Street facade micro-update identification method based on grid network

Abstract

The invention discloses a street facade micro-update identification method based on a grid network. The method comprises the steps of acquisition range determination, road network grading and sampling point arrangement, street scene image acquisition and building facade rasterization processing, building construction or dismantling identification through large and small granularities, building facade material identification, micro-update determination and the like. According to the method, the material change of the building facade is automatically identified through the streetscape image, efficient and accurate monitoring of city micro-updating is realized, and the method is suitable for the fields of city planning, updating evaluation and the like.

Description

Technical Field

[0001] This invention relates to the field of urban renewal monitoring technology, specifically to a method for identifying micro-updates of street facades based on a grid network. Background Technology

[0002] With the acceleration of urbanization and the transformation of urban development models, urban renewal is gradually shifting from large-scale demolition and construction to a refined governance model focused on "micro-renewal." Micro-renewal typically involves minor changes such as building facade renovation, material replacement, and partial repairs. Although these changes are small in scale, they have a significant impact on the urban landscape, neighborhood vitality, and spatial quality. Therefore, continuous and precise monitoring of micro-renewal of urban building facades has become an important task in urban planning, historical preservation, and community governance.

[0003] Currently, urban renewal monitoring mainly relies on manual inspections, remote sensing image interpretation, and oblique photogrammetry, which are insufficient for large-scale, systematic, and dynamic monitoring. Their spatial resolution is limited, making it difficult to identify detailed changes in building facade materials, colors, and components. This is especially true in densely populated urban areas, where the extraction and analysis of facade information still faces numerous challenges. In recent years, street view images have gradually become an important data source for urban spatial perception and analysis due to their wide coverage, frequent updates, realistic perspectives, and high resolution. Therefore, how to combine street view images with road network data to achieve progressive identification from building preservation to changes in facade materials, providing reliable technical support for urban renewal monitoring, is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this application proposes a street facade micro-update recognition method based on grid networks. This method combines street view images and road network data to achieve progressive recognition from building existence judgment to facade material changes, thereby realizing automatic recognition and monitoring of urban building facade micro-updates.

[0005] The technical solution adopted in this invention is as follows: A method for identifying street facade micro-updates based on grid networks includes the following steps: Step 1: Determine the target area and acquire road network data and street view image data for that area from two different years; Step 2: Classify the acquired road network and set up sampling points; Step 3: Obtain street view images of each sampling point in two years and from multiple perspectives, and identify and associate building facades; Step 4: Rasterize the existing building facade images at different granularities; Step 5: Determine whether to rebuild or demolish based on the presence or absence of the building facade; Step 6: Identify the grid material and compare its changes, and determine the micro-update based on the degree of change.

[0006] Furthermore, obtaining road network data involves extracting road vector data for target areas from open street map data for two years and simplifying the data by excluding highways, bridges, and non-public access roads.

[0007] Furthermore, in step 2, the road network is divided into main roads and secondary roads. Sampling points are set up at 50-meter intervals on the main roads and at 30-meter intervals on the secondary roads.

[0008] Furthermore, in step 3, street view images of each sampling point in two years and from multiple perspectives are obtained. The street view images of each sampling point in two years and from multiple perspectives include four directions along the road: front, back, left, and right. Building facades are identified and associated.

[0009] Furthermore, a pre-trained semantic segmentation model is used to identify building facades and perform associated labeling.

[0010] Furthermore, step 4, which involves rasterizing the existing building facade image at two different granularities, includes the following specific steps: Step 4-1: Divide the building facade image into rectangular grid units of the same size and arranged in a regular pattern for subsequent material-level analysis and comparison; Step 4-2: The rectangular grid cells of the building facade image are divided into two layers: a 5×5m large-grained grid and a 1×1m small-grained grid. Step 4-3: Large-grained grids are used to identify new construction and demolition, while small-grained grids are used to identify facade materials.

[0011] Furthermore, step 5, based on the existence or absence of the building facade, includes the following specific steps for determining whether to construct or demolish: Step 5-1: For image raster with the same sampling point and viewpoint, if a valid building facade is not identified in an image from a previous year but is identified in an image from a later year, it is determined to be newly built; Step 5-2: For image raster with the same sampling point and viewpoint, if a valid building facade is identified in an image from a previous year but not in an image from a later year, it is determined to be demolished.

