Deformation monitoring visualization method and system based on multi-source heterogeneous data fusion

Abstract

The disclosure provides a deformation monitoring visualization method and system based on multi-source heterogeneous data fusion, and relates to the technical field of data processing. The method comprises the following steps: acquiring multi-source heterogeneous deformation monitoring data corresponding to a target monitoring area, and performing data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; using data category information corresponding to the classified deformation monitoring data, performing standardized conversion processing on the classified deformation monitoring data to obtain standard deformation monitoring data; generating a surface domain deformation texture using the standard surface domain deformation data, generating a point position continuous deformation texture using the standard point position deformation data, and performing fusion processing on the surface domain deformation texture and the point position continuous deformation texture to obtain a fused deformation texture; performing spatial matching processing on the fused deformation texture and three-dimensional scene data corresponding to the target monitoring area, and performing three-dimensional rendering processing on the fused deformation texture based on the spatial matching processing result to obtain a deformation monitoring visualization result.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more specifically, to a deformation monitoring visualization method and system based on multi-source heterogeneous data fusion. Background Technology

[0002] In engineering scenarios such as hydropower station slopes, dam slopes on both sides, and reservoir landslides, surface deformation is a crucial indicator for evaluating the operational safety of the project. Existing engineering monitoring typically combines multiple monitoring data to analyze the deformation state of the engineering area.

[0003] However, different monitoring data often differ in their data formation methods and expression rules. Existing processing methods typically require processing different monitoring data separately, making it difficult to establish spatial and numerical correspondences between them. Furthermore, current display methods usually present different monitoring data separately or overlay them, making it difficult to directly reflect the numerical correlations between different monitoring data at the same location. When discrepancies exist between different monitoring data, engineers still need to rely on manual comparison for judgment, resulting in low intuitiveness in interpreting monitoring results. Summary of the Invention

[0004] The purpose of this disclosure is to provide a deformation monitoring visualization method based on multi-source heterogeneous data fusion, a deformation monitoring visualization system based on multi-source heterogeneous data fusion, an electronic device, and a computer-readable storage medium, which can improve the spatial consistency and visualization intuitiveness of deformation monitoring results by classifying, standardizing, transforming, texture fusion, and 3D rendering multi-source heterogeneous deformation monitoring data.

[0005] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0006] According to a first aspect of the present disclosure, a deformation monitoring visualization method based on multi-source heterogeneous data fusion is provided, comprising: acquiring multi-source heterogeneous deformation monitoring data corresponding to a target monitoring area, and performing data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein the classified deformation monitoring data includes surface deformation data and point deformation data; using the data category information corresponding to the classified deformation monitoring data, performing standardization conversion processing on the classified deformation monitoring data to obtain standard deformation monitoring data; wherein the standard deformation monitoring data includes standard surface deformation data converted from the surface deformation data, and standard point deformation data converted from the point deformation data; generating surface deformation texture using the standard surface deformation data, generating point continuous deformation texture using the standard point deformation data, and performing fusion processing on the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture; performing spatial matching processing on the fused deformation texture and the three-dimensional scene data corresponding to the target monitoring area, and performing three-dimensional rendering processing on the fused deformation texture based on the spatial matching processing result to obtain a deformation monitoring visualization result corresponding to the target monitoring area.

[0007] According to a second aspect of the present disclosure, a deformation monitoring visualization system based on multi-source heterogeneous data fusion is provided. The system includes: a data source layer, configured to acquire multi-source heterogeneous deformation monitoring data corresponding to a target monitoring area, and perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein the classified deformation monitoring data includes surface deformation data and point deformation data; and a data parsing layer, configured to utilize data category information corresponding to the classified deformation monitoring data to perform standardization transformation processing on the classified deformation monitoring data to obtain standard deformation monitoring data; wherein the standard deformation monitoring data includes data converted from the surface deformation data. The system includes: standard surface deformation data and standard point deformation data converted from the point deformation data; a fusion processing calculation layer, used to generate surface deformation textures using the standard surface deformation data, generate continuous point deformation textures using the standard point deformation data, and perform fusion processing on the surface deformation textures and the continuous point deformation textures to obtain a fused deformation texture; and a three-dimensional scene rendering layer, used to perform spatial matching processing on the fused deformation textures and the three-dimensional scene data corresponding to the target monitoring area, and perform three-dimensional rendering processing on the fused deformation textures based on the spatial matching processing results to obtain the deformation monitoring visualization results corresponding to the target monitoring area.

[0008] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions that, when executed by the processor, implement the deformation monitoring visualization method based on multi-source heterogeneous data fusion as described in the first aspect.

[0009] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the deformation monitoring visualization method based on multi-source heterogeneous data fusion as described in the first aspect.

[0010] The technical solutions provided in this disclosure may have the following beneficial effects: According to the deformation monitoring visualization method based on multi-source heterogeneous data fusion in this example embodiment, on the one hand, by classifying the multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, classified deformation monitoring data including surface deformation data and point deformation data are obtained. This allows deformation monitoring data with different spatial manifestations to enter the corresponding processing according to data categories, reducing the problem of unclear spatial correspondence caused by mixed processing of different types of data. On the other hand, by using the data category information corresponding to the classified deformation monitoring data for standardization conversion, standard deformation monitoring data including standard surface deformation data and standard point deformation data are obtained, enabling surface deformation data and point deformation data to be processed according to data categories. The data can be transformed into a consistent data representation, facilitating subsequent texture generation and fusion processing. Furthermore, by generating surface deformation textures using standard surface deformation data and point-to-point continuous deformation textures using standard point deformation data, and then fusing these textures, the continuous deformation information within the surface area and the high-precision deformation information at the point locations can be fused together at the texture level. Additionally, by spatially matching the fused deformation textures with the corresponding 3D scene data of the target monitoring area, and then performing 3D rendering based on the spatial matching results, the fused deformation information can be presented in the 3D space of the target monitoring area. Therefore, this approach offers advantages such as improved spatial consistency, enhanced fusion expression capabilities, and improved visualization intuitiveness of deformation monitoring results.

[0011] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0012] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0013] Figure 1 The illustration shows a flowchart of a deformation monitoring visualization method based on multi-source heterogeneous data fusion according to some embodiments of the present disclosure.

[0014] Figure 2 The schematic diagram illustrates a flow chart of a standardized conversion process according to some embodiments of the present disclosure.

[0015] Figure 3 The diagram illustrates a surface deformation texture according to some embodiments of the present disclosure.

[0016] Figure 4 A schematic diagram of a point-to-point continuous deformation texture is shown according to some embodiments of the present disclosure.

[0017] Figure 5 A schematic diagram of a fused deformable texture according to some embodiments of the present disclosure is shown.

[0018] Figure 6 The diagram illustrates a block diagram of a deformation monitoring visualization system based on multi-source heterogeneous data fusion according to some embodiments of the present disclosure.

[0019] Figure 7 The schematic diagram illustrates the structure of a deformation monitoring visualization system based on multi-source heterogeneous data fusion according to some embodiments of the present disclosure.

[0020] Figure 8 The schematic diagram illustrates the structural schematic of a computer system of an electronic device according to some embodiments of the present disclosure.

[0021] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of systems and methods consistent with some aspects of this specification as detailed in the appended claims.

[0023] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0025] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, systems, steps, etc., can be employed. In other instances, well-known methods, systems, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0026] Furthermore, the accompanying drawings are for illustrative purposes only and are not necessarily drawn to scale. The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0027] In engineering scenarios such as hydropower station slopes, dam slopes on both sides, and reservoir landslides, surface deformation is a crucial indicator for evaluating the operational safety of the project. Due to the large area and complex terrain of the engineering projects, relevant engineering monitoring typically requires the analysis of deformation status using multiple monitoring data. These monitoring data include both data reflecting the overall trend of regional changes and data reflecting precise changes at local measuring points; different types of data differ in spatial range, data density, and measurement accuracy.

[0028] In related technologies, different monitoring data often differ in terms of data formation methods, data expression rules, and spatial description methods, leading to the need for separate processing of different monitoring data. Due to differences in file formats, coordinate references, numerical units, and data organization methods, it is difficult to establish spatial and numerical correspondences between different monitoring data, which in turn affects the subsequent comprehensive analysis of the deformation state of the engineering area.

[0029] Meanwhile, the current display methods typically present different monitoring data separately or overlay them, making it difficult to directly reflect the numerical correlation between different monitoring data at the same spatial location. When the deformation results of different monitoring data differ, engineers still need to rely on manual comparison for judgment, resulting in low intuitiveness and efficiency in judging monitoring results.

