Insulator real-time rendering method, system and device and medium

Abstract

The invention discloses an insulator real-time rendering method, system and device and a medium. The method comprises the steps of obtaining point cloud data of a transformer substation insulator to be rendered; and inputting the point cloud data of the transformer substation insulator to be rendered into a trained insulator real-time rendering model represented by an implicit 3D shape to obtain a rendered insulator, the insulator real-time rendering model represented by the implicit 3D shape comprises a sparse voxel field construction module, a feature vector query and interpolation module and a light tracing and rendering module, and the method, the system, the equipment and the medium can realize real-time rendering of the insulator, and have the characteristics of excellent detail representation, rendering efficiency and resource consumption performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional rendering, and relates to a method, system, equipment and medium for real-time rendering of insulators. Background Art

[0002] With the rapid development of the Internet of Things and artificial intelligence, digital twin technology has gradually become popular. As one of its core technologies, 3D rendering technology has been widely used in various industries. Through 3D rendering, the appearance, shape and material of objects can be realistically presented, allowing people to observe the equipment intuitively. Especially in industrial scenarios, such as substations, 3D rendering can reproduce the operating status and environment of equipment in real time, providing more efficient support for monitoring and maintenance.

[0003] In order to achieve efficient rendering, common rendering methods, such as rasterization, ray tracing, path tracing, and voxel rendering, are widely used. However, these methods are powerless when faced with complex three-dimensional scenes. Although rasterization is fast, it is difficult to accurately simulate complex lighting and shadow effects; although ray tracing and path tracing can produce realistic rendering, they are computationally intensive and slow to render, making it difficult to meet real-time requirements; voxel rendering faces the problems of high storage requirements and low efficiency. Overall, the shortcomings of common methods in detail expression, rendering efficiency, and resource consumption limit their application in real-time rendering and visualization. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method, system, device and medium for real-time rendering of insulators. The method, system, device and medium can realize real-time rendering of insulators and have the characteristics of excellent detail expression, rendering efficiency and resource consumption performance.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] In one aspect, the present invention provides a method for real-time rendering of an insulator, comprising:

[0007] Get the point cloud data of the substation insulator to be rendered;

[0008] The point cloud data of the substation insulator to be rendered is input into the trained implicit 3D shape representation of the insulator real-time rendering model to obtain the rendered insulator, wherein the implicit 3D shape representation of the insulator real-time rendering model includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module.

[0009] The real-time rendering method for insulators of the present invention is further improved in that:

[0010] Furthermore, before inputting the point cloud data of the substation insulator to be rendered into the trained implicit 3D shape representation of the insulator real-time rendering model, the method further includes:

[0011] Build a dataset;

[0012] Based on the sparse voxel field construction module, feature vector query and interpolation module, and ray tracing and rendering module, an insulator real-time rendering model with implicit 3D shape representation is constructed;

[0013] The data set is used to train the insulator real-time rendering model represented by the implicit 3D shape, so as to obtain the trained insulator real-time rendering model represented by the implicit 3D shape.

[0014] Furthermore, the sparse voxel field construction module is constructed based on an adaptive resolution algorithm;

[0015] The ray tracing and rendering module is built based on the fusion of progressive ray tracing algorithm and adaptive sampling algorithm.

[0016] Furthermore, the loss function in the process of training the insulator real-time rendering model represented by the implicit 3D shape using the data set is:

[0017]

[0018] in, L(x) is the level of the current node, Lmax is the maximum level of the octree, θ is the network parameter to be optimized, and Z is the feature of the octree node.

[0019] In a second aspect of the present invention, the present invention provides an insulator real-time rendering system, comprising:

[0020] An acquisition module is used to obtain point cloud data of substation insulators to be rendered;

[0021] A rendering module is used to input the point cloud data of the substation insulator to be rendered into the trained implicit 3D shape representation of the insulator real-time rendering model to obtain the rendered insulator, wherein the implicit 3D shape representation of the insulator real-time rendering model includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module.

[0022] The insulator real-time rendering system of the present invention is further improved in that:

[0023] Furthermore, it also includes:

[0024] The first building module is used to build a data set;

[0025] A second construction module is used to construct an insulator real-time rendering model represented by an implicit 3D shape based on a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module;

[0026] A training module is used to train the insulator real-time rendering model represented by the implicit 3D shape using the data set to obtain the trained insulator real-time rendering model represented by the implicit 3D shape.

