A three-dimensional model dynamic rendering method and system applied to the transportation field

Abstract

The present invention provides a method and system for dynamic rendering of three-dimensional models applied to the field of transportation, and relates to the field of smart city technology. This method aims at the characteristics of a large number of high-speed moving objects in the field of transportation and being easily affected by the weather environment. By dynamically adjusting the weights, the advantages of each sensor can be fully utilized to improve the accuracy of overall perception. At the same time, based on the different focuses of the modeling stage and the rendering stage, different weight allocation methods are adopted for different stages, which not only enhances the flexibility and adaptability of the system, but also improves the user experience and security. In the field of smart transportation, it can significantly improve the overall performance of the system and provide strong support for practical applications.

Description

Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a three-dimensional model dynamic rendering method and system applied to the transportation field. Background Art

[0002] With the continuous advancement of smart city construction, many new technologies have been introduced in the field of transportation, which can significantly improve traffic management, planning and residents' driving experience. 3D visualization technology for road and vehicle driving status is one of them. By displaying the rendered three-dimensional model in real time, users can view detailed road conditions through related devices. Three-dimensional modeling and rendering of roads are usually based on point cloud technology. However, traditional point cloud technology is mostly used in static environments. When dealing with dynamic scenes, especially fast-moving objects, high precision and real-time performance cannot usually be guaranteed, resulting in modeling and rendering effects that cannot meet expectations, which in turn affects user experience. Achieving high-precision three-dimensional modeling and rendering in a dynamic environment has always been a challenge.

[0003] Therefore, how to provide a better-performing three-dimensional model dynamic rendering method based on the scene characteristics and actual needs in the transportation field is a problem that needs to be solved urgently. Summary of the invention

[0004] In order to improve the above problems, the present invention provides a three-dimensional model dynamic rendering method and system applied to the transportation field.

[0005] A first aspect of an embodiment of the present invention provides a three-dimensional model dynamic rendering method applied to the field of transportation, the method comprising:

[0006] Acquire road environment data collected by a road environment perception system and sensor information for collecting the road environment data, wherein the sensor information includes sensor type, sensor quantity and sensor location;

[0007] Acquiring current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters, and road condition parameters;

[0008] Based on at least one of the environmental condition parameters, obtaining modeling weight parameters of each type of sensor through a preset weight allocation strategy;

[0009] Performing multi-sensor data fusion on the road environment data according to the modeling weight parameters, and dynamically modeling a three-dimensional model of the current scene according to the fused data;

[0010] Based on at least one of the environmental condition parameters, obtaining rendering weight parameters of each type of sensor through a preset weight allocation strategy;

[0011] The road environment data is subjected to multi-sensor data fusion according to the rendering weight parameters, and the three-dimensional model is dynamically rendered according to the fused data.

[0012] Optionally, the step of obtaining the modeling weight parameters of each type of sensor by a preset weight distribution strategy based on at least one of the environmental condition parameters specifically includes:

[0013] Obtaining basic modeling weight parameters according to a preset weight allocation strategy based on the sensor information;

[0014] According to the specific values ​​of various parameters in the environmental condition parameters and the degree of association with the modeling stage, the basic modeling weight parameters are corrected to obtain the modeling weight parameters.

[0015] Optionally, the step of obtaining rendering weight parameters of sensors of various types through a preset weight distribution strategy based on at least one of the environmental condition parameters specifically includes:

[0016] Obtaining basic rendering weight parameters according to a preset weight allocation strategy based on the sensor information;

[0017] According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the rendering stage, the basic rendering weight parameters are modified to obtain rendering weight parameters.

[0018] Optionally, the step of obtaining rendering weight parameters of sensors of various types through a preset weight distribution strategy based on at least one of the environmental condition parameters further specifically includes:

[0019] Extract the performance parameters of each sensor in dynamic modeling;

[0020] According to the specific values ​​of each parameter in the performance parameter and the environmental condition parameter and the correlation with the rendering stage, the basic rendering weight parameter is modified to obtain the rendering weight parameter.

