting facilities; for the administrative layer, the focus may be on the administrative level and service population; and for the religious layer, the focus may be on the scale and frequency of religious activities.

[0075] Temporary structures are typically small, simple in appearance, with a relatively random layout and a loose density. They are often built in a short period of time, often in a lack of adequate urban infrastructure. The materials used for temporary construction are often prefabricated components made of sheet metal, wood, or plastic film. Examples include prefabricated houses built by railway workers along the railway line and temporary bridges erected during construction for traffic or transportation.

[0076] Whether the compared land unit is temporary construction land can be determined by comparing the temporary construction land attributes with the attribute information corresponding to each land unit, including appearance characteristics, material characteristics, time characteristics, surrounding environment, land area and building density.

[0077] Temporary structures are typically constructed while permanent structures are being constructed and are demolished after the permanent structures are completed. To determine the planning of the land for temporary structures after their demolition, the land units occupied by the permanent structures near the temporary structures must also be included in the scope of the temporary construction land block.

[0078] Step S103: marking a land unit whose first matching degree exceeds a preset first matching degree threshold as a reference land unit, merging at least another adjacent land unit with the reference land unit as the center to generate a land block to be determined, and determining a second matching degree between the land block to be determined and the land attribute of the temporary building;

[0079] Step S104: Mark the undetermined land block whose second matching degree exceeds the preset second matching degree threshold as a temporary construction land block, and determine the temporary construction land type of the temporary construction land block according to the land category of the land units contained in the temporary construction land block.

[0080] In step S103 and step S104, the reference land unit is the land unit occupied by the temporary building. When merging adjacent land units, according to the overlapping length of the contour lines between the adjacent land units and the reference land unit, the land unit with the longest overlapping contour line is preferentially selected for merging, and then the adjacent land unit and the reference land unit are taken together as the land block to be determined. If the second matching degree between the attributes of the land block to be determined and the attributes of the temporary building land exceeds the preset second matching degree threshold, then the merging of the adjacent land units is accepted, and the adjacent land units are also marked with the label information of the temporary building land block. If the second matching degree between the attributes of the land block to be determined and the attributes of the temporary building land is less than or equal to the preset second matching degree threshold, then the merging of the adjacent land units is not accepted, and another adjacent land unit is merged again in the order of overlapping contour lines and re-compared with the second matching degree threshold until the adjacent land units near the reference land unit are merged in sequence and the comparison is completed. The temporary construction land block is a collection of land units marked with label information of the temporary construction land block. The land type of the temporary construction land block can be determined according to the land type of each land unit in the temporary construction land block.

[0081] Furthermore, due to the fact that temporary buildings are somewhat dispersed, that is, there are multiple related temporary buildings during the construction of the same batch of construction projects, and there is a certain distance between the two temporary buildings in space, in order to avoid identifying the land blocks where multiple temporary buildings are located as multiple unrelated temporary building land blocks when determining the temporary building land blocks, this embodiment merges the divided temporary building land blocks again, thereby merging multiple related temporary building land blocks into a complete temporary building land block, avoiding missing relevant information in the process of urban land planning analysis.

[0082] The divided temporary construction land blocks are merged again, thereby merging multiple related temporary construction land blocks into a complete temporary construction land block, specifically comprising the following steps: performing positive buffering processing of a preset distance on two temporary construction land blocks that are close to each other but not adjacent to each other and obtaining two positive buffer land blocks after the outlines are expanded; if the two positive buffer land blocks after the outlines are expanded have an intersection, it indicates that the temporary construction land blocks corresponding to the two positive buffer land blocks may be related; then similarity analysis is performed on the geographic spatial data of the two temporary construction land blocks to obtain a similarity result. When the similarity result is greater than a preset similarity threshold, it indicates that the two temporary construction land blocks are related, and the two temporary construction land blocks and other land blocks sandwiched between the two temporary construction land blocks are merged into a complete temporary construction land block. If the two positive buffer land blocks after the outlines are expanded do not have an intersection, it indicates that the temporary construction land blocks corresponding to the two positive buffer land blocks may not be related.

[0083] Step S200: Call the historical planning data of the temporary building land block, and determine at least one target planning time interval of the temporary building land block based on the historical planning data; the target planning time interval includes a time segment between a first historical time node and a second historical time node located after the first historical time node.

[0084] In step S200, the historical planning data refers to the project planning data for the planned construction project within the building land block, such as the location, purpose, area, and start and end time of the declared building. The first historical time node is the start time node of the planned project, and the second historical time node is the end time node of the planned project.

[0085] Determining at least one target planning time interval for the temporary construction land block based on the historical planning data specifically includes: determining the planning project of the temporary construction land block in the historical planning data, and using the start and end time of the planning project as the target planning time interval.

