Urban building safety evaluation method, device and equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of building risk monitoring, in particular to an urban building safety evaluation method, device and equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, topographic data and building contour data of a to-be-evaluated region; based on the optical remote sensing image and the building contour data, identifying spatial form change information of each target building, and generating change parameters used for describing structure adjustment features; generating an interferogram based on the synthetic aperture radar image, extracting a corresponding deformation monitoring point, and generating a settlement parameter reflecting the displacement change of the building; based on the hyperspectral image and the topographic data, identifying spatial relationship information of the target building and the surrounding environment risk body, and generating external influence parameters; and based on the change parameter, the settlement parameter, the external influence parameter and the preset evaluation model, generating a safety evaluation result of each target building, thereby improving the efficiency of urban building safety evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building risk monitoring, and particularly relates to a city building safety evaluation method, device, equipment, storage medium and computer program product. BACKGROUND

[0002] With the rapid development of urbanization, the present stage is in a key period of urban renewal, and city buildings have entered a new stage of focusing on both stock quality improvement and incremental structure adjustment. The existing city buildings, especially some old buildings, are affected by natural disasters, geological conditions, their own quality and environmental disturbances during service, thus producing deformation and damage and gradually accumulating, which may cause structural safety hazards. At the same time, environmental risks such as underground engineering construction, near-slope and near-mountain construction exist in urban construction, which continuously accumulates and develops the hidden dangers, and finally leads to the collapse and destruction of buildings. The existing building safety evaluation methods mainly rely on manual point observation or item-by-item inspection, and can only passively observe the key points according to expert opinions after early accidents, and rely on a large number of personnel and professional knowledge, which leads to poor efficiency of city building safety evaluation. Therefore, how to improve the efficiency of city building safety evaluation has become a technical problem to be solved. SUMMARY

[0003] The main purpose of the present application is to provide a city building safety evaluation method, device, equipment, storage medium and computer program product, which aims to solve the technical problem of how to improve the efficiency of city building safety evaluation.

[0004] To achieve the above purpose, the present application provides a city building safety evaluation method, which comprises the following steps:

[0005] Obtaining a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, terrain data and building contour data of a region to be evaluated;

[0006] Based on the optical remote sensing image and the building contour data, spatial form change information of each target building in the region to be evaluated is identified, and a change parameter for describing structural adjustment characteristics is generated;

[0007] Based on the synthetic aperture radar image, an interferogram is generated, and corresponding deformation monitoring points are extracted to generate a settlement parameter reflecting the displacement change of the building;

[0008] Based on the hyperspectral image and the terrain data, spatial relationship information between the target building and the surrounding environmental risk body is identified, and an external influence parameter is generated;

[0009] Based on the change parameter, the settlement parameter, the external influence parameter and a preset evaluation model, a safety evaluation result of each target building is generated.

[0010] In an embodiment, the step of identifying the spatial form change information of each target building in the to-be-evaluated area based on the optical remote sensing image and the building contour data, and generating the change parameter for describing the structural adjustment feature, comprises:

[0011] The optical remote sensing image at each time point is corrected to obtain a plurality of corrected remote sensing images;

[0012] Based on the building contour data, building area images corresponding to the target building are extracted from the plurality of corrected remote sensing images, and boundary changes of the target building between each time point are extracted through an image difference analysis algorithm;

[0013] Based on the boundary change result, a structural adjustment feature index is determined, the structural adjustment feature index comprising a building area change rate and a boundary expansion ratio;

[0014] The time series of the structural adjustment feature index is normalized and weighted to generate the change parameter for describing the structural adjustment feature.

[0015] In an embodiment, the step of generating an interferogram based on the synthetic aperture radar image and extracting corresponding deformation monitoring points to generate a settlement parameter reflecting building displacement changes comprises:

[0016] The synthetic aperture radar image is preprocessed to obtain the interferogram and a coherence coefficient map, the preprocessing comprising registration, despeckling, and interferogram generation;

[0017] Based on the building contour data, the monitoring points in the interferogram are divided into building monitoring points and ground monitoring points, and based on the coherence coefficient map, points in the building monitoring points with a coherence lower than a preset coherence threshold are removed;

[0018] The vertical deformation and deformation rate of the removed building monitoring points at different time points are extracted and weightedly averaged to obtain a building settlement rate parameter;

[0019] Based on the building settlement rate parameter and the maximum cumulative deformation of the building monitoring points relative to the initial time point, the settlement parameter reflecting the building displacement changes is generated.

[0020] In an embodiment, the step of identifying the spatial relationship information of the target building and the surrounding environmental risk body based on the hyperspectral image and the terrain data, and generating an external influence parameter comprises:

[0021] Based on the hyperspectral image, an image segmentation and classification algorithm is used to identify a risk area, and boundary coordinate information of the risk area is extracted, the risk area including a open channel, a water body, a foundation pit and an underground tunnel;

[0022] According to the terrain data and a preset slope threshold, a slope area is identified, and boundary coordinate information of the slope area is extracted;

[0023] According to the boundary coordinate information of the risk area and the boundary coordinate information of the slope area, a minimum horizontal distance from each building contour boundary to the boundary of each type of risk area is determined;

[0024] The minimum horizontal distance is compared with a preset risk safety threshold, and based on the comparison result, the external influence parameter is generated.

[0025] In an embodiment, the step of generating the safety evaluation result of each target building based on the change parameter, the settlement parameter, the external influence parameter and a preset evaluation model includes:

[0026] Based on a preset multi-dimensional vector format, feature vectors of the change parameter, the settlement parameter and the external influence parameter are constructed to obtain multi-dimensional risk input data;

[0027] Based on the preset evaluation model, a preset index weight configuration strategy is called to assign corresponding weight values to the change parameter, the settlement parameter and the external influence parameter, and a corresponding weighted sub-score is determined according to the assignment result;

[0028] Based on a model aggregation rule of the preset evaluation model, the weighted sub-scores are added up, and based on the addition result, the safety evaluation result of each target building is generated.

[0029] In an embodiment, after the step of generating the safety evaluation result of each target building based on the change parameter, the settlement parameter, the external influence parameter and a preset evaluation model, the method further includes:

[0030] Based on the safety evaluation result, each target building is sorted;

[0031] If the safety evaluation results of multiple target buildings are the same, a settlement cumulative parameter in the settlement parameter and a structure change index in the change parameter corresponding to the multiple target buildings are obtained;

[0032] Based on the settlement cumulative parameter and the structure change index, two-layer and three-layer sorting is performed to obtain a target risk screening hierarchical sequence.

[0033] In addition, to achieve the above object, the application further provides a city building safety evaluation device, which comprises:

[0034] a data acquisition module, configured to acquire synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data of a region to be evaluated;

[0035] a change parameter module, configured to identify spatial form change information of each target building in the region to be evaluated based on the optical remote sensing images and the building contour data, and generate change parameters for describing structural adjustment characteristics;

[0036] a settlement parameter module, configured to generate an interferogram based on the synthetic aperture radar images, extract corresponding deformation monitoring points, and generate settlement parameters reflecting building displacement changes;

[0037] an external influence parameter module, configured to identify spatial relationship information between the target buildings and surrounding environmental risk bodies based on the hyperspectral images and the terrain data, and generate external influence parameters;

[0038] a target module, configured to generate safety evaluation results of the target buildings based on the change parameters, the settlement parameters, the external influence parameters and a preset evaluation model.

