Vehicle driving scene rendering method and device, vehicle and computer storage medium
By dynamically adjusting image category labels and semantic segmentation processing, the problem of rendering on-board AR in high network latency environment is solved, and the rendering effect of AR driving scenes in high latency is achieved.
Patent Information
- Application Number
- CN202310541356.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-11
- Publication Date
- 2024-11-12
AI Technical Summary
Rendering of on-board AR driving scenarios highly relies on data transmission with low network latency, resulting in the inability to guarantee real-time rendering in a high network latency environment.
By acquiring the vehicle's driving scene images and real-time network delay data, the number of image category tags is dynamically adjusted, and the display rendering is enhanced based on semantic segmentation processing to reduce the dependence on low network delay.
Real-time rendering of AR driving scenarios can still be achieved under high network latency, improving the adaptability and stability of on-board AR technology.
Smart Images

Figure CN118941744A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a method and device for rendering a vehicle driving scene, a vehicle, and a computer storage medium. Background Art
[0002] In-vehicle AR (Augmented Reality) technology captures external scene image data in real time through radars and cameras deployed outside the car, performs plane detection and image fusion processing on the scene image data, and then transmits the processed image data to the AR glasses worn by the driver, so that the driver can obtain navigation information or road prompt information contained in the image data through the AR glasses, thereby greatly improving the driver's driving experience.
[0003] However, the current rendering of in-vehicle AR driving scenes is highly dependent on data transmission with low network latency. However, since vehicles will inevitably encounter various high network latency scenes such as tunnels, plateaus, basins, etc. during driving, data transmission with high network latency cannot guarantee the real-time rendering of in-vehicle AR driving scenes in this case. Summary of the invention
[0004] The main purpose of this application is to provide a method, device, vehicle and computer storage medium for rendering a vehicle driving scene, aiming to reduce the dependence of vehicle-mounted AR technology on data transmission with low network latency, so that the vehicle can still render AR driving scenes when high network latency occurs during driving.
[0005] To achieve the above object, the present application provides a method for rendering a vehicle driving scene, the method for rendering a vehicle driving scene comprising the following steps:
[0006] Acquire a driving scene image of a vehicle, and acquire real-time network delay data of the vehicle;
[0007] Determining a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data;
[0008] The driving scene image is semantically segmented according to the category label to obtain a semantic image, and enhanced display rendering of the vehicle driving scene is performed based on the semantic image.
[0009] Optionally, the step of determining a category label corresponding to the driving scene image according to the real-time network delay data includes:
[0010] Performing weighted calculation according to the real-time network delay data to obtain an evaluation result of the current network delay situation of the vehicle;
[0011] Determine a category label corresponding to the driving scene image under current network delay conditions according to the evaluation result.
[0012] Optionally, the category labels include a first category label, a second category label, a third category label and a fourth category label, the number of which decreases in sequence;
[0013] The step of determining, according to the evaluation result, a category label corresponding to the driving scene image under the current network delay condition comprises:
[0014] Detecting a network delay interval in which the evaluation result is located;
[0015] If it is detected that the network delay interval is the first interval, determining that the category label corresponding to the driving scene image under the current network delay condition is the first category label;
[0016] If it is detected that the network delay interval is a second interval, determining that the category label is the second category label, wherein the minimum network delay value of the second interval is higher than the maximum network delay value of the first interval;
[0017] If it is detected that the network delay interval is a third interval, determining that the category label is the third category label, wherein the minimum network delay value of the third interval is higher than the maximum network delay value of the second interval;
[0018] If it is detected that the network delay interval is the fourth interval, the category label is determined to be the fourth category label, wherein the minimum network delay value of the fourth interval is higher than the maximum network delay value of the third interval.
[0019] Optionally, the real-time network delay data includes: bandwidth, delay, jitter and / or packet loss rate;
[0020] The step of obtaining the real-time network delay data of the vehicle includes:
[0021] Confirm whether rendering requirements for vehicle driving scenes have been received;
[0022] If it is confirmed that the rendering request has been received, real-time network delay monitoring is performed on the vehicle to obtain the bandwidth, the delay, the jitter and / or the packet loss rate.
[0023] Optionally, the vehicle is equipped with an enhanced display device, and the step of confirming whether a rendering requirement for a vehicle driving scene is received includes:
[0024] Monitoring the wearing state of the enhanced display device, wherein the wearing state includes: normal wearing and not wearing;
[0025] If it is monitored that the wearing state is the normal wearing state, confirming that the rendering request has been received;
[0026] If it is monitored that the wearing state is not worn, it is determined that the rendering request is not received.
[0027] Optionally, the vehicle is configured with a human-computer interaction interface, and the step of confirming whether a rendering requirement for a vehicle driving scene is received includes:
[0028] monitoring whether the human-computer interaction interface receives a rendering instruction for a vehicle driving scene, wherein the rendering instruction is triggered by a user of the vehicle;
[0029] If it is monitored that the human-computer interaction interface receives the rendering instruction, then confirming that the rendering requirement has been received;
[0030] If it is monitored that the human-computer interaction interface has not received the rendering instruction, it is confirmed that the rendering request has not been received.
[0031] Optionally, the vehicle is equipped with: an image acquisition device, a data processing device and an enhanced display device;
[0032] The step of acquiring a driving scene image of a vehicle comprises:
[0033] The image acquisition device acquires external scene image data of the vehicle to obtain a driving scene image of the vehicle;
[0034] The step of performing semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image comprises:
[0035] The driving scene image is transmitted to the data processing device as input data for semantic segmentation, so that the data processing device uses a preset semantic segmentation algorithm to determine the correspondence between pixels in the driving scene image and the category labels to obtain a semantic image;
[0036] After the step of performing enhanced display rendering of the vehicle driving scene based on the semantic image, the method further includes:
[0037] The vehicle driving scene after enhanced display rendering is displayed through the enhanced display device.
