Shooting method and system for automatically tracking target object and computer equipment

Abstract

The invention provides a shooting method and system for automatically tracking a target object and computer equipment, and is applied to electronic equipment, and the shooting method comprises the steps: inputting the target object into the electronic equipment, and carrying out the feature extraction of the target object; inputting a target object into the electronic equipment, and performing feature extraction on the target object; in response to a received shooting instruction, controlling the camera to shoot the target object; judging whether the target object is located at the center of a current shooting picture or not, and controlling the first screen to rotate relative to the second screen if the target object is not located at the center of the current shooting picture until the target object is adjusted to the center of the shooting picture; if it is judged that the target object is in the center of the current shooting picture, continuing to control the camera to shoot the target object; the target object can be automatically tracked, it is ensured that the target object is located in the center of the shooting picture, and stable and coherent shooting experience is provided for a user.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent shooting, and specifically relates to a shooting method, system, and computer device for automatically tracking a target object. Background Art

[0002] With the popularization of smart phones, the camera performance of mobile phones has received increasing attention from mobile phone manufacturers. Basically, all mobile phone manufacturers have launched mobile phones with front and rear cameras. When traditional mobile phones are used for shooting, the shooter needs to find the target object by himself. When the target object is in a high-speed moving state, it is very difficult for the shooter to accurately control the mobile phone to keep the target object stably in the center of the shooting screen.

[0003] When the shooter wants to shoot his own video, he also cannot leave the shooting range of the mobile phone camera, and cannot show some large-scale actions or change different shooting scenes, so that the shooter can only shoot at a fixed angle, which restricts the activity space of the shooter to a certain extent. Summary of the Invention

[0004] This application provides a shooting method, system, and computer device for automatically tracking a target object, which can automatically track the target object, ensure that the target object is always in the center of the shooting screen, and improve the shooting quality.

[0005] To solve the above technical problems, in a first aspect, this application provides a shooting method for automatically tracking a target object, which is applied to an electronic device. The electronic device includes a first screen provided with a camera and a second screen rotatably connected to the first screen. The first screen and the second screen are located on the same side of the electronic device. The method includes:

[0006] Enter the target object into the electronic device and extract features of the target object;

[0007] In response to a received shooting instruction, control the camera to shoot the target object;

[0008] Determine whether the target object is at the center of the current shooting screen. If it is determined that the target object is not at the center of the current shooting screen, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the shooting screen;

[0009] If it is determined that the target object is at the center of the current shooting screen, continue to control the camera to shoot the target object.

[0010] As a further improvement of this application, the step of entering the target object into the electronic device and extracting features of the target object includes:

[0011] Take multi-angle pictures of the target object through the camera, or select a picture containing the target object from the album of the electronic device as the information source to extract the features of the target object through the picture of the target object;

[0012] Alternatively, input the name of the target object into the electronic device by voice or text, so that the electronic device automatically generates the features of the target object;

[0013] Alternatively, manually click on the target object in the current shooting screen of the electronic device to extract the features of the target object;

[0014] Among them, the features of the target object at least include a first feature and a second feature.

[0015] As a further improvement of the present application, before determining whether the target object is at the center of the shooting screen, it further includes:

[0016] Extract the first feature and the second feature in the current shooting screen in real time, compare the first feature and the second feature of the current shooting screen with the first feature and the second feature of the target object respectively, and determine whether the target object is in the current shooting screen.

[0017] As a further improvement of the present application, determining whether the target object is in the current shooting screen includes:

[0018] Compare the shooting screen of the current camera with the extracted first feature and the second feature to obtain the first feature similarity and the second feature similarity of the current shooting screen;

[0019] Assign weights to the first feature and the second feature. When the comprehensive similarity of the current shooting screen is higher than the preset similarity threshold, it is determined that the target object is in the current shooting screen;

[0020] On the contrary, it is determined that the target object is not in the current shooting screen, and the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the shooting screen.

[0021] As a further improvement of the present application, determining whether the target object is at the center of the current shooting screen includes:

[0022] When the target object is in the shooting screen, based on the first feature of the target object, determine the contour position coordinates of the target object in the current shooting screen;

[0023] Determine the center position coordinates of the target object according to the mean value of several of the contour position coordinates, and compare the center position coordinates with the center coordinates of the current shooting screen;

[0024] When the difference between the central position coordinates and the central coordinates of the current captured image is less than a preset threshold, it is determined that the target object is at the center of the current captured image;

[0025] Conversely, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image.

