Cabin wallpaper generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a cabin wallpaper generation method and device, electronic equipment and a storage medium. The method comprises the steps that an initial image collected by image collection equipment of a target vehicle for the environment where the target vehicle is located is acquired; determining azimuth information and attribute information of a target moving object based on the initial image; generating a target cue word corresponding to a target map generation model according to the azimuth information and the attribute information, wherein the target map generation model is used for generating cabin wallpaper of a preset style based on the cue word and an image; and inputting the target prompt word and the initial image into the target map generation model, and outputting a cabin wallpaper image of the target vehicle. Through the embodiment of the invention, the intelligent and more flexible personalized wallpaper is generated by analyzing the moving object and combining the graph-to-graph model.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle intelligent cockpits, and in particular to a method and device for generating cockpit wallpaper, electronic equipment, and a storage medium. Background Art

[0002] Currently, wallpapers can be set on the vehicle's cabin computer according to user needs. However, the wallpapers on the cabin computer are usually pictures pre-stored by the user on the computer, so the number of wallpapers is limited, and the displayed wallpapers are single and fixed, lacking novelty and appeal. Summary of the invention

[0003] In view of the above problems, a method and device for generating a cockpit wallpaper, an electronic device, and a storage medium are proposed to overcome the above problems or at least partially solve the above problems, including:

[0004] A method for generating a cockpit wallpaper, the method comprising:

[0005] Acquire an initial image captured by an image acquisition device of a target vehicle with respect to an environment in which the target vehicle is located;

[0006] Determine the orientation information and attribute information of the target moving object based on the initial image;

[0007] Generate a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image;

[0008] The target prompt word and the initial image are input into the target image generation model, and a cockpit wallpaper image of the target vehicle is output.

[0009] Optionally, determining the position information and attribute information of the target moving object based on the initial image includes:

[0010] Inputting the initial image into a moving object detection model for detecting moving objects, and outputting target frame information of the target moving object;

[0011] Inputting the target frame information into an attribute recognition model for extracting attribute information of a moving object, and outputting the attribute information of the target moving object;

[0012] Input the target frame information into a depth estimation model for estimating the depth information of a moving object, and output the depth information from the center point of the target frame of the target moving object to the center point of the viewing angle of the image acquisition device;

[0013] The orientation information of the target moving object is determined according to the target frame information and the depth information.

[0014] Optionally, determining the orientation information of the target moving object according to the target frame information and the depth information includes:

[0015] Determining whether the depth information is less than a preset depth threshold;

[0016] When it is determined that the depth information is less than the preset depth threshold, determining a first vector from the center point of the viewing angle of the image acquisition device to the center point of the target frame information, and determining a second vector from the center point of the viewing angle of the image acquisition device to the coordinates of the lower right corner of the initial image;

[0017] determining a target angle between the first vector and the second vector;

[0018] The orientation information of the target moving object is determined based on the target angle.

[0019] Optionally, generating a target prompt word corresponding to the target image model according to the orientation information and the attribute information includes:

[0020] Performing data preprocessing on the orientation information and the attribute information to obtain structured information corresponding to the target graph model;

[0021] Extracting multiple key feature information from the structured information;

[0022] Integrate the multiple key features to obtain integrated feature information;

[0023] Performing expansion processing on the integrated feature information to obtain target feature information;

[0024] Generate target prompt words corresponding to the target graph model based on target feature information.

[0025] Optionally, the method further comprises:

[0026] Acquiring scene information of the environment in which the target vehicle is located;

[0027] The step of generating a target prompt word corresponding to the target image model according to the orientation information and the attribute information includes:

[0028] Generate a target prompt word corresponding to the target image model according to the orientation information, the attribute information and the scene information.

[0029] Optionally, the acquiring scene information of the environment in which the target vehicle is located includes:

[0030] Obtaining real-time location information of the target vehicle;

[0031] The scene information of the environment in which the target vehicle is located is determined based on the real-time position information.

[0032] Optionally, the initial image acquired by the image acquisition device of the target vehicle for the environment in which the target vehicle is located includes:

[0033] When a preset gesture of a target user in the target vehicle is detected, a wallpaper generation function is activated;

[0034] When the wallpaper generation function is turned on, an initial image captured by an image capture device of a target vehicle with respect to the environment in which the target vehicle is located is obtained.

