A method for classifying and extracting information on changes in individual buildings based on spatial relationship features.

By using a model library based on spatial relationship characteristics and automated analysis methods, the accuracy problem of individual building change analysis in existing technologies has been solved, and automated and rapid identification of individual building changes has been achieved.

CN116860902BActive Publication Date: 2026-04-03BEIJING INSTITUTE OF SURVEYING AND MAPPING
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-07-18
Publication Date
2026-04-03

AI Technical Summary

Technical Problem

In existing technologies, the methods for analyzing the increase or decrease of individual buildings mainly rely on manual identification, which makes it difficult to achieve a scientific, accurate, and unified reflection of the actual changes in individual buildings in the research area.

Method used

By acquiring vector data of individual buildings, a model library based on spatial relationship characteristics is established. Using spatial overlay analysis and calculation, the types of changes to individual buildings are automatically identified, including new additions, demolitions, renovations, expansions, and non-real changes.

Benefits of technology

It enables machines to automatically and quickly identify the types of changes in individual buildings, improving the scientific rigor and accuracy of the analysis and reducing reliance on manual labeling.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116860902B_ABST
    Figure CN116860902B_ABST
Patent Text Reader

Abstract

This invention discloses a method for classifying and extracting information on changes in individual buildings based on spatial relationship characteristics. The specific steps are as follows: S1. Obtain vector data of individual buildings through manual collection. The vector data of individual buildings includes vector data of individual buildings in two periods within the scope. S2. Based on the spatial form characteristics of each change cycle of an individual building, S3. Construct a model library. S4. Import the basic data into the model library for calculation and classification. S5. Output the calculation results. This invention first determines the classification criteria for changes in individual buildings, then establishes a model library, imports models designed for different spatial relationship characteristics generated by various changes in individual buildings into the model library, and then imports the basic data into the model library for calculation to obtain the change classification of each individual building. The change classification label of each individual building is used to determine which change type the specific individual building belongs to, which facilitates automatic and rapid machine identification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of building information statistics technology, specifically a method for classifying and extracting information on changes in individual buildings based on spatial relationship characteristics. Background Technology

[0002] The increase or decrease in the number of individual buildings in a city is a crucial indicator for urban health assessment, an important tool for promoting the modernization of the national spatial governance system and governance capabilities, and a fundamental task for the preparation of national spatial plans. Conventional methods for analyzing the increase or decrease of individual buildings mainly rely on manual identification and marking. Existing methods for analyzing the increase or decrease of individual buildings are outdated and limited by the skill level of the personnel performing the manual marking, making it difficult to scientifically, accurately, and uniformly reflect the actual changes in individual buildings in the research area. Summary of the Invention

[0003] The purpose of this invention is to provide a method for classifying and extracting information on changes in individual buildings based on spatial relationship features. The specific steps of this method are as follows:

[0004] S1. Obtain vector data of individual buildings through manual collection. The vector data of individual buildings includes vector data of individual buildings in the two phases within the scope.

[0005] S2. Based on the spatial form characteristics of each change cycle of a single building, determine the classification criteria for the changes in a single building; based on the different spatial location relationships and attribute information of the change cycle of a single building, classify the types of building changes into:

[0006] For newly constructed single-building houses, if there were no single-building houses in the same spatial location in the previous year, but a single-building house has been built in the same spatial location in the following year, it is marked as U. 新增 ;

[0007] For single-building structures subject to demolition, if a single-building structure existed in the same spatial location in the previous year, and has been demolished within the current year, it is marked as U. 灭失 ;

[0008] For renovated or expanded single buildings, if any existing single building in the same spatial location is found to have been renovated, expanded, or partially demolished within one year, it will be marked as U. 改扩建 ;

[0009] For individual buildings whose changes are not actual changes due to changes in the data source, where the change in the data source alters the building's size and boundaries, rather than changes caused by actual conditions, this is labeled as U. 非;

[0010] S3. Construct a model library to identify changes based on the spatial relationship characteristics of individual building lifecycles; analyze the spatial relationship characteristics of vector data of individual buildings at different lifecycles by spatially overlaying data from two periods. Under the same coordinate system, calculate the overlay of the two data sets and categorize them based on the spatial relationship between the overlapping portions of the two periods and the vector data of the previous year and the vector data of the following year. Based on these different spatial relationship characteristics, construct a model library, referring to the vector data of the previous year as V (baseline data) and the vector data of the following year as UV (monitoring data). Calculate the graphic area of ​​the vector data of the two periods, denoted as Shapearea1 (area of ​​individual building in the following year) and Shapearea2 (area of ​​individual building in the previous year), respectively.