[0026] As a further improvement of the present application, the first feature is the shape feature of the target object, and the second feature is the color feature of the target object.

[0027] As a further improvement of the present application, a driving member is provided between the first screen and the second screen, and the driving member is used to control the first screen to rotate relative to the second screen and make the first screen hover at the required shooting angle.

[0028] In a second aspect, the present application provides a shooting system for automatically tracking a target object, which includes:

[0029] An extraction unit for inputting the target object into the electronic device and extracting features of the target object;

[0030] A response unit for controlling the camera to capture the target object in response to a received shooting instruction;

[0031] A judgment unit for judging whether the target object is at the center of the current captured image;

[0032] A control unit for controlling the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image when the target object is not at the center of the current captured image; and for continuing to control the camera to capture the target object when the target object is at the center of the current captured image.

[0033] In a third aspect, the present application provides a computer device, which includes a processor and a memory coupled to the processor. A calculation program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the shooting method for automatically tracking a target object in any one of the above.

[0034] Compared with the prior art, the method for shooting an automatically tracked target object provided by this application inputs the target object into an electronic device, extracts features of the target object through the electronic device, and determines in real time whether the target object is at the center of the current shooting screen during the shooting process. When it is determined that the target object is not at the center of the current shooting screen, the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the center of the shooting screen; it can automatically track the target object, ensure that the target object is at the center of the shooting screen, and provide a stable and coherent shooting experience for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a schematic structural diagram of an electronic device provided by an embodiment of this application.

[0037] Figure 2 It is a flowchart of the method for shooting an automatically tracked target object provided by an embodiment of this application.

[0038] Figure 3 It is a first embodiment diagram of the method for shooting an automatically tracked target object provided by an embodiment of this application.

[0039] Figure 4 It is a second embodiment diagram of the method for shooting an automatically tracked target object provided by an embodiment of this application.

[0040] Figure 5 It is a third embodiment diagram of the method for shooting an automatically tracked target object provided by an embodiment of this application.

[0041] Figure 6 It is a schematic structural diagram of the shooting system for automatically tracking a target object provided by an embodiment of this application.

[0042] Figure 7 It is a schematic structural diagram of a computer device provided by an embodiment of this application.

[0043] Figure 8 It is a schematic structural diagram of a storage medium provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer and more understandable, the following further elaborates on the embodiments of this application in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely used to explain the embodiments of this application and are not used to limit the embodiments of this application.

[0045] In the description of the embodiments of this application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically limited. All directional indications (such as up, down, left, right, front, back...) in the embodiments of this application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0046] To make the description of this disclosure more detailed and complete, the following provides an illustrative description of the implementation manners and specific embodiments of the embodiments of this application; however, this is not the only form for implementing or applying the specific embodiments of the embodiments of this application. The implementation manners cover the features of multiple specific embodiments and the method steps and their sequences for constructing and operating these specific embodiments. However, other specific embodiments can also be used to achieve the same or equivalent functions and step sequences.

[0047] In the embodiments of this application, terms such as "exemplary", "in some embodiments", "in another embodiment", etc. are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" in this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the term "exemplary" is intended to present concepts in a specific manner.

[0048] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0049] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0050] When a traditional mobile phone takes a photo, the photographer has to find the target object by himself. When the target object is in a high-speed motion state, it is very difficult for the photographer to precisely control the mobile phone to keep the target object steadily in the center of the shooting frame.

[0051] When the photographer wants to shoot his own video, he also cannot leave the shooting range of the mobile phone camera, and cannot show some large-scale movements or change different shooting scenes, so that the photographer can only shoot at a fixed angle, which limits the activity space of the photographer to a certain extent.

[0052] In view of this, please refer to Figures 1 - 8 , the embodiments of the present application provide a method, device, equipment and storage medium for automatically tracking a target object, which can automatically track the target object, ensure that the target object is always in the center of the shooting frame, and improve the shooting quality.

[0053] It should be noted that the method for automatically tracking a target object in the present application is applicable to any electronic device with a shooting function and screens on both opposite sides, such as a folding screen mobile phone, a tablet computer, a smart wearable device, etc. The present application does not limit this. For the sake of description, the present application takes a folding screen mobile phone with an up-and-down fold as an example for illustration. Of course, a folding screen mobile phone with a left-and-right fold is also feasible. It can be understood that the technical solution of the present application is also applicable to other applications with a shooting function on the electronic device, not limited to the camera application.

