Vehicle-mounted photographing method and device, vehicle and storage medium

Abstract

This invention discloses an in-vehicle shooting method, apparatus, vehicle, and storage medium. The method includes: acquiring at least one interactive behavior information of a user inside the vehicle; if the at least one interactive behavior information is a preset shooting interaction behavior, acquiring current vehicle driving condition information and the user's facial information; determining the user's shooting intention based on the driving condition information and the user's facial information; and if the shooting intention is to take a picture, controlling the in-vehicle camera to capture images of the current environment of the vehicle. The technical solution of this invention reduces accidental touches during in-vehicle shooting and improves the user experience.

Description

Technical Field

[0001] The present invention relates to the field of automotive technology, and in particular to a vehicle-mounted photography method, device, vehicle, and storage medium. Background Technology

[0002] With the development of intelligent vehicle systems, in-vehicle photography functions have gradually become an important part of enhancing user experience, and are widely used in scenarios such as driving recording, travel scenery shooting, and in-vehicle activity recording.

[0003] Currently, most in-vehicle shooting methods rely on user voice commands for control. However, this method has significant false triggering problems. For example, in noisy driving environments, a single voice command is easily misrecognized due to background noise interference, leading to frequent false triggering of the shooting function. In addition, differences in accents among different users can also exacerbate the risk of false triggering.

[0004] Therefore, there is an urgent need to propose a new method to solve the above problems. Summary of the Invention

[0005] This invention provides a vehicle-mounted shooting method, device, vehicle, and storage medium to reduce accidental touches during vehicle-mounted shooting and improve user experience.

[0006] In a first aspect, embodiments of the present invention provide a vehicle-mounted photography method, the method comprising:

[0007] Obtain at least one interactive behavior information of users inside the vehicle;

[0008] When the at least one interactive behavior information is a preset shooting interactive behavior, the current driving condition information of the vehicle and the user's facial information inside the vehicle are obtained.

[0009] The user's shooting intention is determined based on the driving condition information and the user's facial information;

[0010] When the shooting intention is to take a picture, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle.

[0011] The technical solution of this invention first acquires at least one interactive behavior information of the user inside the vehicle, which can capture the user's potential shooting intention in real time, reduce user waiting time, and provide data support for subsequent decision-making, thereby improving operation response speed and user satisfaction. Simultaneously, the parallel acquisition mechanism of multimodal interactive behavior information is compatible with diverse input methods, meeting the usage habits and preferences of different users, further enhancing the flexibility and inclusiveness of the interactive experience. Next, when at least one interactive behavior information is a preset shooting interaction behavior, the current vehicle driving condition information and the user's facial information inside the vehicle are acquired, providing a data basis for subsequent secondary judgment of the user's shooting intention. Then, the user's shooting intention is determined based on the driving condition information and the user's facial information, which not only more accurately identifies the user's intention, reduces the accidental touch rate, and improves the user experience, but also effectively ensures driving safety. Finally, when the shooting intention is to take a picture, the vehicle-mounted camera is controlled to capture images of the current vehicle environment, which reduces accidental touches during vehicle-mounted shooting and allows for timely control of the vehicle-mounted camera to capture images, thereby meeting the user's shooting needs and improving the user experience. Therefore, the technical solution of this invention solves the problem of easy accidental triggering in the prior art.

[0012] Secondly, embodiments of the present invention also provide a vehicle-mounted camera device, the device comprising:

[0013] The first acquisition module is used to acquire at least one interactive behavior information of the user in the vehicle.

[0014] The second acquisition module is used to acquire the current vehicle's driving condition information and the user's facial information inside the vehicle when the at least one interactive behavior information is a preset shooting interactive behavior.

[0015] The determination module is used to determine the user's shooting intention based on the driving condition information and the user's facial information;

[0016] The shooting module is used to control the vehicle-mounted camera to capture images of the current environment of the vehicle when the shooting intention is to take a picture.

[0017] Thirdly, embodiments of the present invention also provide a vehicle, the vehicle comprising:

[0018] At least one processor; and a memory communicatively connected to said at least one processor;

[0019] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the vehicle-mounted shooting method according to any embodiment of the present invention.

[0020] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, characterized in that the computer-executable instructions, when executed by a computer processor, implement the vehicle-mounted shooting method described in any embodiment of the present invention.

[0021] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the vehicle-mounted camera device, or it may be packaged separately from the processor of the vehicle-mounted camera device; this application does not impose any limitations on this.

[0022] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0023] In this application, the name of the aforementioned vehicle-mounted camera does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0024] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a vehicle-mounted photography method provided in an embodiment of the present invention;

[0027] Figure 2 A flowchart illustrating another vehicle-mounted photography method provided in an embodiment of the present invention;

[0028] Figure 3 This is a schematic diagram of the structure of a vehicle-mounted shooting device provided in an embodiment of the present invention;

[0029] Figure 4 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0031] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0032] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0033] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0034] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, embodiments and features in the embodiments of the present invention can be combined with each other without conflict.