[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a rendering device for a vehicle driving scene, the rendering device for a vehicle driving scene comprising:
[0039] A data acquisition module, used to acquire a driving scene image of a vehicle, and to acquire real-time network delay data of the vehicle;
[0040] A data processing module, used to determine the category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data;
[0041] A scene rendering module is used to perform semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image, and perform enhanced display rendering of the vehicle driving scene based on the semantic image.
[0042] Optionally, each functional module of the vehicle driving scene rendering device implements the steps of the vehicle driving scene rendering method described above during operation.
[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a vehicle, which includes: a memory, a processor, and a rendering program for a vehicle driving scene stored on the memory and runnable on the processor, and when the rendering program for the vehicle driving scene is executed by the processor, the steps of the rendering method for the vehicle driving scene as described above are implemented.
[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a computer storage medium, on which a rendering program for a vehicle driving scene is stored. When the rendering program for the vehicle driving scene is executed by a processor, the steps of the rendering method for the vehicle driving scene as described above are implemented.
[0045] The vehicle driving scene rendering method, device, vehicle and computer storage medium provided in the embodiments of the present application are achieved by obtaining a driving scene image of a vehicle and real-time network delay data of the vehicle; determining a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data; performing semantic segmentation processing on the driving scene image according to the category labels to obtain a semantic image, and performing enhanced display rendering of the vehicle driving scene based on the semantic image.
[0046] In an embodiment of the present application, based on obtaining a driving scene image of a vehicle during driving and obtaining real-time network delay data of the vehicle being connected to the Internet, and then based on the category label of the image used for semantic segmentation, a feature that dynamically changes with the real-time network delay data of the vehicle is used. First, based on the real-time network delay data, the category label corresponding to the driving scene image at the current moment is determined, and finally, according to the category label, semantic segmentation is performed on the driving scene image to obtain a corresponding semantic image, thereby performing enhanced display rendering of the vehicle driving scene based on the semantic image.
[0047] In this way, the embodiment of the present application is based on the real-time network delay data of the monitored vehicle to dynamically change the number of category labels of the driving scene image when performing augmented reality rendering for the vehicle's driving scene, thereby ensuring that real-time rendering of the enhanced display can still be performed when the vehicle encounters high network delay. That is, the embodiment of the present application can reduce the reliance of on-board AR technology on data transmission with low network delay, thereby achieving the effect of being able to perform AR driving scene rendering even when high network delay occurs during driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 It is a schematic diagram of the structure of a terminal device in the hardware operating environment involved in the embodiment of the present application;
[0049] Figure 2 A schematic diagram of a flow chart of an embodiment of a method for rendering a vehicle driving scene of the present application;
[0050] Figure 3 A schematic diagram of an application scenario involved in an embodiment of a method for rendering a vehicle driving scene of the present application;
[0051] Figure 4 A schematic diagram of an application flow involved in an embodiment of a method for rendering a vehicle driving scene of the present application
[0052] Figure 5 This is a schematic diagram of the functional modules involved in an embodiment of a method for rendering a vehicle driving scene of the present application.
[0053] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0054] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0055] Reference Figure 1 , Figure 1 This is a schematic diagram of the terminal device structure of the hardware operating environment involved in the embodiment of the present application.
[0056] It should be noted that Figure 1 The terminal device of the embodiment of the present application may be a vehicle that executes the rendering method of the vehicle driving scene of the present application or a terminal device configured in the vehicle, and the terminal device may specifically be a vehicle computer (also called a vehicle computer processing terminal, etc.), a mobile terminal, a data storage control terminal, a PC or a portable computer, etc.
[0057] like Figure 1As shown, the vehicle or the terminal device configured in the vehicle may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0058] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the vehicle or the terminal device configured in the vehicle, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.
[0059] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and a rendering program for a vehicle driving scene.
[0060] exist Figure 1 In the vehicle shown or the terminal device configured in the vehicle, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; in the embodiment of the present application, the processor 1001 and the memory 1005 can be set in the vehicle or the terminal device configured in the vehicle, and the vehicle or the terminal device configured in the vehicle calls the rendering program of the vehicle driving scene stored in the memory 1005 through the processor 1001, and performs the following operations:
[0061] Acquire a driving scene image of a vehicle, and acquire real-time network delay data of the vehicle;
[0062] Determining a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data;
[0063] The driving scene image is semantically segmented according to the category label to obtain a semantic image, and enhanced display rendering of the vehicle driving scene is performed based on the semantic image.
[0064] Further, the processor 1001 calls the rendering program of the vehicle driving scene stored in the memory 1005, and also performs the following operations:
[0065] Performing weighted calculation according to the real-time network delay data to obtain an evaluation result of the current network delay situation of the vehicle;
[0066] Determine a category label corresponding to the driving scene image under current network delay conditions according to the evaluation result.
[0067] Further, the category tags include first category tags, second category tags, third category tags, and fourth category tags, the number of which decreases in sequence. The processor 1001 calls a rendering program of a vehicle driving scene stored in the memory 1005, and further performs the following operations:
[0068] Detecting a network delay interval in which the evaluation result is located;
[0069] If it is detected that the network delay interval is the first interval, determining that the category label corresponding to the driving scene image under the current network delay condition is the first category label;
[0070] If it is detected that the network delay interval is a second interval, determining that the category label is the second category label, wherein the minimum network delay value of the second interval is higher than the maximum network delay value of the first interval;
[0071] If it is detected that the network delay interval is a third interval, determining that the category label is the third category label, wherein the minimum network delay value of the third interval is higher than the maximum network delay value of the second interval;
[0072] If it is detected that the network delay interval is the fourth interval, the category label is determined to be the fourth category label, wherein the minimum network delay value of the fourth interval is higher than the maximum network delay value of the third interval.