[0021] Optionally, the method for correcting the weight parameter specifically includes:

[0022] Based on the specific values ​​of each parameter, determine whether the threshold for triggering weight correction has been reached;

[0023] If it is reached, the mapping relationship between each parameter and the weight parameter is determined according to the correlation between the parameter and the stage;

[0024] Calculate the value of the weight parameter correction under the influence of various parameters that reach the threshold value that triggers the weight correction.

[0025] Optionally, the method for correcting the weight parameter further includes:

[0026] The application scenarios are divided into regions, and the weight parameters are modified in each region.

[0027] Optionally, the sensor types include at least two of a laser radar, a millimeter wave radar, a camera, an infrared sensor, and a traffic flow sensor, the road environment data includes data collected by sensors of corresponding types, and the step of performing multi-sensor data fusion on the road environment data according to the modeling weight parameters and performing dynamic modeling of a three-dimensional model of the current scene according to the fused data specifically includes:

[0028] The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain first fusion data;

[0029] Bringing the first fused data into a three-dimensional modeling system for modeling;

[0030] The model is dynamically updated based on the continuously acquired first fusion data.

[0031] Optionally, the step of performing multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically rendering the three-dimensional model according to the fused data specifically includes:

[0032] The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain the second fusion data;

[0033] Bringing the second fused data into a model rendering system for rendering;

[0034] The model is dynamically rendered based on the continuously acquired second fusion data.

[0035] Optionally, the method for dynamically rendering the model includes:

[0036] The rendering result is processed according to the environmental condition parameters.

[0037] A second aspect of an embodiment of the present invention provides a three-dimensional model dynamic rendering system applied to the field of transportation, including:

[0038] A data acquisition unit, used to acquire the road environment data collected by the road environment perception system and the sensor information for collecting the road environment data, wherein the sensor information includes the sensor type, the number of sensors and the sensor position;

[0039] A parameter acquisition unit, used to acquire current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters and road condition parameters;

[0040] A weight calculation unit, configured to obtain a modeling weight parameter of each type of sensor through a preset weight distribution strategy based on at least one of the environmental condition parameters;

[0041] A dynamic modeling unit, used for performing multi-sensor data fusion on the road environment data according to the modeling weight parameters, and performing dynamic modeling of a three-dimensional model of the current scene according to the fused data;

[0042] The weight calculation unit is further used to obtain the rendering weight parameters of each type of sensor through a preset weight allocation strategy based on at least one of the environmental condition parameters;

[0043] A dynamic rendering unit is used to perform multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically render the three-dimensional model according to the fused data.

[0044] In summary, the present invention provides a method and system for dynamic rendering of three-dimensional models applied in the field of transportation. In view of the fact that there are a large number of high-speed moving objects in the field of transportation and they are easily affected by the weather environment, the advantages of each sensor can be fully utilized by dynamically adjusting the weights to improve the accuracy of overall perception. At the same time, based on the different focuses of the modeling stage and the rendering stage, different weight allocation methods are adopted for different stages, which not only enhances the flexibility and adaptability of the system, but also improves the user experience and security. In the field of intelligent transportation, it can significantly improve the overall performance of the system and provide strong support for practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A method flow chart of a three-dimensional model dynamic rendering method applied to the transportation field according to an embodiment of the present invention;

[0047] Figure 2 The present invention is a functional module block diagram of a three-dimensional model dynamic rendering system applied to the transportation field according to an embodiment of the present invention.

[0048] Reference numerals:

[0049] Data collection unit 110; parameter acquisition unit 120; weight calculation unit 130; dynamic modeling unit 140; dynamic rendering unit 150. DETAILED DESCRIPTION

[0050] With the continuous advancement of smart city construction, many new technologies have been introduced in the field of transportation, which can significantly improve traffic management, planning and residents' driving experience. 3D visualization technology for road and vehicle driving status is one of them. By displaying the rendered three-dimensional model in real time, users can view detailed road conditions through related devices. Three-dimensional modeling and rendering of roads are usually based on point cloud technology. However, traditional point cloud technology is mostly used in static environments. When dealing with dynamic scenes, especially fast-moving objects, high precision and real-time performance cannot usually be guaranteed, resulting in modeling and rendering effects that cannot meet expectations, which in turn affects user experience. Achieving high-precision three-dimensional modeling and rendering in a dynamic environment has always been a challenge.

