Photographing control method, photographing control apparatus, and storage medium

Abstract

The application relates to a photographing control method, a photographing control device and a storage medium. The method is applied to a terminal, the terminal is provided with a holder, a camera and an audio output device, and the method comprises the following steps: controlling the holder to drive the camera to move along a preset scanning track to collect a preview image containing a user; performing user posture analysis on the collected preview image to obtain a posture analysis result; judging whether a preset photographing condition is met according to the posture analysis result; if the preset photographing condition is met, triggering the camera to photograph a target image containing the user; if the preset photographing condition is not met, adjusting device parameters and / or outputting audio guidance information according to the posture analysis result, and then re-collecting a preview image for the next round of user posture analysis; the device parameters comprise holder parameters and / or camera parameters; and the audio guidance information is used for indicating the adjustment of the user posture. The technical scheme provided by the application can improve the user photographing experience.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and in particular to a shooting control method, shooting control device and storage medium. Background Technology

[0002] With the continuous improvement of the camera capabilities of mobile terminals (such as smartphones), it has become a common practice for users to take photos with their mobile phones in daily life.

[0003] In existing technologies, shooting assistance solutions for ordinary users typically capture images using the terminal's built-in camera, analyze them, and then provide visual cues on the screen to assist the user in completing the shooting operation. However, this solution has a limited field of view during shooting, making it difficult to adapt to the needs of capturing images when the posture changes dynamically; in addition, the visual cues require the user to pay attention to the screen while posing, resulting in a relatively simple interaction method; furthermore, its analysis dimensions mainly focus on parameters such as image composition and lighting, with limited ability to recognize and optimize the user's own posture, thus affecting the user's photography experience. Summary of the Invention

[0004] In view of the above, this application provides a shooting control method, shooting control device, and storage medium to solve at least one problem existing in the background art.

[0005] In a first aspect, embodiments of this application provide a shooting control method, characterized in that it is applied to a terminal, the terminal being equipped with a gimbal, a camera, and an audio output device, the method comprising:

[0006] The gimbal is controlled to move the camera along a preset scanning trajectory to capture a preview image containing the user;

[0007] Perform user pose analysis on the acquired preview images to obtain pose analysis results;

[0008] Determine whether the preset shooting conditions are met based on the posture analysis results;

[0009] If the preset shooting conditions are met, the camera is triggered to capture a target image containing the user;

[0010] If the preset shooting conditions are not met, the device parameters will be adjusted and / or audio guidance information will be output according to the posture analysis results. After the adjustment, a preview image will be re-acquired for the next round of user posture analysis. The device parameters include gimbal parameters and / or camera parameters. The audio guidance information is used to instruct users to adjust their posture.

[0011] Secondly, embodiments of this application provide a shooting control device applied to a terminal, the terminal being equipped with a gimbal, a camera, and an audio output device. The shooting control device includes a processor, which is used to invoke instructions to execute the steps of the shooting control method as described in the first aspect.

[0012] Thirdly, embodiments of this application provide a storage medium on which an executable program is stored, wherein the executable program, when executed by a processor, implements the shooting control method as described in the first aspect.

[0013] This application provides a shooting control method, shooting control device, and storage medium. The method is applied to a terminal equipped with a gimbal, camera, and audio output device. By controlling the gimbal, the camera moves along a preset trajectory and captures preview images, allowing the camera's field of view to cover different framing ranges and reducing incomplete posture capture caused by fixed angles. User posture analysis is performed on the preview images, and the results determine whether shooting conditions are met. When shooting conditions are met, the terminal automatically triggers image capture, reducing the tediousness of repeated manual operations by the user. When shooting conditions are not met, the terminal can selectively adjust device parameters and / or output audio guidance information based on the posture analysis results, and re-capture images for the next round of analysis after each adjustment, forming a closed-loop iterative process. This closed-loop process enables the terminal to achieve more ideal shooting results after multiple automatic adjustments and guidance, thereby improving the user's shooting experience. Attached Figure Description

[0014] Figure 1 This is a schematic flowchart illustrating a shooting control method according to an embodiment of this application;

[0015] Figure 2 for Figure 1 The flowchart of step S101 is shown below;

[0016] Figure 3 for Figure 1 The flowchart of step S102 is shown below;

[0017] Figure 4 for Figure 1 The flowchart of step S105 is shown below;

[0018] Figure 5 This is a schematic flowchart illustrating a shooting control method according to another embodiment of this application. Detailed Implementation

[0019] To make the technical solution and beneficial effects of this application more apparent and understandable, a detailed description is provided below by listing specific embodiments. The accompanying drawings are not necessarily drawn to scale, and local features may be enlarged or reduced to more clearly show the details of the local features; unless otherwise defined, the technical and scientific terms used herein have the same meanings as those in the technical field to which this application pertains.

[0020] The embodiments described in this application are not exhaustive, but merely illustrative of some embodiments, and are not intended to limit the scope of protection of this application. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined with each other. For example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0021] In each embodiment of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0022] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0023] It should be noted that the information (including but not limited to user device information) and data (including but not limited to data used for analysis, stored data, and displayed data) collected in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and it does not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after the aforementioned user or organization has provided their consent.

[0024] In the field of mobile terminal photography, to help ordinary users lacking professional photography experience take ideal photos, an improved solution provides corresponding shooting assistance functions. This solution typically uses the built-in camera of the terminal (such as a smartphone) to capture images of the current shooting scene, and uses artificial intelligence models to identify and analyze parameters such as the composition ratio, subject position, and ambient light intensity. Then, it outputs visual guidance information to the user on the screen in the form of text prompts, guiding the user to manually adjust the shooting position or camera parameters.

[0025] However, the above-mentioned solutions have several shortcomings when applied to posed photography scenarios involving ordinary people. Firstly, the fixed perspective leads to incomplete pose capture. Relying on a smartphone's fixed camera for image acquisition limits the field of view to the camera's initial orientation, making it impossible to dynamically adjust based on changes in the user's posture. Secondly, there is a lack of device-coordinated control and real-time audio interaction. The camera is used only as a passive acquisition tool, and the AI ​​recognition results are only used to generate on-screen visual guidance, without forming a closed-loop control with any actuators. Furthermore, guidance relying solely on on-screen visual feedback is easily ignored by users in environments with strong outdoor light or screen glare, resulting in low effective communication of guidance information. Additionally, its analysis primarily focuses on parameters such as composition and lighting, with limited ability to recognize and optimize the user's own posture, thus impacting the user's photography experience.

