Vehicle model rendering method

Abstract

The invention relates to a vehicle model rendering method. The method comprises the steps of obtaining a to-be-rendered vehicle model, a current weather scene and a current environment image; determining a target material map matched with the current weather scene; performing brightness and chromaticity balance adjustment on the preset illumination scene map based on the current environment image to obtain a target illumination scene map; and rendering the vehicle model according to the target material map and the target illumination scene map. According to the vehicle model rendering method and device, the vehicle model can be rendered from the three aspects of the material and the brightness and chromaticity of illumination, the split feeling of vehicle model rendering and the driving environment is reduced, the vehicle model shows the visual effect integrated with the driving environment, and the use immersion of a user is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of vehicles, and in particular, to a method for rendering a vehicle model. Background Art

[0002] 3D vehicle models are widely used in various interactive scenarios in the automotive field, such as commonly used in: AVM (AroundView Monitor, panoramic imaging system) parking, ADAS (Advanced Driving Assistance System, advanced driving assistance system) parking, and vehicle driving control and other scenarios.

[0003] In various interactive scenarios, the real-time driving environment around the vehicle is relatively changeable. Taking AVM as an example, it displays the real-time driving environment around the current vehicle through panoramic imaging. In contrast, the rendered vehicle model is fixed in terms of lighting scene, chromaticity, and material. Therefore, the fixed vehicle model needs to cope with the changeable driving environment, and the vehicle model will appear abrupt with the driving environment in terms of visual perception. There is a lack of real-time interaction response between the vehicle model and the driving environment, resulting in a sense of disconnection where the vehicle model and the driving environment are not well integrated. This will not only reduce the interactive visual effect, but also affect the user's perception accuracy of image details and weaken the driving guidance effect. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a method for rendering a vehicle model.

[0005] According to one aspect of the present disclosure, there is provided a method for rendering a vehicle model, including:

[0006] Obtaining a vehicle model to be rendered, the current weather scene, and the current environmental image;

[0007] Determining a target material texture map that matches the current weather scene;

[0008] Based on the current environmental image, performing brightness and chromaticity balance adjustment on a preset lighting scene texture map to obtain a target lighting scene texture map;

[0009] Rendering the vehicle model according to the target material texture map and the target lighting scene texture map.

[0010] According to another aspect of the present disclosure, there is also provided a rendering device for a vehicle model, including:

[0011] An obtaining module, configured to obtain a vehicle model to be rendered, the current weather scene, and the current environmental image;

[0012] A material determination module, configured to determine a target material texture map that matches the current weather scene;

[0013] A lighting adjustment module, configured to balance the brightness and chromaticity of a preset lighting scene map based on the current environmental image to obtain a target lighting scene map;

[0014] A model rendering module, configured to render the vehicle model according to the target material map and the target lighting scene map.

[0015] The present disclosure further provides an electronic device, which includes:

[0016] A processor;

[0017] A memory for storing executable instructions of the processor;

[0018] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the above-mentioned vehicle model rendering method.

[0019] The present disclosure further provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned vehicle model rendering method.

[0020] The technical solutions provided in the embodiments of the present disclosure have the following advantages compared with the prior art:

[0021] The technical solutions provided in the embodiments of the present disclosure include: obtaining a vehicle model to be rendered, a current weather scene, and a current environmental image; determining a target material map matching the current weather scene; balancing the brightness and chromaticity of a preset lighting scene map based on the current environmental image to obtain a target lighting scene map; and rendering the vehicle model according to the target material map and the target lighting scene map.

[0022] In this solution, by dynamically determining a target material map matching the current weather scene, the material rendered on the vehicle model can conform to the effect of the current weather scene; balancing the brightness and chromaticity of the preset lighting scene map based on the current environmental image, and providing a lighting effect for the preset lighting scene map of the vehicle model with the current environmental image, so that the preset lighting scene map after the balance adjustment can show a realistic lighting effect under the light conditions of the current environmental image. Thus, the light sense of the rendered vehicle model is consistent with the current environmental image, presenting a more gentle and realistic visual experience. Therefore, this solution renders the vehicle model from three aspects: the material and the brightness and chromaticity of the lighting according to the current weather scene and the current environmental image, reducing the sense of disconnection between the vehicle model rendering and the driving environment, making the vehicle model show a visual effect of integrating with the driving environment, and enhancing the user's use immersion. Description of the Drawings

[0023] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0024] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0025] Figure 1 Flowchart of the rendering method for the vehicle model according to the embodiment of the present disclosure;

[0026] Figure 2 Schematic diagram of the texture map rendering process in response to weather according to the embodiment of the present disclosure;

[0027] Figure 3 Schematic diagram of the current environment image according to the embodiment of the present disclosure;

[0028] Figure 4 Schematic diagram of two adjacent current environment images according to the embodiment of the present disclosure;

[0029] Figure 5 Schematic diagram of the adjustment process of the lighting scene according to the embodiment of the present disclosure;

[0030] Figure 6 Schematic diagram of the lighting switching system according to the embodiment of the present disclosure;

[0031] Figure 7 Schematic diagram of the structure of the rendering device for the vehicle model according to the embodiment of the present disclosure;

[0032] Figure 8 Schematic diagram of the structure of the electronic device according to the embodiment of the present disclosure. Detailed implementation manners

[0033] In order to be able to more clearly understand the above objects, features, and advantages of the present disclosure, the following will further describe the solutions of the present disclosure. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0034] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0035] In various interaction scenarios in the automotive field, a vehicle model with a fixed lighting scenario, fixed chromaticity, and fixed material needs to cope with a changing driving environment affected by factors such as time, climate, indoor and outdoor conditions, etc. Based on this, there is a lack of real-time interaction response between the vehicle model and the driving environment, resulting in a sense of disconnection where the vehicle model does not blend well with the background environment visually. The above will reduce the interactive visual effect and the user's perception accuracy of image details, and weaken the driving guidance effect.