[0035] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] Figure 1This is a flowchart illustrating a vehicle-mounted shooting method provided in an embodiment of the present invention. This embodiment is applicable to reducing shooting errors caused by accidental triggering of user commands during driving. The method can be executed by a vehicle-mounted shooting device, which can be implemented in software and / or hardware. For example, the device can be a vehicle. (Reference) Figure 1 The vehicle-mounted shooting method in this embodiment specifically includes the following steps:

[0038] Step 110: Obtain at least one interactive behavior information of the user inside the vehicle.

[0039] Specifically, in-vehicle users refer to individuals within the vehicle's interior space who may interact with the vehicle, including drivers and passengers. Interaction behavior information refers to behavioral data generated when in-vehicle users interact with the in-vehicle system, used to represent user intentions. For example, interaction behavior information can include voice commands and gestures.

[0040] In practice, at least one type of interactive behavior information of the user in the vehicle can be obtained through voice sensors (such as microphone arrays) and vision sensors (such as cameras) installed in the vehicle.

[0041] In this embodiment, the above steps can capture the user's potential shooting intentions in real time, reducing user waiting time and providing data support for subsequent decision-making, thereby improving operation response speed and user satisfaction. Simultaneously, the parallel acquisition mechanism of multimodal interactive behavior information is compatible with diverse input methods, meeting the usage habits and preferences of different users, further optimizing the flexibility and inclusivity of the interactive experience.

[0042] Step 120: When at least one interactive behavior information is a preset shooting interactive behavior, obtain the current vehicle driving condition information and the user's facial information inside the vehicle.

[0043] Specifically, preset shooting interaction behaviors refer to specific interactive behaviors that are pre-set according to actual conditions or needs to trigger the vehicle's shooting function. For example, preset shooting interaction behaviors may include preset shooting commands (such as "shoot," "take a picture," "photograph," etc.) and preset shooting gestures (such as a thumbs-up gesture, a gesture pointing to the roof, etc.). Driving condition information refers to a set of parameters characterizing the vehicle's current operating state. For example, driving condition information may include driving status information, road condition information, and driving environment information. Among them, driving status information refers to information related to the vehicle's current operating state, such as vehicle speed, acceleration, engine speed, battery charge, and / or the distance between the vehicle and obstacles ahead. Road condition information refers to information on road conditions and traffic conditions along the vehicle's driving route, such as real-time traffic flow, road closures, and / or construction. Driving environment information refers to environmental information around the vehicle, such as weather conditions and / or lighting conditions. User facial information refers to user facial feature data collected through the vehicle's onboard camera, used to assist in determining the shooting intention.

[0044] In practice, after obtaining the interaction behavior information, the corresponding processing model can be automatically called according to the information type of the interaction behavior information. For example, when the interaction behavior information is detected as a speech signal, speech recognition and understanding models such as Transformer-Transducer, Conformer, GMM-HMM or BERT-based can be used to first convert the speech signal into text, and then parse the semantic content to identify specific behavioral commands such as "take a picture" and "cancel". If the collected interaction behavior information is a gesture, the gesture recognition model such as YOLO-NAS and Transformer-CNN can be used to analyze the collected data and determine the gesture type, such as "give a thumbs up" or "point to the roof of the car".

[0045] After processing the interactive behavior information, the system enters the preset behavior matching stage. Specifically, the identified behavioral commands are compared one by one with preset shooting interactive behaviors. If a match is found, the system uses devices deployed on the vehicle, such as accelerometers, speed sensors, wheel speed sensors, steering wheel angle sensors, rain sensors, and cameras, to acquire the current vehicle's driving condition information and the facial information of the user inside the vehicle. For example, when the identified command matches a preset photo-taking command, and / or the gesture is consistent with a preset photo-taking gesture, the data acquisition process is initiated to acquire the current vehicle's driving condition information and the user's facial information.

[0046] Optionally, to further improve the accuracy of capturing intent recognition, when multiple users are present in the vehicle, a user identity association strategy can be employed to obtain user facial information. Specifically, after acquiring at least one interactive behavior information, the target user triggering the interactive behavior can be accurately located through voiceprint features in voice commands, spatial coordinates of gesture operations, or multimodal information fusion. For example, if a "take a photo" voice command is detected, the user issuing the command can be identified through voiceprint recognition technology; if a gesture is captured, the corresponding individual user can be determined based on the spatial coordinates of the gesture in the camera image. Subsequently, if at least one interactive behavior information is a preset capturing interaction behavior, the current vehicle driving condition information and the target user's facial information can be acquired.

[0047] In this embodiment, the above steps provide a data foundation for subsequent secondary judgment of the user's shooting intention.

[0048] Step 130: Determine the user's shooting intention based on driving condition information and user facial information.

[0049] Specifically, the shooting intent refers to whether the user inside the vehicle wishes to trigger the in-vehicle shooting function, as determined based on driving condition information and the user's facial information.

[0050] In practice, before determining the user's shooting intention based on driving condition information and facial information, a large amount of driving condition information can be collected first. Then, deep learning algorithms can be used to train the collected data to build a predictive driving condition model. Afterwards, by inputting real-time driving condition information, the current driving condition of the vehicle can be determined. When the driving condition is unsafe, a preset reminder method (such as voice reminder) can be used to remind the user that the current driving state is not suitable for shooting, and the shooting function is temporarily disabled. When the driving condition is safe, feature extraction is performed on the user's facial information to obtain the user's facial features; the user's facial features are then matched with preset shooting facial features to obtain the matching result; if the matching result is a match, the user's shooting intention is determined to be shooting.

