Zoom control method, apparatus, device, storage medium, and product

Abstract

This application discloses a zoom control method, apparatus, device, storage medium, and product, relating to the field of camera technology. The zoom control method includes: acquiring a first image frame captured in real time by a camera; identifying facial information and a gesture type corresponding to the facial information in the first image frame; if the gesture type is a valid gesture, updating a preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; and performing pan-tilt control on the camera and hybrid zoom control on the camera based on the updated preset second parameter and the facial information. This application enables the camera to dynamically adjust according to the various body movements of participants, such as standing or sitting, ensuring stable facial positions and consistent image clarity in the output image.

Description

Technical Field

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

[0002] In scenarios such as video conferencing, live-streaming e-commerce, and remote teaching, cameras primarily capture real-time images, which are then displayed directly on a display device to achieve a face-to-face interactive effect.

[0003] In related technologies, in order to ensure the effect, existing camera technology usually uses a combination of digital zoom and optical zoom to maintain the proportion and clarity of the image. However, participants often have various physical movements such as standing and sitting, which require the camera to adjust dynamically in real time. The combination of zoom cannot guarantee that the position of the face in the output image is stable or that the image clarity remains unchanged. Summary of the Invention

[0004] The main purpose of this application is to provide a zoom control method, device, equipment, storage medium and product, which aims to solve the technical problem that hybrid zoom cannot guarantee the stability of the face position and the unchanged image clarity in the output image.

[0005] To achieve the above objectives, this application proposes a zoom control method, the zoom control method comprising:

[0006] Acquire the first image frame captured in real time by the camera, and identify the facial information and the gesture type corresponding to the facial information in the first image frame; If the gesture type is a valid gesture, then update the preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; Based on the updated preset second parameter and the facial information, the camera is subjected to gimbal control and hybrid zoom control.

[0007] In one embodiment, the preset second parameter includes a second face tracking parameter, a second distance parameter, and a second width parameter. The step of performing gimbal control on the camera and hybrid zoom control on the camera based on the updated preset second parameter and the face information includes: Based on the tracked face parameters, the target face is determined from the face information; Calculate the image parameters of the target face in the first image frame, wherein the image parameters include a first distance parameter and a first width parameter; Based on the second distance parameter and the first distance parameter, the camera is controlled by a pan-tilt unit; Based on the second width parameter and the first width parameter, hybrid zoom control is performed on the camera after gimbal control.

[0008] In one embodiment, the step of controlling the camera's pan / tilt mechanism based on the second distance parameter and the first distance parameter includes: Calculate the distance deviation between the second distance parameter and the first distance parameter, wherein the distance deviation includes a lateral distance deviation and a longitudinal distance deviation; Based on the lateral distance deviation, the pan-tilt unit is driven to rotate the camera horizontally to adjust its lateral position. Based on the longitudinal distance deviation, the pan-tilt unit is driven to adjust the vertical position of the camera.

[0009] In one embodiment, the step of performing hybrid zoom control on the camera after gimbal control based on the second width parameter and the first width parameter includes: Calculate the ratio of the first width parameter to the second width parameter, and determine the optical zoom ratio based on the ratio; Based on the optical zoom ratio, adjust the focal length of the camera after gimbal control; Acquire the second image frame after optical focal length adjustment, and determine the second face width of the target portrait in the second image frame; If the difference between the width of the second face and the width parameter is greater than the threshold, then digital zoom is applied to the second image frame.

[0010] In one embodiment, the preset first template parameters include a first tracking face parameter, a first distance parameter, and a first width parameter; the valid gestures include at least target switching gestures, zoom gestures, and movement gestures; and the step of updating the preset first parameters if the gesture type is a valid gesture includes: If the gesture information is the switching gesture, then update the first tracked face parameters; If the gesture information is the zoom gesture, then update the first width parameter, wherein the deviation between the first width parameter and the second width parameter is within a first preset adjustment range; If the gesture information is the movement gesture, then the first distance parameter is updated, wherein the deviation between the first distance parameter and the second distance parameter is within a second preset adjustment range.

[0011] In one embodiment, the step of identifying facial information in the first image frame and the gesture type corresponding to the facial information includes: The first image frame is input into a preset target recognition model, and a third image frame labeled with facial information and hands is output. Obtain target tracking results for a preset number of historical image frames consecutive to the first image frame, wherein the target tracking results include face information and hand-bound identifiers in the historical image frames; Assign corresponding identifiers to the hand and face information belonging to the same person in the third image frame; Key points of the hand in the third image frame are identified, and gesture recognition is performed based on the key points to obtain the gesture type. Based on the identifier, the gesture type corresponding to the face information is determined.

[0012] Furthermore, to achieve the above objectives, this application also proposes a zoom control device, which includes: The recognition module is used to acquire the first image frame captured in real time by the camera, and to recognize the facial information and the gesture type corresponding to the facial information in the first image frame; An update module is used to update a preset first parameter if the gesture type is a valid gesture, wherein the preset first parameter is used to locate the target face in the first image frame; The control module is used to perform gimbal control on the camera and hybrid zoom control on the camera based on the updated preset second parameters and the facial information.