[0035] Optionally, the method further comprises:

[0036] The cockpit wallpaper image is displayed on a cockpit computer and / or a ceiling screen of the target vehicle.

[0037] A device for generating cockpit wallpaper, the device comprising:

[0038] An initial image acquisition module, used to acquire an initial image acquired by an image acquisition device of a target vehicle with respect to an environment where the target vehicle is located;

[0039] An information extraction module, used to determine the position information and attribute information of the target moving object based on the initial image;

[0040] A prompt word generation module, used to generate a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image;

[0041] The cockpit wallpaper generation module is used to input the target prompt word and the initial image into the target image generation model, and output the cockpit wallpaper image of the target vehicle.

[0042] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method for generating a cockpit wallpaper as described above when executed by the processor.

[0043] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a cockpit wallpaper as described above is implemented.

[0044] The embodiments of the present invention have the following advantages:

[0045] In an embodiment of the present invention, by acquiring an initial image captured by an image acquisition device of a target vehicle for the environment in which the target vehicle is located, the orientation information and attribute information of the target moving object can be determined based on the initial image, thereby generating a target prompt word corresponding to a target graph-generated image model according to the orientation information and the attribute information, and further inputting the target prompt word and the initial image into the target graph-generated image model, thereby outputting a cockpit wallpaper image of the target vehicle, thereby realizing the generation of intelligent and more flexible personalized wallpapers by analyzing the moving object and combining the graph-generated image model. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0047] Figure 1a It is a schematic diagram of a wallpaper generation process in the prior art;

[0048] Figure 1b is a flowchart of a method for generating a cockpit wallpaper provided by an embodiment of the present invention;

[0049] Figure 2 is a flowchart of another method for generating a cockpit wallpaper provided by an embodiment of the present invention;

[0050] Figure 3a This is a schematic diagram of a cockpit wallpaper generation process provided by an embodiment of the present invention.

[0051] Figure 3b is an initial image captured by an ADAS camera provided by an embodiment of the present invention;

[0052] Figure 3c A comic style wallpaper image generated based on a wallpaper generation function provided by an embodiment of the present invention;

[0053] Figure 4 It is a structural schematic diagram of a device for generating a cockpit wallpaper provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] At present, the wallpapers displayed on the cockpit computers of mainstream car manufacturers are generally stored in advance by users on the computer. Although the method of switching wallpapers using the wallpapers stored in the computer can provide a fast and stable user experience, its inherent disadvantages cannot be ignored. The number and types of predefined wallpapers in the current wallpaper settings are limited, which makes it difficult to meet the increasingly diverse and personalized needs of users. As users' requirements for the aesthetics and personalization of the in-car environment increase, single and fixed wallpaper options appear too limited and lack novelty and appeal. In addition, although predefined wallpapers can be switched quickly, this also means that these wallpapers lack the possibility of dynamic changes and personalized customization. Users can only choose from limited options, and the experience is relatively monotonous. In order to overcome these disadvantages, a smarter and more flexible personalized wallpaper generation method is urgently needed.

[0056] The flowchart of the traditional predefined wallpaper switching method is as follows Figure 1a The steps shown include:

[0057] (1) Upload wallpaper: Vehicle users can select one or more wallpapers according to their preferences and pre-place them on the vehicle computer.

[0058] (2) Voice input: The vehicle computer receives the voice command from the driver and the front passenger: “Help me switch the wallpaper.”

[0059] (3) Speech signal processing: Process speech signals to reduce noise and echo.

[0060] (4) Voice recognition: Recognize voice and convert it into text “Help me switch wallpaper”.

[0061] (5) Natural language processing: understand that the user’s intention is to help me change the wallpaper.

[0062] (6) Dialogue management: Confirm the current wallpaper setting status and decide whether to execute the command to switch wallpaper.

[0063] (7) Execute control command: When it is determined that the wallpaper switching command can be executed, the command “Switch wallpaper.

[0064] (8) Feedback confirmation: Confirm that the wallpaper has been successfully switched and generate feedback information.

[0065] This wallpaper setting method lacks personalized wallpaper generation services and only meets the interaction needs of the driver and front passenger. The experience of rear passengers is often ignored and they cannot enjoy the same convenience and personalized services.