[0036] Taking AVM as an example, AVM provides a top-down bird's-eye view for users by splicing fish-eye images around the vehicle in real time to provide parking guidance; during this process, the 3D vehicle model provides visualization and guidance of the vehicle's own state. The AVM panoramic image shows the real-time driving environment around the current vehicle, and the driving environment is relatively changeable; in contrast, the vehicle model rendered in the panoramic image is fixed in terms of lighting scenario, chromaticity, and material, etc. The above will reduce the visual effect of the panoramic image and the user's perception accuracy of image details, and weaken the parking guidance effect of the panoramic image.

[0037] Facing the above problems, the embodiments of the present disclosure provide a rendering method, device, equipment, and medium for a vehicle model. The present disclosure considers that the sources of the sense of disconnection and unreality between the vehicle model and the driving environment can be summarized into three aspects: material effect, brightness and chromaticity of lighting. Based on this, by obtaining the current weather scenario and the current environmental image, the above three aspects of the vehicle model are rendered in real time. Among them, according to the real-time current weather scenario, the vehicle model is rendered in terms of material; according to the real-time current environmental image, the vehicle model is rendered in terms of the brightness and chromaticity of the lighting scenario. In this way, the sense of fusion between the vehicle model and the real-time driving environment is optimized, so that the vehicle model changes dynamically with the current weather occasion and the current environmental image, showing a visual effect of integrating with the driving environment, and enabling the vehicle model to more realistically integrate into the current driving environment, enhancing the user's immersion experience. For ease of understanding, the embodiments of the present disclosure are described in detail below.

[0038] Figure 1 FIG. is a flowchart of a rendering method for a vehicle model provided by an embodiment of the present disclosure. This method can be applied to various interaction scenarios such as AVM parking, ADAS parking, vehicle driving control, and assisted driving. This rendering method for the vehicle model can be executed by a rendering device for the vehicle model, and this device can be implemented by software and / or hardware, specifically such as an electronic device or a server. Among them, the electronic device can include communication-enabled devices such as an in-vehicle host, a tablet computer, a desktop computer, a laptop computer, and a smart phone. The server can be a cloud server or a server cluster and other devices with storage and computing functions. In this embodiment, taking the electronic device as the execution subject as an example, the rendering method for the vehicle model is described.

[0039] Reference Figure 1 The rendering method of the vehicle model provided in this embodiment includes the following steps S102 - S108.

[0040] S102, Obtain the vehicle model to be rendered, the current weather scene, and the current environmental image.

[0041] In this embodiment, when the rendering program is initialized, the default vehicle model of the vehicle itself can be loaded from a pre - constructed model library. The vehicle model is specifically, for example, the white model to be rendered.

[0042] The electronic device receives the weather signal data of the vehicle head unit in real - time through the CAN bus to obtain the current weather scene. And, the current environmental image around the vehicle is collected in real - time through the camera. The environmental image can be at least one; for example, in the AVM scene, multiple fisheye images with different perspectives are collected in real - time through multiple cameras installed at different positions of the vehicle, and the multiple fisheye images are used as the current environmental image.

[0043] S104, Determine the target material texture map that matches the current weather scene. Among them, the target material texture map is used to represent the visual effect presented by the material of the vehicle itself (such as car paint) in the current weather scene. For example, in a snowy weather scene, the target material texture map can show the effect of a layer of snow covering the car paint, and in a rainy weather scene, the target material texture map can show the effect of some water droplets sticking to the car paint.

[0044] For weather scenes such as seasonal changes, sunny, cloudy, rainy, snowy, foggy, and sandy - stormy, generally fixed materials are used for rendering, and this method lacks the immersion of user experience. Based on this, this embodiment can determine multiple weather scenes, configure material texture maps for each weather scene respectively, generate the matching relationship between the weather scene and the material texture map; after obtaining the current day's scene, use this matching relationship to determine the target material texture map that matches the current weather scene.

[0045] In this embodiment, the above - mentioned weather scenes can include various weathers common in life, such as sunny, cloudy, overcast, rainy, snowy, foggy, sandy - stormy, etc. At this time, the types of weather scenes are more, the corresponding types of material texture maps matching the weather scenes are also rich and diverse, the material texture maps are more refined, and the matching degree with the weather scenes is higher.

[0046] Alternatively, to reduce the amount of data, the above weather scenarios may only include several weather types that can cause significant changes in the visual effects of materials. For example, in an actual scenario, the visual effects of the paint on the same vehicle under sunny, cloudy, and overcast days are very similar. Therefore, sunny, cloudy, and overcast days can be classified as the same weather type, i.e., clear weather. Correspondingly, the visual effects of the paint on the same vehicle under sunny and snowy days are very different. Therefore, snowy days can be regarded as a weather type of snowfall different from clear weather. Based on this, weather scenarios can include, for example, clear weather, snowfall weather, rainfall weather, sandstorm weather, etc. At this time, the types of weather scenarios are fewer, which not only reduces the amount of data of the material texture map, but also can meet the changing requirements of the visual effects of materials under different weather scenarios, making the visual effects of the texture map adapt to the changes in weather scenarios, and can improve the efficiency of determining the target material texture map that matches the current weather scenario.

[0047] S106. Based on the current environmental image, perform brightness and chromaticity balance adjustment on the preset lighting scene texture map to obtain the target lighting scene texture map.

[0048] Among them, the preset lighting scene texture map is a texture map rendered under a certain environmental image, which can represent the brightness and chromaticity effects of the lighting presented on the surface of the vehicle model under this environmental image. Exemplarily, when the rendering program is initialized, the default preset lighting scene texture map can be loaded from a pre-constructed lighting material library. Or, according to the historical rendering results of the vehicle model, count the occurrence times of each historical lighting scene texture map in the recent period (such as 3 months), and use the historical lighting scene texture map with the most occurrence times as the preset lighting scene texture map to be adjusted. Or, obtain the current time and the current position of the vehicle; check whether there is a historical lighting scene texture map in the historical rendering results of the vehicle model that matches the current time and the current position; if it exists, use this historical lighting scene texture map as the preset lighting scene texture map to be adjusted.

[0049] It can be understood that the real driving environment is more complex and changeable, such as: driving during the day and at night, underground garages, tunnels and outdoor roads, sunny days and overcast days, etc. Even at the same location and the same time of day, the brightness and chromaticity of the driving environment are different in different seasons. Therefore, in this embodiment, it is necessary to perform brightness and chromaticity balance adjustment on the preset lighting scene texture map.