[0012] Furthermore, step 6, which involves identifying the grid material and comparing its changes, and determining the micro-update based on the degree of change, includes the following specific steps: Step 6-1: The materials include: glass, concrete, brick, stone, and others; Step 6-2: Determine the degree of change by calculating the proportion of raster cells where the material changes. When this proportion exceeds 30%, it is determined that a micro-update has occurred. The specific expression is: ;in, This indicates the percentage change in material composition, where N represents the total number of grid cells on the facade in the base year. This indicates whether the material of the i-th grid has changed; if it has changed, then... =1, otherwise it is 0; Step 6-3: Summarize the update status of all sampling points and generate a distribution map of the urban micro-update identification results for the target area.

[0013] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the method described above.

[0014] A computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the above-described method.

[0015] The beneficial effects of this invention are: 1. This method combines street view images and road network data to achieve progressive identification from building preservation judgment to facade material changes, enabling automatic identification and monitoring of micro-updates of urban building facades.

[0016] 2. This invention only needs to acquire street view images and road network data within a specific time period to obtain automatic identification of micro-updates of urban building facades within that specific time period, and can realize full-time identification and monitoring of micro-updates of urban building facades.

[0017] 3. This invention eliminates the need for manual inspections, remote sensing image interpretation, oblique photogrammetry, and other technical means, enabling large-scale, systematic, and dynamic monitoring. It can also identify detailed changes in building facade materials, colors, components, and other details. Attached Figure Description

[0018] Figure 1 This is a flowchart of the method of the present invention.

[0019] Figure 2 It contains OSM road data and street view images of a certain location in a certain year.

[0020] Figure 3 yes Figure 2 A simplified diagram showing the sampling points.

[0021] Figure 4 This is a schematic diagram of the building facade in grid form.

[0022] Figure 5 This is a schematic diagram for identifying the materials used in a building facade. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0024] Combination Figure 1 This invention proposes a method for identifying street facade micro-updates based on a grid network, which specifically includes the following steps: Step 1: Determine the target area and acquire road network data and street view image data for that area in two different years. This example uses the old city area of ​​Nanjing as an example, selecting OSM road data and street view images from 2015 and 2025 respectively. Figure 2 As shown.

[0025] More specifically, acquiring road network data involves extracting road vector data for the target area from open street map data for two years and simplifying the road network by excluding highways, bridges, and non-public access roads.

[0026] Step 2: Classify the road network data for the two years and set up sampling points.

[0027] More specifically, the road network was divided into arterial roads and secondary arterial roads. Sampling points were placed at 50-meter intervals on arterial roads and at 30-meter intervals on secondary arterial roads, with reference to... Figure 3 .

[0028] Step 3: Obtain street view images of each sampling point in two years and from multiple perspectives, and identify and associate building facades; For each sampling point, street view images of each sampling point in two years and from multiple perspectives are obtained, including street view images in the front, back, left and right directions along the road; a pre-trained semantic segmentation model is used to identify building facades and perform associated labeling.

[0029] Step 4: Perform rasterization processing on the existing building facade images at two different granularities; the specific steps are as follows: Step 4-1: Divide the building facade image into rectangular grid units of the same size and arranged in a regular pattern for subsequent material-level analysis and comparison; Step 4-2: The rectangular grid cells of the building facade image are divided into two layers: a 5×5m large-grained grid and a 1×1m small-grained grid. Step 4-3: Large-grained grids are used to identify new construction and demolition, while small-grained grids are used to identify facade materials, such as... Figure 4 .

[0030] Step 5: Based on the existence or absence of the building facade, determine whether to rebuild or demolish; specific steps include: Step 5-1: For image raster with the same sampling point and viewpoint, if a valid building facade is not identified in an image from a previous year but is identified in an image from a later year, it is determined to be newly built; Step 5-2: For image raster with the same sampling point and viewpoint, if a valid building facade is identified in an image from a previous year but not in an image from a later year, it is determined to be demolished.