[0011] S4. Import basic data into the model library for calculation and classification. Based on the model library established in S3, import the vector data of individual buildings in the two phases within the scope into the model library for spatial overlay analysis and calculation.

[0012] S5. Output the calculation results. The output will show the change type marker values ​​for all individual buildings within the range. Based on the type of the marker value, the output will determine the change type of each individual building.

[0013] Preferably, the vector data format for individual buildings is .shp or .gdb.

[0014] Preferably, the vector data for individual buildings in both phases should meet the following two conditions:

[0015] 1) The geographic coordinate system of the vector data for individual buildings in both phases must be consistent;

[0016] 2) The vector data of individual buildings in both phases should be the results data of the same study area.

[0017] Preferably, for newly constructed single-building houses, if the same spatial location has the following two situations:

[0018] 1) A unique UV patch exists. 监测 ;

[0019] 2) A unique UV exists. 监测 and several V 本底 ;

[0020] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0021] Overlap=Shapearea1-Shanparea2=0

[0022] Mark it as a new addition in UV_HBLDA;

[0023] For the second case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0024] Overlap=Shapearea1-∑Shanparea2<Shapeareal1*0.5,

[0025] Then, it is marked as UV_HBLDA newly added, and the evolution coefficient U of the marked patch is assigned respectively. 新增1 .

[0026] Preferably, for a single, destroyed building, if the same spatial location has the following two situations:

[0027] 1) There exists a unique feature V 本底 ;

[0028] 2) There exists a unique V 本底 and several UVs 监测 ;

[0029] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0030] Overlap=Shapearea2-Shanparea1=0

[0031] Mark it as UV_HBLDA lost;

[0032] For the second case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0033] Overlap=Shapearea2-∑Shanparea1<Shapeareal2*0.5

[0034] Then, the marker is marked as UV_HBLDA disappearance, and the evolution coefficient U2 is assigned to the marked patch respectively.

[0035] Preferably, for renovated or expanded single-building houses, if the same spatial location has the following four situations:

[0036] 1) A unique UV patch exists. 监测 And the only V 本底 ;

[0037] 2) A unique UV patch exists. 监测 and several V 本底 ;

[0038] 3) There exists a unique feature V 本底 and several UVs 监测 ;

[0039] 4) Several UV patches exist. 监测 and several V本底 ;

[0040] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0041] Overlap=Shapearea1-Shapearea2<Shapearea1*0.85,

[0042] Overlap=Shapearea2-Shapearea1<Shapearea2*0.85,

[0043] If either of the above two conditions is met, mark it as a UV_HBLDA renovation / expansion; for the second condition, calculate the area of ​​the overlapping portion of the map patch space, if:

[0044] Overlap = Shapearea1 - ∑Shapearea2 > Shapearea1 * 0.5, mark it as UV_HBLDA for modification and expansion;

[0045] For the third case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0046] Overlap = Shapearea2 - ∑Shapearea1 > Shapearea2 * 0.5, and mark it as UV_HBLDA for modification and expansion.

[0047] Preferably, the area of ​​the overlapping portion of the map features is calculated if:

[0048] Overlap=∑Shapearea1-∑Shapearea2>Shapearea1*0.5,

[0049] Overlap=∑Shapearea2-∑Shapearea1>Shapearea2*0.5,

[0050] If either of the above two conditions is met, it is marked as a modified / extended UV_HBLDA, and an evolution coefficient U is assigned accordingly. 改扩建1 .

[0051] Preferably, for non-realistically variable individual buildings, if one of the following conditions exists in the same spatial location: a unique UV map exists. 监测 And the only V 本底 ;

[0052] To address the above situation, calculate the area of ​​the overlapping portion of the map features.