[0050] In an embodiment of balancing the brightness and chromaticity of a preset lighting scene map, the current environmental image pre-obtained by a vehicle-mounted camera can be utilized based on Image-Based Lighting (IBL) to provide a lighting effect for the preset lighting scene map of a vehicle model. Taking the current environmental image as a light source, the indirect lighting received by the vehicle surface (such as reflected light and scattered light) is simulated through the current environmental image, and the current environmental image is applied as lighting information to the preset lighting scene map, so that the vehicle model can exhibit delicate reflection and shadow effects under the light conditions of the current driving environment, enhancing the overall visual realism, thereby achieving a realistic lighting effect on the surface of the vehicle model.

[0051] Based on the above description, in a possible embodiment, the environmental image corresponding to the preset lighting scene map can be obtained, that is, which environmental image the preset lighting scene map is the balance adjustment result of, and its corresponding environmental image is used as the standard environmental image.

[0052] Then, in the YUV color space, the first pixel values of the current environmental image in each color channel and the second pixel values of the standard environmental image in each color channel are obtained. If the pixel value difference between the first pixel value and the second pixel value exceeds a preset pixel difference threshold, it indicates that the difference in lighting brightness and chromaticity between the current environmental image and the standard environmental image is relatively large. Using the preset lighting scene map under the standard environmental image to render the vehicle model will result in the vehicle model not being integrated with the current driving environment and having a sense of fragmentation.

[0053] Therefore, when the pixel value difference between the first pixel value and the second pixel value exceeds the preset pixel difference threshold, the model adjustment coefficient can be determined based on the preset lighting adjustment factor, the pixel value difference, and the second pixel mean value of the standard environmental image; the preset lighting scene map is balanced in brightness and chromaticity based on the model adjustment coefficient to obtain the target lighting scene map.

[0054] S108, rendering the vehicle model according to the target material map and the target lighting scene map.

[0055] After obtaining the target material map matching the current weather scene and the target lighting scene map matching the current environmental image according to the above embodiments, the vehicle model is rendered according to the target material map and the target lighting scene map. This step can be implemented through existing technologies, such as using a fragment shader to render the material and lighting effects of the body surface in the vehicle model through the target material map and the target lighting scene map respectively, so as to enhance the realism of the vehicle model in the current environmental image.

[0056] The rendering method of the vehicle model provided in this embodiment includes: obtaining the vehicle model to be rendered, the current weather scene and the current environment image; determining the target material map that matches the current weather scene; balancing the brightness and chromaticity of the preset lighting scene map based on the current environment image to obtain the target lighting scene map; rendering the vehicle model according to the target material map and the target lighting scene map. In this scheme, by dynamically determining the target material map that matches the current weather scene, the material rendered by the vehicle model can meet the effect of the current weather scene; balancing the brightness and chromaticity of the preset lighting scene map based on the current environment image, and using the current environment image as the preset lighting scene map of the vehicle model to provide a lighting effect, so that the preset lighting scene map after the balance adjustment can show a realistic lighting effect under the light conditions of the current environment image, so that the light perception of the rendered vehicle model is consistent with the current environment image, presenting a softer and more realistic visual experience. Therefore, this solution renders the vehicle model from three aspects: material, brightness, and chromaticity of light according to the current weather scene and the current environmental image, reducing the sense of separation between the vehicle model rendering and the driving environment, allowing the vehicle model to appear to be integrated with the driving environment and enhancing the user's sense of immersion.

[0057] In order to better understand the solution, the rendering method of the vehicle model provided in the embodiment of the present disclosure is described in detail below.

[0058] Reference Figure 2 In this embodiment, a method for determining a target material map that matches the current weather scene is provided, including the following contents.

[0059] Obtain the original material map of the vehicle model under the preset weather scene; compare whether the current weather scene is consistent with the preset weather scene; if they are consistent, determine the original material map as the target material map that matches the current weather scene; if they are inconsistent, determine the target material map that matches the current weather scene based on the preset matching relationship between the weather scene and the material map.

[0060] In this embodiment, multiple weather scenes can be determined, and material maps can be configured for each weather scene. The unrendered vehicle model and the material maps matching each weather scene are added to the default material library. Exemplarily, three weather scenes, namely default, rainy day and snowy day, are set respectively, and material maps are made for the above weather scenes respectively to present the visual effects of the materials in the weather scenes. Among them, considering the safety of panoramic image surround stitching for user-assisted guided driving, this embodiment only adds material maps with different weather effects to the surface of the vehicle model.

[0061] In order to complete the real-time switching of material maps, this embodiment provides a set of Figure 2The material hot-switching system shown. When the program for vehicle model rendering performs a cold start, it loads the default vehicle model and the original material map vehicle model under the preset weather scenario to meet the cold start time requirement of the program. Since the cold start time of the in-vehicle computer is relatively slow, the AVM panoramic image needs to quickly generate an image to meet the user's parking guidance requirement.

[0062] Subsequently, after the cold start of the in-vehicle computer is completed, the program obtains the current weather scenario from the in-vehicle computer through the CAN bus. If it is recognized that the weather scenario has changed, that is, the current weather scenario is inconsistent with the preset weather scenario, a material switching thread is started. According to the matching relationship between the weather scenario and the material map, the target material map corresponding to the current weather scenario is loaded from the special effect material library, and the target material map is added to the rendering task.

[0063] Of course, if the weather scenario has not changed, the original material map can be determined as the target material map.

[0064] After the target material map is loaded, the main thread is notified to hot-switch to the target material map corresponding to the current weather scenario without affecting the normal rendering and image generation of the main thread.

[0065] In the above embodiments, by obtaining the current weather scenario, the matching target material map is dynamically determined, enabling the vehicle model to dynamically change according to the real-time weather, presenting a visual effect that blends into the environment, making the vehicle model more realistically integrated into the current driving environment of the vehicle, and enhancing the user's immersion experience.

