A method and system for generating a real-time rendered scene of a simulation simulator

Abstract

The present invention relates to the field of computer graphics rendering. Specifically, it is a method and system for generating real-time rendering scenes of a simulation simulator. The method detects the terrain information and scene information around the perimeter collected by a drone and transmits the terrain information and the scene information to an information processing terminal; the information processing terminal generates terrain data and a scene configuration file required for a training task, solving the problem that there is a deviation between the training effect and the actual battlefield situation. At the same time, by separately rendering terrain simulation and scene simulation and dynamically adjusting the rendering details through an algorithm, it is ensured that under high-quality conditions, computing resources and time are saved, the rendering quality is improved, and the quality and effect of the simulated military training for training personnel are guaranteed, and the training efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer graphics rendering, and more particularly, to a method and system for generating a real-time rendering scene of a simulation simulator. Background Art

[0002] In the modern military training system, early simulation military training plays a crucial role. With the rapid development of technology, the training methods have been continuously innovated to adapt to the complex and changeable battlefield environment. In the initial stage of simulation training, in order to efficiently utilize limited training resources, virtual reality (VR) technology is usually more adopted to construct simulation training content. This training method can not only save a large amount of material and labor costs, but also enable soldiers to familiarize themselves with the battlefield environment and combat procedures in advance through a highly simulated virtual environment. However, in conventional simulation training, direct satellite maps or high-altitude reconnaissance aerial photography are generally used, resulting in a relatively low simulation accuracy of the training simulation environment for the real environment, and thus there is a deviation between the training effect and the actual battlefield situation. Secondly, real-time rendering requires a large amount of computing resources and time. If low-standard real-time rendering is adopted, the real-time rendering effect will be poor, seriously reducing the quality and effect of the simulation military training for training personnel and lowering the training efficiency. In view of this, the present application is specifically proposed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is that the use of direct satellite maps or high-altitude reconnaissance aerial photography results in a relatively low simulation accuracy of the training simulation environment for the real environment, leading to a deviation between the training effect and the actual battlefield situation, and low-standard real-time rendering will also result in a poor real-time rendering effect, seriously reducing the quality and effect of the simulation military training for training personnel.

[0004] To solve the above technical problems, the present invention is realized through the following technical solutions. A method for generating a real-time rendering scene of a simulation simulator, the method comprising the following steps:

[0005] Step S1: Collect the surrounding terrain information and scene information through a detection unmanned aerial vehicle (UAV), and transmit the terrain information and the scene information to an information processing terminal;

[0006] Step S2: Generate the terrain data and scene configuration files required for the training task in the information processing terminal based on the terrain information and the scene information, and initialize the rendering engine;

[0007] Step S3: Construct a terrain basic model based on the terrain data and the scene configuration files, calculate the first visible area in the terrain basic model through a machine vision analysis algorithm, and render the first visible area; the first visible area is the visible area under the initial default view when a training person loads the scene;

[0008] Step S4: Generate the texture and layout of the scene elements in the first visible area by using the first learning rendering algorithm;

[0009] Step S5: Read the training user's viewpoint position, render the first visible area by using the second learning rendering algorithm to obtain an image result, and dynamically adjust the scene detail level;

[0010] Step S6: Output the image result to the VR visual device, and at the same time, update the rendering content in real time according to the user's interaction operation.

[0011] Furthermore, generate the terrain data and scene configuration file required for the training task in the information processing terminal, including: generate the terrain data and scene configuration file required for the training task in the information processing terminal by using the Mesh surface fitting technology, and the Mesh surface fitting technology is optimized by using the self-organizing neural network intelligent algorithm. The mathematical expression of the self-organizing neural network intelligent algorithm is:

[0012] ;

[0013] where, is the weight change of the x-th neuron at the t-th iteration; is the neural network learning rate; is the neighborhood function, indicating the neighborhood relationship between the y-th winning neuron and the x-th neuron; is the current input sample; is the weight vector of the x-th neuron at the t-th iteration; is the current iteration number;

[0014] The neural network learning rate is:

[0015] ;

[0016] where, is the gradient information of the current parameter; is a constant to ensure numerical stability; is the terrain information weight, is the scene information weight; is the hyperparameter, used to control the step size of parameter update;

[0017] The terrain information weight is:

[0018] ;