[0039] In addition, to achieve the above object, the application further provides a city building safety evaluation device, which comprises: a memory, a processor and a city building safety evaluation program stored on the memory and executable on the processor, the city building safety evaluation program being configured to implement the steps of the city building safety evaluation method as described above.

[0040] In addition, to achieve the above object, the application further provides a storage medium, which stores a city building safety evaluation program, the city building safety evaluation program being executable by a processor to implement the steps of the city building safety evaluation method as described above.

[0041] In addition, to achieve the above object, the application further provides a computer program product, which comprises a computer program, the computer program being executable by a processor to implement the steps of the city building safety evaluation method as described above.

[0042] The application obtains a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, terrain data and building contour data of a to-be-evaluated region; based on the optical remote sensing image and the building contour data, spatial form change information of each target building in the to-be-evaluated region is recognized, and a change parameter used for describing a structural adjustment feature is generated; based on the synthetic aperture radar image, an interferogram is generated, and a corresponding deformation monitoring point is extracted, and a settlement parameter reflecting building displacement change is generated; based on the hyperspectral image and the terrain data, spatial relationship information of the target building and a surrounding environment risk body is recognized, and an external influence parameter is generated; based on the change parameter, the settlement parameter, the external influence parameter and a preset evaluation model, a safety evaluation result of each target building is generated. The application obtains the synthetic aperture radar image, the optical remote sensing image, the hyperspectral image, the terrain data and the building contour data, establishes a multi-source data basis required for urban building safety evaluation, and avoids an inefficient manner of manually collecting information one by one; further, based on the optical remote sensing image and the building contour data, building spatial form change information is extracted, structural adjustment features can be automatically recognized and change parameters are generated, and a traditional manual recognition means of structural reconstruction and expansion is replaced; meanwhile, the synthetic aperture radar image is used to generate an interferogram and extract a deformation monitoring point, remote sensing monitoring of building displacement change can be realized in a large range without laying out ground equipment; in addition, the hyperspectral image and the terrain data are used to recognize the spatial relationship of the building and the surrounding risk body, and an external influence parameter is generated, and manual investigation of the surrounding environment risk is replaced; finally, the above parameters are uniformly input into the preset evaluation model to generate a safety evaluation result of the building, an automatic processing flow from data acquisition to result output is constructed, and the efficiency of urban building safety evaluation is improved. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 It is a flowchart of a first embodiment of the urban building safety evaluation method of the application;

[0044] Figure 2 It is a sub-flowchart of a second embodiment of the urban building safety evaluation method of the application;

[0045] Figure 3 It is a sub-flowchart of a third embodiment of the urban building safety evaluation method of the application;

[0046] Figure 4 It is a building safety evaluation index system schematic diagram in an embodiment of the urban building safety evaluation method of the application;

[0047] Figure 5 It is a module structure schematic diagram of the urban building safety evaluation device in an embodiment of the application;

[0048] Figure 6 It is a device structure schematic diagram of a hardware running environment involved in the urban building safety evaluation method in an embodiment of the application.

[0049] The object, features and advantages of the present application will be further illustrated in conjunction with the embodiments, with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are merely intended to explain the present application, and are not intended to limit the present application.

[0051] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments of the specification.

[0052] It should be noted that, with the rapid development of urbanization, the present stage is in a key and important period of urban renewal, and urban buildings have entered a new stage of equal emphasis on stock quality improvement and incremental structure adjustment from large-scale incremental construction. The existing buildings in the city, especially some old buildings, are affected by natural disasters, geological conditions, their own quality and environmental disturbances during their service period, thus producing deformation and damage and may gradually accumulate, causing structural safety hazards. At the same time, there are environmental risks such as underground engineering construction, near-slope and near-mountain in urban construction, which make the hidden dangers develop continuously, thus eventually leading to the collapse and destruction of buildings. The existing building safety evaluation method mainly relies on manual point observation or item-by-item investigation, which can only passively observe the key points according to expert opinions after early accidents occur, and relies heavily on the number of personnel and professional knowledge, resulting in poor efficiency of urban building safety evaluation. Therefore, how to improve the efficiency of urban building safety evaluation has become a technical problem to be solved.

[0053] The main solution of the present application is: acquiring synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data of a region to be evaluated; based on the optical remote sensing images and the building contour data, identifying spatial form change information of each target building in the region to be evaluated, and generating change parameters for describing structural adjustment features; generating an interferogram based on the synthetic aperture radar images, and extracting corresponding deformation monitoring points to generate settlement parameters reflecting building displacement changes; based on the hyperspectral images and the terrain data, identifying spatial relationship information between the target buildings and the surrounding environmental risk bodies, and generating external influence parameters; based on the change parameters, the settlement parameters, the external influence parameters and a preset evaluation model, generating safety evaluation results of each target building.

[0054] The present application establishes a multi-source data basis required for urban building safety evaluation by acquiring synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data, avoiding the inefficient way of manually collecting information one by one. Further, based on the optical remote sensing images and building contour data, the building spatial form change information is extracted, the structural adjustment features are automatically identified and the change parameters are generated, replacing the traditional manual identification means of structural expansion and reconstruction. At the same time, the synthetic aperture radar images are used to generate an interferogram and extract deformation monitoring points, so that remote sensing monitoring of building displacement changes can be realized in a large range without the need to lay out ground equipment. In addition, the spatial relationship between the building and the surrounding risk body is identified through the hyperspectral images and the terrain data, and the external influence parameters are generated, replacing the manual investigation of the surrounding environmental risks. Finally, the above parameters are uniformly input into a preset evaluation model to generate the safety evaluation result of the building, and an automatic processing flow from data acquisition to result output is constructed, thereby improving the efficiency of urban building safety evaluation.

[0055] It should be noted that the execution subject of the method of the present embodiment can be a computing service device with data processing, network communication and program running functions, or a city building safety evaluation device with the same or similar functions. The present embodiment and the following embodiments will be described taking the city building safety evaluation device as an example.

[0056] Based on this, the first embodiment of the city building safety evaluation method of the present application is proposed, please refer to Figure 1 , Figure 1 The flowchart of the first embodiment of the city building safety evaluation method of the present application is shown in the figure.

[0057] In the present embodiment, the city building safety evaluation method comprises the following steps:

[0058] S1: acquiring synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data of the region to be evaluated;

[0059] It should be noted that the synthetic aperture radar image (SAR image) is a ground microwave reflection image obtained by a synthetic aperture radar, which has all-weather and all-day imaging capability and can be used for monitoring ground deformation. The optical remote sensing image is a ground image taken by visible light or near-infrared band, which has high resolution and is convenient for identifying the shape and texture features of ground objects. The hyperspectral image is an image data captured by continuous and subdivided wave bands, each pixel contains rich spectral information, which is helpful for fine classification and material identification. The terrain data (DEM) is a digital elevation model used to represent the height variation of the ground. The building contour data is vector data used to describe the planar boundary of the building.

[0060] Specifically, first, according to the geographical scope of the region to be evaluated, the required remote sensing data sources and data format requirements are determined. Through a multi-source remote sensing data platform or satellite data service, SAR images, optical remote sensing images and hyperspectral images of the corresponding region are obtained to ensure that the images have sufficient temporal coverage and spatial resolution to support subsequent dynamic change monitoring and structural feature recognition. At the same time, the digital elevation model (DEM) of the region is obtained from a public topographic data platform or a surveying and mapping unit to provide surface height information.