[0051] In this embodiment, the above steps not only enable more accurate determination of the user's shooting intention, reduce accidental touch rate, and improve user experience, but also effectively ensure driving safety.

[0052] Step 140: When the shooting intention is to take a picture, control the vehicle-mounted camera to capture images of the current environment of the vehicle.

[0053] Specifically, an in-vehicle camera refers to an image acquisition device installed inside a vehicle (such as the center console, roof, rearview mirror, etc.) or outside the vehicle (such as the windshield, doors, trunk, roof, etc.) to capture images of the vehicle's environment or interior conditions. The image of the current vehicle environment refers to image data captured by the in-vehicle camera that reflects the current surrounding (or interior) environment of the vehicle.

[0054] In practice, when the user's intention to take a picture is determined, the shooting scene can first be determined based on the acquired interaction behavior information. Specifically, if the interaction behavior information includes commands such as "selfie" or "inside the car," or a gesture indicating "pointing inside the car," the shooting scene is determined to be an in-car scene; if the interaction behavior information includes commands such as "scenery," "road conditions," or "outside the window," or a gesture indicating "pointing outside the car," the shooting scene is determined to be an out-of-car scene; if the scene cannot be determined, a default scene (which covers both inside and outside the car) is used. Subsequently, the camera corresponding to the determined shooting scene is activated to obtain the initial camera. Then, based on the acquired user facial information, the gaze direction is analyzed, and the target camera is obtained by filtering from the initial camera according to the gaze direction. Then, the shooting parameters are determined by combining driving condition information (such as vehicle speed and light sensor data) (e.g., increasing sensitivity when driving at night and enabling high dynamic range imaging under strong light). Finally, the target camera is controlled to capture images of the current vehicle environment according to the finally determined parameters.

[0055] In this embodiment, the above steps can reduce accidental touches during vehicle-mounted shooting and enable timely control of the vehicle-mounted camera to capture images, thereby meeting the user's shooting needs and improving the user experience.

[0056] The vehicle-mounted shooting method provided in this invention first acquires at least one interactive behavior information of the user inside the vehicle, which can capture the user's potential shooting intention in real time, reduce user waiting time, and provide data support for subsequent decision-making, thereby improving operation response speed and user satisfaction. Simultaneously, the parallel acquisition mechanism of multimodal interactive behavior information is compatible with diverse input methods, meeting the usage habits and preferences of different users, further enhancing the flexibility and inclusiveness of the interactive experience. Next, when at least one interactive behavior information is a preset shooting interaction behavior, the current vehicle driving condition information and the user's facial information are acquired, providing a data basis for subsequent secondary judgment of the user's shooting intention. Then, the user's shooting intention is determined based on the driving condition information and the user's facial information, which not only more accurately identifies the user's intention, reduces the accidental touch rate, and improves the user experience, but also effectively ensures driving safety. Finally, when the shooting intention is to shoot, the vehicle-mounted camera is controlled to capture images of the current vehicle environment, which reduces accidental touches during vehicle-mounted shooting and allows for timely control of the vehicle-mounted camera to capture images, thereby meeting the user's shooting needs and improving the user experience. Therefore, the technical solution of this invention solves the problem of easy accidental triggering in the prior art.

[0057] Figure 2 A flowchart illustrating another vehicle-mounted photography method provided by an embodiment of the present invention is provided. This embodiment is a specific implementation based on the above embodiments. In this embodiment, the method may further include:

[0058] Step 210: Obtain at least one interactive behavior information of the user in the vehicle.

[0059] Step 211: Determine whether there is at least one interactive behavior information that is a preset shooting interactive behavior.

[0060] If it exists, proceed to step 212; if it does not exist, proceed to step 210.

[0061] In practice, after obtaining at least one interactive behavior information of the user inside the vehicle, the corresponding processing model (such as a speech recognition and understanding model, gesture recognition model, etc.) can be automatically invoked based on the information type of the interactive behavior information to determine the behavior command corresponding to the obtained interactive behavior information. Then, the recognized behavior command is compared one by one with the preset shooting interactive behavior. If a match is found, it is determined that at least one interactive behavior information exists as a preset shooting interactive behavior. At this time, the current vehicle driving condition information and the user's facial information can be obtained for secondary analysis of the user's shooting intention. If no match is found, it is determined that no interactive behavior information exists as a preset shooting interactive behavior. At this time, at least one interactive behavior information of the user inside the vehicle can be obtained again to determine whether a preset shooting interactive behavior exists.

[0062] In this embodiment, the above steps can quickly and accurately identify the user's true shooting intention, avoid the system making misjudgments of non-shooting-related interactive behaviors, reduce invalid operations, improve the accuracy of intention recognition, and provide a reliable basis for subsequent shooting processes.

[0063] Step 212: Obtain the current vehicle's driving condition information and the facial information of the users inside the vehicle.

[0064] Step 213: Determine the user's shooting intention based on driving condition information and user facial information.

[0065] Optional, driving condition information includes driving environment information.