[0066] During actual driving, in the face of climate changes such as overcast, sunny, rainy, and snowy, time changes such as sunrise and sunset, and brightness changes such as indoor and outdoor, all of these will cause significant changes in the environment around the vehicle model. In addition, in an open and sunny scene during the day, due to the relatively bright environmental image (such as the panoramic stitching image in the AVM scene), in contrast, the lighting performance on the surface of the vehicle model (such as the car paint) is generally dark, not only presenting a visual effect contrary to the actual surface performance, resulting in a sense of unreality, but also reducing the user's perception accuracy of the details of the vehicle model components and weakening the guiding role of the self-vehicle model.

[0067] In a night driving scenario or a driving scenario with low brightness in the basement, the brightness of the surrounding environmental map is generally insufficient. In contrast, the surface brightness of the vehicle model is generally very bright, resulting in an unrealistic rendering feeling, and at the same time weakening the driver's observation of the dark details of the environmental image and the auxiliary parking guidance role of the AVM.

[0068] In addition, the subjective perception of a fixed color by the human eye usually changes with the change of the environmental chromaticity. When a vehicle model with a cold chromaticity is in a driving scenario with a warm chromaticity light, the vehicle model will appear not well integrated with the environment, giving the user a relatively rigid rendering effect and reducing the user's visual experience.

[0069] In view of the above problems, this embodiment can adjust the brightness and chromaticity balance of the preset lighting scene map based on the current environment image to obtain the target lighting scene map. In this embodiment, the current environment image may include multiple images from different perspectives, such as fisheye images of multiple cameras in an AVM scene. In this case, the step may include:

[0070] Step S210, performing brightness and chromaticity balance adjustment on the multiple current environment images to obtain multiple target environment images.

[0071] Step S220, adjusting the brightness and chromaticity balance of the preset lighting scene map based on the multiple target environment images to obtain the target lighting scene map.

[0072] In the following embodiments, steps S210 and S220 are described separately.

[0073] With respect to the above step S210, the brightness and chromaticity balance of the multiple current environment images is adjusted to obtain multiple target environment images. This embodiment can be implemented through the following steps S211-S215.

[0074] Step S211 , stitching a plurality of current environment images, and determining a sampling area in each current environment image based on the stitching result.

[0075] In this embodiment, multiple current environment images can be stitched into a panoramic image through perspective projection of the internal and external parameters of the camera and in accordance with a preset stitching arrangement method; the stitching arrangement method, such as from left to right, from top to bottom, or first left to right and then up and down, is not limited here and can be flexibly set according to the actual display screen size and display requirements.

[0076] A single image of the current environment can be referenced Figure 3 For example, when determining the sampling area in the current environment image, in order to avoid unnecessary calculations and reduce the amount of calculations, the present embodiment can limit the sampling area. First, determine the valid environment image in each current environment image. Specifically, for each current environment image, sample the valid cropping area of ​​the current environment image to ensure that the sampled image content is as consistent as possible with the content of the surround stitching image. The valid cropping area refers to the pixel area that can be projected into the panoramic stitching image after the internal and external parameters are converted during the panoramic stitching process. The partial image in the current environment image that contains the valid cropping area is determined as the valid environment image.

[0077] Then, based on the stitching result, the two side areas of each valid environment image are determined as sampling areas.

[0078] Based on the stitching result, there is a stitching and fusion area between adjacent valid environmental images in the panoramic image. As an example, the stitching result includes multiple valid environmental images arranged in a left-to-right stitching pattern; among them, there is a stitching and fusion area between the left sampling area of the valid environmental image Pi and the right sampling area of the valid environmental image Pi-1 arranged on its left; there is a stitching and fusion area between the right sampling area of the valid environmental image Pi and the left sampling area of the valid environmental image Pi+1 arranged on its right.

[0079] Combined with Figure 4 , the valid environmental image of the front view and the valid environmental image of the rear view are adjacent to each other. Both of the above two valid environmental images include a left sampling area and a right sampling area. Moreover, the right sampling area of the valid environmental image of the front view and the left sampling area of the valid environmental image of the rear view are the stitching and fusion area.

[0080] Since multiple cameras are installed around the vehicle body and there are significant differences in their poses, there may be a step change in the brightness between valid environmental images. In this case, each colored fragment in the stitching and fusion area corresponds to different sampling areas of two adjacent valid environmental images. Therefore, during the brightness and chromaticity balance process, the pixel points of the two valid environmental images corresponding to the same colored fragment usually have different brightness and chromaticity.

[0081] To achieve a smooth and gentle transition effect and optimize the stitching effect of multiple valid environmental images, this embodiment can continue to execute the following steps S212 - S215 to perform brightness and chromaticity balance adjustment on multiple valid environmental images, so that the multiple target environmental images and the panoramic image stitched therefrom look uniform in brightness and chromaticity. Subsequently, the lighting scene of the vehicle model is adjusted according to the brightness and chromaticity of the adjusted target environmental images.

[0082] Step S212, in the YUV color space, each color channel is taken as the current color channel one by one.

[0083] Among them, YUV is a color encoding method that divides the image information into two parts: brightness (Y) and chromaticity (U and V), separating the brightness information from the chromaticity information, so that the processing of brightness and chromaticity can be carried out independently.

[0084] This embodiment can take the Y color channel, the U color channel, and the V color channel as the current color channel one by one, and execute the following steps S213 - S215 in the current color channel.

[0085] Step S213, calculate the first pixel mean value of each sampling area in the current color channel respectively.

[0086] For any valid environmental image, calculate the first pixel mean of each sampling region in the current color channel respectively. To reduce computing power consumption, in this embodiment, an interval sampling method can be used to collect the pixel values of the pixel points in the sampling region, and then calculate the mean of these pixel values to obtain the first pixel mean of the sampling region.

[0087] Assume that the current color channel is the Y color channel, and the first pixel mean can be recorded as Y ij , which can specifically represent the brightness mean of the sampling region marked as j (j can represent the left or right) in the i-th valid environmental image. Similarly, the first pixel mean U of the U color channel ij , represents the mean of the chrominance blue difference of the sampling region marked as j in the i-th valid environmental image; the first pixel mean V of the V color channel ij , represents the mean of the chrominance red difference of the sampling region marked as j in the i-th valid environmental image.