[0061] Further, based on the city planning department or remote sensing interpretation platform, building contour data covering the region to be evaluated is imported as the spatial boundary basis for building object recognition and index calculation. After data collection is complete, coordinate system conversion and spatial registration of various image data are performed to ensure spatial consistency between data. Finally, the registered SAR images, optical images, hyperspectral images, terrain data and building contour data are integrated into subsequent processing modules to provide data support for spatial form recognition, deformation monitoring and risk assessment.

[0062] By uniformly obtaining synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data in the initial stage, key data elements that affect building safety status are comprehensively covered from multiple dimensions, and a reliable remote sensing data foundation is established. This step avoids the problems of multiple dispersed collection, inconsistent data formats and difficult spatial alignment in traditional methods, providing efficient and consistent data source support for subsequent parameter extraction and analysis, thereby significantly improving the starting efficiency, automation level and overall processing flow continuity of building safety evaluation work.

[0063] S2: Based on the optical remote sensing images and the building contour data, spatial form change information of each target building in the region to be evaluated is identified, and change parameters for describing structural adjustment features are generated;

[0064] It should be noted that the spatial form change information refers to the changes in structural features such as contour, volume, orientation or height of the building at different time points. The change parameter is a numerical index for quantitatively representing the reconstruction, expansion or shape change of the building structure in the time scale.

[0065] Specifically, in the registered multi-period optical remote sensing images, image segments of each target building at different time points are extracted according to the building contour data. Image processing algorithms such as edge detection and contour extraction are used to identify the structural boundaries in the building images, and the identified regions are further accurately corrected in combination with the building contour data to ensure that each building is accurately corresponded in each period of images.

[0066] Further, the boundary contours of the same target building in each image are compared pair by pair to analyze the area change, boundary expansion direction and boundary shape change in the plane. According to the change result, an index system for structural adjustment is constructed, including parameters such as contour expansion ratio, boundary increment density and change frequency, and these parameters are input to generate a change parameter for describing the structural change characteristics of the target building.

[0067] By automatically recognizing the spatial shape change information of the building based on the optical remote sensing image and the building contour data, the historical adjustment of the building structure can be accurately tracked without relying on field investigation. By comparing the differences in the building boundaries in multiple remote sensing images, the structural changes of the building in the time dimension are extracted and standardized in the form of change parameters, thereby replacing the traditional manual checking of reconstruction and expansion, greatly improving the efficiency and objectivity of the reconstruction behavior recognition, and providing reliable structural characteristics support for the change of building safety state.

[0068] S3: generating an interferogram based on the synthetic aperture radar image, extracting corresponding deformation monitoring points, and generating a settlement parameter reflecting the displacement change of the building;

[0069] It should be noted that the interferogram (interferogram image) is an image generated by interferometric processing of two or more SAR images, which can reflect the micro-deformation information of the ground between different time. The deformation monitoring point refers to a stable and traceable scatterer point in the interferogram. The settlement parameter is a data index for quantitatively representing the vertical displacement characteristics of the building.

[0070] Specifically, the obtained synthetic aperture radar image is registered, despeckled and interfered to generate an interferogram containing deformation information and a corresponding coherence coefficient map. Through coherence analysis and time sequence stability screening, high-coherence scatterers in the image are identified as deformation monitoring points. These monitoring points are usually distributed on the building surface or its surrounding area and are the basis for subsequent deformation calculation.

[0071] Further, the monitoring points are spatially classified in combination with the building contour data, and the points located within the building contour range are marked as building monitoring points. Time series analysis is performed on these building monitoring points to calculate their vertical deformation rate and maximum cumulative deformation at each time. To improve the calculation accuracy, the deformation data can be weighted in combination with the coherence coefficient of the point. Finally, the extracted deformation rate and cumulative settlement amount jointly constitute the settlement parameter of the target building, which is used to reflect the overall displacement change trend and cumulative deformation degree of the target building.

[0072] By generating interferograms based on synthetic aperture radar images and extracting deformation monitoring points, large-scale and continuous vertical displacement monitoring of urban building groups can be achieved without contacting the building body. Compared with traditional manual measurement or ground sensor layout methods, this method has the advantages of high automation, wide coverage, and long time span. The extraction process of settlement parameters relies on accurate classification and coherence weighting, which can ensure the reliability and representativeness of the monitoring data, provide stable and precision-controllable displacement basis for building risk assessment, and significantly improve the detection efficiency and spatial adaptability of building safety evaluation in the dimension of ground deformation.

[0073] S4: Based on the hyperspectral image and the terrain data, the spatial relationship information between the target building and the surrounding environmental risk body is identified, and an external influence parameter is generated.

[0074] It should be noted that the environmental risk body refers to geographical entities that may have potential impact on building safety, such as open channels, water bodies, foundation pits, underground tunnels, and mountain slopes. The external influence parameter is a numerical index used to describe the strength of the spatial relationship between the building and the surrounding environmental risk body, usually generated based on distance, distribution density, or correlation weight.

[0075] Specifically, based on spectral feature analysis of the hyperspectral image, the image segmentation and classification algorithm is used to identify the boundary of typical environmental risk bodies such as open channels, water bodies, foundation pits, and tunnels, and to extract their spatial position information. At the same time, based on the slope analysis of the terrain data, the area with a slope exceeding a certain threshold is identified as a mountain slope risk area, and its boundary coordinates are extracted.

[0076] Further, the contour boundary of each target building is spatially correlated with the boundary of each type of risk area extracted above, the minimum horizontal distance is calculated, and the proximity between the building and each type of environmental risk body is determined. According to the pre-set grading standard, different distances are mapped to corresponding risk impact levels, thereby generating an external influence parameter reflecting the environmental disturbance conditions of the target building. This parameter will be used as an input feature in the subsequent safety evaluation model.

[0077] By combining the fine feature recognition capability of hyperspectral images and the slope extraction capability of terrain data, this step can efficiently and comprehensively identify environmental risk bodies related to building safety without the need for on-site inspection, and quantify the spatial relationship between the target building and the environmental risk bodies. The generation process of the external influence parameter is based on spatial geometric calculation and matching of the risk body identification results, which enables the objective expression of the environmental disturbance conditions of the building, thereby making up for the lack of identification of surrounding environmental factors or subjective judgment bias in traditional evaluation, and significantly improving the comprehensiveness and automation level of the identification of external disturbance factors in urban building safety evaluation.

[0078] S5: generating a safety evaluation result of each target building based on the change parameter, the settlement parameter, the external influence parameter, and a preset evaluation model.

[0079] It should be noted that the preset evaluation model is a multi-index evaluation framework constructed according to building safety risk factors.

[0080] Specifically, the change parameter, the settlement parameter, and the external influence parameter corresponding to each target building are uniformly arranged to construct a multi-dimensional input vector. The vector is used as a feature description of the building to comprehensively represent the current structural state, the foundation stability, and the external risk influence situation.

[0081] Further, a preset building safety evaluation model is called, different weight coefficients are given according to the risk correlation and importance of each parameter, the multi-dimensional input vector is weighted, the sub-scores of each type of risk are calculated, and the comprehensive risk score is further aggregated. According to the scoring result and the grading standard, each target building is divided into a corresponding safety level, such as low risk, medium risk, or high risk. The final output evaluation result can be used as a basis for risk ranking, early warning screening, or subsequent disposal decision.