[0026] This application provides a shooting control method applied to a terminal equipped with a gimbal, a camera, and an audio output device. The terminal includes, but is not limited to, smartphones, tablets, and cameras. The gimbal is a multi-axis mechanical gimbal installed inside or outside the terminal. The gimbal may employ a three-axis mechanical structure, supporting adjustments to the pitch angle (-45° to +45°) and horizontal rotation angle (±120°). The camera (e.g., the terminal's rear camera) is mounted on the gimbal, which can move the camera in multiple degrees of freedom. The audio output device is used to play audio signals, including but not limited to Bluetooth headphones and / or the terminal's built-in speaker. Furthermore, this method is applicable to various shooting scenarios requiring user posture adjustment assistance. For example, in selfie scenarios or when someone else is shooting, audio guidance can be used to provide posture adjustment suggestions to the subject. Alternatively, the gimbal can automatically adjust the camera's shooting angle based on the subject's posture changes, reducing reliance on manual adjustments by the photographer and improving shooting success rate and user experience.

[0027] Figure 1 This is a schematic flowchart illustrating a shooting control method according to an embodiment of this application. See also... Figure 1 The method includes the following steps:

[0028] S101: Controls the pan-tilt unit to move the camera along a preset scanning trajectory to capture a preview image containing the user.

[0029] In this embodiment, the terminal first activates the assisted posing mode. In this mode, the terminal drives the gimbal motor through control commands, causing the camera to move along a preset scanning trajectory. The preset scanning trajectory can be a movement path tailored to the posing scene, such as a continuous scan from low angle to high angle, from left to right, or a priority trajectory from full-body framing to half-body framing, and then to partial framing.

[0030] For example, during the gimbal movement, the camera is controlled to trigger acquisition when the gimbal reaches a preset viewing angle position, acquiring one or more preview images. Multiple preset viewing angles are defined in the preset scanning trajectory (e.g., -30° tilt, 0° horizontal, +20° elevation, etc.). The terminal drives the gimbal motor via control commands, causing the camera to move sequentially to each preset viewing angle. For example, during scanning, the gimbal movement can be step-by-step (i.e., pausing to acquire a preview image after reaching a preset angle position, then continuing to move), or it can be continuous movement with acquisition triggered when passing a preset viewing angle position. After acquisition, the gimbal continues to move to the next preset viewing angle. In this way, each preview image corresponds to a spatial viewing angle, facilitating subsequent analysis of the user's posture adaptation under that viewing angle.

[0031] As another example, during the movement of the gimbal, the camera can continuously capture image frames at a fixed frame rate (e.g., 30 frames / second) to obtain one or more preview images.

[0032] In this embodiment, the preview image captured by the camera is used for user posture analysis. Its resolution can be set to a lower resolution value (e.g., 640×480 or 1280×720) to reduce terminal power consumption and computing load.

[0033] S102: Perform user posture analysis on the acquired preview image and obtain the posture analysis results.

[0034] After acquiring the preview images, the terminal can perform user pose analysis on each frame or every few frames of the preview images. This analysis can be performed using a lightweight artificial intelligence model running locally on the terminal. The model can employ a lightweight architecture based on convolutional neural networks, accelerating inference on the terminal processor (such as an NPU or GPU) to meet the needs of real-time interaction. To improve analysis efficiency, the terminal can scale the preview images to a fixed size (such as 256×256) before inputting them into the model.

[0035] The lightweight artificial intelligence model can detect and identify key points of the human body in the preview image, and output parameters that represent the user's current posture state. These parameters together constitute the posture analysis results.

[0036] In some examples, the posture analysis results may include at least one of the following: posture type (e.g., standing, sitting, swaying), angle fit score (i.e., characterizing the degree of angle fit of the user in the preview image), and posture stiffness score (i.e., characterizing the stiffness of the user's posture). The angle fit score can be calculated by the model based on information such as the user's proportion, position, and orientation in the preview image; the posture stiffness score can be evaluated by the model based on biomechanical characteristics such as joint angles, limb extension, and center of gravity distribution in the preview image.

[0037] S103: Determine whether the preset shooting conditions are met based on the posture analysis results.

[0038] After acquiring the posture analysis results, the terminal compares these results with preset shooting conditions. The preset shooting conditions include pre-defined judgment rules used to determine whether the current user's posture and viewing angle meet the ideal shooting conditions.

[0039] In some examples, preset shooting conditions may include one or more preset thresholds, such as an angle fit threshold and a posture stiffness threshold. When the angle fit score in the posture analysis result is greater than or equal to the angle fit threshold, and the posture stiffness value is less than the posture stiffness threshold, the terminal determines that the preset shooting conditions are met; otherwise, it is determined that they are not met.

[0040] In other examples, the preset shooting conditions may also include a continuity requirement, that is, the pose analysis results of multiple consecutive preview images (such as 3 frames) must meet the above threshold conditions, which can reduce misjudgments caused by momentary shaking or accidental movements.

[0041] S104: If the preset shooting conditions are met, the camera is triggered to capture a target image containing the user.

[0042] When the preset shooting conditions are met, the terminal will trigger the camera to perform a shooting operation and obtain the target image. After the shooting is completed, the terminal can save the target image and notify the user that the shooting is complete through an audio output device or on-screen prompt.

[0043] In some examples, the preview image is obtained by the camera using a first resolution; the target image is obtained by the camera using a second resolution; wherein the first resolution is smaller than the second resolution.

[0044] In this embodiment, the target image can be captured at a resolution higher than that of the preview image (e.g., 4000×3000 or higher) to ensure the image quality of the final photo.

[0045] S105: If the preset shooting conditions are not met, adjust the device parameters and / or output audio guidance information according to the posture analysis results, and re-acquire the preview image after execution for the next round of user posture analysis; the device parameters include gimbal parameters and / or camera parameters; the audio guidance information is used to instruct on adjusting the user posture.

