A residential land building component analysis method, device and system

Abstract

The application relates to the technical field of remote sensing data analysis, and discloses a residential land building component analysis method, device and system. The residential land building component analysis method disclosed by the application takes a reference map as a reference, draws lessons from the concept of pixels in an image, divides the reference map into a plurality of pixel blocks, matches remote sensing data and the reference map, calculates remote sensing parameters (similar to pixel values) of each pixel block through the remote sensing data, sets a traversal strategy of N continuous pixel blocks, analyzes the distribution of the remote sensing parameters in the N continuous pixel blocks, and determines boundary pixel blocks. Through the above method, the boundary calculation of the building component of the residential land can be realized through more reliable remote sensing data, the boundary line of the building component in the residential land is more reliable, and finally, the analysis result of the building component of the residential land is more reliable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote sensing data analysis, and particularly relates to a residential land building component analysis method, device and system. BACKGROUND

[0002] Residential land includes different building components, including: traffic land, living land, industrial land, green land, water body, mountain, forest land, etc. Common analysis of residential land includes heat analysis, carbon emission analysis, land use analysis, pollution monitoring, vegetation analysis, heat island effect analysis, etc. The above analyses all need to analyze the building components of residential land to obtain the parameters of each building component on the residential land.

[0003] In the prior art, the boundary line is often determined based on the reference map itself, for example, the boundary line is directly determined by the standard map officially released, and then the traffic land, living land, industrial land, green land, water body, mountain, forest land, etc. are marked on the boundary map. Research has found that the existing analysis method of residential land building components has the problem of insufficient data reliability, for example, there is a discrepancy between the map data and the actual use of the residential land, or some building components on the residential land change over time. Therefore, it is necessary to improve the reliability of the analysis of residential land building components to obtain more reliable analysis results of residential land building components. SUMMARY

[0004] The present application provides a residential land building component analysis method, device and system, which can improve the reliability of the analysis of residential land building components to obtain more reliable analysis results of residential land building components.

[0005] The first aspect of the present application discloses a residential land building component analysis method, which comprises:

[0006] obtaining a reference map of the residential land to be analyzed, and dividing the reference map into a plurality of pixel blocks;

[0007] obtaining remote sensing data of the residential land to be analyzed, matching the remote sensing data and the reference map, calculating a remote sensing parameter value corresponding to each pixel block according to the remote sensing data, and the remote sensing parameter value is used to represent the quantized value of the remote sensing data in the pixel block;

[0008] traversing all the pixel blocks according to a preset traversal strategy, and for the continuous N pixel blocks in the traversal process: if it is judged that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to a preset boundary distribution rule, the position of the boundary pixel block is determined according to the distribution of the remote sensing parameter values, wherein the boundary pixel block represents the boundary of different building components in the residential land to be analyzed, and N is a preset positive integer;

[0009] According to the positions of the boundary pixel blocks, a boundary line in the reference map is determined, and different building components on the residential land are determined according to the boundary line.

[0010] As an optional implementation, in the first aspect of the present application, if it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule, the position of the boundary pixel block is determined according to the remote sensing parameter value distribution, including:

[0011] The remote sensing parameter value corresponding to each of the N pixel blocks is obtained, and the N remote sensing parameter values are fitted to obtain a remote sensing parameter distribution curve;

[0012] It is determined whether the remote sensing parameter distribution curve conforms to a preset boundary distribution curve line shape, and if it is determined that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule;

[0013] The position of the boundary pixel block is determined according to the remote sensing parameter distribution curve.

[0014] As an optional implementation, in the first aspect of the present application, the determination of whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape includes:

[0015] A plurality of non-boundary line segments are determined from the distribution curve, the length of the non-boundary line segment is greater than or equal to a preset length threshold, and the slope of the non-boundary line segment is less than a preset slope parameter; the remote sensing data weight of each non-boundary line segment is determined according to the remote sensing parameter of all pixel blocks in each non-boundary line segment, and the remote sensing data weight is used to represent the quantitative value of the remote sensing data of all pixel blocks in the corresponding non-boundary line segment;

[0016] If there is a non-boundary line segment at each end of the remote sensing parameter distribution curve, and the difference between the remote sensing data weights corresponding to the non-boundary line segments at the two ends exceeds a preset difference threshold, it is determined that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape.

[0017] As an optional implementation, in the first aspect of the present application, the determination of the position of the boundary pixel block according to the remote sensing parameter distribution curve includes:

[0018] If there is a non-boundary line segment at each end of the remote sensing parameter distribution curve, it is determined that the line segment between the non-boundary line segments at the two ends is a boundary line segment, and the position of the point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block.

[0019] As an optional implementation, in the first aspect of the present application, the calculating of the remote sensing parameter value corresponding to each pixel block according to the remote sensing data comprises:

[0020] calculating a remote sensing initial parameter value corresponding to each pixel block according to the remote sensing data;

[0021] For each pixel block, determining a plurality of pixel blocks within a preset range around the pixel block as reference pixel blocks; calculating an average value of the remote sensing initial parameter values of all the reference pixel blocks corresponding to the pixel block, and determining the average value as the remote sensing parameter value corresponding to the pixel block.

[0022] As an optional implementation, in the first aspect of the present application, the dividing of the reference map into a plurality of pixel blocks comprises:

[0023] obtaining the precision requirement of residential land building component analysis, determining the setting density of pixel blocks according to the precision requirement, and dividing the reference map into a plurality of pixel blocks based on the setting density.

[0024] As an optional implementation, in the first aspect of the present application, the method further comprises:

[0025] obtaining the scale of the reference map and the resolution of the remote sensing data;

[0026] determining the size of a positive integer N according to the scale and the resolution.

[0027] As an optional implementation, in the first aspect of the present application, the method further comprises:

[0028] updating the traversal strategy, and then retriggering the execution of traversing all the pixel blocks, and for the continuous N pixel blocks in the traversal process: if it is judged that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to a preset boundary distribution rule, then determining the position of the boundary pixel block according to the operation of the remote sensing parameter value distribution to obtain the position update value of all the boundary pixel blocks;

[0029] and the determining of the boundary line in the reference map according to the positions of all the boundary pixel blocks comprises:

[0030] determining the boundary line in the reference map according to the positions of all the boundary pixel blocks and the position update value of all the boundary pixel blocks.