[0030] To address all or part of the technical problems in the aforementioned related technologies, this disclosure provides an example embodiment of a deformation monitoring visualization method based on multi-source heterogeneous data fusion. This method can be implemented using a deformation monitoring visualization system based on multi-source heterogeneous data fusion. Figure 1 The illustration schematically shows a flowchart of a deformation monitoring visualization method based on multi-source heterogeneous data fusion according to some embodiments of the present disclosure. (Reference) Figure 1 As shown, this deformation monitoring visualization method based on multi-source heterogeneous data fusion may include the following steps: Step S110: Obtain multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, and perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein, the classified deformation monitoring data includes surface deformation data and point deformation data; Step S120: Using the data category information corresponding to the classified deformation monitoring data, the classified deformation monitoring data is standardized and converted to obtain standard deformation monitoring data; wherein, the standard deformation monitoring data includes standard surface deformation data converted from surface deformation data and standard point deformation data converted from point deformation data. Step S130: Generate a surface deformation texture using standard surface deformation data, generate a point continuous deformation texture using standard point deformation data, and perform a fusion process on the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture. Step S140: Spatial matching processing is performed using the fused deformed texture and the corresponding 3D scene data of the target monitoring area. Based on the spatial matching processing result, the fused deformed texture is rendered in 3D to obtain the deformation monitoring visualization result corresponding to the target monitoring area.

[0031] According to the deformation monitoring visualization method based on multi-source heterogeneous data fusion in this example embodiment, on the one hand, by classifying the multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, classified deformation monitoring data including surface deformation data and point deformation data are obtained. This allows deformation monitoring data with different spatial manifestations to enter the corresponding processing according to data categories, reducing the problem of unclear spatial correspondence caused by mixed processing of different types of data. On the other hand, by using the data category information corresponding to the classified deformation monitoring data for standardization conversion, standard deformation monitoring data including standard surface deformation data and standard point deformation data are obtained, enabling surface deformation data and point deformation data to be processed according to data categories. The data can be transformed into a consistent data representation, facilitating subsequent texture generation and fusion processing. Furthermore, by generating surface deformation textures using standard surface deformation data and point-to-point continuous deformation textures using standard point deformation data, and then fusing these textures, the continuous deformation information within the surface area and the high-precision deformation information at the point locations can be fused together at the texture level. Additionally, by spatially matching the fused deformation textures with the corresponding 3D scene data of the target monitoring area, and then performing 3D rendering based on the spatial matching results, the fused deformation information can be presented in the 3D space of the target monitoring area. Therefore, this approach offers advantages such as improved spatial consistency, enhanced fusion expression capabilities, and improved visualization intuitiveness of deformation monitoring results.

[0032] The deformation monitoring visualization method based on multi-source heterogeneous data fusion in this example embodiment will be further explained below.

[0033] Step S110: Obtain multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, and perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein, the classified deformation monitoring data includes surface deformation data and point deformation data.

[0034] The target monitoring area can represent the engineering spatial area requiring deformation monitoring, such as the slope of a hydropower station, the slopes on both sides of a dam, a landslide in a reservoir area, or other engineering areas requiring surface deformation monitoring. Multi-source heterogeneous deformation monitoring data can represent deformation monitoring data from different sources, with different data structures, or different spatial representations, such as radar scan data, Interferometric Synthetic Aperture Radar (InSAR) data, numerical simulation data, thermal infrared imaging data, Global Navigation Satellite System (GNSS) measurement point data, total station measurement point data, surveying robot measurement point data, Geographic Tagged Image File Format (GeoTIFF) raster data, Portable Network Graphics (PNG) image data, or Joint Photographic Experts Group (JPEG) image data. Data classification processing can represent the process of dividing multi-source heterogeneous deformation monitoring data into different categories according to the spatial coverage, data source, or data organization characteristics.

[0035] Specifically, multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area can be read, and the spatial coverage of each deformation monitoring data can be used to determine whether it belongs to the area coverage type or the point distribution type. Data that can cover a continuous area or describe the deformation distribution of the area in the form of raster, image, point cloud, etc., can be identified as area deformation data; data formed by multiple discrete measuring points and recording the measuring point positions and deformation values ​​can be identified as point deformation data. Through this step, deformation monitoring data with different spatial manifestations can be classified first, which facilitates subsequent standardization and conversion processing according to the corresponding categories.

[0036] Step S120: Using the data category information corresponding to the classified deformation monitoring data, the classified deformation monitoring data is standardized and converted to obtain standard deformation monitoring data; wherein, the standard deformation monitoring data includes standard surface deformation data converted from surface deformation data and standard point deformation data converted from point deformation data.

[0037] Among these, data category information can represent information describing the data type, data structure, spatial representation, or data source format of the categorized deformation monitoring data. Standardization transformation processing can represent the process of converting spatial and deformation information under different data categories into a unified representation. Standard deformation monitoring data can represent deformation monitoring data formed after standardization transformation processing, capable of participating in subsequent texture generation and fusion processing. Standard area deformation data can represent area-type data with unified spatial and deformation value representations, obtained by transforming area deformation data. Standard point deformation data can represent point-type data with unified spatial and deformation value representations, obtained by transforming point deformation data.

[0038] Specifically, by utilizing the data category information corresponding to the categorized deformation monitoring data, format recognition, spatial information extraction, and deformation information extraction can be performed on the categorized deformation monitoring data. The extracted spatial information is then converted to a unified spatial reference, and the extracted deformation information is converted to a unified numerical unit. For example, for raster data in the geographic tag image file format, the spatial location can be determined based on its geographic reference parameters; for portable network graphic image data or Joint Image Experts Group (JIE) image data, the spatial correspondence can be determined based on control point data; for point-based data, the corresponding spatial location and deformation value can be extracted based on the measurement point coordinate field and deformation value field. Through this step, the area deformation data and point-based deformation data can be transformed from their original heterogeneous representations into standardized deformation monitoring data that can jointly participate in subsequent processing, thereby reducing the impact of incompatibility between different data structures on subsequent fusion processing.

[0039] Step S130: Generate a surface deformation texture using standard surface deformation data, generate a point continuous deformation texture using standard point deformation data, and perform a fusion process on the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture.

[0040] Among them, surface deformation texture can represent texture data generated from standard surface deformation data, used to characterize the deformation distribution within a surface region. Point-to-point continuous deformation texture can represent texture data generated after continuous processing of standard point-to-point deformation data, used to characterize the continuous distribution of point-to-point deformation data within a region. Fusion processing can represent the computational integration of texture data with corresponding spatial positions from surface deformation texture and point-to-point continuous deformation texture. Fusion deformation texture can represent texture data formed after fusion processing, simultaneously containing both surface deformation information and point-to-point deformation information.

[0041] Specifically, standard surface deformation data can be mapped to texture space based on its spatial location and deformation value to generate surface deformation texture; point-to-point continuous deformation texture can be generated by performing continuous calculation based on the measurement point location and deformation value in standard point deformation data. Further, the surface deformation texture and the point-to-point continuous deformation texture can be used as objects to be fused, and their deformation values ​​at corresponding pixel locations can be fused to obtain a fused deformation texture. For example, the fusion process can be performed on a graphics processing unit (GPU), or it can be achieved by using a fragment shader based on a Web Graphics Library (WebGL) to perform parallel sampling and fusion calculations on the texture data at corresponding pixel locations. Through this step, the continuous deformation representation within the surface region and the deformation representation at point locations can be unified into the texture fusion result, improving the continuity and comprehensiveness of deformation information representation.

[0042] Step S140: Spatial matching processing is performed using the fused deformed texture and the corresponding 3D scene data of the target monitoring area. Based on the spatial matching processing result, the fused deformed texture is rendered in 3D to obtain the deformation monitoring visualization result corresponding to the target monitoring area.

[0043] The 3D scene data can represent data used to characterize the 3D spatial morphology of the target monitoring area, such as 3D terrain data, 3D model data, or engineering scene model data. Spatial matching processing can represent the process of determining the mapping position of the fused deformable texture in the 3D scene based on the spatial positional relationship between the fused deformable texture and the corresponding spatial positional relationship in the 3D scene data. 3D rendering processing can represent the process of displaying the fused deformable texture at the corresponding spatial position in the 3D scene data. Deformation monitoring visualization results can represent the display results of presenting the deformation distribution of the target monitoring area in the 3D scene.