[0066] Further, step 213 may specifically include: determining the current driving sight distance based on driving environment information; determining whether the current driving sight distance is greater than the preset driving sight distance; if the current driving sight distance is greater than the preset driving sight distance, then inputting the user's facial information into the pre-trained intent determination model to obtain the user's shooting intent.

[0067] Specifically, sight distance refers to the maximum distance at which a driver can clearly observe the road or objects ahead while the vehicle is in motion. Preset sight distance refers to a sight distance threshold set in advance based on actual conditions or needs, serving as a safety benchmark for shooting. A pre-trained intent determination model refers to a predictive model obtained through supervised training of a deep learning model using historical user facial expression data and its corresponding shooting intent labels.

[0068] In practical implementation, the radar line-of-sight distance (LAS) is first determined based on the radar sensors installed on the vehicle; this is the straight-line distance from the nearest obstacle detected by the radar. Then, a forward-facing camera (mounted at the front of the vehicle) is used with a deep learning model (such as DeepLabV3+) to identify the vanishing point of the road and the passable area. This is combined with monocular depth estimation to obtain the visual line-of-sight distance, i.e., the visible distance of the road. The minimum of these two values ​​is then determined as the base LAS. Next, the current weather information and day / night status are determined based on the driving environment information. The weather correction factor is obtained by querying a table of weather and meteorological correction factors based on the current weather information, and the day / night correction factor is obtained by querying a table of day / night and day / night correction factors based on the day / night status. Finally, the product of the base LAS, the meteorological correction factor, and the day / night correction factor is calculated to obtain the current driving LAS. The meteorological correction factor refers to the parameter that adjusts the base LAS based on different weather information. The day / night correction factor refers to the parameter that adjusts the base LAS based on different day and night lighting conditions.

[0069] Next, it determines whether the current driving visibility distance is greater than the preset driving visibility distance. If it is, the user's facial information is input into a pre-trained intent determination model to obtain the user's shooting intent. If it is not greater than the preset driving visibility distance, an insufficient visibility warning message can be displayed and the shooting function can be temporarily disabled.

[0070] It should be noted that the correspondence tables between weather and meteorological correction factors and between day and night correction factors were established in advance based on actual conditions or needs.

[0071] In this embodiment, the above steps can quickly assess the safety level of the current driving environment, ensuring that there is no conflict between the user's desire to take photos and driving safety. This effectively prevents the shooting function from distracting the driver's attention from the road, thus meeting the user's shooting needs while ensuring driving safety. Furthermore, shooting in a safe scenario with sufficient visibility not only significantly improves the quality of the captured images but also greatly reduces invalid shots, thereby creating a superior shooting experience for the user.

[0072] Furthermore, after determining whether the current driving visibility distance is greater than the preset driving visibility distance, the system also includes: if the current driving visibility distance is not greater than the preset driving visibility distance, displaying a visibility distance insufficient reminder message and a shooting confirmation request; receiving feedback information from the in-vehicle user regarding the shooting confirmation request; and, if the feedback information is a confirmation of shooting, controlling the in-vehicle camera to capture images of the current vehicle environment.

[0073] Specifically, the insufficient visibility warning message refers to the prompt displayed to the user inside the vehicle, informing them that the current visibility is insufficient, which may affect shooting safety or quality. The shooting confirmation request refers to the request displayed to the user asking whether they wish to continue shooting. The feedback message refers to the user's response to the shooting confirmation request; for example, the feedback message could be "Confirm Shooting" or "Cancel Shooting".

[0074] In practice, when the current driving distance is no greater than a preset driving distance, a insufficient visibility warning and a shooting confirmation request can be displayed on the in-vehicle display screen. Then, the feedback from the user in the vehicle regarding this request can be received through the in-vehicle display screen or voice recognition system. If the feedback is a confirmation to shoot, the in-vehicle camera is controlled to capture an image of the current environment of the vehicle. If the feedback is a cancellation to shoot or no confirmation, it is determined that the user has no intention to shoot. At this time, at least one interactive behavior information of the user in the vehicle can be obtained to identify whether there is a preset shooting interaction behavior.

[0075] In this embodiment, by taking the above steps, the user can have the right to choose when to shoot, thus avoiding user resistance caused by directly stopping the shooting, thereby enhancing the user's sense of participation and experience.

[0076] Optionally, driving condition information may also include driving status information and road condition information.

[0077] Further, step 213 may specifically include: determining a driving state coefficient based on driving state information, determining a road condition coefficient based on driving road condition information, and determining an environmental coefficient based on driving environment information; determining a shooting safety coefficient based on the driving state coefficient, road condition coefficient, and environmental coefficient; and determining the user's shooting intention based on the user's facial information if the shooting safety coefficient is greater than the preset safety coefficient.

[0078] Specifically, the driving state coefficient is a quantitative indicator calculated based on driving state information, used to measure the impact of vehicle driving state on shooting safety. The road condition coefficient is a quantitative indicator calculated based on road condition information, used to measure the impact of road conditions on shooting safety. The environment coefficient is a quantitative indicator calculated based on driving environment information, used to measure the impact of the external environment on shooting safety. The shooting safety coefficient is a comprehensive value calculated based on the driving state coefficient, road condition coefficient, and environment coefficient, used to assess the safety level of shooting under current driving conditions. The preset safety coefficient is a threshold value set in advance based on actual conditions or needs to determine shooting safety.