[0054] Please refer to Figure 1 , which is a schematic structural diagram of the electronic device provided by the embodiment of the present application. The electronic device includes a first screen provided with a camera and a second screen rotatably connected to the first screen. The first screen and the second screen are arranged on the same side of the electronic device. The first screen and the camera can be arranged on different sides of the electronic device or on the same side of the electronic device. The present application does not make further limitations on this.

[0055] Based on the above electronic device structure, please refer to Figure 2 , which is a flowchart of the method for automatically tracking a target object provided by the embodiment of the present application. The shooting method includes the following steps:

[0056] Step S1: Enter the target object into the electronic device and extract features of the target object;

[0057] As an optional implementation manner, the above-mentioned entering the target object into the electronic device and extracting features of the target object includes:

[0058] Take multi-angle pictures of the target object through the camera, or select pictures containing the target object from the album of the electronic device as the information source to extract the features of the target object through the pictures of the target object;

[0059] Alternatively, input the name of the target object into the electronic device by voice or text, so that the electronic device automatically generates the features of the target object;

[0060] Alternatively, manually click on the target object in the current shooting screen of the electronic device to achieve feature extraction of the target object;

[0061] Among them, the features of the target object at least include the first feature and the second feature.

[0062] In the embodiments of the present application, since an electronic device usually has a shooting function and a camera application function, the target object can be photographed through the camera equipped with the electronic device.

[0063] When conditions permit, it is possible to not only shoot from the same fixed angle, but shoot around the target object from different directions and perspectives, so as to show different details and features of the target object and provide richer and more comprehensive image information for subsequent feature extraction.

[0064] Or using the camera application function of the electronic device, taking the target object as the selfie-taker as an example, various selfie photos previously taken or saved by the user are usually stored in the camera of the electronic device. The selfie-taker can directly select relevant selfie photos as the information source for subsequent feature extraction; or taking the target object as a pet as an example, the photographer can directly select the relevant photos of the pet. This method of directly applying the existing picture resources without prior shooting is also feasible and can adapt to different application scenarios and shooting requirements.

[0065] Optionally, the name of the target object can also be input into the electronic device by voice or text. The photographer directly inputs the name of the target object such as a pet into the electronic device by voice or text, so that the electronic device automatically generates the features of the target object according to the received name of the target object.

[0066] Furthermore, the target object can also be manually clicked on the current shooting screen of the electronic device. For example, when the photographer needs to shoot a moving pet, the pet can be manually selected on the current shooting screen of the electronic device, so that the electronic device extracts the features of the currently selected target object.

[0067] The above methods for extracting the features of the target object are all feasible, and the present application does not make too many restrictions on this. Those skilled in the art should know this.

[0068] Further, after obtaining the picture of the target object, it is necessary to extract the first feature and the second feature of the target object.

[0069] Exemplarily, the above-mentioned first feature may be the shape feature of the target object, and the above-mentioned second feature may be the color feature of the target object. Of course, the above-mentioned first feature and second feature may also be related features such as the texture feature and contour feature of the target object, which should be known to those skilled in the art.

[0070] Taking the first feature as the shape feature of the target object as an example, the edge shape of the target object can be obtained by means of traditional edge detection operators, or the edge pixels of the target object can be determined through a CNN (Convolutional Neural Network) detection model, so as to obtain the edge shape of the target object. It is also possible to continuously update the contour of the target object through the Snakes model until convergence, so as to obtain the final edge shape of the target object. The above methods for obtaining the shape feature of the target object are all feasible. This application does not elaborate too much on the specific methods and steps for extracting the shape feature of the target object.

[0071] Further, taking the second feature as the color feature of the target object as an example, the color feature of the target object can be obtained by means of traditional color space conversion and histogram statistics, such as which color combinations of hue, saturation, and lightness the target object mainly contains. It is also possible to extract the color feature of the target object through color moments, color quantization, or some existing training models. The above methods for obtaining the color feature of the target object are also feasible. This application does not elaborate too much on the specific methods and steps for extracting the color feature of the target object.

[0072] Step S2: In response to the received shooting instruction, control the camera to shoot the target object;

[0073] In the embodiment of the present application, when the electronic device receives the shooting instruction, the electronic device will start corresponding operations, such as controlling the camera to shoot the target object. Here, the target object refers to the specific object to be shot, which may have been pre-determined by the electronic device or may be the target object specifically determined by the user in a certain way.

