A shooting method and electronic device

Abstract

This application discloses a shooting method and electronic device, relating to the field of electronic devices, which enables users to conveniently photograph their pets when they are not at home. The specific solution is as follows: First image frame data is acquired, and the user's private pet model is used to determine whether the first image frame data meets the shooting conditions; if the first image frame data meets the shooting conditions, the user's private pet model is used to determine the first target pet information in the first image frame data; second image frame data is acquired, and the user's private pet model is used to determine the second target pet information in the second image frame data; based on the first target pet information and the second target pet information, the user's pet is tracked and photographed to acquire third image frame data.

Description

Technical Field

[0001] This application relates to the field of electronic devices, and more particularly to a shooting method and an electronic device. Background Technology

[0002] As people's living standards improve, more and more users are choosing to keep pets and consider them as members of the family. Many users enjoy sharing videos of their pets, capturing their adorable moments. However, most of the time, due to work or other reasons, users cannot record videos at home whenever they want, thus missing many of their pets' wonderful moments.

[0003] Therefore, there is an urgent need for a method to photograph pets so that users can still take pictures of their pets when they are not at home, thereby recording their wonderful moments. Summary of the Invention

[0004] This application provides a shooting method and electronic device that allows users to conveniently take photos of their pets when they are not at home.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution: To achieve the above objective, the embodiments of this application adopt the following technical solution:

[0006] In a first aspect, embodiments of this application provide a shooting method applied to an electronic device. The shooting method may include: acquiring first image frame data and determining whether the first image frame data meets shooting conditions using a user-owned pet model; if the first image frame data meets shooting conditions, determining first target pet information in the first image frame data using the user-owned pet model; acquiring second image frame data and determining second target pet information in the second image frame data using the user-owned pet model; and tracking and shooting the user's pet based on the first target pet information and the second target pet information to acquire third image frame data.

[0007] Based on the method described in the first aspect, the above-mentioned shooting method may further include: acquiring first image frame data, and determining whether the first image frame data meets the shooting conditions through a user's private pet model. When the first image frame data meets the shooting conditions, the electronic device can continue to track and shoot the user's pet. Therefore, the solution of this application can facilitate users to track and shoot their pets when they are not at home. Furthermore, the solution of this application, when the first image frame data meets the shooting conditions, will track and shoot the user's pet based on the first target pet information and the second target pet information, which can improve the accuracy of tracking and shooting the user's pet.

[0008] Based on this possible implementation, since electronic devices can add corresponding anthropomorphic sound data to the tracked and captured image frames, the user experience can be improved. Furthermore, the electronic devices can also send the tracked and captured image frames to other electronic devices of the user, allowing the user to easily view the tracked pet's image frames on other devices, further enhancing the user experience.

[0009] Based on the method described in the first aspect, the above-mentioned tracking and photographing of the user's pet based on the first target pet information and the second target pet information to obtain third image frame data may include: obtaining first predicted image frame data based on the first image frame data and through a user-owned pet model; obtaining first predicted target pet information corresponding to the first predicted image frame data based on the first predicted image frame data and through a user-owned pet model; determining first posture adjustment information of the electronic device based on the first target pet information and the second target pet information when the second target pet information matches the first predicted target pet information; adjusting the posture of the electronic device based on the first posture adjustment information to obtain the first posture of the electronic device; obtaining fourth image frame data through the first posture; the third image frame data includes the fourth image frame data.

[0010] Based on this possible implementation, since the electronic device can match the target pet information included in the second image frame data with the target pet information included in the first predicted image frame data, and continues to track and photograph the user's pet when the target pet information included in the second image frame data matches the target pet information included in the first predicted image frame data, the accuracy of the electronic device in tracking and photographing the user's pet can be guaranteed.

[0011] Based on the method described in the first aspect, the above-mentioned shooting method may further include: when the second target pet information does not match the first target pet information, determining the pet information in the second target pet information that matches the first target pet information to a degree greater than a preset threshold as the third target pet information corresponding to the second image frame data; determining the second posture adjustment information of the electronic device based on the first target pet information and the third target pet information; adjusting the posture of the electronic device based on the second posture adjustment information to obtain the second posture of the electronic device; acquiring the fifth image frame data through the second posture; the third image frame data includes the fifth image frame data.

[0012] Based on this possible implementation, since the electronic device can match the target pet information included in the second image frame data with the target pet information included in the first predicted image frame data, if the target pet information included in the second image frame data does not match the target pet information included in the first predicted image frame data, the electronic device can re-determine that the target pet information included in the second image frame data is the same as the target pet information included in the first image frame data, thereby continuing to track and photograph the user's pet, which can further ensure the accuracy of the electronic device when tracking and photographing the user's pet.

[0013] Based on the method described in the first aspect, before determining the target pet image data corresponding to the user's pet based on the first image frame data, the second image frame data, and the third image frame data, the above shooting method may further include: determining whether the third image frame data meets the stop shooting condition; if the third image frame data meets the stop shooting condition, determining that the target pet image frame data includes the first image frame data and the second image frame data.

[0014] Based on this possible implementation, since the electronic device can determine whether the third image frame data meets the stop shooting condition, when the third image frame data meets the stop shooting condition, the electronic device can stop tracking and shooting the user's pet, thereby improving the user experience.

[0015] Based on the method described in the first aspect, the above-mentioned shooting method may further include: when the third image frame data does not meet the conditions for stopping shooting, tracking and shooting the user's pet based on the third image frame data to obtain a sixth image frame data, wherein the third image frame data includes the sixth image frame data, and the target pet image frame data is determined to include the first image frame data, the second image frame data, and the third image frame data.

[0016] Based on this possible implementation, since the electronic device can determine whether the third image frame data meets the conditions for stopping shooting, the electronic device can continue to track and shoot the user's pet when the third image frame data does not meet the conditions for stopping shooting, thereby improving the user experience.

[0017] Based on the method described in the first aspect, the shooting conditions may include the user's pet being included in the first image frame data, or the user's pet being included in the first image frame data, and the user's pet's behavior meeting preset conditions.

[0018] Based on this possible implementation, since the shooting conditions may include the user's pet in the first image frame data, or the user's pet in the first image frame data and the user's pet's behavior meets preset conditions, when the shooting conditions are met, the electronic device can track and shoot the user's pet, thereby avoiding the electronic device from continuously tracking and shooting the user's pet, and further improving the user experience.

[0019] Based on the method described in the first aspect, the aforementioned conditions for stopping shooting may include the third image frame data not including the user's pet, or the third image frame data including the user's pet and the user's pet's behavior not meeting the preset conditions, or the shooting duration reaching the preset duration.

[0020] Based on this possible implementation, since the conditions for stopping shooting may include the third image frame data not including the user's pet, or the third image frame data including the user's pet and the user's pet's behavior not meeting the preset conditions, or the shooting time reaching the preset time, when the conditions for stopping shooting are met, the electronic device can stop tracking and shooting the user's pet, thereby avoiding the electronic device from continuously tracking and shooting the user's pet and further improving the user experience.

[0021] Based on the method described in the first aspect, the aforementioned electronic device can be a tracking and shooting electronic device, which may include a camera module for acquiring image frame data and a motion module for adjusting the posture of the tracking and shooting electronic device.

[0022] Based on this possible implementation, since the electronic device may include a camera module for acquiring image frame data and a motion module for adjusting the posture of the electronic device, the electronic device can adjust its posture through the motion module and track and film the user's pet through the camera module.

[0023] Secondly, embodiments of this application provide a shooting device that can be applied to an electronic device to implement the method described in the first aspect. The function of the shooting device can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, such as an acquisition module, a determination module, etc.

[0024] The acquisition module can be used to acquire the first image frame data.

[0025] The determination module can be used to determine whether the first image frame data meets the shooting conditions based on the user's private pet model.

[0026] The determination module can also be used to determine the first target pet information in the first image frame data by using a user-owned pet model, provided that the first image frame data meets the shooting conditions.

[0027] The acquisition module can also be used to acquire second image frame data.

[0028] The determination module can also be used to determine the second target pet information in the second image frame data using a user-owned private pet model.

[0029] The acquisition module can also be used to track and photograph a user's pet based on the information of the first target pet and the information of the second target pet, in order to obtain third image frame data.

[0030] Thirdly, a shooting device is provided, which has the function of implementing the method described in the first aspect. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-described function.

[0031] Fourthly, a shooting device is provided, comprising: a processor and a memory; the memory is used to store computer execution instructions, and when the shooting device is running, the processor executes the computer execution instructions stored in the memory to cause the shooting device to perform the shooting method as described in any one of the first aspects above.

[0032] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions thereon. When the computer program instructions are executed by an electronic device, the electronic device performs the photographing method as described in any one of the first aspects or possible implementations of the first aspect.

[0033] Sixthly, embodiments of this application provide a computer program product including computer-readable code that, when executed in an electronic device, causes the electronic device to implement the shooting method as described in any one of the first aspects or possible implementations of the first aspect.

[0034] In a seventh aspect, an apparatus (e.g., a system-on-a-chip) is provided, comprising a processor for supporting an electronic device in performing the functions described in the first aspect above. In one possible design, the apparatus further comprises a memory for storing program instructions and data necessary for the electronic device. When the apparatus is a system-on-a-chip, it may be composed of chips or may include chips and other discrete devices.

[0035] It should be understood that the beneficial effects of the second to seventh aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0036] Figure 1 A schematic diagram illustrating the principle of the shooting method provided in the embodiments of this application;

[0037] Figure 2 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application;

[0038] Figure 3 This is a flowchart illustrating a shooting method provided in an embodiment of this application;

[0039] Figure 4 A schematic diagram of the shooting method provided in the embodiments of this application. Figure 1 ;

[0040] Figure 5 A schematic diagram of the shooting method provided in the embodiments of this application. Figure 2 ;

[0041] Figure 6 A schematic diagram of the shooting method provided in the embodiments of this application. Figure 3 ;

[0042] Figure 7 This is a schematic diagram of the structure of a shooting device provided in an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] 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 technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0045] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that “ / ” means “or,” for example, A / B can mean A or B; “and / or” in the text is merely a description of the relationship between related persons, indicating that three relationships can exist, for example, A and / or B can mean: A alone, A and B simultaneously, and B alone.