[0019] where, is the exponential decay coefficient, and 0.45 > > 0.9; For detecting the ratio of mountain terrain collected by the detection UAV, For detecting the ratio of hilly terrain collected by the detection UAV, For detecting the ratio of flat terrain collected by the detection UAV, For detecting the ratio of water area terrain collected by the detection UAV, For detecting the ratio of valley terrain collected by the detection UAV, For the ratio of terrain information collected by the detection UAV in the (t - 1)-th iteration; For the exponentially weighted moving average;

[0020] The weight of the said scenario information is:

[0021] ;

[0022] Wherein, For the ratio of urban scenarios collected by the detection UAV, For the ratio of forest scenarios collected by the detection UAV, For the ratio of grassland shrub scenarios collected by the detection UAV, For the ratio of other scenarios collected by the detection UAV, For the ratio of scenario information collected by the detection UAV in the (t - 1)-th iteration.

[0023] Furthermore, the first visible area in the terrain basic model is calculated by the machine vision analysis algorithm, and the machine vision analysis algorithm calculates using the binocular matching algorithm, and its formula is:

[0024] ;

[0025] Wherein, For the area map to be rendered in the first visible area; For the energy function corresponding to the area map to be rendered in the first visible area; For the left-eye imaging area, For the right-eye imaging area; For the other areas outside the left-eye imaging area in the area map to be rendered in the first visible area; For the time cost and performance cost when rendering the area map in the first visible area. The time cost is the unit time length required to render this image area, and the performance cost is the amount of computing resources required to render this image area; For the disparity value of the left-eye imaging area; For the disparity value of the right-eye imaging area; For the penalty coefficient, which is applicable to the case where the disparity value of the left-eye imaging area differs from the disparity value of the right-eye imaging area by 1; is also the penalty coefficient, applicable to the case where the disparity value in the left-eye imaging area differs from the disparity value in the right-eye imaging area by more than 1; is the indicator function, which returns 1 if the condition is true and 0 otherwise.

[0026] Further, the first learning rendering algorithm includes: a texture rendering algorithm formula and a reflection algorithm formula. The texture rendering algorithm formula is:

[0027] ;

[0028] where is the color of the final pixel in the pixel area; is the weight of the i-th texture; is the color value of the i-th texture at the coordinate (j, k, l); is the abscissa in the coordinate (j, k, l), is the ordinate in the coordinate (j, k, l), is the height coordinate in the coordinate (j, k, l); is the total number of textures;

[0029] The reflection algorithm formula is:

[0030] ;

[0031] where is the brightness of the reflected light of the final pixel; is the intensity of the ambient light; is the ambient light reflection coefficient; is the intensity of the main light source; is the diffuse reflection coefficient; is the specular reflection coefficient; is the light source direction vector; is the surface normal vector; is the reflected light direction vector; is the viewing direction vector; is the specular highlight exponent.

[0032] Further, the second learning rendering algorithm includes: a first rendering algorithm weight formula and a second rendering algorithm weight formula; the first rendering algorithm weight formula is used to calculate the rendering priority of the current terrain information, and the first rendering algorithm weight formula is:

[0033] ;

[0034] where is the rendering weight corresponding to the terrain; is the complexity coefficient of the terrain; is the performance requirement coefficient of the terrain; is the rendering priority coefficient of the terrain; is the corresponding terrain. When = 1, it is mountainous terrain, = 2, it is hilly terrain, = 3, it is flat terrain, = 4, it is water area, = 5, it is valley;

[0035] The second rendering algorithm weight formula is used to calculate the rendering priority of the current scene information. The second rendering algorithm weight formula is:

[0036] ;

[0037] Among them, is the rendering weight of the corresponding scene; is the complexity coefficient of the scene; is the performance requirement coefficient of the scene; is the rendering priority coefficient of the scene; is the corresponding scene. When = 1, it is a city, = 2, it is a forest, = 3, it is grassland and shrub, = 4, it is other types;

[0038] Among them, when ≥ , the details in the terrain information are preferentially rendered. When < , the details in the scene information are preferentially rendered.

[0039] Furthermore, the complexity coefficient of the terrain and the complexity coefficient of the scene are trained and optimized by using a computer image training algorithm; the computer image training algorithm is trained by using a computer image training algorithm formula, and the computer image training algorithm formula is:

[0040] ;

[0041] Among them, is the optimization weight rate; is the first-order matrix; is the second-order matrix; is a constant, and 1 ≥ >0.