[0086] Step S300: Determine the geospatial change degree of the temporary construction land block according to the first historical geospatial data of the temporary construction land block at the first historical time node and the second historical geospatial data at the second historical time node.

[0087] Geospatial data refers to data associated with geographic spatial locations, which describes the characteristics, locations and relationships of spatial objects within the target city. Typically, geospatial data includes vector data, raster data and attribute data. Vector data consists of geometric objects such as points, lines, and surfaces, such as the boundaries of roads, rivers, administrative divisions, etc.; raster data uses pixels or grid cells as basic units; attribute data describes non-spatial information related to geospatial objects, such as land use type, purpose of buildings, etc. The first historical geospatial data and the second historical geospatial data of this embodiment mainly include vector data and attribute data of temporary building land blocks. Whether the spatial object in the temporary building land block is a temporary building is determined by vector data, and its land use type is determined based on attribute information.

[0088] Among them, the geospatial change degree of the temporary construction land block is determined based on the first historical geospatial data of the temporary construction land block at the first historical time node and the second historical geospatial data at the second historical time node, specifically including: determining the geospatial change degree between the first historical geospatial data and the second historical geospatial data according to a preset loss function.

[0089] The formula of the loss function is:

[0090]

[0091] Wherein, L is the degree of geospatial change between the first historical geospatial data and the second historical geospatial data; X is the first historical geospatial data; and Y is the second historical geospatial data.

[0092] Step S400: When the geographic space change degree is lower than a preset geographic space change threshold, determining whether the temporary building land block is an abnormal land block based on the historical remote sensing image of the target city at the second historical time node and the current remote sensing image.

[0093] Usually, temporary buildings will be demolished after the completion of their corresponding construction planning projects. However, due to their use value or ornamental value, some temporary buildings are not demolished, but are transformed into temporary buildings or semi-permanent buildings with extended periods. This embodiment can effectively identify temporary building land blocks where temporary buildings have not been demolished by comparing the geospatial change degree of the temporary building land blocks with a preset geospatial change threshold, and determine based on the historical remote sensing images and current remote sensing images of the temporary building land blocks that the reason why the temporary buildings have not been demolished is due to unconventional reasons (for example, a temporary factory is transformed into an exhibition hall for tourist check-ins, and a temporary hospital cabin is transformed into a sub-designated hospital), and mark the temporary building land blocks where the temporary buildings have not been demolished due to these unconventional reasons as abnormal land blocks.

[0094] The historical remote sensing image and the current remote sensing image include the temporary construction land block and a land block adjacent to the temporary construction land block; and determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image and the current remote sensing image of the target city at the second historical time node specifically includes:

[0095] Step S401: In the historical remote sensing image, taking the boundary line of the temporary construction land block as a reference, performing negative buffering processing on the temporary construction land block with a preset distance to obtain a negative buffer area, and performing masking processing on the negative buffer area to obtain a masked historical remote sensing image of the temporary construction land block;

[0096] In step S401, due to the dispersed nature of temporary structures, i.e., multiple related temporary building blocks exist within the same construction project, and these blocks are spatially spaced at a certain distance. By masking the negative buffer area in the masked historical remote sensing imagery, other land blocks between the related temporary building blocks and within the negative buffer area can be ablated.

[0097] Step S402: inputting the masked historical remote sensing image into a preset image restoration model for restoration, thereby obtaining a restored remote sensing image.

[0098] Step S403: When the similarity between the restored remote sensing image and the current remote sensing image is less than a preset similarity threshold, the temporary building land block is determined to be an abnormal land block.

[0099] In steps S402 and S403, when the temporary building blocks on both sides of the negative buffer region are associated, the image restoration model will also generate associated temporary building groups within the negative buffer region when restoring the obscured historical remote sensing image, thereby connecting the temporary building blocks on both sides. When the temporary building blocks on both sides of the negative buffer region are not associated, the image restoration model restores the image of the negative buffer region based on conventional reasons, so that the restored remote sensing image has a high degree of overlap with the current remote sensing image, that is, the similarity between the restored remote sensing image and the current remote sensing image is high. If the similarity between the restored remote sensing image and the current remote sensing image is low and less than a preset similarity threshold, the temporary building land block can be determined to be an abnormal land block.

[0100] Before inputting the masked historical remote sensing image into a preset image restoration model for restoration to obtain a restored remote sensing image, the method further includes: constructing an image restoration sample data set; the image restoration sample data set includes remote sensing images of multiple non-demolished temporary buildings at different time nodes and non-demolished planning information of the non-demolished temporary buildings; and training the image restoration model through a neural network model based on the image restoration sample data set.

