A method and device for projecting a three-dimensional space video by a drone

Abstract

The application relates to a kind of unmanned aerial vehicle three-dimensional space video projection method and device, its method includes: obtaining the three-dimensional scene data of target area, the three-dimensional scene data includes digital ground model and digital elevation model;Based on the three-dimensional scene data, the contour of target ground object is extracted, and a plurality of three-dimensional facade slices are generated according to the contour;Real-time parameters of unmanned aerial vehicle are obtained, the real-time parameters at least include flight position parameter and camera parameter;Photographic ray of unmanned aerial vehicle is determined according to the real-time parameters, and the intersection of the photographic ray and the three-dimensional facade slice is calculated to determine the photographic space range of unmanned aerial vehicle video picture on the three-dimensional facade slice;The unmanned aerial vehicle video picture is projected into the three-dimensional scene where the photographic space range is located, and three-dimensional space video fusion is realized.The application realizes the accurate projection of unmanned aerial vehicle video three-dimensional space by constructing three-dimensional facade slice, terrain and real-time state of unmanned aerial vehicle based on three-dimensional scene.

Description

Technical Field

[0001] This invention belongs to the field of UAV and 3D video technology, specifically relating to a method and device for UAV 3D spatial video projection. Background Technology

[0002] With the development of drone technology, drones return real-time video footage and geographical locations during flight. The video footage, combined with AI target recognition, can display the flying target in the video footage. However, it cannot construct a three-dimensional geographic space and integrate the video into the geographic world. How to integrate drone video footage with three-dimensional spatiotemporal space to achieve a geographic digital twin effect has become a technical problem that urgently needs to be solved.

[0003] The current technical solution is to draw video footage onto a map using "A Map Drawing Method Based on UAVs". This solution only handles two-dimensional map fusion and cannot achieve three-dimensional spatial map fusion. Summary of the Invention

[0004] To address the problems raised in the background art, a first aspect of the present invention provides a method for projecting three-dimensional spatial video from a UAV, comprising: acquiring three-dimensional scene data of a target area, the three-dimensional scene data including a digital terrain model and a digital elevation model; extracting the contours of target features based on the three-dimensional scene data, and generating multiple three-dimensional elevation slices based on the contours; acquiring real-time parameters of the UAV, the real-time parameters including at least flight position parameters and camera parameters; determining the UAV's photographic ray based on the real-time parameters, and calculating the intersection points of the photographic ray and the three-dimensional elevation slices to determine the photographic spatial range of the UAV video image on the three-dimensional elevation slices; and projecting the UAV video image onto the three-dimensional scene where the photographic spatial range is located, thereby achieving three-dimensional spatial video fusion.

[0005] In some embodiments of the present invention, the flight position parameters include the real-time latitude, real-time longitude, and real-time ellipsoidal elevation of the UAV.

[0006] In some embodiments of the present invention, the step of extracting the contour of the target feature based on the three-dimensional scene data includes: calculating the relative height of the grid within the target area based on the digital land surface model and the digital elevation model; filtering the relative height according to a preset height threshold to remove grids corresponding to low-lying features; and inputting the filtered grid data into a pre-trained contour extraction model to extract continuous pixels of the target feature as an initial contour pixel set.

[0007] In some embodiments of the present invention, generating multiple three-dimensional facade slices based on the contour includes: selecting a starting pixel from the initial contour pixel set, gradually exploring adjacent contour pixels and collecting an ordered set of contour vector points until a closed contour loop is formed; vectorizing the closed contour loop according to a corner threshold and converting it into geographic coordinates to form a vector polyline; stretching the vector polyline based on the elevation of the digital surface model to form multiple three-dimensional facade slices.

[0008] In some embodiments of the present invention, determining the photographic ray of the UAV based on the real-time parameters and calculating the intersection point of the photographic ray with the three-dimensional facade slice includes: constructing a function of the photographic ray based on the flight position parameters of the UAV and the horizontal azimuth angle of the camera; constructing a function of the tangent line segment based on the polyline coordinates of the three-dimensional facade slice; calculating the intersection point of the photographic ray function and the tangent line segment function; and when there are multiple intersection points, selecting the intersection point closest to the UAV as the target intersection point.