[0031] The second aspect of the present application discloses a residential land building component analysis device, which comprises:

[0032] a pixel division module, configured to obtain a reference map of a residential land to be analyzed, and divide the reference map into a plurality of pixel blocks;

[0033] a remote sensing data processing module, configured to acquire remote sensing data of a residential land to be analyzed, match the remote sensing data and the reference map, and calculate a remote sensing parameter value corresponding to each pixel block according to the remote sensing data, the remote sensing parameter value being used to represent a quantized value of remote sensing data in the pixel block;

[0034] a boundary position determining module, configured to traverse all the pixel blocks according to a preset traversal strategy, and for N continuous pixel blocks in the traversal process: if it is judged that a remote sensing parameter value distribution corresponding to the N pixel blocks conforms to a preset boundary distribution rule, then the position of a boundary pixel block is determined according to the remote sensing parameter value distribution, wherein the boundary pixel block represents a boundary of different building components in the residential land to be analyzed, and N is a preset positive integer;

[0035] a boundary line determining module, configured to determine a boundary line in the reference map according to the positions of all the boundary pixel blocks, and determine different building components on the residential land according to the boundary line.

[0036] As an optional implementation form, in the second aspect of the present application, the specific operation mode of determining the position of the boundary pixel block according to the remote sensing parameter value distribution if it is judged that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule comprises:

[0037] acquiring a remote sensing parameter value corresponding to each pixel block in the N pixel blocks, fitting N remote sensing parameter values to obtain a remote sensing parameter distribution curve;

[0038] judging whether the remote sensing parameter distribution curve conforms to a preset boundary distribution curve line shape, and if it is judged that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, then it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule;

[0039] determining the position of the boundary pixel block according to the remote sensing parameter distribution curve.

[0040] As an optional implementation form, in the second aspect of the present application, the specific operation mode of the boundary position determining module judging whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape comprises:

[0041] determining a plurality of non-boundary line segments from the distribution curve, the length of the non-boundary line segment being greater than or equal to a preset length threshold, and the slope of the non-boundary line segment being less than a preset slope parameter; determining a remote sensing data weight of each non-boundary line segment according to the remote sensing parameter of all the pixel blocks in each non-boundary line segment, the remote sensing data weight being used to represent a quantized value of remote sensing data of all the pixel blocks in the corresponding non-boundary line segment;

[0042] If there are two non-boundary line segments at two ends of the remote sensing parameter distribution curve respectively, and the difference of the remote sensing data weight corresponding to the non-boundary line segments at the two ends exceeds a preset difference threshold, it is determined that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape.

[0043] As an optional implementation, in the second aspect of the present application, the specific operation mode of the boundary position determination module for determining the position of the boundary pixel block according to the remote sensing parameter distribution curve comprises:

[0044] If there are two non-boundary line segments at two ends of the remote sensing parameter distribution curve respectively, the line segment between the non-boundary line segments at the two ends is determined as a boundary line segment, and the position of the point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block.

[0045] As an optional implementation, in the second aspect of the present application, the specific operation mode of the remote sensing data processing module for calculating the remote sensing parameter value corresponding to each pixel block according to the remote sensing data comprises:

[0046] The remote sensing initial parameter value corresponding to each pixel block is calculated according to the remote sensing data.

[0047] For each pixel block, a plurality of pixel blocks within a preset range around the pixel block are determined as reference pixel blocks, the average of the remote sensing initial parameter values of all the reference pixel blocks corresponding to the pixel block is calculated, and the average is determined as the remote sensing parameter value corresponding to the pixel block.

[0048] As an optional implementation, in the second aspect of the present application, the specific operation mode of the pixel division module for dividing the reference map into a plurality of pixel blocks comprises:

[0049] The accuracy requirement of residential land building component analysis is obtained, the setting density of the pixel block is determined according to the accuracy requirement, and the reference map is divided into a plurality of pixel blocks based on the setting density.

[0050] As an optional implementation, in the second aspect of the present application, the device further comprises:

[0051] The traversal setting module is configured to obtain the scale of the reference map and obtain the resolution of the remote sensing data, and determine the size of the positive integer N according to the scale and the resolution.

[0052] As an optional implementation, in the second aspect of the present application, the device further comprises:

[0053] a boundary updating module, configured to update the traversal strategy, and then re-trigger the execution of the traversal of all the pixel blocks, for the N continuous pixel blocks in the traversal process: if it is judged that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to a preset boundary distribution rule, then the position of the boundary pixel block is determined according to the remote sensing parameter value distribution, and the position update value of all the boundary pixel blocks is obtained;

[0054] In addition, the boundary line determination module determines the specific operation mode of the boundary line in the reference map according to the positions of all the boundary pixel blocks, including:

[0055] The boundary line in the reference map is determined according to the positions of all the boundary pixel blocks and the position update values of all the boundary pixel blocks.

[0056] The third aspect of the present application discloses a residential land building component analysis system, the system comprising:

[0057] a memory storing executable program codes;

[0058] a processor coupled with the memory;

[0059] The processor invokes the executable program codes stored in the memory to execute part or all of the steps of the residential land building component analysis method of any one of the first aspect of the present application.

[0060] The fourth aspect of the present application discloses a computer storage medium storing computer instructions, which are invoked to execute part or all of the steps of the residential land building component analysis method of any one of the first aspect of the present application.

[0061] Compared with the prior art, the present application has the following beneficial effects:

[0062] The residential land building component analysis method disclosed in the embodiments of the present application takes the reference map as a reference, learns from the concept of pixels in an image, and divides the reference map into a plurality of pixel blocks. Then, through the matching of remote sensing data and the reference map, the remote sensing parameters (similar to pixel values) of each pixel block are calculated through the remote sensing data. Then, the traversal strategy of the continuous N pixel blocks is set, and in the N continuous pixel blocks, the boundary pixel blocks are determined by analyzing the distribution of the remote sensing parameters. Through the above method, the building component boundary calculation of the residential land can be realized through more reliable remote sensing data, so that more reliable boundary lines of the building components in the residential land are obtained, and finally more reliable analysis results of the residential land building components are obtained. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description only need to be some embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without any creative work based on the embodiments of the present application shall fall within the protection scope of the present application.