[0013] In addition, to achieve the above objectives, this application also proposes a zoom control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the zoom control method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the zoom control method described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the zoom control method described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: In related technologies, to ensure effectiveness, existing camera technologies typically use a combination of digital zoom and optical zoom to maintain the proportion and clarity of the image. However, attendees often engage in various physical movements, such as standing or sitting, requiring the camera to dynamically adjust in real time. Hybrid zoom cannot guarantee a stable face position or consistent image clarity in the output image. In contrast, this application acquires a first image frame captured in real time by the camera, identifies facial information and the corresponding gesture type in the first image frame; if the gesture type is a valid gesture, it updates a preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; based on the updated preset second parameter and the facial information, it performs pan-tilt control on the camera and hybrid zoom control on the camera. After obtaining image frames captured by the camera, this application identifies the facial information and the corresponding gesture type in the image frames. If the current gesture type matches a valid gesture, it changes the preset first parameter used to locate the target face. Based on the facial information and the updated preset second parameter, it performs pan-tilt control on the camera. After pan-tilt control, it performs hybrid zoom control on the camera, which allows the camera to be dynamically adjusted according to the various body movements of the participants, such as standing or sitting, to ensure that the position of the face in the output image remains stable and the image clarity remains unchanged. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the zoom control method of this application. Figure 2 This is a schematic diagram of the preset parameters of the zoom control method of this application in an image frame; Figure 3 This is an overall flowchart of the zoom control method of this application; Figure 4 This is a flowchart illustrating Embodiment 2 of the zoom control method of this application; Figure 5 This is a schematic diagram of the key points of the zoom control method of this application; Figure 6 This is a schematic diagram of the module structure of the zoom control device according to an embodiment of this application; Figure 7This is a schematic diagram of the device structure of the hardware operating environment involved in the zoom control method in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is: to acquire a first image frame captured by the camera in real time, to identify the face information in the first image frame and the gesture type corresponding to the face information; if the gesture type is a valid gesture, to update the preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; based on the updated preset second parameter and the face information, to perform pan-tilt control on the camera and to perform hybrid zoom control on the camera.

[0024] In related technologies, in order to ensure the effect, existing camera technology usually uses a combination of digital zoom and optical zoom to maintain the proportion and clarity of the image. However, participants often have various physical movements such as standing and sitting, which require the camera to adjust dynamically in real time. The combination of zoom cannot guarantee that the position of the face in the output image is stable or that the image clarity remains unchanged.

[0025] After obtaining image frames captured by the camera, this application identifies the facial information and the corresponding gesture type in the image frames. If the current gesture type matches a valid gesture, it changes the preset first parameter used to locate the target face. Based on the facial information and the updated preset second parameter, it performs pan-tilt control on the camera. After pan-tilt control, it performs hybrid zoom control on the camera, which allows the camera to be dynamically adjusted according to the various body movements of the participants, such as standing or sitting, to ensure that the position of the face in the output image remains stable and the image clarity remains unchanged.

[0026] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or zoom control device capable of performing the above functions. The following description uses a zoom control device as an example to illustrate this embodiment and the subsequent embodiments.

[0027] Based on this, the embodiments of this application provide a zoom control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the zoom control method of this application.

[0028] In this embodiment, the zoom control method includes steps S10 to S30: Step S10: Acquire the first image frame captured in real time by the camera, and identify the facial information and the gesture type corresponding to the facial information in the first image frame; It should be noted that the execution entity in this embodiment is a zoom control device. This zoom control device is equipped with a gimbal, which is connected to a camera. The camera can cooperate with the gimbal to perform panning and tilting operations. Face information refers to the face region detected in the image and its related features, including at least the face's position (boundary box), identity identifier (ID), and possible face pose data. Gesture type refers to a specific gesture category identified by analyzing hand key points or hand region images, such as switching targets, zooming in / out, and moving up / down / left / right, used to control the camera's zoom and image adjustment. The zoom control device acquires the first image frame captured in real time by the camera, processes the image frame by calling a target detection model (such as YOLO) pre-deployed on the system-on-a-chip (SoC), and detects the face region and hand region within it; then, it uses a key point extraction model (such as RTMPose) to locate key points in the hand region, and then uses a gesture classification model (such as a ResNet-based classifier) ​​to classify these key points, thereby identifying the gesture type associated with the current face information. Through this process, the device can associate faces with gestures and provide input signals for subsequent hybrid zoom control. This enables real-time perception of user intent using natural gesture interaction without relying on additional remote control equipment, laying the data foundation for face tracking and image adjustment.

[0029] This step, by simultaneously recognizing facial information and corresponding gesture types in the first image frame captured in real time by the camera, binds the facial region and hand movements together. This allows the camera to accurately perceive who the current user is and what control command they want to execute (such as adjusting the portrait ratio, moving the image, etc.), thus providing accurate and real-time input parameters for the subsequent hybrid zoom control module. This combination of face tracking and gesture recognition overcomes the lag and inaccuracy of traditional manual adjustment, achieving contactless and intuitive control. It significantly improves the user's ease of operation and the real-time performance of image adjustments in scenarios such as video conferencing and live streaming.