[0066] In an embodiment of the present invention, an initial image captured by an image acquisition device of a target vehicle for the environment in which the target vehicle is located is obtained; the orientation information and attribute information of a target moving object are determined based on the initial image; a target prompt word corresponding to a target graph-generated image model is generated according to the orientation information and the attribute information, and the target graph-generated image model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image; the target prompt word and the initial image are input into the target graph-generated image model, and an image of the cockpit wallpaper of the target vehicle is output, thereby realizing the generation of intelligent and more flexible personalized wallpaper by analyzing the moving object in combination with the graph-generated image model.

[0067] Reference Figure 1b , shows a flowchart of a method for generating a cockpit wallpaper provided by an embodiment of the present invention, which may specifically include the following steps:

[0068] Step S101, obtaining an initial image captured by an image acquisition device of a target vehicle with respect to the environment in which the target vehicle is located;

[0069] In practical applications, the target vehicle may be equipped with an image acquisition device, which may be used to acquire initial images inside and outside the vehicle to assist the vehicle in driving better. The image acquisition device may be a camera. Specifically, the image acquisition device in the embodiment of the present invention may be an ADAS (Advanced Driver Assistance Systems) camera. In the embodiment of the present invention, the real-time environment image of the target vehicle is acquired by calling the ADAS camera to capture the scene in front, and then the wallpaper effect associated with the actual driving environment may be generated based on the image.

[0070] In one embodiment of the present invention, a wallpaper generation function may be set, and the user may enable the wallpaper generation function in a variety of different preset activation methods. After enabling the wallpaper generation function, step S101 is executed to obtain an initial image, and then a wallpaper image is generated based on the initial image.

[0071] In one example, when a preset gesture of a target user in a target vehicle is detected, the wallpaper generation function is turned on, so that when the wallpaper generation function is turned on, an initial image of the environment in which the target vehicle is located is acquired by the image acquisition device of the target vehicle. The preset gesture can be set according to the actual scene, and in the embodiment of the present invention, there is no excessive restriction on this. For example, the preset gesture is a dynamic gesture for clicking a function button generated by the cockpit wallpaper.

[0072] Specifically, the image acquisition device may be used to acquire the user image corresponding to the target user, and then the user image may be analyzed and processed to determine whether the preset gesture of the target user is detected in the user image. If the preset gesture of the target user is detected in the user image, the wallpaper generation function may be enabled. If the preset gesture of the target user is not detected in the user image, the user image of the next cycle may be acquired for image analysis.

[0073] In the embodiment of the present invention, by triggering the wallpaper generation function through air gestures, the user can conveniently and dynamically generate personalized wallpapers in the cockpit without directly touching the screen.

[0074] In another example, the target vehicle may be set up for voice interaction, and then the target user may activate the wallpaper generation function through voice interaction with the target vehicle.

[0075] In another example, the central control screen of the target vehicle may be a touch screen, and the user may directly activate the wallpaper generation function by performing touch operations on the touch screen.

[0076] Step S102, determining the orientation information and attribute information of the target moving object based on the initial image;

[0077] After acquiring the initial image, the initial image can be subjected to image analysis processing to determine the orientation information and attribute information of the target moving object existing in the initial image, wherein the attribute information may include the target moving object's own attributes and the moving attributes of the target moving object, and the specific type of the attribute information can be determined according to the type of the target moving object.

[0078] Taking the target user object as a pedestrian as an example, the attributes of the pedestrian may include but are not limited to the pedestrian's gender attribute, age attribute, etc.; the movement attributes may include but are not limited to whether there is a vehicle, the type of vehicle, such as a pedestrian riding a motorcycle, a pedestrian riding a bicycle, etc.

[0079] Step S103, generating a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image;

[0080] After obtaining the position information and attribute information, a target prompt word in a preset format can be generated according to the position information and attribute information. The preset format is the format of the prompt word that can be input and used in the target graph generation model. The preset format can be determined according to the graph generation model obtained by actual training.

[0081] In an embodiment of the present invention, the input data of the target image generation model is the prompt word and the initial image, and the output data is a cockpit wallpaper of a preset style. The preset style can be set according to actual needs. For example, the preset style in the embodiment of the present invention can be a comic style.