[0046] As people's living standards improve, more and more users are choosing to keep pets and consider them as members of the family. Many users enjoy sharing videos of their pets, capturing their adorable moments. However, most of the time, due to work or other reasons, users cannot record videos at home whenever they want, thus missing many of their pets' wonderful moments.

[0047] Furthermore, since pets are often in motion, and it is difficult to pinpoint their adorable or memorable moments (i.e., when a user feels the need to photograph them), users need to move alongside their pets when using electronic devices to capture these moments. This makes it difficult for users to capture these adorable or memorable moments.

[0048] Therefore, related technologies utilize electronic devices (such as tracking and filming devices) to follow and film pets, capturing their adorable and memorable moments. However, current tracking and filming devices are prone to losing track of pets, making it difficult to capture these cute and memorable moments.

[0049] Furthermore, even if the tracking and recording electronic device can track and film the pet when the user is not at home, capturing adorable and exciting moments, the user cannot see these moments in real time. This results in a poor user experience.

[0050] To address the aforementioned issues, this application provides a shooting method applied to an electronic device. This electronic device can be a tracking and shooting device, meaning it can track and shoot a subject (such as a pet). The shooting method may include the tracking and shooting device acquiring image frame data including the pet. Based on the image frame data including the pet, the tracking and shooting device determines whether a pet capture event is triggered. After determining that the pet's image frame data triggers a pet capture event, the tracking and shooting device can lock the capture target for focus tracking (i.e., identify the pet to be tracked and ensure that the pet is always within the camera's focus range). Then, the tracking and shooting device can track and shoot the locked target by moving, switching / raising / lowering the camera, etc. After capturing image or video data of the pet, the tracking and shooting device can send the captured image or video data to other devices of the user (such as the user's mobile phone), allowing the user to view the captured image or video data of the pet on other electronic devices.

[0051] The solution proposed in this application, because the tracking and shooting electronic device can lock onto the target and track the focus (i.e., identify the pet to be followed and ensure that the pet is always within the camera's focus range) when the pet's image frame data triggers a pet capture event, can then track and shoot the pet. Therefore, the tracking and shooting electronic device can still track and shoot the pet even when the user is not at home, thereby improving the user experience. Furthermore, because the tracking and shooting electronic device can lock onto the target and track the focus (i.e., identify the pet to be followed and ensure that the pet is always within the camera's focus range), the solution proposed in this application will not lose track of the pet, thus ensuring that adorable or memorable moments of the pet are captured.

[0052] Furthermore, the solution in this application allows the tracking and recording electronic device to send the captured image or video data of the pet to other devices of the user (such as the user's mobile phone), enabling the user to view the captured images or videos on other electronic devices. Therefore, this solution allows users to see their pet's adorable and exciting moments even when they are not at home, thus further enhancing the user experience.

[0053] The following is combined with Figure 1 The principle of the imaging method provided in the embodiments of this application will be illustrated below. Combined with... Figure 1 As shown, the shooting method provided in this application embodiment may include the following process.

[0054] First, the tracking and shooting electronic device can acquire image frames and determine whether a pet capture event has been triggered, such as whether the image frame acquired by the tracking and shooting electronic device includes a pet.

[0055] Afterwards, the tracking and shooting electronic device can lock onto the target and keep it in focus. That is, the tracking and shooting electronic device can identify the pet to be followed and filmed, and ensure that the pet to be followed and filmed is always within the focus range of the camera.

[0056] Then, when the pet is activated, the tracking and filming electronic device can track and film the pet based on the identified pet. That is, the tracking and filming electronic device can track and film the pet by moving, switching / raising / lowering the camera, etc.

[0057] After capturing images or videos of the pet, the tracking and camera device can process the captured data and send it to other devices of the user (such as the user's mobile phone). The user can then view the captured images or videos on other electronic devices. In other words, the tracking and camera device can intelligently post-process the captured images or videos, automatically save them, and push them to the user.

[0058] The imaging method provided in the embodiments of this application is described below.

[0059] The shooting method provided in this application can be applied to the aforementioned electronic device, namely a tracking and shooting electronic device, or a tracking and shooting robot. This application does not limit the specific form of the tracking and shooting electronic device.

[0060] In some examples, the structural schematic diagram of the tracking and imaging electronic device provided in the embodiments of this application can be as follows: Figure 2 As shown. Figure 2 As shown, the tracking and shooting electronic device may include a control module, an image processing module, an algorithm module, a camera module, a communication module, a storage module, a power supply module, etc.

[0061] The control module can be used to control the movement and behavior of the tracking and shooting electronic device.

[0062] For example, the control module can be used to control the camera module included in the tracking and shooting electronic device to film the pet. The control module can also be used to control the motion module included in the tracking and shooting electronic device to adjust the movement and posture of the tracking and shooting electronic device, thereby enabling the camera module to track and film the pet and ensuring that the pet to be tracked and filmed is always within the focus range of the camera.

[0063] The control module can also control the algorithm module included in the tracking and shooting electronic device to determine whether the image frame data captured by the camera module included in the tracking and shooting electronic device triggers a pet capture event, such as whether the image frame data obtained by the tracking and shooting electronic device includes a pet.

[0064] The control module can also control the image processing module included in the tracking and shooting electronic device to perform image processing on the image data or video data of the pet captured by the camera module included in the tracking and shooting electronic device, such as adding anthropomorphic sound data of the pet to the captured image data or video data of the pet.

[0065] The control module can also be used to control the storage module included in the tracking and shooting electronic device to store image data or video data of the pet captured by the camera module included in the tracking and shooting electronic device, or to store image data or video data of the pet processed by the image processing module included in the tracking and shooting electronic device.

[0066] The control module can also be used to control the communication module to establish connections with other electronic devices of the user (such as the user's mobile phone, tablet, etc.). The control module can also control the communication module to send image or video data, including pet data, processed by the image processing module of the tracking and capturing electronic device to other electronic devices of the user.

[0067] In some examples, the control module may include a main control chip, sensors, and a drive module. The main control chip can receive and send commands to control the tracking and filming electronic device to perform various actions and functions. Sensors may include distance sensors, orientation sensors, and speed sensors, which can be used to perceive environmental information, as well as the relative position and movement state between the pet and the robot, to achieve automatic tracking and filming. For example, a distance sensor can detect the distance between the robot and the pet, and an orientation sensor can detect the robot's direction and angle. The drive module can receive commands from the main control chip and drive the motion module of the tracking and filming electronic device to move and perform actions according to the commands. The specific type of control module included in the tracking and filming electronic device is not limited in the embodiments of this application.

[0068] The camera module can be used to film pets. It can also be used to track and capture images of pets.

[0069] In some examples, the camera module may include one or more cameras. When multiple cameras are included, they may include different types of cameras, such as zoom cameras, wide-angle cameras, etc. Wide-angle cameras can capture a wider field of view, so when tracking and filming electronic devices to capture pets, wide-angle cameras can help the tracking and filming electronic devices capture a more comprehensive scene, including the pet and its surrounding environment. Zoom cameras, on the other hand, have the function of adjusting the focus, allowing for shooting the pet at different distances without moving the tracking and filming electronic devices. Zoom cameras provide greater flexibility, allowing the photographer to adjust the focus as needed to better capture the pet's movements and expressions.

[0070] This application does not limit the specific type or number of cameras included in the camera module. It should be noted that in this application, the tracking and filming electronic device can also control the switching of cameras included in the camera module, or control the raising and lowering of cameras included in the camera module, through the control module, to better track and film pets.

[0071] The motion module can be used to adjust the movement and posture of the tracking and shooting electronic device, so that the camera module can track and shoot the pet and ensure that the pet to be tracked and shot is always within the focus range of the camera.

[0072] In some examples, the motion module may include moving devices such as motors, gears, and wheels, thereby enabling the tracking and filming electronic device to move and track and film the pet. The specific content of the motion module included in the tracking and filming electronic device is not limited in the embodiments of this application.

[0073] The algorithm module can include a user's private pet model. Using this model, the module can determine whether image frames captured by the camera module of the tracking and filming electronic device trigger a pet capture event, such as whether the image frames include the pet. The module can also use the user's private pet model to lock onto the capture target and track focus (i.e., identify the pet to be filmed and ensure it remains within the camera's focus range). Furthermore, the module can use the user's private pet model to determine the anthropomorphic sound data corresponding to the pet in the image or video data captured by the camera module.

[0074] A power module is used to provide the power required by the tracking and imaging electronic device. For example, a power module can typically be a rechargeable battery or an external power source. The specific type of power module is not limited in the embodiments of this application.

[0075] The image processing module can be used to process image or video data, including pet images, captured by the camera module of the tracking and capturing electronic device. For example, image processing can include operations such as noise reduction, color adjustment, and contrast enhancement to improve image quality. Image processing can also include adding anthropomorphic sound data of the pet to the captured image or video data.

[0076] The image processing module can also determine the pose adjustment data for the tracking and shooting electronic device based on the image or video data, including the pet, captured by the camera module. The control module of the tracking and shooting electronic device can then adjust the movement and posture of the device via the motion module, and adjust the camera's height or switching via the camera module, based on this pose adjustment data. For example, the image processing module can include image processing algorithms. These algorithms can be used to perform feature extraction, target recognition, optical flow, and other techniques on the image or video data, including the pet, captured by the camera module, to detect and track the position and movement trajectory of the pet or other target objects, thereby obtaining the pose adjustment data for the tracking and shooting electronic device.

[0077] The storage module can be used to store image or video data of the pet captured by the camera module included in the tracking and shooting electronic device, or to store image or video data of the pet processed by the image processing module included in the tracking and shooting electronic device.

[0078] The communication module can be used to control the connection between the communication module and other electronic devices of the user (such as the user's mobile phone, tablet, etc.). The control module can also be used to control the communication module to send image data or video data of the pet, processed by the image processing module of the tracking and capturing electronic device, to other electronic devices of the user.

[0079] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the tracking and capturing electronic device. In other embodiments, the tracking and capturing electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0080] The shooting methods described in the following embodiments can all be implemented in a tracking and shooting electronic device with the above-described hardware structure.