[0030] Step S20: If the gesture type is a valid gesture, then update the preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; Understandably, a valid gesture refers to a specific gesture predefined by the device as having control significance among the gesture types identified in the previous step, such as switching targets, zooming in, zooming out, and moving the image. These gestures are recognized and responded to by the device, thereby triggering corresponding control operations. The preset first parameter is used to determine the position and size range of the target face in the image. Specifically, it may include parameters such as the white space pixels along the top edge of the face, the distance from the center of the face to the left (pixels), and the face width. These parameters collectively define the ideal position and proportion of the desired image in the image. The target face is the object that the current speaker or user wants the camera to track. The zoom control device first determines whether the identified gesture type belongs to the predefined set of valid gestures, such as zooming in, zooming out, switching targets, or moving the image. If it is a valid gesture, the preset first parameter is updated according to the specific meaning of the gesture. The preset first parameter is used to locate the target face in the first image frame, including the desired face width, the horizontal offset of the face in the image, and thresholds for vertical white space. For example, if the gesture is zooming in, the preset face width value is increased; if it is moving the image to the left, the horizontal offset of the face center is adjusted. This enables the dynamic adjustment of the target portrait's ideal position and size within the frame via gesture commands, providing updated target parameters for subsequent hybrid zoom control.

[0031] Step S30: Based on the updated preset second parameter and the face information, perform gimbal control on the camera and perform hybrid zoom control on the camera.

[0032] It should be noted that pan-tilt control refers to adjusting the camera's shooting angle by controlling the horizontal and vertical rotation of the camera's pan-tilt head, so that the target face is positioned in the desired location in the frame. Hybrid zoom control refers to adjusting the camera's focal length by combining optical zoom and digital zoom to change the proportion of the image in the frame, while prioritizing image sharpness. The zoom control device uses updated preset second parameters and real-time face information to coordinate the control of the pan-tilt head and hybrid zoom, enabling the camera to automatically and accurately adjust the shooting angle and focal length according to the new target parameters adjusted by the user's gestures.

[0033] In one feasible implementation, the steps of performing gimbal control on the camera and hybrid zoom control on the camera based on the updated preset second parameter and the facial information include: Based on the tracked face parameters, the target face is determined from the face information; Understandably, the tracking face parameter Is_Target indicates whether it is the target face to be tracked. The target face corresponds to the object the user wants the camera to track, and its position and size will serve as the reference for subsequent pan-tilt control and hybrid zoom adjustment. The zoom control device matches and filters all face information extracted from the first image frame based on the continuously maintained tracking face parameters to determine the current target face.

[0034] Specifically, the preset parameters (preset first parameter or preset second parameter) include: top_thre: The number of pixels left as white space along the edge of the face; Left_thre: The distance of the center of the face from the left side in pixels; Face_w: Width of the face; Is_Target: Whether it is a target face being tracked.

[0035] Furthermore, referring to Figure 2 , Figure 2 A schematic diagram of the preset parameters in the image frame is provided.

[0036] Calculate the image parameters of the target face in the first image frame, wherein the image parameters include a first distance parameter and a first width parameter; It should be noted that the image parameters refer to a set of quantified values ​​calculated by analyzing the position and size of the target face in the image, used to describe the actual state of the current image in the frame. The first distance parameter refers to the distance information of the target face relative to the frame boundary in the image, specifically including the vertical distance from the top edge of the target face to the top edge of the frame (i.e., the vertical white space pixels), and the horizontal distance from the center of the target face to the left edge of the frame (i.e., the horizontal offset). The first width parameter refers to the width value of the target face in the image, which is used to describe the actual proportion of the face in the current frame. The zoom control device calculates its image parameters for the identified target face in the first image frame. Specifically, the device extracts the bounding box of the target face from the first image frame, which precisely defines the face region. Based on the coordinate information of the bounding box, the device calculates the first distance parameters: including the vertical distance from the top edge of the target face to the top edge of the frame (i.e., the current vertical white space pixels), and the horizontal distance from the center point of the target face to the left edge of the frame (i.e., the current horizontal offset). Simultaneously, the device calculates the first width parameter, which is the horizontal width value (in pixels) of the target face bounding box. This completes the precise quantification of the actual position and size of the target image in the current image, providing real-time and quantifiable basic data for subsequent comparison with preset target parameters (preset first parameter).

[0037] Based on the second distance parameter and the first distance parameter, the camera is controlled by a pan-tilt unit; Understandably, the zoom control device controls the camera's pan-tilt unit based on a preset second distance parameter and a currently calculated first distance parameter. Specifically, the device compares the current vertical clearance in the first distance parameter with the target's vertical clearance in the second distance parameter to calculate the vertical deviation. Simultaneously, it compares the current horizontal offset in the first distance parameter with the target's horizontal offset in the second distance parameter to calculate the horizontal deviation. Based on these deviations, the device generates control commands for pan-tilt rotation, driving the pan-tilt unit to rotate horizontally and vertically to gradually reduce the deviation and move the target face's actual position towards the preset ideal position. This achieves automatic adjustment of the camera's pan-tilt unit, ensuring the target face is stably positioned in the ideal position within the frame without manual intervention.

[0038] Based on the second width parameter and the first width parameter, hybrid zoom control is performed on the camera after gimbal control.

[0039] It should be noted that after the gimbal control is completed and the target face position is basically aligned, the zoom control device performs hybrid zoom control on the camera based on the preset second width parameter and the currently calculated first width parameter.