[0082] In the target image generation model, the input prompts are prompts in a preset format. In the target image generation model, the initial image can be converted according to a preset style. During the conversion process, the prompts serve to further enhance the characteristics of the target moving object, so that when the initial image is converted according to the preset style, a target moving object of a preset style can be generated.

[0083] In one embodiment of the present invention, generating a target prompt word corresponding to the target image model according to the orientation information and the attribute information may specifically include the following sub-steps:

[0084] Sub-step S11, pre-processing the position information and attribute information to obtain structured information corresponding to the target graph model;

[0085] Position information and attribute information are key data for describing moving objects and scenes. In order to make this information effectively used by the target graph-generated model (such as convolutional neural network, graph neural network, etc.), data preprocessing is required to convert it into structured information that can be used by the target graph-generated model. Preprocessing can specifically include any one or more of data collection and alignment processing and data standardization processing.

[0086] In practical applications, the position information and attribute information can be standardized to meet the input requirements of the target graph generation model. The data standardization process can specifically include but is not limited to coordinate standardization, speed and direction standardization, and attribute standardization.

[0087] Sub-step S12, extracting multiple key feature information from the structured information;

[0088] After obtaining the structured information, key features can be selected from the structured information, such as object type, position, speed, direction, color, size, etc. Then, the selected key features are extracted from the structured information of each target moving object.

[0089] Sub-step S13, integrating multiple key features to obtain integrated feature information;

[0090] Concatenate the key features of each object into a feature vector.

[0091] Sub-step S14, performing expansion processing on the integrated feature information to obtain target feature information;

[0092] Generate a natural language description based on the integrated feature vector, and then add context information based on the scene to achieve expansion and obtain more comprehensive target feature information.

[0093] Sub-step S15, generating a target prompt word corresponding to the target graph model based on the target feature information.

[0094] Convert the natural language description into a format that the target graph model can understand, such as a structured data format or a specific prompt template, i.e., the target prompt word.

[0095] In one embodiment of the present invention, the scene information of the environment in which the target vehicle is located can be acquired in advance; and then the target prompt words corresponding to the target image model can be generated according to the orientation information, attribute information and scene information.

[0096] In practical applications, the orientation information, attribute information and scene information can be combined for preprocessing, integration and expansion to generate target prompt words corresponding to the target image model, so as to generate wallpaper that fits the current vehicle environment.

[0097] In the embodiment of the present invention, by integrating scene information and motion object analysis information (i.e., position information and attribute information), a structured input is provided to the image generation model, so that the generated wallpaper is more in line with the current scene atmosphere.

[0098] In one example, the scene information may include the weather conditions (sunny, rainy, sunny, etc.) at the location of the user's vehicle and the time period information (morning, afternoon, and evening).

[0099] In an embodiment of the present invention, the real-time location information of the target vehicle can be obtained, and then the scene information of the environment in which the target vehicle is located can be determined through a preset interface based on the real-time location information. For example, the preset interface can be called according to the real-time location information to obtain weather information and clock information, thereby determining the weather status at the real-time location and the current time period.

[0100] Step S104, input the target prompt word and the initial image into the target image generation model, and output the cockpit wallpaper image of the target vehicle.

[0101] After obtaining the target prompt word, the target prompt word and the initial image can be input into the trained target image generation model, and the image generation model can generate a cockpit wallpaper image of a preset style. In actual applications, the image generation model can be trained according to various wallpaper styles, and then a cockpit wallpaper image corresponding to the initial image can be generated according to the style selected by the user or the wallpaper style used by the user in the past.

[0102] For example, the graph-generated graph model can be obtained by training based on a diffusion model, and the diffusion model specifically includes but is not limited to SDXL (Stable Diffusion XL), DIL (Deep Integration Learning Model), and other models.

[0103] In the embodiment of the present invention, wallpapers of different styles can be generated through the image generation module, so that the cockpit wallpaper is coordinated with the actual scene atmosphere, thereby enhancing the user's immersion and aesthetic experience.

[0104] In one embodiment of the present invention, a cockpit wallpaper image is displayed on the cockpit computer and / or ceiling screen of the target vehicle. By mapping the generated wallpaper to the cockpit computer or ceiling screen, the effect of instantly displaying the personalized generated wallpaper can be achieved, thereby improving the user experience and the sense of technology in the cockpit.