[0044] Specifically, a spatial matching relationship can be established between the fused deformable texture and the 3D scene data based on the spatial range, texture coordinates, and scene coordinates corresponding to the fused deformable texture. Then, based on this spatial matching relationship, the fused deformable texture can be mapped to the 3D terrain surface or engineering scene surface corresponding to the target monitoring area, and 3D rendering processing can be performed to obtain the deformation monitoring visualization result. This step allows the fused deformation information to be displayed according to the real spatial location of the target monitoring area, improving the spatial correspondence and intuitiveness of the deformation monitoring results in the engineering scene.

[0045] The contents of steps S110 to S140 will be described in detail below.

[0046] In some embodiments, multi-source heterogeneous deformation monitoring data is classified to obtain classified deformation monitoring data, specifically including the following technical steps: First, the data sources of the multi-source heterogeneous deformation monitoring data are identified to obtain the data source types corresponding to the multi-source heterogeneous deformation monitoring data.

[0047] Specifically, data source identification can refer to the process of determining the source category of multi-source heterogeneous deformation monitoring data based on the data acquisition method, data file characteristics, data field structure, or data content characteristics. Data source type can represent the source category corresponding to the multi-source heterogeneous deformation monitoring data, such as at least one of the following: radar scan data type, satellite interferometry data type, numerical simulation data type, thermal infrared imaging data type, global navigation satellite system measurement point data type, total station measurement point data type, surveying robot measurement point data type, geotagged image file format raster data type, portable network graphic image data type, or Joint Image Experts Group image data type.

[0048] Specifically, the input multi-source heterogeneous deformation monitoring data can be read for data features, and the corresponding data source type can be determined based on the read data file characteristics, field structure, or content characteristics. For example, data with point cloud location and deformation fields can be identified as radar scan data; data with measurement point coordinates and measurement point deformation values ​​can be identified as discrete measurement point data; data with raster georeferenced features can be identified as raster data; and data with image file features can be identified as image data. This step clarifies the source attributes of different deformation monitoring data before classification, reducing misclassification of data categories caused by mixing data from different sources.

[0049] Then, based on the data source type and the spatial distribution of the multi-source heterogeneous deformation monitoring data, the multi-source heterogeneous deformation monitoring data is classified to obtain surface deformation data and point deformation data; wherein, surface deformation data includes at least one of surface continuous deformation data, raster deformation data and image deformation data, and point deformation data includes discrete point deformation data.

[0050] The spatial distribution can represent the spatial representation of multi-source heterogeneous deformation monitoring data within the target monitoring area, such as continuous area coverage, regular grid distribution, image coverage, or discrete measurement point distribution. Area deformation data can represent data characterizing the deformation distribution of the target monitoring area as continuous regions, grid cells, image regions, or point cloud coverage areas. Point deformation data can represent data characterizing the local deformation of the target monitoring area as discrete measurement point locations and corresponding deformation values. Continuous area deformation data can include at least one of radar scan data, satellite interferometry data, numerical simulation data, or thermal infrared imaging data; discrete point deformation data can include at least one of global navigation satellite system measurement point data, total station measurement point data, or measurement robot measurement point data.

[0051] Specifically, the source category of each deformation monitoring data can be determined based on the data source type, and the coverage method of each deformation monitoring data in the target monitoring area can be determined by combining the spatial distribution form. Data with continuous spatial coverage or that can express the regional deformation distribution can be classified as area deformation data; data composed of multiple discrete measuring points, and expressing the local deformation through the measuring point location and measuring point deformation value, can be classified as point deformation data. Through this step, multi-source heterogeneous deformation monitoring data can be divided into area deformation data and point deformation data, providing a clear data category basis for subsequent corresponding processing.

[0052] Further, refer to Figure 2 As shown, the categorized deformation monitoring data is standardized using the data category information corresponding to the categorized deformation monitoring data to obtain standard deformation monitoring data. The specific technical steps include the following: Step S210: Using data category information, perform format recognition processing on the classified deformation monitoring data to obtain the format recognition result.

[0053] Format recognition processing refers to determining the data format of the categorized deformation monitoring data based on its data carrier format, file characteristics, or field structure. The format recognition result indicates the data format determination result obtained after format recognition processing, signifying whether the categorized deformation monitoring data belongs to raster data, image data, point cloud data, measurement point record data, or other parsable data.

[0054] Specifically, the format characteristics of the categorized deformation monitoring data can be read based on data category information, and the corresponding format recognition result can be determined according to different format characteristics. For example, for binary data, it can be determined whether it belongs to the geographic tag image file format by reading the file header information; for file objects, it can be determined whether it belongs to image data by media type information; for structured data, it can be determined whether it belongs to point cloud data or measurement point record data by field structure; for data lacking clear format identification, it can be attempted to be identified as general point cloud data or general measurement point data. Through this step, the corresponding analytical basis can be determined for subsequent spatial information extraction and deformation information extraction.

[0055] Step S220: Using the format recognition results, spatial information extraction and deformation information extraction are performed on the classified deformation monitoring data to obtain the original spatial data and the original deformation data.

[0056] The raw spatial data can represent information extracted from the categorized deformation monitoring data to describe the spatial location of the data, such as point coordinates, raster georeferenced parameters, image control point data, or point cloud location data. The raw deformation data can represent information extracted from the categorized deformation monitoring data to describe the deformation of the target monitoring area, such as measurement point deformation values, point cloud deformation field values, raster pixel values, or image pixel values.

[0057] Specifically, the corresponding data reading method can be invoked based on the format recognition results to extract spatial and deformation information from the categorized deformation monitoring data. For example, for point cloud data, spatial information can be extracted from the point cloud location field, and deformation information from the deformation field; for raster data, spatial information can be extracted from raster georeferenced parameters, and deformation information from raster values; for measurement point record data, spatial information can be extracted from the measurement point coordinate field, and deformation information from the measurement point value field; for image data, spatial correspondence information can be extracted based on image control point data, and deformation-related image numerical information can be extracted based on image pixel values. Through this step, the spatial and deformation content in different data formats can be extracted separately, forming the raw data foundation required for subsequent conversion processing.

[0058] Step S230: Perform spatial datum transformation on the original spatial data to obtain standard spatial data, and perform deformation value transformation on the original deformation data to obtain standard deformation data.

[0059] Spatial datum transformation refers to the process of converting raw spatial data to a unified coordinate datum. Standard spatial data refers to location data with a unified spatial representation after spatial datum transformation. Deformation value transformation refers to the process of converting raw deformed data to a unified numerical representation. Standard deformed data refers to deformed data with a unified numerical unit or a unified value representation after deformation value transformation.

[0060] Specifically, the coordinates of the original spatial data can be standardized based on its data source and coordinate representation. For example, for raster data with projection information, it can be converted to the World Geodetic System 1984 (WGS84) based on the projection information; for image data, the correspondence between pixel coordinates and geographic coordinates can be determined based on image control point data; for point cloud data or measurement point record data that already has geographic coordinates, the corresponding coordinates can be directly read as standard spatial data. Furthermore, the deformation values ​​of the original deformed data can be converted based on the data unit, numerical meaning, or pixel representation. For example, data with recorded deformation can be converted to a unified millimeter unit; for raster numerical data, the corresponding deformation value can be extracted based on the meaning of the raster value; for image pixel data, the deformation value can be determined based on the correspondence between pixel values ​​and deformation. Through this step, the spatial location and deformation values ​​of data from different sources can have a unified representation basis.

[0061] Step S240: Generate standard deformation monitoring data based on standard spatial data and standard deformation data.

[0062] Standard deformation monitoring data can represent deformation monitoring data formed by associating standard spatial data and standard deformation data. Each data item in the standard deformation monitoring data can include its spatial location and its corresponding deformation value, in order to characterize the deformation state at the corresponding location in the target monitoring area.

[0063] Specifically, standard spatial data and standard deformation data can be correlated according to data source, spatial location, or data recording order to generate standard deformation monitoring data with a correspondence between spatial location and deformation value. For area deformation data, standard area deformation data can be generated based on its standard spatial data and standard deformation data; for point deformation data, standard point deformation data can be generated based on its standard spatial data and standard deformation data. Through this step, classified deformation monitoring data can be converted into standard deformation monitoring data.

[0064] In some embodiments, data category information is used to perform format recognition processing on the classified deformation monitoring data to obtain the format recognition result, which can be done in three cases.