[0074] It can be understood that the user can also control the camera to shoot the target object through voice instructions, Bluetooth instructions, etc. This application does not impose too many restrictions on the specific form of the above shooting instruction.

[0075] Step S3: Determine whether the target object is at the center of the current captured image. If it is determined that the target object is not at the center of the current captured image, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image;

[0076] If it is determined that the target object is at the center of the current captured image, continue to control the camera to capture the target object.

[0077] As an alternative implementation, before determining whether the target object is at the center of the captured image, it further includes:

[0078] Extract the first feature and the second feature in the current captured image in real time, compare the first feature and the second feature of the current captured image with the first feature and the second feature of the target object respectively, and determine whether the target object is in the current captured image.

[0079] In the embodiment of the present application, during the process of the electronic device capturing the target object, the above-mentioned first feature and second feature are obtained in real time from the image being captured, such as the shape feature and color feature in the captured image.

[0080] It can be understood that the process of obtaining the first feature and the second feature is carried out simultaneously during the process of capturing the target object, and the feature extraction and analysis of the current captured image are performed in real time, which will not affect the normal capture of the target object currently.

[0081] After the first feature and the second feature in the current captured image are extracted in real time, the first feature of the current captured image is compared with the first feature of the target object, and the second feature of the current captured image is compared with the second feature of the target object. According to the comparison of the above features, it is determined whether the target object is in the current captured image.

[0082] It should be noted that when the user needs to capture in a certain shooting scene, it may occur that a shooting instruction is issued to control the camera to capture, but the user needs to move to the shooting scene by himself. Therefore, during the movement, the target object does not exist in the captured image. Therefore, the present application adds a judgment step to determine whether the target object exists in the captured image. After it is determined that the target object exists in the captured image, it is further determined whether the target object is at the center of the captured image.

[0083] As an alternative implementation, the above determination of whether the target object is in the current captured image includes:

[0084] Compare the captured image of the current camera with the extracted first feature and the second feature to obtain the first feature similarity and the second feature similarity of the current captured image;

[0085] Assign weights to the first feature and the second feature. When the comprehensive similarity of the current captured image is higher than the preset similarity threshold, it is determined that the target object is in the current captured image;

[0086] On the contrary, it is determined that the target object is not in the current captured image, and the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the captured image.

[0087] In the embodiments of the present application, after the first feature and the second feature in the current captured image are extracted in real time, the first feature of the current captured image will be compared with the first feature of the target object, and the second feature of the current captured image will be compared with the second feature of the target object, so as to further obtain the first feature similarity and the second feature similarity between the current captured image and the target object.

[0088] Exemplarily, when the first feature is a shape feature, the first feature similarity can be determined by calculating the difference between their Fourier transform coefficients through, for example, the Fourier descriptor, or by calculating the required first feature similarity according to the difference of different order moments through the moment descriptor. The above methods for calculating the first feature similarity are all feasible.

[0089] When the second feature is a color feature, the color histogram of the current captured image can be compared with the color histogram of the target object, and the distance between the two can be calculated as a similarity metric, such as calculating the required second feature similarity in the way of using the Bhattacharyya distance, Euclidean distance or Cosine Similarity.

[0090] It can be understood that in the technical research and application practice of image recognition and related fields, calculating feature similarity is a very common and basic operation. The above methods for calculating the first feature similarity and the second feature similarity are widely recorded and applied, and the present application will not elaborate too much here.

[0091] Further, after calculating the first feature similarity and the second feature similarity, corresponding weights can be assigned to the first feature and the second feature according to the application requirements or according to the importance of the first feature and the second feature, so as to obtain the comprehensive similarity S of the current captured image.

[0092] Specifically, the required comprehensive similarity can be calculated according to the formula S = W1 * S1 + W2 * S2, where W1 + W2 = 1, S1 is the first feature similarity, W1 is the weight assigned to the first feature, S2 is the second feature similarity, and W2 is the weight assigned to the second feature. Of course, the specific numerical assignments of W1 and W2 can also be adjusted and optimized according to actual needs, which should be known to those skilled in the art.

[0093] Further, compare the comprehensive similarity of the current captured image with a preset similarity threshold. When the comprehensive similarity of the current captured image is higher than the preset similarity threshold, it is determined that the target object is already in the current captured image.

