A digital conversion sand table construction method and system based on aerial photography technology

Abstract

The application discloses a kind of digital conversion sand table construction method and system based on aerial photography technology, it is related to three-dimensional sand table construction technical field, including obtaining aerial photography image, and dynamic path planning and multimodal data record are carried out;Aerial photography image splicing and correction, generate digital elevation model;Generate three-dimensional digital sand table, and embed dynamic update and multi-platform display function.The method improves the precision of image acquisition, reduces the repeated coverage and blind area, improves the overall efficiency of aerial photography task, reduces the splicing error caused by complex terrain, illumination change and other factors in traditional method, so that the overall image parameter of output is more accurate and consistent, improves the detail performance ability of model, lays a solid foundation for subsequent three-dimensional digital sand table construction, meets the display needs of multi-platform, also makes sand table model have higher operability and shareability in city planning, emergency response and other practical scenarios, effectively optimizes user interaction experience.

Description

Technical Field

[0001] This invention relates to the field of three-dimensional sand table construction technology, specifically to a digital conversion sand table construction method and system based on aerial photography technology. Background Technology

[0002] With the rapid development of drone technology, data acquisition and processing based on aerial imagery has been widely applied in fields such as Geographic Information Systems (GIS), environmental monitoring, and urban planning. The precision and flexibility of aerial photography technology enable it to achieve efficient image acquisition in complex terrains and wide areas, and it has shown significant advantages in digital terrain modeling (DTM), orthophoto stitching, and 3D reconstruction. In recent years, multimodal data fusion methods have further expanded the application scope of aerial data, from single image acquisition to dynamic path optimization, real-time data recording, and comprehensive processing. At the same time, 3D sand table construction technology based on digital elevation models (DEM) has gradually emerged in scenarios such as simulation training, disaster emergency response, and planning and design, providing researchers with innovative tools for transitioning from two-dimensional data to multi-dimensional display. However, existing technologies still have considerable room for improvement in terms of accuracy, real-time performance, and diversified display functions.

[0003] Although aerial photography has become an important means of spatial data acquisition, existing technologies still have many limitations in dynamic path planning, multimodal data fusion, and subsequent processing. In dynamic path planning, traditional methods rely heavily on preset fixed paths, which are difficult to adjust in real time to adapt to complex terrain or dynamic task requirements, resulting in limited image acquisition efficiency and integrity. The development of synchronous recording and processing technologies for multimodal data is lagging behind, and existing methods cannot simultaneously take into account the acquisition, matching, and fusion of multi-source data, resulting in insufficient diversity and practicality of results. In the subsequent image stitching and correction process, existing stitching algorithms have poor robustness to complex scenes and are prone to introducing errors, affecting the accuracy of digital elevation models. Especially in the construction of 3D sand tables, traditional systems have limited functions, cannot achieve real-time updates of dynamic data, and cannot meet the display needs of multiple platforms and multiple scenarios. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that existing 3D sand table construction technologies suffer from low efficiency in dynamic path planning, incomplete multimodal data recording, insufficient dynamic updating and multi-platform display functions, and the problem of how to achieve efficient processing of aerial images, accurate modeling, and dynamic updating and multi-platform display of 3D sand tables.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for constructing a digital transformation sand table based on aerial photography technology, comprising acquiring aerial images and performing dynamic path planning and multimodal data recording; stitching and correcting the aerial images to generate a digital elevation model; generating a three-dimensional digital sand table and embedding dynamic update and multi-platform display functions.

[0007] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the dynamic path planning includes adjusting the drone's flight path according to wind speed, temperature, and humidity parameters, and automatically optimizing shooting parameters in areas with insufficient light or strong reflections through the dynamic exposure adjustment function of the aerial photography equipment, as expressed as:

[0008]

[0009] Where P(t) is the flight path, representing the change of the UAV's trajectory with time t, t0 represents the start time of the flight mission, and t f Let α represent the end time of the flight mission, β represent the velocity weight, β represent the adaptability weight, v(t) represent the flight velocity of the UAV at time t, and η(t) represent the environmental adaptability coefficient at time t, expressed as:

[0010]

[0011] Where w(t) is the wind speed at time t, T(t) is the real-time temperature at time t, and T opt The optimal temperature is given by κ1, which is the wind speed weighting parameter, and κ2, which is the temperature deviation weighting parameter.