[0051] Therefore, how to provide a better-performing three-dimensional model dynamic rendering method based on the scene characteristics and actual needs in the transportation field is a problem that needs to be solved urgently.

[0052] In view of this, the designers of the present invention have designed a three-dimensional model dynamic rendering method and system for use in the field of transportation.

[0053] 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, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0054] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0055] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0056] In the description of the present invention, it should be noted that the terms "top", "bottom", "inside", "outside", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invented product is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0057] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0059] The following is a detailed description of a three-dimensional model dynamic rendering method applied to the transportation field provided in this embodiment.

[0060] See also Figure 1 This embodiment provides a three-dimensional model dynamic rendering method applied to the transportation field, the method comprising:

[0061] Step S101, acquiring road environment data collected by a road environment perception system and sensor information for collecting the road environment data, wherein the sensor information includes sensor type, sensor quantity and sensor location.

[0062] In actual applications, in the road environment perception system of smart cities, different types of sensors are set up to obtain different types of road environment data according to different needs.

[0063] Sensor types include at least two of laser radar, millimeter wave radar, camera, infrared sensor, and traffic flow sensor. Among them, laser radar is mainly used to obtain three-dimensional point cloud data, which is the core data needed for subsequent three-dimensional modeling. Millimeter wave radar obtains relevant data by emitting millimeter wave signals and measuring the reflected signals, including distance information, speed information, angle information, target physical properties, etc., which has a very important weight for modeling high-speed moving objects in traffic scenes. Camera users obtain image or video data, which contains rich color and texture information to support subsequent rendering, and can also provide depth information and semantic information (such as traffic signs, lane lines, pedestrians, etc.). Infrared sensors are a supplement to the above sensor data under low lighting conditions. Traffic flow sensors can obtain real-time traffic flow information and help guide the allocation of resources in the modeling process. For example, during peak hours, the proportion of modeling resources for vehicles or pedestrians should be increased accordingly. The data collected by these different types of sensors together constitute the road environment data of the road environment perception system.

[0064] In different specific scenarios, the road environment perception system includes different types of sensors, and the corresponding road environment data composition is also different. Taking the common road environment perception system roadside holographic perception system as an example, the roadside holographic perception system usually deploys multiple types of sensors on both sides of the road, including cameras, radars, lidars, etc., to fully perceive the road traffic environment.

[0065] When acquiring data, in addition to acquiring the collected road environment data, it is also necessary to obtain sensor information. The sensor type in the sensor information is not only used to distinguish the road environment data and facilitate subsequent processing, but also affects the weight parameter allocation in the subsequent modeling and rendering process. In different scenarios, even if the sensor type is the same, due to the different numbers and locations of each type of sensor, there will be different weight parameter allocations. For example, when the number of sensors of a certain type is significantly higher than that of other types, and the location settings are relatively dense, the road environment data collected by this type of sensor will be assigned a higher weight parameter in the subsequent modeling and rendering process.

[0066] Step S102, obtaining current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters and road condition parameters.

[0067] Weather condition parameters are used to reflect the impact of weather, including light intensity (day and night, shadows and strong light), severe weather (rain, snow, fog, etc.); traffic condition parameters include the flow, speed, density, etc. of vehicles or people; road condition parameters include road surface conditions, road size and direction, and the size and location of surrounding buildings.

[0068] Environmental condition parameters have a great impact on both modeling and rendering. In the process of dynamic modeling, more attention is paid to data quality, consistency and real-time update, and weight adjustment is more frequent and complex, aiming to provide an accurate and detailed 3D environmental model. Therefore, obtaining environmental condition parameters and specifically participating in the adjustment of modeling weight parameters can achieve better dynamic modeling results.