[0064] Figure 1 is a flowchart of a residential land building component analysis method disclosed by the embodiments of the present application;

[0065] Figure 2 is a pixel block division schematic diagram disclosed by the embodiments of the present application;

[0066] Figure 3 is a remote sensing parameter distribution schematic diagram disclosed by the embodiments of the present application;

[0067] Figure 4 is a remote sensing parameter distribution curve fitting and analysis diagram disclosed by the embodiments of the present application;

[0068] Figure 5 is another remote sensing parameter distribution curve fitting and analysis diagram disclosed by the embodiments of the present application;

[0069] Figure 6 is another flowchart of a residential land building component analysis method disclosed by the embodiments of the present application;

[0070] Figure 7 is a structural schematic diagram of a residential land building component analysis device disclosed by the embodiments of the present application;

[0071] Figure 8 is a structural schematic diagram of a residential land building component analysis system disclosed by the embodiments of the present application. DETAILED DESCRIPTION

[0072] In order to make the technical solutions in the embodiments of the present application clearer, the accompanying drawings needed in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description only need to be some embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without any creative work based on the embodiments of the present application shall fall within the protection scope of the present application.

[0073] The terms "first", "second", and the like in the description and in the claims of the present application and in the above drawings mean for distinguishing different objects, not for describing a particular sequential order. Moreover, the terms "comprises", "comprising", "has", "having", "includes", "including" and the like are to be construed open- ended, allowing for instances where there are equivalents. For instance, an element or step recited in a process, method, apparatus, product or the like can be encompassed by an equivalent thereof that is not specifically recited. All such equivalents are intended to be encompassed by the claims.

[0074] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all directed to the same embodiment, or to a common alternative embodiment. It is explicitly contemplated that embodiments described herein can be combined with each other.

[0075] The application discloses a residential land building component analysis method, device and system, which can improve the reliability of residential land building component analysis, thereby obtaining more reliable analysis results of residential land building components. The following will be described in detail.

[0076] Embodiment one

[0077] Please refer to Figure 1 , Figure 1 is a flowchart of a residential land building component analysis method disclosed by the embodiment of the application. In the method, Figure 1 The described residential land building component analysis method can be integrated in a residential land building component analysis device, and the residential land building component analysis early warning device can be integrated in a cloud server or a local server. As Figure 1 shown, the residential land building component analysis method can include the following operations:

[0078] Step 101, obtaining a reference map of a residential land to be analyzed, and dividing the reference map into a plurality of pixel blocks.

[0079] In the embodiment of the application, the reference map can be an official standard map of the residential land to be analyzed, or a map obtained by surveying or a map obtained by unmanned aerial vehicle shooting. The reference map includes different building components, including traffic land, residential land, industrial land, green land, water body, mountain, forest land and the like. Common analysis of residential land includes heat analysis, carbon emission analysis, land use analysis, pollution monitoring, vegetation analysis, heat island effect analysis and the like. The above analysis all need to analyze the building components of the residential land, so as to obtain the shape, area and accurate boundary of each building component on the residential land.

[0080] In the embodiment of the present application, the core of the building component analysis of residential land is to calculate the boundary lines of various building components on the reference map. In the prior art, the boundary line is often determined based on the reference map itself, for example, the boundary line is directly determined by the standard map officially released, and then the traffic land, residential land, industrial land, green land, water body, mountain, forest land, etc. are marked on the boundary map. The above method has the problem of insufficient data reliability, for example, there is a discrepancy between the map data and the actual use of the residential land, or some building components on the residential land change over time. In some other cases, the boundary line is accurately calculated, and the boundary accuracy on the map is low, which is difficult to meet the requirements. Therefore, the analysis of the building components of the residential land in the embodiment of the present application mainly depends on the calculation of the boundary line of the building components. For this purpose, the embodiment of the present application takes the reference map as the reference, and takes the data on the reference map as the reference data, and then calculates the boundary line based on the reference data. First, the embodiment of the present application divides the reference map into a plurality of pixel blocks, which is similar to that each image includes different pixel points in image processing. The pixel block in the embodiment of the present application can be a relatively small area, for example, an entire reference map is divided into A*B small squares, and each small square is a pixel block. As shown in Figure 2 , Figure 2 is a schematic diagram of a pixel block division method, Figure 2 In the embodiment of the present application, a part of a reference map is divided into 50*50 square grids, and each grid represents a pixel block.

[0081] The embodiment of the present application calculates the boundary line based on the pixel block, wherein the more the number of pixel blocks, the higher the accuracy, which is similar to that the higher the pixel of the picture, the clearer the image.

[0082] Step 102, acquiring remote sensing data of the residential land to be analyzed, matching the remote sensing data and the reference map, and calculating a remote sensing parameter value corresponding to each pixel block according to the remote sensing data.

[0083] In the embodiment of the present application, the remote sensing parameter value is used to represent the quantized value of the remote sensing data in the pixel block. Remote sensing data refers to data obtained from a distance by a non-contact method using a sensor (such as an optical or electronic device carried by a satellite, a drone, an airplane, etc.) to obtain information of the earth's surface or the atmosphere. These data can be images, spectral information, radar signals or other electromagnetic wave signals, which are used to analyze and understand the physical, chemical and biological characteristics of the earth's surface.

[0084] In the embodiment of the present application, the type of remote sensing data can include:

[0085] Optical remote sensing data:

[0086] Multispectral data: Records reflectance information of multiple bands (such as red light, near-infrared light, etc.), which can be used for land use classification, vegetation monitoring, etc.

[0087] Hyperspectral data: Contains more detailed spectral information, with a large number of bands and high spectral resolution, which can be used for fine feature identification and composition analysis.

[0088] Hyper-spectral data: Higher spectral resolution, more bands, can be used for complex environment monitoring and material composition analysis.

[0089] Radar remote sensing data:

[0090] Synthetic Aperture Radar (SAR) data: Using the reflection characteristics of radar waves, it can penetrate clouds and vegetation, obtain terrain information and feature structure of the ground, and can be used for topographic mapping, flood monitoring and vegetation penetration research.

[0091] Laser radar (LiDAR) data: Measures the height and terrain of the ground by laser pulses, generates high-precision digital elevation model (DEM), which can be used for urban modeling, forest structure analysis, etc.