[0042] Based on the same inventive concept, on the other hand, the present invention also provides a real-time rendering scene generation system for a simulation simulator, and the system includes: a detection drone, an information processing terminal, an image simulation simulator, and a VR visual device; the detection drone transmits information to the information processing terminal, the information processing terminal transmits data and a configuration file to the image simulation simulator, and the image simulation simulator transmits the generated image result to the VR visual device; the detection drone is used to obtain the surrounding terrain information and scene information, the information processing terminal is used to process the terrain information and scene information obtained by the detection drone, generate terrain data and a scene configuration file required for a training task through the terrain information and the scene information, the image simulation simulator is used to render the terrain data and the scene configuration file to generate the image result, and the VR visual device is used to present the rendered image result.

[0043] Further, the image simulation simulator further includes: a first image information processing module and a second image information processing module, the terrain data and the scene configuration file obtain the first visible area through the first image information processing module, and the first visible area obtains the image result through the second image information processing module.

[0044] Compared with the prior art, the present invention has the following advantages and beneficial effects: using a drone for low-altitude scanning to collect terrain information and scene information, collecting a large amount of rich information data, generating terrain data and a scene configuration file required for a training task through the information processing terminal, solving the problem that there is a deviation between the training effect and the actual battlefield situation. At the same time, by separately rendering the terrain simulation and the scene simulation, and dynamically adjusting the rendering details through an algorithm, it is ensured that under high-quality conditions, computing resources and time are saved, the rendering quality is improved, and the quality and effect of the simulated military training for training personnel are guaranteed, and the training efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can also be obtained based on these drawings without creative efforts.

[0046] Figure 1 It is a flowchart of a method for generating a real-time rendering scene of a simulation simulator provided by an embodiment of the present invention.

[0047] Figure 2 It is a block diagram of a module of a real-time rendering scene generation system for a simulation simulator provided by an embodiment of the present invention. Detailed Implementation Manner

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the embodiments and the accompanying drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0049] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, it will be apparent to those of ordinary skill in the art that: the present invention does not have to employ these specific details. In other embodiments, well-known structures, circuits, materials, or methods have not been specifically described in order to avoid obscuring the present invention.

[0050] Throughout the specification, references to "one embodiment", "an embodiment", "one example", or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "one embodiment", "an embodiment", "one example", or "an example" appearing throughout the specification do not necessarily all refer to the same embodiment or example. Additionally, the specific features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0051] Embodiment 1: As Figure 1 shown, a method for generating a real-time rendering scene of a simulation simulator provided in this embodiment includes the following steps:

[0052] Step S1: Collect the surrounding terrain information and scene information through a detection drone, and transmit the terrain information and the scene information to an information processing terminal;

[0053] Step S2: Generate the terrain data and scene configuration files required for the training task in the information processing terminal based on the terrain information and the scene information, and initialize the rendering engine;

[0054] Step S3: Construct a terrain basic model based on the terrain data and the scene configuration file, calculate the first visible area in the terrain basic model through a machine vision analysis algorithm, and render the first visible area; the first visible area is the visible area under the initial default perspective when the training personnel load into the scene;

[0055] Step S4: Generate the textures and layouts of the scene elements in the first visible area by using a first learning rendering algorithm;

[0056] Step S5: Read the training user's viewpoint position, render the first visible area using the second learning rendering algorithm to obtain an image result, and dynamically adjust the scene detail level;

[0057] Step S6: Output the image result to the VR visual device, and at the same time, update the rendering content in real time according to the user's interaction operations.

[0058] Furthermore, the terrain data and scene configuration files required for the training task in the information processing terminal are generated through the Mesh surface fitting technology, and the Mesh surface fitting technology is optimized using the self-organizing neural network intelligent algorithm. The mathematical expression of the self-organizing neural network intelligent algorithm is:

[0059] ;

[0060] where is the weight change of the x-th neuron at the t-th iteration; is the neural network learning rate; is the neighborhood function, representing the neighborhood relationship between the y-th winning neuron and the x-th neuron; is the current input sample; is the weight vector of the x-th neuron at the t-th iteration; is the current iteration number;

[0061] The neural network learning rate is:

[0062] ;

[0063] where is the gradient information of the current parameter; is a constant to ensure numerical stability; is the terrain information weight, is the scene information weight; is an extraordinary parameter used to control the step size of parameter update;

[0064] The terrain information weight is:

[0065] ;

[0066] where is the exponential decay coefficient, and 0.45 > > 0.9; is the proportion of mountainous terrain collected by the detection UAV, is the proportion of hilly terrain collected by the detection UAV, is the proportion of flat terrain collected by the detection UAV, To detect the ratio of the water area terrain collected by the drone, To detect the ratio of the valley terrain collected by the drone, It is the ratio of the terrain information collected by the detection drone at the (t - 1)-th iteration; It is the exponentially weighted moving average;

[0067] The weight of the said scenario information is:

[0068] ;

[0069] Among them, It is the ratio of the urban scenario collected by the detection drone, It is the ratio of the forest scenario collected by the detection drone, It is the ratio of the grassland and shrub scenario collected by the detection drone, It is the ratio of other scenarios collected by the detection drone, It is the ratio of the scenario information collected by the detection drone at the (t - 1)-th iteration.