[0046] When the preset shooting conditions are not met, the terminal determines and performs at least one of the following operations based on the deviation of the specific parameters in the posture analysis results from the preset shooting conditions: adjusting device parameters or outputting audio guidance information. After performing the above-determined operations, the terminal will re-acquire preview images to obtain new preview images for the next round of posture analysis, thus forming a continuous feedback loop until the preset shooting conditions are met or the user manually exits the shooting process.

[0047] In some examples, adjusting the gimbal parameters includes controlling the gimbal to adjust the pitch angle and / or horizontal rotation angle within any one of the full-body framing range, half-body framing range, and partial framing range, so as to change the camera's viewing angle.

[0048] In some examples, adjusting camera parameters includes at least one of the following: adjusting the camera's zoom parameters to adapt to changes in the field of view during gimbal scanning; and adjusting the camera's exposure parameters to adapt to the current ambient light intensity. The exposure parameters may include ISO values, shutter speed, and / or exposure compensation values, etc.

[0049] In some examples, when outputting audio guidance information, the terminal can generate natural language guidance statements (such as "lower your left shoulder slightly" or "turn your body slightly to the right") based on the posture analysis results, and play them to the user in real time through an audio output device (such as a Bluetooth headset or a built-in speaker).

[0050] It should be noted that the terminal can choose to adjust only device parameters, output only audio guidance, or perform both in parallel, based on the optimization directions suggested by the posture analysis results. For example, when the angle adaptation is poor but the user's posture is natural, only the gimbal and camera parameters can be adjusted to actively adapt to the user's current posture. When the user's posture is stiff but the viewing angle is suitable, only audio guidance can be output to guide the user to adjust their posture. When both need optimization, both device parameters and audio guidance can be adjusted simultaneously to combine proactive device adaptation with proactive user adjustment, thereby optimizing the overall shooting effect.

[0051] In the shooting control method provided in this embodiment, the camera is moved along a preset trajectory by controlling the gimbal to capture preview images. This allows the camera's field of view to cover different framing ranges, reducing incomplete posture capture caused by a fixed perspective. User posture analysis is performed on the preview images, and the results are used to determine whether shooting conditions are met. When shooting conditions are met, the terminal automatically triggers image capture, reducing the tediousness of repeated manual operations by the user. When shooting conditions are not met, the terminal can selectively adjust device parameters and / or output audio guidance information based on the posture analysis results. After each adjustment, images are recaptured for the next round of analysis, forming a closed-loop iterative process. This closed-loop process enables the terminal to achieve more ideal shooting results after multiple automatic adjustments and guidance, thereby improving the user's shooting experience.

[0052] In some embodiments, such as Figure 2 As shown, in step S101 above, the control of the pan-tilt unit to move the camera along a preset scanning trajectory to acquire a preview image containing the user may include:

[0053] S1011: Control the gimbal to drive the camera to scan in sequence according to the full-body view, half-body view, and partial view, and capture the first preview image within each view to determine the user's target view.

[0054] S1012: Control the gimbal to move the camera within the target field of view to a preset viewing angle, so as to trigger the acquisition of a second preview image for user posture analysis at the preset viewing angle.

[0055] In this embodiment, different gimbal postures correspond to different framing ranges. Specifically, the correspondence between the two can be established through a mapping table. For example, the gimbal posture corresponding to the full-body framing range can be a downward angle of -15° and a horizontal angle of 0°. Under this perspective, the image can fully present the user's overall outline from head to toe. The gimbal posture corresponding to the half-body framing range can be a downward angle of -5° and a horizontal angle of 0°. Under this perspective, the image can present the user's upper body and hand gestures. The gimbal posture corresponding to the partial framing range can be a horizontal angle of 0° and the zoom magnification can be increased to a preset magnification. Under this perspective, the image can capture the user's facial expressions or hand details.

[0056] The terminal controls the gimbal to move the camera sequentially to preset viewing positions for full-body, half-body, and partial framing, capturing one or more first preview images from each viewpoint. The gimbal's movement between the preset views is continuous, and the speed can be set according to actual needs; no specific limit is set here.

[0057] The terminal can perform human detection on each captured image frame to determine whether the user's limbs are complete and whether the subject is located within a reasonable area of ​​the frame in each framing range, thus determining the target framing range. For example, if the user extends both arms, and both arms are fully visible in the full-body framing image, but the arms extend beyond the frame boundary in the half-body or partial framing image, then the full-body framing range is determined as the target framing range. If the user mainly displays facial expressions, and the user's face is located in the upper-center area of ​​the frame in the half-body framing image, but the face fills the frame in the partial framing image, then the terminal determines the half-body framing range as the target framing range.

[0058] After determining the target framing range, the terminal controls the gimbal to move the camera within the target framing range to a preset viewing angle, and triggers the acquisition of a second preview image at the preset viewing angle for subsequent user posture analysis.

[0059] It should be noted that after acquiring the second preview image, the terminal controls the gimbal to remain at the preset viewing angle position, in order to wait for parameter adjustment commands that may be issued after the posture analysis is completed.

[0060] In this embodiment, by acquiring the first preview image within each framing range, the target framing range corresponding to the user is determined. The terminal can quickly determine the appropriate framing range for the user based on the user's actual posture, and acquire the preview image from the corresponding viewpoint within the framing range, thereby providing more targeted image data for subsequent user posture analysis.

[0061] In some embodiments, such as Figure 3 As shown, in step S102 above, the step of performing user pose analysis on the preview image and obtaining the pose analysis results may include:

[0062] S1021: Input the preview image into the pose detection model, and output the pose type, the angle fit score of the user in the preview image, and the user's pose stiffness value through the pose detection model;

[0063] S1022: Generate posture analysis results based on posture type, angle fit score, and posture stiffness score.

[0064] In this embodiment, the attitude detection model is a lightweight attitude detection model, which is trained and deployed on the terminal for operation.