[0065] Firstly, when the classification deformation monitoring data is binary data, the file header information of the binary data is read, and the format recognition result corresponding to the binary data is determined based on the file header information.

[0066] The binary data can represent classification deformation monitoring data input in the form of a byte sequence, such as array buffer type data. The file header information can represent the byte information located at the beginning of the binary data, used to characterize the data format. The format recognition result can represent the data format type determined based on the file header information.

[0067] Specifically, the first two bytes of the binary data can be read and matched with preset file header features. For example, if the first two bytes are 0x49 0x49, the binary data can be determined to have a II identifier; if the first two bytes are 0x4D 0x4D, the binary data can be determined to have an MM identifier. If the binary data has either a II or MM identifier, the format identification result can be determined as geographic tag image file format data. For binary data without preset file header features, it can be parsed as general point cloud data. This method allows for format identification based on the byte characteristics of the data itself, reducing identification errors caused by relying solely on file names or manual selection.

[0068] Secondly, when the classification deformation monitoring data is a file object, the media type information of the file object is read, and the format recognition result corresponding to the file object is determined based on the media type information.

[0069] Here, a file object can represent categorized deformation monitoring data input in file form and carrying file attribute information, such as an image file object. Media type information can represent information in the file object used to describe the file content type, such as Multipurpose Internet Mail Extensions (MIME) information. The format recognition result corresponding to the file object can represent the image format type determined based on the media type information.

[0070] Specifically, the media type information carried by the file object can be read and matched with a preset image format type. For example, if the media type information is image / png, the format recognition result corresponding to the file object can be determined as portable network graphics image data; if the media type information is image / jpeg, the format recognition result corresponding to the file object can be determined as Joint Image Experts Group image data. In this way, image format recognition can be performed using the media type information carried by the file object itself, improving the access and recognition efficiency of image-based deformation monitoring data.

[0071] Third, when the classification deformation monitoring data is structured data, the field structure in the structured data is read, and the format recognition result corresponding to the structured data is determined based on the field structure.

[0072] Structured data can represent categorized deformation monitoring data organized according to fields, arrays, or key-value relationships, such as JavaScript Object Notation (JSON). Field structure can represent field names, field hierarchy, array contents, and field combination relationships within structured data. The format recognition result corresponding to the structured data can represent the data record type determined based on the field structure.

[0073] Specifically, the field structure of structured data can be read, and the data format of the structured data can be determined based on the field structure. For example, if the structured data includes a `points` array, and each point record in the `points` array includes a `position` field and a `deformation` field, the format recognition result of the structured data can be determined as radar point cloud data. If the structured data includes a `records` array, or includes at least one common sensor field among `lng`, `lat`, and `value` fields, the format recognition result of the structured data can be determined as Application Programming Interface (API) response data or discrete sensor data. In this way, format recognition can be performed based on the field content of structured data, enabling point cloud data and sensor data to be automatically determined according to their internal field characteristics.

[0074] In some embodiments, the original spatial data is subjected to spatial reference transformation to obtain standard spatial data, and the original deformed data is subjected to deformation value transformation to obtain standard deformed data. Specifically, the technical steps include the following: The first step is to use the point coordinates, raster georeference parameters, sensor coordinate fields, or image control point data in the original spatial data to determine the georeference data corresponding to the classification deformation monitoring data.

[0075] Specifically, point coordinates can represent the coordinate information used to record spatial locations in point cloud data, such as longitude, latitude, and elevation read from the position field. Raster georeference parameters can represent parameters used to determine the correspondence between pixel coordinates and geographic coordinates in raster data, such as geographic origin parameters and pixel resolution parameters. Sensor coordinate fields can represent fields used to record the location of measurement points in point data, such as longitude, latitude, and elevation fields. Image control point data can represent the corresponding point data between image pixel locations and geographic locations in a 3D scene. Georeferenced data can represent data used to determine the actual spatial location of the classification deformation monitoring data within the target monitoring area.

[0076] Specifically, when the deformation monitoring data is radar point cloud data, longitude, latitude, and elevation can be read from the position field, and the results can be used as the corresponding geographic reference data. When the deformation monitoring data is raster data in geographic label image file format, the geographic coordinate origin parameter and pixel resolution parameter can be parsed, and the corresponding geographic coordinates can be calculated based on the pixel coordinates. For example, if the pixel coordinates are (i,j), the longitude in the geographic coordinates can be obtained by adding the geographic coordinate origin longitude to i times the pixel longitude resolution, and the latitude can be obtained by subtracting j times the pixel latitude resolution from the geographic coordinate origin latitude. When the deformation monitoring data is sensor data, the longitude field, latitude field, and elevation field can be automatically matched. For example, the longitude field can be lng, longitude, or x; the latitude field can be lat, latitude, or y; and the elevation field can be height, elev, or z. When the deformation monitoring data is image data lacking geographic reference, the transformation relationship between image pixel coordinates and geographic coordinates can be determined by solving the affine transformation matrix using the least squares method based on at least three image control point data. This step allows for the extraction of corresponding spatial positioning data for different data formats, providing a clear data foundation for subsequent coordinate processing.

[0077] The second step involves performing coordinate unification processing on the original spatial data based on georeferenced data to obtain standard spatial data.

[0078] Coordinate unification processing refers to the process of converting raw spatial data with different coordinate representations to the same spatial coordinate reference. Standard spatial data refers to location data with a unified coordinate representation after coordinate unification processing.

[0079] Specifically, the coordinate representation of the original spatial data can be determined based on georeferenced data, and the original spatial data can be transformed to a unified coordinate system. For example, for raster data in the format of geotagged image files with projection information, if it uses the universal transverse Mercator projection, it can be converted to latitude and longitude coordinates using a projection transformation formula; if it uses other projection methods, coordinate transformation tools can be used for coordinate transformation. For image data, the aforementioned affine transformation matrix can be used to map image pixel coordinates to geographic coordinates. For radar point cloud data and sensor data, if they already use a unified coordinate system, their original coordinates can be directly used as standard spatial data. Through this step, spatial locations from different sources and with different representations can be transformed to the same spatial reference.

[0080] The third step is to use the data units, raster values, point deformation values, or image pixel values ​​corresponding to the original deformation data to perform deformation value normalization processing on the original deformation data to obtain standard deformation data.

[0081] Here, data units can represent the units of measurement corresponding to the deformation values ​​in the original deformation data. Raster values ​​can represent the values ​​recorded in a raster cell. Point deformation values ​​can represent the deformation measurements recorded at discrete measurement points. Image pixel values ​​can represent the color or grayscale values ​​corresponding to pixels in an image. Deformation value normalization processing can represent the process of converting original deformation data from different sources and with different representations into a unified deformation value expression. Standard deformation data can represent the deformation value data formed after deformation value normalization processing.

[0082] Specifically, the deformation data can be converted according to its data type and numerical meaning. When the deformation monitoring data is radar point cloud data, the deformation value in the `deformation` field can be directly read. When the deformation monitoring data is raster data in a geographic tag image file format, the original deformation value can be extracted from the raster values. For single-band data, the band values ​​can be directly read; for multi-band data, the corresponding deformation value can be extracted based on the band meaning. When the deformation monitoring data is sensor data, the point deformation value in the `value` field can be read. When the deformation monitoring data is image data, a mapping relationship between image pixel values ​​and deformation values ​​can be established through sampling analysis, and the deformation value corresponding to the image pixel can be deduced based on this mapping relationship. For example, multiple pixels can be sampled on the image, the color value of each pixel can be recorded, and a linear mapping relationship can be established based on the correspondence between color distribution and deformation amplitude. Through this step, deformation information in different data formats can be converted into a unified numerical expression, providing a consistent deformation value basis for generating standard deformation monitoring data.

[0083] In some embodiments, generating a surface deformation texture using standard surface deformation data specifically includes the following technical steps: The first step is to use the standard spatial data in the standard area deformation data to determine the texture space range and pixel mapping relationship corresponding to the standard area deformation data.

[0084] The texture space extent can represent the range of a two-dimensional texture region used to carry standard surface deformation data, such as the canvas area determined by the spatial boundaries of the standard surface deformation data. The pixel mapping relationship can represent the correspondence between spatial positions in the standard spatial data and pixel positions in the texture space.