[0009] In some embodiments of the present invention, determining the photographic space range of the UAV video image on the three-dimensional facade slice includes: determining the corresponding field of view angle according to the camera magnification of the UAV, and calculating the lateral half-angle and longitudinal half-angle of the field of view respectively in combination with the width and height of the photographic image; calculating the lateral offset and longitudinal offset of the UAV projected onto the three-dimensional facade slice based on the lateral half-angle and longitudinal half-angle of the field of view; converting the coordinates of the target intersection point into projected coordinates, and calculating the projected coordinates of the four vertices of the photographic space range based on the lateral offset and longitudinal offset; converting the projected coordinates of the four vertices into latitude and longitude coordinates to obtain the final photographic space range.

[0010] A second aspect of the present invention provides a UAV three-dimensional spatial video projection device, comprising: a first acquisition module for acquiring three-dimensional scene data of a target area, the three-dimensional scene data including a digital terrain model and a digital elevation model; a generation module for extracting the contours of target features based on the three-dimensional scene data and generating multiple three-dimensional elevation slices based on the contours; a second acquisition module for acquiring real-time parameters of the UAV, the real-time parameters including at least flight position parameters and camera parameters; a determination module for determining the photographic ray of the UAV based on the real-time parameters and calculating the intersection point of the photographic ray with the three-dimensional elevation slice to determine the photographic spatial range of the UAV video image on the three-dimensional elevation slice; and a projection module for projecting the UAV video image onto the three-dimensional scene where the photographic spatial range is located, thereby achieving three-dimensional spatial video fusion.

[0011] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the UAV three-dimensional spatial video projection method provided in the first aspect of the present invention.

[0012] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the UAV three-dimensional spatial video projection method provided in the first aspect of the present invention.

[0013] The beneficial effects of this invention are: By loading a 3D model into a real-world 3D scene, constructing 3D facade slices based on the 3D scene, and using terrain and real-time drone status, the coordinate position of the drone photography target in 3D space is realized. The drone video image is accurately drawn within the 3D geographic coordinate range of the photography, realizing the 3D spatial projection of drone video, thus making up for the shortcomings of drone rendering in 3D spatial applications. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the basic process of the UAV three-dimensional spatial video projection method in some embodiments of the present invention; Figure 2 This is a schematic diagram illustrating the specific process of the UAV three-dimensional spatial video projection method in some embodiments of the present invention; Figure 3 This is a schematic diagram of the structure of a UAV three-dimensional spatial video projection device in some embodiments of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0015] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0016] Example 1 refer to Figure 1 and Figure 2In a first aspect of the present invention, a method for projecting three-dimensional spatial video from a UAV is provided, comprising: S100. acquiring three-dimensional scene data of a target area, the three-dimensional scene data including a digital terrain model and a digital elevation model; S200. extracting the contours of target features based on the three-dimensional scene data, and generating multiple three-dimensional elevation slices based on the contours; S300. acquiring real-time parameters of the UAV, the real-time parameters including at least flight position parameters and camera parameters; S400. determining the photographic ray of the UAV based on the real-time parameters, and calculating the intersection point of the photographic ray with the three-dimensional elevation slice to determine the photographic spatial range of the UAV video image on the three-dimensional elevation slice; S500. projecting the UAV video image onto the three-dimensional scene where the photographic spatial range is located, thereby achieving three-dimensional spatial video fusion.

[0017] In step S100 of some embodiments of the present invention, three-dimensional scene data of the target area is obtained, the three-dimensional scene data including a digital surface model and a digital elevation model; Specifically, oblique photogrammetry technology is used to plan UAV flight paths, collect field data through UAV flight, process the data in the office, and form target point cloud data, DSM, DOM, 3D model and DEM, which are then loaded into the Cesium 3D scene.

[0018] In step S200 of some embodiments of the present invention, extracting the contour of the target feature based on the three-dimensional scene data includes: S201. Calculate the relative height of the grid within the target area based on the digital surface model and digital elevation model; Specifically, based on the DSM and DEM, the relative height of the monitoring area is calculated: , In the formula: i, j For the model row and column numbers, It is the absolute elevation of the grid. It is the topographic elevation of the grid. h (i，j) This is the relative elevation, i.e., the actual height of the ground feature.

[0019] S202. Filter the relative heights according to a preset height threshold and remove grids corresponding to low-lying features; Specifically, In the formula, h min This is the minimum height threshold.

[0020] S203. Input the filtered grid data into the pre-trained contour extraction model to extract the continuous pixels of the target feature as the initial contour pixel set.