[0040] In one feasible implementation, the step of performing pan-tilt control on the camera based on the second distance parameter and the first distance parameter includes: Calculate the distance deviation between the second distance parameter and the first distance parameter, wherein the distance deviation includes a lateral distance deviation and a longitudinal distance deviation; Understandably, lateral distance deviation refers to the difference between the horizontal offset of the current face center from the left edge of the image (the horizontal component in the first distance parameter) and the target horizontal offset (the horizontal component in the second distance parameter) in the horizontal direction. Vertical distance deviation refers to the difference between the vertical margin between the top edge of the current face and the top edge of the image (the vertical component in the first distance parameter) and the target vertical margin (the vertical component in the second distance parameter) in the vertical direction. The zoom control device extracts the corresponding components from the second and first distance parameters respectively: in the horizontal direction, it calculates the difference between the current horizontal offset in the first distance parameter and the target horizontal offset in the second distance parameter to obtain the lateral distance deviation; in the vertical direction, it calculates the difference between the current vertical margin in the first distance parameter and the target vertical margin in the second distance parameter to obtain the vertical distance deviation. These two deviation values ​​not only reflect the degree to which the target face deviates from the ideal position but also indicate the direction of deviation (e.g., left or right, up or down) through positive or negative values.

[0041] Based on the lateral distance deviation, the pan-tilt unit is driven to rotate the camera horizontally to adjust its lateral position. It should be noted that the zoom control device, based on the calculated lateral distance deviation, drives the pan-tilt unit to rotate the camera horizontally, thereby adjusting the lateral position of the target face. Specifically, the system acquires the value and direction of the lateral distance deviation: if the deviation value is positive, it means the current face center is off to the right of the ideal position, so the pan-tilt unit is driven to rotate to the left, moving the camera's field of view to the left, thus adjusting the image to the right in the frame; if the deviation value is negative, it means the current face center is off to the left of the ideal position, so the pan-tilt unit is driven to rotate to the right, moving the camera's field of view to the right, thus adjusting the image to the left in the frame. The rotation speed and angle of the pan-tilt unit are proportional to the absolute value of the lateral distance deviation; the larger the deviation, the greater the rotation angle and speed, achieving fast and smooth adjustment.

[0042] Based on the longitudinal distance deviation, the pan-tilt unit is driven to adjust the vertical position of the camera.

[0043] Understandably, the zoom control device, based on the calculated longitudinal distance deviation, drives the pan-tilt unit to rotate the camera vertically, thereby adjusting the vertical position of the target image. Specifically, the system acquires the value and direction of the longitudinal distance deviation: if the deviation value is positive, it means that the edge of the current face is higher than the ideal position (i.e., the image is lower in the frame), so the pan-tilt unit is driven to rotate upward, moving the camera's field of view upward, thus adjusting the image downward in the frame; if the deviation value is negative, it means that the edge of the current face is lower than the ideal position (i.e., the image is higher in the frame), so the pan-tilt unit is driven to rotate downward, moving the camera's field of view downward, thus adjusting the image upward in the frame.

[0044] In one feasible implementation, the step of performing hybrid zoom control on the camera after pan-tilt control based on the second width parameter and the first width parameter includes: Calculate the ratio of the first width parameter to the second width parameter, and determine the optical zoom ratio based on the ratio; It should be noted that the zoom control device calculates the ratio of the first width parameter to the second width parameter and determines the optical zoom ratio based on this ratio. Specifically, the device first divides the currently detected actual face width (first width parameter) by the preset target face width (second width parameter) to obtain a dimensionless scaling factor. For example, if the ratio is less than 1, it means the current face is too small and the image needs to be magnified; in this case, the device sets the optical zoom ratio to a value greater than the current magnification. If the ratio is greater than 1, it means the current face is too large and the image needs to be reduced; in this case, the device sets the optical zoom ratio to a value less than the current magnification. When determining the optical zoom ratio, the device references the physical zoom range of the optical lens to ensure that the target magnification is within the focal length supported by the lens. This transforms the visual requirement of the portrait proportion into a specific optical zoom control target, providing clear physical parameters for subsequent precise adjustment of the portrait proportion.

[0045] Based on the optical zoom ratio, adjust the focal length of the camera after gimbal control; Understandably, the zoom control device converts the target optical zoom ratio calculated in the previous step into a specific lens focal length control command, drives the camera's optical zoom motor, and moves the lens group to the corresponding physical position, thereby changing the actual focal length of the lens.

[0046] Acquire the second image frame after optical focal length adjustment, and determine the second face width of the target portrait in the second image frame; It should be noted that after the zoom control device completes the optical focal length adjustment, it reacquires the second image frame captured in real time by the camera, identifies the target human image that is being continuously tracked in the image frame, and calculates its second face width.

[0047] If the difference between the width of the second face and the width parameter is greater than the threshold, then digital zoom is applied to the second image frame.

[0048] Understandably, the threshold refers to a pre-set allowable error range, which is a pixel difference. When the difference between the second face width and the second width parameter is less than or equal to this threshold, the portrait proportion is considered to meet the requirements; when the difference is greater than the threshold, the adjustment precision of the optical zoom is considered insufficient to meet the requirements, and further compensation is needed. The zoom control device compares the second face width with the preset second width parameter, calculates the absolute difference between the two, and determines whether the difference is greater than the preset threshold. If the difference is greater than the threshold, it means that the portrait proportion still does not meet the ideal precision requirements after simply relying on optical zoom adjustment, and there is a visible deviation. At this time, the device activates digital zoom as a supplementary adjustment method, digitally cropping and scaling the second image frame to make the portrait width accurately match the second width parameter in the final output image. The scaling factor of digital zoom is calculated and determined based on the remaining deviation value to achieve precise fine-tuning of the portrait proportion. Thus, after the optical zoom reaches its physical limit or step size limit, the remaining precision error is compensated by digital zoom to ensure that the portrait proportion of the final output image accurately meets the preset requirements. Figure 3 , Figure 3 An overall flowchart is provided.

