Vehicle photographing method, device, system and vehicle

Abstract

The application discloses a vehicle photographing method, device, system and vehicle. The method comprises the following steps: in response to a wake-up instruction of a target object, an environment image of an environment in which the target object is located is acquired through a camera of the vehicle, wherein the environment image contains environment information of the environment and the target object; feature information of the target object in the environment image is acquired, and a sample picture is queried from a database, wherein the similarity between attribute information contained in the sample picture and the environment information and the feature information both exceeds a first threshold value, and the attribute information comprises the environment information and the feature information; the target object is photographed according to the sample picture, and a target picture is obtained; a target score of the target object on the target picture is received, and a photographing preference of the target object is learned according to the target score. The application solves the technical problem that the vehicle cannot photograph the user in the prior art, the user needs to adjust the position according to the photographing result in the photographing process, and the photographing preference of the user cannot be learned.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method, apparatus, system, and vehicle for taking photographs of vehicles. Background Technology

[0002] With technological advancements, people's demands for documenting their lives are becoming increasingly diverse. As cars are used in more and more scenarios in people's lives, the vehicle's camera function can become a supplement to people's photography. For example, when we travel, we hope that the car can automatically take pictures for us and provide shooting suggestions, such as where to stand, what pose to strike, and what kind of lighting to choose.

[0003] Currently, there are no good selfie devices available, especially since vehicles do not have this function at all. Although mobile phones can take selfies, their selfie modes are not suitable for taking selfies from a distance, and full-body photos are limited. In addition, with current selfie devices, users need to take the photo, check the shooting effect, adjust their position according to the effect, and then check it again, which is a complicated process and wastes a lot of time.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a method, apparatus, system, and vehicle for taking photos, to at least solve the technical problems in the prior art where vehicles cannot take photos of users, require users to adjust their positions according to the shooting results during the photo taking process, and cannot learn the user's photo taking preferences.

[0006] According to one aspect of the embodiments of this application, a method for taking pictures of a vehicle is provided, comprising: in response to a wake-up command of a target object, acquiring an environmental image of the environment in which the target object is located through a camera of the vehicle, wherein the environmental image includes environmental information and the target object; acquiring feature information of the target object in the environmental image and querying sample images from a database, wherein the similarity between the attribute information contained in the sample images and the environmental information and feature information both exceed a first threshold, and the attribute information includes environmental information and feature information; taking a picture of the target object based on the sample images to obtain a target image; receiving a target score from the target object for the target image, and learning the target object's photography preferences based on the target score.

[0007] Optionally, before querying sample images from the database, the method further includes: obtaining source images and corresponding image scores, wherein the source images are pre-uploaded images, and the image scores are scores given to the source images according to preset standards, and the image scores are used to quantify the degree to which the images conform to aesthetic standards; training an evaluation model based on the source images and image scores, wherein the evaluation model is used to score the images; scoring the source images in the source image library based on the evaluation model, and saving images with scores exceeding a second threshold in the sample image library.

[0008] Optionally, taking a picture of the target object based on the sample image includes: establishing a three-dimensional model based on environmental information; determining the imaging effect of the target object under different shooting parameters in the three-dimensional model based on the shooting parameters of the sample image, and obtaining multiple preview images, wherein the shooting parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images based on the evaluation model, and selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the shooting parameters in the first image.

[0009] Optionally, taking a picture of the target object based on the shooting parameters in the first image includes: obtaining the shooting parameters of the first image, wherein the shooting parameters of the first image include at least: the second position information of the person in the first image, the posture information of the person in the first image, and the shooting angle of the first image; generating a prompt message to adjust the position of the target object based on the shooting parameters of the first image, or adjusting the position of the camera to take a picture of the target object.

[0010] Optionally, adjusting the position of the camera or the target object includes: adjusting the shooting angle of the camera according to the shooting parameters of the first image; generating shooting suggestions based on prompt information or the second position information of the person in the first image and the posture information of the person in the first image, and playing voice information generated based on the shooting suggestions.

[0011] Optionally, when adjusting the position of the camera or the target object, the following priorities should be followed: the rotation angle of the camera, the horizontal movement position of the vehicle, and the horizontal movement position of the target object.

[0012] Optionally, the target object's photo preferences are learned based on the target score, including updating the evaluation model based on the target score and the target image.