[0065] In some examples, the pose detection model can be built based on the YOLOv8 network (a deep learning-based object detection network). This model uses a convolutional neural network-based backbone as a feature extractor. The input layer receives a scaled and normalized preview image, and the intermediate layers extract high-level semantic features from the image through multiple convolutional and pooling operations. Internally, the model performs multi-task processing on the extracted features, outputting three sets of data. The first set is the pose type classification result; the model outputs the confidence scores for multiple categories, and the category with the highest confidence score is taken as the current pose type. The second set is the angle fit score, obtained through end-to-end inference from the model, representing the degree of angle fit between the user and the preview image. A higher score indicates that the user's position, proportion, and orientation in the image are more reasonable. The third set is the pose stiffness score, also obtained through end-to-end inference from the model, representing the stiffness of the user's pose. A higher score indicates a stiffer and more unnatural pose.

[0066] In some examples, the model first performs keypoint detection, identifying the positions of multiple key joints in the human body, such as the shoulder, elbow, wrist, hip, knee, and ankle. Based on the coordinates of these keypoints, the model further calculates features such as joint angles, limb extension, and center of gravity distribution. For example, the angle formed by the three keypoints at the elbow joint determines whether the arm is excessively bent or extended; the height difference between the left and right shoulder keypoints determines whether the shoulder is level; and the angle between the central axis formed by the hip and shoulder keypoints and the vertical direction determines whether the body is tilted. Based on these calculated features, the model's output branches generate posture type classification results, angle fit scores, and posture stiffness scores, respectively.

[0067] To enable the model to adapt to the pose recognition requirements of different shooting scenarios, a scenario-based pose database covering various subdivided poses such as standing, sitting, and dynamic posing can be used during the model training phase. The various output branches can be optimized simultaneously through multi-task learning.

[0068] In some examples, the terminal can obtain stiffness parameters of the user's posture from the output of the posture detection model. For instance, in addition to outputting the stiffness level of the posture, the posture detection model can also output the coordinate positions of key joints in the human body and the angle values ​​of each joint. By analyzing this data, the terminal can identify specific areas with stiffness problems, such as an excessively small elbow angle or an excessively large spinal tilt angle. These stiffness parameters can be used as a basis for generating audio guidance information.

[0069] In this embodiment, by outputting multi-dimensional quantitative evaluation indicators through the posture detection model, the terminal can accurately evaluate the user's current posture state from multiple dimensions such as posture type, composition adaptability, and posture stiffness, thereby providing reliable data basis for subsequent shooting condition judgment and determination of differentiated adjustment strategies.

[0070] In some embodiments, step S104 above, which involves triggering the camera to capture a target image containing the user if the preset shooting conditions are met, may include:

[0071] If the pose analysis results of each frame of the preview image continuously acquired under the same preset viewpoint meet the preset shooting conditions, the preset viewpoint is used as the optimal viewpoint to trigger the camera to capture the target image.

[0072] Here, the terminal continuously captures multiple frames of preview images from each preset viewing angle of the gimbal. For example, if the gimbal is currently positioned at a frontal horizontal view, the camera continuously captures preview images at a preset frame rate. The terminal performs posture analysis on each frame of the preview image and records the angle adaptation score and posture stiffness value for each frame.

[0073] For example, the preset shooting conditions can be set to an angle adaptation score greater than a first threshold and a posture stiffness score less than a second threshold. When the posture analysis results of N consecutive preview images (e.g., N is 3) under the preset viewpoint all meet the preset shooting conditions, the terminal uses the preset viewpoint as the optimal viewpoint and triggers the camera to perform shooting. During shooting, the camera can automatically switch to high-resolution mode to capture the target image.

[0074] In this embodiment, by requiring the posture analysis results of multiple consecutive preview images to meet preset shooting conditions before triggering shooting, the terminal can trigger shooting when the user's posture is stable rather than momentarily or accidentally meeting the conditions. Since single-frame analysis results can be affected by factors such as momentary user tremors, subtle facial expressions, or fluctuations in ambient light, relying solely on a single frame can easily lead to false triggers. However, if multiple consecutive frames meet the conditions, it indicates that the user's posture has been consistently stable within the ideal range. In this case, the target image obtained by triggering shooting at this time exhibits high reliability in terms of the naturalness of the user's posture and the adaptability of the angle, thereby improving the success rate of capture and the quality of the final photo.

[0075] In some embodiments, such as Figure 4 As shown, in step S105 above, if the preset shooting conditions are not met, the device parameters are adjusted and / or audio guidance information is output based on the posture analysis results. After execution, a preview image is re-acquired for the next round of user posture analysis, which may include:

[0076] S1051: If the preset shooting conditions are not met, the target mode is determined based on the comparison between the posture analysis results and the preset shooting conditions.

[0077] S1052: If the target mode is the device parameter adjustment mode, then adjust the device parameters and use the adjusted device parameters to control the pan-tilt unit to move the camera along the preset scanning trajectory in order to re-acquire the preview image;

[0078] S1053: If the target mode is audio guidance mode, output audio guidance information and control the gimbal to maintain the current posture and re-acquire the preview image;

[0079] S1054: If the target mode is parallel adjustment mode, adjust the device parameters and output audio guidance information synchronously. Use the adjusted device parameters to control the pan-tilt unit to drive the camera to move along the preset scanning trajectory in order to re-acquire the preview image.

[0080] In this embodiment, if the preset shooting conditions are not met, the terminal selects one of the following modes—device parameter adjustment mode, audio guidance mode, and parallel adjustment mode—based on the comparison between the posture analysis result and the preset shooting conditions, and performs the corresponding adjustment operation according to the selected mode.

[0081] For example, when only the angle fit score is below the threshold while the posture stiffness value meets the requirements, the terminal selects the device parameter adjustment mode. For instance, if the posture analysis result indicates that the user is leaning to the left in the image, the terminal controls the gimbal to rotate to the right by an appropriate angle, while simultaneously controlling the camera to appropriately increase the zoom level to center the user and ensure a reasonable proportion. No audio guidance is output during the adjustment process to avoid disturbing the user who has already assumed the correct posture. After the adjustment is complete, the adjusted device parameters are used to control the gimbal to move the camera along a preset scanning trajectory to re-acquire and preview the image.