[0081] The following is in conjunction with the appendix Figure 3 The imaging method provided in the embodiments of this application will be described in detail. This imaging method can be applied to the above-mentioned... Figure 2 The tracking and imaging electronic device shown. For example... Figure 3 As shown, the photographing method may include the following steps S301-S316.

[0082] S301, Tracking and shooting electronic devices to acquire the first image frame data.

[0083] In the photographing method provided in this application embodiment, the tracking and shooting electronic device can acquire first image frame data, thereby determining whether to trigger a capture event based on the first image frame data.

[0084] In some examples, combined Figure 2 As shown, the tracking and shooting electronic device acquires the first image frame data, which can be achieved by the tracking and shooting electronic device acquiring the first image frame data through the camera module included in the tracking and shooting electronic device.

[0085] It should be noted that before acquiring the first image frame data, the tracking and shooting electronic device can perform pre-shooting. If the image frame data obtained from the pre-shooting meets the tracking and shooting conditions, the tracking and shooting electronic device can perform formal shooting, that is, acquire the first image frame data. If the image frame data obtained from the pre-shooting does not meet the tracking and shooting conditions, the tracking and shooting electronic device may not perform formal shooting, that is, it may not acquire the first image frame data.

[0086] In other words, before the tracking and shooting electronic device acquires the first image frame data, it can first acquire a preset number of image frames or acquire image frames within a preset time period. Afterward, the tracking and shooting electronic device can determine whether the preset number or preset time period of image frames meets the tracking and shooting conditions.

[0087] The tracking shooting conditions can be whether each image frame within a preset number of image frames or a preset duration includes the target pet information (i.e., whether each image includes the user's pet). Alternatively, the tracking shooting conditions can also be whether more than a preset number of image frames within a preset number of image frames or a preset duration include the target pet information (i.e., whether each image includes the user's pet), and whether the target pet information included in each image frame matches the pet's exciting moments information.

[0088] The "pet highlight moment" information can be the target pet's information, including the pet's actions, expressions, and sounds, matched with preset pet actions, expressions, and sounds. In other words, when the target pet information matches the "pet highlight moment" information, the tracking and recording electronic device can track and record the pet's highlight moment. Therefore, the tracking and recording electronic device can determine that tracking and recording the pet is necessary, and thus acquire the first image frame data. When the target pet information does not match the "pet highlight moment" information, the tracking and recording electronic device can determine that tracking and recording the pet will not record the highlight moment. Therefore, the tracking and recording electronic device can stop tracking and recording the pet, and thus does not acquire the first image frame data.

[0089] It should be noted that, once the tracking and shooting electronic device determines that the pre-captured image frame data meets the tracking and shooting conditions, the tracking and shooting electronic device can store the pre-captured image frame data, allowing the user to view the pre-captured image frame data (i.e., the pet's exciting moments) through the tracking and shooting electronic device. The tracking and shooting electronic device can also perform image processing on the pre-captured image frame data, such as adding anthropomorphic sound data corresponding to the pet, thereby improving the user experience.

[0090] The tracking and shooting electronic device can also process the image frame data obtained from the pre-captured image frame data and send the processed image frame data to the user's other electronic devices, thereby ensuring that the user can view the pre-captured image frame data (i.e., the pet's wonderful moments) even when the user is not at home, further improving the user experience.

[0091] In some examples, after the tracking and capturing electronic device obtains the pre-captured image frame data, it determines whether the pre-captured image frame data meets the tracking and capturing conditions. This can be achieved by the tracking and capturing electronic device using a user-owned pet big data model. In other words, the tracking and capturing electronic device can use the user-owned pet big data model to determine the target pet information in the pre-captured image frame data. Subsequently, the tracking and capturing electronic device can use both the user-owned pet big data model and the target pet information in the image frame data to determine whether the pre-captured image frame data meets the tracking and capturing conditions.

[0092] S302, The tracking and shooting electronic device determines whether the first image frame data triggers a capture event.

[0093] After the tracking and shooting electronic device acquires the first image frame data, it can determine whether the first image frame data triggers a capture event (in this embodiment, the capture event can also be referred to as a shooting condition).

[0094] If the tracking and capturing electronic device determines that the first image frame data has not triggered a capture event, the tracking and capturing electronic device may continue to acquire image frame data and determine whether the continued acquisition will trigger a capture event. That is, if the tracking and capturing electronic device determines that the first image frame data has not triggered a capture event, the tracking and capturing electronic device may continue to execute the above-described S301-S302.

[0095] If the tracking and shooting electronic device determines that the first image frame data triggers a capture event, the tracking and shooting electronic device can determine that the first image frame data includes the target pet. That is, if the tracking and shooting electronic device determines that the first image data triggers a capture event, the tracking and shooting electronic device can continue to execute the following S303.

[0096] In some examples, the tracking and capturing electronic device determines whether the first image frame data triggers a capture event, which can be achieved by using a user's private pet big model to determine whether the first image frame data triggers a capture event.

[0097] For example, a user's private pet big model may include a snapshot event sub-model. The snapshot event sub-model can be built upon a pet big model trained using a public database, by feeding in pet behavior data recorded on the device side, continuously strengthening its learning, and establishing the snapshot event sub-model included in the user's private pet big model. The public database may include pet information of different pets obtained through other user devices or through the network, such as image or video data of pets obtained through other user devices, or image or video data of different pets obtained through the network. Pet information may include pet facial expressions, pet actions, pet appearance, pet sounds, etc. The specific type of pet information is not limited in this application embodiment. Pet facial expressions may include information such as the pet smiling or sticking out its tongue. Pet actions may include information such as the pet stretching, rolling, running, and jumping. Pet appearance information may include information such as the pet's face, coat color, and markings. Pet sounds may include the sounds corresponding to the pet when performing different actions.

[0098] It should be noted that pet information can also include information about the pet's highlights, such as the pet's facial expressions (e.g., the pet sticking out its tongue), the pet's actions (e.g., the pet rolling around), and the sounds the pet makes when it rolls around.

[0099] Pet behavior data recorded on the device side, i.e., the user's pet information. The user's pet information may include pet information from image data or video data of the pet locally stored on the tracking and recording electronic device, or pet information from image data or video data of the pet stored on other electronic devices of the user under the same user account.

[0100] In other words, the tracking and capturing electronic device can first obtain pet information from different pets through other user devices or through the network, and then train a large-scale pet model using this information to obtain a public pet model. Next, the tracking and capturing electronic device can obtain pet information from the user's pets, including pet information from local image data or video data, as well as pet information from other electronic devices belonging to the same user account. Then, the tracking and capturing electronic device can use this pet information to train the public pet model, thereby obtaining a user-specific pet model including capture event sub-models. The pet model can be a machine learning model, or other models; this embodiment does not limit the specific type of pet model.

[0101] It should be noted that the snapshot event sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device, or it can be trained by other electronic devices and sent to the tracking and shooting electronic device. This application embodiment does not limit this; the embodiment is illustrated by the example that the snapshot event sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device.

[0102] For example, the training process of the snapshot event sub-model included in the large user-owned pet model can be as follows: Figure 4 As shown. Figure 4As shown, the tracking and shooting electronic device can acquire public data of the large model (i.e., pet information of different pets obtained through other user devices or through the network), such as (image / video data of cats / dogs' faces, tongues sticking out, smiling, stretching, rolling, running, jumping, etc.), as well as private data of the large model (i.e., pet information of the user's pets), such as pet information recorded on the device side (the tracking and shooting electronic device or other electronic devices of the user under the same user account as the tracking and shooting electronic device), and incorporate its own pet characteristics to further enhance learning. The tracking and shooting electronic device trains the pet large model through the public and private data of the large model, thereby obtaining a user-owned pet large model with its own pet characteristics that can judge pet behavior, that is, the user-owned pet large model includes the snapshot event sub-model.

[0103] After obtaining a user-defined private pet model containing the pet's characteristics and capable of determining pet behavior (i.e., a snapshot event sub-model included in the user-defined private pet model), the tracking and capturing electronic device can acquire image frame data. Based on this acquired image frame data and the snapshot event sub-model within the user-defined private pet model, the tracking and capturing electronic device can determine whether the acquired image frame data triggers a snapshot event. When the acquired image frame data triggers a snapshot event, the tracking and capturing electronic device can track and capture images of the pet.

[0104] In some examples, the capture event may include the user's target pet (in this embodiment, the user's target pet can also be referred to as the user's pet) in the first image frame data. The user may have one or more target pets, and this embodiment does not limit this. This embodiment illustrates the scenario with one target pet. That is, when the user's target pet is included in the first image frame data, the tracking and capturing electronic device can determine whether the first image frame data triggers a capture event. When the user's target pet is not included in the first image frame data, the tracking and capturing electronic device can determine that the first image frame data has not triggered a capture event.

[0105] In other words, after acquiring the first image frame data, the tracking and capturing electronic device can determine whether the first image frame data includes the capture event sub-model within the user's private pet big model. If the first image frame data includes the user's target pet's pet information, the tracking and capturing electronic device can determine that the first image frame data triggered a capture event. If the first image frame data does not include the user's target pet's pet information, the tracking and capturing electronic device can determine that the first image frame data did not trigger a capture event.

[0106] In other examples, the capture event may include the user's target pet in the first image frame data, and the pet's information matches the pet's highlight moment information. The highlight moment information may include the pet's facial expressions, actions, and sounds. Facial expressions may include the pet smiling, sticking out its tongue, etc. Actions may include stretching, rolling, running, jumping, etc. Appearance information may include the pet's face, coat color, and markings. Sounds may include the sounds the pet makes when performing different actions.

[0107] In other words, after acquiring the first image frame data, the tracking and shooting electronic device can determine whether the first image frame data includes the pet information of the user's target pet through the capture event sub-model included in the user's private pet big model. If the first image frame data includes the pet information of the user's target pet, the tracking and shooting electronic device can determine whether the pet information of the target pet included in the first image frame data matches the pet's exciting moment information through the capture event sub-model included in the user's private pet big model.

[0108] If the first image frame data includes the user's target pet's pet information, and the user's target pet's pet information matches the pet's highlight moment information, the tracking and capturing electronic device can determine that the first image frame data triggered a capture event. If the first image frame data includes the user's target pet's pet information, but the user's target pet's pet information does not match the pet's highlight moment information, the tracking and capturing electronic device can determine that the first image frame data did not trigger a capture event.