[0085] Specifically, the texture space range can be determined based on the latitude and longitude range or spatial boundaries of each spatial location in the standard area deformation data, and a mapping relationship from standard spatial data to pixel positions can be established according to a preset texture resolution. For example, for radar point cloud data, the canvas size can be determined first based on the point cloud data boundaries, such as 512×512 or 1024×1024, and then the latitude and longitude coordinates of each point can be mapped to pixel coordinates in the canvas. For raster data, the correspondence between raster pixels and texture pixels can be determined based on the geographical range corresponding to the raster unit. For image data, the position of image pixels in the texture space can be determined based on the spatial range corresponding to the image. Through this step, a unified texture space carrying foundation can be established for data of different area forms.

[0086] The second step is to use pixel mapping relationships to map the standard deformation data in the standard surface region deformation data to the corresponding pixel positions to obtain the surface region pixel deformation data.

[0087] Among them, the area pixel deformation data can represent the deformation data recorded in the texture space in units of pixel positions. This data includes the pixel position and its corresponding deformation value.

[0088] Specifically, standard deformation data from standard area deformation data can be written to corresponding pixel positions according to pixel mapping relationships. For example, for radar point cloud data, the deformation value corresponding to each point can be mapped to the corresponding pixel position, and the drawing radius, transparency, or display parameters can be determined based on the deformation value. For raster data, the deformation value corresponding to each raster pixel can be directly mapped to the corresponding pixel position in texture space. For image data, the image can be directly loaded to form a texture, or, if it is necessary to re-express the deformation value, the area pixel deformation data can be regenerated based on the deformation value corresponding to the image pixel. Through this step, different forms of area deformation information can be converted into pixelated deformation representations in texture space.

[0089] The third step is to sample the pixel deformation data of the area region when the amount of data meets the preset sampling conditions, and then use the deformation amplitude and deformation gradient to process the pixel deformation data of the area region to obtain the sampled pixel deformation data of the area region.

[0090] Among them, the preset sampling conditions can represent the data volume conditions used to determine whether to sample the surface pixel deformation data, such as the number of point clouds, the number of pixels, or the number of objects to be drawn exceeding a preset threshold. The deformation amplitude can represent the magnitude of the deformation value corresponding to the pixel position. The deformation gradient can represent the degree of deformation change between adjacent pixel positions or adjacent spatial positions. The sampled surface pixel deformation data can represent the surface pixel deformation data retained after sampling processing.

[0091] Specifically, when the amount of surface region pixel deformation data is large, sampling priority can be determined based on deformation amplitude and deformation gradient, prioritizing the retention of pixel data with larger deformation amplitude or more significant deformation changes. For example, for large-scale radar point clouds, sampling can be performed when the number of points exceeds a preset threshold, prioritizing the retention of point cloud data corresponding to high deformation areas or areas with drastic deformation changes. This step reduces the amount of surface region data to be drawn while retaining deformation area information that is more important for engineering safety assessment.

[0092] The fourth step is to generate a surface deformation texture based on the surface pixel deformation data or the sampled surface pixel deformation data.

[0093] Specifically, when the surface pixel deformation data does not trigger sampling conditions, surface deformation textures can be directly generated based on the surface pixel deformation data; when the surface pixel deformation data triggers sampling conditions, surface deformation textures can be generated based on the sampled surface pixel deformation data. For example, radar point clouds, raster data, or image data can be uniformly rendered as texture data, converting standard surface deformation data into surface deformation textures suitable for subsequent processing. Through these steps, different types of surface deformation data can be uniformly converted into texture representations, improving the consistency and rendering efficiency of subsequent processing of surface deformation data.

[0094] For example, the results of region deformation textures can be as follows: Figure 3 As shown in the figure, the texture results generated based on standard surface deformation data are illustrated. This result maps surface deformation information within the target monitoring area to a three-dimensional terrain surface, presenting the overall deformation distribution of the slope area in a continuous planar form. The figure demonstrates that the surface deformation texture can reflect the deformation differences at different spatial locations within the target monitoring area.

[0095] In some embodiments, generating continuous deformation textures at standard point locations using standard point deformation data specifically includes the following technical steps: The first step is to construct point deformation sample data using standard spatial data and standard deformation data from the standard point deformation data.

[0096] Point deformation sample data can represent sample data composed of the spatial location of points and their corresponding deformation values, used to describe the deformation state at discrete points. Specifically, the spatial location and corresponding deformation value of each discrete measuring point can be extracted from the standard point deformation data, and each spatial location can be associated with its corresponding deformation value to obtain the point deformation sample data. For example, the point deformation sample data may include the coordinates and millimeter-level deformation values ​​of multiple sensor points, measurement points, or monitoring points. Through this step, scattered point deformation records can be organized into sample data that can be used for spatial modeling.

[0097] The second step is to perform spatial correlation modeling based on the point deformation sample data to obtain the point deformation spatial model.

[0098] Spatial correlation modeling refers to the process of establishing the spatial variation relationship of deformation values ​​based on the spatial distance and deformation value relationship between different points. The point deformation spatial model can represent a model used to describe the spatial distribution law of point deformation values ​​within the target monitoring area. Specifically, variogram modeling can be performed based on point deformation sample data, and model parameters can be determined by fitting the point deformation sample data. For example, the spatial correlation modeling method corresponding to Kriging interpolation can be used, and an exponential model can be used as the variogram model to characterize the spatial correlation relationship between measuring points. Through this step, the spatial variation relationship between discrete measuring points can be established, providing a model foundation for subsequent continuous calculations.

[0099] The third step is to use the point deformation space model to perform interpolation calculations on the grid positions in the target monitoring area to obtain the continuous deformation field data of the point.

[0100] Here, grid location refers to the spatial location within the target monitoring area, divided according to a preset grid. Point-based continuous deformation field data refers to the continuous deformation distribution data formed by interpolation calculations from discrete point data. Specifically, an interpolation grid of a preset size, such as a 200×200 interpolation grid, can be generated within the target monitoring area, and the deformation value of each grid location can be predicted using a point-based deformation spatial model. For example, for any grid location, the corresponding weight can be determined based on the spatial distance between neighboring measuring points and the grid location, as well as a spatial correlation model. A weighted calculation is then performed based on the deformation values ​​of neighboring measuring points to obtain the predicted deformation value corresponding to that grid location. Through this step, sparsely distributed point deformation data can be converted into continuously distributed point-based continuous deformation field data.

[0101] The fourth step is to perform texture conversion processing on the continuous deformation field data of the points to obtain the continuous deformation texture of the points.

[0102] Texture conversion processing can be described as the process of converting point-based continuous deformation field data into texture data. Specifically, the predicted deformation values ​​corresponding to each grid position in the point-based continuous deformation field data can be mapped to the corresponding pixel positions, and point-based continuous deformation textures can be generated based on the predicted deformation values ​​at each pixel position. Through the above steps, discrete measurement point deformation data can be converted into a continuous texture representation, giving the point-based deformation data a data form that corresponds to the surface deformation texture.

[0103] For example, point-to-point continuous deformation texture results can be like... Figure 4 As shown, this result is based on the spatial location and deformation values ​​of discrete measuring points, and through continuous processing, a continuous deformation distribution of points covering the target monitoring area is formed. The figure shows that the originally sparsely distributed point deformation data is transformed into a continuous texture representation, allowing the deformation trend of the area surrounding the measuring points to be continuously presented on the three-dimensional terrain surface.

[0104] In some embodiments, the area deformation texture and the point continuous deformation texture are fused to obtain a fused deformation texture, which specifically includes the following technical steps: The first step is to upload the area deformation texture and the point continuous deformation texture to the graphics processor's video memory, and then bind the area deformation texture and the point continuous deformation texture to the texture unit corresponding to the fragment shader of the web graphics library.

[0105] In this context, GPU memory can represent the storage space within the GPU used to store texture data. A texture unit can represent the interface unit in the fragment shader used to read texture data. Specifically, surface deformation textures and point-to-point continuous deformation textures can be uploaded to GPU memory separately and bound to different texture units in the web graphics library's fragment shader. During binding, the surface deformation texture and the point-to-point continuous deformation texture can have consistent texture size and pixel coordinate system, so that the same pixel position in both textures corresponds to the same spatial position in the target monitoring area. Through this step, the two types of texture data to be fused can be prepared as data objects that the GPU can read in parallel.

[0106] The second step is to send the fusion parameters to the fragment shader of the web graphics library; the fusion parameters include weight parameters, fusion mode parameters, and validity threshold parameters.

[0107] The weight parameter represents the weight of the area deformation texture and the point continuous deformation texture in the fusion calculation. The fusion mode parameter represents the calculation method used for fusion, such as weighted average mode, maximum value mode, minimum value mode, or product mode. The validity threshold parameter represents the threshold condition used to determine whether a pixel deformation value is valid.