[0082] For example, when only the posture stiffness value exceeds the threshold while the angle adaptation score meets the requirements, the terminal selects the audio guidance mode. For instance, if it detects that the user's shoulder height is inconsistent or the arm joint angle is too small, the terminal matches the corresponding guidance statement from the audio guidance library, plays it through Bluetooth headphones, and simultaneously controls the gimbal to maintain the current posture, avoiding device movement from interfering with the user's posture adjustment. A preview image can be recaptured within a preset time after the audio guidance information has finished playing.

[0083] For another example, when both the angle adaptation score and the posture stiffness score fail to meet the requirements, the terminal selects a parallel adjustment mode. For instance, if the posture analysis result indicates that the user's body is tilted to the right and to the left, the terminal controls the gimbal to rotate to the left to correct the viewing angle, while simultaneously playing an audio guide that says "slightly turn your body to the right to straighten it," ensuring that the device's adjustment and the user's adjustment are aligned with the same optimization target. After the adjustment is complete, the terminal controls the gimbal to move the camera along a preset scanning trajectory to re-acquire and preview the image.

[0084] In this way, the terminal can adopt an adaptive adjustment strategy for different types of posture problems, reduce unnecessary device movement or interference with the user, and improve the efficiency of shooting iteration adjustment.

[0085] In some embodiments, the posture analysis results include the user's angle fit score in the preview image and the user's posture stiffness value; the angle fit score represents the degree of angle fit of the user in the preview image; the posture stiffness value represents the degree of stiffness of the user's posture; the preset shooting conditions include a first preset threshold and a second preset threshold.

[0086] The terminal can quantitatively judge the rationality of the composition from the current perspective based on the angle adaptation score, in order to determine whether it is necessary to adjust the gimbal parameters or camera parameters to optimize the perspective. Angle adaptation refers to the degree of matching between the presentation of the user subject in the picture and the ideal composition standard from the current shooting perspective.

[0087] In this application, the degree of angle adaptation can be evaluated using at least one parameter: subject position, subject proportion, and subject orientation. Subject position refers to the distribution of the user subject within the frame; ideally, it should be located in the visual center of the image, avoiding deviation from the center. Subject proportion refers to the area occupied by the user subject within the frame; ideally, it should maintain an appropriate proportion, neither too small to make the subject unprominent nor too dense to fill the frame and lack a sense of space. Subject orientation refers to the angle of the user subject facing the camera from the front, side, or back; ideally, a suitable orientation should be chosen based on the shooting intention to reduce the obstruction of key parts or poor viewing angles caused by unfavorable orientation. When the above parameters are close to ideal, the degree of angle adaptation is high, and the corresponding angle adaptation score is also high; conversely, the angle adaptation score is low.

[0088] In this embodiment, the specific values ​​of the first preset threshold and the second preset threshold can be flexibly configured according to the shooting scene, user preferences, or historical data statistics results, and are not limited here. For example, the first preset threshold (i.e., the angle adaptation threshold) can be set to 75 points, that is, when the angle adaptation score reaches 75 points or above, it means that the composition under the current viewpoint meets the basic requirements; the second preset threshold (i.e., the posture stiffness threshold) can be set to 20 points, that is, when the posture stiffness value is below 20 points, it means that the user's posture naturalness is within an acceptable range.

[0089] In step S1051 above, the step of determining the target mode based on the comparison between the posture analysis result and the preset shooting conditions if the preset shooting conditions are not met may include:

[0090] When the angle adaptation score is less than the first preset threshold and the posture stiffness value is less than the second preset threshold, the target mode is determined to be the device parameter adjustment mode.

[0091] When the angle adaptation score is greater than or equal to the first preset threshold and the posture stiffness value is greater than or equal to the second preset threshold, the target mode is determined to be the guidance information output mode.

[0092] When the angle adaptation score is less than the first preset threshold and the posture stiffness score is greater than the second preset threshold, the target mode is determined to be the parallel adjustment mode.

[0093] In this embodiment, the terminal compares the angle adaptation score with a first preset threshold and the posture stiffness score with a second preset threshold, and determines the target mode based on the combination of the comparison results.

[0094] When the angle adaptation score is less than the first preset threshold and the posture stiffness score is less than the second preset threshold, it indicates that the user's posture is natural but the viewing angle is poor. At this time, the target mode is determined to be the device parameter adjustment mode.

[0095] When the angle adaptation score is greater than or equal to the first preset threshold and the posture stiffness score is greater than or equal to the second preset threshold, it indicates that the viewing angle is appropriate but the user's posture is stiff. At this time, the target mode is determined to be the audio guidance mode.

[0096] When the angle adaptation score is less than the first preset threshold and the posture stiffness score is greater than the second preset threshold, it indicates that both the viewpoint and posture need to be optimized. At this time, the target mode is determined to be the parallel adjustment mode.

[0097] When the angle adaptation score is greater than or equal to the first preset threshold and the posture stiffness score is less than the second preset threshold, the terminal determines that the preset shooting conditions are met, and at this time the camera is triggered to capture a target image containing the user.

[0098] In this embodiment, through the above-mentioned pattern determination based on dual-parameter thresholds, the terminal can accurately match and adjust strategies according to the current posture problem type, reducing the low adjustment efficiency caused by improper strategy selection.

[0099] In some embodiments, step S105 above may include: when the posture stiffness value in the posture analysis result exceeds a second preset threshold, obtaining the stiffness parameter corresponding to the user posture in the preview image, matching and generating the audio guidance information in the audio guidance library according to the stiffness parameter, converting the audio guidance information into an audio instruction, and playing the audio instruction according to the detected current ambient noise intensity.

[0100] In this embodiment, after the terminal detects that the posture stiffness value exceeds a second preset threshold, it can further obtain the stiffness parameters corresponding to the user's posture from the output of the posture detection model. Stiffness parameters include, but are not limited to, at least one of the following: angle values ​​of key joints in the human body, relative positional deviations of various limb parts, and tilt angles of the body's central axis. For example, the key point coordinates output by the model can be used to calculate specific values ​​such as the shoulder horizontal height difference, elbow flexion angle, the angle between the spine and the vertical direction, and the relative position of the wrist and shoulder.