[0073] Furthermore, the real-time network delay data includes: bandwidth, delay, jitter and / or packet loss rate. The processor 1001 calls the rendering program of the vehicle driving scene stored in the memory 1005, and also performs the following operations:
[0074] Confirm whether rendering requirements for vehicle driving scenes have been received;
[0075] If it is confirmed that the rendering request has been received, real-time network delay monitoring is performed on the vehicle to obtain the bandwidth, the delay, the jitter and / or the packet loss rate.
[0076] Furthermore, the vehicle is equipped with an enhanced display device, and the processor 1001 calls a rendering program of the vehicle driving scene stored in the memory 1005, and further performs the following operations:
[0077] Monitoring the wearing state of the enhanced display device, wherein the wearing state includes: normal wearing and not wearing;
[0078] If it is monitored that the wearing state is the normal wearing state, confirming that the rendering request has been received;
[0079] If it is monitored that the wearing state is not worn, it is determined that the rendering request is not received.
[0080] Furthermore, the vehicle is equipped with a human-machine interaction interface, and the processor 1001 calls a rendering program of a vehicle driving scene stored in the memory 1005, and further performs the following operations:
[0081] monitoring whether the human-computer interaction interface receives a rendering instruction for a vehicle driving scene, wherein the rendering instruction is triggered by a user of the vehicle;
[0082] If it is monitored that the human-computer interaction interface receives the rendering instruction, then confirming that the rendering requirement has been received;
[0083] If it is monitored that the human-computer interaction interface has not received the rendering instruction, it is confirmed that the rendering request has not been received.
[0084] Furthermore, the vehicle is configured with: an image acquisition device, a data processing device and an enhanced display device, the processor 1001 calls a rendering program of a vehicle driving scene stored in the memory 1005, and also performs the following operations:
[0085] The image acquisition device acquires external scene image data of the vehicle to obtain a driving scene image of the vehicle;
[0086] The driving scene image is transmitted to the data processing device as input data for semantic segmentation, so that the data processing device uses a preset semantic segmentation algorithm to determine the correspondence between pixels in the driving scene image and the category labels to obtain a semantic image;
[0087] The processor 1001 calls the rendering program of the vehicle driving scene stored in the memory 1005, and after performing the enhanced display rendering of the vehicle driving scene based on the semantic image, further performs the following operations:
[0088] The vehicle driving scene after enhanced display rendering is displayed through the enhanced display device.
[0089] Based on the above-mentioned terminal device, various embodiments of the method for rendering the vehicle driving scene of the present application are provided.
[0090] Please refer to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the method for rendering a vehicle driving scene of the present application.
[0091] It should be understood that although a logical order is shown in the flowchart, in some cases, the method for rendering a vehicle driving scene of the present application may of course also perform the steps shown or described in an order different from that shown here.
[0092] In this embodiment, the rendering method of the vehicle driving scene of the present application is applied to a vehicle or a terminal device such as a vehicle computer configured for the vehicle. For the convenience of explanation and reading comprehension, the following text uses the vehicle computer as the execution subject to explain the embodiment of the rendering method of the vehicle driving scene of the present application.
[0093] like Figure 2 As shown, in a first embodiment of the method for rendering a vehicle driving scene of the present application, the method for rendering a vehicle driving scene of the present application may include the following steps:
[0094] Step S10: acquiring a driving scene image of a vehicle, and acquiring real-time network delay data of the vehicle;
[0095] In this embodiment, when the vehicle is started by the user and driven, the vehicle computer continuously acquires the driving scene images of the vehicle acquired by the image acquisition device configured on the vehicle exterior based on the connection with the image acquisition device configured on the vehicle exterior. In addition, the vehicle computer also acquires the real-time network delay data of the vehicle during the entire driving process based on the network delay monitoring of the vehicle.
[0096] It should be noted that, in this embodiment, the network delay monitoring of the vehicle by the vehicle computer is a technology for measuring the quality of network connection. This technology usually uses the Ping (Packet Internet Groper, an Internet packet explorer) command to measure the time delay required to reach the target host in real time.
[0097] Based on the network delay monitoring of the vehicle, the rendering of the in-vehicle AR scene can dynamically transmit data to the AR display end through real-time delay monitoring. In-vehicle AR scene rendering refers to the process of rendering virtual objects into the real world corresponding to the vehicle driving scene in AR augmented reality applications. This process involves fusing the image of the virtual object with the image of the real world (obtained based on semantic segmentation of the driving scene image) so that users can see the interaction between the virtual object and the real world. The position, size and direction of the virtual object need to correspond to the real-world objects.
[0098] The position, size and direction of the virtual object correspond to the real-world objects, so semantic segmentation technology is needed to detect the objects in the real world, and then align the virtual object with the monitored object. Semantic segmentation technology is a technology that divides an image into regional blocks with certain semantic meanings and identifies the semantic category of each regional block. Optionally, there are three main types of semantic segmentation technologies, namely region-based semantic segmentation, fully convolutional network semantic segmentation, and weakly supervised semantic segmentation. Among them, semantic segmentation is a classification at the pixel level, and pixels belonging to the same category are classified into one category, so semantic segmentation understands the image from the pixel level. Semantic segmentation labels each pixel in the image with a category label. During vehicle driving, semantic segmentation can help the vehicle identify objects such as roads, pedestrians, and vehicles, so as to better complete driving tasks.
[0099] Optionally, in this embodiment and various feasible embodiments described below, the step of “obtaining a driving scene image of the vehicle” in the above step S10 may include:
[0100] The image acquisition device acquires external scene image data of the vehicle to obtain a driving scene image of the vehicle;
[0101] In this embodiment, the vehicle's computer can be connected to an image acquisition device configured for the vehicle to send control instructions to the image acquisition device so that the image acquisition device can continuously collect external scene image data of the vehicle during the driving process of the vehicle, thereby the vehicle's computer can obtain the driving scene image outside the vehicle.
[0102] For example, the image acquisition device configured on the vehicle exterior can be a panoramic camera of the vehicle. In this way, the vehicle computer can obtain the driving scene image outside the vehicle in real time through the panoramic camera based on the connection with the panoramic camera.