[0053] Overlap=Shapearea1-Shapearea2>Shapearea1*0.85,

[0054] Overlap = Shapearea2 - Shapearea1 > Shapearea2 * 0.85, which is marked as a non-realistic change in UV_HBLDA.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention first determines the classification criteria for changes in individual buildings, then establishes a model library, imports the models designed for the different spatial relationship characteristics generated by various changes in individual buildings into the model library, and then imports the basic data into the model library for calculation to obtain the change classification of each individual building. The change classification mark of each individual building is used to determine which change type the specific individual building belongs to, which facilitates automatic and rapid machine identification. Attached Figure Description

[0056] Figure 1 This is a flowchart of the present invention;

[0057] Figure 2 This is a flowchart of the process for the new type of single-building housing in this invention;

[0058] Figure 3 This is a flowchart illustrating the process of this invention for demolishable single-building structures.

[0059] Figure 4 This is a flowchart of the process for renovating and expanding single-building structures according to the present invention;

[0060] Figure 5 This is a flowchart of a single building structure for addressing non-realistic changes caused by changes in the data source, as presented in this invention. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0062] Example 1

[0063] A method for classifying and extracting information on changes in individual buildings based on spatial relationship features, the specific steps of which are as follows:

[0064] S1. Obtain vector data of individual buildings through manual collection. The vector data of individual buildings includes vector data of individual buildings in the two phases within the scope. The vector data of individual buildings is in the format of .shp or .gdb.

[0065] The vector data for individual buildings in both phases should meet the following two conditions:

[0066] 1) The geographic coordinate system of the vector data for individual buildings in both phases must be consistent;

[0067] 2) The vector data of individual buildings in both phases should be data from the same study area.

[0068] S2. Based on the spatial form characteristics of each change cycle of a single building, determine the classification criteria for the changes in a single building; based on the different spatial location relationships and attribute information of the change cycle of a single building, classify the types of building changes into:

[0069] For newly constructed single-building houses, if there were no single-building houses in the same spatial location in the previous year, but a single-building house has been built in the same spatial location in the following year, it is marked as U. 新增 For newly constructed single-building houses, if the same spatial location has the following two situations:

[0070] 1) A unique UV patch exists. 监测 ;

[0071] 2) A unique UV exists. 监测 and several V 本底 ;

[0072] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0073] Overlap=Shapearea1-Shanparea2=0

[0074] Mark it as a new addition in UV_HBLDA;

[0075] For the second case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0076] Overlap=Shapearea1-∑Shanparea2<Shapeareal1*0.5,

[0077] Then, it is marked as UV_HBLDA newly added, and the evolution coefficient U of the marked patch is assigned respectively. 新增1 .

[0078] For single-building structures subject to demolition, if a single-building structure existed in the same spatial location in the previous year, and has been demolished within the current year, it is marked as U. 灭失 For single buildings that have been destroyed, if the same spatial location contains either of the following two situations:

[0079] 1) There exists a unique feature V 本底 ;

[0080] 2) There exists a unique V 本底 and several UVs 监测 ;

[0081] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0082] Overlap=Shapearea2-Shanparea1=0

[0083] Mark it as UV_HBLDA lost;

[0084] For the second case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0085] Overlap=Shapearea2-∑Shanparea1<Shapeareal2*0.5

[0086] Then its marker is UV_HBLDA annihilation, and the evolution coefficient U of the marked patch is assigned respectively. 灭失1 .

[0087] For renovated or expanded single buildings, if any existing single building in the same spatial location is found to have been renovated, expanded, or partially demolished within one year, it will be marked as U. 改扩建 For renovated or expanded single-building structures, if any of the following four situations exist in the same spatial location:

[0088] 1) A unique UV patch exists. 监测 And the only V 本底 ;

[0089] 2) A unique UV patch exists. 监测 and several V 本底 ;

[0090] 3) There exists a unique feature V 本底 and several UVs 监测 ;

[0091] 4) Several UV patches exist. 监测 and several V 本底 ;

[0092] For the first case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0093] Overlap=Shapearea1-Shapearea2<Shapearea1*0.85,

[0094] Overlap=Shapearea2-Shapearea1<Shapearea2*0.85,

[0095] If either of the above two conditions is met, mark it as a UV_HBLDA renovation / expansion; for the second condition, calculate the area of ​​the overlapping portion of the map patch space, if:

[0096] Overlap = Shapearea1 - ∑Shapearea2 > Shapearea1 * 0.5, mark it as UV_HBLDA for modification and expansion;

[0097] For the third case, calculate the area of ​​the overlapping portion of the polygon space. If:

[0098] Overlap = Shapearea2 - ∑Shapearea1 > Shapearea2 * 0.5, and mark it as UV_HBLDA for modification and expansion.