[0013] According to another aspect of the embodiments of this application, a vehicle photography device is also provided, comprising: an acquisition module, configured to acquire an environmental image of the environment in which the target object is located via a vehicle camera in response to a wake-up command of a target object, wherein the environmental image contains environmental information and the target object; a query module, configured to acquire feature information of the target object in the environmental image and query sample images from a database, wherein the similarity between the attribute information contained in the sample images and the environmental information and feature information exceeds a first threshold, and the attribute information includes environmental information and feature information; a photographing module, configured to take a photograph of the target object based on the sample images to obtain a target image; and a receiving module, configured to receive a target score from the target object for the target image and learn the target object's photography preferences based on the target score.

[0014] According to another aspect of the embodiments of this application, a vehicle photography system is also provided, comprising: a vehicle, a camera, a voice interaction module, a 3D simulation module, an evaluation module, and a processing module, wherein the vehicle is used to respond to a wake-up command from a target object and activate the vehicle's photography function; the camera is installed on the vehicle and used to photograph the target object to obtain an environmental image of the environment in which the target object is located; the 3D simulation unit is used to establish a 3D model based on the environmental information in the environmental image; the voice interaction unit is used to notify the target object of a shooting suggestion, wherein the shooting suggestion includes shooting location information and shooting posture information; the evaluation unit is used to score the image captured by the camera; the processing unit is used to acquire an environmental image of the environment in which the target object is located, wherein the environmental image contains environmental information and the target object; acquire feature information of the target object in the environmental image and query sample images from a database, wherein the similarity between the attribute information contained in the sample image and the environmental information and feature information both exceed a first threshold, and the attribute information includes environmental information and feature information; take a picture of the target object based on the sample image to obtain a target image; receive a target score from the target object for the target image, and learn the target object's photography preferences based on the target score.

[0015] According to another aspect of the embodiments of this application, a vehicle is also provided, the controller of which is used to perform the above-described vehicle photography method.

[0016] In this embodiment, in response to a wake-up command from the target object, the vehicle's camera acquires an environmental image of the target object's environment, which includes environmental information and the target object. Feature information of the target object in the environmental image is acquired, and sample images are queried from a database. The similarity between the attribute information and environmental information and feature information in the sample images exceeds a first threshold. The attribute information includes both environmental information and feature information. A photo is taken of the target object based on the sample image to obtain a target image. The target object's target rating for the target image is received, and the vehicle's photo-taking preferences are learned based on the target rating. This achieves the vehicle's goal of taking photos of the user based on intelligently recommended sample images, thus realizing the technical effect of learning user preferences based on user ratings. This solves the technical problem in the prior art where the vehicle cannot take photos of the user, and the user needs to adjust their position manually based on the photo-taking results, making it impossible to learn the user's photo-taking preferences. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a structural diagram of a vehicle photography system according to an embodiment of this application;

[0019] Figure 2a This is a flowchart of an example of obtaining an evaluation model according to an embodiment of this application;

[0020] Figure 2b This is a flowchart of a vehicle photography system according to an embodiment of this application;

[0021] Figure 3 This is a flowchart of a method for taking photos of a vehicle according to an embodiment of this application;

[0022] Figure 4 This is a structural diagram of a vehicle photography device according to an embodiment of this application. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Figure 1 This is a structural diagram of a vehicle photography system according to an embodiment of this application, such as... Figure 1 As shown, the system includes: a vehicle 10, a camera 11, a voice interaction unit 12, a 3D simulation unit 13, an evaluation unit 14, and a processing unit 15. The vehicle is used to respond to a wake-up command from the target object and activate its camera function. The camera, mounted on the vehicle, is used to capture images of the target object, obtaining an environmental image of the target object's environment. The 3D simulation unit is used to build a 3D model based on the environmental information in the environmental image. The voice interaction unit is used to notify the target object of shooting suggestions, including shooting location information and shooting posture information. The evaluation unit is used to score the images captured by the camera. The processing unit is used to acquire an environmental image of the target object's environment, containing environmental information and the target object; acquire feature information of the target object in the environmental image and query sample images from a database, wherein the similarity between the attribute information and environmental information and feature information contained in the sample images exceeds a first threshold, and the attribute information includes environmental information and feature information; capture an image of the target object based on the sample image to obtain a target image; receive the target object's target score for the target image and learn the target object's shooting preferences based on the target score.

[0026] In this embodiment, the camera in the vehicle may be composed of a three-axis 360-degree gimbal to ensure that it can be adjusted to any angle within the front hemisphere of the vehicle; the aforementioned voice interaction unit can be woken up by the user's voice, and the user can wake up the vehicle's automatic shooting function through voice interaction. The voice interaction unit is also responsible for interacting with the user, providing shooting suggestions to the user, and collecting user needs.