[0109] In other words, the shooting conditions (i.e., the snapshot event) may include the user's pet being included in the first image frame data, or the user's pet being included in the first image frame data, and the user's pet's behavior meeting preset conditions. The preset conditions are that the user's pet's pet information matches the pet's highlight moment information. The shooting conditions (i.e., the snapshot event) may also include the user's pet being included in the first image frame data, or the user's pet being included in the first image frame data, and the user's pet's behavior meeting at least one of the preset conditions.

[0110] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device acquires the first image frame data through the camera module included in the tracking and shooting electronic device, the tracking and shooting electronic device can determine whether the first image frame data triggers a capture event through the algorithm module included in the tracking and shooting electronic device (that is, the algorithm module may include the capture event sub-model included in the user's private pet big model).

[0111] S303. The tracking and shooting electronic device determines the target pet information included in the first image frame data based on the first image frame data.

[0112] After the tracking and capturing electronic device determines that the first image frame data triggers a capture event, it can determine the target pet information included in the first image frame data (in this embodiment, the target pet information included in the first image frame data can also be referred to as the first target pet information), that is, determine the information of the target pet that needs to be tracked and captured. Therefore, the tracking and capturing electronic device can track and capture the target pet based on the target pet information.

[0113] In some examples, the target pet information includes the target pet's facial expressions, actions, appearance, and vocal information. This application does not limit the specific type of pet information. The target pet's facial expressions may include smiling, sticking out its tongue, etc. The target pet's actions may include stretching, rolling, running, jumping, etc. The target pet's appearance may include the pet's face, coat color, and markings. The target pet's vocal information may include the sounds the pet makes when performing different actions.

[0114] It should be noted that the target pet information may include the pet information of one of the user's pets, or it may include the pet information of multiple of the user's pets. This application embodiment does not limit this.

[0115] In some examples, the tracking and capturing electronic device determines the target pet information included in the first image frame data based on the first image frame data. This can be achieved by the tracking and capturing electronic device using a user's private pet big data model to determine whether the first image frame data triggers a capture event.

[0116] In other words, a user's private pet big model can include a target pet sub-model (also known as a segmentation model). The target pet sub-model can be built upon a pet big model trained using a public database, by feeding in pet behavior data recorded on the device side, continuously reinforcing the learning process, and establishing the target pet sub-model included in the user's private pet big model. The public database can include pet information from different pets obtained through other user devices or through the network, such as image or video data of pets obtained through other user devices, or image or video data of different pets obtained through the network.

[0117] Pet behavior data recorded on the device side, i.e., the user's pet information. The user's pet information may include pet information from image data or video data of the pet locally stored on the tracking and recording electronic device, or pet information from image data or video data of the pet stored on other electronic devices of the user under the same user account.

[0118] In other words, the tracking and filming electronic device can first obtain pet information from different user devices or through the network, and then train a large pet model using this information to obtain a public pet model. Next, the tracking and filming electronic device can obtain pet information from the user's own pets, including pet information from local image data or video data, as well as pet information from other electronic devices belonging to the same user account. Finally, the tracking and filming electronic device can use this pet information to train the public pet model, thereby obtaining the target pet sub-models included in the user's private pet model.

[0119] It should be noted that the target pet sub-models included in the user's private pet large model can be trained by the tracking and shooting electronic device, or they can be trained by other electronic devices and sent to the tracking and shooting electronic device. This application embodiment does not limit this; the embodiment is illustrated by the example that the target pet sub-models included in the user's private pet large model can be trained by the tracking and shooting electronic device.

[0120] For example, combining Figure 5 As shown, after the tracking and shooting electronic device determines that the first image frame data triggers the capture event, the tracking and shooting electronic device can determine the target pet information included in the first image frame data based on the first image frame data. That is, the tracking and shooting electronic device can segment the first image frame data through the target pet sub-model (i.e., the segmentation model) included in the user's private pet big model, thereby segmenting the target subject (i.e., the target pet information in the first image frame data) and the background (i.e., the information in the first image frame data other than the target pet information).

[0121] After the tracking and shooting electronic device segments the first image frame data to identify the target subject, it can perform instance tracking on the segmented target subject (i.e., the target pet information in the first image frame data), that is, track and shoot the target pet.

[0122] The tracking and capturing electronic device performs instance tracking on the segmented target subject (i.e., the target pet information in the first image frame data). This can include, after the tracking and capturing electronic device acquires subsequent image frame data, segmenting the subsequently acquired image frame data using a target pet sub-model to obtain the target subject in the subsequently acquired image frame data, and then matching the target subject in the subsequently acquired image frame data with the target pet information in the first image frame data. If the target subject in the subsequently acquired image frame data matches the target pet information in the first image frame data, it can be determined that the subsequently acquired image frame data is for instance tracking of the target pet in the first image frame data. If the target subject in the subsequently acquired image frame data does not match the target pet information in the first image frame data, it can be determined that the subsequently acquired image frame data is not for instance tracking of the target pet in the first image frame data.

[0123] It should be noted that, in combination Figure 5 As shown, when the tracking and shooting electronic device performs instance tracking on the segmented target subject (i.e., the target pet information in the first image frame data), it can also combine feature point recognition for instance tracking. Feature points serve as an auxiliary judgment for target pet tracking and shooting, which can improve the accuracy of the tracking and shooting electronic device in segmenting the target subject. That is, the tracking and shooting electronic device segments the subsequently acquired image frame data through the target pet sub-model to obtain the target subject in the subsequently acquired image frame data. Then, while matching the target subject in the subsequently acquired image frame data with the target pet information in the first image frame data, the tracking and shooting electronic device can also obtain the feature points of the user's pet and the feature points corresponding to the target subject in the subsequently acquired image frame data. The feature points of the user's pet may include the pet's breed, coat color, pattern, head-to-body ratio, leg-to-body ratio, etc. The feature points corresponding to the target subject in the subsequently acquired image frame data may include the pet's breed, coat color, pattern, head-to-body ratio, leg-to-body ratio, etc.

[0124] If the tracking and capturing electronic device determines that the feature points of the user's pet match the feature points of the target subject in the subsequently acquired image frame data, the tracking and capturing electronic device can determine that the target subject obtained by segmenting the subsequently acquired image frame data using the target pet sub-model is correct. Therefore, the tracking and capturing electronic device can determine that the subsequently acquired image frame data is image frame data for instance tracking of the target pet in the first image frame data. Conversely, if the tracking and capturing electronic device determines that the feature points of the user's pet do not match the feature points of the target subject in the subsequently acquired image frame data, the tracking and capturing electronic device can determine that the target subject obtained by segmenting the subsequently acquired image frame data using the target pet sub-model is incorrect. Therefore, the tracking and capturing electronic device can determine that the subsequently acquired image frame data is not image frame data for instance tracking of the target pet in the first image frame data.

[0125] When necessary, such as Figure 5 As shown, during the tracking and shooting process of the electronic device, reinforcement learning can also be performed on the target pet sub-model included in the user's private pet big model. That is, during the tracking process, pet image frames are continuously acquired and hot-swapped to train the private pet big model (i.e., the target pet sub-model), thereby obtaining the private pet big model (i.e., the target pet sub-model) to improve the accuracy of tracking and judging the target (i.e., the target pet).

[0126] In some examples, after the tracking and capturing electronic device determines the target pet information included in the first image frame data based on the target pet information included in the first image frame data, the tracking and capturing electronic device can also determine the composition information of the target pet in the first image frame data based on the target pet information included in the first image frame data. Composition information refers to the positional information of the target pet in the first image frame data.

[0127] In some examples, the composition information can be the golden ratio. The golden ratio is a commonly used photographic composition method that divides the frame into thirds and uses the golden ratio points and lines to arrange the position of the subject, creating a balanced, harmonious, and captivating visual effect. At the same time, a three-dimensional composition can enhance the sense of depth and visual impact of a photograph, making it more vivid and three-dimensional.

[0128] In other words, if the first image frame data meets the shooting conditions, the first target pet information in the first image frame data is determined by the user's private pet model.

[0129] In some examples, combined Figure 2As shown, after the tracking and shooting electronic device determines the first image frame data to trigger the capture event through the algorithm module included in the tracking and shooting electronic device (i.e., the algorithm module may include the target pet sub-model included in the user's private pet big model), the tracking and shooting electronic device can determine the target pet information included in the first image frame data based on the first image frame data through the algorithm module included in the tracking and shooting electronic device.

[0130] S304. The tracking and shooting electronic device determines the first predicted image frame data and the target pet information corresponding to the first predicted image frame data based on the first image frame data.

[0131] After the tracking and capturing electronic device determines that the first image frame data triggers a capture event, it can determine the first predicted image frame data and the target pet information corresponding to the first predicted image frame data (in this embodiment, the target pet information corresponding to the first predicted image frame data can also be referred to as the first predicted target pet information). Therefore, the tracking and capturing electronic device can determine the accuracy of the target pet information in the next image frame data acquired by it through the first predicted image frame data and the target pet information corresponding to the first predicted image frame data.

[0132] In some examples, the tracking and shooting electronic device determines the first predicted image frame data and the target pet information corresponding to the first predicted image frame data based on the first image frame data. This can be achieved by the tracking and shooting electronic device determining the first predicted image frame data through a user-owned private pet big model and obtaining the target pet information corresponding to the first predicted image frame data through the user-owned private pet big model and the first predicted image frame data.

[0133] In other words, a user-owned private pet model can include a pet prediction sub-model. This pet prediction sub-model can be built upon a user-owned private pet model trained on a public database, by feeding in pet behavior data recorded on the device side and continuously reinforcing the learning process. The public database can include the next image frame data after the first image frame data obtained from other user devices or via the network, such as image or video data of the pet from other user devices, or the next image frame data after the first image frame data obtained from the network.

[0134] The pet behavior data recorded on the device side may include the next image frame data after the user's first image frame data. The next image frame data after the user's first image frame data may include the next image frame data after the first image frame data in the image data or video data of the pet locally on the tracking and shooting electronic device, or it may include the next image frame data after the first image frame data in the image data or video data of the pet on other electronic devices of the user under the same user account.