[0070] Specifically, the combination of the Mesh surface fitting technology and the self-organizing neural network intelligent algorithm can significantly improve the efficiency, accuracy and intelligence level of Mesh generation. The Mesh surface fitting technology can be used for automatic mesh generation. Through the self-learning ability of the neural network, this method can automatically generate meshes adapted to complex shapes according to the input geometric shapes and topological information. For example, the Let-It-Grow neural network has been used to generate coarse meshes for the overlapping unstructured multi-mesh algorithm. Through the adjustment and optimization of the self-organizing neural network intelligent algorithm, the meshes can be dynamically adjusted and optimized according to different application scenarios and requirements. For example, it can automatically predict the mesh density to generate meshes adapted to the needs of different regions. This method can automatically generate high-quality meshes according to complex geometric shapes and physical characteristics, reducing manual intervention. The combination of the Mesh surface fitting technology and the self-organizing neural network intelligent algorithm can not only improve the efficiency and quality of mesh generation, but also make the complex image rendering process more intelligent.

[0071] Furthermore, in the process of calculating the first visible area in the terrain basic model by the machine vision analysis algorithm, the machine vision analysis algorithm adopts the binocular matching algorithm, and its formula is:

[0072] ;

[0073] Among them, It is the rendering area map of the first visible area; It is the energy function corresponding to the rendering area map of the first visible area; It is the left-eye imaging area, is the imaging area for the right eye; is the other area in the rendering area of the first visible area except for the imaging area of the left eye in the figure; are the time cost and performance cost when rendering the rendering area of the first visible area. The time cost is the length of the unit time required to render this image area, and the performance cost is the amount of computing resources required to render this image area; is the disparity value of the left-eye imaging area; is the disparity value of the right-eye imaging area; is the penalty coefficient, applicable to the case where the disparity value of the left-eye imaging area differs from the disparity value of the right-eye imaging area by 1; is also the penalty coefficient, applicable to the case where the disparity value of the left-eye imaging area differs from the disparity value of the right-eye imaging area by more than 1; is the indicator function, which returns 1 if the condition is true and 0 otherwise;

[0074] Specifically, the visual analysis algorithm is the core technology in the field of computer vision, aiming to extract and understand visual information from images or videos through image processing and pattern recognition technologies. These algorithms are widely used in many fields such as image recognition, object detection, face recognition, and pose estimation. The binocular matching algorithm obtains the three-dimensional information of an object through multiple images. Common stereo vision algorithms include those based on binocular stereo vision and those based on structured light. Drawing on the "disparity" principle of human binoculars, that is, there are differences in the observations of a certain object in the real world by the left and right eyes, and our brains precisely utilize the differences between the left and right eyes to enable us to identify the distance of objects. In computer vision, the depth information of an object is calculated through the disparity between two or more images. Taking the SAD algorithm as an example, its basic process is as follows:

[0075] 1. Input two rectified and row-aligned left views (Left-Image) and right views (Right-Image).

[0076] 2. Scan the left view to select an anchor point and construct a small window.

[0077] 3. Use this small window to cover the left view and the right view, and select all the pixel points in the covered area of the small window.

[0078] 4. Calculate the sum of the absolute values of the pixel differences in the covered areas of the left and right views.

[0079] 5. Move the small window of the right view and repeat the above operations to find the small window with the minimum SAD value, which is the best-matched pixel block.

[0080] Similarly, the binocular matching algorithm renders the terrain information and scene information in the field of view separately, calculates the required time length and the computational amount required for rendering separately, gives priority to solving important rendering objects, and renders different rendering objects in a segmented manner to achieve different rendering precisions for different objects, realizing the preliminary and rapid rendering of the scene, enabling the training personnel to obtain better visual information before the start of training and avoiding the discomfort caused by low-quality rendering.