[0031] Step 6: Identify the grid material and compare its changes, determining the micro-update based on the degree of change. Specific steps include: Step 6-1: Materials include, but are not limited to: glass, concrete, brick, stone, and others; Step 6-2: Determine the degree of change by calculating the proportion of raster cells where the material changes. When this proportion exceeds 30%, it is determined that a micro-update has occurred. The specific expression is: ;in, This indicates the percentage change in material composition, where N represents the total number of grid cells on the facade in the base year (an earlier year). This indicates whether the material of the i-th grid has changed; if it has changed, then... =1, otherwise it is 0; Step 6-3: Summarize the update status of all sampling points and generate a distribution map of the urban micro-update identification results for the target area.

[0032] Experiments show that this method can effectively identify changes in building facade materials and achieve automated monitoring of urban micro-renewal.

[0033] The present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0034] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0035] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A method for identifying street facade micro-updates based on grid networks, characterized in that, Includes the following steps: Step 1: Determine the target area and acquire road network data and street view image data for that area from two different years; Step 2: Classify the acquired road network and set up sampling points; Step 3: Obtain street view images of each sampling point in two years and from multiple perspectives, and identify and associate building facades; Step 4: Rasterize the existing building facade images at different granularities; Step 5: Determine whether to rebuild or demolish based on the presence or absence of the building facade; Step 6: Identify the grid material and compare its changes, and determine the micro-update based on the degree of change.

2. The method for micro-updating and recognizing street facades based on a grid network according to claim 1, characterized in that, Obtaining road network data involves extracting road vector data for target areas from open street map data for two years and simplifying it by excluding highways, bridges, and non-public access roads.

3. The method for micro-updating and recognizing street facades based on a grid network according to claim 1, characterized in that, In step 2, the road network is divided into main roads and secondary roads. Sampling points are set up at 50-meter intervals on the main roads and at 30-meter intervals on the secondary roads.

4. The method for micro-updating and identifying street facades based on a grid network according to claim 1, characterized in that, In step 3, street view images of each sampling point in two years and from multiple perspectives are obtained. The street view images of each sampling point in two years and from multiple perspectives include four directions along the road: front, back, left, and right. Building facades are identified and associated.

5. The method for identifying street facade micro-updates based on grid networks according to claim 1, characterized in that, A pre-trained semantic segmentation model is used to identify building facades and perform associated labeling.

6. The method for micro-updating and recognizing street facades based on a grid network according to claim 1, characterized in that, The specific steps of step 4, which involves rasterizing the existing building facade image at two different granularities, include: Step 4-1: Divide the building facade image into rectangular grid units of the same size and arranged in a regular pattern for subsequent material-level analysis and comparison; Step 4-2: The rectangular grid cells of the building facade image are divided into two layers: a 5×5m large-grained grid and a 1×1m small-grained grid. Step 4-3: Large-grained grids are used to identify new construction and demolition, while small-grained grids are used to identify facade materials.

7. The method for identifying street facade micro-updates based on grid networks according to claim 1, characterized in that, Step 5, based on the preservation or loss of the building facade, includes the following specific steps for determining whether to construct or demolish: Step 5-1: For image raster with the same sampling point and viewpoint, if a valid building facade is not identified in an image from a previous year but is identified in an image from a later year, it is determined to be newly built; Step 5-2: For image raster with the same sampling point and viewpoint, if a valid building facade is identified in an image from a previous year but not in an image from a later year, it is determined to be demolished.

8. The method for micro-updating and recognizing street facades based on a grid network according to claim 1, characterized in that, Step 6, which identifies the grid material and compares its changes, and determines the micro-update based on the degree of change, includes the following specific steps: Step 6-1: The materials include: glass, concrete, brick, stone, and others; Step 6-2: Determine the degree of change by calculating the proportion of raster cells where the material changes. When this proportion exceeds 30%, it is determined that a micro-update has occurred. The specific expression is: ;in, This indicates the percentage change in material composition, where N represents the total number of grid cells on the facade in the base year. This indicates whether the material of the i-th grid has changed; if it has changed, then... =1, otherwise it is 0; Step 6-3: Summarize the update status of all sampling points and generate a distribution map of the urban micro-update identification results for the target area.

9. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the grid network-based street facade micro-update recognition method as described in claim 1.

10. A computer-readable storage medium, characterized in that, It stores a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the grid network-based street facade micro-update recognition method as described in claim 1.

Images