[0105] In an embodiment of the present invention, by acquiring an initial image captured by an image acquisition device of a target vehicle for the environment in which the target vehicle is located, the orientation information and attribute information of the target moving object can be determined based on the initial image, thereby generating a target prompt word corresponding to a target graph-generated image model according to the orientation information and the attribute information, and further inputting the target prompt word and the initial image into the target graph-generated image model, thereby outputting a cockpit wallpaper image of the target vehicle, thereby realizing the generation of intelligent and more flexible personalized wallpapers by analyzing the moving object and combining the graph-generated image model.

[0106] Reference Figure 2 , shows a flowchart of another method for generating a cockpit wallpaper provided by an embodiment of the present invention, which may specifically include the following steps:

[0107] Step S201, obtaining an initial image captured by an image acquisition device of a target vehicle with respect to the environment in which the target vehicle is located;

[0108] Step S202, inputting the initial image into a moving object detection model for detecting moving objects, and outputting target frame information of the target moving object;

[0109] After obtaining the initial image, the initial image can be preprocessed, such as image scaling, image normalization, and image enhancement.

[0110] The preprocessed image is then input into the trained motion object detection model to output the target box information, including the object category, confidence, position (x, y, width, height), etc.

[0111] In an embodiment of the present invention, a YOLO (You Only Look Once) or SSD (Single Shot Multi Box Detector) model may be used to implement target detection.

[0112] Step S203, inputting the target frame information into an attribute recognition model for extracting the attribute information of the moving object, and outputting the attribute information of the target moving object;

[0113] Then, the target frame information and the initial image can be input into the attribute recognition model, and the attribute recognition model can perform attribute recognition on the target moving object in the target frame in the initial image, and obtain the attribute information of the target moving object.

[0114] Specifically, a convolutional neural network (CNN) or a residual network (ResNet) may be used to train an attribute recognition model to achieve attribute recognition.

[0115] Step S204, inputting the target frame information into a depth estimation model for estimating the depth information of the moving object, and outputting the depth information from the center point of the target frame of the target moving object to the center point of the viewing angle of the image acquisition device;

[0116] After obtaining the target frame information, the target frame information and the initial image can be combined to perform depth estimation in a depth estimation model to determine the depth information from the center point of the target frame of the target moving object to the center point of the viewing angle of the image acquisition device.

[0117] For example, a monocular depth estimation model (such as Monodepth2) or a stereo depth estimation model (such as PSMNet) can be used for depth estimation.

[0118] In an embodiment of the present invention, some end-side multimodal models with a small number of parameters can also be used to replace the motion object detection model, the attribute recognition model and the depth estimation model, so as to achieve the output of the orientation information and attribute information obtained in the initial image by inputting the initial image to the end-side multimodal model.

[0119] Step S205: determining the orientation information of the target moving object according to the target frame information and the depth information.

[0120] After obtaining the target frame information and depth information, the specific position of the target moving object can be further determined.

[0121] In one embodiment of the present invention, determining the position information of the target moving object according to the target frame information and the depth information includes the following sub-steps:

[0122] Sub-step S21, determining whether the depth information is less than a preset depth threshold;

[0123] Since the moving object appears blurry when it accounts for too small a proportion of the image, such moving objects can be ignored. In the embodiment of the present invention, a preset depth threshold can be set to screen effective target moving objects. The preset depth threshold can be set according to the actual scene, and there is no excessive restriction on this in the embodiment of the present invention.

[0124] Sub-step S22, when it is determined that the depth information is less than a preset depth threshold, determining a first vector from the center point of the image acquisition device's viewing angle to the center point of the target frame information, and determining a second vector from the center point of the image acquisition device's viewing angle to the coordinates of the lower right corner of the initial image;

[0125] When it is determined that the depth information is less than a preset depth threshold, it is necessary to determine the orientation of the target moving object. The specific orientation can be determined according to the perspective coordinate system under the perspective of the image acquisition device, such as determining the coordinates of the perspective center point and the target frame information center point, and then determining the first vector from the perspective center point to the target frame information center point; determining the coordinates of the perspective center point of the image acquisition device and the coordinates of the lower right corner of the initial image, and then determining the second vector from the perspective center point of the image acquisition device to the coordinates of the lower right corner of the initial image.