[0103] Optionally, since vehicles generally have four or more panoramic cameras, in some feasible embodiments, the rendering method of the vehicle driving scene of the present application only needs to use the image information collected by the vehicle's front-view camera. At this time, the vehicle's computer can continuously collect the vehicle's driving scene images based only on the vehicle's front-view camera among the vehicle's four panoramic cameras during the vehicle driving process.
[0104] Step S20: determining a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data;
[0105] In this embodiment, after the vehicle's computer obtains the driving scene image of the vehicle and obtains the real-time network delay data of the vehicle during the entire driving process based on network delay monitoring, the computer can determine the category label corresponding to the driving scene image at the current moment based on the real-time network delay data according to the number of category labels used for semantic segmentation in the pre-set image that dynamically changes with the real-time network delay data.
[0106] It should be noted that, in this embodiment and other feasible embodiments described below, the feature that the number of category labels used for semantic segmentation in a pre-set image changes dynamically with the real-time network delay data means: considering that the more image labels there are, the greater the amount of calculation, the higher the network transmission pressure will be, and if the number of image labels is smaller, the amount of calculation will be smaller, and the corresponding network transmission pressure will be lower. Therefore, the vehicle's computer dynamically changes the number of image category labels based on real-time network delay monitoring of the vehicle, that is, the number of category labels of the driving scene image changes dynamically corresponding to the real-time network delay data.
[0107] Step S30, performing semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image, and performing enhanced display rendering of the vehicle driving scene based on the semantic image.
[0108] In this embodiment, after the vehicle's computer determines the category label corresponding to the driving scene image at the current moment based on the vehicle's real-time network delay data, the computer can further perform semantic segmentation on the driving scene image according to the category label to obtain a corresponding semantic image. Then, the computer performs enhanced display rendering of the vehicle's driving scene based on the semantic image.
[0109] Optionally, in this embodiment and various feasible embodiments described below, the vehicle is further equipped with a data processing device specifically used for performing semantic segmentation processing on the driving scene image of the vehicle. The data processing device may specifically be the vehicle computer itself, or any data processing terminal integrated with or external to the vehicle computer.
[0110] Based on this, the step of "performing semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image" in the above step S30 may include:
[0111] The driving scene image is transmitted to the data processing device as input data for semantic segmentation, so that the data processing device uses a preset semantic segmentation algorithm to determine the correspondence between pixels in the driving scene image and the category labels to obtain a semantic image;
[0112] In this embodiment, after the vehicle's on-board computer determines the category label corresponding to the driving scene image at the current moment, the on-board computer immediately uses the driving scene image as input data that needs to be processed by semantic segmentation, thereby transmitting the driving scene image to an internally integrated or externally connected data processing device (if the data processing device is the on-board computer itself, the on-board computer first transmits the driving scene image to its own integrated semantic segmentation model). In this way, the data processing device can use the pre-configured semantic segmentation algorithm to perform semantic segmentation processing on the driving scene image, thereby determining the correspondence between each pixel in the driving scene image and the category label corresponding to the driving scene image at the current moment. Based on this, the vehicle's on-board computer can obtain the semantic image corresponding to the driving scene image at the current moment.
[0113] After that, the vehicle's onboard computer further performs image registration on the obtained semantic image and the virtual driving parameter image, thereby completing enhanced display rendering of the vehicle driving scene based on the semantic image.
[0114] Optionally, in this embodiment and various feasible embodiments described below, the vehicle is also equipped with an enhanced display device, that is, AR glasses. Based on this, after the above step of "performing enhanced display rendering of the vehicle driving scene based on the semantic image", the rendering method of the vehicle driving scene of the present application may also include:
[0115] Step S40, displaying the vehicle driving scene after enhanced display rendering through the enhanced display device.
[0116] In this embodiment, after the vehicle computer performs enhanced display rendering of the vehicle driving scene based on the semantic image, the vehicle driving scene after enhanced display rendering can be further transmitted to the enhanced display device for display.
[0117] For example, Figure 3 In the application scenario shown, the vehicle's computer obtains the driving scene image during the vehicle's driving process in real time through the vehicle's front camera, and then performs digital image processing on the driving scene image based on the result of real-time network delay monitoring of the vehicle - real-time network delay data, to obtain the vehicle driving scene after enhanced display rendering, and the processed vehicle driving scene is further displayed on the enhanced display device - AR glasses through streaming.
[0118] In this embodiment, when the vehicle is started by the user for driving, the vehicle's on-board computer continuously acquires the driving scene image of the vehicle acquired by the image acquisition device configured on the vehicle exterior based on the connection with the image acquisition device. In addition, the vehicle's on-board computer also acquires the real-time network delay data of the vehicle during the entire driving process based on the network delay monitoring of the vehicle. Afterwards, the vehicle computer first determines the category label corresponding to the driving scene image at the current moment based on the real-time network delay data according to the feature that the number of category labels used for semantic segmentation in the pre-set image changes dynamically with the real-time network delay data. Finally, the vehicle computer further performs semantic segmentation processing on the driving scene image according to the category label to obtain the corresponding semantic image, and then, the vehicle computer performs enhanced display rendering of the vehicle driving scene based on the semantic image.
[0119] In this way, the embodiment of the present application is based on the real-time network delay data of the monitored vehicle to dynamically change the number of category labels of the driving scene image when performing augmented reality rendering for the vehicle's driving scene, thereby ensuring that real-time rendering of the enhanced display can still be performed when the vehicle encounters high network delay. That is, the embodiment of the present application can reduce the reliance of on-board AR technology on data transmission with low network delay, thereby achieving the effect of being able to perform AR driving scene rendering even when high network delay occurs during driving.
[0120] Based on the first embodiment of the method for rendering a vehicle driving scene of the present application, a second embodiment of the method for rendering a vehicle driving scene of the present application is proposed.