[0027] In the evaluation unit of the aforementioned vehicle photography system, this unit includes an evaluation model. The process of acquiring the evaluation model is as follows: acquiring source images and corresponding image scores, wherein the source images are pre-uploaded images, and the image scores are scores given to the source images according to preset standards, and the image scores are used to quantify the degree to which the images meet aesthetic standards; training the evaluation model based on the source images and image scores, wherein the evaluation model is used to score the images; scoring the source images in the source image library based on the evaluation model, and saving images with scores exceeding a second threshold in the sample image library.

[0028] In the embodiments of this application, such as Figure 2a The diagram shows that the source images are pictures or materials uploaded by photographers (including professional and semi-professional photographers), photography enthusiasts, and other professionals. These source images form a source image library. Professional photographers and aesthetic experts rate the source images, using this as input data and integrating basic aesthetic standards. A preliminary evaluation system neural network model (hereinafter referred to as the evaluation model) is trained using deep learning algorithms. The evaluation model rates other source images in the source library, selecting high-scoring images as sample images and storing them in a sample image library. These sample images are provided to users when needed. It should be noted that the aforementioned high-scoring images are those with a score greater than a second threshold. In this embodiment, when the score range is [1, 10], the second threshold can be set to, for example, 8 points. Images with a score greater than 8 points can be considered high-scoring images and stored in the sample image library. However, the aforementioned score range can be set independently, for example, to [0, 1], and the corresponding second threshold can be set to 0.8. No limitation is made here. The example image library in this application embodiment can provide users with high-scoring works that are of reference value in the shooting scene when the user takes a photo, which can inspire the user's choice of posture, lighting and angle.

[0029] In the processing unit of the aforementioned vehicle photography system, taking a picture of the target object based on a sample image specifically includes the following steps: establishing a three-dimensional model based on environmental information; determining the imaging effect of the target object under different photography parameters in the three-dimensional model based on the photography parameters of the sample image, obtaining multiple preview images, wherein the photography parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images based on an evaluation model, selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the photography parameters in the first image.

[0030] In this embodiment, after the user activates the vehicle's intelligent shooting function via voice, the vehicle's camera acquires an environmental image of the target object's environment. The 3D simulation unit acquires environmental information from this image, such as information about trees, lighting, and mountains. Using this environmental information, a 3D model is created, and the shooting parameters from a sample image are obtained. These parameters include the first position of the person in the sample image, the person's posture, and the shooting angle. Based on the shooting parameters of the sample image, the imaging effect of the target object under different combinations of shooting parameters is determined, resulting in multiple preview images. A trained evaluation model scores these preview images, and the image with the highest score is selected to capture the target object. This highest-scoring image, also known as the first image, includes shooting parameters such as the optimal shooting angle, the target object's best position in the current environment, and the target object's best posture. Based on these shooting parameters, different shooting suggestions are provided, such as backlighting or front lighting.

[0031] In the processing unit of the aforementioned vehicle photography system, taking a picture of the target object based on the photography parameters in the first image specifically includes the following process: obtaining the photography parameters of the first image, wherein the photography parameters of the first image include at least: the second position information of the person in the first image, the posture information of the person in the first image, and the shooting angle of the first image; generating a prompt message to adjust the position of the target object based on the photography parameters of the first image, or adjusting the position of the camera to take a picture of the target object.

[0032] In the processing unit of the aforementioned vehicle photography system, adjusting the position of the camera or the target object specifically includes the following process: adjusting the shooting angle of the camera according to the shooting parameters of the first image; generating a shooting suggestion based on the prompt information or the second position information of the person in the first image and the posture information of the person in the first image, and playing the voice information generated based on the shooting suggestion.

[0033] In the aforementioned vehicle photography system, the shooting suggestions are communicated to the target object through the voice interaction module. This solves the problem that current automatic photography tools only provide automatic shooting functions when taking pictures of users, without offering shooting suggestions or other similar features.

[0034] In the processing unit of the aforementioned vehicle photography system, when adjusting the position of the camera or the target object, the following priorities are followed: the camera's rotation angle, the vehicle's horizontal movement position, and the target object's horizontal movement position.

[0035] In the processing unit of the aforementioned vehicle photography system, the photography preferences of the target object are learned based on the target score, including updating the evaluation model based on the target score and the target image.