[0088] In two adjacent valid environmental images, the first pixel means of the two sampling regions corresponding to the same splicing and fusion region are usually different, that is, the brightness and chrominance are different. Furthermore, based on the first pixel means of each sampling region and the subsequent steps, brightness and chrominance balance adjustment is performed on the valid environmental image.

[0089] Step S214, based on the first pixel means of each sampling region, determine image adjustment coefficients corresponding to each sampling region one by one.

[0090] In one embodiment, the implementation process of this step S214 can be referred to as follows.

[0091] For two adjacent current environmental images at any perspective, take the sampling region corresponding to the smaller first pixel mean as the first sampling region, and take the sampling region corresponding to the larger first pixel mean as the second sampling region.

[0092] Specific examples are as Figure 4 shown. Among the two sampling regions corresponding to the same splicing and fusion region, the sampling region corresponding to the smaller first pixel mean is taken as the first sampling region, and the sampling region corresponding to the larger first pixel mean is taken as the second sampling region. Here, it is assumed that the first pixel mean of the right sampling region in the front view is smaller and is used as the first sampling region; the first pixel mean of the left sampling region in the right view is larger and is used as the second sampling region.

[0093] Determine a first adjustment value for the first sampling area based on the sum of the first pixel mean of the first sampling area and the target difference; wherein, the target difference is half of the difference between the first pixel mean of the first sampling area and the first pixel mean of the second sampling area.

[0094] Specifically, taking the Y color channel as an example, the following formula (1) can be referred to, and the pixel mean of the smaller first sampling area can be adjusted upwards to approach the larger second sampling area:

[0095] Y dst1 =(Y 2 -Y 1 ) / 2 + Y 1 (1)

[0096] Wherein, Y dst1 represents the first adjustment value of the first sampling area, Y 2 represents the first pixel mean of the second sampling area, Y 1 represents the first pixel mean of the first sampling area, and (Y 2 -Y 1 ) / 2 is the target difference.

[0097] Similarly, determine a second adjustment value for the second sampling area based on the difference between the first pixel mean Y 2 of the second sampling area and the target difference; specifically, refer to the following formula (2) and adjust the pixel mean of the larger second sampling area downwards to approach the smaller first sampling area:

[0098] Y dst2 =(Y 2 -(Y 2 -Y 1 ) / 2)(2)

[0099] Wherein, Y dst2 represents the first adjustment value of the second sampling area.

[0100] According to the above formulas (1) and (2), on the brightness represented by the Y color channel, adjust the two sampling areas with a large difference in the first pixel mean to the first adjustment value and the second adjustment value that are close to each other, so as to achieve a certain degree of brightness balance adjustment.

[0101] Determine the ratio between the first adjustment value Y dst1 and the first pixel mean Y 1 of the first sampling area as the first image adjustment coefficient R 1 corresponding to the first sampling area; specifically, it is the following formula (3):

[0102] R 1 =Y dst1 / Y 1 (3)

[0103] The first image adjustment coefficient R 1 For further balancing the brightness of the current environmental image of the front view angle to which the first adopted area belongs.

[0104] Take the ratio between the second adjustment value Y dst2 and the first pixel average value Y of the second sampling area 2 as the second image adjustment coefficient R corresponding to the second sampling area 2 ; specifically, it is the following formula (4):

[0105] R 2 = Y dst2 / Y 2 (4)

[0106] The second image adjustment coefficient R 2 For further balancing the brightness of the current environmental image of the right view angle to which the second adopted area belongs.

[0107] In addition, it should be noted that the above embodiments only describe the process of determining the image adjustment coefficient of the sampling area by taking the Y color channel as an example. For the U color channel and the V color channel, the same embodiments will be used to determine the image adjustment coefficient of the sampling area, and no detailed description will be given here.

[0108] Step S215, according to the image adjustment coefficients corresponding to each sampling area, perform brightness and chromaticity balance adjustment on the current environmental images to which each sampling area belongs, and obtain multiple target environmental images.

[0109] In order to achieve a better transition during image stitching, or rather, in order to better balance the brightness and chromaticity of multiple current environmental images, an embodiment can be provided as follows to implement this step S215.

[0110] According to the stitching direction of multiple current environmental images, divide the current current environmental image into multiple sub-areas. Taking left-right stitching as an example, each current environmental image can be equally spaced from left to right into n (such as n = 32) sub-areas.

[0111] Interpolate the image adjustment coefficients corresponding to the current current environmental image to obtain multiple interpolation adjustment coefficients; among them, the number of interpolation adjustment coefficients is equal to the number of sub-areas. Specifically, through the foregoing embodiments, the image adjustment coefficients of the two sampling areas on the left and right sides of each current environmental image are determined. Then, linearly interpolate the image adjustment coefficients of the two sampling areas on the left and right sides to obtain n interpolation adjustment coefficients.

[0112] Next, based on multiple interpolation adjustment coefficients, perform brightness and chroma balance adjustment on multiple sub-regions to obtain a target environmental image corresponding to the current environmental image.

[0113] In this embodiment, by using n interpolation adjustment coefficients to perform brightness and hue balance adjustment on n sub-regions, the accuracy of the balance adjustment can be improved, and the obtained target environmental image gradually develops from the brightness and hue on the left to the brightness and hue on the right, achieving a better transition.

[0114] According to the above embodiments, by performing brightness and chroma balance adjustment on multiple current environmental images, multiple target environmental images with soft brightness and chroma transitions can be obtained. After that, in order to quantify the adjustment amount of the lighting scene of the vehicle model, the preset lighting scene map can be adjusted for brightness and chroma based on multiple target environmental images to obtain a target lighting scene map. This embodiment may include the following content.

[0115] Step S221, obtain the standard environmental image corresponding to the preset lighting scene map.

[0116] Since the preset lighting scene map is a map rendered under a certain environmental image and can represent the brightness and chroma effects of the lighting presented on the surface of the vehicle model under that environmental image. Therefore, in this embodiment, the standard environmental map corresponding to the preset lighting scene map can be obtained and used as the standard reference value for subsequent real-time adjustment.