[0099] Calculate the area of ​​the overlapping region of the polygons in space. If:

[0100] Overlap=∑Shapearea1-∑Shapearea2>Shapearea1*0.5,

[0101] Overlap=∑Shapearea2-∑Shapearea1>Shapearea2*0.5,

[0102] If either of the above two conditions is met, it is marked as a modified / extended UV_HBLDA, and an evolution coefficient U is assigned accordingly. 改扩建1

[0103] For individual buildings whose changes are not actual changes due to changes in the data source, where the change in the data source alters the building's size and boundaries, rather than changes caused by actual conditions, this is labeled as U. 非 ;

[0104] For non-realistically variable individual buildings, if one of the following conditions exists in the same spatial location: a unique UV map exists. 监测 And the only V 本底 ;

[0105] To address the above situation, calculate the area of ​​the overlapping portion of the map features.

[0106] Overlap=Shapearea1-Shapearea2>Shapearea1*0.85,

[0107] Overlap = Shapearea2 - Shapearea1 > Shapearea2 * 0.85, which is marked as a non-realistic change in UV_HBLDA.

[0108] S3. Construct a model library to identify changes based on the spatial relationship characteristics of individual building lifecycles; analyze the spatial relationship characteristics of vector data of individual buildings at different lifecycles by spatially overlaying data from two periods. Under the same coordinate system, calculate the overlay of the two data sets and categorize them based on the spatial relationship between the overlapping portions of the two periods and the vector data of the previous year and the vector data of the following year. Based on these different spatial relationship characteristics, construct a model library, referring to the vector data of the previous year as V (baseline data) and the vector data of the following year as UV (monitoring data). Calculate the graphic area of ​​the vector data of the two periods, denoted as Shapearea1 (area of ​​individual building in the following year) and Shapearea2 (area of ​​individual building in the previous year), respectively.

[0109] S4. Import basic data into the model library for calculation and classification. Based on the model library established in S3, import the vector data of individual buildings in the two phases within the scope into the model library for spatial overlay analysis and calculation.

[0110] S5. Output the calculation results. The output will show the change type marker values ​​for all individual buildings within the range. Based on the type of the marker value, the output will determine the change type of each individual building.

[0111] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for classifying and extracting information on changes in individual buildings based on spatial relationship features, characterized in that: The specific steps of this method for classifying and extracting information on changes in individual buildings based on spatial relationship features are as follows: S1. Obtain vector data of individual buildings through manual collection. The vector data of individual buildings includes vector data of individual buildings in the two phases within the scope. S2. Based on the spatial form characteristics of each change cycle of a single building, determine the classification criteria for the changes in a single building; based on the different spatial location relationships and attribute information of the change cycle of a single building, classify the types of building changes into: For newly constructed single-building houses, if there were no single-building houses in the same spatial location in the previous year, but a single-building house has been built in the same spatial location in the following year, it is marked as U. 新增 ; For single-building structures subject to demolition, if a single-building structure existed in the same spatial location in the previous year, and has been demolished within the current year, it is marked as U. 灭失 ; For renovated or expanded single buildings, if any existing single building in the same spatial location is found to have been renovated, expanded, or partially demolished within one year, it will be marked as U. 改扩建 ; For individual buildings whose changes are not actual changes due to changes in the data source, where the change in the data source alters the building's size and boundaries, rather than changes caused by actual conditions, this is labeled as U. 非 ; S3. Construct a model library to determine changes based on the spatial relationship characteristics of the life cycle of individual buildings; The spatial relationship characteristics of individual building vector data at different life cycles are analyzed by spatially overlaying two periods of individual building data. Under the same coordinate system, the two data are overlaid and calculated. The spatial relationship between the overlapping parts of the two periods and the individual building vector data of the previous year and the individual building vector data of the following year is classified. Based on the different spatial relationship characteristics, a model library is constructed. The individual building vector data of the previous year is referred to as V, and the individual building vector data of the following year is referred to as UV. The graphic area of ​​the individual building vector data of the two periods is calculated and denoted as Shapearea1 and Shapearea2, respectively. S4. Import basic data into the model library for calculation and classification. Based on the model library established in S3, import the vector data of individual buildings in the two phases within the scope into the model library for spatial overlay analysis and calculation. S5. Output the calculation results. The output will show the change type marker values ​​for all individual buildings within the range. Based on the type of the marker value, the output will determine the change type of each individual building.

2. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: The vector data format for individual buildings is .shp or .gdb.

3. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: The vector data for individual buildings in both phases should meet the following two conditions: 1) The geographic coordinate system of the vector data for individual buildings in both phases must be consistent; 2) The vector data of individual buildings in both phases should be the results data of the same study area.

4. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: For newly constructed standalone buildings, if the same spatial location has the following two situations: 1) A unique UV patch exists. 监测 ; 2) A unique UV exists. 监测 and several V 本底 ; For the first case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap=Shapearea1-Shanparea2=0 Mark it as a new addition in UV_HBLDA; For the second case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap=Shapearea1-∑Shanparea2<Shapeareal1*0.5, Then, it is marked as UV_HBLDA newly added, and the evolution coefficient U of the marked patch is assigned respectively. 新增1 .

5. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: For a single building that has been destroyed, if the same spatial location contains either of the following: 1) There exists a unique feature V 本底 ; 2) There exists a unique V 本底 and several UVs 监测 ; For the first case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap=Shapearea2-Shanparea1=0 Mark it as UV_HBLDA lost; For the second case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap=Shapearea2-∑Shanparea1<Shapeareal2*0.5 Then its marker is UV_HBLDA annihilation, and the evolution coefficient U of the marked patch is assigned respectively. 灭失1 .

6. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: For renovated or expanded single-building structures, if the following four situations exist in the same spatial location: 1) A unique UV patch exists. 监测 And the only V 本底 ; 2) A unique UV patch exists. 监测 and several V 本底 ; 3) There exists a unique feature V 本底 and several UVs 监测 ; 4) Several UV patches exist. 监测 and several V 本底 ; For the first case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap=Shapearea1-Shapearea2<Shapearea1*0.85, Overlap=Shapearea2-Shapearea1<Shapearea2*0.85, If either of the above two conditions is met, mark it as a UV_HBLDA renovation / expansion; for the second condition, calculate the area of ​​the overlapping portion of the map patch space, if: Overlap = Shapearea1 - ∑Shapearea2 > Shapearea1 * 0.5, mark it as UV_HBLDA for modification and expansion; For the third case, calculate the area of ​​the overlapping portion of the polygon space. If: Overlap = Shapearea2 - ∑Shapearea1 > Shapearea2 * 0.5, and mark it as UV_HBLDA for modification and expansion.

7. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: Calculate the area of ​​the overlapping region of the polygons in space. If: Overlap=∑Shapearea1-∑Shapearea2>Shapearea1*0.5, Overlap=∑Shapearea2-∑Shapearea1>Shapearea2*0.5, If either of the above two conditions is met, it is marked as a modified / extended UV_HBLDA, and an evolution coefficient U is assigned accordingly. 改扩建1 .

8. The method for classifying and extracting individual building change information based on spatial relationship features according to claim 1, characterized in that: For non-realistically variable individual buildings, if one of the following conditions exists in the same spatial location: a unique UV map exists. 监测 And the only V 本底 ; To address the above situation, calculate the area of ​​the overlapping portion of the map features. Overlap=Shapearea1-Shapearea2>Shapearea1*0.85, Overlap = Shapearea2 - Shapearea1 > Shapearea2 * 0.85, which is marked as a non-realistic change in UV_HBLDA.

Citation Information

Patent Citations

  • Urban population spatialization method and system considering residential building attributes

    CN109829029A

  • Systems and methods for configuring a building management system

    US20110077779A1