[0079] In practice, after obtaining driving status information, road condition information, and driving environment information, a suitable coefficient determination method can be selected based on the actual situation or requirements. For example, the coefficient determination method could be a multi-parameter weighted evaluation method or a fuzzy logic evaluation method. Then, the selected coefficient determination method is applied in conjunction with the driving status information, road condition information, and driving environment information to determine the driving status coefficient, road condition coefficient, and environment coefficient in sequence. Alternatively, the driving status information, road condition information, and driving environment information can be quantified separately based on preset quantization rules to obtain the driving status coefficient, road condition coefficient, and environment coefficient.

[0080] Then, the shooting safety factor is determined based on the driving state coefficient, road condition coefficient, and environmental coefficient. Specifically, weights can be assigned to these three coefficients—driving state coefficient, road condition coefficient, and environmental coefficient—based on historical data and expert opinions to reflect their relative importance to the shooting safety factor. The shooting safety factor can then be determined as: (Driving State Coefficient × Driving State Weight) + (Road Condition Coefficient × Road Condition Weight) + (Environmental Coefficient × Environmental Weight).

[0081] Finally, it is determined whether the shooting safety factor is greater than a preset safety factor. If it is, the user's shooting intention is determined based on their facial information. Specifically, the user's facial information can be input into a pre-trained intention determination model to obtain the user's shooting intention. If it is not greater than the preset safety factor, a shooting safety reminder message can be displayed and the shooting function can be temporarily disabled.

[0082] In this embodiment, the above steps enable a comprehensive and detailed assessment of the driving scenario, effectively adapting to complex and ever-changing road conditions, thereby better ensuring driving safety. Furthermore, it avoids misjudgment of user facial information and triggering of unnecessary shooting operations in unsafe scenarios, reducing ineffective computing resources and energy consumption, and improving efficiency.

[0083] Furthermore, determining the user's shooting intention based on the user's facial information includes: extracting features from the user's facial information to obtain the user's facial features; matching the user's facial features with preset shooting facial features to obtain a matching result; if the matching result is a match, then determining that the user's shooting intention is to take a picture.

[0084] Specifically, user facial features refer to key feature points or pattern data extracted from user facial information. Preset shooting facial features refer to facial features that are pre-set according to actual conditions or needs, representing the user's intention to be photographed.

[0085] In practice, multi-task convolutional neural networks, cascaded convolutional neural networks, spherical networks, curved network networks, and networks based on 3D deformable models can be used to extract features from the user's facial information. These user facial features are then matched with preset facial features to obtain a matching result. Specifically, a suitable similarity calculation method (such as cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient, etc.) can be selected based on the actual situation or needs. The selected similarity calculation method is then applied to calculate the similarity between the user's facial features and the preset facial features to obtain the target similarity. If the target similarity is greater than a preset similarity threshold, the matching result is considered a match, indicating that the user's intention to take a picture is to do so. If the target similarity is not greater than the preset threshold, the matching result is considered a mismatch, indicating that the user's intention to take a picture is not to do so.

[0086] In this embodiment, the above steps can improve the accuracy of determining the shooting intention, thereby reducing false triggering.

[0087] Step 214: Determine whether the shooting intention is to take a picture.

[0088] If it is for taking a picture, proceed to step 215; otherwise, proceed to step 210.

[0089] In practice, after determining the user's shooting intention, it can be determined whether the shooting intention is to take a picture. If it is to take a picture, the historical shooting information of the current vehicle is obtained to determine the target shooting parameters, thereby improving the shooting quality. If it is not to take a picture, at least one interaction behavior information of the user in the vehicle is obtained to determine whether there is a preset shooting interaction behavior.

[0090] In this embodiment, a basis is provided for subsequent secondary determination of whether to take a picture, thereby helping to reduce the occurrence of accidental touches.

[0091] Step 215: Obtain the historical shooting information of the current vehicle.

[0092] Specifically, historical shooting information refers to the parameters and scene data recorded when the current vehicle performed shooting operations in the past.

[0093] In practice, a database query statement can be used to query the database storing the vehicle's historical shooting information to obtain the current vehicle's historical shooting information.

[0094] In this embodiment, by acquiring the historical shooting information of the current vehicle, a data foundation is provided for subsequently determining the target shooting parameters.

[0095] Step 216: Based on the driving condition information, filter out the shooting parameters that match the driving condition information from the historical shooting information to obtain the target shooting parameters.

[0096] Specifically, shooting parameters refer to the various settings that control the working status of the vehicle-mounted camera. For example, shooting parameters include camera serial number, focal length, aperture, shutter speed, ISO, and shooting mode. Target shooting parameters refer to shooting parameters selected from historical shooting data based on driving condition information and matching the current driving conditions.

[0097] In practice, features of driving condition information can be extracted using methods such as vehicle speed feature extraction, acceleration feature extraction, vehicle attitude feature extraction, and geographic location feature extraction to obtain real-time driving feature vectors. The same methods are then used to extract features of driving condition information from historical footage to obtain historical driving feature vectors. Then, a suitable similarity calculation method (such as cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient, etc.) is selected based on actual needs to calculate the similarity between the two. If the similarity between the historical driving feature vector and the real-time driving feature vector exceeds a preset similarity threshold, the shooting parameters corresponding to the historical footage with the highest similarity are determined as the target shooting parameters; otherwise, the default shooting parameters are determined as the target shooting parameters. The default shooting parameters refer to the shooting configuration parameters set in advance according to actual conditions or needs.