[0117] Step S222, in the current color channel of the YUV color space, determine the pixel value difference between the standard environmental image and the sampling regions of each target environmental image.

[0118] In this embodiment, in the current color channel, the average pixel value of the standard environmental image can be determined, and the average pixel value of the sampling regions of each target environmental image can be determined, and then based on this, the pixel value difference between the standard environmental image and the sampling regions of each target environmental image can be determined. For example, in the Y color channel, the pixel value difference can be recorded as ΔY 标,i，j , representing the brightness difference between the standard environmental image and the sampling region j of the i-th target environmental image; similarly, it may also include: the pixel value difference ΔU in the U color channel 标,i,j , and the pixel value difference ΔV in the V color channel 标,i,j .

[0119] Step S223, in the case where at least one pixel value difference exceeds the preset pixel difference threshold, determine the model adjustment coefficient based on the preset lighting adjustment factor, the pixel value difference, and the second pixel mean value of the standard environmental image.

[0120] Among them, there is at least one pixel value difference exceeding a preset pixel difference threshold, which can be understood as that under at least one color channel, the pixel value difference between the standard environment image and at least one sampling area of at least one target environment image exceeds the preset pixel difference threshold.

[0121] That there is at least one pixel value difference exceeding the preset pixel difference threshold indicates that the lighting scene difference between the target environment image and the standard environment image used for rendering the preset lighting scene map is relatively large, and it is necessary to perform balance adjustment on the brightness and chromaticity of the preset lighting scene map so that the adjusted target lighting scene map can be more integrated with the target environment image.

[0122] In order to perform balance adjustment on the brightness and chromaticity of the preset lighting scene map, first refer to the following embodiments to determine the model adjustment coefficient based on the preset lighting adjustment factor, pixel value difference, and the second pixel mean value of the standard environment image, including:

[0123] For each target environment image and its corresponding pixel difference, determine a third adjustment value according to the pixel value difference and the second pixel mean value of the standard environment image.

[0124] Specifically, taking any target environment image as an example, if the second pixel mean value of the standard environment image is less than the pixel mean value of this target environment image, then refer to the method of determining the first adjustment value in the foregoing embodiments, and adjust the second pixel mean value of the standard environment image up to the third adjustment value to be closer to this target environment image with a larger pixel value. On the contrary, if the second pixel mean value of the standard environment image is greater than the pixel mean value of this target environment image, then refer to the method of determining the second adjustment value in the foregoing embodiments, and adjust the second pixel mean value of the standard environment image down to the third adjustment value to be closer to this target environment image with a smaller pixel value.

[0125] Adjust the third adjustment value to a fourth adjustment value according to the preset adjustment factor; specifically, for example, the product of the adjustment factor and the adjusted third adjustment value is the fourth adjustment value. In addition, it can be understood that for the Y color channel, the above adjustment factor is the brightness adjustment factor; for the U color channel, the above adjustment factor is the chromaticity blue difference adjustment factor; for the V color channel, the above adjustment factor is the chromaticity red difference adjustment factor.

[0126] Determine the ratio between the fourth adjustment value and the second pixel mean value as the model adjustment coefficient. This step can refer to formula (3) or formula (4) in the foregoing embodiments.

[0127] According to the above embodiments, each sampling region of each target environment image can correspond to a model adjustment coefficient. Specifically, for the target environment image spliced in the middle position, there can be two model adjustment coefficients, namely, the left and right ones. Multiple model adjustment coefficients are jointly used to balance the brightness and chromaticity of the preset lighting scene map.

[0128] Step S224: Based on the model adjustment coefficient, perform balance adjustment on the brightness and chromaticity of the preset lighting scene map to obtain the target lighting scene map.

[0129] In one embodiment, it may include: determining first lighting scene images corresponding to each target environment image on the preset lighting scene map; adjusting the brightness and chromaticity of each first lighting scene image according to the model adjustment coefficient corresponding to each target environment image to obtain multiple second lighting scene images; and splicing the multiple second lighting scene images into the target lighting scene map.

[0130] In a possible actual scenario, an HDR lighting scene is adopted. Correspondingly, the preset lighting scene map can be an HDR equirectangular projection map projected from a sphere.

[0131] During the rendering process, the HDR equirectangular projection map is usually converted into a cube map to reduce the sampling computing power consumption of the fragment shader. Therefore, in this embodiment, the lighting scene will be adjusted in the YUV color space directly on the HDR equirectangular projection map.

[0132] Specifically, determine the first lighting scene image corresponding to each target environment image in the HDR equirectangular projection map. Then, apply the model adjustment coefficient corresponding to each target environment image calculated in the foregoing embodiment to the HDR equirectangular projection map.

[0133] In Figure 5 , the left, front, right, and back above represent multiple target environment images under different perspectives. At the same time, their arrangement order also represents the splicing method of the multiple target environment images. Figure 5 The left, front, right, and back below represent the first lighting scene images corresponding to each target environment image on the preset lighting scene map.

[0134] In this embodiment, the target environment image P 左 from the left perspective and its corresponding first lighting scene image Q 左 are taken as examples for illustration. In order to make the lighting transition smooth and soft, similar to the embodiment of step S215, in this embodiment, the first lighting scene image Q 左 is divided into multiple lighting sub-regions, and the target environment image P 左Perform linear interpolation on the corresponding two model adjustment coefficients to obtain multiple interpolated model adjustment coefficients; balance the brightness and chromaticity of multiple illumination sub-regions according to the multiple interpolated model adjustment coefficients to obtain the first illumination scene image Q 左 The corresponding second illumination scene image Q 左 '.

[0135] In the same way, obtain multiple second illumination scene images, and splice the multiple second illumination scene images into a target illumination scene image.