[0049] Optionally, the zoom control device monitors the current position of the optical zoom lens in real time when performing hybrid zoom control. When the target optical zoom ratio calculated by the device based on the scaling factor exceeds the physical range of the lens (i.e., reaches the optical zoom limit), an adaptive digital zoom compensation and enhancement mechanism based on image quality assessment is triggered. The specific steps are as follows: The device first adjusts the optical zoom lens to its extreme position (wide-angle or telephoto). Then, based on the remaining proportional deviation between the current actual face width and the target face width, it calculates the required digital zoom ratio. When initiating digital zoom, the device uses linear frame interpolation or a easing function to ensure the magnification or reduction effect of digital zoom takes effect gradually, rather than abruptly. Simultaneously, the device controls the compensation speed based on a zoom transition smoothness threshold, ensuring a continuous and smooth transition from optical to digital zoom perceptibly to the human eye. Starting from the first frame after digital zoom compensation takes effect, the device invokes the image quality evaluation module to perform real-time analysis of the current image frame. The evaluation focuses on the target face region, calculating image quality indicators such as face region sharpness, edge sharpness, and noise level, and comparing them with a reference frame before digital zoom. If the image quality evaluation module detects that the face region sharpness is lower than a preset image quality degradation threshold, indicating that digital zoom has caused a perceptible loss of image quality, the device immediately triggers adaptive enhancement compensation. The enhancement compensation strategy includes: lightly sharpening the target face area, enhancing edge contrast, and compensating for the blurring of details caused by digital magnification.

[0050] Furthermore, the image quality evaluation module is seamlessly integrated with the identifier-based target face tracking mechanism from the previous steps. The device can accurately locate the target face that needs enhancement, avoiding ineffective enhancement of the background or other unimportant areas, thus saving computational resources while ensuring optimal image quality in key areas.

[0051] In this implementation, a threshold is set as the judgment criterion, and digital zoom is only activated when the remaining deviation after optical zoom adjustment exceeds the allowable range. This avoids unnecessary activation of digital zoom within acceptable deviation range, which would result in image quality loss. This hierarchical control mechanism prioritizes the use of lossless optical zoom for coarse adjustment, and only uses digital zoom for fine adjustment when the optical zoom accuracy is insufficient. This ensures both the accuracy of the final composition and the maximum maintenance of image sharpness.

[0052] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 In step S20, the zoom control method further includes steps S01 to S03: Step S01: If the gesture information is the switching gesture, then update the first tracked face parameters; It should be noted that the switching gesture is a specific gesture type predefined as the control intent of "switching target faces". When this gesture is recognized, the device will perform a target face switching operation, shifting the tracking focus from the current target face to another valid face. The zoom control device determines whether the currently recognized gesture information is a predefined switching gesture. If the gesture information is confirmed to be a switching gesture, the first tracking face parameter update operation is performed. Specifically, the device determines the next target face to switch to based on multiple face information and their corresponding tracking parameters present in the current scene. For example, when switching to another detected face, the current target face is marked as not being the target tracking face.

[0053] Step S02: If the gesture information is the zoom gesture, then update the first width parameter, wherein the deviation between the first width parameter and the second width parameter is within a first preset adjustment range; It is understandable that the first preset adjustment range refers to a pre-defined reasonable range that allows the first width parameter to be adjusted relative to the second width parameter in a single gesture update. The zoom control device determines whether the currently recognized gesture information is a predefined zoom gesture (zoom in or zoom out). If the gesture information is confirmed to be a zoom gesture, the device performs an update operation on the first width parameter. Specifically, the device adjusts the first width parameter incrementally or incrementally within the preset first preset adjustment range based on the direction (zoom in or zoom out) and amplitude of the zoom gesture.

[0054] Step S03: If the gesture information is the movement gesture, then update the first distance parameter, wherein the deviation between the first distance parameter and the second distance parameter is within a second preset adjustment range.

[0055] It should be noted that the second preset adjustment range refers to a pre-defined reasonable range that allows the first distance parameter to be adjusted relative to the second distance parameter in a single gesture update. This range limits the step size or amplitude of each gesture adjustment, ensuring smooth and controllable changes in image position and avoiding sudden changes or oscillations in the image due to excessive adjustments in a single instance. The zoom control device determines whether the currently recognized gesture information is a predefined movement gesture (up, down, left, or right). If the gesture information is confirmed to be a movement gesture, the first distance parameter is updated. Specifically, based on the direction (up, down, left, right) and amplitude of the movement gesture, the device adjusts the corresponding component of the first distance parameter incrementally or incrementally within the preset second preset adjustment range. For example, if the gesture is an upward movement, the target vertical white space value is decreased (making the image move upward in the image); if the gesture is a downward movement, the target vertical white space value is increased (making the image move downward); if the gesture is a leftward movement, the target horizontal offset value is decreased (making the image move left); if the gesture is a rightward movement, the target horizontal offset value is increased (making the image move right). During the adjustment process, the device ensures that the deviation between the updated first distance parameter and the currently detected second distance parameter is limited to a second preset adjustment range, that is, the expected position change caused by each gesture update is moderate and smooth.