[0098] In this embodiment, the above steps can dynamically adapt to driving scenarios, improve shooting quality and reliability, reduce manual intervention costs, and thus improve user experience.

[0099] Step 217: Control the vehicle-mounted camera to acquire images of the current environment of the vehicle based on the target shooting parameters.

[0100] In practice, after obtaining the target shooting parameters, the camera serial number can be extracted from them and the corresponding vehicle camera can be determined accordingly. Then, based on the specific parameters corresponding to each camera serial number in the target shooting parameters, the corresponding vehicle camera is controlled to collect images of the current vehicle environment.

[0101] In this embodiment, the above steps can provide users with personalized shooting services, thereby bringing users a better experience.

[0102] Furthermore, the method also includes: acquiring historical images of the current vehicle; analyzing the historical images to obtain personalized shooting scenes; matching the personalized shooting scenes with driving condition information to obtain scene matching results; displaying a personalized shooting suggestion request when the scene matching result is a match; receiving feedback from the in-vehicle user regarding the personalized shooting suggestion request; and controlling the on-board camera to acquire images of the current vehicle's environment when the feedback is in agreement.

[0103] Specifically, historically acquired images refer to various environmental image data collected by the vehicle in the past. Personalized shooting scenes refer to scenes that match the user's shooting preferences and habits, derived from the analysis of historically acquired images. Scene matching results refer to the results obtained by comparing and analyzing personalized shooting scenes with current driving condition information, used to determine whether the current driving condition matches a certain personalized shooting scene. Personalized shooting suggestion requests refer to the request sent to the user in the vehicle with shooting suggestions when the scene matching result is a match, asking the user whether they accept it.

[0104] In the specific implementation, data is first retrieved from a database storing historical images of the current vehicle. Then, features are extracted from the historical images using preset extraction methods (such as color feature extraction, texture feature extraction, shape feature extraction, spatial feature extraction, and deep learning feature extraction methods) to obtain historical scene features. Next, a clustering algorithm (such as the DBSCAN algorithm) is used to cluster the historical scene features, thereby generating personalized shooting scenes. Then, a suitable similarity calculation method (such as cosine similarity, Euclidean distance, Manhattan distance, and Pearson correlation coefficient) is selected based on actual needs to calculate the similarity between the personalized shooting scene and the driving condition information. If any personalized shooting scene has a similarity greater than a preset similarity value with the driving condition information, the scene matching result is determined to be a match. At this point, a personalized shooting suggestion request can be displayed on the in-vehicle display screen, and feedback from the in-vehicle user regarding the request can be received in real time. If the feedback is "agree," the in-vehicle camera is controlled to capture images of the current vehicle environment according to preset parameters. If the scene matching result is not a match, after obtaining new driving condition information, the step of matching the personalized shooting scene with the driving condition information and obtaining the scene matching result will be triggered.

[0105] In this embodiment, the above steps enable personalized services to be provided to users based on real-time scenarios. This process not only enhances the user's interactive experience but also increases user engagement, thereby comprehensively optimizing the user experience.

[0106] The vehicle-mounted shooting method provided in this invention first acquires at least one interactive behavior information of the user inside the vehicle. This allows for real-time capture of the user's potential shooting intentions, reducing user waiting time and providing data support for subsequent decision-making, thereby improving operation response speed and user satisfaction. Simultaneously, the parallel acquisition mechanism of multimodal interactive behavior information is compatible with diverse input methods, meeting the usage habits and preferences of different users, further enhancing the flexibility and inclusiveness of the interactive experience. Next, it determines whether at least one interactive behavior information constitutes a preset shooting interaction behavior. If not, it continues to acquire at least one interactive behavior information of the user inside the vehicle to determine whether a preset shooting interaction behavior exists. If it exists, it acquires the current vehicle driving condition information and the user's facial information, providing a data basis for subsequent secondary judgment of the user's shooting intention. Then, based on the driving condition information and the user's facial information, it determines the user's shooting intention, which not only more accurately identifies the user's intention, reduces the false touch rate, and improves the user experience, but also effectively ensures driving safety. Finally, it determines whether the shooting intention is to shoot. If not, it acquires at least one interactive behavior information of the user inside the vehicle to determine whether a preset shooting interaction behavior exists. If the system is taking a picture, it acquires the vehicle's historical shooting information, providing a data foundation for determining the target shooting parameters. Then, based on driving condition information, it filters the historical shooting information to select shooting parameters that match the driving condition information, obtaining the target shooting parameters. This improves the quality and reliability of subsequent shooting, reduces manual intervention costs, and further optimizes the user experience. Finally, based on the target shooting parameters, it controls the onboard camera to capture images of the vehicle's current environment. This not only reduces accidental triggering during onboard shooting and allows for timely control of the onboard camera's image acquisition, but also provides personalized shooting services for users, resulting in a better user experience. Therefore, the technical solution of this invention solves the problem of easy accidental triggering in the prior art.