[0069] Similarly, in the process of dynamic rendering, more attention is paid to real-time performance and graphics quality. By obtaining environmental condition parameters, textures and lighting effects that match the environment can be used to enhance the visual experience. On the one hand, the amount of data calculation can be reduced, and on the other hand, better rendering effects can be achieved. Or when rendering, factors that may affect the user's visual experience can be filtered, such as fog, rain, etc.

[0070] Step S103: Based on at least one of the environmental condition parameters, a modeling weight parameter of each type of sensor is obtained through a preset weight distribution strategy.

[0071] After obtaining the road environment data and environmental condition parameters, the modeling weight parameters corresponding to the data of each type of sensor in the obtained road environment data can be configured through a pre-set weight allocation strategy to facilitate subsequent modeling.

[0072] The setting of the weight distribution strategy can be obtained in a variety of ways, such as an experience-based table mapping setting, or a deep learning model based on historical data to learn the optimal weight distribution strategy.

[0073] As a preferred embodiment of the present invention, step S103 specifically includes:

[0074] Obtaining basic modeling weight parameters according to a preset weight allocation strategy based on the sensor information;

[0075] According to the specific values ​​of various parameters in the environmental condition parameters and the degree of association with the modeling stage, the basic modeling weight parameters are corrected to obtain the modeling weight parameters.

[0076] The process of obtaining the modeling weight parameters is divided into two steps. First, according to the classification of sensor types, the preliminary basic modeling weight parameters are obtained. This parameter only considers the advantages and disadvantages of different sensor types and applicable scenarios, and cannot fully match the current scenario. Therefore, on this basis, it is necessary to further consider the influence of environmental condition parameters. As mentioned above, the mapping relationship (i.e., correlation) of the environmental condition parameters to the influence of weight parameters is different in the modeling stage and the rendering stage. Therefore, when correcting the weight parameters, different strategies should be implemented for the modeling and rendering stages respectively.

[0077] During the modeling phase, the weights may need to be adjusted frequently based on the influence of various dimensions of environmental condition parameters. For example, in low light conditions, the weight of the camera may be reduced, while the weight of the lidar and millimeter-wave radar may be increased. In rainy and snowy weather, the weight of the millimeter-wave radar may be increased, while the weight of the lidar and camera may be reduced. The weight of the lidar may be increased in tunnels, and the weight of the infrared camera may be increased at night. For stationary targets, the weights of the lidar and camera may be increased; for moving targets, the weights of the millimeter-wave radar and camera may be increased. For high-speed moving targets, the weight of the millimeter-wave radar may be increased; for low-speed moving targets, the weights of the lidar and camera may be increased. For vehicles, the weights of the millimeter-wave radar and lidar may be increased; for pedestrians, the weights of the camera and infrared camera may be increased. For small targets (such as bicycles and pets), the weights of the camera and lidar may be increased; for large targets (such as trucks and buses), the weight of the millimeter-wave radar may be increased. In traffic flow monitoring, the weights of the millimeter-wave radar and camera may be increased to accurately count the number and speed of vehicles. In accident response, the weights of the camera and lidar may be increased to quickly obtain detailed information on the scene.

[0078] In the rendering stage, weight adjustment needs to consider the quality and real-time requirements of rendering in addition to sensor performance and environmental conditions. The frequency of weight adjustment is relatively low because rendering focuses more on the final visual effect rather than the slight changes in each frame of data. For example, for noisy data from cameras and lidars, denoising can be performed before rendering to improve image quality. In applications that require high resolution and details, the weights of lidar and high-resolution cameras can be increased. In applications where resolution requirements are not high, the weight of millimeter-wave radar can be increased to improve data processing efficiency.