[0101] The image restoration sample dataset contains remote sensing images of various temporary structures that have not been demolished at different time points, as well as information on their planned demolition. For example, tin sheds along the railway line have been used as power distribution rooms for railway inspection equipment, exhibition sheds have been converted into vegetable markets, and temporary fences have been reinforced with concrete to become semi-permanent fences.

[0102] Based on the image restoration sample data set, the image restoration model is trained by a neural network model, which can be achieved by the following method: dividing the image restoration sample data set into training samples and test samples according to a preset ratio; determining a primary restoration model based on the training samples, and generating an evaluation index based on the test samples; when the evaluation index is within the preset evaluation index range, determining that the primary prediction model is an image restoration model; if the evaluation index is not within the preset evaluation index range, returning to the process of dividing the ultrasound image sample data set into training samples and test samples according to the preset ratio.

[0103] The target variable is defined as "the difference between the restored remote sensing image and the remote sensing image at different time nodes", and the remote sensing image and the non-demolition planning information are used as feature variables to construct the objective function. The training samples are trained iteratively for multiple rounds through the classification model to generate a new objective function. Each round of iteration generates a new residual. The residual of the previous round of prediction is fitted in the new round of iteration to improve the accuracy of the neural network model, solve the optimal value of the final objective function, and train the neural network model based on the optimal value.

[0104] Step S500: When it is determined that the temporary construction land block is an abnormal land block, the temporary construction land block is subjected to association analysis with land blocks corresponding to the same land type as the temporary construction land block.

[0105] In step S500, after determining that the temporary construction land parcel is an anomalous land parcel, the geospatial data of the temporary construction land parcel is extracted to perform an association analysis on land parcels of the same land type as the temporary construction land parcel. This geospatial data includes multiple indicators, such as spatial distribution characteristics, temporal variation trends, attribute feature comparisons, and surrounding environmental impacts. Spatial distribution characteristics refer to the geographic distribution relationship between the anomalous land parcel and other normal land parcels of the same type, determining whether there is a clustered or dispersed pattern. Temporal variation trends compare changes at different points in time. Attribute feature comparisons refer to the differences in attribute information, such as building structure and usage, between the anomalous land parcel and other normal land parcels of the same type. Surrounding environmental impacts refer to the impact of environmental factors surrounding the anomalous land parcel, such as transportation conditions, infrastructure, and policy planning, on it, and are compared with the surrounding environmental impacts of other land parcels. If other land parcels of the same type share similar geospatial data with the anomalous land parcel, the attribute information of the temporary construction land parcel corresponding to the anomalous land parcel can be used as a reference for analysis of the same land type.

[0106] To sum up, in an urban land planning analysis method based on remote sensing images in this embodiment, by analyzing the current remote sensing images of the target city, the temporary building land blocks and the corresponding temporary building land types of the target city can be determined, and combined with the historical planning data and historical geographic spatial data of the temporary building land blocks, it can be determined whether the temporary building land blocks are land blocks where temporary buildings have not been demolished under abnormal circumstances, so that the attribute information of the temporary building land blocks marked as abnormal land blocks can be used as an analysis reference for the same land type.

[0107] This embodiment also provides a GIS-based urban land planning analysis system, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is used to be loaded by the processor and execute the above-mentioned urban land planning analysis method based on remote sensing images.

[0108] Based on the same inventive concept as the above embodiment, this embodiment also provides a computer-readable storage medium, which stores instructions for the processor to load and execute the above-mentioned urban land planning analysis method based on remote sensing images.

[0109] In the embodiments of the mobile terminal and computer-readable storage medium provided in this application, all technical features of the above-mentioned control method embodiments are included. The expanded and explained contents of the specification are basically the same as those of the above-mentioned method embodiments and will not be repeated here.

[0110] An embodiment of the present application further provides a computer program product, which includes computer program code. When the computer program code runs on a computer, the computer executes the methods in the various possible implementation modes described above.

[0111] An embodiment of the present application also provides a chip, including a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that a device equipped with the chip executes the methods in the various possible implementation modes as described above.

[0112] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0113] In this application, the same or similar terminology, technical solutions and / or application scenario descriptions are generally only described in detail the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of this application, for the same or similar terminology, technical solutions and / or application scenario descriptions that are not described in detail later, you can refer to the previous relevant detailed descriptions.