[0012] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the multimodal data recording includes using a drone equipped with visible light, infrared light and LiDAR sensors to collect surface details and three-dimensional terrain data, and using global navigation satellite system and inertial measurement unit data to correct the image shooting position and direction.

[0013] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the aerial image stitching and correction includes: the UAV completing image acquisition according to the optimized path, stitching and correcting the overlapping areas of adjacent images, extracting feature points of the images using the SIFT algorithm, correcting geometric distortion of the images using bundle adjustment, correcting geometric errors caused by UAV motion and lens distortion based on the bundle adjustment algorithm, generating a corrected overall image, and incorporating the gradient information of the path optimization. Introducing bundle adjustment, the output of stitching and correction is the corrected image parameter x, expressed as:

[0014] x=(ATWA)-1 A T W(l+e(τ i ))

[0015] Where x represents the corrected image parameters, A is the design matrix including the design parameters for bundle adjustment, W is the weighting matrix used to adjust the error weights, l is the observation vector representing the initial error of the image, and e(τ) i ) is the path correction vector, represented as:

[0016]

[0017] Where, τ i For the time point of path optimization, λ i Adjust the weights for the path. For path P(t) at time point τ i The gradient of n is the number of known points.

[0018] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the generation of the digital elevation model includes generating a high-precision digital elevation model (DEM) by combining LiDAR point clouds, and fusing it with orthophotos to generate complete terrain data, wherein the corrected image parameters x and LiDAR point cloud data Z are... i Together they constitute the input for elevation modeling.

[0019] The elevation of unknown points is calculated using an interpolation algorithm, and the Laplacian operator of the image texture is used. To enhance the detail of the terrain model, the generated digital elevation model z(x,y) is represented as:

[0020]

[0021] Where z(x,y) is the elevation value of the coordinate point (x,y), and w i (x,y) represents the interpolation weights, used to measure the influence of point (x,y) on the known point i. i Let i be the elevation of a known point i in the LiDAR point cloud data. γ is the Laplacian operator for image texture, γ is the image texture fusion weight, and n is the number of known points.

[0022] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the generation of the three-dimensional digital sand table includes generating a three-dimensional sand table model supported by Level of D (LOD) based on a digital elevation model z(x,y) and orthophotos. The LOD model adopts a layered construction method, combined with the resolution parameter R. ki and texture details T ki Describing different levels of terrain accuracy using the Gaussian kernel function φ iThe (x,y) smooth texture variation allows the model to adapt to the display requirements of multiple platforms, and is represented as:

[0023]

[0024] Among them, LOD k (x,y) represents the detail weight of the k-th layer LOD sandbox model at coordinate point (x,y), R ki Let T be the LOD resolution parameter for the k-th layer. ki φ represents the LOD texture detail weight at layer k. i (x, y) is the Gaussian kernel function, used to smooth texture variations, x i ,y i σ represents the coordinates of the center point of the Gaussian kernel function, σ represents the smoothing width of the Gaussian kernel function, z(x,y) represents the elevation data of the terrain, γ represents the image texture fusion weight, and m represents the number of texture points in the LOD model.

[0025] As a preferred embodiment of the digital transformation sand table construction method based on aerial photography technology described in this invention, the embedded dynamic update and multi-platform display functions include: integrating a real-time data stream update module, dynamically updating the sand table model through new aerial photography data, establishing a multi-user collaboration platform, supporting hierarchical permission management and collaborative editing, providing a remote access interface based on a cloud platform, and enabling digital sand table sharing and dynamic interaction among multiple devices.

[0026] Another objective of this invention is to provide a digital transformation sand table construction system based on aerial photography technology, which can generate a three-dimensional digital sand table and embed dynamic update and multi-platform display functions, thus solving the problems of current three-dimensional terrain modeling and visualization technologies, such as lagging model updates, poor platform compatibility, and insufficient user interaction experience.

[0027] As a preferred embodiment of the digital transformation sand table construction system based on aerial photography technology described in this invention, it includes an image acquisition module, a stitching and correction module, and a sand table update module.

[0028] The image acquisition module is used to acquire aerial images and perform dynamic path planning and multimodal data recording; the stitching and correction module is used to stitch and correct the aerial images to generate a digital elevation model; the sand table update module is used to generate a three-dimensional digital sand table and embed dynamic update and multi-platform display functions.

[0029] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement a method for constructing a digital transformation sand table based on aerial photography technology.