[0056] Furthermore, while acquiring the first image frame, the zoom control device collects ambient audio signals through a microphone array, performs audio energy detection, and determines whether a user is speaking and the approximate direction of the sound source. If a significant increase in sound energy from a certain direction is detected and matches human voice characteristics, the device matches the facial information corresponding to that direction with the face in the current image frame to identify the current speaker. The device then updates the target face to reflect the detected speaker and assigns a speaking rights identifier, enabling the camera to automatically track the speaker. When a shift in speaking rights is detected (e.g., a stronger voice from another direction), the device dynamically switches the target face and updates the corresponding tracking parameters. This achieves intelligent target locking based on sound activation, ensuring the camera always focuses on the currently active speaker.

[0057] Furthermore, after recognizing a zoom gesture, the zoom control device first calls a scene classifier to analyze the current image and audio to determine the current scene context (such as a single-person close-up, a multi-person panorama, a demonstration, etc.). Based on different scene types, the device dynamically adjusts the range of the first preset adjustment interval, i.e., the zoom step size corresponding to each zoom gesture. For example, in a single-person close-up scene, the face is already large, and even a small zoom change will significantly affect the viewing experience; therefore, the device uses a smaller step size, allowing the user to finely adjust the portrait proportions. In a multi-person panorama scene, the face is small, requiring a larger zoom range to produce a noticeable effect; therefore, the device uses a larger step size to achieve rapid composition switching. The device then updates the first width parameter based on the adjusted step size and executes subsequent zoom control. This achieves intelligent zoom step size adjustment based on scene context, making the response of gesture interaction more consistent with the actual needs of the current scene.

[0058] Furthermore, after recognizing zoom gestures and determining that the current scenario is a demonstration, the zoom control device activates a dynamic acceleration mechanism to adjust the zoom step size in real time. The device first records the time of each zoom gesture and calculates the time interval between adjacent gestures. When it detects that the user makes consecutive zoom gestures with intervals less than a preset threshold (e.g., 0.5 seconds), the device determines that the user intends to quickly switch compositions and begins to gradually increase the zoom step size. For example, the first gesture uses a default medium step size (e.g., 20 pixels), the second consecutive gesture increases the step size to 30 pixels, the third to 40 pixels, and so on, achieving an acceleration effect. When the user stops the gesture or the gesture interval exceeds the preset threshold, the device determines that the user has entered a fine-tuning mode and gradually restores the zoom step size to the default medium value, facilitating fine adjustments. The device updates the first width parameter based on the adjusted dynamic step size and executes subsequent zoom control. This achieves automatic switching between "rapid switching" and "fine-tuning" modes in demonstration scenarios by intelligently recognizing the user's operational rhythm, ensuring that the response amplitude of a single gesture matches the user's intent.

[0059] In one feasible implementation, the step of identifying facial information in the first image frame and the gesture type corresponding to the facial information includes: The first image frame is input into a preset target recognition model, and a third image frame labeled with facial information and hands is output. Understandably, the pre-set target recognition model refers to a deep learning model pre-trained and deployed on a system-on-a-chip (SoC). This model is specifically trained to simultaneously detect face and hand regions from input images. This model is typically based on object detection algorithms such as YOLO and undergoes optimization processes like quantization to ensure efficient operation on terminal devices. The zoom control device inputs the first image frame, captured in real-time by the camera, into the pre-deployed target recognition model on the SoC. This target recognition model, based on deep learning algorithms such as YOLO, is specifically trained to simultaneously detect face and hand regions in the image. The model performs forward inference calculations on the first image frame and outputs detection results, including the bounding box coordinates and confidence scores for each face region and each hand region. The device overlays these detection results onto the original image in labeled form, generating a third image frame that clearly marks the positions of the face and hand in the image.

[0060] Obtain target tracking results for a preset number of historical image frames consecutive to the first image frame, wherein the target tracking results include face information and hand-bound identifiers in the historical image frames; It should be noted that the zoom control device acquires a preset number of historical image frames that are temporally consecutive to the first image frame, and reads the target tracking results corresponding to these historical image frames from the tracking buffer maintained by the device. These target tracking results include face and hand information detected in each historical image frame, as well as binding identifiers assigned to each face and hand after cross-frame association. The setting of binding identifiers ensures that the face and hand of the same person share the same ID, allowing the device to clearly know which hand belongs to which person. For example, for speaker A, the ID of his hand region is consistent with the ID of his face region. This provides rich historical context information for the processing of the current first image frame, enabling the system to accurately inherit and bind the IDs of the faces and hands detected in the current frame based on historical identity association information, ensuring the continuity of tracking and the consistency of identity.

[0061] Assign corresponding identifiers to the hand and face information belonging to the same person in the third image frame; Understandably, the zoom control device assigns corresponding identifiers to hand and face information belonging to the same person in the third image frame based on the target tracking results of the acquired historical image frames. Specifically, the system matches and associates all face and hand regions detected in the third image frame with the target tracking results that have been bound to identifiers in the historical image frames. By analyzing the proximity of spatial locations, the consistency of motion trajectories, and the similarity of appearance features, the system determines which faces and hands in the current frame belong to the same person. For successfully matched faces and hands, the system inherits the corresponding identifiers from the historical tracking results, ensuring that faces and hands of the same person share the same ID. For newly appearing faces or hands, the system assigns a new identifier and continues to track them in subsequent frames.