[0126] Sub-step S23, determining a target angle between the first vector and the second vector;

[0127] The angle between two vectors can be calculated based on the two vectors. The specific calculation process is as follows:

[0128]

[0129] Wherein, θ represents the target angle, OA0 represents the second vector, and OA1 represents the first vector.

[0130] Sub-step S24, determining the orientation information of the target moving object based on the target angle.

[0131] After calculating the target angle, the orientation information can be determined based on the target angle. For example, when θ is between 75°-105°, it is determined to be directly in front, when θ is between 0°-75°, it is determined to be right front, and when θ is between 105°-180°, it is determined to be left front.

[0132] Step S206, generating a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image;

[0133] Step S207, input the target prompt word and the initial image into the target image generation model, and output the cockpit wallpaper image of the target vehicle.

[0134] The embodiment of the present invention achieves accurate analysis of moving objects in the front scene and ensures that the generated wallpaper can contain important visual objects, such as people and animals, by combining a moving object detection model, attribute recognition and a depth estimation model.

[0135] Reference Figure 3a FIG. 1 is a schematic diagram of a cockpit wallpaper generation process according to an embodiment of the present invention, which may include the following process:

[0136] (1) Gesture-triggered wallpaper generation function: Use dynamic gestures to click the function button for generating cockpit wallpaper to trigger the wallpaper generation function for the cockpit ceiling screen or the front row of the car screen;

[0137] (2) Calling the ADAS camera: At this time, ADAS takes a picture of the scene ahead and obtains an initial image, such as Figure 3b shown.

[0138] (3) Moving object analysis: Use the pre-trained moving object detection model, attribute recognition model, and depth estimation model to determine the position information of the moving object (such as the information of the target box in the picture and whether it is in front of the car, in front of the right, or in front of the left) and related motion attributes (such as pedestrians riding motorcycles, pedestrians riding bicycles, etc.) and the approximate age and gender attributes of the pedestrians, and output the relevant position information and related attribute information of the moving object in a structured form.

[0139] The general algorithm flow of the moving object orientation judgment in the moving object analysis module is as follows:

[0140] The detection model is used to extract the target frame of the moving object, and the depth estimation model is used to estimate the depth of the frame image. The center point of the moving object target frame is calculated, and then the distance relationship between the moving object in front and the driving vehicle is determined according to the depth value from the center point to the center point under the camera's perspective. By setting the corresponding depth value threshold K, it is determined whether the moving object in front is an available scene moving object. If the moving object in front is an available scene moving object, the direction of the moving object in front is further determined.

[0141] To determine whether the moving object in front is directly in front, right in front, or left in front, the vectors from the center point of the bottom of the picture to the center point of the target frame of the moving object in front can be defined as OA1, OA2, OA3, ..., O, and the vector from the center point of the bottom of the picture to the coordinates of the lower right corner can be defined as OA0. The corresponding angles between the vectors are calculated. Taking OA1 and OA0 as an example, the formula is as follows:

[0142]

[0143] When θ is between 75°-105°, it is determined to be directly in front; when θ is between 0°-75°, it is determined to be the right front; and when θ is between 105°-180°, it is determined to be the left front.

[0144] (4) Front scene analysis: This step uses some interfaces to obtain the weather conditions (sunny, rainy, sunny, etc.) and time period information (morning, afternoon, and evening) at the location of the user's vehicle;

[0145] (5) Prompt expansion module: This module integrates and expands the structured information output by the motion object analysis module and the structured information output by the scene analysis module, and converts them into prompts required for model input;

[0146] (6) Image generation module: The input of this module is the prompts and corresponding scene images expanded and integrated by the prompt expansion module, such as Figure 3b As shown in , the output is a comic-style image that matches the atmosphere of the scene picture (in order to show the effect, a rainy day is added to show the generated effect. In fact, in reality, the atmospheres of the two should match each other). Figure 3c shown.