[0027] Furthermore, the sparse voxel field construction module is constructed based on an adaptive resolution algorithm;

[0028] The ray tracing and rendering module is built based on the fusion of progressive ray tracing algorithm and adaptive sampling algorithm.

[0029] Furthermore, the loss function in the process of training the insulator real-time rendering model represented by the implicit 3D shape using the data set is:

[0030]

[0031] in, L(x) is the level of the current node, Lmax is the maximum level of the octree, θ is the network parameter to be optimized, and Z is the feature of the octree node.

[0032] In a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the insulator real-time rendering method when executing the computer program.

[0033] In a fourth aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the insulator real-time rendering method are implemented.

[0034] The present invention has the following beneficial effects:

[0035] During specific operation, the insulator real-time rendering method, system, device and medium of the present invention input the point cloud data of the substation insulator to be rendered into the insulator real-time rendering model represented by the trained implicit 3D shape to obtain the rendered insulator, wherein the insulator real-time rendering model represented by the implicit 3D shape includes a sparse voxel field construction module, a feature vector query and interpolation module and a ray tracing and rendering module, wherein the insulator real-time rendering model combines adaptive step-by-step ray tracing and adaptive sampling on the basis of the ray tracing algorithm, and can dynamically adjust the step size and sampling number of the ray according to the complexity of the scene, so as to perform denser sampling in high-detail areas, which not only improves the rendering efficiency and reduces the amount of calculation, but also optimizes resource consumption, realizes the real-time rendering of the 3D scene while maintaining the high-precision geometry and appearance information of the substation insulator. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 is a flow chart of the method of the present invention;

[0038] Figure 2 is a schematic diagram of the insulator after pretreatment;

[0039] Figure 3 It is a framework diagram of the model in the present invention;

[0040] Figure 4 is the partition diagram of voxel space;

[0041] Figure 5 This is the flowchart of the ray tracing and rendering module;

[0042] Figure 6 A rendering of an insulator. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0045] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0046] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0047] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0048] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0050] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0051] Embodiment 1

[0052] refer to Figure 1 The insulator real-time rendering method of the present invention comprises:

[0053] 1) Build a dataset;

[0054] refer to Figure 2 , a large amount of point cloud data of substation insulators was collected using LiDAR for model training and testing. Due to environmental conditions, equipment limitations, and the characteristics of the insulators themselves, the collected point cloud data inevitably contains noise points. To improve data quality, the point cloud data is processed: 11) voxel downsampling is used to reduce the point cloud density and reduce the amount of data; 12) radius filtering is used for rough denoising to remove most discrete noise points; 13) point cloud data is manually and accurately denoised to ensure the integrity of the insulator shape features. The point cloud data after the above processing has significantly improved its quality and provided reliable data support for model training.

[0055] 2) Construct a real-time rendering model of insulators with implicit 3D shape representation;

[0056] refer to Figure 3It should be noted that the real-time rendering model of insulators represented by implicit 3D shapes in the present invention includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module, wherein the sparse voxel field construction module is constructed based on an adaptive resolution algorithm; the ray tracing and rendering module is constructed based on a fusion step-by-step ray tracing algorithm and an adaptive sampling algorithm, wherein the sparse voxel field construction module is used to efficiently divide the space and store features with the help of an octree data structure, introduce an adaptive resolution strategy, divide the area that requires higher details into smaller sub-voxels, and update the corresponding geometric information, while no finer division is performed in other areas; the feature vector query and interpolation module is used to predict the signed distance function and optimize the network parameters through gradient back propagation; the ray tracing and rendering module is used to perform real-time rendering of insulators represented by implicit 3D shapes according to the ray tracing algorithm. Experimental results show that the real-time rendering of insulators represented by implicit 3D shapes can achieve high-precision real-time rendering of substation insulators, and significantly improve the efficiency and safety of substation operation and maintenance by optimizing data storage and rendering processes and intelligently analyzing the status of insulators. Figure 4 , specifically:

[0057] 21) The sparse voxel field construction module performs spatial sampling on the acquired insulator point cloud data, and establishes a sparse octree in 3D space. The nodes are only allocated in the area containing the surface, and each node stores the corner feature Z to capture local geometric information. Specifically, the operation process of the sparse voxel field construction module is as follows:

[0058] 211) Construct a feature voxel octree and store the feature vectors after the multi-layer perceptron at the vertices of the voxels, such as Figure 4 As shown, adjacent voxels share their features. Since SDF only focuses on surface information, it only needs to further subdivide Gray voxels and store feature information.