[0121] In the second embodiment of the method for rendering a vehicle driving scene of the present application, the step of "determining the category label corresponding to the driving scene image according to the real-time network delay data" in the above step S20 may include:
[0122] Step S201, performing weighted calculation according to the real-time network delay data to obtain an evaluation result of the current network delay situation of the vehicle;
[0123] Step S202: determining, according to the evaluation result, a category label corresponding to the driving scene image under the current network delay condition.
[0124] In this embodiment, after the vehicle's on-board computer performs real-time network delay monitoring on the vehicle to determine the real-time network delay data, the on-board computer determines the category label corresponding to the driving scene image at the current moment based on the real-time network delay data. A weight calculation is first performed based on the real-time network delay data determined by the monitoring and the weight value of the real-time network delay data, so as to obtain an evaluation result for the current network delay situation of the vehicle, and then the category label corresponding to the driving scene image when the vehicle is in the current network delay situation is determined based on the evaluation result.
[0125] It should be noted that in this embodiment and other feasible embodiments described below, there are four category labels corresponding to the driving scene image outside the vehicle, and each category label corresponds to a network delay evaluation result belonging to a different network delay interval (that is, an evaluation result for the current network delay situation of the vehicle).
[0126] In addition, in this embodiment and other feasible embodiments described below, the vehicle's on-board computer performs real-time network delay monitoring for the vehicle to determine real-time network delay data including: bandwidth, delay, jitter and / or packet loss rate. Based on this, the vehicle's on-board computer comprehensively determines the network delay evaluation standard for evaluating the current network delay situation of the vehicle based on the four parameters of bandwidth, delay, jitter and packet loss rate, and the formula is as follows: Score = kx1 + lx2 + mx3 + nx4. In this formula, Score represents the evaluation result, x1, x2, x3 and x4 are the scores of bandwidth, delay, jitter and packet loss rate, respectively, and k, l, m and n are the weight values corresponding to the four parameters, respectively.
[0127] Based on this, the vehicle's computer can perform real-time network delay monitoring on the vehicle to determine the above four real-time network delay data, and then immediately calculate according to the above formula Score=kx1+lx2+mx3+nx4 to obtain an evaluation result of the current network delay situation of the vehicle.
[0128] Optionally, the above evaluation results can be divided into 4 categories according to experiments and calculations, namely A, B, C, and D. Among them, the evaluation result A corresponds to the largest number of labels, which can be divided into roads, traffic, people, vehicles, vegetation, sky, etc.; the labels corresponding to the evaluation result B classify vegetation, sky, desert, etc. as nature; the labels corresponding to the evaluation result C classify roads, traffic, etc. as driving; and the labels corresponding to the evaluation result D are divided into red zone, green zone and yellow zone. The category label corresponding to the driving scene image determined by the vehicle computer when the vehicle is in the current network delay can be represented by Y, and Y can be expressed as: Y = Score (x).
[0129] Optionally, in this embodiment and other feasible embodiments described below, the category labels include a first category label, a second category label, a third category label and a fourth category label, the number of labels decreasing in sequence; wherein the first category label corresponds to the above-mentioned evaluation result A, the second category label corresponds to the above-mentioned evaluation result B, the third category label corresponds to the above-mentioned evaluation result C, and the fourth category label corresponds to the above-mentioned evaluation result D.
[0130] Based on this, the above step S202, determining the category label corresponding to the driving scene image under the current network delay according to the evaluation result, may include:
[0131] Step S2021, detecting the network delay interval in which the evaluation result is located;
[0132] In this embodiment, since the four category labels each correspond to a network delay evaluation result belonging to a different network delay interval, after the vehicle's computer calculates the evaluation result of the vehicle's current network delay situation, based on detecting the network delay interval in which the evaluation result is located, the category label corresponding to the network delay interval is determined as the category label corresponding to the driving scene image under the current network delay situation.
[0133] Step S2022: if it is detected that the network delay interval is the first interval, determining that the category label corresponding to the driving scene image under the current network delay is the first category label;
[0134] In this embodiment, the first interval is the network delay interval to which the above evaluation result A belongs. Based on this, when the vehicle's on-board computer detects the evaluation result of the vehicle's current network delay situation, and the network delay interval is the first interval to which the above evaluation result A belongs, the vehicle computer can determine that the category label corresponding to the driving scene image under the current network delay situation is the first category label with the largest number among the four categories of labels.
[0135] Step S2023: If it is detected that the network delay interval is a second interval, determining that the category label is the second category label, wherein the minimum network delay value of the second interval is higher than the maximum network delay value of the first interval;
[0136] In this embodiment, the second interval is the network delay interval to which the above evaluation result B belongs. Based on this, when the vehicle's on-board computer detects the evaluation result of the vehicle's current network delay situation, and the network delay interval in which it is located is the second interval to which the above evaluation result B belongs, the vehicle computer can determine that the category label corresponding to the driving scene image under the current network delay situation is the second category label among the four categories of labels, the number of which is second only to the above first category label.
[0137] Step S2024: if it is detected that the network delay interval is the third interval, determining that the category label is the third category label, wherein the minimum network delay value of the third interval is higher than the maximum network delay value of the second interval;
[0138] In this embodiment, the third interval is the network delay interval to which the above evaluation result C belongs. Based on this, when the vehicle's on-board computer detects the evaluation result of the vehicle's current network delay situation, and the network delay interval is the third interval to which the above evaluation result C belongs, the vehicle computer can determine that the category label corresponding to the driving scene image under the current network delay situation is the third category label among the four categories of labels, which is the second largest in number than the above second category label.
[0139] Step S2025: If it is detected that the network delay interval is the fourth interval, determine that the category label is the fourth category label, wherein the minimum network delay value of the fourth interval is higher than the maximum network delay value of the third interval.