[0108] Specifically, blending parameters can be sent to the fragment shader of the web graphics library based on user configuration or default configuration. For example, weight parameters can include area texture weights and point texture weights, such as an area texture weight of 0.6 and a point texture weight of 0.4; blending mode parameters can indicate whether weighted average, maximum value, minimum value, or product method is used for calculation; validity threshold parameters can be used to determine whether pixel deformation values ​​are null, exceed the reasonable engineering range, or meet confidence requirements. This step provides calculation rules for the pixel-level blending calculation of the fragment shader.

[0109] The third step involves using the fragment shader from the web graphics library to sample the texture data of corresponding pixel positions in the face-domain deformed texture and the point-position continuous deformed texture in parallel, thereby obtaining the face-domain pixel deformation value and the point-position pixel deformation value.

[0110] Parallel sampling refers to the graphics processor's simultaneous texture reading of multiple pixel locations. Area pixel deformation values ​​represent pixel-level deformation values ​​sampled from area deformation textures. Point pixel deformation values ​​represent pixel-level deformation values ​​sampled from point continuous deformation textures. Specifically, for each pixel location in the output image, the web graphics library fragment shader can simultaneously read the texture data of both the area deformation texture and the point continuous deformation texture at that pixel location, and deduce the corresponding area pixel deformation value and point pixel deformation value based on the texture data. Since the sampling and calculation of each pixel location are independent, the graphics processor can process multiple pixel locations in parallel. This step avoids sequential reading pixel by pixel, providing two types of deformation values ​​for the corresponding pixel location for subsequent pixel-level fusion calculations.

[0111] The fourth step involves using the validity threshold parameter to determine the validity of the surface pixel deformation value and the point pixel deformation value, and then performing pixel-level fusion calculation based on the validity determination result and the fusion mode parameter to obtain the fused pixel deformation value.

[0112] Among these, validity judgment can refer to the process of determining whether a pixel deformation value meets a preset validity condition. Pixel-level fusion calculation can refer to the process of fusing the deformation values ​​of surface pixels and point pixels at the same pixel location. Fused pixel deformation value can refer to the deformation value obtained after fusion calculation for the corresponding pixel location.

[0113] Specifically, the validity of area pixel deformation values ​​and point pixel deformation values ​​can be determined separately based on a validity threshold parameter. If one pixel deformation value is invalid, the weights in the fusion calculation can be adjusted to include valid pixel deformation values ​​in the calculation; if both pixel deformation values ​​are valid, fusion calculation can be performed according to the fusion mode parameters. For example, in the weighted average mode, the area pixel deformation values ​​and point pixel deformation values ​​can be weighted and summed based on the weight parameters; in the maximum value mode, the larger of the two can be selected; in the minimum value mode, the smaller of the two can be selected; and in the product mode, the two can be producted and normalized. Through this step, two types of deformation values ​​can be fused at the same pixel location to obtain the corresponding fused pixel deformation value.

[0114] The fifth step involves generating a fused deformed texture based on multiple fused pixel deformation values. Specifically, the fused pixel deformation values ​​corresponding to each pixel position can be remapped to texture data, and the texture data can be output to the frame buffer to generate the fused deformed texture. Through the above steps, pixel-level fusion processing of area deformed textures and point-to-point continuous deformed textures can be completed on the graphics processor side, improving the generation efficiency and spatial consistency of the fused deformed texture.

[0115] For example, the result of blending deformed textures can be as follows: Figure 5 As shown in the figure, the texture result obtained after fusing surface deformation texture and point continuous deformation texture is presented. This result comprehensively presents surface deformation information and point deformation information in the 3D scene of the target monitoring area, enabling different types of deformation monitoring data to form a fused expression at the same spatial location. The figure demonstrates that the fused deformation texture can simultaneously reflect the overall deformation trend of the area and the influence of local measurement point deformation, which is beneficial for improving the spatial consistency and intuitiveness of the deformation monitoring results.

[0116] Furthermore, in this embodiment of the disclosure, the quality of the fused deformed texture can also be evaluated. Specifically, the fusion quality of the fused deformed texture can be evaluated based on the difference deformation data between the deformation values ​​of surface pixels and the deformation values ​​of point pixels, to obtain a fusion quality evaluation result; and using the fusion quality evaluation result, the target area in the fused deformed texture is quality-marked to obtain a fused deformed texture with quality marks; and then, based on the fused deformed texture with quality marks, a deformation monitoring visualization result corresponding to the target monitoring area is generated.

[0117] The fusion quality assessment can be described as the process of evaluating the reliability or consistency of the fused deformed texture based on the difference in deformation values ​​between the surface deformed texture and the point-to-point continuous deformed texture at corresponding pixel positions. The fusion quality assessment result can represent the quality evaluation result corresponding to different spatial locations in the fused deformed texture, such as consistent regions, dissimilar regions, or anomalous regions. Quality labeling processing can represent the process of labeling regions with significant differences in the fused deformed texture based on the fusion quality assessment result. The target region can represent the region in the fused deformed texture that meets preset quality labeling conditions, such as regions where the differential deformation data exceeds a preset difference threshold.

[0118] Specifically, the difference magnitude corresponding to each pixel position in the fused deformed texture can be determined using difference deformation data, and then compared with a preset difference threshold. If the difference magnitude corresponding to a pixel position is less than or equal to the preset difference threshold, then that pixel position can be determined as a fused consistent position; if the difference magnitude corresponding to a pixel position is greater than the preset difference threshold, then that pixel position can be determined as a fused difference position. Furthermore, multiple adjacent fused difference positions can be aggregated to obtain difference regions, and these difference regions can be subjected to quality marking processing.

[0119] For example, quality marking processing may include at least one of the following: boundary marking of difference areas, transparency adjustment, association of prompt information, or layer highlighting. In this way, after the fused deformation texture is generated, locations with significant differences between the surface deformation texture and the point-to-point continuous deformation texture can be further identified, enabling engineers to combine the fusion results and quality marking results for a more intuitive interpretation of the deformation state in the target monitoring area.

[0120] In some embodiments, spatial matching processing is performed using the fused deformable texture and the corresponding 3D scene data of the target monitoring area, and 3D rendering processing is performed on the fused deformable texture based on the spatial matching processing result to obtain the deformation monitoring visualization result corresponding to the target monitoring area. Specifically, the following technical steps are included: The first step is to perform spatial matching processing using the texture space data corresponding to the fused deformed texture and the scene space data corresponding to the 3D scene data to obtain the texture-scene matching relationship.

[0121] Texture spatial data can represent the texture coordinates, spatial extent, or geographical location range corresponding to the fused deformable texture. Scene spatial data can represent the 3D coordinates, terrain surface location, or engineering structure surface location corresponding to the 3D scene data. Texture-scene matching relationship can represent the spatial correspondence between the fused deformable texture and the 3D scene data. Specifically, based on the spatial extent corresponding to the fused deformable texture and the spatial extent corresponding to the 3D scene data, a correspondence between texture coordinates and 3D scene coordinates can be established to obtain the texture-scene matching relationship. Through this step, the mapping range and mapping position of the fused deformable texture in the 3D scene data can be determined.

[0122] The second step is to map the fused deformed texture to the corresponding three-dimensional spatial location of the three-dimensional scene data based on the texture scene matching relationship.

[0123] The three-dimensional spatial location can represent the location of the target monitoring area on the terrain surface or the engineering structure surface in the three-dimensional scene. Specifically, based on the texture scene matching relationship, the fused deformable texture can be mapped to the corresponding three-dimensional terrain surface or engineering structure surface of the target monitoring area, so that the position of each pixel in the fused deformable texture matches the corresponding spatial position in the three-dimensional scene. Through this step, the fused deformable texture can have the mapping basis for spatial display in the three-dimensional scene.

[0124] The third step is to calculate the difference between the area pixel deformation value and the point pixel deformation value to obtain the difference deformation data.

[0125] Specifically, differential deformation data represents the difference between the deformation values ​​of area pixels and the deformation values ​​of point pixels, characterizing the degree of difference between the two types of deformation data at corresponding pixel locations. Specifically, for the same pixel location, the difference between the area pixel deformation value and the point pixel deformation value can be calculated to obtain the differential deformation value corresponding to that pixel location. Differential deformation data is then formed based on the differential deformation values ​​corresponding to multiple pixel locations. This step establishes a data foundation reflecting the differences between the two types of deformation data.