[0030] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for constructing a digital conversion sand table based on aerial photography technology.

[0031] The beneficial effects of this invention are as follows: The digital transformation sand table construction method based on aerial photography technology provided by this invention acquires aerial images and performs dynamic path planning and multimodal data recording, ensuring the stability and clarity of the aerial images. The dynamic exposure adjustment function optimizes the shooting effect in areas with insufficient light or strong reflection, improves the quality and reliability of aerial data, increases data acquisition efficiency, and reduces the impact of environmental factors. Aerial images are stitched and corrected to generate a digital elevation model, realizing the conversion from discrete aerial images to a continuous and accurate terrain model. This reduces manual intervention, improves modeling efficiency and accuracy, generates a three-dimensional digital sand table, and embeds dynamic updating and multi-platform display functions, achieving real-time updates of terrain information and multi-angle, multi-platform visualization. This ensures the accuracy and display effect of the model at different resolutions, provides highly interactive and information-rich three-dimensional terrain display, enhances user experience, and improves data sharing and collaboration efficiency. This invention achieves better results in terms of aerial image acquisition efficiency, digital elevation model accuracy, and dynamic interaction and display of the three-dimensional digital sand table. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 The first embodiment of the present invention provides an overall flowchart of a digital transformation sand table construction method based on aerial photography technology.

[0034] Figure 2 The following is an overall flowchart of a digital transformation sand table construction system based on aerial photography technology, provided as a third embodiment of the present invention. Detailed Implementation

[0035] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0036] Example 1, referring to Figure 1As an embodiment of the present invention, a method for constructing a digital transformation sand table based on aerial photography technology is provided, comprising:

[0037] S1: Acquire aerial images and perform dynamic path planning and multimodal data recording.

[0038] Furthermore, dynamic path planning includes adjusting the drone's flight path based on wind speed, temperature, and humidity parameters, and automatically optimizing shooting parameters in low-light or highly reflective areas using the dynamic exposure adjustment function of the aerial photography equipment. This can be represented as:

[0039]

[0040] Where P(t) is the flight path, representing the change of the UAV's trajectory with time t, t0 represents the start time of the flight mission, and t f Let α represent the end time of the flight mission, β represent the velocity weight, β represent the adaptability weight, v(t) represent the flight velocity of the UAV at time t, and η(t) represent the environmental adaptability coefficient at time t, expressed as:

[0041]

[0042] Where w(t) is the wind speed at time t, T(t) is the real-time temperature at time t, and T opt The optimal temperature is given by κ1, which is the wind speed weighting parameter, and κ2, which is the temperature deviation weighting parameter.

[0043] It should be noted that multimodal data recording involves using drones equipped with visible light, infrared light, and LiDAR sensors to collect surface details and three-dimensional terrain data, and using global navigation satellite system and inertial measurement unit data to correct the image capture position and orientation.

[0044] It should also be noted that dynamic path planning and multimodal data recording solve the problems of low image acquisition efficiency, unstable quality, and limited data in traditional aerial photography, laying a solid foundation for subsequent data processing and modeling. Dynamic path planning uses environmental parameters as the core input, adjusting the drone's flight path in real time to optimize flight efficiency and image coverage. By introducing speed and adaptability weights, the drone's flight trajectory is adjusted according to different environmental conditions, achieving task optimization in complex terrain and dynamic environments. In areas with high wind speeds, the drone automatically reduces its flight speed and adjusts its flight direction to ensure the stability and clarity of aerial images. Real-time monitoring and weight allocation of temperature and humidity parameters enable the drone to select the optimal shooting time, avoiding image blurring or data loss due to adverse weather conditions. This path planning method not only improves the accuracy of image acquisition but also reduces redundant coverage and blind spots, improving the overall efficiency of aerial photography missions.

[0045] S2: Stitch and correct aerial images to generate a digital elevation model.

[0046] Furthermore, the aerial image stitching and correction process includes the UAV acquiring images according to the optimized path, stitching and correcting overlapping areas of adjacent images, extracting feature points from the images using the SIFT algorithm, and correcting geometric distortions using bundle adjustment. The bundle adjustment algorithm is then used to correct geometric errors caused by UAV motion and lens distortion, generating a corrected overall image, and incorporating gradient information from the path optimization. Introducing bundle adjustment, the output of stitching and correction is the corrected image parameter x, expressed as:

[0047] x=(A T WA) -1 A T W(l+e(τ i ))

[0048] Where x represents the corrected image parameters, A is the design matrix including the design parameters for bundle adjustment, W is the weighting matrix used to adjust the error weights, l is the observation vector representing the initial error of the image, and e(τ) i ) is the path correction vector, represented as:

[0049]

[0050] Where, τ i For the time point of path optimization, λ i Adjust the weights for the path. For path P(t) at time point τ i The gradient of n is the number of known points.