[0101] The terminal can input stiffness parameters into the audio guidance generation module. This module has a built-in guidance statement library, which pre-stores guidance statements corresponding to various stiffness parameters. For example, if the stiffness parameter indicates an issue with inconsistent shoulder height, the statement library can store two statements: "Raise your left shoulder slightly" and "Lower your right shoulder slightly," selecting the appropriate direction of guidance based on the actual stiffness parameter. If the stiffness parameter indicates an issue with an excessively small elbow angle, it can match guidance statements such as "Relax your arms and let them hang naturally." The audio guidance generation module selects the corresponding guidance statement based on the currently identified stiffness parameter and synthesizes them into audio guidance information in natural language form. After generating the guidance text, the terminal calls a text-to-speech engine to convert it into audio commands.

[0102] To ensure that audio instructions are clearly received by users under different environmental conditions, the terminal can capture ambient audio through the microphone before playing the audio command, analyze the current ambient noise level, and adaptively adjust the playback volume of the audio command. After playing the audio command, the terminal recaptures the preview image for the next round of user posture analysis to evaluate the effect of the user adjusting their posture according to the instructions.

[0103] In this way, the terminal can generate targeted audio guidance based on rigid parameters, better guide users to adjust problematic body parts, and ensure that the guidance instructions can be clearly conveyed under different environmental conditions through adaptive volume adjustment, thereby improving the effectiveness of posture adjustment.

[0104] In some embodiments, the method may further include: controlling the execution time of adjusting device parameters and / or outputting audio guidance information based on the acquisition time of the preview image, so that the time deviation between the execution time and the acquisition time of the preview image is within a preset range.

[0105] In this embodiment, the terminal records the timestamp of the acquisition time of each preview image frame. After determining the adjustment operations to be performed based on the analysis results of a preview image frame, the terminal uses the acquisition time of that preview image frame as a reference to set the execution timing of each control command (such as gimbal movement commands, camera parameter adjustment commands, audio playback commands, etc.), ensuring that the time deviation between the actual execution time of gimbal parameter adjustment, camera parameter adjustment, audio guidance information playback, etc., and the acquisition time of the preview image is controlled to be no greater than a preset duration. Through this synchronization mechanism, control chaos caused by asynchrony between device adjustments and audio guidance can be suppressed, improving the effectiveness of closed-loop feedback and thus further enhancing the shooting experience.

[0106] In some embodiments, the terminal can execute a corresponding degradation strategy for abnormal scenarios that may occur during the shooting process.

[0107] For example, the audio output device includes a Bluetooth headset. When communication between the terminal and the Bluetooth headset is interrupted, the audio guidance information is switched to the terminal's speaker. Specifically, after detecting a Bluetooth connection interruption, the terminal can switch the audio guidance output channel to the built-in speaker to ensure that the user receives posture adjustment prompts.

[0108] For example, when the user posture analysis fails, the process returns to controlling the gimbal to move the camera along a preset scanning trajectory. Specifically, when multiple consecutive frames fail to output valid analysis results due to reasons such as insufficient light or severe limb obstruction, the terminal controls the gimbal to re-execute the initial scanning phase to attempt to restore normal posture recognition. If recognition still fails multiple times after resetting, the user can be informed via audio guidance to change the shooting environment or posture.

[0109] For example, when the gimbal malfunctions, the current gimbal posture is locked and the system switches to audio guidance mode, which outputs audio guidance information. Specifically, when a gimbal motor stops or a communication failure is detected, the terminal locks the current gimbal posture and switches to pure audio guidance mode, outputting posture adjustment guidance to the user only through the audio output device.

[0110] In this embodiment, through the above-mentioned anomaly handling mechanism, the terminal can effectively cope with various abnormal scenarios, improving the continuity of the shooting process and the availability of the system.

[0111] Next, we will further explain the shooting control method provided in this application with specific examples.

[0112] In one embodiment, such as Figure 5 As shown, the shooting control method may include the following steps:

[0113] S201: Activate AI Posing Assist Mode. Users can click the AI ​​Posing Function entry in the camera application, and the terminal will respond to the user's operation and activate the AI ​​Posing Assist Mode. In this mode, the terminal automatically wakes up the gimbal, rear camera, and audio output device, preparing for dynamic scanning and intelligent guidance.

[0114] S202: The gimbal initiates dynamic scanning according to a preset trajectory. The terminal controls the gimbal to move the camera along a preset scanning trajectory. For example, for a rear-facing camera, this trajectory can use a priority order of "full body → half body → partial" for the initial scan to preliminarily determine the suitable framing range for the user.

[0115] S203: Simultaneously wake up the camera and configure optimized parameters for posed shooting. While the gimbal starts scanning, the terminal wakes up the rear camera and configures basic parameters suitable for the posed shooting scenario. For example, the camera is set to wide-angle mode, autofocus is enabled, and exposure compensation is adjusted appropriately to ensure initial image quality. These parameters will be further adaptively adjusted during subsequent scans based on the framing and lighting conditions.

[0116] S204: The UI displays a pose image to the user. The terminal displays a preset pose reference image on the screen, providing the user with a preliminary posing suggestion. This image can be a common pose example built into the system, helping the user understand the desired pose direction in the current mode. In some examples, step S204 is optional.

[0117] S205: The gimbal moves to a key angle, triggering the rear camera to capture an image frame. The gimbal moves according to the scanning trajectory to a preset key angle (e.g., a downward angle of -30° for a full-body scan, a horizontal angle of 0° for a half-body scan, and an upward angle of +20° for a partial scan). When the gimbal reaches these key angles, a hardware synchronization signal triggers the rear camera to capture an image frame, obtaining a preview image from the current viewpoint.

[0118] S206: Binding Image Frames to Gimbal Attitude Data. The terminal binds the acquired image frames to the current gimbal attitude data (including pitch angle, horizontal rotation angle, zoom magnification, etc.) and writes this metadata into the image frames for subsequent AI analysis. In this way, each preview image frame corresponds to a clear spatial viewpoint, facilitating the analysis of the degree of adaptation to the user's posture from that viewpoint.

[0119] S207: Uses an edge AI model to identify the current posture and determine whether the preset shooting conditions are met.