[0059] 212) For the area where the user is focused, the refinement level needs to be gradually increased, the current voxel is divided into smaller sub-voxels, and the corresponding geometric information is updated. For the area far from the viewpoint or unimportant, a lower refinement level can be maintained.

[0060] 213) The preprocessed data is sampled. There are three main ways to distribute the sampling points, namely: uniform sampling randomly selects points in the entire space, surface sampling selects points with high density near the surface, and near-surface perturbation sampling applies random perturbations to surface points. Each sampling point x is stored as a triple (x, d, L), where d is the true signed distance and L is the highest depth of the sparse voxel octree.

[0061] 22) The feature vector query and interpolation module is used to find the voxel corresponding to the sampling point through the octree, and use the trilinear interpolation technology to input the fused feature data features into the neural network and output the predicted signed distance function (SDF). The specific operations of the feature vector query and interpolation module are as follows:

[0062] 221) For the query point x, the most appropriate octree level is selected according to the octree structure with adaptive resolution, and the voxel information corresponding to x is retrieved at different levels.

[0063] 222) For each level, the features at the 8 corners of the voxel are interpolated to x through trilinear interpolation as the eigenvalues ​​of the level, and the eigenvalues ​​of each level are summed Get the eigenvalues ​​of the query point.

[0064] 223) Input the feature value of the query point into the trained neural network, predict the corresponding SDF value, and calculate the SDF value The formula is:

[0065]

[0066] Among them, traverse the tree until level L, find all voxels V1:L={V1,...,VL} containing x, To perform trilinear interpolation on the 8 corner features of the voxel at x, the features of each layer are added together.

[0067] 224) Calculate the loss function, using the actual distance d and the predicted distance Calculate the loss.

[0068]

[0069] in, L(x) is the level of the current node, Lmax is the maximum level of the octree, and the higher its level, the greater its weight. The neural network parameters θ and the features Z of the octree nodes are optimized by back propagation of the loss function gradient. The MLP of L and the features Z are jointly optimized to ensure that the geometric details of the insulator can be accurately captured at all resolutions.

[0070] 224) According to the sign and size of the SDF value, determine whether the query point is inside the shape (negative SDF value), outside (positive SDF value), or on the surface (SDF value is close to zero, and a threshold needs to be set to consider calculation accuracy and performance).

[0071] S={x∈R 3 |f(x)=0}(3)

[0072] 23) The ray tracing and rendering module extracts feature vectors from the sparse voxel field, queries the SDF step by step, and determines the intersection point of the light and the shape surface to achieve real-time rendering. For details, refer to Figure 5 , the operation process of the ray tracing and rendering module is:

[0073] 231) Starting from the observer's position, initialize one or more rays.

[0074] 232) According to formula (4), the size of the step from the starting point along the direction of the light is dynamically calculated, and the current position is recorded at each step. Let the initial step be δ, and the influence of depth and illumination on the step size is controlled according to the depth change rate Δz and illumination gradient ΔL of the current position.

[0075]

[0076] Among them, k1 and k2 are weight factors.

[0077] 233) In each step, the octree acceleration structure is used to apply the axis-aligned bounding box intersection test to remove voxels that do not intersect with the insulator. The specific process is as follows:

[0078] 2331) Calculate the minimum and maximum intersection parameters t of the light in the x, y, and z directions x_min ,t x_max ,t y_min ,t y_max ,t z_min and t z_max .

[0079] 2332) When the ray intersects with the AABB, the projection of the ray on the three axes should intersect with the projection of the AABB, that is, t x_min <t x_max And t y_min <t y_max And t z_min <t z_max At the same time, max(t x_min ,t y_min ,t z_min ) <min(t x_max ,t y_max ,t z_max ).

[0080] 234) In the intersecting voxels, when the highest depth of the voxel is not reached, its sub-voxels are further checked and the intersection with the light is continued to be refined, and the intersection point, normal vector and other information of the light and the voxel are recorded and filled into the light-voxel intersection list until the highest depth is reached. After reaching the highest depth, all non-intersecting voxels are eliminated.