[0135] In other words, the tracking and recording electronic device can first acquire the next image frame data after the first image frame data from other user devices or through the network, and then train the large pet model using this next image frame data to obtain a public pet model. Subsequently, the tracking and recording electronic device can acquire the next image frame data after the first image frame data from the user, i.e., the next image frame data after the first image frame data in local image data or video data including the pet, as well as the next image frame data after the first image frame data in image data or video data including the pet from other electronic devices of the user under the same user account. Then, the tracking and recording electronic device can use the next image frame data after the first image frame data from the user to train the public pet model, thereby obtaining the pet prediction sub-model included in the user's private pet model.

[0136] It should be noted that the pet prediction sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device, or it can be trained by other electronic devices and sent to the tracking and shooting electronic device. This application embodiment does not limit this; the embodiment is illustrated by the example that the pet prediction sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device.

[0137] After the tracking and shooting electronic device acquires the first image frame data, it can obtain the first predicted image frame data (i.e., the next image frame data after the predicted first image frame data) based on the first image frame data and the pet prediction sub-model included in the user's private pet big model. Then, the tracking and shooting electronic device can obtain the target pet information corresponding to the first predicted image frame data using the first predicted image frame data and the target pet sub-model included in the user's private pet big model.

[0138] For example, combining Figure 5As shown, after the tracking and shooting electronic device segments the first image frame data to extract the target subject, the tracking and shooting electronic device can perform instance tracking on the segmented target subject (i.e., the target pet information in the first image frame data), that is, track and shoot the target pet.

[0139] When the tracking and shooting electronic device performs instance tracking on the segmented target subject (i.e., the target pet information in the first image frame data), the tracking and shooting electronic device can perform large model prediction. That is, the tracking and shooting electronic device can obtain the first predicted image frame data (i.e. the next image frame data of the predicted first image frame data) based on the first image frame data and the pet prediction sub-model included in the user's private pet large model.

[0140] Subsequently, the tracking and capturing electronic device can obtain the target pet information corresponding to the first predicted image frame data using the first predicted image frame data and the target pet sub-model included in the user's private pet big model. Therefore, the tracking and capturing electronic device can determine the accuracy of the target pet information in the next image frame data acquired by the tracking and capturing electronic device using the first predicted image frame data and the corresponding target pet information. In other words, the tracking and capturing electronic device can use the big model's judgment of the next frame as a discriminator, and improve the accuracy of target segmentation by comprehensively considering the predictions of the big model.

[0141] It should be noted that the execution order of S303 and S304 is not limited in this embodiment. That is, S303 can be executed first and then S304, or S304 can be executed first and then S303, or both S303 and S304 can be executed simultaneously. This embodiment is illustrated by taking the example of executing S303 first and then S304.

[0142] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device determines the first image frame data and triggers the capture event through the algorithm module included in the tracking and shooting electronic device (i.e., the algorithm module may include the target pet sub-model included in the user's private pet big model), the tracking and shooting electronic device can determine the first predicted image frame data and the target pet information corresponding to the first predicted image frame data based on the first image frame data through the algorithm module included in the tracking and shooting electronic device.

[0143] S305 The tracking and shooting electronic device obtains the second image frame data based on the pet information corresponding to the previous image frame data.

[0144] After the tracking and shooting electronic device determines the first predicted image frame data and the target pet information corresponding to the first predicted image frame data based on the first image frame data, the tracking and shooting electronic device can obtain the second image frame data based on the pet information corresponding to the previous image frame data. That is, the tracking and shooting electronic device can track and shoot the target pet based on the pet information corresponding to the previous image frame data, thereby obtaining the second image frame data including the target pet.

[0145] It should be noted that the second image frame data can be the image frame data following the first image frame data, or it can be the image frame data following the image frame data after the first image frame data. This embodiment does not limit this. That is, if the first image frame data meets the shooting conditions, the tracking and shooting electronic device can acquire the second image frame data.

[0146] In some examples, the tracking and capturing electronic device obtains the second image frame data based on the pet information corresponding to the previous image frame data. This may include the tracking and capturing electronic device determining posture adjustment information based on the pet information corresponding to the previous image frame data. Then, the tracking and capturing electronic device can adjust its posture according to the posture adjustment information, thereby obtaining the second image frame data based on the adjusted posture.

[0147] In some examples, the posture adjustment information may include movement information of the tracking and shooting electronic device (such as the direction of movement, distance of movement, etc.) and adjustment information of the camera module included in the tracking and shooting electronic device (such as switching of cameras, raising and lowering of cameras, and adjustment of camera angles, etc.). This application does not limit the specific types of posture adjustment information included in its embodiments.

[0148] In some examples, when the previous image frame data is the first image frame data, the electronic device determines the posture adjustment information of the tracking and shooting electronic device based on the pet information corresponding to the previous image frame data. This can be achieved by the tracking and shooting electronic device obtaining the target pet's movement information (such as movement distance, movement direction, etc.) based on the pet information corresponding to the first image frame data and the target pet information corresponding to the first predicted image frame data. Then, the tracking and shooting electronic device can determine its posture adjustment information based on the target pet's movement information. It should be noted that when the tracking and shooting electronic device determines its posture adjustment information based on the target pet's movement information, it can combine this information with the target pet's composition information in the first image frame data. That is, the posture adjustment information of the tracking and shooting electronic device ensures that the target pet's composition information in the second image frame data acquired by the tracking and shooting electronic device is the same as the target pet's composition information in the first image frame data.

[0149] For example, if the composition information of the target pet in the first image frame data is the golden ratio, the tracking and shooting electronic device can determine the posture adjustment information of the tracking and shooting electronic device based on the movement information of the target pet and the composition information of the target pet in the first image frame data. This can ensure that the composition information of the target pet in the second image frame data acquired by the tracking and shooting electronic device is also the golden ratio, thereby ensuring the shooting quality.

[0150] In some examples, combined Figure 2 As shown, after the tracking and capturing electronic device determines the first predicted image frame data and the corresponding target pet information based on the first image frame data using its algorithm module, the tracking and capturing electronic device can determine its posture adjustment information based on the pet information corresponding to the previous image frame data using its algorithm module. Then, the tracking and capturing electronic device can adjust its posture based on the posture adjustment information using its motion module. Finally, the tracking and capturing electronic device can acquire the second image frame data using its camera module.

[0151] S306. The tracking and shooting electronic device determines the target pet information included in the second image frame data based on the second image frame data.

[0152] After the tracking and capturing electronic device acquires the second image frame data, it can determine the target pet information included in the second image frame data (in this embodiment, the target pet information included in the second image frame data can also be referred to as the second target pet information). Therefore, the tracking and capturing electronic device can determine whether the subject segmentation of the second image frame data is accurate based on the target pet information included in the second image frame data and the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data, i.e., whether the target pet information included in the second image frame data is accurate.

[0153] In some examples, the tracking and capturing electronic device determines the target pet information included in the second image frame data based on the second image frame data. This can be achieved by the tracking and capturing electronic device using a target pet sub-model (i.e., a segmentation model) to determine the target pet information included in the second image frame data.

[0154] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device obtains the second image frame data based on the pet information corresponding to the previous image frame data, the tracking and shooting electronic device can determine the target pet information included in the second image frame data based on the second image frame data through the algorithm module (the algorithm module includes the target pet sub-model).

[0155] It should be noted that after the tracking and shooting electronic device acquires the second image frame data, it can also determine the predicted image frame data corresponding to the second image frame data through the pet prediction sub-model included in the user's private pet big model, and determine the target pet information included in the predicted image frame data corresponding to the second image frame data through the target pet sub-model included in the user's private pet big model. Therefore, when the tracking and shooting electronic device acquires the next image frame data, it can determine whether the target pet information included in the predicted image frame data corresponding to the second image frame data matches the target pet information included in the next image frame data.

[0156] In other words, if the first image frame data meets the shooting conditions, the tracking and shooting electronic device can determine the first target pet information in the first image frame data through the user's private pet model. Then, the tracking and shooting electronic device can acquire the second image frame data and determine the second target pet information in the second image frame data through the user's private pet model. Afterwards, based on the first and second target pet information, the tracking and shooting electronic device can track and shoot the user's pet to obtain the third image frame data. The specific process of the tracking and shooting electronic device acquiring the third image frame data can be referred to in S307-S313 below.

[0157] S307. The tracking and shooting electronic device determines whether the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data.

[0158] After the tracking and shooting electronic device determines the target pet information included in the second image frame data based on the second image frame data, the tracking and shooting electronic device can determine whether the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data.

[0159] In some examples, the tracking and capturing electronic device determines whether the target pet information included in the second image frame data matches the target pet information in the predicted image frame data corresponding to the previous image frame data. This can be achieved by the tracking and capturing electronic device determining the feature information corresponding to the target pet information included in the second image frame data, and the feature information corresponding to the target pet information in the predicted image frame data corresponding to the previous image frame data. Then, the tracking and capturing electronic device determines whether the feature information corresponding to the target pet information included in the second image frame data matches the feature information corresponding to the target pet information in the predicted image frame data corresponding to the previous image frame data.

[0160] If the tracking and shooting electronic device determines that the target pet information included in the second image frame data does not match the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data, the tracking and shooting electronic device can re-determine the target pet information included in the second image frame data, that is, it can continue to execute the following S308-S309.

[0161] If the tracking and shooting electronic device determines that the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data, the following S310 can continue to be executed.

[0162] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device determines the target pet information included in the second image frame data based on the second image frame data through the algorithm module (the algorithm module includes a target pet sub-model), the tracking and shooting electronic device can determine whether the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data through the algorithm module included in the tracking and shooting electronic device.

[0163] S308 The tracking and shooting electronic device re-determines the target pet information included in the second image frame data based on the second image frame data and the target pet information corresponding to the previous predicted image frame data.

[0164] If the tracking and shooting electronic device determines that the target pet information included in the second image frame data does not match the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data, the tracking and shooting electronic device can re-determine the target pet information included in the second image frame data (in this embodiment, the re-determined target pet information included in the second image frame data can also be referred to as the third target pet information corresponding to the second image frame data).

[0165] It should be noted that the previous predicted image frame data can be the predicted image frame data corresponding to the image frame data preceding the second image frame data. When the second image frame data is the next image frame data of the first image frame data, the previous predicted image frame data can be the first predicted image frame data corresponding to the first image frame data. When the second image frame data is the next image frame data after the first image frame data, the previous predicted image frame data can be the predicted image frame data corresponding to that next image frame data. This application does not impose limitations on this aspect in its embodiments.