[0140] In this embodiment, the fourth interval is the network delay interval to which the above evaluation result D belongs. Based on this, when the vehicle's onboard computer detects the evaluation result of the vehicle's current network delay situation, and the network delay interval is the third interval to which the above evaluation result D belongs, the vehicle computer can determine that the category label corresponding to the driving scene image under the current network delay situation is the fourth category label among the four categories of labels, which is second in number to the third category label.
[0141] It should be noted that, in this embodiment and other feasible embodiments, the minimum network delay value and the maximum network delay value of the network delay interval are respectively the network delay values with the smallest value and the largest value among all the network delay values contained in a network delay interval (which can be any one of the first to fourth intervals or any other intervals). For example, if a network delay interval is 1ms to 30ms, then the network delay interval contains thirty network delay values from 1 to 30, and the minimum network delay value of the network delay interval is 1ms, which is the smallest value among the thirty network delay values, and the maximum network delay value of the network delay interval is 30ms, which is the smallest value among the thirty network delay values; similarly, if a network delay interval is 100ms to 300ms, then the minimum network delay value of the network delay interval is 100ms, and the maximum network delay value of the network delay interval is 300ms.
[0142] In this embodiment, the rendering method of the vehicle driving scene of the present application, by defining four types of network delay evaluation results A, B, C, and D, each corresponding to a different number of image labels, thereby flexibly selecting a corresponding number of image labels for semantic segmentation and rendering based on the current network delay of the vehicle represented by the network delay evaluation result. That is, the rendering method of the vehicle driving scene of the present application obtains the delay detection parameter evaluation value Score in real time. As the evaluation value Score fluctuates, the label classification method also changes accordingly, and different classification methods have different numbers of labels, thereby alleviating the complexity of the kernel AR rendering calculation. In this way, it is ensured that the vehicle has corresponding effective rendering effects for driving scenes under various network delay conditions.
[0143] Furthermore, based on the first embodiment and / or the second embodiment of the method for rendering a vehicle driving scene of the present application, a third embodiment of the method for rendering a vehicle driving scene of the present application is proposed.
[0144] In the third embodiment of the method for rendering a vehicle driving scene of the present application, the real-time network delay data of the vehicle includes: bandwidth, delay, jitter and / or packet loss rate. Based on this, the step of "obtaining the real-time network delay data of the vehicle" in the above step S10 may include:
[0145] Step A, confirming whether a rendering requirement for a vehicle driving scene has been received;
[0146] Step B: If it is confirmed that the rendering request has been received, real-time network delay monitoring is performed on the vehicle to obtain the bandwidth, the delay, the jitter and / or the packet loss rate.
[0147] In this embodiment, when the vehicle's on-board computer performs real-time network delay monitoring for the vehicle to obtain the real-time network delay data of the vehicle, it first determines whether a rendering requirement for rendering the vehicle driving scene has been received. Therefore, only when it is determined that a rendering requirement for rendering the vehicle driving scene has been received, the real-time network delay monitoring for the vehicle is started to obtain the real-time bandwidth, delay, jitter and / or packet loss rate of the vehicle at the current moment. If it is confirmed that no rendering requirement for rendering the vehicle driving scene has been received, the on-board computer does not take any of the above operations.
[0148] Optionally, the vehicle is equipped with an enhanced display device, such as AR glasses. Based on this, the above step A, confirming whether a rendering requirement for the vehicle driving scene is received, may include:
[0149] Monitoring the wearing state of the enhanced display device, wherein the wearing state includes: normal wearing and not wearing;
[0150] If it is monitored that the wearing state is the normal wearing state, confirming that the rendering request has been received;
[0151] If it is monitored that the wearing state is not worn, it is determined that the rendering request is not received.
[0152] In this embodiment, the vehicle computer can monitor the wearing state of the enhanced display device configured by the vehicle through the connection with the enhanced display device, so that when the vehicle computer detects that the enhanced display device is used by the user and its wearing state is normal, it can confirm that the rendering request for the current vehicle driving scene needs to be rendered has been received. On the contrary, if the vehicle computer detects that the enhanced display device is not used by the user and its wearing state is not worn, it is confirmed that the rendering request for the current vehicle driving scene needs to be rendered has not been received.
[0153] It should be noted that, in this embodiment and other feasible embodiments, the vehicle computer can determine the wearing status of the enhanced display device by receiving signals transmitted by sensors such as light sensors, temperature sensors and / or gyroscopes on the enhanced display device.
[0154] For example, Figure 4As shown, in the case where the augmented reality device configured in the vehicle is an AR glasses, when the user of the vehicle wears the AR glasses during the driving process of the vehicle, the vehicle computer determines that it has received the rendering request for rendering the current vehicle driving scene, and then the vehicle computer of the vehicle detects whether the front camera of the vehicle is faulty, whether the vehicle computer itself can normally collect the data of the front camera, and whether the AR glasses configured by the vehicle can normally display the rendered frame data. Therefore, when all the detections are yes, the front camera of the vehicle is used to obtain the driving scene image of the vehicle exterior cleaning, and then the network delay of the vehicle is monitored to obtain real-time network delay data including bandwidth, delay, jitter and packet loss rate, and then the number of labels is determined based on the real-time network delay data obtained by the network delay monitoring, and then the semantic segmentation algorithm is used to obtain the label corresponding to each part of the driving scene image outside the vehicle to obtain a semantic image, and the semantic image and the virtual driving parameter image are image-aligned to render the vehicle driving scene, and finally the rendered result is transmitted to the AR glasses for display.
[0155] Optionally, the vehicle is equipped with a human-machine interaction interface, such as a data input interface that is in communication with a gesture signal acquisition device, a voice signal acquisition device and / or a command button. Based on this, the above step A, confirming whether a rendering requirement for a vehicle driving scene is received, may also include:
[0156] monitoring whether the human-computer interaction interface receives a rendering instruction for a vehicle driving scene, wherein the rendering instruction is triggered by a user of the vehicle;
[0157] If it is monitored that the human-computer interaction interface receives the rendering instruction, then confirming that the rendering requirement has been received;
[0158] If it is monitored that the human-computer interaction interface has not received the rendering instruction, it is confirmed that the rendering request has not been received.