[0107] Figure 3 This is a schematic diagram of a vehicle-mounted shooting device provided in an embodiment of the present invention. This device belongs to the same inventive concept as the vehicle-mounted shooting methods in the above embodiments. For details not described in detail in the embodiments of the vehicle-mounted shooting device, please refer to the embodiments of the above vehicle-mounted shooting methods.

[0108] like Figure 3 As shown, the device includes:

[0109] The first acquisition module 310 is used to acquire at least one interactive behavior information of the user in the vehicle.

[0110] The second acquisition module 320 is used to acquire the current vehicle's driving condition information and the user's facial information inside the vehicle when the at least one interactive behavior information is a preset shooting interactive behavior.

[0111] The determination module 330 is used to determine the user's shooting intention based on the driving condition information and the user's facial information;

[0112] The shooting module 340 is used to control the vehicle-mounted camera to capture images of the current environment of the vehicle when the shooting intention is to take a picture.

[0113] Based on the above embodiments, the driving condition information includes driving environment information, and the determination module 330 is specifically used for:

[0114] Determine the current driving visibility distance based on the driving environment information;

[0115] Determine whether the current driving visibility distance is greater than the preset driving visibility distance;

[0116] If the current driving visibility distance is greater than the preset driving visibility distance, the user's facial information is input into the pre-trained intent determination model to obtain the user's shooting intent.

[0117] Based on the above embodiments, the device further includes:

[0118] The feedback module is used to, after determining whether the current driving visibility distance is greater than the preset driving visibility distance, if the current driving visibility distance is not greater than the preset driving visibility distance, display a visibility distance insufficient reminder message and a shooting confirmation request; receive feedback information from the user in the vehicle regarding the shooting confirmation request; and, if the feedback information confirms shooting, control the vehicle-mounted camera to capture images of the current vehicle's environment.

[0119] Based on the above embodiments, the driving condition information also includes driving status information and road condition information. The determination module 330 is specifically used for:

[0120] The driving state coefficient is determined based on the driving state information, the road condition coefficient is determined based on the driving road condition information, and the environmental coefficient is determined based on the driving environment information.

[0121] The shooting safety factor is determined based on the driving state factor, the road condition factor, and the environmental factor.

[0122] If the shooting safety factor is greater than the preset safety factor, the user's shooting intention is determined based on the user's facial information.

[0123] Based on the above embodiments, the determining module 330 determines the user's shooting intention based on the user's facial information, including:

[0124] Feature extraction is performed on the user's facial information to obtain the user's facial features;

[0125] The user's facial features are matched with preset captured facial features to obtain a matching result;

[0126] If the matching result is a match, then the user's shooting intention is determined to be shooting.

[0127] Based on the above embodiments, the imaging module 340 controls the vehicle-mounted camera to acquire images of the current environment of the vehicle, including:

[0128] Obtain the historical image information of the current vehicle;

[0129] Based on the driving condition information, shooting parameters that match the driving condition information are selected from the historical shooting information to obtain the target shooting parameters;

[0130] Based on the target shooting parameters, the vehicle-mounted camera is controlled to acquire images of the current environment of the vehicle.

[0131] Based on the above embodiments, the device further includes:

[0132] The personalized prompt module is used to acquire historical images of the current vehicle; analyze the historical images to obtain personalized shooting scenes; match the personalized shooting scenes with the driving condition information to obtain scene matching results; if the scene matching result is a match, display a personalized shooting suggestion request; receive feedback from the in-vehicle user regarding the personalized shooting suggestion request; and if the feedback is in agreement, control the on-board camera to acquire images of the current vehicle's environment.

[0133] The vehicle-mounted shooting device provided in the embodiments of the present invention can execute the vehicle-mounted shooting method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0134] It is worth noting that in the embodiments of the above-mentioned vehicle-mounted shooting device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0135] Figure 4 This is a structural schematic diagram of a vehicle provided in an embodiment of the present invention. Figure 4 A block diagram of an exemplary vehicle 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The vehicle 4 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0136] like Figure 4As shown, vehicle 4 is represented in the form of a general-purpose computing electronic device. The components of vehicle 4 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0137] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0138] Vehicle 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by vehicle 4, including volatile and non-volatile media, removable and non-removable media.

[0139] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Vehicle 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0140] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0141] Vehicle 4 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with vehicle 4, and / or with any device that enables vehicle 4 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, vehicle 4 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 4 As shown, network adapter 20 communicates with other modules of vehicle 4 via bus 18. It should be understood that, although... Figure 4 As not shown in the diagram, other hardware and / or software modules may be used in conjunction with vehicle 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0142] Processing unit 16 executes various functional applications and page displays by running programs stored in system memory 28, such as implementing the vehicle-mounted shooting method provided in this embodiment of the invention, which includes:

[0143] Obtain at least one interactive behavior information of users inside the vehicle;

[0144] When the at least one interactive behavior information is a preset shooting interactive behavior, the current driving condition information of the vehicle and the user's facial information inside the vehicle are obtained.

[0145] The user's shooting intention is determined based on the driving condition information and the user's facial information;

[0146] When the shooting intention is to take a picture, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle.

[0147] Of course, those skilled in the art will understand that the processor can also implement the technical solutions of the vehicle-mounted shooting method provided in any embodiment of the present invention.