[0036] In this embodiment, an online evaluation model is downloaded during user program initialization. User feedback, specifically target ratings for the target image, is collected. The evaluation model is then updated based on these target ratings, iterating gradually to a model suited to the user's aesthetic preferences. The evaluation model guides the user from the following perspectives: 1. Feature analysis of the user taking the photo, providing shooting angle suggestions to help the user present the most aesthetically pleasing angle; 2. Aesthetics of the user's posture; 3. Matching degree of the user's posture with the background or environment; 4. Whether the user's position in the background is appropriate, whether it obstructs important scenery, and whether it meets compositional requirements; 5. Whether the user's shooting angle meets lighting conditions.

[0037] The vehicle photography system provided in this application embodiment can assist users in taking photos. After the user triggers the photo-taking function on the vehicle, the vehicle provides high-scoring sample images of the scene. Through evaluation models, 3D simulation units, and voice interaction units, the system provides shooting guidance to the user, offering suggestions on shooting posture, shooting position, shooting light selection, and shooting background selection. It assists the user in adjusting posture, lighting, shooting angle, and position in the background, and helps the user take high-scoring photos of the scene in a suitable environment, such as an open field or a travel highway. At the same time, it learns the user's preferences to make the shooting style closer to the user's preferences.

[0038] Figure 2b This is a flowchart of a vehicle photography system according to an embodiment of this application, such as... Figure 2bAs shown, the user activates the vehicle's intelligent photography function via voice and loads a trained evaluation model. The vehicle's camera captures an environmental image of the target object's location, including environmental information and the target object. A processing unit analyzes the target object's features and the environmental information, and queries a sample image library for highly relevant images matching the target object's features and environment. A 3D simulation unit constructs a 3D environmental model based on the environmental information. Using the photography parameters in the sample images, multiple preview images of the target object are determined under different photography parameters. The evaluation model scores these preview images, selecting the highest-scoring image as the final sample image for photographing the target object—the first image. Based on the first image's photography parameters, the camera or target object's position is adjusted according to the following priority: camera rotation angle, vehicle horizontal movement, and target object horizontal movement. A shooting suggestion is communicated to the target object via a voice interaction module, including at least the target object's correct position and posture. After parameter adjustment, the camera captures the target image, and the target object's target score is received. The evaluation model is updated based on the target score to learn the target object's photography preferences.

[0039] In the above operating environment, this application embodiment also provides a method embodiment for taking pictures of vehicles. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than that shown here.

[0040] Figure 3 This is a flowchart of a vehicle photography method according to an embodiment of this application, such as... Figure 3 As shown, the method includes the following steps:

[0041] Step S302: In response to the wake-up command of the target object, an environmental image of the environment in which the target object is located is acquired through the vehicle's camera, wherein the environmental image contains environmental information and the target object;

[0042] Step S304: Obtain feature information of the target object in the environmental image and query sample images from the database. The similarity between the attribute information and the environmental information and feature information contained in the sample images exceeds the first threshold. The attribute information includes environmental information and feature information.

[0043] Step S306: Take a picture of the target object based on the sample image to obtain the target image;

[0044] Step S308: Receive the target object's target score for the target image, and learn the target object's photography preferences based on the target score.

[0045] In step S304 of the above-mentioned vehicle photography method, before querying sample images from the database, the method further includes the following steps: obtaining source images and corresponding image scores, wherein the source images are pre-uploaded images, and the image scores are scores given to the source images according to preset standards, and the image scores are used to quantify the degree to which the images conform to aesthetic standards; training an evaluation model based on the source images and image scores, wherein the evaluation model is used to score the images; scoring the source images in the source image library based on the evaluation model, and saving images with scores exceeding a second threshold in the sample image library.

[0046] In step S306 of the above-mentioned vehicle photography method, taking a picture of the target object based on the sample image includes: establishing a three-dimensional model based on environmental information; determining the imaging effect of the target object under different photography parameters in the three-dimensional model based on the photography parameters of the sample image, and obtaining multiple preview images. The photography parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images based on the evaluation model, and selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the photography parameters in the first image.

[0047] In the above steps, taking a picture of the target object based on the shooting parameters in the first image specifically includes the following steps: obtaining the shooting parameters of the first image, wherein the shooting parameters of the first image include at least: the second position information of the person in the first image, the posture information of the person in the first image, and the shooting angle of the first image; generating a prompt message to adjust the position of the target object based on the shooting parameters of the first image, or adjusting the position of the camera to take a picture of the target object.

[0048] In the above steps, adjusting the position of the camera or the target object specifically includes the following steps: adjusting the shooting angle of the camera according to the shooting parameters of the first image; generating shooting suggestions based on the prompt information or the second position information of the person in the first image and the posture information of the person in the first image, and playing the voice information generated based on the shooting suggestions.