[0166] In some examples, the tracking and capturing electronic device redetermines the target pet information included in the second image frame data based on the target pet information corresponding to the previous predicted image frame data. This can be achieved by the tracking and capturing electronic device using the target pet sub-models included in the user's private pet big model. Then, the tracking and capturing electronic device can compare the target pet information included in the second image frame data with the target pet information corresponding to the first predicted image frame data. Target pet information in the second image frame data that is identical to the target pet information corresponding to the first predicted image frame data is used to redetermine the target pet information included in the second image frame data. Thus, the tracking and capturing electronic device can continue tracking and capturing the target pet information included in the redetermined second image frame data. Target pet information in the second image frame data that is different from the target pet information corresponding to the first predicted image frame data is used to determine the background information included in the second image frame data.

[0167] In other words, if the information of the second target pet does not match the information of the first target pet, the tracking and shooting electronic device can determine that the pet information in the second target pet information that matches the information of the first target pet information to a degree greater than a preset threshold is the third target pet information corresponding to the second image frame data. The specific value of the preset threshold can be set according to the actual situation, and this application embodiment does not limit it.

[0168] For example, when the target pet information corresponding to the first image frame data is the pet information of one of the user's pets, the tracking and shooting electronic device can determine the pet information of that pet based on the first image frame data and the target pet sub-model included in the user's private pet big model. Then, using the pet prediction sub-model included in the user's private pet big model, the tracking and shooting electronic device can obtain the first predicted image frame data corresponding to the first image frame data. Afterward, based on the first predicted image frame data and the target pet sub-model included in the user's private pet big model, the tracking and shooting electronic device can determine the pet information of that pet, thus obtaining the target pet information corresponding to the first predicted image frame data (such as the pet information of two pets).

[0169] Subsequently, the tracking and capturing electronic device can compare the target pet information included in the second image frame data with the target pet information corresponding to the first predicted image frame data. The target pet information in the second image frame data that is identical to the target pet information corresponding to the first predicted image frame data (i.e., information about the same pet) is used to redetermine the target pet information included in the second image frame data. The target pet information in the second image frame data that is different from the target pet information corresponding to the first predicted image frame data (i.e., information about another pet) is used to determine the background information included in the second image frame data.

[0170] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device determines the target pet information included in the second image frame data based on the second image frame data using the algorithm module (which includes a target pet sub-model), the tracking and shooting electronic device can use the algorithm module to determine whether the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data of the previous image frame data. If the target pet information included in the second image frame data does not match the target pet information corresponding to the predicted image frame data of the previous image frame data, the algorithm module can use the pet prediction sub-model included in the user's private pet model to re-determine the target pet information included in the second image frame data based on the second image frame data and the target pet information corresponding to the previous predicted image frame data.

[0171] S309. The tracking and shooting electronic device determines the posture adjustment information of the tracking and shooting electronic device based on the pet information corresponding to the previous image frame data and the target pet information included in the newly determined second image frame data.

[0172] After the tracking and capturing electronic device re-determines the target pet information included in the second image frame data based on the second image frame data and the target pet information corresponding to the first predicted image frame data, the tracking and capturing electronic device can determine its posture adjustment information (which can also be referred to as the second posture adjustment information in this embodiment) based on the pet information corresponding to the first image frame data and the re-determined target pet information included in the second image frame data. Thus, the tracking and capturing electronic device can adjust its posture based on the posture adjustment information. That is, after the tracking and capturing electronic device determines its posture adjustment information, it can continue to execute S311 below.

[0173] In some examples, the tracking and capturing electronic device determines its posture adjustment information based on the pet information corresponding to the first image frame data and the target pet information included in the redefined second image frame data. Alternatively, the tracking and capturing electronic device can determine its posture adjustment information based on the pet information corresponding to the previous image frame data and the target pet information included in the redefined second image frame data. Then, the tracking and capturing electronic device can adjust its posture according to the posture adjustment information, thereby continuing tracking and capturing with the adjusted posture, i.e., re-acquiring the second image frame data.

[0174] In some examples, the posture adjustment information may include movement information of the tracking and shooting electronic device (such as the direction of movement, distance of movement, etc.) and adjustment information of the camera module included in the tracking and shooting electronic device (such as switching of cameras, raising and lowering of cameras, and adjustment of camera angles, etc.). This application does not limit the specific types of posture adjustment information included in its embodiments.

[0175] In some examples, when the previous image frame data is the first image frame data, the electronic device determines the posture adjustment information of the tracking and shooting electronic device based on the pet information corresponding to the previous image frame data. This can be achieved by the tracking and shooting electronic device obtaining the target pet's movement information (such as movement distance, movement direction, etc.) based on the pet information corresponding to the first image frame data and the target pet information corresponding to the first predicted image frame data. Then, the tracking and shooting electronic device can determine its posture adjustment information based on the target pet's movement information. It should be noted that when the tracking and shooting electronic device determines its posture adjustment information based on the target pet's movement information, it can combine this information with the target pet's composition information in the first image frame data. That is, the posture adjustment information of the tracking and shooting electronic device ensures that the target pet's composition information in the second image frame data acquired by the tracking and shooting electronic device is the same as the target pet's composition information in the first image frame data.

[0176] In some examples, combined Figure 2 As shown, in the algorithm module included in the tracking and shooting electronic device, after the pet prediction sub-model included in the user's private pet big model redetermines the target pet information included in the second image frame data based on the second image frame data and the target pet information corresponding to the previous predicted image frame data, the algorithm module included in the tracking and shooting electronic device can determine the posture adjustment information of the tracking and shooting electronic device based on the pet information corresponding to the previous image frame data and the target pet information included in the redetermined second image frame data.

[0177] It should be noted that the tracking and capturing electronic device can determine its posture adjustment information based on the pet information corresponding to the previous image frame and the target pet information included in the newly determined second image frame. The tracking and capturing electronic device can also determine its posture adjustment information based on the pet information corresponding to multiple (e.g., 10) image frames preceding the second image frame and the target pet information included in the newly determined second image frame. In other words, the tracking and capturing electronic device can predict its posture adjustment information for a subsequent period (e.g., when it subsequently acquires 10 image frames) based on multiple image frames preceding the second image frame.

[0178] For example, when the tracking and capturing electronic device determines its posture adjustment information based on the pet information corresponding to the preceding 10 image frames and the target pet information included in the newly determined second image frame data, the tracking and capturing electronic device can adjust its posture accordingly. Afterward, the tracking and capturing electronic device can reacquire 10 image frames (i.e., reacquire 10 second image frames) in the adjusted posture. After reacquiring these 10 image frames, the tracking and capturing electronic device can redetermine its posture adjustment information based on these reacquired image frames.

[0179] S310, The tracking and shooting electronic device determines the posture adjustment information of the tracking and shooting electronic device based on the target pet information in the previous image frame data and the target pet information in the second image frame data.

[0180] If the tracking and capturing electronic device determines that the target pet information included in the second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data, the tracking and capturing electronic device can determine the posture adjustment information of the tracking and capturing electronic device (which can also be referred to as the first posture adjustment information in this embodiment) based on the target pet information in the first image frame data and the target pet information in the second image frame data. That is, after the tracking and capturing electronic device determines the posture adjustment information of the tracking and capturing electronic device, it can continue to execute the following S311.

[0181] In this embodiment, the specific process by which the tracking and shooting electronic device determines its posture adjustment information based on the target pet information in the first image frame data and the target pet information in the second image frame data can be referred to in S309 above, where the tracking and shooting electronic device determines its posture adjustment information based on the pet information corresponding to the previous image frame data and the target pet information included in the newly determined second image frame data. This process will not be repeated in this embodiment.

[0182] S311. The tracking and shooting electronic device adjusts its posture according to the posture adjustment information, and reacquires the second image frame data based on the adjusted posture.

[0183] After determining the attitude adjustment information of the tracking and shooting electronic device, the tracking and shooting electronic device can adjust its attitude according to the attitude adjustment information, and reacquire the second image frame data based on the adjusted attitude.

[0184] In other words, when the information of the second target pet matches the information of the first predicted target pet, the tracking and capturing electronic device can determine its first posture adjustment information based on both the first and second target pet information. Then, the tracking and capturing electronic device can adjust its posture based on this first posture adjustment information to obtain its first posture. Afterward, the tracking and capturing electronic device can acquire fourth image frame data using this first posture. The third image frame data may include the fourth image frame data.

[0185] If the second target pet information does not match the first target pet information, the tracking and capturing electronic device can identify the pet information in the second target pet information whose matching degree with the first target pet information is greater than a preset threshold as the third target pet information corresponding to the second image frame data. Then, the tracking and capturing electronic device can determine its second posture adjustment information based on the first and third target pet information. Next, the tracking and capturing electronic device can adjust its posture based on the second posture adjustment information to obtain its second posture. Then, the tracking and capturing electronic device can acquire the fifth image frame data through the second posture. The third image frame data includes the fifth image frame data. That is, the reacquired second image frame data can be the third image frame data, and the reacquired second image frame data can include both the fourth and fifth image frame data.

[0186] In some examples, combined Figure 2 As shown, after the algorithm module of the tracking and shooting electronic device determines the attitude adjustment information of the device, the motion module can adjust the attitude of the device based on this information. After the attitude adjustment, the tracking and shooting electronic device can reacquire the second image frame data through its camera module, thus continuing the tracking and shooting process.

[0187] It should be noted that after the tracking and capturing electronic device adjusts its posture according to the posture adjustment information and reacquires the second image frame data based on the adjusted posture, the tracking and capturing electronic device can continue to determine the target pet information included in the reacquired second image frame data. Then, the tracking and capturing electronic device can determine whether the target pet information included in the reacquired second image frame data matches the target pet information corresponding to the predicted image frame data corresponding to the previous image frame data (i.e., the second image frame data). In other words, after the tracking and capturing electronic device reacquires the second image frame data, it can continue to execute the above-described S306-S310 steps.