[0079] As a preferred embodiment of the present invention, the method for correcting the weight parameter specifically includes:

[0080] Based on the specific values ​​of each parameter, determine whether the threshold for triggering weight correction has been reached;

[0081] If it is reached, the mapping relationship between each parameter and the weight parameter is determined according to the correlation between the parameter and the stage;

[0082] Calculate the value of the weight parameter correction under the influence of various parameters that reach the threshold value that triggers the weight correction.

[0083] In actual scenarios, the environmental condition parameters obtained are dynamically changing. Based on the above logic, the modeling weight parameters must also be dynamically corrected. The specific correction process can be achieved through commonly used algorithms, such as performance evaluation-based algorithms (such as online learning, reinforcement learning) and environment perception-based algorithms (such as environment recognition models).

[0084] It should be noted that when modifying weight parameters, for the same parameter, the thresholds for triggering weight modification are different in the modeling stage and the rendering stage to reflect the different needs of different stages.

[0085] On the other hand, as a preferred embodiment of the present invention, the method for correcting the weight parameter further includes:

[0086] The application scenarios are divided into regions, and the weight parameters are modified in each region.

[0087] As a preferred method, when computing power or computing resources support it, in addition to configuring modeling weight parameters according to sensor type, it is also possible to further refine and configure weight parameters based on specific sensors. That is, for each road environment data collected by each sensor, a weight parameter is individually assigned to participate in subsequent data fusion, so as to obtain more accurate results.

[0088] Step S104, performing multi-sensor data fusion on the road environment data according to the modeling weight parameters, and performing dynamic modeling of a three-dimensional model of the current scene according to the fused data.

[0089] The multi-sensor data fusion process is to align the data from different sensors into the same coordinate system, while ensuring the consistency of the data from different sensors in time and space. It is necessary to complement and cross-validate the data from multiple sensors to improve the robustness and accuracy of the system. However, in practical applications, there may be contradictions in the data between different sensors. To address this contradiction, it is necessary to handle it through the configuration process of the weight parameters mentioned above. Higher weight parameters correspond to higher credibility in data complementarity and cross-validation. For example, LiDAR provides accurate 3D point cloud data, millimeter wave radar provides distance and speed information, and cameras provide rich color and texture information. If one sensor detects an object and other sensors do not, the existence of the object can be further verified, and the final modeling result is determined by the modeling weight parameters.

[0090] As a preferred embodiment of the present invention, step S104 specifically includes:

[0091] The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain first fusion data;

[0092] Bringing the first fused data into a three-dimensional modeling system for modeling;

[0093] The model is dynamically updated based on the continuously acquired first fusion data.

[0094] Since the system continuously acquires new road environment data and environmental condition parameters, the established three-dimensional model is dynamically updated based on the acquired new data to keep the model updated in real time and reflect environmental changes. As a preferred embodiment of the present invention, an incremental update strategy can be adopted to update only the changed parts instead of rebuilding the entire model. At the same time, a consistency correction algorithm (such as EKF) is used to maintain consistency between multiple frames of data.

[0095] It should be noted that during the entire dynamic modeling process, the modeling weight parameters of each type of sensor are also dynamically changed and modified.

[0096] Multi-sensor data fusion in dynamic modeling of 3D models can be implemented based on sensor fusion platforms, such as DAMS (Automatic Dynamic Analysis of Mechanical Systems) or ROS (Robot Operating System).

[0097] Step S105 , based on at least one of the environmental condition parameters, obtaining rendering weight parameters of each type of sensor through a preset weight distribution strategy.

[0098] After completing the dynamic modeling of the 3D model of the current scene, real-time dynamic rendering can be performed based on the 3D dynamic model.

[0099] Specifically, the above step S105 specifically includes:

[0100] Obtaining basic rendering weight parameters according to a preset weight allocation strategy based on the sensor information;

[0101] According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the rendering stage, the basic rendering weight parameters are modified to obtain rendering weight parameters.