[0147] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0148] Reference Figure 4 , shows a schematic diagram of the structure of a device for generating a cockpit wallpaper provided by an embodiment of the present invention, which may specifically include the following modules:

[0149] An initial image acquisition module 401 is used to acquire an initial image acquired by an image acquisition device of a target vehicle with respect to an environment where the target vehicle is located;

[0150] An information extraction module 402 is used to determine the position information and attribute information of the target moving object based on the initial image;

[0151] A prompt word generation module 403, used to generate a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image;

[0152] The cockpit wallpaper generation module 404 is used to input the target prompt word and the initial image into the target image generation model, and output the cockpit wallpaper image of the target vehicle.

[0153] In one embodiment of the present invention, the information extraction module 402 may include:

[0154] a target frame information determination submodule, configured to input the initial image into a moving object detection model for detecting moving objects, and output target frame information of the target moving object;

[0155] An attribute information determination submodule, used for inputting the target frame information into an attribute recognition model for extracting attribute information of a moving object, and outputting the attribute information of the target moving object;

[0156] A depth estimation submodule, configured to input the target frame information into a depth estimation model for estimating the depth information of a moving object, and output the depth information from the center point of the target frame of the target moving object to the center point of the viewing angle of the image acquisition device;

[0157] The orientation information determination submodule is used to determine the orientation information of the target moving object according to the target frame information and the depth information.

[0158] In one embodiment of the present invention, the position information determination submodule may include the following units:

[0159] A depth judgment unit, used to judge whether the depth information is less than a preset depth threshold;

[0160] a vector determination unit, for determining, when it is determined that the depth information is less than the preset depth threshold, a first vector from the center point of the viewing angle of the image acquisition device to the center point of the target frame information, and a second vector from the center point of the viewing angle of the image acquisition device to the coordinates of the lower right corner of the initial image;

[0161] a vector angle calculation unit, used to determine a target angle between the first vector and the second vector;

[0162] The orientation determining unit is used to determine the orientation information of the target moving object based on the target angle.

[0163] In one embodiment of the present invention, the prompt word generation module 403 may include the following submodules:

[0164] A preprocessing submodule, used for performing data preprocessing on the orientation information and the attribute information to obtain structured information corresponding to the target graph model;

[0165] A key information extraction submodule, used to extract multiple key feature information from the structured information;

[0166] An integration processing submodule, used for integrating the multiple key features to obtain integrated feature information;

[0167] An expansion processing submodule, used for performing expansion processing on the integrated feature information to obtain target feature information;

[0168] The target prompt word generation submodule is used to generate the target prompt word corresponding to the target graph model based on the target feature information.

[0169] In one embodiment of the present invention, the device further comprises:

[0170] A scene information acquisition module, used to acquire scene information of the environment in which the target vehicle is located;

[0171] When the prompt word generation module 403 is used to generate the target prompt word corresponding to the target image model according to the orientation information and the attribute information, it is specifically used to:

[0172] Generate a target prompt word corresponding to the target image model according to the orientation information, the attribute information and the scene information.

[0173] In one embodiment of the present invention, the scene information acquisition module includes:

[0174] A real-time location acquisition submodule is used to acquire the real-time location information of the target vehicle;

[0175] The scene information determination submodule is used to determine the scene information of the environment in which the target vehicle is located based on the real-time position information.

[0176] In one embodiment of the present invention, the initial image acquisition module 401 may include the following submodules:

[0177] A wallpaper generation function activation submodule, configured to activate a wallpaper generation function when a preset gesture of a target user in the target vehicle is detected;

[0178] The initial image acquisition submodule is used to obtain an initial image captured by an image acquisition device of a target vehicle with respect to the environment in which the target vehicle is located when the wallpaper generation function is turned on.

[0179] In one embodiment of the present invention, the device further comprises:

[0180] The wallpaper display module is used to display the cockpit wallpaper image on the cockpit computer and / or ceiling screen of the target vehicle.

[0181] In an embodiment of the present invention, by acquiring an initial image captured by an image acquisition device of a target vehicle for the environment in which the target vehicle is located, the orientation information and attribute information of the target moving object can be determined based on the initial image, thereby generating a target prompt word corresponding to a target graph-generated image model according to the orientation information and the attribute information, and further inputting the target prompt word and the initial image into the target graph-generated image model, thereby outputting a cockpit wallpaper image of the target vehicle, thereby realizing the generation of intelligent and more flexible personalized wallpapers by analyzing the moving object and combining the graph-generated image model.