[0082] This step establishes an executable and repeatable building safety automatic evaluation mechanism by taking the change parameter, the settlement parameter, and the external influence parameter as multi-dimensional input and introducing a preset evaluation model for quantitative analysis. Compared with the traditional method of relying on manual scoring or single index judgment, this step realizes the structured integration and unified modeling of multiple risk dimensions, improves the systematicness and scientificity of building risk determination. In addition, through the solidification of the model rules, the batch processing demand of a large range of urban building groups can be quickly adapted, and the efficiency and objectivity of building safety grading judgment are significantly improved.

[0083] The embodiment obtains a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, terrain data and building contour data of a region to be evaluated; identifies spatial form change information of each target building in the region to be evaluated based on the optical remote sensing image and the building contour data, and generates change parameters for describing structural adjustment features; generates an interferogram based on the synthetic aperture radar image, extracts corresponding deformation monitoring points, and generates settlement parameters reflecting building displacement changes; identifies spatial relationship information between the target building and a surrounding environment risk body based on the hyperspectral image and the terrain data, and generates external influence parameters; and generates safety evaluation results of the target buildings based on the change parameters, the settlement parameters, the external influence parameters and a preset evaluation model. The embodiment obtains the synthetic aperture radar image, the optical remote sensing image, the hyperspectral image, the terrain data and the building contour data, establishes a multi-source data basis required for urban building safety evaluation, and avoids an inefficient manual information collection mode. Further, the spatial form change information of the building is extracted based on the optical remote sensing image and the building contour data, the structural adjustment features are automatically identified, and the change parameters are generated, which replaces a traditional manual structural identification method. Meanwhile, the interferogram is generated based on the synthetic aperture radar image, and the deformation monitoring points are extracted, which enables remote sensing monitoring of building displacement changes in a large range without ground equipment. In addition, the spatial relationship between the building and the surrounding risk body is identified based on the hyperspectral image and the terrain data, and the external influence parameters are generated, which replaces manual investigation of the surrounding environment risk. Finally, the safety evaluation results of the building are generated by inputting the above parameters into the preset evaluation model, an automatic processing flow from data acquisition to result output is constructed, and the efficiency of urban building safety evaluation is improved.

[0084] Based on the first embodiment, a second embodiment of the urban building safety evaluation method is provided. Figure 2 , Figure 2 FIG. 2 is a sub-process schematic diagram of the second embodiment of the urban building safety evaluation method.

[0085] As shown in FIG. 2, in the embodiment, step S2 includes: Figure 2

[0086] S21: performing correction processing on the optical remote sensing image at each time point to obtain a plurality of corrected remote sensing images;

[0087] S22: based on the building contour data, extracting building region images corresponding to the target building in the plurality of corrected remote sensing images, and extracting boundary changes of the target building between each time point through an image difference analysis algorithm;

[0088] S23: determining a structural adjustment feature index based on the boundary change result, the structural adjustment feature index including a building area change rate and a boundary expansion ratio; ​

[0089] S24: normalizing and weighting the time series of the structural adjustment feature indicators to generate the change parameter for describing the structural adjustment feature.

[0090] It should be noted that the corrected remote sensing image refers to an image obtained by performing geometric correction, radiation correction and the like on the original remote sensing image. The image difference analysis algorithm detects the differences in position, shape or texture of the same ground object in different time images by comparing the pixel changes of the same ground object in different time images, and is used to identify the change area. The building area change rate refers to the ratio of the contour area change of the target building between two time points to the reference area, and is used to measure the horizontal expansion degree. The boundary expansion ratio is used to describe the expansion degree of the building contour boundary between different time points, and reflects the extension change of the structural contour.

[0091] Specifically, in the first stage, the optical remote sensing images at each time point are geometrically corrected and radiometrically corrected to ensure consistency between the images in terms of spatial position and pixel brightness, thereby eliminating errors caused by imaging angle, illumination change and the like, to obtain a plurality of corrected remote sensing images. In the second stage, based on the building contour data, the area image in which the target building is located is intercepted in each corrected remote sensing image. Subsequently, the image segments of adjacent time points are selected to perform image difference analysis, and the boundary change of the building between different periods is extracted through pixel-level edge comparison or contour reconstruction, including the newly added area and the boundary offset.

[0092] Further, in the third stage, the building area change rate and the boundary expansion ratio are calculated as the core indicators of the structural adjustment feature according to the boundary change result. The area change rate is used to measure whether the building has been horizontally expanded, and the boundary expansion ratio is used to identify the extension change of the building shape or layout. In the fourth stage, the area change rate and the boundary expansion ratio sequences formed by multiple time points are normalized to have a unified numerical scale, and are linearly weighted and integrated according to the preset weight, to finally generate the structural adjustment change parameter for subsequent building risk assessment.

[0093] This step extracts boundary change information by correcting and difference analyzing multiple period optical remote sensing images in combination with building contour data, which can accurately identify the structural adjustment behavior of the target building in the time sequence without the need for on-site monitoring, and construct a quantitative change indicator system. Further, the change parameter is generated by normalizing and weighting, which not only realizes the standard expression of the reconstruction and expansion feature, but also ensures the comparability and evaluability of the parameters between different buildings. The processing procedure avoids the identification bottleneck of the traditional method of relying on drawings or on-site investigation of building changes, significantly improves the efficiency, accuracy and automation level of the reconstruction behavior identification, and provides a quantifiable and traceable structural change basis for subsequent building safety risk analysis.

[0094] Based on the first embodiment, in the present embodiment, step S3 comprises:

[0095] S31: preprocessing the synthetic aperture radar image to obtain the interferogram and the coherence coefficient map, the preprocessing comprising registration, despeckling and interferogram generation;

[0096] S32: based on the building contour data, dividing the monitoring points in the interferogram into building monitoring points and ground monitoring points, and based on the coherence coefficient map, performing elimination processing on the points in the building monitoring points whose coherence is lower than a preset coherence threshold;

[0097] S33: extracting the vertical deformation variable and the deformation rate of the building monitoring points after elimination at different time points, and performing weighted average to obtain the building settlement rate parameter;

[0098] S34: based on the building settlement rate parameter and the maximum cumulative deformation variable of the building monitoring points relative to the initial time point, generating the settlement parameter reflecting the displacement change of the building.

[0099] It should be noted that the coherence coefficient map describes the coherence degree of two SAR images at corresponding pixel points, and the higher the value, the stronger the signal stability. The building monitoring points are high-coherence points within the building contour range, which are used to represent the building surface deformation.

[0100] Specifically, the original synthetic aperture radar image is preprocessed, and the steps include: performing image registration to ensure the spatial consistency of multi-period SAR images; performing despeckling operation to reduce noise interference; and performing interference processing on the registered image pair to generate an interferogram for deformation extraction and a coherence coefficient map for point screening. These images constitute the basis for subsequent monitoring point screening and deformation analysis. Subsequently, combined with the building contour data, the monitoring points in the interferogram are divided into "building monitoring points" and "ground monitoring points" according to their spatial positions. In order to improve the credibility of the monitoring data, further based on the coherence coefficient map, the points in the building monitoring points whose coherence is lower than a preset threshold are eliminated, and only the high-coherence points suitable for deformation analysis are retained.

[0101] Further, the vertical deformation variable and the deformation rate data of the building monitoring points after elimination at each time point are extracted, and weighted average is performed based on the coherence of each point or other weight factors to obtain the building settlement rate parameter for representing the overall settlement trend of the target building. Finally, combined with the historical observation data of the building monitoring points, the maximum cumulative vertical deformation variable of each monitoring point relative to the initial time point is calculated. The building settlement rate parameter and the cumulative settlement amount are integrated to form the settlement parameter for representing the displacement change of the building, which provides a key basis for subsequent building stability evaluation.