[0062] Key points of the hand in the third image frame are identified, and gesture recognition is performed based on the key points to obtain the gesture type. Based on the identifier, the gesture type corresponding to the face information is determined.

[0063] It should be noted that the keypoints of the hand refer to the coordinates of key points of the hand skeleton detected from the hand region image using a keypoint extraction model (such as RTMPose). This typically includes 21 keypoints, corresponding to locations such as the wrist, finger joints, and fingertips. (See reference...) Figure 5 , Figure 5 A keypoint diagram is provided. These keypoints constitute a detailed description of hand pose and movement. The zoom control device extracts keypoints and recognizes gestures in the hand regions detected in the third image frame, and associates the recognized gesture type with the corresponding facial information based on identifiers. Specifically, the device first locates all hand bounding boxes in the third image frame. For each hand region, it calls a keypoint extraction model (such as RTMPose) to extract the coordinates of 21 skeletal keypoints of the hand. Then, these keypoint coordinates are input into a gesture classification model (such as a ResNet-based classifier), and the model outputs the gesture type corresponding to the hand (such as zoom in, zoom out, toggle, etc.). Finally, the device uses the identifiers assigned in the previous step to bind the recognized gesture type with facial information with the same identifier, determining which face the user associated with the gesture type performed.

[0064] In this implementation, key point extraction and gesture classification models are used to accurately identify gesture types from the hand region. Identifiers are then used to bind gestures to specific facial information, enabling the system to accurately determine "who" performed "what gesture." This identifier-based association mechanism effectively solves the problem of unclear gesture attribution in multi-person scenarios, ensuring that only the gesture commands of the currently tracked target (i.e., the user corresponding to the face with the specific identifier) ​​are responded to by the system, avoiding accidental triggering caused by unintentional actions of other participants. All user-related data involved in this application (such as user facial data and user behavior data) were obtained with the user's permission or consent; that is, when this application is used in a specific product or technology, user permission is required to obtain and process the relevant data, and the processing of the relevant data must comply with the relevant laws, regulations and regulatory standards of the relevant countries and regions.

[0065] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the zoom control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0066] This application also provides a zoom control device, please refer to... Figure 6 The zoom control device includes: The recognition module 10 is used to acquire the first image frame captured by the camera in real time, and to recognize the facial information and the gesture type corresponding to the facial information in the first image frame; The update module 20 is used to update a preset first parameter if the gesture type is a valid gesture, wherein the preset first parameter is used to locate the target face in the first image frame; The control module 30 is used to perform pan-tilt control on the camera and hybrid zoom control on the camera based on the updated preset second parameters and the face information.

[0067] Optionally, the control module includes: The calculation submodule is used to determine the target face in the face information according to the tracked face parameters; calculate the image parameters of the target face in the first image frame, wherein the image parameters include a first distance parameter and a first width parameter; perform pan-tilt control on the camera based on the second distance parameter and the first distance parameter; and perform hybrid zoom control on the pan-tilt controlled camera based on the second width parameter and the first width parameter.

[0068] Optionally, the computing submodule includes: A first control unit is configured to calculate the distance deviation between the second distance parameter and the first distance parameter, wherein the distance deviation includes a lateral distance deviation and a longitudinal distance deviation; based on the lateral distance deviation, drive the pan-tilt unit to rotate the camera horizontally to adjust its lateral position; and based on the longitudinal distance deviation, drive the pan-tilt unit to adjust the camera's vertical position.

[0069] The second control unit is configured to calculate the ratio of the first width parameter to the second width parameter, determine the optical zoom ratio based on the ratio, adjust the focal length of the camera after gimbal control based on the optical zoom ratio, acquire the second image frame after the optical focal length adjustment, and determine the second face width of the target portrait in the second image frame; if the difference between the second face width and the width parameter is greater than a threshold, then digitally zoom the second image frame.

[0070] Optionally, the update module includes: An update submodule is configured to update the first tracking face parameter if the gesture information is the switching gesture; update the first width parameter if the gesture information is the zoom gesture, wherein the deviation between the first width parameter and the second width parameter is within a first preset adjustment range; and update the first distance parameter if the gesture information is the movement gesture, wherein the deviation between the first distance parameter and the second distance parameter is within a second preset adjustment range.

[0071] Optionally, the identification module includes: The allocation submodule is used to input the first image frame into a preset target recognition model and output a third image frame labeled with face information and hands; acquire target tracking results of a preset number of historical image frames consecutive to the first image frame, wherein the target tracking results include identifiers bound to face information and hands in the historical image frames; assign corresponding identifiers to the hands and face information belonging to the same person in the third image frame; identify key points of the hands in the third image frame, perform gesture recognition based on the key points to obtain the gesture type, and determine the gesture type corresponding to the face information based on the identifier.

[0072] The zoom control device provided in this application, employing the zoom control method in the above embodiments, can solve the technical problem of zoom control. Compared with the prior art, the beneficial effects of the zoom control device provided in this application are the same as those of the zoom control method provided in the above embodiments, and other technical features in the zoom control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0073] This application provides a zoom control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the zoom control method in the above embodiment 1.