[0051] It should be noted that generating a digital elevation model includes combining LiDAR point clouds to generate a high-precision digital elevation model (DEM), and fusing it with orthophotos to generate complete terrain data, including the corrected image parameters x and LiDAR point cloud data Z. i Together, they constitute the input for elevation modeling; the elevation of unknown points is calculated using an interpolation algorithm, and then processed by the Laplacian operator of the image texture. To enhance the detail of the terrain model, the generated digital elevation model z(x,y) is represented as:

[0052]

[0053] Where z(x,y) is the elevation value of the coordinate point (x,y), wi(x,y) is the interpolation weight used to measure the influence of point (x,y) on the known point i, z i Let i be the elevation of a known point i in the LiDAR point cloud data. γ is the Laplacian operator for image texture, γ is the image texture fusion weight, and n is the number of known points.

[0054] It should also be noted that using image data acquired through optimized paths for stitching and correction significantly improves the overall image quality and geometric accuracy. The SIFT algorithm is used to extract feature points from the images, making feature matching between adjacent images more accurate. Combined with bundle adjustment, geometric errors caused by UAV motion and lens distortion are corrected. Path optimization gradient information is introduced, and dynamic flight path adjustment data is integrated into the bundle adjustment process, improving the accuracy of image correction. This approach reduces stitching errors caused by complex terrain and lighting variations in traditional methods, resulting in more accurate and consistent overall image parameters. By combining LiDAR point cloud data and orthophotos, refined terrain modeling is achieved. Elevation values ​​of unknown points are calculated using interpolation algorithms, and the Laplacian operator of image textures is used to enhance the detail of the terrain model. The generated DEM not only has higher spatial resolution and more realistically reflects terrain features, but also enhances the model's detail representation, laying a solid foundation for subsequent 3D digital sand table construction.

[0055] S3: Generates a 3D digital sand table and embeds dynamic updates and multi-platform display functions.

[0056] Furthermore, the generation of a 3D digital sand table includes generating a Level of Dimension (LOD) supported 3D sand table model based on a digital elevation model z(x,y) and orthophotos. The LOD model adopts a hierarchical construction method, combined with the resolution parameter R. ki and texture details T ki Describing different levels of terrain accuracy using the Gaussian kernel function φ i The (x,y) smooth texture variation allows the model to adapt to the display requirements of multiple platforms, and is represented as:

[0057]

[0058] Among them, LOD k (x,y) represents the detail weight of the k-th LOD sandbox model at coordinates (x,y), Rki represents the LOD resolution parameter of the k-th layer, and T ki Here, φi(x,y) represents the detail weight of the k-th LOD texture, and φi(x,y) is the Gaussian kernel function used to smooth texture variations. i ,y i σ represents the coordinates of the center point of the Gaussian kernel function, σ represents the smoothing width of the Gaussian kernel function, z(x,y) represents the elevation data of the terrain, γ represents the image texture fusion weight, and m represents the number of texture points in the LOD model.

[0059] It should be noted that the embedded dynamic update and multi-platform display functions include integrating a real-time data stream update module, dynamically updating the sand table model through new aerial photography data, establishing a multi-user collaboration platform, supporting hierarchical permission management and collaborative editing, providing a cloud-based remote access interface, and enabling digital sand table sharing and dynamic interaction among multiple devices.

[0060] It should also be noted that the generation of a 3D digital sand table based on a digital elevation model (DEM) and orthophotos achieves a comprehensive digital transformation from two-dimensional to three-dimensional, LOD (Level of Dimensioning). The sand table model supported by (ofDetail) utilizes a layered construction approach to provide adaptive terrain accuracy and texture detail at different resolutions. This ensures that the sand table model can display detailed terrain features on high-performance devices while maintaining smooth operation on low-performance devices. A Gaussian kernel function is used to smooth texture variations, making the sand table's visual appearance more natural and avoiding the disjointed feel caused by multi-resolution switching. This feature expands the applicable scenarios of the 3D sand table, meeting user needs for both detailed simulation training and lightweight mobile display. The embedded dynamic update function further enhances the system's practicality. Through a real-time data stream update module, the system can dynamically update the sand table model based on the latest aerial data, giving the sand table real-time performance and adaptability. With the support of the cloud platform, the sand table model can be operated collaboratively by multiple users, providing hierarchical permission management, collaborative editing, and other functions. This not only meets the display needs of multiple platforms but also makes the sand table model more operable and shareable in practical scenarios such as urban planning and emergency response, providing users with a better interactive experience.