[0136] In the above embodiment, by using the current environment image as the benchmark for illumination balance adjustment, the brightness and chromaticity of the preset illumination scene map are balanced accordingly, so that the adjusted target illumination scene map can adaptively change with the environmental brightness and color temperature. Through the above brightness and chromaticity balance adjustment process, this embodiment discretely samples pixel information from the current environment images of multiple cameras of the vehicle, statistically analyzes the pixel values representing brightness and chromaticity of each camera, and optimizes and balances the input multiple current environment images to improve the visual effect of panoramic image stitching. Subsequently, the illumination scene of the preset illumination scene map is adjusted according to the balanced multiple target environment images, and the vehicle model is rendered using the adjusted target illumination scene image, so that the brightness and chromaticity of the illumination presented on the surface of the vehicle model are consistent with the driving environment, improving the integration degree, reducing the sense of disconnection between the vehicle model and the driving environment, and making the light perception of the 3 vehicle model present a softer and more realistic visual experience. And for driving scenarios such as indoor basements and nights, by balancing and adjusting the brightness of the vehicle model, the user's perception effect of the dark details of the panoramic stitching image can be improved, enhancing driving safety.

[0137] Refer to Figure 6 , in another embodiment, for the above step S106, based on the current environment image, performing brightness and chromaticity balance adjustment on the preset illumination scene map to obtain a target illumination scene map may further include:

[0138] In the main thread, perform brightness and chromaticity balance adjustment on multiple current environment images to obtain multiple target environment images; in the sub-thread, asynchronously perform brightness and chromaticity balance adjustment on the preset illumination scene map based on the multiple target environment images to obtain a target illumination scene map; wherein, the execution priority of the main thread is higher than that of the sub-thread.

[0139] According to the foregoing embodiments, the image-based illumination algorithm can simulate an infinite number of light sources and any type of light source, and at the same time can simulate any type of light source. However, for image-based illumination, it requires a pre-computation process with huge computing power consumption, which poses a huge challenge to the real-time performance of the embedded board development platform.

[0140] To solve this problem, this embodiment can provide a real-time running light switching system applied to an embedded board. This system separates the AVM rendering task from the light adaptive adjustment task in terms of architecture. For tasks that must be rendered stably in real time for each frame, this embodiment places them in the main thread and, based on a relatively high execution priority, ensures the stable rendering of AVM. In the main thread, the task of performing brightness and chromaticity balance adjustment on multiple current environment images to obtain multiple target environment images mainly includes: performing brightness and hue balance adjustment on multiple current environment images, and stitching the target environment images. The specific implementation process has been described in detail in the foregoing embodiments and will not be elaborated here.

[0141] The calculation and balance adjustment task of the preset light scene map, since it is not updated for each frame, and the condition for triggering the update is that in the driving scene, the brightness and chromaticity change between the target environment image and the standard environment image exceeds the pixel difference threshold. Therefore, the task of adjusting the brightness and chromaticity of the preset light scene map is calculated and processed by this embodiment in a child thread. The execution priority of the child thread is set lower than that of the main thread to ensure that the processing of the preset light scene map does not interfere with the AVM rendering task. In the child thread, the task of asynchronously performing brightness and chromaticity balance adjustment on the preset light scene map based on multiple target environment images to obtain the target light scene map mainly includes: performing brightness and chromaticity balance adjustment on the preset light scene map when the pixel value difference between the standard environment image and each target environment image exceeds the pixel difference threshold.

[0142] During the process of performing brightness and chromaticity balance adjustment on the preset light scene map, it is necessary to calculate the pre-convolution irradiance map, pre-filtered environment map, and BRDF integral map corresponding to the preset light scene map. Since the BRDF integral map assumes that the incident light is all white light L(p,x)=0 and describes the Fresnel response coefficient (R channel) and deviation value (G channel), the BRDF integral map does not need to be updated in real time. Therefore, only the pre-convolution irradiance map and the pre-filtered environment map are updated, but it is impossible to update them in real time for each frame. Therefore, this embodiment designs an asynchronous calculation method to perform brightness and chromaticity balance adjustment on an asynchronous thread, and the main thread performs real-time rendering of AVM-related tasks.

[0143] When the main thread recognizes that the accumulated pixel value difference between the standard environment image and each target environment image exceeds the pixel difference threshold, it notifies the child thread to perform brightness and chromaticity balance adjustment and generate the corresponding target light scene map. After the child thread generates the target light scene map, it notifies the main thread to perform map switching, and the main thread uses the target light scene map to render the vehicle model. The above method can achieve real-time switching to the target light scene map without blocking the main thread rendering.

[0144] Figure 7 This is a schematic structural diagram of a rendering device for a vehicle model provided by an embodiment of the present disclosure. This device is used to implement the above-mentioned vehicle model rendering method. The device includes the following modules.

[0145] An acquisition module 310, configured to acquire a vehicle model to be rendered, a current weather scene, and a current environmental image;

[0146] A material determination module 320, configured to determine a target material texture map that matches the current weather scene;

[0147] A lighting adjustment module 330, configured to perform balance adjustment of brightness and chromaticity on a preset lighting scene texture map based on the current environmental image to obtain a target lighting scene texture map;

[0148] A model rendering module 340, configured to render the vehicle model according to the target material texture map and the target lighting scene texture map.

[0149] For the device provided in this embodiment, the implementation principle and the technical effects produced are the same as those of the foregoing method embodiment. For a brief description, for the parts not mentioned in the device embodiment, reference may be made to the corresponding content in the foregoing method embodiment.

[0150] Figure 8 This is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 8 shown, the electronic device 400 includes one or more processors 401 and a memory 402.

[0151] The processor 401 may be a central processing unit (CPU) or other form of processing unit having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 400 to perform desired functions.

[0152] The memory 402 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 401 may run the program instructions to implement the vehicle model rendering method of the embodiment of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0153] In one example, the electronic device 400 may further include: an input device 403 and an output device 404, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0154] In addition, the input device 403 may further include, for example, a keyboard, a mouse, and the like.

[0155] The output device 404 may output various information to the outside, including the determined distance information, direction information, etc. The output device 404 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, and the like.

[0156] Of course, for simplicity, Figure 8 only some of the components related to the present disclosure in the electronic device 400 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application scenarios, the electronic device 400 may further include any other appropriate components.

[0157] Furthermore, this embodiment also provides a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is used to execute the above-mentioned rendering method of the vehicle model.

[0158] A computer program product of a rendering method, device, electronic device, and medium of a vehicle model provided by an embodiment of the present disclosure includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the method described in the foregoing method embodiments. For specific implementation, reference can be made to the method embodiments, and details are not described herein again.