[0126] The fourth step involves performing ground-based rendering and layer linkage processing on the 3D scene data based on the fused deformation texture and differential deformation data to obtain the deformation monitoring visualization results corresponding to the target monitoring area.

[0127] Among these, "ground-fitting rendering" refers to the process of pasting the blended deformable texture onto the terrain surface or engineering structure surface in the 3D scene data. "Layer linkage processing" refers to the process of synchronously controlling the display of the blended deformable texture, differential deformation data, and related display layers in the 3D scene. Specifically, the blended deformable texture can be pasted onto the terrain surface or engineering structure surface corresponding to the 3D scene data, and the difference areas can be visualized based on the differential deformation data. Furthermore, the visibility, transparency, or mapping rules of the blended deformable texture, differential deformation data, and related monitoring layers can be linked and controlled to obtain the deformation monitoring visualization results corresponding to the target monitoring area. Through these steps, the distribution of the blended deformation and the data differences can be simultaneously displayed in the 3D scene, improving the intuitiveness for engineers in interpreting the deformation state of the target monitoring area.

[0128] Furthermore, in this embodiment of the disclosure, the 3D scene data can also be rendered asynchronously in batches. Specifically, the 3D scene data can be divided into blocks to obtain multiple scene rendering blocks; based on the spatial range and display state corresponding to the multiple scene rendering blocks, the batch rendering order corresponding to the multiple scene rendering blocks is determined; according to the batch rendering order, the multiple scene rendering blocks are asynchronously loaded and rendered to obtain batch asynchronous rendering results; based on the batch asynchronous rendering results, fused deformation textures and differential deformation data, a deformation monitoring visualization result corresponding to the target monitoring area is generated.

[0129] The scene rendering chunks can represent local scene data obtained by dividing 3D scene data according to spatial extent, terrain tiles, model regions, or viewport extent. Display status indicates the display status of the scene rendering chunks in the current 3D view, such as being within the current viewport, close to the current viewport, far from the current viewport, or not currently displayed. Batch rendering order indicates the order in which multiple scene rendering chunks are loaded and rendered. Asynchronous loading and rendering indicates the process of loading and updating scene rendering chunks in batches without blocking current interactive operations. Batch asynchronous rendering result represents the 3D scene display result formed after multiple scene rendering chunks are loaded and rendered in batches.

[0130] Specifically, the 3D scene data can be divided into multiple scene rendering blocks based on the spatial range of the target monitoring area, and the corresponding spatial range of each scene rendering block can be recorded. Then, the display status of each scene rendering block can be determined based on the current viewpoint, field of view, zoom level, or user interaction status, prioritizing the loading and rendering of scene rendering blocks within or near the current field of view. Scene rendering blocks that are not yet in the current field of view or are far from the current field of view can be loaded later or on demand.

[0131] Furthermore, after loading and rendering any scene rendering block, the texture region corresponding to that scene rendering block in the blended deformation texture can be mapped to that scene rendering block, and the corresponding region can be displayed differently or in a layer-linked manner based on the differential deformation data. This method avoids the excessive display pressure caused by loading and rendering the entire 3D scene data at once, allowing the blended deformation texture and differential deformation data to be loaded and displayed gradually with each scene rendering block, thereby improving the rendering efficiency and interactive smoothness of large-scale target monitoring areas.

[0132] Furthermore, in the exemplary embodiments of this disclosure, a deformation monitoring visualization system based on multi-source heterogeneous data fusion is also provided. (Refer to...) Figure 6 As shown, the deformation monitoring visualization system 600 based on multi-source heterogeneous data fusion includes: a data source layer 610, a data parsing layer 620, a fusion processing and calculation layer 630, and a 3D scene rendering layer 640. Wherein: The data source layer 610 can be used to acquire multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, and perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; among which, the classified deformation monitoring data includes surface deformation data and point deformation data.

[0133] The data parsing layer 620 can be used to standardize and transform the classified deformation monitoring data using the data category information corresponding to the classified deformation monitoring data to obtain standard deformation monitoring data. The standard deformation monitoring data includes standard surface deformation data converted from surface deformation data and standard point deformation data converted from point deformation data.

[0134] The fusion processing computation layer 630 can be used to generate a surface deformation texture using standard surface deformation data, generate a point continuous deformation texture using standard point deformation data, and perform fusion processing on the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture.

[0135] The 3D scene rendering layer 640 can be used to perform spatial matching processing using the fused deformable texture and the 3D scene data corresponding to the target monitoring area, and perform 3D rendering processing on the fused deformable texture based on the spatial matching processing results to obtain the deformation monitoring visualization results corresponding to the target monitoring area.

[0136] Furthermore, combined Figure 7 The deformation monitoring visualization system based on multi-source heterogeneous data fusion in the embodiments of this disclosure will be further described.

[0137] like Figure 7As shown, the deformation monitoring visualization system based on multi-source heterogeneous data fusion can be set up in sequence according to the data processing flow as data source layer 610, data parsing layer 620, fusion processing calculation layer 630 and 3D scene rendering layer 640.

[0138] Specifically, the data source layer 610 is used to receive different types of raw monitoring data. In the data source layer 610, continuous area data can represent deformation monitoring data with continuous spatial coverage, corresponding to radar scan data, InSAR, numerical simulation, thermal infrared imaging, and data event monitoring. Data event monitoring can represent a monitoring mechanism used to sense continuous area data update events and trigger data access, parsing, or refresh processing. Discrete data can represent deformation monitoring data obtained through discrete measuring points, corresponding to GNSS (Global Navigation Satellite System), total stations, and surveying robots. GeoTIFF raster data and PNG / JPEG can be used as image-based data input. Therefore, the data source layer 610 can provide the data foundation for subsequent data classification and processing, including area deformation data and point deformation data.

[0139] The data parsing layer 620 is used to standardize and transform the categorized deformation monitoring data. In the data parsing layer 620, the data format of the categorized deformation monitoring data can be automatically identified, the spatial positioning basis corresponding to the categorized deformation monitoring data can be determined through georeference extraction, data under different spatial expressions can be converted to a unified spatial benchmark through coordinate unification, and deformation values ​​under different numerical expressions can be converted to a unified numerical expression through value range normalization. Furthermore, the data parsing layer 620 can also be configured with a surface data extraction parser, a GeoTIFF parser, an image parser, and a discrete data parser to respectively parse continuous surface data, GeoTIFF raster data, PNG / JPEG images, and discrete data. Through the data parsing layer 620, surface deformation data can be converted into standard surface deformation data, and point deformation data can be converted into standard point deformation data.

[0140] The fusion processing computation layer 630 is used to generate fused deformation textures based on standard deformation monitoring data. Within this layer, area data (unified heatmap rendering) can be used to convert standard area deformation data into area deformation textures. The point cloud-color deformation field below it maps point cloud positions and deformation values ​​to a colorized deformation field, the raster-color mapping maps raster deformation values ​​to color representations, and the image-color texture converts image data into color textures. Discrete point data can be used to generate point-to-point continuous deformation textures through Kriging interpolation-continuous color deformation fields. Kriging is used to generate continuous deformation fields based on the spatial relationships of discrete measurement points. Furthermore, the WebGL shader GPU real-time fusion can perform parallel sampling and fusion computation of the area deformation texture and the point-to-point continuous deformation texture at corresponding pixel positions to obtain the fused deformation texture. Fusion quality evaluation can assess the fusion processing results based on the differences between the area deformation texture and the point-to-point continuous deformation texture.

[0141] The 3D scene rendering layer 640 is used to generate deformation monitoring visualization results based on the blended deformation texture. Within the 3D scene rendering layer 640, ground-fitting rendering can be used to apply the blended deformation texture to the 3D terrain surface or engineering structure surface corresponding to the target monitoring area; layer linkage can be used to synchronously control the display of the blended deformation texture, difference display content, and related monitoring layers; interactive control can be used to respond to operations such as viewpoint switching, display range adjustment, or layer control; and batch asynchronous rendering can be used to load and render large-scale 3D scene data or texture data in batches. Therefore, the 3D scene rendering layer 640 can generate deformation monitoring visualization results corresponding to the target monitoring area based on the spatial matching relationship between the blended deformation texture and the 3D scene data.

[0142] Through the above processing, multi-source heterogeneous deformation monitoring data can be sequentially converted into classified deformation monitoring data, standard deformation monitoring data, fused deformation texture, and deformation monitoring visualization results, so that deformation monitoring data from different sources and in different forms of expression can be fused and displayed in the same three-dimensional scene.