[0092] Thermal infrared remote sensing data:

[0093] Records the thermal radiation information of the ground or atmosphere, which can be used to monitor ground temperature, urban heat island effect, volcanic activity, etc.

[0094] Microwave remote sensing data:

[0095] Using microwave band electromagnetic waves, it can penetrate clouds and vegetation, and can be used for soil moisture monitoring, glacier research, etc.

[0096] In the embodiment of the present application, the matching of remote sensing data and reference map includes one-to-one correspondence between the obtained remote sensing data and the position on the reference map, so that it is possible to calculate the boundary line with remote sensing data. The remote sensing parameter value is used to represent the quantized value of the remote sensing data in the pixel block, which is a number used to measure the overall numerical value of the remote sensing data in a pixel block. For example, for spectral data, the quantized value can be the frequency value with the largest proportion, for radar data, it can be the radar reflection signal strength value, and for infrared remote sensing data, it can be the overall infrared light intensity in the pixel block. As shown in Figure 3 , Figure 3 is an exemplary remote sensing parameter value distribution diagram, in which Figure 3 is the remote sensing parameter corresponding to each pixel block calculated according to the near-infrared spectral data. As can be seen from the figure, the remote sensing parameter corresponding to the pixel block on the industrial land is higher than that corresponding to the pixel block on the green land, and the remote sensing parameter at the boundary line is between the two and fluctuates.

[0097] In the embodiment of the present application, different building components correspond to different remote sensing data, for example, remote sensing data of industrial land and green land are different, and correspondingly, remote sensing parameters corresponding to different building components in the pixel blocks are also different. The present application measures different building components by remote sensing parameters, thereby facilitating subsequent division of boundary lines of different building components by remote sensing data.

[0098] In step 103, all pixel blocks are traversed according to a preset traversal strategy, and for N continuous pixel blocks in the traversal process: if it is judged that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule, the position of the boundary pixel block is determined according to the remote sensing parameter value distribution.

[0099] In the embodiment of the present application, the boundary pixel block represents the boundary of different building components in the residential land to be analyzed; N is a preset positive integer. The specific value of N can be set according to the specific situation, or set according to the required accuracy. For the setting of N, it should also be noted that for the area where the remote sensing parameter changes greatly, it is not necessarily a boundary area, but also may be data fluctuation at different positions in a certain area, for example, islands on water bodies, factory roofs in industrial land, small area lawns in residential land, etc. Therefore, the present application traverses N pixel blocks at a time, which can filter out the "interference items" of non-boundary areas by setting the value of N.

[0100] The embodiment of the present application finds that the boundary line of different building components on the residential land has the following characteristics: for the boundary line pixel block, the remote sensing parameter distribution of the pixel block on the left side (relatively speaking) fluctuates slightly, the remote sensing parameter distribution of the pixel block on the right side (relatively speaking) fluctuates slightly, and the difference between the remote sensing parameters of the pixel block on the left side and the pixel block on the right side exceeds a certain threshold. For example, N is 20, the remote sensing parameters of the leftmost 8 pixel blocks in the 20 pixel blocks are between 5.5-6.3, the remote sensing parameters of the rightmost 7 pixel blocks are between 10.6-11.8, and the remote sensing parameters of the middle 5 pixel blocks fluctuate greatly, and the overall value is between 5.5-11.8. Therefore, the boundary pixel block can be determined according to the remote sensing parameter value distribution of the N pixel blocks, and the boundary pixel block can be one or more.

[0101] Therefore, the embodiment of the present application finds that for the boundary line of different building components, the remote sensing data parameters in the pixel blocks will have corresponding change rules near the boundary line, which can be obtained by analyzing a large amount of remote sensing data, and then the rule is set as the preset boundary distribution rule. The distribution rule can be the change trend of the remote sensing parameter, the change trend of the slope of the remote sensing parameter, the scatter plot of the remote sensing parameter or the distribution curve of the remote sensing parameter.

[0102] In the embodiment of the present application, whether the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution rule can be determined by determining whether one or more of the following conforms to the preset boundary distribution rule: a change trend of the remote sensing parameter values corresponding to the N pixel blocks, a change trend of the slope of the remote sensing parameter, a scatter plot of the remote sensing parameter, or a distribution curve of the remote sensing parameter.

[0103] In the embodiment of the present application, if it is determined that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution rule, it is indicated that the boundary pixel block exists in the current N pixel blocks. At this time, the position of the boundary pixel block can be determined according to the distribution of the remote sensing parameter values, for example, the pixel block with the most drastic change in the remote sensing parameter value (for example, the maximum slope) can be determined as the boundary pixel block, the middle pixel block in the N pixel blocks can be directly selected as the boundary pixel block, or the position of the boundary pixel block can be preset in the preset boundary distribution rule, and once it is determined that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution rule, the position of the boundary pixel block is obtained. Alternatively, a special artificial intelligence model can be trained, the distribution of the remote sensing parameter values corresponding to the N pixel blocks is analyzed by the model, and then the boundary pixel block is extracted.

[0104] In the embodiment of the present application, each pixel block is taken as a starting point, and the N-1 pixel blocks behind the starting point are combined with the starting point to form N pixel blocks for processing. The traversal strategy can be to traverse each pixel block from left to right and from top to bottom. For the right edge position, when the number of pixel blocks behind the traversed pixel block is less than N-1, the traversal of the pixel block is cancelled.

[0105] In step 104, the positions of all the boundary pixel blocks are determined, the boundary line in the reference map is determined according to the positions of the boundary pixel blocks, and different building components on the residential land are determined according to the boundary line.

[0106] In the embodiment of the present application, after all the boundary pixel blocks are obtained, the boundary line can be obtained through all the boundary pixel blocks, for example, the boundary line can be obtained by connecting all the boundary pixel blocks. Optionally, fitting and screening steps can be performed in the connecting process to make the boundary line smoother and more reasonable. Finally, the embodiment of the present application can draw the boundary line between different building components on the reference map, so as to determine different building components on the residential land.

[0107] The building component analysis method for residential land disclosed in the embodiment of the present application takes a reference map as a reference, learns from the concept of pixels in an image, and divides the reference map into a plurality of pixel blocks. Then, through matching of remote sensing data and the reference map, the remote sensing parameters (similar to pixel values) of each pixel block are calculated through remote sensing data. Then, a traversal strategy of N continuous pixel blocks is set. In the N continuous pixel blocks, the boundary pixel block is determined by analyzing the distribution of the remote sensing parameters. Through the above method, the boundary calculation of the building component of the residential land can be realized through the remote sensing data with higher reliability, so that the boundary line of the building component in the residential land is obtained more reliably, and finally the analysis result of the building component of the residential land is obtained more reliably.