[0021] Using an existing depthwise convolution model, the final continuous pixels of the house outline are extracted through depthwise convolution calculation: , , , , In the formula, h This is the set of grid layer height values ​​from the previous step, after removing low-lying features. The value is the result of the convolution operation and activation processing at the nth layer. O This is the set of grid layer height values ​​output by the model. , The first n Layer weights and biases c This is a set of pixels representing the outline of the house.

[0022] In some embodiments of the present invention, generating multiple three-dimensional facade slices based on the contour includes: S204. Select a starting pixel from the initial contour pixel set, gradually explore adjacent contour pixels and collect an ordered set of contour vector points until a closed contour loop is formed. Specifically, based on the set of house outline pixels obtained in the previous step, arbitrarily select a pixel as the starting point, gradually explore adjacent outline pixels, collect an ordered set of outline vector points, and remove the point from the original set. When returning to the starting pixel, a closed loop of house outline is formed. When the original set is empty, it means that all houses have been extracted. , , , ; Single house exploration termination conditions: , .

[0023] In the formula, c is the original set of house outline pixels. Indicates exclusion The set c after the point, and o is an ordered and closed contour pixel point.

[0024] S205. The closed contour loop is vectorized according to the corner threshold and converted into geographic coordinates to form a vector polyline; Specifically, ordered pixels are straightened based on corners (the actual corners of a house are generally quite large) and converted into geographic coordinates to form a true vector polyline.

[0025] , , , In the formula, The converted geographic coordinates , The coordinates of the bottom left corner of the DSM are: i, j The row and column numbers are pixels. , These represent the grid width and height geographical span, respectively. Let k represent the angle between three consecutive points, and k represent the final set of vector nodes. This is the corner threshold.

[0026] S206. Based on the elevation of the digital surface model, stretch the vector polyline to form multiple three-dimensional facade slices.

[0027] Specifically, the vector polyline is stretched according to elevation to form the final three-dimensional elevation cross-section, each cross-section being an elevation rectangle stretched from the ellipsoid according to the DSM elevation:

[0028] In the formula, For the nth elevation section, , , , The coordinates are the three-dimensional coordinates of the elevation.

[0029] It is understandable that in step S200, the vector surface and elevation information of the house are used to design the flight path of the UAV. In order to simplify the calculation process, the UAV flight photography orientation is set to the vertical target orientation.

[0030] In step S300 of some embodiments of the present invention, real-time parameters of the UAV are obtained, the real-time parameters including at least flight position parameters and camera parameters; Specifically, since drones can acquire vertical azimuth, horizontal azimuth, magnification, geographic coordinates and ellipsoidal height in real time, the photographic spatial range of the drone can be calculated in real time.

[0031] Real-time acquisition of UAV vertical azimuth, horizontal azimuth, magnification, geographic coordinates, and ellipsoidal elevation via MQTT requests: , In the formula, This is a set of real-time parameters, where P, T, and Z are the horizontal azimuth, vertical azimuth, and magnification, respectively, and B, L, and H are the real-time latitude, longitude, and ellipsoidal altitude of the UAV, respectively.

[0032] In step S400 of some embodiments of the present invention, determining the photographic ray of the UAV based on the real-time parameters and calculating the intersection point of the photographic ray and the three-dimensional facade slice includes: S401. Construct a function for the photographic ray based on the flight position parameters of the UAV and the horizontal azimuth angle of the camera; S402. Construct a function for the sectional line segment based on the polyline coordinates of the three-dimensional elevation slice; Specifically, based on the drone's coordinates and horizontal azimuth angle, the drone's photographic ray function is obtained. Based on the elevation cross-section in step S300, the function of each cross-section line segment can be derived: , , , , In the formula, t(x) is the ray function of the UAV. Let P be the polyline function of the nth 3D cross section, and P be the azimuth angle of the UAV. L , B For the latitude and longitude of the drone, These are the coordinates of the endpoints of the line segment.

[0033] S403. Calculate the intersection point of the photographic ray function and the tangent line segment function. When there are multiple intersection points, select the intersection point closest to the UAV as the target intersection point.

[0034] Specifically, traverse the 3D cross-section and calculate the intersection points of the UAV ray and the 3D cross-section line segments (note that when there are multiple intersection points, take the closest one). The coordinates of the intersection points are: , ; Is the intersection point within the line segment? ,

[0035] , In the formula, x and y are the coordinates of the intersection point. This indicates taking the minimum value. This indicates taking the maximum value. The shortest distance between the drone and the 3D cross-section; other parameters are consistent with the meaning of step S402.