[0120] The terminal inputs a preview image with gesture data into a locally deployed lightweight gesture detection model. The model outputs the gesture type, angle fit score, and gesture stiffness score. Based on these outputs, the terminal determines whether the current user's gesture is stiff and whether the viewpoint is appropriate, and decides on subsequent operation branches accordingly.

[0121] If the model identifies that the user's posture is natural and the angle adaptation meets the requirements (i.e., the composition under the current viewpoint meets the requirements), then proceed to step S208; if the model identifies that the user's posture is stiff and the angle adaptation meets the requirements, then proceed to step S209. If the model identifies that the angle adaptation does not meet the requirements and the user's posture is stiff, then proceed to step S211. If the model identifies that the angle adaptation does not meet the requirements but the user's posture is natural, then proceed to step S212.

[0122] S208: Trigger optimal angle shooting. At this time, the terminal controls the gimbal to fine-tune to the currently analyzed optimal angle and automatically switches to high-resolution shooting mode to capture the final target image. After shooting is completed, a prompt sound can be played or the user can be informed of the completion of shooting via audio, and then the AI ​​posing assistance mode ends.

[0123] S209: Generate personalized audio guidance. After step S209, proceed to step S210.

[0124] Based on the fine-grained deviation information output by the model (such as shoulder height difference, elbow angle, body tilt, etc.), the terminal matches and synthesizes corresponding guidance statements from the audio guidance library, such as "lower your right shoulder slightly and relax your arm a little." Then, it plays the instructions to the user in real time through Bluetooth headphones or speakers.

[0125] After hearing the audio instructions, the user adjusts their posture accordingly. During this process, the gimbal maintains its current posture to avoid interfering with the user's adjustments.

[0126] S210: Trigger the camera to capture image frames and return to step S206 to continue the loop.

[0127] After the user adjusts their posture, the terminal controls the gimbal to move to the key angle again (or continues to move along the scanning trajectory), re-captures the preview image, and performs AI recognition again. This process is repeated iteratively until the user's posture meets the preset shooting conditions, triggering shooting or the user manually exits.

[0128] S211: Adjust device parameters and output audio guidance synchronously. After step S211 is executed, return to step S205 to continue acquiring preview images.

[0129] If the model identifies that the angle adaptation does not meet the requirements and the user's posture is stiff, it indicates that both the current viewpoint and the user's posture need optimization. The terminal generates gimbal adjustment commands based on the angle adaptation deviation information output by the model (such as the user's subject being too far to the left or right, or too large or too small in proportion). For example, it controls the gimbal to rotate left or right by an appropriate angle, or controls the camera to adjust the zoom level to center the user's subject and ensure a reasonable proportion. Simultaneously, the terminal generates audio guidance statements based on the posture stiffness parameters output by the model (such as shoulder height difference, elbow angle, body tilt, etc.), such as "Slightly turn your body to the left to straighten, and at the same time, slightly lower your right shoulder." The terminal plays the audio guidance in real time through Bluetooth headphones or a speaker and executes the gimbal adjustment commands synchronously to ensure that the device's adjustment direction is consistent with the user's adjustment direction. After adjustment, the system returns to step S205 to continue acquiring preview images.

[0130] S212: Adjust device parameters. After step S212 is executed, return to step S205 to continue acquiring preview images.

[0131] If the model identifies that the angle adaptation does not meet the requirements but the user's posture is natural, it indicates that the current viewing angle is poor, but the user's posture itself is natural. The terminal only adjusts the device parameters and does not output audio guidance. The terminal generates gimbal adjustment instructions based on the angle adaptation deviation information output by the model, such as controlling the gimbal to rotate at an appropriate angle or adjusting the camera zoom to optimize the composition. No audio guidance is played during the adjustment process to avoid disturbing the user who has already assumed a pose. After the adjustment is completed, return to step S205 to continue acquiring preview images.

[0132] In summary, the shooting control method provided in this application, by controlling the gimbal to move the camera along a preset scanning trajectory, achieves dynamic image acquisition from multiple perspectives and framing ranges, avoiding the problem of incomplete posture capture caused by a fixed perspective. By analyzing the user's posture in the preview image, the user's current state can be quantitatively evaluated from multiple dimensions such as posture type, angle adaptability, and posture stiffness, providing an accurate data foundation for subsequent closed-loop adjustments. Based on this, according to the comparison between the posture analysis results and preset shooting conditions, device parameter adjustments and / or audio guidance output are selectively executed, forming a continuous closed-loop feedback mechanism. When only the perspective is poor, the device parameters are automatically adjusted to avoid disturbing the user who has already posed; when only the posture is stiff, audio guidance is output to guide the user to adjust their posture; when both need optimization, they are executed in parallel to ensure that device adjustments and user adjustments are coordinated and consistent. Finally, when multiple consecutive frames meet the preset shooting conditions, high-resolution shooting is automatically triggered, achieving intelligent capture of the optimal posture.

[0133] The various embodiments or implementation methods described in this specification are presented in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other.

[0134] In the various embodiments of the specification, some or all of the steps and their optional implementations can be arbitrarily combined with some or all of the steps in other embodiments, or arbitrarily combined with the optional implementations in other embodiments.

[0135] This application also provides a shooting control device for a terminal, wherein the terminal is equipped with a gimbal, a camera, and an audio output device. The shooting control device includes a processor, which is used to call instructions to execute the steps of the shooting control method provided in any of the foregoing embodiments.

[0136] This application also provides a storage medium, including an executable program stored thereon, which, when executed by a processor, implements the steps of the shooting control method provided in any of the foregoing embodiments.

[0137] For ease of understanding, the following focuses on explaining the terminology used in this embodiment:

[0138] In this application embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a Graphics Processing Unit (GPU) (which can be understood as a type of microprocessor), or a Digital Signal Processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconstructable. For example, the processor is a hardware circuit implemented using an Application-Specific Integrated Circuit (ASIC) or a Programmable Logic Device (PLD), such as an FPGA. In a reconstructable hardware circuit, the processor loads a configuration document, implementing a cyclical process of hardware circuit configuration. This can be understood as the processor loading instructions to implement the functions of some or all of the above units or modules in a cyclical process. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), a Deep Learning Processing Unit (DPU), etc.