[0049] In the above steps, when adjusting the position of the camera or the target object, the following priorities should be followed: the rotation angle of the camera, the horizontal movement position of the vehicle, and the horizontal movement position of the target object.

[0050] In step S308 of the above vehicle photography method, the photography preference of the target object is learned based on the target score, which is specifically manifested as: updating the evaluation model based on the target score and the target image.

[0051] It should be noted that, Figure 3 The method shown for taking photos of vehicles can be applied to... Figure 1 The vehicle photography system shown above is an example of a system for taking photos of vehicles. Therefore, the explanations and descriptions related to the vehicle photography system described above also apply to the method for taking photos of vehicles, and will not be repeated here.

[0052] Figure 4 This is a structural diagram of a vehicle photography device according to an embodiment of this application, such as... Figure 4 As shown, the device includes:

[0053] The acquisition module 402 is used to acquire an environmental image of the environment in which the target object is located through the vehicle's camera in response to the wake-up command of the target object. The environmental image contains environmental information and the target object.

[0054] The query module 404 is used to obtain the feature information of the target object in the environmental image and query the sample image from the database. The similarity between the attribute information and the environmental information and feature information contained in the sample image exceeds the first threshold. The attribute information includes environmental information and feature information.

[0055] The camera module 406 is used to take a picture of the target object based on the sample image to obtain the target image;

[0056] The receiving module 408 is used to receive the target object's target rating of the target image and learn the target object's photography preferences based on the target rating.

[0057] It should be noted that, Figure 4 The vehicle photography device shown is used to perform... Figure 3 The method for taking pictures of vehicles shown above is explained in the same way as the device for taking pictures of vehicles, and will not be repeated here.

[0058] This application embodiment also provides a non-volatile storage medium, which includes a stored program. During program execution, the device containing the non-volatile storage medium performs the following vehicle photography method: In response to a wake-up command from a target object, acquiring an environmental image of the target object's environment using the vehicle's camera, wherein the environmental image contains environmental information and the target object; acquiring feature information of the target object in the environmental image and querying sample images from a database, wherein the similarity between the attribute information contained in the sample images and the environmental information and feature information exceeds a first threshold, and the attribute information includes both environmental information and feature information; taking a picture of the target object based on the sample images to obtain a target image; receiving a target score from the target object for the target image, and learning the target object's photography preferences based on the target score.

[0059] This application also provides a vehicle whose controller is used to perform... Figure 3 The method for taking pictures of the vehicle shown above is also applicable to the controller of this vehicle, and will not be repeated here.

[0060] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0061] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0062] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0063] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0065] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0066] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for taking photos of vehicles, characterized in that, include: In response to a wake-up command from the target object, an environmental image of the environment in which the target object is located is acquired through the vehicle's camera, wherein the environmental image contains environmental information of the environment and the target object; The feature information of the target object in the environmental image is obtained, and a sample image is queried from the database. The similarity between the attribute information contained in the sample image and the environmental information and the feature information exceeds a first threshold. The attribute information includes the environmental information and the feature information. The target object is photographed based on the example image to obtain the target image; Receive the target object's target rating of the target image, and learn the target object's photography preferences based on the target rating; The step of taking a picture of the target object based on the sample image includes: establishing a three-dimensional model based on the environmental information; determining the imaging effect of the target object under different shooting parameters in the three-dimensional model based on the shooting parameters of the sample image, and obtaining multiple preview images, wherein the shooting parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images according to the evaluation model, and selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the shooting parameters in the first image. The method further includes: downloading the evaluation model during user program initialization and collecting target scores for the target image; updating the evaluation model based on the target scores, wherein the updated evaluation model is used to provide multi-dimensional suggestion information for the target object, the suggestion information including: suggestion information for adjusting the shooting angle; suggestion information for adjusting the matching degree between the pose of the target object and the background or the environment; and suggestion information for adjusting the position of the target object in the background.

2. The method according to claim 1, characterized in that, Before retrieving sample images from the database, the method further includes: Obtain source images and corresponding image ratings, wherein the source images are pre-uploaded images, and the image ratings are scores given to the source images based on preset standards, and the image ratings are used to quantify the degree to which the images conform to aesthetic standards; An evaluation model is trained based on the source images and the image ratings, wherein the evaluation model is used to rate the images; The images in the material library are scored according to the evaluation model, and images with scores exceeding the second threshold are saved in the sample image library.