[0188] It should be noted that after the tracking and shooting electronic device adjusts its posture according to the posture adjustment information and reacquires the second image frame data based on the adjusted posture, the tracking and shooting electronic device can also determine whether the stopping shooting condition is met, that is, the tracking and shooting electronic device can continue to execute S312 below. After the stopping shooting condition is met, the tracking and shooting electronic device can stop tracking and shooting.

[0189] S312. The tracking and shooting electronic device determines whether the conditions for stopping shooting are met.

[0190] After the tracking and shooting electronic device adjusts its posture according to the posture adjustment information, and reacquires the second image frame data based on the adjusted posture, the tracking and shooting electronic device determines whether the shooting stop condition is met.

[0191] In some examples, the stop-shooting condition may include the absence of the user's target pet in the reacquired second image frame data. That is, if the user's target pet is not present in the reacquired second image frame data, the tracking and shooting electronics can determine that the stop-shooting condition is met. If the user's target pet is present in the reacquired second image frame data, the tracking and shooting electronics can determine that the stop-shooting condition is not met.

[0192] The conditions for stopping recording can also include situations where the reacquired second image frame data includes the user's target pet, but the pet's information does not match the pet's highlight moment information. That is, if the reacquired second image frame data includes the user's target pet, but the pet's information does not match the pet's highlight moment information, the tracking and recording electronic device can determine that the conditions for stopping recording are met. Conversely, if the reacquired second image frame data includes the user's target pet, but the pet's information matches the pet's highlight moment information, the tracking and recording electronic device can determine that the conditions for stopping recording are not met.

[0193] In other words, the conditions for stopping filming can include either the third image frame data not including the user's target pet, or the third image frame data including the user's pet and the pet's behavior not meeting preset conditions, or the filming duration reaching a preset duration. The preset conditions are that the pet's information matches the pet's highlight moment information. The conditions for stopping filming can also include at least one of the following: the third image frame data not including the user's target pet, or the third image frame data including the user's pet and the pet's behavior not meeting preset conditions, or the filming duration reaching a preset duration.

[0194] If the tracking and shooting electronic device determines that the conditions for stopping shooting are met, the tracking and shooting electronic device may stop tracking and shooting, that is, the tracking and shooting electronic device may continue to execute S313-S316 below. If the tracking and shooting electronic device determines that the conditions for stopping shooting are not met, the tracking and shooting electronic device may continue tracking and shooting, that is, the tracking and shooting electronic device may continue to execute S305-S312 above.

[0195] In some examples, combined Figure 2 As shown, after the attitude adjustment of the tracking and shooting electronic device, the tracking and shooting electronic device can reacquire the second image frame data through its included camera module. Then, the tracking and shooting electronic device can determine through the algorithm module whether the reacquired second image frame data meets the conditions for stopping shooting.

[0196] S313, Tracking and capturing electronic equipment to determine image data of the target pet.

[0197] Once the tracking and recording electronic device determines that the conditions for stopping recording have been met, it can cease tracking and recording. The tracking and recording electronic device can also determine the image data of the target pet.

[0198] The target pet image data can include image frame data that triggers the capture event, as well as image frame data acquired by the tracking and capturing electronic device while tracking the target pet before the second image frame data, acquired after the capture event is triggered and before the shooting stop condition is met. In other words, the target pet image data can consist of multiple image frames. For example, when the second image frame data meets the shooting stop condition, the target pet image data can include both the first and second image frames.

[0199] It should be noted that if the reacquired second image frame data does not meet the conditions for stopping shooting, the tracking and shooting electronic device continues to track and shoot the target pet. That is, the tracking and shooting electronic device can determine that the target pet image data includes the reacquired second image frame data.

[0200] In other words, after acquiring the third image frame data, the tracking and shooting electronic device can determine whether the third image frame data meets the conditions for stopping shooting. If the third image frame data meets the conditions for stopping shooting, the tracking and shooting electronic device can determine that the target pet image frame data includes the first image frame data and the second image frame data.

[0201] If the third image frame data does not meet the stop shooting condition, the tracking and shooting electronic device can track and shoot the user's pet based on the third image frame data to obtain the sixth image frame data. The third image frame data includes the sixth image frame data, and the target pet image frame data includes the first image frame data, the second image frame data, and the third image frame data.

[0202] In some examples, combined Figure 2 As shown, after the tracking and shooting electronic device determines through the algorithm module that the reacquired second image frame data meets the stop shooting condition, the tracking and shooting electronic device can determine the target pet image data through the algorithm module. The target pet image data includes the first image frame data and the second image frame data.

[0203] S314. The tracking and shooting electronic device determines the anthropomorphic sound data of the pet corresponding to the target pet image data based on the target pet image data.

[0204] After the tracking and shooting electronic device determines the image data of the target pet, it can determine the anthropomorphic sound data of the pet corresponding to the image data.

[0205] In some examples, the tracking and recording electronic device determines the corresponding anthropomorphic sound data of the pet based on pet image data. This can be achieved by using a user-owned private pet model to determine the pet state corresponding to each target pet image data. Subsequently, the tracking and recording electronic device can determine the anthropomorphic sound data corresponding to the pet state of each target pet image data.

[0206] For example, a pet's status can include happy, hungry, and unhappy states. When a pet is in a hungry state, the corresponding anthropomorphic voice data could be something like "I'm hungry." When a pet is in a happy state, the corresponding anthropomorphic voice data could be something like "I'm happy."

[0207] In some examples, a user's private pet master model may include pet state sub-models. These pet state sub-models can be built upon a pet master model trained on a public database, by feeding in pet state data recorded on the device side, and continuously reinforcing the learning process to establish the pet state sub-models included in the user's private pet master model.

[0208] Public databases may include pet status data of different pets obtained through other user devices or through the network, such as pet image data or video data obtained through other user devices, or pet status data of different pets obtained through the network.

[0209] Pet status data can include pet facial expression data, pet body movement data, and pet vocal data. Pet facial expression data can include key facial features, eye data, ear data, mouth data, and tongue data. Pet body movement data can include movement direction data, movement distance data, and movement speed data. Pet vocal data can include pitch, volume, and timing data of the pet's vocalizations.

[0210] The pet status data recorded on the device side refers to the pet's status data for the user's pet. This pet status data can include image data or video data of the pet stored locally on the tracking and recording electronic device, or image data or video data of the pet stored on other electronic devices belonging to the same user account as the tracking and recording electronic device.

[0211] In other words, the tracking and recording electronic device can first obtain pet status data from different pets acquired through other user devices or via the network, and then train a large pet model using this data to obtain a public pet model. Next, the tracking and recording electronic device can acquire the user's pet status data, including pet status data from local image or video data, as well as pet status data from other electronic devices belonging to the same user account. Finally, the tracking and recording electronic device can use this pet status data to train the public pet model, thereby obtaining a pet status sub-model within the user's private pet model.

[0212] It should be noted that the pet status data sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device, or it can be trained by other electronic devices and sent to the tracking and shooting electronic device. This application embodiment does not limit this; the embodiment is illustrated by the example that the pet status data sub-model included in the user's private pet large model can be trained by the tracking and shooting electronic device.

[0213] In other words, after the tracking and capturing electronic device identifies the target pet's image data, it can determine the pet's state corresponding to each target pet image data using a pet state sub-model. After determining the pet's state for each target pet image data, the tracking and capturing electronic device can further determine the corresponding pet state and anthropomorphic sound data by establishing a correspondence between the pet's state and its anthropomorphic sound data.

[0214] It should be noted that the correspondence between pet status and anthropomorphic pet voice data can include the correspondence between pet status recorded on other electronic devices and anthropomorphic pet voice data, the correspondence between pet status recorded locally by the user on the tracking and recording electronic device and anthropomorphic pet voice data, and the correspondence between pet status recorded on other electronic devices of the user under the same user account as the tracking and recording electronic device and anthropomorphic pet voice data. This application embodiment does not limit this aspect.

[0215] For example, combining Figure 6 As shown, the tracking and shooting electronic device determines the anthropomorphic sound data of the pet corresponding to the target pet image data, which can also be called pet emotion understanding. After determining the target pet image data, the tracking and shooting electronic device can determine the pet state corresponding to each target pet image data through the pet state sub-model included in the user's private pet big model. That is, the tracking and shooting electronic device can analyze the pet's facial expressions (i.e., analyze the pet's facial key points, eyes, ears, mouth, tongue, etc.) in each target pet image data through the pet state sub-model included in the user's private pet big model, analyze the pet's body movements (i.e., analyze the three elements of the pet's body language movement direction, distance, and speed in each target pet image data, which can be calculated using three-dimensional information), and analyze the pet's vocalizations (i.e., analyze the three elements of the pet's voice pitch, volume, and time in the audio corresponding to each target pet image data, which can be represented by waveforms). Subsequently, the tracking and shooting electronic device can comprehensively analyze the pet's pet status (i.e., behavior or emotion) in each target pet image data through the pet status sub-model included in the user's private pet big model, thereby determining the anthropomorphic sound data corresponding to the pet status.

[0216] In some examples, combined Figure 2As shown, after the tracking and shooting electronic device determines the target pet image data through the algorithm module, it can then determine the pet state corresponding to each target pet image data through the algorithm module (i.e., the pet state sub-model included in the user's private pet big model). Subsequently, the tracking and shooting electronic device can determine the anthropomorphic sound data corresponding to the pet state for each target pet image data based on the correspondence between the pet state and the anthropomorphic sound data.

[0217] S315 The tracking and shooting electronic device obtains data on the pet's exciting moments based on the target pet image data and the pet's anthropomorphic sound data corresponding to the target pet image data.

[0218] After the tracking and recording electronic device determines the anthropomorphic sound data corresponding to the target pet's image data, it can then obtain the pet's highlight moments data based on both the target pet's image data and its corresponding anthropomorphic sound data. Once obtained, the tracking and recording electronic device can store these highlight moments data, allowing users to view them on their devices.

[0219] In some examples, combined Figure 2 As shown, the tracking and shooting electronic device can determine the anthropomorphic sound data corresponding to the pet state for each target pet image data by using the algorithm module based on the correspondence between the pet state and the pet anthropomorphic sound data. Then, the tracking and shooting electronic device can use its image processing module to synthesize the target pet image data and the pet anthropomorphic sound data corresponding to the target pet image data to obtain the pet's exciting moments data.