[0182] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the method for generating a cockpit wallpaper as described above is implemented.

[0183] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a cockpit wallpaper as described above is implemented.

[0184] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0185] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0186] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0187] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in one process or multiple processes in the flowchart and / or one box or multiple boxes in the block diagram.

[0188] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0189] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce computer-implemented processing, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0190] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0191] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0192] The above provides a detailed introduction to a method and device for generating a cockpit wallpaper, an electronic device, and a storage medium. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for generating cockpit wallpaper, characterized in that: The method comprises: Acquire an initial image captured by an image acquisition device of a target vehicle with respect to an environment in which the target vehicle is located; Determine the orientation information and attribute information of the target moving object based on the initial image; Generate a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image; The target prompt word and the initial image are input into the target image generation model, and a cockpit wallpaper image of the target vehicle is output.

2. The method according to claim 1, characterized in that The determining the position information and attribute information of the target moving object based on the initial image includes: Inputting the initial image into a moving object detection model for detecting moving objects, and outputting target frame information of the target moving object; Inputting the target frame information into an attribute recognition model for extracting attribute information of a moving object, and outputting the attribute information of the target moving object; Input the target frame information into a depth estimation model for estimating the depth information of a moving object, and output the depth information from the center point of the target frame of the target moving object to the center point of the viewing angle of the image acquisition device; The orientation information of the target moving object is determined according to the target frame information and the depth information.

3. The method according to claim 2, characterized in that The determining the position information of the target moving object according to the target frame information and the depth information includes: Determining whether the depth information is less than a preset depth threshold; When it is determined that the depth information is less than the preset depth threshold, determining a first vector from the center point of the viewing angle of the image acquisition device to the center point of the target frame information, and determining a second vector from the center point of the viewing angle of the image acquisition device to the coordinates of the lower right corner of the initial image; determining a target angle between the first vector and the second vector; The orientation information of the target moving object is determined based on the target angle.

4. The method according to claim 1, characterized in that: The step of generating a target prompt word corresponding to the target image model according to the orientation information and the attribute information includes: Performing data preprocessing on the orientation information and the attribute information to obtain structured information corresponding to the target graph model; Extracting multiple key feature information from the structured information; Integrate the multiple key features to obtain integrated feature information; Performing expansion processing on the integrated feature information to obtain target feature information; Generate target prompt words corresponding to the target graph model based on target feature information.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Acquiring scene information of the environment in which the target vehicle is located; The step of generating a target prompt word corresponding to the target image model according to the orientation information and the attribute information includes: Generate a target prompt word corresponding to the target image model according to the orientation information, the attribute information and the scene information.

6. The method according to claim 5, characterized in that The acquiring of scene information of the environment in which the target vehicle is located includes: Obtaining real-time location information of the target vehicle; The scene information of the environment in which the target vehicle is located is determined based on the real-time position information.

7. The method according to any one of claims 1 to 4, characterized in that The initial image acquired by the image acquisition device of the target vehicle for the environment in which the target vehicle is located includes: When a preset gesture of a target user in the target vehicle is detected, a wallpaper generation function is activated; When the wallpaper generation function is turned on, an initial image captured by an image capture device of a target vehicle with respect to the environment in which the target vehicle is located is obtained.

8. The method according to any one of claims 1 to 4, characterized in that The method further comprises: The cockpit wallpaper image is displayed on a cockpit computer and / or a ceiling screen of the target vehicle.

9. A device for generating cockpit wallpaper, characterized in that: The device comprises: An initial image acquisition module, used to acquire an initial image acquired by an image acquisition device of a target vehicle with respect to an environment where the target vehicle is located; An information extraction module, used to determine the position information and attribute information of the target moving object based on the initial image; A prompt word generation module, used to generate a target prompt word corresponding to a target image raw model according to the orientation information and the attribute information, wherein the target image raw model is used to generate a cockpit wallpaper of a preset style based on the prompt word and the image; The cockpit wallpaper generation module is used to input the target prompt word and the initial image into the target image generation model, and output the cockpit wallpaper image of the target vehicle.

10. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the method for generating a cockpit wallpaper according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating a cockpit wallpaper according to any one of claims 1 to 8 is implemented.

Images