[0114] In this application, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0115] The various technical features of the technical solution of this application can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0116] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium as above, including a number of instructions for enabling a terminal device to execute the method of each embodiment of the present application. The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the content of the present application specification and drawings, or directly or indirectly used in other related technical fields, is similarly included in the scope of patent protection of the present application. It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0117] The foregoing description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed herein are intended to be encompassed within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for urban land planning analysis based on remote sensing images, characterized in that: include: Determining, based on a current remote sensing image of a target city, a temporary construction land block of the target city and a temporary construction land type of the temporary construction land block; Retrieving historical planning data of the temporary construction land block, and determining at least one target planning time interval of the temporary construction land block based on the historical planning data; The target planning time interval includes a time segment between a first historical time node and a second historical time node located after the first historical time node; Determining the geospatial change degree of the temporary construction land block based on first historical geospatial data of the temporary construction land block at the first historical time node and second historical geospatial data at the second historical time node; specifically comprising: determining the geospatial change degree between the first historical geospatial data and the second historical geospatial data based on a preset loss function; The formula of the loss function is: ; Where L is the degree of geospatial change between the first historical geospatial data and the second historical geospatial data; X is the first historical geospatial data; Y is the second historical geospatial data; When the geographic space change degree is lower than a preset geographic space change threshold, determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image of the target city at the second historical time node and the current remote sensing image; When it is determined that the temporary construction land block is an abnormal land block, the temporary construction land block is subjected to association analysis with land blocks corresponding to the same land type as the temporary construction land block.

2. The urban land planning analysis method based on remote sensing images according to claim 1 is characterized in that: The determining of the temporary construction land block and the land type of the temporary construction land block in the target city based on the current remote sensing image of the target city specifically includes: Assigning pixels of the current remote sensing image of the target city to preset land categories, and dividing the target city into a plurality of land units; the land categories include land cover categories and land use categories; Performing spatial analysis on each of the land units to determine attribute information corresponding to each of the land units and a first matching degree between the attribute information and a preset temporary building land attribute; Marking a land unit whose first matching degree exceeds a preset first matching degree threshold as a reference land unit, merging at least another adjacent land unit with the reference land unit as the center to generate a land block to be determined, and determining a second matching degree between the land block to be determined and the land attribute of the temporary building; The undetermined land block whose second matching degree exceeds the preset second matching degree threshold is marked as a temporary construction land block, and the temporary construction land type of the temporary construction land block is determined according to the land category of the land units contained in the temporary construction land block.

3. The urban land planning analysis method based on remote sensing images according to claim 2 is characterized in that: The allocating pixels of the current remote sensing image of the target city to preset land categories and dividing the target city into a plurality of land units specifically includes: Based on the spectral band corresponding to the preset land category, the current remote sensing image is subjected to spectral analysis, and pixels of the current remote sensing image that match the spectral analysis are assigned to the land category; Merge connected pixels belonging to the same land category into the same land unit.

4. The urban land planning analysis method based on remote sensing images according to claim 2 is characterized in that: The performing of spatial analysis on each of the land units to determine the attribute information corresponding to each of the land units specifically includes: extracting geometric features of each of the land units; Superimposing the land unit with a preset human factor layer based on the geometric features, and marking the land unit whose intersection area after superposition is greater than a preset intersection area threshold with a corresponding artificial structure label; Attribute information corresponding to each of the land units is determined based on the query index corresponding to the man-made structure tag.

5. The urban land planning analysis method based on remote sensing images according to claim 1 is characterized in that: The determining of at least one target planning time interval for the temporary construction land block based on the historical planning data specifically includes: The planning project of the temporary building land block in the historical planning data is determined, and the start and end times of the planning project are used as the target planning time interval.

6. The urban land planning analysis method based on remote sensing images according to any one of claims 1 to 5, characterized in that: The historical remote sensing image and the current remote sensing image include the temporary construction land block and a land block adjacent to the temporary construction land block; and determining whether the temporary construction land block is an abnormal land block based on the historical remote sensing image and the current remote sensing image of the target city at the second historical time node specifically includes: In the historical remote sensing image, taking the boundary line of the temporary construction land block as a reference, performing negative buffer processing on the temporary construction land block with a preset distance to obtain a negative buffer area, and performing masking processing on the negative buffer area to obtain a masked historical remote sensing image of the temporary construction land block; Inputting the masked historical remote sensing image into a preset image restoration model for restoration, thereby obtaining a restored remote sensing image; When the similarity between the restored remote sensing image and the current remote sensing image is less than a preset similarity threshold, the temporary building land block is determined to be an abnormal land block.

7. The urban land planning analysis method based on remote sensing images according to claim 6 is characterized in that: Before inputting the masked historical remote sensing image into a preset image restoration model for restoration to obtain a restored remote sensing image, the method further includes: Constructing an image restoration sample data set; the image restoration sample data set includes remote sensing images of multiple temporary buildings that have not been demolished at different time nodes and non-demolished planning information of the temporary buildings that have not been demolished; Based on the image restoration sample data set, the image restoration model is trained by a neural network model.

Images