[0102] This step can obtain extensive and time-continuous building surface subsidence information without laying ground sensors by standardizing preprocessing and interference analysis of synthetic aperture radar images. With the aid of building contour data, the monitoring points are spatially classified, and the reliability is screened by the coherence coefficient to ensure that the extracted building monitoring points have high stability and reliability. Further, the weighted average method is used to fuse multi-point deformation information, which can effectively suppress the interference of individual abnormal points and improve the robustness of subsidence rate calculation. At the same time, the cumulative subsidence is calculated combined with the historical observation data, so that the subsidence parameters have real-time and accumulation, which can comprehensively reflect the current deformation trend and potential risk of the building, thereby improving the analysis accuracy and processing efficiency of the foundation subsidence problem in building safety evaluation.

[0103] In this embodiment, the synthetic aperture radar image, the optical remote sensing image, the hyperspectral image, the terrain data and the building contour data of the region to be evaluated are obtained. Based on the optical remote sensing image and the building contour data, the spatial form change information of each target building in the region to be evaluated is identified, and the change parameter for describing the structural adjustment feature is generated. Based on the synthetic aperture radar image, the interference graph is generated, and the corresponding deformation monitoring point is extracted to generate the subsidence parameter reflecting the displacement change of the building. Based on the hyperspectral image and the terrain data, the spatial relationship information between the target building and the surrounding environment risk body is identified, and the external influence parameter is generated. Based on the change parameter, the subsidence parameter, the external influence parameter and the preset evaluation model, the safety evaluation result of each target building is generated. In this embodiment, the synthetic aperture radar image, the optical remote sensing image, the hyperspectral image, the terrain data and the building contour data are obtained to establish the multi-source data basis required for urban building safety evaluation, avoiding the inefficient way of manually collecting information one by one. Further, the building spatial form change information is extracted based on the optical remote sensing image and the building contour data, which can automatically identify the structural adjustment feature and generate the change parameter, replacing the traditional manual identification means of structural expansion and reconstruction. At the same time, the interference graph is generated by using the synthetic aperture radar image, and the deformation monitoring point is extracted, which can realize remote sensing monitoring of building displacement change in a large range without laying ground equipment. In addition, the spatial relationship between the building and the surrounding risk body is identified by using the hyperspectral image and the terrain data, and the external influence parameter is generated, which replaces the manual investigation of the surrounding environmental risk. Finally, the safety evaluation result of the building is generated by inputting the above parameters into the preset evaluation model, and an automatic processing flow from data acquisition to result output is constructed, which improves the efficiency of urban building safety evaluation.

[0104] Based on the above-mentioned second embodiment, a third embodiment of the city building safety evaluation method of the present application is proposed. Please refer to Figure 3 , Figure 3 is a sub-process schematic diagram in the third embodiment of the city building safety evaluation method of the present application.

[0105] In the present embodiment, step S4 comprises:

[0106] S41: Based on the hyperspectral image, an image segmentation and classification algorithm is used to identify a risk region, and boundary coordinate information of the risk region is extracted, the risk region including open channels, water bodies, foundation pits, and underground tunnels;

[0107] S42: According to the terrain data and a preset slope threshold, a slope region is identified, and boundary coordinate information of the slope region is extracted;

[0108] S43: According to the boundary coordinate information of the risk region and the boundary coordinate information of the slope region, a minimum horizontal distance of each building contour boundary to the boundary of each type of risk region is determined;

[0109] S44: The minimum horizontal distance is compared with a preset risk safety threshold, and based on the comparison result, the external influence parameter is generated.

[0110] It should be noted that the image segmentation and classification algorithm divides the image into regions with similar spectral characteristics, and assigns each type of region with a corresponding ground object category label (such as water body, building, foundation pit, etc.). The boundary coordinate information refers to the coordinate data of the target region boundary in geographic space. The slope threshold represents the limit value of the slope of the terrain change, and a slope risk is considered to exist when the value is higher than the threshold. The minimum horizontal distance refers to the nearest Euclidean distance between the building boundary and the risk region boundary in the horizontal direction.

[0111] Specifically, the hyperspectral image is used to perform image segmentation and spectral classification processing on the region to be evaluated, to identify ground object regions with typical spectral characteristics, including open channels, water bodies, foundation pits, and underground tunnels. For each type of identified risk region, the boundary contour information of its two-dimensional space range is extracted to form a polygon boundary coordinate set, laying a foundation for subsequent spatial relationship calculation. Subsequently, slope analysis is performed based on the terrain data (DEM). By calculating the local elevation change rate of each grid cell, the slope threshold is compared, and the region with a slope greater than the threshold is determined as a potential slope region, and its boundary coordinate information is extracted and included in the risk region set together with the risk region extracted by the hyperspectral image.

[0112] Further, for each target building, its building contour boundary is extracted and spatial analysis is performed with all the risk region boundaries described above. The minimum horizontal distance from the building boundary to each type of risk region boundary is calculated, obtaining a set of shortest spatial distance indicators between the building and each type of risk region. Finally, the minimum distance values are compared with the safety distance threshold set for each type of risk to determine whether the building is within the risk interference range. If less than the threshold, it is determined that the risk item has an impact on the building. Based on the impact determination results of each risk item, external influence parameters are generated, which can be standardized input for risk assessment using polynomial mapping, risk level assignment or logic rule normalization.

[0113] By combining the feature recognition capability of hyperspectral images and the slope analysis capability of terrain data, various environmental risk regions related to building safety can be automatically identified and their boundary coordinate information accurately extracted. On this basis, distance calculation between buildings and various types of risk regions is realized through spatial geometric analysis, and the potential interference degree of environmental risk to buildings is objectively quantified by comparing with the preset safety threshold. This processing method replaces the cumbersome process of traditional manual identification and on-site measurement of risk region location, realizes standardized, efficient and data-driven processing of external risk identification, provides indispensable environmental factor support for building safety comprehensive evaluation, and improves the applicability and processing efficiency of the entire system in large-scale urban scenes.

[0114] Based on the second embodiment described above, in this embodiment, step S5 comprises:

[0115] S51: Based on the preset multi-dimensional vector format, the change parameter, the settlement parameter and the external influence parameter are constructed into a feature vector to obtain multi-dimensional risk input data;

[0116] S52: Based on the preset evaluation model, a preset index weight configuration strategy is called to assign weight values corresponding to the change parameter, the settlement parameter and the external influence parameter respectively, and the corresponding weighted sub-scores are determined according to the assignment results;

[0117] S53: Based on the model aggregation rule of the preset evaluation model, the weighted sub-scores are summed up, and based on the summation result, the safety evaluation results of the target buildings are generated.

[0118] It should be noted that the feature vector construction refers to the unified organization of multiple numerical indicators into an ordered sequence form as the standard input format for model calculation. The multi-dimensional risk input data is a multi-dimensional numerical set composed of change parameters, settlement parameters, external influence parameters, etc., representing different types of risk states faced by the building. The preset index weight configuration strategy is a pre-set configuration scheme for setting the relative importance of each indicator (such as change, settlement, external risk). The weighted sub-score refers to the risk score obtained by multiplying the single indicator by the corresponding weight, representing the independent contribution value of each factor to the total score. The model aggregation rule is a strategy for combining multiple weighted sub-scores into a comprehensive score.