[0036] In step S400 of some embodiments of the present invention, determining the photographic spatial range of the UAV video image on the three-dimensional elevation slice includes: S404. Determine the corresponding field of view angle based on the camera magnification of the UAV, and calculate the horizontal half-angle and vertical half-angle of the field of view respectively in combination with the width and height of the photographed image; Specifically, based on the intersection point of the drone photography and the 3D cross-section calculated in step S403, the photography range of the drone image on the 3D cross-section is calculated: Based on the relationship between the drone camera magnification and field of view (the field of view at various magnifications can be calculated by adjusting the magnification) and the width and height of the captured image, the horizontal and vertical half-angles of the field of view are calculated: , ; S405. Based on the horizontal and vertical half-angles of the field of view, calculate the horizontal and vertical offsets of the UAV projected onto the three-dimensional facade slice; Specifically, the lateral and longitudinal offsets of the drone's projection onto the three-dimensional facade are calculated: , , In the formula, , These represent the lateral and longitudinal offsets projected by the drone, respectively. Note that the unit is meters.

[0037] S406. Convert the coordinates of the target intersection point into projected coordinates, and calculate the projected coordinates of the four vertices of the photographic space range based on the lateral and longitudinal offsets; Specifically, the latitude and longitude coordinates and intersection coordinates of the line segment are projected and transformed: , , , , In the formula, , Let be the projected coordinates of the two endpoints of the polyline segment. The coordinates of the ray intersection point are the projected coordinates. The projected coordinates of the UAV's position. It is a Gaussian positive calculation function.

[0038] Line segment coordinate transformation function: , , In the formula, The length of the broken line segment. This represents the mapping relationship between the lateral offset and the photographic coordinates on the line segment; other parameters are the same as in the previous formula.

[0039] , , , , In the formula, , , , For the three-dimensional coordinates of the photography area, , Here are the coordinates of the midpoint of the photograph (the intersection of the ray and the facade), H is the drone altitude, and other parameters are the same as in the above formula.

[0040] S407. Convert the projected coordinates of the four vertices into latitude and longitude coordinates to obtain the final photographic spatial range.

[0041] Specifically, the four projected coordinates are converted into the final latitude and longitude coordinates using a GIS conversion algorithm.

[0042] In step S500 of some embodiments of the present invention, the video footage of the drone is projected onto the three-dimensional scene where the photography space is located, thereby realizing three-dimensional spatial video fusion.

[0043] Specifically, in the Cesium map framework, reference data such as 3D oblique photography and DSM are preloaded. When the drone starts flying, the drone image is projected onto the spatial coordinates of step S400 to achieve the final 3D spatial video projection effect.

[0044] Example 2 refer to Figure 3 In a second aspect, the present invention provides a UAV three-dimensional spatial video projection device 1, comprising: a first acquisition module 11, configured to acquire three-dimensional scene data of a target area, the three-dimensional scene data including a digital terrain model and a digital elevation model; a generation module 12, configured to extract the contours of target features based on the three-dimensional scene data, and generate multiple three-dimensional elevation slices based on the contours; a second acquisition module 13, configured to acquire real-time parameters of the UAV, the real-time parameters including at least flight position parameters and camera parameters; a determination module 14, configured to determine the photographic ray of the UAV based on the real-time parameters, and calculate the intersection point of the photographic ray with the three-dimensional elevation slice, so as to determine the photographic spatial range of the UAV video image on the three-dimensional elevation slice; and a projection module 15, configured to project the UAV video image onto the three-dimensional scene where the photographic spatial range is located, thereby realizing three-dimensional spatial video fusion.

[0045] Furthermore, the generation module 12 includes: a calculation unit, used to calculate the relative height of the grid within the target area based on the digital surface model and the digital elevation model; a filtering unit, used to filter the relative height according to a preset height threshold and remove grids corresponding to low-lying features; and an extraction unit, used to input the filtered grid data into a pre-trained contour extraction model and extract the continuous pixels of the target feature as an initial contour pixel set.

[0046] Example 3 refer to Figure 4 In a third aspect, the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the UAV three-dimensional spatial video projection method of the first aspect of the present invention.