[0139] The computer-readable storage medium provided in this embodiment can execute the shooting control method of the above embodiment. Its implementation principle and technical effect are similar to those of the above embodiment, and will not be described again here.

[0140] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0141] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in an electronic device or a host device.

[0142] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0143] The various embodiments or implementation methods described in this specification are presented in a progressive manner. Each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other.

[0144] In the description of this specification, references to "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A shooting control method, characterized in that, Applied to a terminal equipped with a gimbal, camera, and audio output device, the method includes: The gimbal is controlled to move the camera along a preset scanning trajectory to capture a preview image containing the user; Perform user pose analysis on the acquired preview images to obtain pose analysis results; Determine whether the preset shooting conditions are met based on the posture analysis results; If the preset shooting conditions are met, the camera is triggered to capture a target image containing the user; If the preset shooting conditions are not met, the device parameters will be adjusted and / or audio guidance information will be output according to the posture analysis results. After the adjustment, a preview image will be re-acquired for the next round of user posture analysis. The device parameters include gimbal parameters and / or camera parameters. The audio guidance information is used to instruct users to adjust their posture.

2. The shooting control method according to claim 1, characterized in that, The control of the pan-tilt unit to move the camera along a preset scanning trajectory to capture a preview image containing the user includes: The gimbal is controlled to drive the camera to scan in sequence according to the full-body view, half-body view, and partial view, and to capture the first preview image within each view to determine the target view corresponding to the user. The gimbal is controlled to move the camera within the target field of view to a preset viewing angle, thereby triggering the acquisition of a second preview image for user posture analysis at the preset viewing angle.

3. The shooting control method according to claim 1, characterized in that, If the preset shooting conditions are not met, the device parameters are adjusted and / or audio guidance information is output based on the posture analysis results. After the adjustment, a preview image is re-acquired for the next round of user posture analysis, including: If the preset shooting conditions are not met, the target mode is determined based on the comparison between the posture analysis results and the preset shooting conditions. If the target mode is the device parameter adjustment mode, then the device parameters are adjusted, and the adjusted device parameters are used to control the gimbal to move the camera along a preset scanning trajectory in order to re-acquire the preview image; If the target mode is audio guidance mode, then output audio guidance information and control the gimbal to maintain the current posture and re-acquire the preview image; If the target mode is the parallel adjustment mode, the device parameters are adjusted and audio guidance information is output synchronously. The adjusted device parameters are used to control the gimbal to move the camera along a preset scanning trajectory in order to re-acquire the preview image.

4. The shooting control method according to claim 3, characterized in that, The posture analysis results include the user's angle fit score in the preview image and the user's posture stiffness score; the angle fit score represents the degree of angle fit of the user in the preview image. The posture stiffness value represents the degree of stiffness in the user's posture; The preset shooting conditions include a first preset threshold and a second preset threshold; If the preset shooting conditions are not met, the target mode is determined based on the comparison between the posture analysis result and the preset shooting conditions, including: When the angle adaptation score is less than the first preset threshold and the posture stiffness value is less than the second preset threshold, the target mode is determined to be the device parameter adjustment mode. When the angle adaptation score is greater than or equal to the first preset threshold and the posture stiffness value is greater than or equal to the second preset threshold, the target mode is determined to be the guidance information output mode. When the angle adaptation score is less than the first preset threshold and the posture stiffness score is greater than the second preset threshold, the target mode is determined to be the parallel adjustment mode.

5. The shooting control method according to any one of claims 1 to 4, characterized in that, The step of performing user pose analysis on the preview image and obtaining pose analysis results includes: The preview image is input into the pose detection model, and the pose detection model outputs the pose type, the angle fit score of the user in the preview image, and the stiffness value of the user's pose. Based on the posture type, the angle fit score, and the posture stiffness score, a posture analysis result is generated.

6. The shooting control method according to claim 1, characterized in that, The output audio guidance information includes: When the stiffness value in the posture analysis result exceeds the second preset threshold, the stiffness parameter corresponding to the user's posture in the preview image is obtained, and the audio guidance information is generated by matching the stiffness parameter in the audio guidance library. The audio guidance information is converted into audio commands, and the audio commands are played according to the detected current ambient noise intensity.

7. The shooting control method according to any one of claims 1 to 4, characterized in that, Adjusting the gimbal parameters includes: within any one of the full-body framing range, half-body framing range, and partial framing range, controlling the gimbal to adjust the pitch angle and / or horizontal rotation angle to change the camera's viewing angle; And / or, adjusting the camera parameters includes at least one of the following: Adjust the zoom parameters of the camera to adapt to the changes in the field of view of the gimbal scanning; Adjust the camera's exposure parameters to match the current ambient light intensity.

8. The shooting control method according to claim 1, characterized in that, If the preset shooting conditions are met, triggering the camera to capture a target image containing the user includes: If the pose analysis results of each frame of the preview image continuously acquired under the same preset viewpoint meet the preset shooting conditions, the preset viewpoint is used as the optimal viewpoint to trigger the camera to capture the target image.

9. The shooting control method according to claim 1 or 8, characterized in that, The preview image is obtained by the camera using a first resolution; the target image is obtained by the camera using a second resolution; wherein the first resolution is smaller than the second resolution.

10. The shooting control method according to claim 1, characterized in that, The method further includes: Based on the acquisition time of the preview image, the execution time of adjusting device parameters and / or outputting audio guidance information is controlled so that the time deviation between the execution time and the acquisition time of the preview image is within a preset range.

11. The shooting control method according to claim 1, characterized in that, The method further includes at least one of the following: The audio output device includes a Bluetooth headset. When the communication between the terminal and the Bluetooth headset is interrupted, the terminal's speaker will play audio guidance information. When the user posture analysis fails, return to the step of controlling the gimbal to move the camera along a preset scanning trajectory; When the gimbal malfunctions, the current attitude of the gimbal is locked and switched to audio guidance mode, which is used to output audio guidance information.

12. A shooting control device, characterized in that, The device is applied to a terminal, which is equipped with a gimbal, a camera, and an audio output device. The shooting control device includes a processor, which is used to invoke instructions to execute the steps of the shooting control method as described in any one of claims 1 to 11.

13. A storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the shooting control method as described in any one of claims 1 to 11.

Images