[0102] The calculation process of the rendering weight parameter is the same as the basic logic of the modeling weight parameter, and the same parts are not repeated here. The main difference is that for the needs of dynamic rendering, sensor performance is also a very important consideration factor when performing rendering weight parameters. Based on this, as a preferred method of an embodiment of the present invention, step S105 specifically includes:

[0103] Extract the performance parameters of each sensor in dynamic modeling;

[0104] According to the specific values ​​of each parameter in the performance parameter and the environmental condition parameter and the correlation with the rendering stage, the basic rendering weight parameter is modified to obtain the rendering weight parameter.

[0105] Through the modeling phase, using road environment data from different sensors and the effects of dynamic modeling, performance parameters that reflect sensor performance can be extracted. The performance parameters are then used as an influencing dimension to modify the rendering weight parameters. For example, when a sensor fails or its performance degrades, its weight can be reduced in real time, and the weights of other sensors can be increased to compensate. For example, if the calibration of a camera deviates, its weight can be reduced.

[0106] For the dynamic correction of rendering weight parameters, we can combine rendering requirements and use a weight adjustment strategy that is simpler than the modeling weight parameters, such as weight allocation based on fixed rules or statistical methods based on historical data.

[0107] On the basis of the above, as a preferred implementation, the obtained performance parameters can also be further used in the dynamic correction process of subsequent modeling weight parameters to improve the precision and accuracy of modeling.

[0108] Step S106, performing multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically rendering the three-dimensional model according to the fused data.

[0109] As a preferred implementation, step S106 specifically includes:

[0110] The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain the second fusion data;

[0111] Bringing the second fused data into a model rendering system for rendering;

[0112] The model is dynamically rendered based on the continuously acquired second fusion data.

[0113] After obtaining the second fusion data calculated based on the rendering weight parameters, you can start rendering the 3D model. Choose a suitable graphics engine, such as Unity, Unreal Engine, etc., for high-precision dynamic rendering. Use high-resolution texture maps to provide rich color and texture information, especially in severe weather conditions, which can provide more details and color information. Apply advanced lighting models (such as PBR, Physically Based Rendering) to simulate real lighting effects, including reflection, refraction, etc.

[0114] In order to achieve better rendering effect, as a preferred implementation, step S106 further specifically includes:

[0115] The rendering result is processed according to the environmental condition parameters.

[0116] After obtaining the environmental condition parameters, the physical properties of different materials can be simulated for the target surface, such as metal, glass, concrete, etc. For weather conditions, HDR effects are applied to simulate the brightness differences under corresponding weather conditions to enhance visual realism. Even in severe weather conditions, raindrops, snow flakes and other effects can be simulated through post-processing to enhance the visual experience.

[0117] The following describes a three-dimensional model dynamic rendering method applied to the transportation field provided by the present invention through a specific scenario.

[0118] Autonomous driving vehicle driving in rainy weather:

[0119] Modeling phase:

[0120] Road environment data collection: LiDAR, millimeter wave radar and cameras collect data simultaneously.

[0121] Weight adjustment: After rainfall is detected, the weight of the millimeter-wave radar is increased and the weight of the camera and lidar is reduced.

[0122] Multimodal fusion: The weighted data is fused to generate a high-precision three-dimensional environment model.

[0123] Real-time Update: The model is continuously updated to reflect dynamic changes around the vehicle.

[0124] Rendering stage:

[0125] Weight adjustment: Increase the weight of parameters related to water surface reflection, halo effect, etc., and reduce the weight of some detail textures. Use high-resolution textures for vehicle and pedestrian models to improve details and realism.

[0126] High-Quality Textures: Use high-resolution texture maps to enhance the details of the road surface and surrounding objects.

[0127] Advanced Lighting: Uses a PBR lighting model to simulate the lighting effects of rainy days, including water droplet reflection and refraction.

[0128] Post-processing: Add water drop effects to car windows, car bodies and other surfaces to simulate rain dripping and flowing.