[0108] In an optional embodiment, if it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule, the position of the boundary pixel block can be determined according to the remote sensing parameter value distribution, which can include:

[0109] Obtaining the remote sensing parameter value corresponding to each pixel block in the N pixel blocks, fitting the N remote sensing parameter values to obtain a remote sensing parameter distribution curve;

[0110] Determining whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape. If it is determined that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to the preset boundary distribution rule;

[0111] Determining the position of the boundary pixel block according to the remote sensing parameter distribution curve.

[0112] In the embodiment of the present application, the description of the remote sensing parameter value distribution corresponding to the N pixel blocks is realized in a curve fitting manner, for example, as shown in Figure 4 or Figure 5 It is set that N is 12, 12 continuous pixel blocks are set, the pixel block position is taken as the horizontal coordinate, and the remote sensing parameter corresponding to the pixel block is taken as the vertical coordinate to fit the remote sensing parameter distribution curve corresponding to the N remote sensing parameter values.

[0113] In the embodiment of the present application, the boundary of different building components has special remote sensing data distribution characteristics, for example, from a relatively stable remote sensing parameter to another relatively stable remote sensing parameter, and there is a transition interval of a remote sensing parameter fluctuation. Therefore, only the rule of the boundary distribution curve needs to be analyzed in advance and preset as the boundary distribution curve line shape. Then, whether the N pixel blocks correspond to the boundary pixel block is determined by judging whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape. When it is determined that the boundary pixel block exists, the position of the boundary pixel block is determined according to the remote sensing parameter distribution curve.

[0114] In this embodiment of the invention, optionally, the position of the boundary pixel block is determined according to the remote sensing parameter distribution curve. The actual position of the boundary pixel block can be determined based on a preset reference point for the boundary pixel block position within the boundary distribution curve. For example, the position of the midpoint can be directly selected as the position of the boundary pixel block. In this embodiment of the invention, the position of the boundary pixel block does not refer to a specific pixel block being designated as the boundary pixel block and then its position defined. Instead, a position is determined based on the remote sensing parameter distribution curve, and this position may be between two pixel blocks.

[0115] This optional embodiment predetermines the shape of the boundary distribution curve through curve fitting, thereby enabling the quick and efficient execution of the judgment operation on the existence of boundary pixel blocks.

[0116] In this optional embodiment, further optionally, determining whether the remote sensing parameter distribution curve conforms to a preset boundary distribution curve shape based on the remote sensing data distribution characteristics of the boundaries of different building components discovered in the embodiments of the present invention may include:

[0117] Multiple non-boundary line segments are identified from the distribution curve. The length of the non-boundary line segments is greater than or equal to a preset length threshold, and the slope of the non-boundary line segments is less than a preset slope parameter. Based on the remote sensing parameters of all pixel blocks within each non-boundary line segment, the remote sensing data weight of each non-boundary line segment is determined. The remote sensing data weight is used to represent the quantized value of the remote sensing data of all pixel blocks within the corresponding non-boundary line segment.

[0118] If there is a non-boundary line segment at each end of the remote sensing parameter distribution curve, and the difference in the weights of the remote sensing data corresponding to the non-boundary line segments at both ends exceeds a preset difference threshold, then the remote sensing parameter distribution curve is judged to conform to the preset boundary distribution curve shape.

[0119] In this optional embodiment, such as Figure 4 or Figure 5 As shown, the length of the non-boundary line segment is greater than or equal to a preset length threshold, such as 5 pixel blocks. This sufficient distance prevents local factors related to residential areas from affecting the determination of boundary pixel blocks. The slope of the non-boundary line segment is less than a preset slope parameter, thus conforming to the characteristic of a relatively stable remote sensing parameter distribution, indicating that the pixel blocks within the non-boundary line segment all belong to the same building component. For example... Figure 4 or Figure 5 As shown, the entire remote sensing parameter distribution curve can be divided into three parts: the non-boundary line segments at the leftmost and rightmost ends and the boundary line segments in the middle part. Among them, the boundary pixel block is located on the boundary line segment, which can be a real pixel block or a virtual pixel block between two real pixel blocks.

[0120] In the optional embodiment, further optionally, determining the position of the boundary pixel block according to the remote sensing parameter distribution curve can comprise:

[0121] If there are two non-boundary line segments at the two ends of the remote sensing parameter distribution curve, a line segment between the two non-boundary line segments at the two ends is determined as a boundary line segment, and the position of a point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block.

[0122] In the optional embodiment, the position with the maximum absolute value of the slope is determined as the position of the boundary. The optional embodiment finds that when a building component transitions from one type to another type, the change of the remote sensing data at the boundary line is the most steep, that is, the absolute value of the slope is the largest.

[0123] In the optional embodiment, a more reasonable method for determining the position of the boundary pixel block is designed according to the remote sensing data distribution characteristics of the boundary of different building components. If there are two non-boundary line segments at the two ends of the remote sensing parameter distribution curve, and the difference between the remote sensing data weights corresponding to the two non-boundary line segments at the two ends exceeds a preset difference threshold, it is determined that there is a boundary pixel block, then a line segment between the two non-boundary line segments at the two ends is determined as a boundary line segment, and the position of a point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block. Through the above method, a more reasonable and accurate boundary position can be obtained under the premise of being more consistent with the distribution law of the boundary position.

[0124] Embodiment Two

[0125] Please refer to Figure 6 , Figure 6 is a flowchart of another residential land building component analysis method disclosed by the embodiment of the application. Among them, Figure 6 The described residential land building component analysis method can be integrated in a residential land building component analysis device, and the residential land building component analysis early warning device can be integrated in a cloud server or a local server. As Figure 6 shown, the residential land building component analysis method can comprise the following operations:

[0126] Step 201, obtaining a reference map of the residential land to be analyzed, and dividing the reference map into a plurality of pixel blocks.

[0127] Step 202, obtaining remote sensing data of the residential land to be analyzed, and matching the remote sensing data and the reference map.