[0081] Further, the first learning rendering algorithm includes: a texture rendering algorithm formula and a reflection algorithm formula. The texture rendering algorithm formula is:

[0082] ;

[0083] Among them, is the color of the final pixel in the pixel area; is the weight of the i-th texture; is the color value of the i-th texture at the coordinates (j, k, l); is the abscissa in the coordinates (j, k, l), is the ordinate in the coordinates (j, k, l), is the height coordinate in the coordinates (j, k, l);

[0084] The reflection algorithm formula is:

[0085] ;

[0086] Among them, is the brightness of the reflected light of the final pixel; is the intensity of the ambient light; is the ambient light reflection coefficient; is the intensity of the main light source; is the diffuse reflection coefficient; is the specular reflection coefficient; is the light source direction vector; is the surface normal vector; is the reflected light direction vector; is the viewing direction vector; is the specular highlight index.

[0087] Further, the second learning rendering algorithm includes: a first rendering algorithm weight formula and a second rendering algorithm weight formula; the first rendering algorithm weight formula is used to calculate the rendering priority of the current terrain information, and the first rendering algorithm weight formula is:

[0088] ;

[0089] Among them, is the rendering weight for the corresponding terrain; is the complexity coefficient of the terrain; is the performance requirement coefficient of the terrain; is the rendering priority coefficient of the terrain; is the corresponding terrain. When = 1, it is a mountain; = 2, it is a hill; = 3, it is flat ground; = 4, it is water area; = 5, it is a valley;

[0090] The second rendering algorithm weight formula is used to calculate the rendering priority of the current scene information. The second rendering algorithm weight formula is:

[0091] ;

[0092] Among them, is the rendering weight of the corresponding scene; is the complexity coefficient of the scene; is the performance requirement coefficient of the scene; is the rendering priority coefficient of the scene; is the corresponding scene. When = 1, it is a city; = 2, it is a forest; = 3, it is grassland and shrubs; = 4, it is other types;

[0093] Among them, when ≥ , the details in the terrain information are preferentially rendered. When < , the details in the scene information are preferentially rendered.

[0094] Furthermore, the complexity coefficient of the terrain and the complexity coefficient of the scene are trained and optimized using a computer image training algorithm; the computer image training algorithm is trained using a computer image training algorithm formula, and the computer image training algorithm formula is:

[0095] ;

[0096] Among them, is the optimization weight rate; is the first-order matrix; is the second-order matrix; is a constant, and 1 ≥ >0.