[0220] S316, Tracking and recording electronic devices send pet's exciting moments data to the user's other electronic devices.

[0221] After the tracking and recording electronic device obtains and stores the pet's highlight moments based on pet image data and corresponding anthropomorphic pet sound data, it can send these highlights to the user's other electronic devices. The user can then view these highlights on other devices.

[0222] It should be noted that the user's other electronic devices can be connected to the tracking and recording electronic device, allowing the tracking and recording electronic device to send data on the pet's exciting moments to the user's other electronic devices through the established connection.

[0223] In other words, after the tracking and capturing electronic device acquires the third image frame data, it can determine the target pet image data corresponding to the user's pet based on the first, second, and third image frame data. Then, based on the target pet image frame data and the user's private pet model, the tracking and capturing electronic device can determine the pet's state corresponding to the target pet image frame data. Next, based on the pet's state, the tracking and capturing electronic device can obtain the anthropomorphic sound data corresponding to the target pet image frame data. Finally, the tracking and capturing electronic device can synthesize the target pet image frame data and its corresponding anthropomorphic sound data to obtain the target pet's highlight moments data. Finally, the tracking and capturing electronic device can send the target pet's highlight moments data to the user's other electronic devices.

[0224] The solution proposed in this application allows the tracking and shooting electronic device to track and photograph the target pet when the pet's image frame data triggers a pet capture event. Therefore, the tracking and shooting electronic device can still track and photograph the pet even when the user is not at home, thereby improving the user experience. Furthermore, because the tracking and shooting electronic device can adjust its posture to track and photograph the target pet, this solution will not lose track of the pet, thus ensuring that adorable and memorable moments of the pet are captured.

[0225] Furthermore, the solution in this application allows the tracking and recording electronic device to send the captured image or video data of the pet to other devices of the user (such as the user's mobile phone), enabling the user to view the captured images or videos on other electronic devices. Therefore, this solution allows users to see their pet's adorable and exciting moments even when they are not at home, thus further enhancing the user experience.

[0226] Corresponding to the methods in the foregoing embodiments, this application also provides a shooting device. This shooting device can be applied to an electronic device to implement the methods in the foregoing embodiments. The functions of the shooting device can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0227] For example, Figure 7 A schematic diagram of the structure of a shooting device 700 is shown, as follows: Figure 7 As shown, the shooting device 700 may include: an acquisition module 701, a determination module 702, etc.

[0228] The acquisition module 701 can be used to acquire the first image frame data.

[0229] The determination module 702 can be used to determine whether the first image frame data meets the shooting conditions based on the user's private pet model.

[0230] The determination module 702 can also be used to determine the first target pet information in the first image frame data by means of a user-owned pet model, provided that the first image frame data meets the shooting conditions.

[0231] The acquisition module 701 can also be used to acquire second image frame data.

[0232] The determination module 702 can also be used to determine the second target pet information in the second image frame data through the user's private pet model.

[0233] The acquisition module 701 can also be used to track and photograph the user's pet based on the first target pet information and the second target pet information to obtain third image frame data.

[0234] It should be understood that the division of units or modules (hereinafter referred to as units) in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, all units in the device can be implemented in software through processing element calls; all units can be implemented in hardware; or some units can be implemented in software through processing element calls, and some units can be implemented in hardware.

[0235] For example, each unit can be a separate processing element, or it can be integrated into a chip within the device. Alternatively, it can be stored as a program in memory, invoked and executed by a processing element within the device. Furthermore, these units can be integrated in whole or in part, or implemented independently. The processing element described here can also be called a processor, which can be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each of the above units can be implemented through integrated logic circuits in the processor element or through software invoked by the processing element.

[0236] In one example, the unit in the above device may be one or more integrated circuits configured to implement the above methods, such as one or more ASICs, or one or more DSPs, or one or more FPGAs, or a combination of at least two of these integrated circuit forms.

[0237] For example, when the units in the device can be implemented through a processing element scheduler, the processing element can be a general-purpose processor, such as a CPU or other processor capable of calling programs. Alternatively, these units can be integrated together to form a system-on-a-chip (SoC).

[0238] In one implementation, the units that implement the corresponding steps in the above methods can be implemented in the form of a processing element scheduler. For example, the device may include a processing element and a storage element, wherein the processing element calls a program stored in the storage element to execute the methods described in the above embodiments. The storage element may be a storage element located on the same chip as the processing element, i.e., an on-chip storage element.

[0239] In another implementation, the program for performing the above methods can be located on a storage element on a different chip than the processing element, i.e., an off-chip storage element. In this case, the processing element calls or displays the program from the off-chip storage element to the on-chip storage element to call and execute the methods described in the above method embodiments.

[0240] For example, embodiments of this application may also provide an apparatus, such as an electronic device, which may include a processor and a memory for storing processor-executable instructions. When the processor is configured to execute the aforementioned instructions, the electronic device implements the imaging method described in the foregoing embodiments. The memory may be located within or outside the electronic device. Furthermore, the processor may include one or more processors.

[0241] In another implementation, the unit implementing each step of the above method can be configured as one or more processing elements, which can be disposed on the corresponding electronic device described above. These processing elements can be integrated circuits, such as one or more ASICs, one or more DSPs, one or more FPGAs, or combinations of these types of integrated circuits. These integrated circuits can be integrated together to form a chip.

[0242] For example, this application also provides a chip that can be applied to the aforementioned electronic device. The chip includes one or more interface circuits and one or more processors; the interface circuits and processors are interconnected via lines; the processor receives and executes computer instructions from the electronic device's memory through the interface circuits to implement the methods described in the above method embodiments.

[0243] This application also provides a computer program product, including computer instructions for operation of the electronic device described above.

[0244] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0245] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0246] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0247] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0248] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to related technologies, or all or part of the technical solutions, can be embodied in the form of a software product, such as a program. This software product is stored in a program product, such as a computer-readable storage medium, and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0249] For example, embodiments of this application may also provide a computer-readable storage medium storing computer program instructions thereon. When the computer program instructions are executed by an electronic device, the electronic device causes the electronic device to implement the shooting method as described in the foregoing method embodiments.

[0250] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope 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.

Claims

1. A shooting method, characterized in that, Applied to electronic devices, the method includes: First image frame data is acquired, and whether the first image frame data includes the user's pet is determined by the snapshot event sub-model in the user's private pet model, wherein the user's private pet model is trained based on pet behavior data recorded on the device side; If the first image frame data includes the user's pet, the first target subject in the first image frame data is determined by the target pet sub-model in the user's private pet model. The target pet sub-model is used to segment the first image frame data to segment out the first target subject in the first image frame data. The second image frame data is acquired, and the second target subject in the second image frame data is determined through the target pet sub-model. The target pet sub-model is also used to segment the second image frame data to segment out the second target subject in the second image frame data. Based on the first target subject and the second target subject, the user's pet is tracked and photographed to obtain third image frame data; based on the first image frame data, the second image frame data and the third image frame data, the target pet image data corresponding to the user's pet is determined; Based on the target pet image frame data, the pet state corresponding to the target pet image frame data is determined through the pet state sub-model in the user's private pet model. The pet state sub-model is used to parse the pet's facial expressions, body movements, and barks in the target pet image frame data to obtain the corresponding pet state. Based on the pet state corresponding to the target pet image frame data, the anthropomorphic sound data corresponding to the target pet image frame data is obtained; The target pet image frame data and the corresponding anthropomorphic sound data are synthesized to obtain the target pet's highlight moments data; Send the target pet's highlight moments data to the user's other electronic devices.

2. The method according to claim 1, characterized in that, The step of tracking and photographing the user's pet based on the first target subject and the second target subject to obtain third image frame data includes: Based on the first image frame data, the first predicted image frame data is obtained through the pet prediction sub-model in the user's private pet model; Based on the first predicted image frame data, the first predicted target subject corresponding to the first predicted image frame data is obtained through the target pet sub-model; When the second target subject matches the first predicted target subject, the first attitude adjustment information of the electronic device is determined based on the first target subject and the second target subject; The attitude of the electronic device is adjusted according to the first attitude adjustment information to obtain the first attitude of the electronic device; The fourth image frame data is obtained through the first posture; the third image frame data includes the fourth image frame data.

3. The method according to claim 2, characterized in that, The method further includes: If the second target subject does not match the first target subject, the subject in the second target subject whose matching degree with the first target subject is greater than a preset threshold is determined as the third target subject corresponding to the second image frame data; Based on the first target subject and the third target subject, the second attitude adjustment information of the electronic device is determined; The attitude of the electronic device is adjusted according to the second attitude adjustment information to obtain the second attitude of the electronic device; The fifth image frame data is obtained through the second posture; the third image frame data includes the fifth image frame data.

4. The method according to claim 1, characterized in that, Before determining the target pet image data corresponding to the user's pet based on the first image frame data, the second image frame data, and the third image frame data, the method further includes: Determine whether the third image frame data meets the conditions for stopping shooting; If the third image frame data meets the conditions for stopping shooting, the target pet image frame data is determined to include the first image frame data and the second image frame data.

5. The method according to claim 4, characterized in that, The method further includes: If the third image frame data does not meet the stop shooting condition, the user's pet is tracked and photographed based on the third image frame data to obtain a sixth image frame data. The third image frame data includes the sixth image frame data, and it is determined that the target pet image frame data includes the first image frame data, the second image frame data, and the third image frame data.

6. The method according to claim 1, characterized in that, The shooting conditions include either the first image frame data including the user's pet, or the first image frame data including the user's pet, and the user's pet's behavior meeting preset conditions.

7. The method according to claim 4, characterized in that, The conditions for stopping shooting include the third image frame data not including the user's target pet, or the third image frame data including the user's pet and the pet's behavior not meeting the preset conditions, or the shooting time reaching the preset time.

8. The method according to any one of claims 1-7, characterized in that, The electronic device is a tracking and shooting electronic device, which includes a camera module for acquiring image frame data and a motion module for adjusting the posture of the tracking and shooting electronic device.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory for storing processor-executable instructions; the processor is configured to, when executing the instructions, cause the electronic device to perform the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon; characterized in that, When the computer program instructions are executed by the electronic device, the electronic device performs the method as described in any one of claims 1 to 8.

Images