[0128] For the description of steps 201-202, please refer to the description of steps 101-102 in the embodiment one of the application, which will not be described here.

[0129] Step 203, calculating a remote sensing initial parameter value corresponding to each pixel block according to the remote sensing data.

[0130] Step 204, for each pixel block, determining a plurality of pixel blocks within a preset range around the pixel block as reference pixel blocks; calculating an average value of the remote sensing initial parameter values of all the reference pixel blocks corresponding to the pixel block, and determining the average value as the remote sensing parameter value corresponding to the pixel block.

[0131] In the embodiment of the present application, instead of directly calculating the remote sensing parameter corresponding to each pixel block through remote sensing data, an initial remote sensing parameter is first calculated, and the calculation method of the initial remote sensing parameter can be the same as the calculation method of the remote sensing parameter in the first embodiment of the present application.

[0132] It is found in the embodiment of the present application that if the remote sensing parameter corresponding to each pixel block is directly calculated through remote sensing data, the entire reference map is not smooth enough, that is, the local variation (position of remote sensing data mutation) existing in the remote sensing data will be directly reflected through the corresponding pixel block. For example, there is a green part in a certain small area, and the corresponding remote sensing data of the green part is different from that of other parts of the small area. If the remote sensing parameter of the pixel block of the green part is directly calculated, it will also be different from the remote sensing parameters of other parts. Therefore, the remote sensing data of the surrounding part of the green part will be used to recalculate the remote sensing parameter, so as to prevent the green part from being identified as a boundary in the subsequent process.

[0133] In the embodiment of the present application, the average value of the remote sensing initial parameter values of all the reference pixel blocks corresponding to the pixel block is calculated, and the average value is determined as the remote sensing parameter value corresponding to the pixel block. In the above example, the number of pixel blocks in the green part is not large, and the remote sensing parameter value corresponding to the pixel blocks in the green part is replaced by the average value of the surrounding pixel blocks. In this way, the pixel blocks in the green part will not suddenly fluctuate, and will not affect the subsequent boundary identification operation. It should be particularly noted that the preset range around the pixel block will be designed according to the specific operation needs. For a real boundary, such as the boundary between industrial land and water body, since the areas on both sides of the boundary are large enough, even if the average value is used as the remote sensing parameter as described above, it will not affect the determination of the boundary, but will filter out the influencing factors near the boundary, thereby improving the accuracy of the determination of the boundary.

[0134] Step 205, traversing all the pixel blocks according to a preset traversal strategy, and for N continuous pixel blocks in the traversal process: if it is judged that the distribution of the remote sensing parameter values corresponding to the N pixel blocks indicates that there is a boundary pixel block in the N pixel blocks, the position of the boundary pixel block is determined.

[0135] Step 206, determining the boundary line in the reference map according to the positions of all the boundary pixel blocks, and determining different building components on the residential land according to the boundary line.

[0136] As to the description of steps 205-206, refer to the description of steps 103-104 in the first embodiment of the application, and the second embodiment of the application will not be described herein.

[0137] It can be seen that the building component analysis method for residential land disclosed by the embodiments of the application takes the reference map as a reference, divides the reference map into a plurality of pixel blocks by referring to the concept of pixels in an image, calculates the remote sensing initial parameters (similar to pixel values) of each pixel block through the matching of the remote sensing data and the reference map, and then sets the average value of the remote sensing initial parameters of the pixel blocks in the set range around each pixel block as the remote sensing parameter of each pixel block, so as to filter out the dramatic change noise points at the non-boundary of the remote sensing data and improve the reliability of the data. Then, the traversal strategy of the continuous N pixel blocks is set, and the boundary pixel blocks are determined by analyzing the distribution of the remote sensing parameters in the N continuous pixel blocks. Through the above method, the building component boundary of the residential land can be calculated by using the remote sensing data with higher reliability, so that the boundary line of the building component in the residential land is obtained more reliably, and finally the analysis result of the building component of the residential land is obtained more reliably.

[0138] In an optional embodiment, the reference map is divided into a plurality of pixel blocks, including:

[0139] The accuracy requirement of the building component analysis of the residential land is obtained, the setting density of the pixel blocks is determined according to the accuracy requirement, and the reference map is divided into a plurality of pixel blocks based on the setting density.

[0140] The embodiments of the application realize the calculation of the boundary line based on the pixel blocks, wherein the more the number of the pixel blocks is, the higher the accuracy is, and similarly, the higher the pixel of the image is, the clearer the image is. Correspondingly, the higher the accuracy requirement of the building component analysis of the residential land is, the higher the pixel block density is. Meanwhile, the higher the pixel block density is, the larger the subsequent calculation amount is, and therefore, the optional embodiment flexibly sets the density of the pixel blocks according to the accuracy requirement, and when the accuracy requirement is low, the pixel blocks with low density are set, which is beneficial to the saving of the calculation amount.

[0141] In another optional embodiment, the method can further include:

[0142] The scale of the reference map is obtained, the resolution of the remote sensing data is obtained, the size of the positive integer N is determined according to the scale and the resolution.

[0143] In the optional embodiment, the positive integer N affects the traversal process and finally affects the judgment of the boundary, and the value of N should be set in accordance with the distribution law of the building component boundary. If N is too small, a large number of sub-building components in the same building component may be calculated as the boundary of other building components. If N is too large, it may be directly impossible to identify smaller other building components. For example, for a small lake on residential land, if N is too large, it is very likely that the boundary between other parts and the water body cannot be identified. At the same time, the setting of N is also related to the scale of the reference map and the resolution of the remote sensing data. The corresponding relationship between the scale and the resolution and N can be preset, so that the size of the positive integer N is determined according to the scale and the resolution.

[0144] In another optional embodiment, the method can further include:

[0145] updating the traversal strategy, and then retriggering the execution of the traversal of all the pixel blocks, and for the continuous N pixel blocks in the traversal process: if it is judged that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution law, then the operation of determining the position of the boundary pixel block according to the distribution of the remote sensing parameter values is performed to obtain the position update value of all the boundary pixel blocks;

[0146] and determining the boundary line in the reference map according to the positions of all the boundary pixel blocks can include:

[0147] determining the boundary line in the reference map according to the positions of all the boundary pixel blocks and the position update values of all the boundary pixel blocks.