[0097] Specifically, multiple detection drones are dispatched to collect information from the simulated training area. The detection drones fly along a preset route, using the position accuracy sensors they carry to collect terrain height data to form terrain information, and using the image recognition sensors they carry to collect scene environment data to form scene information. These data are transmitted to the information processing terminal for subsequent processing and analysis. After receiving the data transmitted by the drones, the information processing terminal begins to generate the terrain data and scene configuration files required for the training tasks. Through information comparison, it is obtained that the collected terrain information includes the proportion information of each terrain type: mountain terrain accounts for 40%; hilly terrain accounts for 10%; flat terrain accounts for 35%; water terrain accounts for 10%; valley terrain accounts for 5%. The collected scene information includes the proportion information of each scene type: urban area accounts for 15%; forest area accounts for 30%; grassland and shrub area accounts for 35%; other areas account for 20%. Terrain data: includes grid point coordinates, terrain types (such as mountains, flatlands, etc.) and height information. Scene configuration file: includes the position, type and size information of scene elements (such as buildings, trees, etc.). Optimization is carried out using the Mesh surface fitting technology combined with the self-organizing neural network intelligent algorithm. Through the Mesh surface fitting technology, the collected terrain and scene data are meshed to generate a mesh model of the terrain and a layout configuration of the scene. For example, for mountain terrain, grid points with different altitudes are generated according to the height data to form a three-dimensional mesh model of the mountain. At the same time, combined with the optimization of the self-organizing neural network, the mesh model is optimized through the neural network algorithm to adjust the density and distribution of the meshes to better adapt to the complexity of the terrain and the scene. For example, for a complex urban area, the neural network will increase the mesh density to more precisely represent the outlines of buildings and street layouts. Calculate the first visible area and render Based on the generated terrain data and scene configuration files, a terrain base model is constructed. The machine vision analysis algorithm is used to calculate the first visible area under the initial default view of the training personnel and render the first visible area. The machine vision analysis algorithm uses the binocular matching algorithm to calculate the first visible area. Assuming that the initial view of the training personnel is straight ahead, the algorithm determines the range of the first visible area visible from this view by analyzing the grid points and scene elements in the terrain base model. For example, if the training personnel are located on flat ground and there are mountains and part of the urban area in front, the algorithm will calculate the part of the mountain slope and urban buildings that can be seen from the current position. Render the first visible area. For example, render the green vegetation-covered area of the mountain, the gray building outlines of the city, and the blue background of the sky. Generate the texture and layout of scene elements, and use the first learning rendering algorithm to generate the texture and layout of scene elements in the first visible area. Use the texture rendering algorithm formula to generate corresponding textures according to the type and position of scene elements. For example, for the trees in the forest area, green leaf textures and brown trunk textures are generated according to the types and distribution densities of the trees.For buildings in urban areas, generate gray wall textures and blue glass window textures. Use the reflection algorithm formula to calculate the reflection effect of scene elements. For example, for the glass windows of a building, calculate the brightness and color of the glass window reflection based on the ambient light intensity and the light source direction in the surrounding environment. Assume the ambient light intensity is 80 (full value 100), the main light source intensity is 100, the diffuse reflection coefficient is 0.5, and the specular reflection coefficient is 0.3. Calculate the reflection brightness of the glass window as 40 (ambient light reflection) + 30 (specular reflection) = 70. Read the viewpoint position of the training user and adopt the second learning rendering algorithm to dynamically adjust the scene detail level. Calculate the rendering priority of the current terrain and scene according to the terrain and scene complexity coefficient, performance requirement coefficient, and rendering priority coefficient. For example, for mountainous terrain, the complexity coefficient is 0.8, the performance requirement coefficient is 0.7, and the rendering priority coefficient is 0.9. Calculate the rendering weight of the mountain as 0.8 × 0.7 × 0.9 = 0.504. For urban areas, the complexity coefficient is 0.9, the performance requirement coefficient is 0.6, and the rendering priority coefficient is 0.8. Calculate the rendering weight of the city as 0.9 × 0.6 × 0.8 = 0.432. Dynamically adjust the scene detail level according to the user's viewpoint position and movement direction. For example, when the training personnel's field of view is close to the urban area, give priority to rendering the details of urban buildings; when far from the urban area, reduce the detail level of the urban area to improve the rendering efficiency of other areas. Output the rendered scene image to the display device and update the rendering content according to the user's interaction operations. Render the terrain and scene elements of the image result according to the calculated texture, layout, and detail level to generate a complete scene image. Transmit the rendered image to the VR visual device, and the user can immerse themselves in observing and interacting through the VR device. When the user moves or changes the viewing angle in the scene, update the rendering content in real time. For example, when the user turns from the urban area to the forest area, the rendering system will dynamically adjust the detail level of the forest area and re-render the scene to ensure that the user always sees a more realistic scene.

[0098] Based on the same inventive concept, such as Figure 2As shown in the figure, this embodiment further provides a real-time rendering scene generation system for a simulation simulator, including: a detection drone, an information processing terminal, an image simulation simulator, and a VR visual device; the detection drone transmits information to the information processing terminal, the information processing terminal transmits data and a configuration file to the image simulation simulator, and the image simulation simulator transmits the generated image result to the VR visual device; the detection drone is used to obtain the surrounding terrain information and scene information, the information processing terminal is used to process the terrain information and scene information obtained by the detection drone, generate terrain data and a scene configuration file required for a training task through the terrain information and the scene information, the image simulation simulator is used to render the terrain data and the scene configuration file to generate the image result, and the VR visual device is used to present the rendered image result.

[0099] Further, the image simulation simulator further includes: a first image information processing module and a second image information processing module. The first visible area is obtained from the terrain data and the scene configuration file through the first image information processing module, and the image result is obtained from the first visible area through the second image information processing module.