[0119] Specifically, according to the preset multi-dimensional vector format, the structural change parameters, settlement parameters and external influence parameters extracted for each target building are spliced in a fixed order to construct the feature vector of the building. This vector completely expresses the structural state, displacement trend and external risk situation, serving as the standardized input for subsequent model scoring. The preset safety evaluation model is called, and according to the weight configuration strategy built in the model, the change parameters, settlement parameters and external influence parameters are assigned corresponding index weights. The system calculates the weighted sub-score of each type of parameter according to the set weight and corresponding parameter value, thereby evaluating the independent contribution degree of this type of risk factor to the overall safety state of the building. According to the aggregation rule set in the model, all sub-scores are summed to generate the total risk score of the building. Subsequently, the system divides the building into different safety level categories (such as low risk, medium risk, high risk) according to the score and risk level division standard, and outputs the corresponding safety evaluation result for subsequent sorting, screening or management.

[0120] This step can integrate risk data from different dimensions uniformly by using the feature vector construction mechanism, so that various structural, safety and environmental indicators have standardized expression forms, facilitating input into the evaluation model for processing. Combined with the weight configuration strategy, the importance of each factor in scoring can be flexibly adjusted according to the actual situation, making the evaluation result more targeted and professional. Finally, the unified output of multi-factor risk scoring is realized through the model aggregation rule, effectively improving the automation degree of building safety evaluation in data-driven, model processing and level division, significantly improving the efficiency and objectivity of large-scale urban building group risk identification and fine management.

[0121] Based on the above second embodiment, in this embodiment, after step S5, it further includes:

[0122] S5a: sorting each target building based on the safety evaluation result;

[0123] S5b: If the safety evaluation results of multiple target buildings are the same, obtain the settlement cumulative parameter in the settlement parameters corresponding to the multiple target buildings and the structure change index in the change parameters;

[0124] S5c: Based on the settlement cumulative parameter and the structure change index, perform two-layer and three-layer sorting to obtain a target risk screening hierarchical sequence.

[0125] It should be noted that the settlement cumulative parameter is the cumulative vertical settlement of the building monitoring point in the observation period. The structure change index is a numerical index calculated based on the time series difference of the building profile. The risk screening hierarchical sequence is a building priority list formed according to the sorting rules, which is used to guide the subsequent investigation, reinforcement or supervision decision.

[0126] Specifically, based on the score results output by the aforementioned safety evaluation model, all target buildings are sorted according to the risk score value from high to low to generate a preliminary risk priority list. The list is used to mark high-risk buildings that need to be paid attention to in the city area. Subsequently, the system performs a duplicate checking operation on the sorting results, and if it is found that there are multiple buildings with the same safety score value, it is considered that these buildings cannot be further distinguished in the first evaluation dimension. Therefore, the system extracts the "settlement cumulative parameter" in the settlement parameters corresponding to these buildings, and performs a second layer sorting on it to identify those with higher risk in the deformation history. If there are still buildings with the same score in the second layer sorting, the system will further extract the structure change index, which represents the change frequency or intensity of the building expansion and reconstruction, and perform a third layer sorting based on it to distinguish those with higher long-term structural disturbance risk.

[0127] This step introduces the settlement cumulative parameter and the structure change index as the second and third layer discrimination basis based on the comprehensive safety score sorting, and constructs a multi-level risk sorting mechanism. This mechanism not only solves the problem of not being able to distinguish the priority of buildings when the score is repeated, but also improves the accuracy and rationality of the sorting by introducing more detailed deformation and structural adjustment information. Compared with the traditional single value sorting method, this method can output a stable and fine risk hierarchical sequence, which helps city managers to quickly and accurately identify the building targets that need to be prioritized for investigation and intervention under the condition of limited resources, thereby improving the accuracy and effectiveness of building group risk screening.

[0128] The embodiment obtains a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, terrain data and building contour data of a region to be evaluated; identifies spatial form change information of each target building in the region to be evaluated based on the optical remote sensing image and the building contour data, and generates change parameters for describing structural adjustment features; generates an interferogram based on the synthetic aperture radar image, extracts corresponding deformation monitoring points, and generates settlement parameters reflecting building displacement changes; identifies spatial relationship information of the target building and a surrounding environment risk body based on the hyperspectral image and the terrain data, and generates external influence parameters; and generates safety evaluation results of each target building based on the change parameters, the settlement parameters, the external influence parameters and a preset evaluation model. The embodiment obtains the synthetic aperture radar image, the optical remote sensing image, the hyperspectral image, the terrain data and the building contour data, establishes a multi-source data basis required for urban building safety evaluation, and avoids an inefficient manner of manually collecting information one by one. Further, the spatial form change information of the building is extracted based on the optical remote sensing image and the building contour data, the structural adjustment features can be automatically identified and the change parameters are generated, and a traditional manual identification means for structural reconstruction and expansion is replaced. Meanwhile, the interferogram is generated based on the synthetic aperture radar image, and the deformation monitoring points are extracted, so that remote sensing monitoring of building displacement changes can be realized in a large range without ground equipment. In addition, the spatial relationship of the building and the surrounding risk body is identified based on the hyperspectral image and the terrain data, and the external influence parameters are generated, so that manual investigation of the surrounding environment risk is replaced. Finally, the above parameters are uniformly input into the preset evaluation model to generate the safety evaluation results of the building, and an automatic processing flow from data acquisition to result output is constructed, and the efficiency of urban building safety evaluation is improved.

[0129] Please refer to Figure 4 , Figure 4 Figure 1 is a schematic diagram of a building safety evaluation index system in an embodiment of the urban building safety evaluation method of the present application. As shown in Figure 1, in an embodiment, a comprehensive evaluation system and method for urban existing building safety based on optical remote sensing and InSAR technology are provided. The specific steps are as follows. Figure 4

[0130] Step 1: According to the determined target region, SAR images with optimal time and spatial baselines, high-precision DEM data, optical and hyperspectral data of the target region, building vector data and the like are obtained. An existing building safety evaluation system is established. The first-level indexes include building safety hazards, foundation site safety hazards and external risks. The building safety hazards include reconstruction and expansion, height change, comprehensive building settlement rate and building cumulative settlement indexes. The foundation site hazards include ground deformation rate and building density indexes. The external risks include open river and open channel, foundation pit and tunnel and mountain slope indexes.

[0131] ​Step two: Establishing the housing reconstruction, height change, and building density index based on optical remote sensing technology. Import the optical and hyperspectral image data of the target area, and extract the building targets through building frame vector data or image processing technology. For the building reconstruction index, select the two closest times from a series of data collected at different times for comparison and estimation, calculate the reconstruction index for this time, and the formula is shown in (1). Process the above-mentioned for a series of images to obtain a sequence of reconstruction indexes, and calculate the average value of the sequence as the building reconstruction index A, and the formula is shown in (2).

[0132]

[0133] where i represents the time, △change represents the number of pixels in the building area that have changed at this time and the previous time, area represents the number of pixels contained in the building frame, and t represents the number of time points in the calculation period.

[0134] The height change index and reconstruction index have the same technical route. Estimate the height and reconstruct the height to estimate the height change, and then calculate the average value of each time point height change index as the building height change index B. The calculation formulas (3) and (4) are as follows.

[0135]

[0136] where i represents the time, △h represents the building height change at this time and the previous time, H represents the initial height of the building, and t represents the number of time points in the calculation period.

[0137] Grid the target area, and use external reliable land classification data sets to calculate the building density index F according to the divided grid. The calculation formula is shown in (5).