[0148] In the optional embodiment, different convenience strategies affect the judgment of the boundary position, but different convenience strategies can complement each other for reference, so as to obtain a more accurate convenience strategy. For example, if the traversal method from left to right is used, it is difficult to identify the horizontal boundary line. At this time, if the traversal strategy from top to bottom is used, the deficiency that the horizontal boundary line is difficult to identify can be made up. Therefore, the optional embodiment updates the traversal strategy again on the basis of the original scheme, and then re-traverses to obtain the position update value of all the boundary pixel blocks. Finally, the boundary line in the reference map is determined according to the positions of all the boundary pixel blocks and the position update values of all the boundary pixel blocks. Thus, the accuracy of boundary identification is further improved.

[0149] Embodiment three

[0150] The embodiment of the application discloses a residential land building component analysis device, as shown in the figure, which can include: Figure 7

[0151] The pixel division module 301 is configured to obtain a reference map of a residential land to be analyzed, and divide the reference map into a plurality of pixel blocks.

[0152] ​The remote sensing data processing module 302 is configured to acquire remote sensing data of the residential land to be analyzed, match the remote sensing data and a reference map, and calculate a remote sensing parameter value corresponding to each pixel block according to the remote sensing data, where the remote sensing parameter value is used to represent a quantized value of the remote sensing data in the pixel block.

[0153] The boundary position determination module 303 is configured to traverse all the pixel blocks according to a preset traversal strategy, and for N continuous pixel blocks in the traversal process: if it is determined that a distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to a preset boundary distribution rule, the position of a boundary pixel block is determined according to the distribution of the remote sensing parameter values, where the boundary pixel block represents a boundary of different building components in the residential land to be analyzed, and N is a preset positive integer.

[0154] The boundary line determination module 304 is configured to determine a boundary line in the reference map according to the positions of all the boundary pixel blocks, and determine different building components on the residential land according to the boundary line.

[0155] In an optional embodiment, the boundary position determination module 303 determines the position of the boundary pixel block according to the distribution of the remote sensing parameter values when it is determined that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution rule, and the specific operation mode includes:

[0156] The remote sensing parameter value corresponding to each of the N pixel blocks is acquired, and a remote sensing parameter distribution curve is fitted from the N remote sensing parameter values.

[0157] It is determined whether the remote sensing parameter distribution curve conforms to a preset boundary distribution curve line shape, and if it is determined that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, it is determined that the distribution of the remote sensing parameter values corresponding to the N pixel blocks conforms to the preset boundary distribution rule.

[0158] The position of the boundary pixel block is determined according to the remote sensing parameter distribution curve.

[0159] In another optional embodiment, the specific operation mode of the boundary position determination module 303 for determining whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape includes:

[0160] A plurality of non-boundary line segments are determined from the distribution curve, the length of the non-boundary line segment is greater than or equal to a preset length threshold, and the slope of the non-boundary line segment is less than a preset slope parameter; a remote sensing data weight of each non-boundary line segment is determined according to the remote sensing parameter of all the pixel blocks in each non-boundary line segment, where the remote sensing data weight is used to represent a quantized value of the remote sensing data of all the pixel blocks in the corresponding non-boundary line segment.

[0161] If there are two non-boundary line segments at two ends of the remote sensing parameter distribution curve, and the difference of the remote sensing data weight corresponding to the non-boundary line segments at the two ends exceeds a preset difference threshold, it is determined that the remote sensing parameter distribution curve meets the preset boundary distribution curve line shape.

[0162] In yet another optional embodiment, the boundary position determination module 303 determines the position of the boundary pixel block according to the remote sensing parameter distribution curve in the following specific manner:

[0163] If there are two non-boundary line segments at two ends of the remote sensing parameter distribution curve, the line segment between the non-boundary line segments at the two ends is determined as the boundary line segment, and the position of the point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block.

[0164] In yet another optional embodiment, the remote sensing data processing module 302 calculates the remote sensing parameter value corresponding to each pixel block according to the remote sensing data in the following specific manner:

[0165] The remote sensing initial parameter value corresponding to each pixel block is calculated according to the remote sensing data.

[0166] For each pixel block, a plurality of pixel blocks within a preset range around the pixel block are determined as reference pixel blocks; the average value of the remote sensing initial parameter values of all reference pixel blocks corresponding to the pixel block is calculated, and the average value is determined as the remote sensing parameter value corresponding to the pixel block.

[0167] In yet another optional embodiment, the pixel division module 301 divides the reference map into a plurality of pixel blocks in the following specific manner:

[0168] The accuracy requirement of residential land building component analysis is obtained, the setting density of the pixel block is determined according to the accuracy requirement, and the reference map is divided into a plurality of pixel blocks based on the setting density.

[0169] In yet another optional embodiment, the device further comprises:

[0170] The traversal setting module is configured to obtain the scale of the reference map and the resolution of the remote sensing data; and the size of the positive integer N is determined according to the scale and the resolution.

[0171] In yet another optional embodiment, the device further comprises:

[0172] The boundary updating module is configured to update the traversal strategy, and then re-trigger the execution of the traversal of all pixel blocks; for the continuous N pixel blocks in the traversal process: if it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks meets the preset boundary distribution rule, the position of the boundary pixel block is determined according to the remote sensing parameter value distribution, and the position updating value of all boundary pixel blocks is obtained.

[0173] And the boundary line determination module 304 determines the specific operation mode of the boundary line in the reference map according to the positions of all the boundary pixel blocks, including:

[0174] The boundary line in the reference map is determined according to the positions of all the boundary pixel blocks and the position update values of all the boundary pixel blocks.

[0175] Embodiment four

[0176] Please refer to Figure 8 , Figure 8 is a structural schematic diagram of a residential land building component analysis system disclosed by an embodiment of the application. The residential land building component analysis system can include:

[0177] The memory 401 stores executable program codes;

[0178] The processor 402 is coupled with the memory 401;

[0179] The processor 402 invokes the executable program codes stored in the memory 401 to execute part or all of the steps of any one of the residential land building component analysis methods in the embodiment one or the embodiment two of the application.