[0159] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0160] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for rendering a vehicle model, characterized in that: include: Obtain the vehicle model to be rendered, the current weather scene and the current environment image; Determining a target material map that matches the current weather scene; Based on the current environment image, a preset lighting scene map is adjusted for balance in brightness and chroma to obtain a target lighting scene map; The vehicle model is rendered according to the target material map and the target lighting scene map.

2. The method according to claim 1, characterized in that: The determining of a target material map matching the current weather scene comprises: Obtaining the original material map of the vehicle model under a preset weather scenario; Comparing whether the current weather scene is consistent with the preset weather scene; If they are consistent, determining the original material map as the target material map that matches the current weather scene; If they are inconsistent, the target material map that matches the current weather scene is determined based on a preset matching relationship between the weather scene and the material map.

3. The method according to claim 1, characterized in that The current environment image includes multiple images at different viewing angles; the brightness and chromaticity balance adjustment of the preset lighting scene map based on the current environment image to obtain the target lighting scene map includes: Performing brightness and chromaticity balance adjustment on the multiple current environment images to obtain multiple target environment images; Based on the multiple target environment images, the preset lighting scene map is balanced by adjusting the brightness and chromaticity to obtain the target lighting scene map.

4. The method according to claim 3, characterized in that The step of performing brightness and chromaticity balance adjustment on the multiple current environment images to obtain multiple target environment images includes: splicing a plurality of the current environment images, and determining a sampling area in each of the current environment images based on the splicing result; In the YUV color space, each color channel is used as the current color channel one by one; Calculate the first pixel mean of each sampling area in the current color channel respectively; Determining image adjustment coefficients corresponding to each of the sampling areas based on the first pixel mean value of each of the sampling areas; According to the image adjustment coefficient corresponding to each sampling area, the current environment image to which each sampling area belongs is adjusted for balance of brightness and chromaticity to obtain a plurality of target environment images.

5. The method according to claim 4, characterized in that The step of determining the image adjustment coefficient corresponding to each sampling area based on the first pixel mean value of each sampling area comprises: For two current environment images adjacent to each other at any viewing angle, the sampling area corresponding to the smaller first pixel mean value is used as the first sampling area, and the sampling area corresponding to the larger first pixel mean value is used as the second sampling area; Determine a first adjustment value of the first sampling area based on a sum of a first pixel mean value of the first sampling area and a target difference value; wherein the target difference value is half of a difference between a first pixel mean value of the first sampling area and a first pixel mean value of the second sampling area; determining a second adjustment value of the second sampling area based on a difference between the first pixel mean value of the second sampling area and the target difference value; determining a ratio between the first adjustment value and a first pixel average of the first sampling area as a first image adjustment coefficient corresponding to the first sampling area; A ratio between the second adjustment value and the first pixel average of the second sampling area is determined as a second image adjustment coefficient corresponding to the second sampling area.

6. The method according to claim 4, characterized in that According to the image adjustment coefficient corresponding to each sampling area, the current environment image to which each sampling area belongs is adjusted for brightness and chromaticity balance to obtain multiple target environment images, including: Dividing the current environment image into a plurality of sub-areas according to the splicing direction of the plurality of current environment images; Interpolating the image adjustment coefficient corresponding to the current environment image to obtain a plurality of interpolation adjustment coefficients; wherein the number of the interpolation adjustment coefficients is equal to the number of the sub-regions; The brightness and chromaticity balance of the multiple sub-areas is adjusted according to the multiple interpolation adjustment coefficients to obtain a target environment image corresponding to the current environment image.

7. The method according to claim 4, characterized in that The determining of the sampling area in each of the current environment images based on the stitching result includes: Determining a valid environment image among the current environment images; Based on the stitching result, the two side areas of each of the effective environment images are determined as sampling areas.

8. The method according to claim 3, characterized in that The method of performing a balance adjustment on brightness and chromaticity of a preset lighting scene map based on a plurality of target environment images to obtain a target lighting scene map comprises: Obtain the standard environment image corresponding to the preset lighting scene map; Determining, in a current color channel of a YUV color space, a pixel value difference between a sampling area of ​​the standard environment image and a sampling area of ​​each of the target environment images; In a case where at least one of the pixel value differences exceeds a preset pixel difference threshold, determining a model adjustment coefficient based on a preset illumination adjustment factor, the pixel value difference and a second pixel mean of the standard environment image; The preset lighting scene map is adjusted for balance of brightness and chromaticity based on the model adjustment coefficient to obtain a target lighting scene map.

9. The method according to claim 8, characterized in that The determining of the model adjustment coefficient based on the preset illumination adjustment factor, the pixel value difference and the second pixel mean of the standard environment image includes: For each of the target environment images and the corresponding pixel difference values ​​thereof, determine a third adjustment value according to the pixel value difference value and a second pixel mean value of the standard environment image; adjusting the third adjustment value to a fourth adjustment value according to a preset adjustment factor; The ratio of the fourth adjustment value to the second pixel mean is determined as a model adjustment coefficient.

10. The method according to claim 8, characterized in that The step of performing a balance adjustment on the brightness and chromaticity of the preset lighting scene map based on the model adjustment coefficient to obtain a target lighting scene map includes: Determining first illumination scene images respectively corresponding to each of the target environment images on the preset illumination scene map; Adjusting the brightness and chromaticity of each of the first illumination scene images according to the model adjustment coefficient corresponding to each of the target environment images to obtain a plurality of second illumination scene images; The plurality of the second lighting scene images are stitched together into a target lighting scene map.

11. The method according to claim 1 or 3, characterized in that: The step of adjusting the brightness and chromaticity balance of a preset lighting scene map based on the current environment image to obtain a target lighting scene map includes: In the main thread, a balance adjustment of brightness and chromaticity is performed on the multiple current environment images to obtain multiple target environment images; In the child thread, asynchronously executing the balance adjustment of brightness and chromaticity of the preset lighting scene map based on the multiple target environment images to obtain the target lighting scene map; Among them, the execution priority of the main thread is higher than the execution priority of the sub-thread.

Images