[0081] 235) By analyzing the depth information of the current pixel (whether there are obvious geometric features or edges) and the lighting changes (near the light source or the edge of the reflective object), it is determined whether higher details are needed in the current area.

[0082] 236) If higher details are needed, the number of rays of the current pixel is dynamically adjusted, that is, the number is increased in high-detail areas (such as object edges or areas with sudden changes in illumination), and the number is reduced in flat areas.

[0083] 237) For each ray that intersects a surface, the surface can be directly generated based on the predicted SDF, and ray tracing can be continued to calculate reflection, refraction and shadowing with the insulator.

[0084] 238) Use the information in the ray-voxel intersection list to calculate the lighting, and perform a weighted average of the lighting information at each intersection to generate the final pixel color.

[0085] 3) Based on the data set constructed in step 1), the insulator real-time rendering model of implicit 3D shape representation constructed in step 2) is trained to obtain a trained insulator real-time rendering model of implicit 3D shape representation.

[0086] 4) Using the trained implicit 3D shape representation of the insulator real-time rendering model to perform real-time rendering of insulators.

[0087] Specifically, refer to Figure 6 , the present invention sets the hidden dimension of the multilayer perceptron (MLP) of all single hidden layers to h = 128. In order to support arbitrary distances, the ReLU activation function is used in the intermediate layer, and no activation function is used in the output layer. The feature dimension of SVO is set to m = 32, and all voxel features are initialized using a Gaussian prior with a standard deviation of σ = 0.01. During training, the Adam optimizer is used, the learning rate is set to 0.001, 50,000 points are resampled in each epoch, and the batch size is 512. These points are distributed in a ratio of 2:2:1, coming from the surface, nearby areas, and uniform samples, respectively. During the model rendering process, when the number of iterations of the spherical trajectory exceeds the maximum value or reaches the stopping criterion (where δ<0.0003), the algorithm for each ray is terminated.

[0088] Confirmatory trials

[0089] As shown in Table 1, the present invention performs well in all indicators. The real-time rendering model should occupy a small space on Storage (KB) to ensure fast loading; #Inference Param (inference parameter) should be as small as possible to improve the inference speed. gIoU and Chamfer-L1 reflect geometric matching and rendering accuracy respectively. Higher gIoU and lower Chamfer-L1 indicate better rendering effects. It can be seen that the present invention performs well in balancing storage, speed and accuracy.

[0090] Table 1

[0091]

[0092]

[0093] As shown in Table 2, in real-time rendering, Frametimes (ms) and Improvement Factor are key indicators for judging the quality of rendering. The rendering model should minimize Frametimes and keep the millisecond value low. At the same time, by optimizing the Improvement Factor, the model can increase the rendering speed without sacrificing quality, thereby improving the overall performance.

[0094] Table 2

[0095]

[0096] Embodiment 2

[0097] The insulator real-time rendering system of the present invention comprises:

[0098] An acquisition module is used to obtain point cloud data of substation insulators to be rendered;

[0099] A rendering module is used to input the point cloud data of the substation insulator to be rendered into the trained implicit 3D shape representation of the insulator real-time rendering model to obtain the rendered insulator, wherein the implicit 3D shape representation of the insulator real-time rendering model includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module.

[0100] As an embodiment of the present invention, it also includes:

[0101] The first building module is used to build a data set;

[0102] A second construction module is used to construct an insulator real-time rendering model represented by an implicit 3D shape based on a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module;

[0103] A training module is used to train the insulator real-time rendering model represented by the implicit 3D shape using the data set to obtain the trained insulator real-time rendering model represented by the implicit 3D shape.

[0104] As an implementation scheme of the present invention, the sparse voxel field construction module is constructed based on an adaptive resolution algorithm; the ray tracing and rendering module is constructed based on a fusion step-by-step ray tracing algorithm and an adaptive sampling algorithm.

[0105] As an implementation scheme of the present invention, the loss function in the process of training the insulator real-time rendering model represented by the implicit 3D shape using the data set is:

[0106]

[0107] in, L(x) is the level of the current node, Lmax is the maximum level of the octree, θ is the network parameter to be optimized, and Z is the feature of the octree node.