[0138]

[0139] where buildingarea represents the number of pixels in the building grid classified as building, and gridarea represents the number of all pixels in the grid.

[0140] Step three: Establishing external risk indexes based on optical remote sensing technology, including open river, open channel, foundation pit tunnel, and mountain slope indexes. Extract the open river, open channel, and foundation pit tunnel regions through image segmentation and recognition technology, and extract the mountain slope region through DEM. Calculate the planar distance from the building frame range to the extracted open river, open channel, foundation pit tunnel, and mountain slope region. The open river, open channel, foundation pit tunnel, and mountain slope indexes are represented by G1-G3, and the calculation formula is shown in (6).

[0141]

[0142] where e represents the risk order, dist represents the nearest distance from the building to the risk area, and threshold represents the minimum risk safety distance.

[0143] Step four: Establish the building subsidence rate, building cumulative subsidence, and ground subsidence rate indicators based on InSAR technology. Import the SAR image and generate the interferogram and InSAR deformation monitoring point cloud using InSAR technology, including the monitoring point height, deformation amount, and deformation rate parameters. First, perform monitoring point classification and screening, and based on the same classification rule, divide the InSAR monitoring points into two categories: building monitoring points and ground monitoring points. For ground monitoring points, the center point of the building outer frame is taken as the target point, and the surrounding ground monitoring point subsidence rate is used for spatial interpolation to calculate the building ground subsidence rate indicator E, as shown in formula (7).

[0144] [E = f g (x,y)]]> (7)

[0145] Fg(·) represents the spatial interpolation function established by the surrounding ground monitoring points, and xy represents the coordinates of the center point of the building outer frame.

[0146] For building monitoring points, the InSAR point coherence coefficient is extracted from each set of master-slave image coherence coefficient maps generated by InSAR technology, and the arithmetic mean is calculated as the average coherence coefficient. According to the building outer frame vector or optical remote sensing identification method, the InSAR points within the building range are extracted, the monitoring point deformation rate attribute is extracted, and the coherence weighted calculation is performed to obtain the building subsidence rate indicator C, as shown in formula (8).

[0147]

[0148] where wp represents the coherence weight of the monitoring point, vp represents the deformation rate parameter of the point, and n represents the number of building monitoring points. The calculation of the coherence weight can be performed using linear interpolation and other methods.

[0149] The maximum cumulative subsidence of each InSAR monitoring point of the building within the monitoring time period is extracted as the building cumulative subsidence indicator D. When calculating the cumulative subsidence, the first period of subsidence data should be zeroed, as shown in formula (9).

[0150]

[0151] where d t p represents the cumulative subsidence of the pth monitoring point of the building at time t, m represents the InSAR monitoring time point, and n represents the number of building monitoring points.

[0152] Step five: build a comprehensive evaluation system weight model, set the weight score of each secondary index and calculate the final evaluation score of the building. The evaluation index weight can be set by subjective weighting method, which can use expert experience method and weight distribution method based on analytic hierarchy process. The questionnaire for setting the weight by expert experience method is shown in Table 1, and the weight score is set according to the importance of the index to the final building risk evaluation. After collecting the questionnaire, the average value of the expert weight is calculated as the weight of the evaluation system index.

[0153] Table 1 Expert questionnaire table of evaluation index system

[0154]

[0155] wherein W x represents the weight score of the secondary index, and the evaluation score of the building can be calculated by combining the weight score and the index state. The calculation formula is shown in equation (10).

[0156] Score =∑w index ×g index , index = A, B, C, D, E, F, G1~G3 (10)

[0157] wherein score is the final score, w index is the weight of the secondary index, and g index is the index risk state. The function formula of each index risk state is shown in equation (11).

[0158]

[0159] Step six: calculate the index score of each target building in the target area, and sort the risk according to the following steps:

[0160] 1) Sort according to the total score in the first level;

[0161] 2) For buildings with the same total score, sort according to the building and foundation site hidden danger score in the second level;

[0162] 3) For buildings with the same building and foundation site hidden danger score, sort according to the cumulative settlement index D in the third level;

[0163] 4) Sort the building risk sorting results and mark the serial number. Buildings with the same score are marked with the same serial number.

[0164] After the above steps of sorting and marking, the safety evaluation results of the target buildings in the target area can be obtained, which provides data basis for subsequent precise screening and management.

[0165] The embodiment of the present application also provides a city building safety evaluation device, which is described in detail in the city building safety evaluation method. Figure 5 , Figure 5A module structure schematic diagram of a city building safety evaluation device is provided in the embodiment of the present application, and the city building safety evaluation device comprises:

[0166] The data acquisition module 501 is configured to acquire synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data and building contour data of a region to be evaluated.

[0167] The change parameter module 502 is configured to identify spatial form change information of each target building in the region to be evaluated based on the optical remote sensing images and the building contour data, and generate change parameters for describing structural adjustment features.

[0168] The settlement parameter module 503 is configured to generate an interferogram based on the synthetic aperture radar images, extract corresponding deformation monitoring points, and generate settlement parameters reflecting building displacement changes.

[0169] The external influence parameter module 504 is configured to identify spatial relationship information between the target buildings and surrounding environmental risk bodies based on the hyperspectral images and the terrain data, and generate external influence parameters.

[0170] The target module 505 is configured to generate safety evaluation results of the target buildings based on the change parameters, the settlement parameters, the external influence parameters and a preset evaluation model.

[0171] The city building safety evaluation device provided in the embodiment of the present application adopts the city building safety evaluation method in the above embodiment, and can solve the technical problem of how to improve the efficiency of city building safety evaluation. Compared with the prior art, the city building safety evaluation device provided in the embodiment of the present application has the same beneficial effects as the city building safety evaluation method provided in the above embodiment, and other technical features in the city building safety evaluation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0172] The present application provides a city building safety evaluation device, which comprises at least one processor and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the city building safety evaluation method in the above embodiment.

[0173] Reference will be made to the following Figure 6 , Figure 6 The device structure schematic diagram of a hardware running environment involved in the city building safety evaluation method in the embodiment of the present application is shown, which shows a structure schematic diagram of a city building safety evaluation device suitable for implementing the embodiment of the present application. Figure 6The illustrated urban building safety evaluation device is merely an example and should not bring any limitation to the function and use range of the embodiments of the present application.

[0174] As shown in Figure 6 The urban building safety evaluation device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. In the RAM 1004, various programs and data required for operation of the urban building safety evaluation device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the urban building safety evaluation device to communicate with other devices wirelessly or by wire to exchange data. Although the urban building safety evaluation device having various systems is illustrated in the figure, it should be understood that all of the illustrated systems are not required to be implemented or provided. More or fewer systems can be alternatively implemented or provided.

[0175] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product including a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are performed.

[0176] The urban building safety evaluation device provided by the present application adopts the urban building safety evaluation method in the above-mentioned embodiments, and can solve the technical problem of how to improve the efficiency of urban building safety evaluation. Compared with the prior art, the urban building safety evaluation device provided by the present application has the same beneficial effects as the urban building safety evaluation method provided by the above-mentioned embodiments, and other technical features in the urban building safety evaluation device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0177] It should be understood that portions of the application disclosed can be implemented in hardware, software, firmware, or combinations thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0178] The above description is merely illustrative of the application and not restrictive thereof; the scope of the application is not limited to the above description, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the application, which should be encompassed within the scope of the application. Therefore, the scope of the application should be subject to the protection scope of the claims.

[0179] The application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the urban building safety evaluation method in the above-described embodiments.