[0148] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements, for example, the vehicle-mounted photography method provided in this invention, the method comprising:

[0149] Obtain at least one interactive behavior information of users inside the vehicle;

[0150] When the at least one interactive behavior information is a preset shooting interactive behavior, the current driving condition information of the vehicle and the user's facial information inside the vehicle are obtained.

[0151] The user's shooting intention is determined based on the driving condition information and the user's facial information;

[0152] When the shooting intention is to take a picture, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle.

[0153] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0154] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0155] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0156] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0157] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0158] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant laws and regulations.

[0159] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A vehicle-mounted shooting method, characterized in that, The method includes: Obtain at least one interactive behavior information of users inside the vehicle; When the at least one interactive behavior information is a preset shooting interactive behavior, the current driving condition information of the vehicle and the user's facial information inside the vehicle are obtained. The user's shooting intention is determined based on the driving condition information and the user's facial information; When the shooting intention is to take a picture, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle. The driving condition information includes driving environment information. Based on the driving condition information and the user's facial information, the user's shooting intention is determined, including: The current driving sight distance is determined based on the driving environment information; it is determined whether the current driving sight distance is greater than the preset driving sight distance; if the current driving sight distance is greater than the preset driving sight distance, the user's facial information is input into the pre-trained intent determination model to obtain the user's shooting intent; wherein, the preset driving sight distance refers to the driving sight distance threshold that is preset according to the actual situation or needs and serves as a safe shooting benchmark. The driving condition information also includes driving status information and road condition information. Based on the driving condition information and the user's facial information, the user's shooting intention is determined, including: A driving state coefficient is determined based on the driving state information; a road condition coefficient is determined based on the road condition information; and an environmental coefficient is determined based on the driving environment information. A shooting safety coefficient is determined based on the driving state coefficient, the road condition coefficient, and the environmental coefficient. If the shooting safety coefficient is greater than a preset safety coefficient, the user's shooting intention is determined based on the user's facial information.

2. The vehicle-mounted shooting method according to claim 1, characterized in that, After determining whether the current driving visibility distance is greater than the preset driving visibility distance, the method further includes: If the current driving visibility distance is not greater than the preset driving visibility distance, a warning message indicating insufficient visibility and a request to confirm taking a picture will be displayed. Receive feedback information from the user inside the vehicle regarding the request for confirmation of the shooting; If the feedback information confirms the shooting, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle.

3. The vehicle-mounted shooting method according to claim 1, characterized in that, Determining the user's shooting intent based on the user's facial information includes: Feature extraction is performed on the user's facial information to obtain the user's facial features; The user's facial features are matched with preset captured facial features to obtain a matching result; If the matching result is a match, then the user's shooting intention is determined to be shooting.

4. The vehicle-mounted shooting method according to claim 1, characterized in that, Controlling the onboard camera to acquire images of the current environment of the vehicle includes: Obtain the historical image information of the current vehicle; Based on the driving condition information, shooting parameters that match the driving condition information are selected from the historical shooting information to obtain the target shooting parameters; Based on the target shooting parameters, the vehicle-mounted camera is controlled to acquire images of the current environment of the vehicle.

5. The vehicle-mounted shooting method according to claim 1, characterized in that, The method further includes: Acquire historical images of the current vehicle; analyze the historical images to obtain personalized shooting scenes; The personalized shooting scene is matched with the driving condition information to obtain the scene matching result; If the scene matching result is a match, a personalized shooting suggestion request will be displayed; Receive feedback from the in-vehicle user regarding the personalized shooting suggestion request; If the feedback indicates agreement, the vehicle-mounted camera is controlled to capture images of the current environment of the vehicle.

6. A vehicle-mounted camera, characterized in that, The device includes: The first acquisition module is used to acquire at least one interactive behavior information of the user in the vehicle. The second acquisition module is used to acquire the current vehicle's driving condition information and the user's facial information inside the vehicle when the at least one interactive behavior information is a preset shooting interactive behavior. The determination module is used to determine the user's shooting intention based on the driving condition information and the user's facial information; The shooting module is used to control the vehicle-mounted camera to capture images of the current environment of the vehicle when the shooting intention is to take a picture; The driving condition information includes driving environment information. The determination module is specifically used to determine the current driving sight distance based on the driving environment information; determine whether the current driving sight distance is greater than the preset driving sight distance; if the current driving sight distance is greater than the preset driving sight distance, then the user's facial information is input into the pre-trained intent determination model to obtain the user's shooting intent; wherein, the preset driving sight distance refers to the driving sight distance threshold that is preset according to the actual situation or needs and serves as a safe shooting benchmark. The driving condition information also includes driving status information and road condition information. The determination module is further used to determine a driving status coefficient based on the driving status information, a road condition coefficient based on the road condition information, and an environmental coefficient based on the driving environment information; determine a shooting safety coefficient based on the driving status coefficient, the road condition coefficient, and the environmental coefficient; and determine the user's shooting intention based on the user's facial information if the shooting safety coefficient is greater than a preset safety coefficient.

7. A vehicle, characterized in that, The vehicles include: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle-mounted shooting method according to any one of claims 1-5.

8. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the vehicle-mounted photography method according to any one of claims 1-5.

Images