[0047] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0048] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0049] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer 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. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-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 computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0050] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to: Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0051] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for projecting three-dimensional video from a drone, characterized in that, include: Acquire three-dimensional scene data of the target area, wherein the three-dimensional scene data includes a digital terrain model and a digital elevation model; Based on the three-dimensional scene data, the outline of the target features is extracted, and multiple three-dimensional elevation slices are generated according to the outline; Acquire real-time parameters of the UAV, including at least flight position parameters and camera parameters; The drone's photographic ray is determined based on the real-time parameters, and the intersection of the photographic ray with the three-dimensional facade slice is calculated to determine the photographic space range of the drone's video image on the three-dimensional facade slice. The drone video footage is projected onto the three-dimensional scene within the photographic space to achieve three-dimensional spatial video fusion.

2. The UAV three-dimensional spatial video projection method according to claim 1, characterized in that, The flight position parameters include the UAV's real-time latitude, real-time longitude, and real-time ellipsoidal elevation.

3. The UAV three-dimensional spatial video projection method according to claim 1, characterized in that, The extraction of the target feature's outline based on the 3D scene data includes: The relative height of the grid within the target area is calculated based on the digital surface model and the digital elevation model. The relative height is filtered according to a preset height threshold, and the grid corresponding to low-lying features is removed. The filtered grid data is input into a pre-trained contour extraction model to extract continuous pixels of the target feature as the initial contour pixel set.

4. The UAV three-dimensional spatial video projection method according to claim 1, characterized in that, The step of generating multiple three-dimensional facade slices based on the contour includes: Starting from the initial set of contour pixels, select a starting pixel, gradually explore adjacent contour pixels and collect an ordered set of contour vector points until a closed contour loop is formed. The closed contour loop is vectorized based on the corner threshold and converted into geographic coordinates to form a vector polyline; Based on the elevation of the digital surface model, the vector polyline is stretched to form multiple three-dimensional facade slices.

5. The UAV three-dimensional spatial video projection method according to claim 1, characterized in that, The step of determining the UAV's photographic ray based on the real-time parameters and calculating the intersection point of the photographic ray with the three-dimensional facade slice includes: Based on the flight position parameters of the UAV and the horizontal azimuth angle of the camera, construct a function for the photographic ray; Based on the polyline coordinates of the three-dimensional facade slices, a function for constructing the sectional line segments is generated; Calculate the intersection point of the photographic ray function and the tangent line segment function. When there are multiple intersection points, select the intersection point closest to the UAV as the target intersection point.

6. The UAV three-dimensional spatial video projection method according to claim 1, characterized in that, The determination of the photographic spatial range of the drone video footage on the three-dimensional elevation slice includes: The corresponding field of view is determined based on the camera magnification of the drone, and the horizontal and vertical half-angles of the field of view are calculated in combination with the width and height of the photographed image. Based on the horizontal and vertical half-angles of the field of view, calculate the horizontal and vertical offsets of the UAV projected onto the three-dimensional facade slice. The coordinates of the target intersection point are converted into projected coordinates, and the projected coordinates of the four vertices of the photographic space range are calculated based on the lateral and longitudinal offsets. The projected coordinates of the four vertices are converted into latitude and longitude coordinates to obtain the final photographic spatial range.

7. A UAV three-dimensional spatial video projection device, characterized in that, include: The first acquisition module is used to acquire three-dimensional scene data of the target area, wherein the three-dimensional scene data includes a digital land surface model and a digital elevation model. The generation module is used to extract the outline of the target features based on the three-dimensional scene data, and generate multiple three-dimensional facade slices based on the outline; The second acquisition module is used to acquire real-time parameters of the UAV, which include at least flight position parameters and camera parameters; The determination module is used to determine the photographic ray of the UAV based on the real-time parameters, and calculate the intersection point of the photographic ray with the three-dimensional facade slice, so as to determine the photographic space range of the UAV video image on the three-dimensional facade slice; The projection module is used to project the video footage from the drone onto the three-dimensional scene within the photographic space, thereby achieving three-dimensional spatial video fusion.

8. The UAV three-dimensional spatial video projection device according to claim 7, characterized in that, The generation module includes: A calculation unit is used to calculate the relative height of the grid within the target area based on the digital surface model and the digital elevation model; The filtering unit is used to filter the relative height according to a preset height threshold and remove grids corresponding to low-lying features; The extraction unit is used to input the filtered grid data into a pre-trained contour extraction model to extract continuous pixels of the target feature as an initial contour pixel set.

9. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the UAV three-dimensional spatial video projection method as described in any one of claims 1 to 6.

10. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the UAV three-dimensional spatial video projection method as described in any one of claims 1 to 6.

Images