[0061] Example 2 is an embodiment of the present invention, which provides a method for constructing a digital transformation sand table based on aerial photography technology. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0062] First, six representative areas were selected for the experiment, covering complex terrains such as plains, hills, and mountains, to comprehensively evaluate the performance of the invention under different environments. The experiment used a UAV equipped with multimodal sensors, including visible light and infrared cameras and LiDAR sensors, as well as GNSS and IMU modules to ensure the positioning accuracy of the image data. The experimental tasks were divided into four stages: data acquisition, image stitching and correction, digital elevation model generation, and 3D digital sand table construction. In the experimental preparation stage, the meteorological conditions of the six target areas were comprehensively evaluated, including factors such as wind speed, temperature and humidity, and light intensity. Using the dynamic path planning module, optimized flight paths were generated based on the real-time environmental parameters in the area. The optimization of dynamic path planning took into account wind speed weight and temperature and humidity adaptability, and the flight speed and path direction were adjusted by monitoring environmental parameters in real time. For example, in areas with high wind speeds, the system reduced the drone's flight speed and adjusted its altitude to minimize image jitter caused by wind. In areas with low light or strong reflections, the dynamic exposure adjustment function optimized the shooting parameters to ensure image clarity and color consistency. During data acquisition, the drone sequentially completed aerial photography tasks in six areas, collecting multimodal data including visible light images, thermal imaging data, and LiDAR point cloud data. Using GNSS and IMU modules, the system recorded the shooting position and attitude parameters in real time to ensure image positioning accuracy. The experiment also recorded the number and coverage of images collected in each area to measure data integrity. In the image stitching and correction stage, the collected images were input into the stitching and correction module. The SIFT algorithm is used to extract feature points from adjacent images, and the bundle adjustment algorithm is combined to correct geometric distortion. Path optimization gradient information further improves the stitching accuracy. For example, in hilly areas (such as Area 3), complex terrain undulations may lead to overlap errors in traditional stitching algorithms. However, by introducing path correction vectors, the system significantly reduces the error range. Subsequently, the corrected images are fused with LiDAR point cloud data to generate a digital elevation model (DEM). During DEM generation, interpolation algorithms are used to calculate the elevation of unknown points, while the Laplacian operator of image texture is used to enhance the detail of the model. Finally, based on the digital elevation model and orthophotos, a 3D sand table model supporting multi-level detail (LOD) is experimentally constructed, and dynamic updating and multi-platform display functions are embedded. The real-time data stream update module is used in subsequent experiments to test the dynamic loading function of new data. At the same time, multi-user collaboration and remote access are realized through a cloud platform. The experimental results show that this invention is applicable to various terrain and climate conditions, and has advantages in high-precision image acquisition, rapid stitching correction, and dynamic 3D sand table construction, providing an efficient and innovative solution for geographic information processing and applications.

[0063] Example 3, referring to Figure 2As an embodiment of the present invention, a digital conversion sand table construction system based on aerial photography technology is provided, including an image acquisition module, a stitching and correction module, and a sand table update module.

[0064] The image acquisition module is used to acquire aerial images and perform dynamic path planning and multimodal data recording; the stitching and correction module is used to stitch and correct aerial images to generate a digital elevation model; and the sand table update module is used to generate a three-dimensional digital sand table and embed dynamic update and multi-platform display functions.