[0159] In this embodiment, in addition to monitoring the wearing state of the enhanced display device through the connection with the enhanced display device configured for the vehicle, thereby determining whether a rendering request for the vehicle driving scene that needs to be rendered is received based on the wearing state, the vehicle computer can also monitor whether the human-computer interaction interface configured for the vehicle receives the rendering instruction for the vehicle driving scene that is triggered by the user through gestures, voice and / or by touching and clicking preset instruction buttons. Thus, when the vehicle computer detects that the human-computer interaction interface has received the rendering instruction generated by the user triggering, it can confirm that the rendering request for the vehicle driving scene that needs to be rendered is received. On the contrary, if the vehicle computer does not detect that the human-computer interaction interface has received the rendering instruction generated by the user triggering, it confirms that the rendering request for the vehicle driving scene that needs to be rendered has not been received.
[0160] In this embodiment, the rendering method of the vehicle driving scene of the present application monitors the network delay of the vehicle, and uses the real-time network delay data obtained by monitoring as an adjustment condition for the number of labels in the process of semantic segmentation of the external scene. In this way, the real-time video rendering effect of the enhanced display device can be improved, so that the vehicle can achieve a smooth AR scene rendering effect even in a high-latency network environment.
[0161] Furthermore, to achieve the above objectives, the present application also provides a rendering device for a vehicle driving scene.
[0162] Please refer to Figure 5 , Figure 5 This is a schematic diagram of functional modules involved in an embodiment of a rendering device for a vehicle driving scene of the present application, such as Figure 5 As shown, the rendering device of the vehicle driving scene of the present application includes:
[0163] A data acquisition module 10 is used to acquire a driving scene image of a vehicle, and to acquire real-time network delay data of the vehicle;
[0164] A data processing module 20, configured to determine a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data;
[0165] The scene rendering module 30 is used to perform semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image, and perform enhanced display rendering of the vehicle driving scene based on the semantic image.
[0166] Furthermore, the data processing module 20 includes:
[0167] A calculation unit, configured to perform weighted calculation according to the real-time network delay data to obtain an evaluation result of the current network delay situation of the vehicle;
[0168] A determination unit is used to determine, according to the evaluation result, a category label corresponding to the driving scene image under the current network delay condition.
[0169] Furthermore, the category labels include a first category label, a second category label, a third category label and a fourth category label, the number of which decreases in sequence; and the determination unit includes:
[0170] A detection subunit, used to detect the network delay interval in which the evaluation result is located;
[0171] A first determining subunit is configured to determine that the category label corresponding to the driving scene image under the current network delay is the first category label if it is detected that the network delay interval is a first interval;
[0172] a second determining subunit, configured to determine that the category label is the second category label if it is detected that the network delay interval is a second interval, wherein the minimum network delay value of the second interval is higher than the maximum network delay value of the first interval;
[0173] a third determining subunit, configured to determine that the category label is the third category label if it is detected that the network delay interval is a third interval, wherein the minimum network delay value of the third interval is higher than the maximum network delay value of the second interval;
[0174] The fourth determining subunit is used to determine that the category label is the fourth category label if it is detected that the network delay interval is a fourth interval, wherein the minimum network delay value of the fourth interval is higher than the maximum network delay value of the third interval.
[0175] Furthermore, the real-time network delay data includes: bandwidth, delay, jitter and / or packet loss rate; the data acquisition module 10 includes:
[0176] A demand confirmation unit, used to confirm whether a rendering demand for a vehicle driving scene has been received;
[0177] A delay monitoring unit is used to perform real-time network delay monitoring on the vehicle to obtain the bandwidth, the delay, the jitter and / or the packet loss rate if it is confirmed that the rendering request has been received.
[0178] Furthermore, the vehicle is equipped with an enhanced display device, a demand confirmation unit, including:
[0179] A first monitoring subunit is used to monitor the wearing state of the enhanced display device, wherein the wearing state includes: normal wearing and not wearing;
[0180] A first confirmation subunit is used to confirm that the rendering request is received if the wearing state is monitored to be the normal wearing state;
[0181] The second confirmation subunit is used to determine that the rendering request has not been received if it is monitored that the wearing state is not worn.
[0182] Furthermore, the vehicle is equipped with a human-machine interaction interface, a demand confirmation unit, and further includes:
[0183] A second monitoring subunit is used to monitor whether the human-computer interaction interface receives a rendering instruction for a vehicle driving scene, wherein the rendering instruction is triggered by a user of the vehicle;
[0184] A third confirmation subunit is used to confirm the receipt of the rendering requirement if it is detected that the human-computer interaction interface has received the rendering instruction;
[0185] The fourth confirmation subunit is used to confirm that the rendering request has not been received if it is monitored that the human-computer interaction interface has not received the rendering instruction.
[0186] Furthermore, the vehicle is equipped with: an image acquisition device, a data processing device and an enhanced display device;
[0187] The data acquisition module 10 is further used to acquire the external scene image data of the vehicle through the image acquisition device to obtain the driving scene image of the vehicle;
[0188] The data processing module 20 is further used to transmit the driving scene image as input data for semantic segmentation to the data processing device, so that the data processing device uses a preset semantic segmentation algorithm to determine the correspondence between the pixels in the driving scene image and the category labels to obtain a semantic image;
[0189] The rendering device of the vehicle driving scene of the present application also includes:
[0190] The output display module is used to display the vehicle driving scene after enhanced display rendering through the enhanced display device.
[0191] In addition, the present application also provides a vehicle having a rendering program for a vehicle driving scene that can be run on a processor, and when the vehicle executes the rendering program for the vehicle driving scene, the steps of the vehicle driving scene rendering method as described in any of the above embodiments are implemented.