[0143] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described deformation monitoring visualization method based on multi-source heterogeneous data fusion is also provided.

[0144] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be embodied in the following forms: a completely hardware embodiment, a completely software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0145] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0146] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0147] The storage unit stores program code that can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure. The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) unit 821 and / or a cache memory unit 822, and may further include a read-only memory unit (ROM) unit 823.

[0148] The storage unit 820 may also include a program / utility 824 having a set (at least one) of program modules 825, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0149] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0150] Electronic device 800 can also communicate with one or more external devices 870 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 800, and / or with any device that enables electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0151] Through the description of the above embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal system, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0152] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0153] The program product for implementing the above-described deformation monitoring visualization method based on multi-source heterogeneous data fusion according to embodiments of this disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of this disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, system, or device.

[0154] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0155] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, system, or device.

[0156] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0157] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0158] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0159] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0160] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0161] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A deformation monitoring visualization method based on multi-source heterogeneous data fusion, characterized in that, The method includes: Acquire multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, and perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein, the classified deformation monitoring data includes surface deformation data and point deformation data; Using the data category information corresponding to the classified deformation monitoring data, the classified deformation monitoring data is standardized and converted to obtain standard deformation monitoring data; wherein, the standard deformation monitoring data includes standard surface deformation data converted from the surface deformation data, and standard point deformation data converted from the point deformation data; A surface deformation texture is generated using the standard surface deformation data, a point continuous deformation texture is generated using the standard point deformation data, and the surface deformation texture and the point continuous deformation texture are fused to obtain a fused deformation texture. Spatial matching processing is performed using the fused deformable texture and the corresponding 3D scene data of the target monitoring area, and 3D rendering processing is performed on the fused deformable texture based on the spatial matching processing result to obtain the deformation monitoring visualization result corresponding to the target monitoring area.

2. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The process of classifying the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data includes: The data source of the multi-source heterogeneous deformation monitoring data is identified to obtain the data source type corresponding to the multi-source heterogeneous deformation monitoring data; By utilizing the data source type and the spatial distribution of the multi-source heterogeneous deformation monitoring data, the multi-source heterogeneous deformation monitoring data is classified to obtain the surface deformation data and the point deformation data. The surface deformation data includes at least one of surface continuous deformation data, raster deformation data, and image deformation data, and the point deformation data includes discrete point deformation data.

3. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The standardization transformation of the classified deformation monitoring data, using the data category information corresponding to the classified deformation monitoring data, to obtain standard deformation monitoring data includes: Using the data category information, the classified deformation monitoring data is processed for format recognition to obtain the format recognition result; Using the format recognition results, spatial information and deformation information are extracted from the classified deformation monitoring data to obtain the original spatial data and the original deformation data; The original spatial data is subjected to spatial reference transformation to obtain standard spatial data, and the original deformed data is subjected to deformation value transformation to obtain standard deformed data; Based on the standard spatial data and the standard deformation data, the standard deformation monitoring data is generated.

4. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 3, characterized in that, The step of using the data category information to perform format recognition processing on the classified deformation monitoring data to obtain the format recognition result includes: When the classification deformation monitoring data is binary data, the file header information of the binary data is read, and the format recognition result corresponding to the binary data is determined based on the file header information; When the classified deformation monitoring data is a file object, the media type information of the file object is read, and the format recognition result corresponding to the file object is determined based on the media type information; When the classification deformation monitoring data is structured data, the field structure in the structured data is read, and the format recognition result corresponding to the structured data is determined based on the field structure.

5. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 3, characterized in that, The process of performing spatial datum transformation on the original spatial data to obtain standard spatial data, and performing deformation value transformation on the original deformed data to obtain standard deformed data, includes: Using the point coordinates, raster geographic reference parameters, sensor coordinate fields, or image control point data in the original spatial data, determine the geographic reference data corresponding to the classification deformation monitoring data; Based on the geographic reference data, the original spatial data is subjected to coordinate unification processing to obtain the standard spatial data; Using the data unit, raster value, point deformation value, or image pixel value corresponding to the original deformation data, the deformation value is normalized to obtain the standard deformation data.

6. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The step of generating a surface deformation texture using the standard surface deformation data includes: Using the standard spatial data in the standard surface region deformation data, the texture space range and pixel mapping relationship corresponding to the standard surface region deformation data are determined; Using the pixel mapping relationship, the standard deformation data in the standard surface deformation data is mapped to the corresponding pixel positions to obtain the surface pixel deformation data; When the amount of data of the area pixel deformation data meets the preset sampling conditions, the area pixel deformation data is sampled using the deformation amplitude and deformation gradient to obtain sampled area pixel deformation data. The surface deformation texture is generated based on the surface pixel deformation data or the sampled surface pixel deformation data.

7. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The step of generating continuous deformation textures at points using the standard point deformation data includes: Using the standard spatial data and standard deformation data in the standard point deformation data, point deformation sample data is constructed; Spatial correlation modeling is performed based on the aforementioned point deformation sample data to obtain a spatial model of point deformation; Using the aforementioned point deformation space model, interpolation calculations are performed on the grid positions in the target monitoring area to obtain continuous deformation field data for the points. The continuous deformation field data at the point is subjected to texture conversion processing to obtain the continuous deformation texture at the point.

8. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 1, characterized in that, The process of fusing the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture includes: The surface deformation texture and the point continuous deformation texture are uploaded to the graphics processor's video memory, and the surface deformation texture and the point continuous deformation texture are bound to the texture unit corresponding to the fragment shader of the web graphics library. Send fusion parameters to the webpage graphics library fragment shader; wherein, the fusion parameters include weight parameters, fusion mode parameters, and validity threshold parameters; Using the fragment shader of the web graphics library, the texture data of the corresponding pixel positions in the surface deformation texture and the point continuous deformation texture are sampled in parallel to obtain the surface pixel deformation value and the point pixel deformation value. Using the validity threshold parameter, the validity of the area pixel deformation value and the point pixel deformation value is judged, and pixel-level fusion calculation is performed based on the validity judgment result and the fusion mode parameter to obtain the fused pixel deformation value; The fused deformation texture is generated based on the deformation values ​​of multiple fused pixels.

9. The deformation monitoring visualization method based on multi-source heterogeneous data fusion according to claim 8, characterized in that, The process involves spatial matching of the fused deformable texture and the corresponding 3D scene data of the target monitoring area, followed by 3D rendering of the fused deformable texture based on the spatial matching results to obtain a deformation monitoring visualization result corresponding to the target monitoring area. This includes: Spatial matching processing is performed using the texture space data corresponding to the fused deformed texture and the scene space data corresponding to the three-dimensional scene data to obtain the texture-scene matching relationship; Based on the texture scene matching relationship, the fused deformed texture is mapped to the three-dimensional spatial position corresponding to the three-dimensional scene data; The difference is calculated using the area pixel deformation value and the point pixel deformation value to obtain the difference deformation data; Based on the fused deformation texture and the differential deformation data, the 3D scene data is rendered along the ground and processed by layer linkage to obtain the deformation monitoring visualization result corresponding to the target monitoring area.

10. A deformation monitoring visualization system based on multi-source heterogeneous data fusion, used to implement the deformation monitoring visualization method based on multi-source heterogeneous data fusion as described in any one of claims 1 to 9, characterized in that, The system includes: The data source layer is used to acquire multi-source heterogeneous deformation monitoring data corresponding to the target monitoring area, and to perform data classification processing on the multi-source heterogeneous deformation monitoring data to obtain classified deformation monitoring data; wherein, the classified deformation monitoring data includes surface deformation data and point deformation data; The data parsing layer is used to perform standardization transformation on the classified deformation monitoring data using the data category information corresponding to the classified deformation monitoring data to obtain standard deformation monitoring data; wherein, the standard deformation monitoring data includes standard surface deformation data converted from the surface deformation data and standard point deformation data converted from the point deformation data. The fusion processing calculation layer is used to generate a surface deformation texture using the standard surface deformation data, generate a point continuous deformation texture using the standard point deformation data, and perform fusion processing on the surface deformation texture and the point continuous deformation texture to obtain a fused deformation texture. The three-dimensional scene rendering layer is used to perform spatial matching processing on the fused deformation texture and the three-dimensional scene data corresponding to the target monitoring area, and to perform three-dimensional rendering processing on the fused deformation texture based on the spatial matching processing result to obtain the deformation monitoring visualization result corresponding to the target monitoring area.

Images