[0100] Further,

[0101] In addition, detection drones have important applications in multiple fields, including but not limited to: Military field: Improve the battlefield situation awareness ability and provide real-time and accurate drone intelligence for the command department. Civilian field: Applied in fields such as aviation, meteorology, and environmental protection to support the economic and social development. Airport clearance area: Detect and track drones that invade the airport clearance area to ensure flight safety. Protection of important infrastructure: Provide outer protection for bases and important infrastructure. The detection drones in this invention are mainly used for scanning terrain data information and collecting environmental data information. The optoelectronic detection technology uses the principles of optics and electronics to achieve long-distance and non-contact detection of targets by capturing and analyzing the optical signals reflected or emitted by the drones. This detection drone can collect information in multiple ways, including visible light imaging, infrared imaging, and laser imaging. The optoelectronic detection technology can provide intuitive image information, is suitable for daytime and nighttime detection, and has high detection accuracy especially in complex environments. An information processing terminal refers to a device that directly interacts with users or other devices in a computer network. These devices, as interfaces for information processing and communication, are usually used to input programs and data into a computer or receive the processing results output by the computer. For example, common information processing terminals include desktop computers, laptop computers, smartphones, tablets, etc., which achieve interaction with users through various input and output devices (such as keyboards, mice, monitors, cameras, etc.). In this invention, the information processing terminal is mainly used for information processing. Through highly integrated design, it adopts a highly integrated SoC (System On Chip) design, integrating multiple functions such as a central processing unit, a memory, and a communication module, improving the performance and reliability of the device. An image simulation simulator is a device or software system used to generate and process image data, capable of simulating real-world image scenes in a virtual environment. It generates realistic image data streams through computer graphics and image processing technologies, and is used to test and verify image processing algorithms, computer vision systems, and machine learning models. For example, the CamSim™ camera simulator can generate high-quality image data streams and supports multiple interface standards. In this invention, high-quality and high-resolution image data is generated through the image simulation simulator, supporting multiple image formats and sensor types, and at the same time supporting real-time image generation and transmission, ensuring the synchronization and real-time nature of the image data, ensuring improved image transmission efficiency, reducing time costs, and ensuring the reliability and accuracy of the images. VR visual devices, that is, virtual reality (VR) devices, refer to devices that generate a three-dimensional virtual environment through computer technology, allowing users to immerse themselves in it and interact with it. These devices usually include head-mounted display devices (such as VR headsets), controllers, sensors, etc., and can provide multi-sensory experiences including vision, hearing, and even touch. In this invention, the VR visual device is mainly used for providing training images, enabling training personnel to train better.

[0102] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only for the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for generating a real-time rendering scene of a simulation simulator, characterized in that: The method comprises the following steps: Collecting surrounding terrain information and scene information through a detection drone, and transmitting the terrain information and scene information to an information processing terminal; Generating terrain data and scene configuration files required for a training task in the information processing terminal through the terrain information and the scene information includes: In the information processing terminal, the terrain data and scene configuration files required for the training task are generated by the Mesh surface fitting technology. The Mesh surface fitting technology is optimized by a self-organizing neural network intelligent algorithm. The mathematical expression of the self-organizing neural network intelligent algorithm is: ； in, is the weight change of the xth neuron at the tth iteration; is the neural network learning rate; is the neighborhood function, which represents the neighborhood relationship between the y-th winning neuron and the x-th neuron; is the current input sample; is the weight vector of the xth neuron at iteration number t; is the current iteration number; The neural network learning rate is: ； in, is the gradient information of the current parameter; is a constant to ensure numerical stability; is the terrain information weight, is the scene information weight; is an extraordinary parameter used to control the step size of parameter update; The terrain information weight is: ； in, is an exponential decay coefficient, and 0.45> >0.9; To detect the percentage of mountain terrain collected by drones, To detect the percentage of hilly terrain collected by drones, To detect the proportion of flat terrain collected by the drone, To detect the water terrain ratio collected by the drone, To detect the valley terrain percentage value collected by the drone, is the proportion of terrain information collected by the detection drone at the t-1th iteration; is an exponentially weighted moving average; The scene information weight is: ； in, To detect the proportion of urban scenes collected by drones, To detect the proportion of forest scenes collected by drones, To detect the percentage of grassland shrub scenes collected by drones, To detect the proportion of other scenes collected by the drone, is the percentage of scene information collected by the detection drone at the t-1th iteration; And initialize the rendering engine; A terrain basic model is constructed according to the terrain data and the scene configuration file, a first visible area in the terrain basic model is calculated by a machine vision analysis algorithm, and the first visible area is rendered; the first visible area is a visible area at an initial default viewing angle in a scene loaded by a trainee; Using a first learning rendering algorithm to generate texture and layout of scene elements in the first visible area; Reading the viewpoint position of the training user, rendering the first visible area using a second learning rendering algorithm to obtain an image result, and dynamically adjusting the scene detail level; The image result is output to a VR visual device, and the rendering content is updated in real time according to the user's interactive operation.