[0065] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0067] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0068] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc. It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for constructing a digital conversion sand table based on aerial photography technology, characterized in that, include: Acquire aerial imagery and perform dynamic path planning and multimodal data recording; The dynamic path planning includes adjusting the drone's flight path based on wind speed, temperature, and humidity parameters, and automatically optimizing shooting parameters in low-light or highly reflective areas using the dynamic exposure adjustment function of the aerial photography equipment. This can be represented as: in, The flight path represents the trajectory of the drone over time. Changes, Indicates the start time of the flight mission. Indicates the end time of the flight mission. For speed weights, For adaptive weights, Indicates the time of the drone Flight speed, For time The environmental adaptability coefficient is expressed as: in, For time wind speed, For time Real-time temperature, For optimal temperature, For wind speed weighting parameters, The weighting parameter for temperature deviation; Aerial images are stitched and corrected to generate a digital elevation model; Generate a 3D digital sand table and embed dynamic updates and multi-platform display functions.

2. The method for constructing a digital conversion sand table based on aerial photography technology as described in claim 1, characterized in that: The multimodal data recording includes using a drone equipped with visible light, infrared light, and LiDAR sensors to collect surface details and three-dimensional terrain data, and using data from the Global Navigation Satellite System and Inertial Measurement Unit to correct the image capture position and orientation.

3. The method for constructing a digital conversion sand table based on aerial photography technology as described in claim 2, characterized in that: The aerial image stitching and correction process includes the UAV acquiring images according to an optimized path, stitching and correcting overlapping areas of adjacent images, extracting feature points from the images using the SIFT algorithm, correcting geometric distortions using bundle adjustment, correcting geometric errors caused by UAV motion and lens distortion based on the bundle adjustment algorithm, generating a corrected overall image, and incorporating gradient information from the path optimization. Introducing bundle adjustment, the output of stitching and correction is the corrected image parameters. , is represented as: in, To correct image parameters, The design matrix includes design parameters for bundle adjustment. This is a weighting matrix used to adjust the error weights. Let be the observation vector, representing the initial error of the image. The path correction vector is represented as: in, For the time point of path optimization, Adjust the weights for the path. For path At the point of time gradient, The number of known points.

4. The method for constructing a digital conversion sand table based on aerial photography technology as described in claim 3, characterized in that: The generated digital elevation model includes combining LiDAR point clouds to generate a high-precision digital elevation model (DEM), fusing it with orthophotos to generate complete terrain data, and correcting the image parameters. and LiDAR point cloud data Together they constitute the input for elevation modeling; The elevation of unknown points is calculated using an interpolation algorithm, and the Laplacian operator of the image texture is used. Enhance the detail of the terrain model and generate a digital elevation model. , is represented as: in, Coordinates Elevation value, These are interpolation weights used to measure points. For a known point The impact, Known points in LiDAR point cloud data elevation, For image texture Laplacian operator, For image texture fusion weights, The number of known points.

5. The method for constructing a digital conversion sand table based on aerial photography technology as described in claim 4, characterized in that: The generation of the three-dimensional digital sand table includes a digital elevation model. Using orthophotos, a 3D sandbox model supporting LOD is generated. The LOD model is constructed in a layered manner, taking into account resolution parameters. and texture details Describing different levels of terrain accuracy using a Gaussian kernel function. Smooth texture changes allow the model to adapt to the display requirements of multiple platforms, as shown below: in, For the first Layered LOD sand table model at coordinate points Detail weighting, For the first Layer LOD resolution parameters, For the first Layer LOD texture detail weight, This is a Gaussian kernel function used to smooth texture variations. The coordinates of the center point of the Gaussian kernel function are: The smoothing width of the Gaussian kernel function. For terrain elevation data, For image texture fusion weights, This represents the number of texture points in the LOD model.

6. The method for constructing a digital conversion sand table based on aerial photography technology as described in claim 5, characterized in that: The embedded dynamic update and multi-platform display functions include an integrated real-time data stream update module, which dynamically updates the sand table model with new aerial data, establishes a multi-user collaboration platform, supports hierarchical permission management and collaborative editing, provides a cloud-based remote access interface, and enables digital sand table sharing and dynamic interaction among multiple devices.

7. A system employing the digital transformation sand table construction method based on aerial photography technology as described in any one of claims 1 to 6, characterized in that: Includes an image acquisition module, a stitching and correction module, and a sand table update module; The image acquisition module is used to acquire aerial images and perform dynamic path planning and multimodal data recording. The stitching and correction module is used to stitch and correct aerial images to generate a digital elevation model. The sand table update module is used to generate a three-dimensional digital sand table and embed dynamic update and multi-platform display functions.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the digital transformation sand table construction method based on aerial photography technology as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the digital transformation sand table construction method based on aerial photography technology as described in any one of claims 1 to 6.

Images