[0192] The specific embodiments of the vehicle of the present application are basically the same as the embodiments of the rendering method of the vehicle driving scene mentioned above, and will not be repeated here.
[0193] In addition, the present application also provides a computer storage medium, on which a rendering program for a vehicle driving scene is stored. When the rendering program for the vehicle driving scene is executed by a processor, the steps of the vehicle driving scene rendering method described in any of the above embodiments are implemented.
[0194] The specific embodiments of the computer storage medium of the present invention are basically the same as the embodiments of the above-mentioned vehicle driving scene rendering method, and will not be described in detail here.
[0195] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.
[0196] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.
[0197] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, including a number of instructions for enabling a terminal device (which can be a device for executing the rendering method of the vehicle driving scene of the present application, and the terminal device can specifically be a mobile terminal, a data storage control terminal, a PC or a portable computer, etc.) to execute the methods described in each embodiment of the present application.
[0198] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A method for rendering a vehicle driving scene, characterized in that: The method for rendering a vehicle driving scene comprises the following steps: Acquire a driving scene image of a vehicle, and acquire real-time network delay data of the vehicle; Determining a category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data; The driving scene image is semantically segmented according to the category label to obtain a semantic image, and enhanced display rendering of the vehicle driving scene is performed based on the semantic image.
2. The method for rendering a vehicle driving scene according to claim 1, characterized in that: The step of determining the category label corresponding to the driving scene image according to the real-time network delay data comprises: Performing weighted calculation according to the real-time network delay data to obtain an evaluation result of the current network delay situation of the vehicle; Determine a category label corresponding to the driving scene image under current network delay conditions according to the evaluation result.
3. The method for rendering a vehicle driving scene according to claim 2, characterized in that: The category labels include first category labels, second category labels, third category labels and fourth category labels with decreasing number of labels in sequence; The step of determining, according to the evaluation result, a category label corresponding to the driving scene image under the current network delay condition comprises: Detecting a network delay interval in which the evaluation result is located; If it is detected that the network delay interval is the first interval, determining that the category label corresponding to the driving scene image under the current network delay condition is the first category label; If it is detected that the network delay interval is a second interval, determining that the category label is the second category label, wherein the minimum network delay value of the second interval is higher than the maximum network delay value of the first interval; If it is detected that the network delay interval is a third interval, determining that the category label is the third category label, wherein the minimum network delay value of the third interval is higher than the maximum network delay value of the second interval; If it is detected that the network delay interval is the fourth interval, the category label is determined to be the fourth category label, wherein the minimum network delay value of the fourth interval is higher than the maximum network delay value of the third interval.
4. The method for rendering a vehicle driving scene according to claim 1, characterized in that: The real-time network delay data includes: bandwidth, delay, jitter and / or packet loss rate; The step of obtaining the real-time network delay data of the vehicle includes: Confirm whether rendering requirements for vehicle driving scenes have been received; If it is confirmed that the rendering request has been received, real-time network delay monitoring is performed on the vehicle to obtain the bandwidth, the delay, the jitter and / or the packet loss rate.
5. The method for rendering a vehicle driving scene according to claim 4, characterized in that: The vehicle is equipped with an enhanced display device, and the step of confirming whether a rendering requirement for a vehicle driving scene is received includes: Monitoring the wearing state of the enhanced display device, wherein the wearing state includes: normal wearing and not wearing; If it is monitored that the wearing state is the normal wearing state, confirming that the rendering request has been received; If it is monitored that the wearing state is not worn, it is determined that the rendering request is not received.
6. The method for rendering a vehicle driving scene according to claim 4, characterized in that: The vehicle is configured with a human-machine interaction interface, and the step of confirming whether a rendering requirement for a vehicle driving scene has been received comprises: monitoring whether the human-computer interaction interface receives a rendering instruction for a vehicle driving scene, wherein the rendering instruction is triggered by a user of the vehicle; If it is monitored that the human-computer interaction interface receives the rendering instruction, then confirming that the rendering requirement has been received; If it is monitored that the human-computer interaction interface has not received the rendering instruction, it is confirmed that the rendering request has not been received.
7. The method for rendering a vehicle driving scene according to any one of claims 1 to 6, characterized in that: The vehicle is equipped with: an image acquisition device, a data processing device and an enhanced display device; The step of acquiring a driving scene image of a vehicle comprises: The image acquisition device acquires external scene image data of the vehicle to obtain a driving scene image of the vehicle; The step of performing semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image comprises: The driving scene image is transmitted to the data processing device as input data for semantic segmentation, so that the data processing device uses a preset semantic segmentation algorithm to determine the correspondence between pixels in the driving scene image and the category labels to obtain a semantic image; After the step of performing enhanced display rendering of the vehicle driving scene based on the semantic image, the method further includes: The vehicle driving scene after enhanced display rendering is displayed through the enhanced display device.
8. A rendering device for a vehicle driving scene, characterized in that: The rendering device of the vehicle driving scene comprises: A data acquisition module, used to acquire a driving scene image of a vehicle, and to acquire real-time network delay data of the vehicle; A data processing module, used to determine the category label corresponding to the driving scene image according to the real-time network delay data, wherein the number of the category labels is dynamically changed corresponding to the real-time network delay data; A scene rendering module is used to perform semantic segmentation processing on the driving scene image according to the category label to obtain a semantic image, and perform enhanced display rendering of the vehicle driving scene based on the semantic image.
9. A vehicle, characterized in that: The vehicle includes: a memory, a processor, and a rendering program for a vehicle driving scene stored in the memory and executable on the processor. When the rendering program for the vehicle driving scene is executed by the processor, the steps of the method for rendering a vehicle driving scene as described in any one of claims 1 to 7 are implemented.
10. A computer storage medium, characterized in that: The computer storage medium stores a rendering program for a vehicle driving scene, and when the rendering program for a vehicle driving scene is executed by a processor, the steps of the method for rendering a vehicle driving scene according to any one of claims 1 to 7 are implemented.