[0180] The device embodiments described above are only schematic, wherein the modules illustrated as separate components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, i.e., can be located in one place or distributed on multiple network modules. Part or all of the modules can be selected to achieve the purposes of the embodiment schemes according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0181] Those skilled in the art can clearly understand the technical solutions of the various embodiments through the above specific description of the embodiments, and the various embodiments can be realized by means of software and necessary universal hardware platforms, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in terms of contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, which includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically-Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM), or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to carry or store computer readable instructions.

[0182] Finally, it should be noted that: the above-mentioned embodiments disclosed only the preferred embodiments of the present application, only for the description of the technical solutions of the present application, and not limited; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand; it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A residential land building component analysis method characterized by, The method comprises: acquiring a reference map of a residential land to be analyzed, and dividing the reference map into a plurality of pixel blocks; acquiring remote sensing data of the residential land to be analyzed, matching the remote sensing data and the reference map, and calculating a remote sensing parameter value corresponding to each of the pixel blocks according to the remote sensing data, the remote sensing parameter value being used to represent a quantized value of the remote sensing data in the pixel block; traversing all the pixel blocks according to a preset traversal strategy, and for N continuous pixel blocks in the traversal process: acquiring a remote sensing parameter value corresponding to each of the N pixel blocks, fitting the N remote sensing parameter values to obtain a remote sensing parameter distribution curve; judging whether the remote sensing parameter distribution curve conforms to a preset boundary distribution curve line shape, and if it is judged that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, it is determined that the remote sensing parameter value distribution corresponding to the N pixel blocks conforms to a preset boundary distribution rule; determining a position of a boundary pixel block according to the remote sensing parameter distribution curve, wherein the boundary pixel block represents a boundary of different building components in the residential land to be analyzed, and N is a preset positive integer; determining a boundary line in the reference map according to the positions of all the boundary pixel blocks, and determining different building components on the residential land according to the boundary line.

2. The residential land building component analysis method according to claim 1, characterized by, The judgment of whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape comprises: determining a plurality of non-boundary line segments from the distribution curve, the length of the non-boundary line segment being greater than or equal to a preset length threshold, and the slope of the non-boundary line segment being less than a preset slope parameter; determining a remote sensing data weight of each non-boundary line segment according to the remote sensing parameters of all the pixel blocks in each non-boundary line segment, the remote sensing data weight being used to represent the quantized value of the remote sensing data of all the pixel blocks in the corresponding non-boundary line segment; if there is one non-boundary line segment at each end of the remote sensing parameter distribution curve, and the difference between the remote sensing data weights of the non-boundary line segments at the two ends exceeds a preset difference threshold, it is judged that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape.

3. The residential land parcel building component analysis method according to claim 1, wherein, The determination of the position of the boundary pixel block according to the remote sensing parameter distribution curve comprises: if there is one non-boundary line segment at each end of the remote sensing parameter distribution curve, it is determined that a line segment in the middle of the non-boundary line segments at the two ends is a boundary line segment, and the position of a point with the maximum absolute value of the slope on the boundary line segment is determined as the position of the boundary pixel block.

4. The residential land parcel building component analysis method according to claim 1, wherein, The calculation of the remote sensing parameter value corresponding to each of the pixel blocks according to the remote sensing data comprises: calculating a remote sensing initial parameter value corresponding to each of the pixel blocks according to the remote sensing data; for each pixel block, determining a plurality of pixel blocks within a preset range around the pixel block as reference pixel blocks, calculating an average value of the remote sensing initial parameter values of all the reference pixel blocks corresponding to the pixel block, and determining the average value as the remote sensing parameter value corresponding to the pixel block.

5. The residential land building component analysis method according to claim 4, characterized by, The division of the reference map into a plurality of pixel blocks comprises: The precision requirement of the building component analysis of the residential land is obtained, the setting density of the pixel block is determined according to the precision requirement, and the reference map is divided into a plurality of pixel blocks based on the setting density.

6. The residential land parcel building component analysis method according to any one of claims 1-5, wherein, The method further comprises: The scale of the reference map is obtained, and the resolution of the remote sensing data is obtained. The size of the positive integer N is determined according to the scale and the resolution.

7. The residential land parcel building component analysis method according to any one of claims 1 to 5, characterized by, The method further comprises: The traversal strategy is updated, and then the execution of traversing all the pixel blocks is retriggered. For the N continuous pixel blocks in the traversal process: the remote sensing parameter value corresponding to each pixel block in the N pixel blocks is obtained, and the remote sensing parameter distribution curve is fitted by the N remote sensing parameter values. If it is judged that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, the position of the boundary pixel block is determined according to the remote sensing parameter distribution curve, and the position update value of all the boundary pixel blocks is obtained. And, the boundary line in the reference map is determined according to the position of all the boundary pixel blocks, comprising: The boundary line in the reference map is determined according to the position of all the boundary pixel blocks and the position update value of all the boundary pixel blocks.

8. A device for analyzing the building components of residential land, characterized in that, The device comprises: A pixel division module is configured to obtain a reference map of a residential land to be analyzed, and divide the reference map into a plurality of pixel blocks. A remote sensing data processing module is configured to obtain remote sensing data of the residential land to be analyzed, match the remote sensing data and the reference map, and calculate a remote sensing parameter value corresponding to each pixel block according to the remote sensing data. The remote sensing parameter value is used to represent a quantitative value of the remote sensing data in the pixel block. A boundary position determination module is configured to traverse all the pixel blocks according to a preset traversal strategy. For the N continuous pixel blocks in the traversal process: the remote sensing parameter value corresponding to each pixel block in the N pixel blocks is obtained, and the remote sensing parameter distribution curve is fitted by the N remote sensing parameter values. It is judged whether the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape. If it is judged that the remote sensing parameter distribution curve conforms to the preset boundary distribution curve line shape, it is determined that the remote sensing parameter value distribution of the N pixel blocks conforms to the preset boundary distribution rule. The position of the boundary pixel block is determined according to the remote sensing parameter distribution curve, wherein the boundary pixel block represents the boundary of different building components in the residential land to be analyzed, and N is a preset positive integer. A boundary line determination module is configured to determine the boundary line in the reference map according to the position of all the boundary pixel blocks, and determine different building components on the residential land according to the boundary line.

9. A residential land building component analysis system characterized by, The system comprises a memory storing executable program codes, a processor coupled with the memory, and the processor invokes the executable program codes stored in the memory to execute the residential land building component analysis method according to any one of claims 1-7.

Images