3. The method according to claim 2, characterized in that, Taking a picture of the target object based on the photographing parameters in the first image includes: The first image capture parameters are obtained, wherein the first image capture parameters include at least: the second position information of the person in the first image, the posture information of the person in the first image, and the shooting angle of the first image. Based on the shooting parameters of the first image, a prompt message is generated to adjust the position of the target object, or the position of the camera is adjusted to take a picture of the target object.

4. The method according to claim 3, characterized in that, Adjusting the position of the camera or the position of the target object includes: Adjust the shooting angle of the camera according to the shooting parameters of the first image; Based on the prompt information or the second location information of the person in the first image and the posture information of the person in the first image, a shooting suggestion is generated, and voice information generated based on the shooting suggestion is played.

5. The method according to claim 3, characterized in that, When adjusting the position of the camera or the target object, the following priorities shall be followed: the rotation angle of the camera, the horizontal movement position of the vehicle, and the horizontal movement position of the target object.

6. A device for taking vehicle photos, characterized in that, include: The acquisition module is used to acquire an environmental image of the environment in which the target object is located through the vehicle's camera in response to a wake-up command of the target object. The environmental image contains environmental information of the environment and the target object. The query module is used to obtain feature information of the target object in the environmental image and query sample images from the database. The similarity between the attribute information contained in the sample image and the environmental information and the feature information both exceed a first threshold. The attribute information includes the environmental information and the feature information. The camera module is used to take a picture of the target object based on the sample image to obtain a target image; The receiving module is used to receive the target object's target score for the target image and learn the target object's photography preferences based on the target score; The camera module is further configured to perform the following steps: establishing a three-dimensional model based on the environmental information; determining the imaging effect of the target object under different camera parameters in the three-dimensional model based on the camera parameters of the sample image, thereby obtaining multiple preview images, wherein the camera parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images according to an evaluation model, and selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the camera parameters in the first image. The vehicle photography device is further configured to perform the following steps: downloading the evaluation model during user program initialization and collecting target scores for the target image; updating the evaluation model based on the target scores, wherein the updated evaluation model is used to provide multi-dimensional suggestion information for the target object, the suggestion information including: suggestion information for adjusting the shooting angle; suggestion information for adjusting the matching degree between the pose of the target object and the background or the environment; and suggestion information for adjusting the position of the target object in the background.

7. A vehicle photography system, characterized in that, include: The system comprises a vehicle, a camera, a voice interaction unit, a 3D simulation unit, an evaluation unit, and a processing unit. The vehicle is used to respond to the wake-up command of the target object and activate the vehicle's camera function; The camera is mounted on the vehicle and is used to capture images of the target object to obtain an environmental image of the environment in which the target object is located. The three-dimensional simulation unit is used to establish a three-dimensional model based on the environmental information in the environmental image. The voice interaction unit is used to notify the target object of shooting suggestions, wherein the shooting suggestions include shooting location information and shooting posture information; The evaluation unit is used to score the images captured by the camera; The processing unit is configured to: acquire an environmental image of the environment in which the target object is located, wherein the environmental image contains environmental information of the environment and the target object; acquire feature information of the target object in the environmental image and query sample images from a database, wherein the similarity between the attribute information contained in the sample images and the environmental information and the feature information exceeds a first threshold, and the attribute information includes the environmental information and the feature information; take a picture of the target object based on the sample images to obtain a target image; receive a target score from the target object for the target image, and learn the target object's photography preferences based on the target score; The vehicle photography system further includes the following steps: establishing a three-dimensional model based on the environmental information; determining the imaging effect of the target object under different photography parameters in the three-dimensional model based on the photography parameters of the sample image, obtaining multiple preview images, wherein the photography parameters of the sample image include at least: the first position information of the person in the sample image, the posture information of the person in the sample image, and the shooting angle of the sample image; scoring the multiple preview images according to an evaluation model, and selecting the image with the highest score from the scoring results as the first image; and taking a picture of the target object based on the photography parameters in the first image. The evaluation model is downloaded during user program initialization, and target scores for the target images are collected. Based on the target scores, the evaluation model is updated, wherein the updated evaluation model is used to provide multi-dimensional suggestion information for the target object, including: suggestion information for adjusting the shooting angle, suggestion information for adjusting the matching degree between the pose of the target object and the background or the environment, and suggestion information for adjusting the position of the target object in the background.

8. A vehicle, characterized in that, The vehicle controller is used to execute the vehicle photography method according to any one of claims 1 to 5.

Images