[0129] In summary, the three-dimensional model dynamic rendering method applied to the transportation field provided by the embodiment of the present invention can fully utilize the advantages of each sensor and improve the accuracy of overall perception by dynamically adjusting the weights, in view of the characteristics that there are a large number of high-speed moving objects in the transportation field and they are easily affected by the weather environment. At the same time, based on the different focuses of the modeling stage and the rendering stage, different weight allocation methods are adopted for different stages, which not only enhances the flexibility and adaptability of the system, but also improves the user experience and security. In the field of smart transportation, it can significantly improve the overall performance of the system and provide strong support for practical applications.

[0130] like Figure 2 As shown, a three-dimensional model dynamic rendering system applied to the transportation field provided by an embodiment of the present invention includes:

[0131] The data acquisition unit 110 is used to acquire the road environment data acquired by the road environment perception system and the sensor information for acquiring the road environment data, wherein the sensor information includes the sensor type, the number of sensors and the sensor position;

[0132] The parameter acquisition unit 120 is used to acquire current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters and road condition parameters;

[0133] A weight calculation unit 130, configured to obtain a modeling weight parameter of each type of sensor through a preset weight distribution strategy based on at least one of the environmental condition parameters;

[0134] A dynamic modeling unit 140, configured to perform multi-sensor data fusion on the road environment data according to the modeling weight parameters, and perform dynamic modeling of a three-dimensional model of the current scene according to the fused data;

[0135] The weight calculation unit 130 is further configured to obtain rendering weight parameters of each type of sensor through a preset weight allocation strategy based on at least one of the environmental condition parameters;

[0136] The dynamic rendering unit 150 is used to perform multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically render the three-dimensional model according to the fused data.

[0137] The three-dimensional model dynamic rendering system applied to the transportation field provided by the embodiment of the present invention is used to implement the above-mentioned three-dimensional model dynamic rendering method applied to the transportation field. Therefore, the specific implementation method is the same as the above-mentioned method and will not be repeated here.

[0138] In summary, the present invention provides a method and system for dynamic rendering of three-dimensional models applied in the field of transportation. In view of the fact that there are a large number of high-speed moving objects in the field of transportation and they are easily affected by the weather environment, the advantages of each sensor can be fully utilized by dynamically adjusting the weights to improve the accuracy of overall perception. At the same time, based on the different focuses of the modeling stage and the rendering stage, different weight allocation methods are adopted for different stages, which not only enhances the flexibility and adaptability of the system, but also improves the user experience and security. In the field of intelligent transportation, it can significantly improve the overall performance of the system and provide strong support for practical applications.

[0139] In several embodiments disclosed in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a module, a program segment or a part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0141] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A three-dimensional model dynamic rendering method applied to the field of transportation, characterized in that: The method comprises: Acquire road environment data collected by a road environment perception system and sensor information for collecting the road environment data, wherein the sensor information includes sensor type, sensor quantity and sensor location; Acquiring current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters, and road condition parameters; Based on at least one of the environmental condition parameters, obtaining modeling weight parameters of each type of sensor through a preset weight allocation strategy; Performing multi-sensor data fusion on the road environment data according to the modeling weight parameters, and dynamically modeling a three-dimensional model of the current scene according to the fused data; Based on at least one of the environmental condition parameters, obtaining rendering weight parameters of each type of sensor through a preset weight allocation strategy; Performing multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically rendering the three-dimensional model according to the fused data; The step of obtaining the modeling weight parameters of each type of sensor by a preset weight distribution strategy based on at least one of the environmental condition parameters specifically includes: Obtaining basic modeling weight parameters according to a preset weight allocation strategy based on the sensor information; According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the modeling stage, the basic modeling weight parameters are modified to obtain modeling weight parameters; The step of obtaining the rendering weight parameters of each type of sensor by a preset weight distribution strategy based on at least one of the environmental condition parameters specifically includes: Obtaining basic rendering weight parameters according to a preset weight allocation strategy based on the sensor information; According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the rendering stage, the basic rendering weight parameters are modified to obtain rendering weight parameters.