2. A method for generating a real-time rendering scene of a simulation simulator according to claim 1, characterized in that: The calculating the first visible area in the terrain basic model by using a machine vision analysis algorithm includes: The machine vision analysis algorithm adopts binocular matching algorithm, and its formula is: ； in, The area map needs to be rendered for the first visible area; The energy function corresponding to the area map to be rendered for the first visible area; is the left eye imaging area, is the imaging area of ​​the right eye; For the first visible area, other areas other than the left eye imaging area in the area map need to be rendered; The time cost and performance cost of rendering the area map for the first visible area, where the time cost is the unit time required to render the image area, and the performance cost is the amount of computing resources required to render the image area; is the disparity value of the left eye imaging area; is the disparity value of the right eye imaging area; is a penalty coefficient, which is applicable to the case where the disparity value of the left eye imaging area differs from the disparity value of the right eye imaging area by 1; It is also a penalty coefficient, which is applicable to the case where the difference between the disparity value of the left eye imaging area and the disparity value of the right eye imaging area is greater than 1; It is an indicator function that returns 1 if the condition is true, otherwise it returns 0.

3. A method for generating a real-time rendering scene of a simulation simulator according to claim 1, characterized in that: The first learning rendering algorithm includes: a texture rendering algorithm formula and a reflection algorithm formula, and the texture rendering algorithm formula is: ； in, is the color of the final pixel in the pixel area; is the weight of the i-th texture; is the color value of the i-th texture at coordinate (j, k, l); is the horizontal coordinate in the coordinate (j, k, l), is the ordinate in the coordinates (j, k, l), is the height coordinate in the coordinates (j, k, l); is the total number of textures; The reflection algorithm formula is: ； in, is the brightness of the reflected light of the final pixel; is the ambient light intensity; is the ambient light reflection coefficient; is the main light intensity; is the diffuse reflectance; is the specular reflection coefficient; is the light source direction vector; is the surface normal vector; is the reflected light direction vector; is the viewing direction vector; is the specular highlight exponent.

4. A method for generating a real-time rendering scene of a simulation simulator according to claim 1, characterized in that: The second learning rendering algorithm includes: a first rendering algorithm weight formula and a second rendering algorithm weight formula; the first rendering algorithm weight formula is used to calculate the rendering priority of the current terrain information, and the first rendering algorithm weight formula is: ； in, is the rendering weight of the corresponding terrain; is the complexity coefficient of the terrain; is the performance demand coefficient of the terrain; The rendering priority coefficient of the terrain; is the corresponding terrain, when =1 for mountainous areas, =2 for hills, =3 is flat ground, =4 is water area, =5 is a valley; The second rendering algorithm weight formula is used to calculate the rendering priority of the current scene information, and the second rendering algorithm weight formula is: ； in, is the rendering weight of the corresponding scene; is the complexity coefficient of the scene; is the performance requirement coefficient of the scenario; is the rendering priority coefficient of the scene; For the corresponding scene, when =1 for cities, =2 means forest, =3 is grassland shrubs, =4 means other types; Among them, when ≥ When , the details in the terrain information are rendered first. < When rendering the scene information, details in the scene information are given priority.

5. A method for generating a real-time rendering scene of a simulation simulator according to claim 4, characterized in that: The complexity coefficient of the terrain and the complexity coefficient of the scene are trained and optimized using a computer image training algorithm; the computer image training algorithm is trained using a computer image training algorithm formula, and the computer image training algorithm formula is: ； in, To optimize the weight ratio; is a first-order matrix; is a second-order matrix; is a constant, and 1≥ >

0.

6. A simulation simulator real-time rendering scene generation system, based on the method according to any one of claims 1 to 5, characterized in that: The system includes: a detection drone, an information processing terminal, an image simulation simulator, and a VR visual device; the detection drone transmits information to the information processing terminal, the information processing terminal transmits data and configuration files to the image simulation simulator, and the image simulation simulator transmits the generated image results to the VR visual device; the detection drone is used to obtain surrounding terrain information and scene information, the information processing terminal is used to process the terrain information and scene information obtained by the detection drone, and generate terrain data and scene configuration files required for training tasks through the terrain information and the scene information, the image simulation simulator is used to render the terrain data and the scene configuration files to generate the image results, and the VR visual device is used to present the rendered image results.

7. A simulation simulator real-time rendering scene generation system according to claim 6, characterized in that: The image simulation simulator also includes: a first image information processing module and a second image information processing module. The terrain data and the scene configuration file obtain the first visible area through the first image information processing module, and the first visible area obtains the image result through the second image information processing module.

Images