[0108] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0109] Embodiment 3

[0110] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the insulator real-time rendering method when executing the computer program, for example, comprising: constructing a data set; constructing an insulator real-time rendering model represented by an implicit 3D shape based on a sparse voxel field construction module, a feature vector query and interpolation module and a ray tracing and rendering module; training the insulator real-time rendering model represented by an implicit 3D shape using the data set to obtain a trained insulator real-time rendering model represented by an implicit 3D shape; acquiring point cloud data of a substation insulator to be rendered; inputting the point cloud data of the substation insulator to be rendered into the trained insulator real-time rendering model represented by an implicit 3D shape to obtain a rendered insulator, wherein the insulator real-time rendering model represented by an implicit 3D shape comprises a sparse voxel field construction module, a feature vector query and interpolation module and a ray tracing and rendering module. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, network interface, and memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0111] Embodiment 4

[0112] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the insulator real-time rendering method are implemented, for example, including: constructing a data set; constructing an insulator real-time rendering model represented by an implicit 3D shape based on a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module; using the data set to train the insulator real-time rendering model represented by the implicit 3D shape to obtain the trained insulator real-time rendering model represented by the implicit 3D shape; obtaining point cloud data of the substation insulator to be rendered; inputting the point cloud data of the substation insulator to be rendered into the insulator real-time rendering model represented by the implicit 3D shape after training, to obtain the rendered insulator, wherein the insulator real-time rendering model represented by the implicit 3D shape includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module. Specifically, the computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include a random access memory (RAM) and / or a cache memory, etc. The non-volatile memory may include a read-only memory (ROM), a hard disk, a flash memory, an optical disk, a magnetic disk, and the like.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0118] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0119] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A real-time rendering method for insulators, characterized in that: include: Get the point cloud data of the substation insulator to be rendered; The point cloud data of the substation insulator to be rendered is input into the trained implicit 3D shape representation of the insulator real-time rendering model to obtain the rendered insulator, wherein the implicit 3D shape representation of the insulator real-time rendering model includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module.

2. The insulator real-time rendering method according to claim 1, characterized in that: Before inputting the point cloud data of the substation insulator to be rendered into the trained implicit 3D shape representation of the insulator real-time rendering model, the method further includes: Build a dataset; Based on the sparse voxel field construction module, feature vector query and interpolation module, and ray tracing and rendering module, an insulator real-time rendering model with implicit 3D shape representation is constructed; The data set is used to train the insulator real-time rendering model represented by the implicit 3D shape, so as to obtain the trained insulator real-time rendering model represented by the implicit 3D shape.

3. The insulator real-time rendering method according to claim 2, characterized in that: The sparse voxel field construction module is constructed based on an adaptive resolution algorithm; The ray tracing and rendering module is built based on the fusion of progressive ray tracing algorithm and adaptive sampling algorithm.

4. The insulator real-time rendering method according to claim 2, characterized in that: The loss function in the process of training the insulator real-time rendering model represented by the implicit 3D shape using the data set is: in, L(x) is the level of the current node, Lmax is the maximum level of the octree, θ is the network parameter to be optimized, and Z is the feature of the octree node.

5. An insulator real-time rendering system, characterized in that: include: An acquisition module is used to obtain point cloud data of substation insulators to be rendered; A rendering module is used to input the point cloud data of the substation insulator to be rendered into the trained implicit 3D shape representation of the insulator real-time rendering model to obtain the rendered insulator, wherein the implicit 3D shape representation of the insulator real-time rendering model includes a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module.

6. The insulator real-time rendering system according to claim 5, characterized in that: Also includes: The first building module is used to build a data set; A second construction module is used to construct an insulator real-time rendering model represented by an implicit 3D shape based on a sparse voxel field construction module, a feature vector query and interpolation module, and a ray tracing and rendering module; A training module is used to train the insulator real-time rendering model represented by the implicit 3D shape using the data set to obtain the trained insulator real-time rendering model represented by the implicit 3D shape.

7. The insulator real-time rendering system according to claim 6, characterized in that: The sparse voxel field construction module is constructed based on an adaptive resolution algorithm; The ray tracing and rendering module is built based on the fusion of progressive ray tracing algorithm and adaptive sampling algorithm.

8. The insulator real-time rendering system according to claim 6, characterized in that: The loss function in the process of training the insulator real-time rendering model represented by the implicit 3D shape using the data set is: in, L(x) is the level of the current node, Lmax is the maximum level of the octree, θ is the network parameter to be optimized, and Z is the feature of the octree node.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the insulator real-time rendering method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the insulator real-time rendering method according to any one of claims 1 to 4 are implemented.

Images