2. The three-dimensional model dynamic rendering method applied to the traffic field according to claim 1 is characterized in that: The step of obtaining the rendering weight parameters of each type of sensor by a preset weight distribution strategy based on at least one of the environmental condition parameters further specifically includes: Extract the performance parameters of each sensor in dynamic modeling; According to the specific values ​​of each parameter in the performance parameter and the environmental condition parameter and the correlation with the rendering stage, the basic rendering weight parameter is modified to obtain the rendering weight parameter.

3. The three-dimensional model dynamic rendering method applied to the traffic field according to any one of claims 1 to 2, characterized in that: The method for correcting the weight parameter specifically includes: Based on the specific values ​​of each parameter, determine whether the threshold for triggering weight correction has been reached; If it is reached, the mapping relationship between each parameter and the weight parameter is determined according to the correlation between the parameter and the stage; Calculate the value of the weight parameter correction under the influence of various parameters that reach the threshold value that triggers the weight correction.

4. The three-dimensional model dynamic rendering method applied to the traffic field according to claim 3 is characterized in that: The method for correcting the weight parameter further includes: The application scenarios are divided into regions, and the weight parameters are modified in each region.

5. The three-dimensional model dynamic rendering method applied to the traffic field according to claim 1, characterized in that: The sensor types include at least two of a laser radar, a millimeter wave radar, a camera, an infrared sensor, and a traffic flow sensor, the road environment data includes data collected by sensors of corresponding types, and the step of performing multi-sensor data fusion on the road environment data according to the modeling weight parameters and performing dynamic modeling of a three-dimensional model of the current scene according to the fused data specifically includes: The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain first fusion data; Bringing the first fused data into a three-dimensional modeling system for modeling; The model is dynamically updated based on the continuously acquired first fusion data.

6. The three-dimensional model dynamic rendering method applied to the traffic field according to claim 5 is characterized in that: The step of performing multi-sensor data fusion on the road environment data according to the rendering weight parameter and dynamically rendering the three-dimensional model according to the fused data specifically includes: The road environment data of each type of sensor is weighted averaged according to its corresponding modeling weight parameter to obtain the second fusion data; Bringing the second fused data into a model rendering system for rendering; The model is dynamically rendered based on the continuously acquired second fusion data.

7. The three-dimensional model dynamic rendering method applied to the traffic field according to claim 6 is characterized in that: Methods for dynamically rendering models include: The rendering result is processed according to the environmental condition parameters.

8. A three-dimensional model dynamic rendering system applied in the field of transportation, characterized in that: include: A data acquisition unit, used to acquire the road environment data collected by the road environment perception system and the sensor information for collecting the road environment data, wherein the sensor information includes the sensor type, the number of sensors and the sensor position; A parameter acquisition unit, used to acquire current environmental condition parameters, wherein the environmental condition parameters include weather condition parameters, traffic condition parameters and road condition parameters; A weight calculation unit, configured to obtain a modeling weight parameter of each type of sensor through a preset weight distribution strategy based on at least one of the environmental condition parameters; A dynamic modeling unit, used for performing multi-sensor data fusion on the road environment data according to the modeling weight parameters, and performing dynamic modeling of a three-dimensional model of the current scene according to the fused data; The weight calculation unit is further used to obtain the rendering weight parameters of each type of sensor through a preset weight allocation strategy based on at least one of the environmental condition parameters; A dynamic rendering unit, used for performing multi-sensor data fusion on the road environment data according to the rendering weight parameter, and dynamically rendering the three-dimensional model according to the fused data; The weight calculation unit is specifically used for: Obtaining basic modeling weight parameters according to a preset weight allocation strategy based on the sensor information; According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the modeling stage, the basic modeling weight parameters are modified to obtain modeling weight parameters; The weight calculation unit is further specifically used for: Obtaining basic rendering weight parameters according to a preset weight allocation strategy based on the sensor information; According to the specific values ​​of various parameters in the environmental condition parameters and the correlation with the rendering stage, the basic rendering weight parameters are modified to obtain rendering weight parameters.

Images