[0074] The following is for reference. Figure 7The diagram illustrates a structural schematic suitable for implementing the zoom control device in the embodiments of this application. The zoom control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, tablets, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The zoom control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0075] like Figure 7 As shown, the zoom control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the zoom control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the zoom control device to communicate wirelessly or wiredly with other devices to exchange data. Although zoom control devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0076] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0077] The zoom control device provided in this application, employing the zoom control method described in the above embodiments, can solve the technical problem of zoom control. Compared with the prior art, the beneficial effects of the zoom control device provided in this application are the same as those of the zoom control method provided in the above embodiments, and other technical features of the zoom control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0078] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0079] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0080] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the zoom control method in the above embodiments.

[0081] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0082] The aforementioned computer-readable storage medium may be included in the zoom control device; or it may exist independently and not be assembled into the zoom control device.

[0083] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the zoom control device, cause the zoom control device to: acquire a first image frame captured in real time by the camera; identify facial information and a gesture type corresponding to the facial information in the first image frame; if the gesture type is a valid gesture, update a preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; and based on the updated preset second parameter and the facial information, perform gimbal control on the camera and perform hybrid zoom control on the camera.

[0084] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and 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 can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0086] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0087] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described zoom control method, thereby solving the technical problem of zoom control. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the zoom control method provided in the above embodiments, and will not be repeated here.

[0088] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the zoom control method described above.

[0089] The computer program product provided in this application can solve the technical problem of zoom control. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the zoom control method provided in the above embodiments, and will not be repeated here.

[0090] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A zoom control method, characterized in that, The zoom control method includes: Acquire the first image frame captured in real time by the camera, and identify the facial information and the gesture type corresponding to the facial information in the first image frame; If the gesture type is a valid gesture, then update the preset first parameter, wherein the preset first parameter is used to locate the target face in the first image frame; Based on the updated preset second parameter and the facial information, the camera is subjected to gimbal control and hybrid zoom control.

2. The zoom control method as described in claim 1, characterized in that, The preset second parameters include a second face tracking parameter, a second distance parameter, and a second width parameter. The steps of performing gimbal control on the camera and hybrid zoom control on the camera based on the updated preset second parameters and the face information include: Based on the tracked face parameters, the target face is determined from the face information; Calculate the image parameters of the target face in the first image frame, wherein the image parameters include a first distance parameter and a first width parameter; Based on the second distance parameter and the first distance parameter, the camera is controlled by a pan-tilt unit; Based on the second width parameter and the first width parameter, hybrid zoom control is performed on the camera after gimbal control.

3. The zoom control method as described in claim 2, characterized in that, The step of controlling the camera's pan-tilt mechanism based on the second distance parameter and the first distance parameter includes: Calculate the distance deviation between the second distance parameter and the first distance parameter, wherein the distance deviation includes a lateral distance deviation and a longitudinal distance deviation; Based on the lateral distance deviation, the pan-tilt unit is driven to rotate the camera horizontally to adjust its lateral position. Based on the longitudinal distance deviation, the pan-tilt unit is driven to adjust the vertical position of the camera.

4. The zoom control method as described in claim 2, characterized in that, The step of performing hybrid zoom control on the camera after gimbal control based on the second width parameter and the first width parameter includes: Calculate the ratio of the first width parameter to the second width parameter, and determine the optical zoom ratio based on the ratio; Based on the optical zoom ratio, adjust the focal length of the camera after gimbal control; Acquire the second image frame after optical focal length adjustment, and determine the second face width of the target portrait in the second image frame; If the difference between the width of the second face and the width parameter is greater than the threshold, then digital zoom is applied to the second image frame.

5. The zoom control method as described in claim 2, characterized in that, The preset first template parameters include a first tracked face parameter, a first distance parameter, and a first width parameter. The valid gestures include at least target switching gestures, zoom gestures, and movement gestures. The step of updating the preset first parameters if the gesture type is a valid gesture includes: If the gesture information is the switching gesture, then update the first tracked face parameters; If the gesture information is the zoom gesture, then update the first width parameter, wherein the deviation between the first width parameter and the second width parameter is within a first preset adjustment range; If the gesture information is the movement gesture, then the first distance parameter is updated, wherein the deviation between the first distance parameter and the second distance parameter is within a second preset adjustment range.

6. The zoom control method as described in claim 1, characterized in that, The step of identifying facial information in the first image frame and the gesture type corresponding to the facial information includes: The first image frame is input into a preset target recognition model, and a third image frame labeled with facial information and hands is output. Obtain target tracking results for a preset number of historical image frames consecutive to the first image frame, wherein the target tracking results include face information and hand-bound identifiers in the historical image frames; Assign corresponding identifiers to the hand and face information belonging to the same person in the third image frame; Key points of the hand in the third image frame are identified, and gesture recognition is performed based on the key points to obtain the gesture type. Based on the identifier, the gesture type corresponding to the face information is determined.

7. A zoom control device, characterized in that, The device includes: The recognition module is used to acquire the first image frame captured in real time by the camera, and to recognize the facial information and the gesture type corresponding to the facial information in the first image frame; An update module is used to update a preset first parameter if the gesture type is a valid gesture, wherein the preset first parameter is used to locate the target face in the first image frame; The control module is used to perform gimbal control on the camera and hybrid zoom control on the camera based on the updated preset second parameters and the facial information.

8. A zoom control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the zoom control method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the zoom control method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the zoom control method as described in any one of claims 1 to 6.

Images