[0180] The computer-readable storage medium described above carries one or more programs, which, when executed by the urban building safety evaluation device, cause the urban building safety evaluation device to: acquire a synthetic aperture radar image, an optical remote sensing image, a hyperspectral image, terrain data, and building contour data of a region to be evaluated; identify spatial form change information of each target building in the region to be evaluated based on the optical remote sensing image and the building contour data, and generate a change parameter for describing a structural adjustment feature; generate an interferogram based on the synthetic aperture radar image, extract corresponding deformation monitoring points, and generate a settlement parameter reflecting building displacement changes; identify spatial relationship information between the target building and a surrounding environmental risk body based on the hyperspectral image and the terrain data, and generate an external influence parameter; and generate a safety evaluation result of each target building based on the change parameter, the settlement parameter, the external influence parameter, and a preset evaluation model. The computer program code for executing the operations of the application can be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on a user computer, partially on a user computer, as a separate software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0181] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.

[0182] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the unit itself.

[0183] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e. computer program) for executing the above-mentioned urban building safety evaluation method, and can solve the technical problem of how to improve the efficiency of urban building safety evaluation. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the urban building safety evaluation method provided by the above-mentioned embodiments, which will not be repeated here.

[0184] The embodiment of the present application provides a computer program product, which comprises a computer program. When the computer program is executed by a processor, the steps of the urban building safety evaluation method are realized.

[0185] The computer program product provided by the present application can solve the technical problem of how to improve the efficiency of urban building safety evaluation. Compared with the prior art, the computer program product provided by the embodiment of the present application has the same beneficial effects as the urban building safety evaluation method provided by the above-mentioned embodiments, which will not be repeated here.

[0186] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation according to the content of the specification and drawings of the present application, or direct or indirect application in other related technical fields, is also included in the patent processing scope of the present application.

Claims

1. A method for evaluating the safety of urban buildings, characterized in that, The method includes: Acquire synthetic aperture radar images, optical remote sensing images, hyperspectral images, topographic data, and building outline data of the area to be evaluated; Based on the optical remote sensing images and the building outline data, the spatial morphological change information of each target building in the area to be evaluated is identified, and change parameters for describing structural adjustment characteristics are generated. An interferogram is generated based on the synthetic aperture radar image, and the corresponding deformation monitoring points are extracted to generate settlement parameters that reflect changes in building displacement. Based on the hyperspectral image and the terrain data, the spatial relationship information between the target building and the surrounding environmental risk bodies is identified, and external impact parameters are generated; Based on the changed parameters, the settlement parameters, the external influence parameters, and the preset evaluation model, safety evaluation results are generated for each target building.

2. The method as described in claim 1, characterized in that, The step of identifying spatial morphological change information of each target building in the area to be evaluated based on the optical remote sensing image and the building outline data, and generating change parameters to describe the structural adjustment characteristics, includes: The optical remote sensing images at each time point are corrected to obtain multiple corrected remote sensing images; Based on the building outline data, the building area image corresponding to the target building is extracted from the multiple corrected remote sensing images, and the boundary changes of the target building between different time points are extracted by the image difference analysis algorithm. Based on the boundary change results, structural adjustment characteristic indicators are determined, including the building area change rate and the boundary expansion ratio. The time series of the structural adjustment characteristic indicators are normalized and weighted to generate the change parameters used to describe the structural adjustment characteristics.

3. The method as described in claim 1, characterized in that, The step of generating an interferogram based on the synthetic aperture radar image, extracting the corresponding deformation monitoring points, and generating settlement parameters reflecting changes in building displacement includes: The synthetic aperture radar image is preprocessed to obtain the interferogram and coherence coefficient map. The preprocessing includes registration, speckle removal, and interferogram generation. Based on the building outline data, the monitoring points in the interferogram are divided into building monitoring points and ground monitoring points. Based on the coherence coefficient map, points in the building monitoring points with coherence lower than a preset coherence threshold are removed. The vertical deformation and deformation rate of the building monitoring points after removal were extracted at different time points and weighted averaged to obtain the building settlement rate parameters. Based on the building settlement rate parameter and the maximum cumulative deformation of the building monitoring point relative to the initial time point, the settlement parameter reflecting the building displacement change is generated.

4. The method as described in claim 1, characterized in that, The step of identifying the spatial relationship information between the target building and surrounding environmental risk bodies based on the hyperspectral image and the terrain data, and generating external impact parameters, includes: Based on the hyperspectral image, an image segmentation and classification algorithm is used to identify risk areas and extract the boundary coordinate information of the risk areas, which include open channels, water bodies, foundation pits and underground tunnels. Based on the terrain data and the preset slope threshold, the slope area is identified, and the boundary coordinate information of the slope area is extracted; Based on the boundary coordinates of the risk area and the boundary coordinates of the slope area, determine the minimum horizontal distance from the boundary of each building outline to the boundary of each type of risk area; The minimum horizontal distance is compared with a preset risk safety threshold, and the external influence parameter is generated based on the comparison result.

5. The method as described in claim 1, characterized in that, The step of generating safety evaluation results for each target building based on the changed parameters, the settlement parameters, the external influence parameters, and the preset evaluation model includes: Based on a preset multidimensional vector format, feature vectors are constructed from the changed parameters, the settlement parameters, and the external influence parameters to obtain multidimensional risk input data; Based on the preset evaluation model, the preset index weight configuration strategy is invoked to assign weight values ​​to the change parameter, the settlement parameter and the external influence parameter respectively, and the corresponding weighted sub-score is determined according to the assignment results; Based on the model aggregation rules of the preset evaluation model, the weighted sub-scores are summed, and based on the summation results, the safety evaluation results of each target building are generated.

6. The method as described in claim 1, characterized in that, After the step of generating safety evaluation results for each target building based on the changed parameters, the settlement parameters, the external influence parameters, and the preset evaluation model, the method further includes: Based on the safety assessment results, each target building is ranked. If multiple target buildings have the same safety evaluation results, obtain the cumulative settlement parameter and the structural change index from the settlement parameters and change parameters corresponding to the multiple target buildings. Based on the cumulative settlement parameters and the structural change index, a second-level and third-level sorting is performed to obtain the target risk screening classification sequence.

7. A device for evaluating the safety of urban buildings, characterized in that, The device includes: The data acquisition module is used to acquire synthetic aperture radar images, optical remote sensing images, hyperspectral images, terrain data, and building outline data of the area to be evaluated. The parameter change module is used to identify the spatial morphological change information of each target building in the area to be evaluated based on the optical remote sensing image and the building outline data, and generate change parameters to describe the structural adjustment characteristics. The settlement parameter module is used to generate an interferogram based on the synthetic aperture radar image, extract the corresponding deformation monitoring points, and generate settlement parameters that reflect changes in building displacement. The external impact parameter module is used to identify the spatial relationship information between the target building and the surrounding environmental risk bodies based on the hyperspectral image and the terrain data, and to generate external impact parameters. The target module is used to generate safety evaluation results for each target building based on the changed parameters, the settlement parameters, the external influence parameters, and the preset evaluation model.

8. A computer device, characterized in that, The device includes: a memory, a processor, and an urban building safety assessment program stored in the memory and executable on the processor, the urban building safety assessment program being configured to implement the steps of the urban building safety assessment method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores an urban building safety evaluation program, which, when executed by a processor, implements the steps of the urban building safety evaluation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the urban building safety evaluation method as described in any one of claims 1 to 6.

Images