[0094] Conversely, when the comprehensive similarity of the current captured image is less than or equal to the preset similarity threshold, it is determined that the target object is not in the current captured image. Therefore, it is necessary to control the first screen to rotate relative to the second screen so that the target object is adjusted into the captured image.

[0095] It should be noted that during the process of adjusting the target object into the captured image here, the adjustment accuracy of the first screen relative to the second screen will be relatively greater than the process of adjusting the target object to the center of the captured image. That is to say, first roughly adjust the angle of the first screen relative to the second screen. After the target object enters the captured image, then finely adjust the angle of the first screen relative to the second screen to ensure that the target object is adjusted to the center of the captured image.

[0096] In the embodiment of the present application, a driving member capable of controlling the first screen to rotate relative to the second screen is provided between the first screen and the second screen. The driving member can be implemented by combining a small motor with a transmission mechanism and a hinge. The driving member can be provided between the first screen and the second screen, or can be integrally arranged inside the electronic device. Of course, other structures capable of controlling the first screen to rotate relative to the second screen to adjust the opening angle between the first screen and the second screen are also feasible. The present application does not limit the specific setting form of the driving member too much.

[0097] Step S3: Determine whether the target object is at the center of the current captured image. If it is determined that the target object is not at the center of the current captured image, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image;

[0098] If it is determined that the target object is at the center of the current captured image, continue to control the camera to capture the target object.

[0099] As an optional implementation manner, determining whether the target object is at the center of the current captured image includes:

[0100] When the target object is in the captured image, based on the first feature of the target object, determine the contour position coordinates of the target object in the current captured image;

[0101] Determine the center position coordinates of the target object according to the mean value of several of the contour position coordinates, and compare the center position coordinates with the center coordinates of the current captured image;

[0102] When the difference between the center position coordinates and the center coordinates of the current captured image is less than a preset threshold, it is determined that the target object is at the center of the current captured image;

[0103] Conversely, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image.

[0104] In the embodiments of the present application, after determining that the target object is in the captured image, it is necessary to further determine whether the target object is at the center of the current captured image.

[0105] Specifically, when it is determined that the target object is in the captured image, based on the first feature of the target object, that is, the first feature extracted in step S2, namely the shape feature, according to the shape feature of the target object, determine the contour position coordinates of the target object in the captured image.

[0106] It can be understood that after extracting the shape feature of the target object, such as after extracting the shape feature of the target object through Fourier descriptors, the edges of the target object can be determined by common edge detection algorithms such as the Canny edge detection algorithm, mark the contour edge pixels of the target object, and then use algorithms such as the Moore-Neighbor tracking algorithm to obtain the position coordinates of the contour; of course, the above is an example implementation method, as long as other setting methods that can determine the contour coordinate position of the target object in the captured image are also feasible, and the present application does not limit this too much.

[0107] Further, when several contour coordinate positions of the target object in the captured image are obtained, the center position coordinates of the target object can be determined by the mean value of these coordinate positions. Since the captured image is generally rectangular in shape, the captured image can be regarded as a two-dimensional plane, and the lower left corner of the image is determined as the origin, and further obtain the center coordinates of the captured image.

[0108] Compare the center position coordinates of the target object with the center coordinates of the current captured image, calculate the difference d between the two coordinate points. When the difference between the center position coordinates of the target object and the center coordinates of the current captured image is less than the preset threshold, it is determined that the target object is at the center of the current captured image, and then continue to capture the target object at this angle.

[0109] When the difference between the central position coordinates of the target object and the central coordinates of the current captured image is greater than or equal to a preset threshold, it is necessary to adjust the first screen, control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the captured image.

[0110] It can be understood that in actual applications, simply judging whether the target object is at the center of the captured image by calculating the difference in coordinates may not be accurate enough. The target object may have different postures such as moving, rotating, and jumping. For example, when the target object approaches the camera, the proportion of the target object in the current captured image may be relatively large, and at this time, the allowable preset threshold may be relatively small. When the target object is far from the camera, the proportion of the target object in the current captured image may be relatively small, so the preset threshold can be appropriately increased.

[0111] Similarly, the preset threshold can also be adjusted according to the speed of the target object. For example, when the movement speed of the target object is relatively fast, in order to track its position in a timely manner, the preset threshold can be appropriately increased during the tracking process. After the target object moves stably, the preset threshold can be appropriately decreased to improve the accuracy of comparison.

[0112] That is to say, the above-provided preset threshold is not a fixed value, but can be adjusted according to the actual application scenario and shooting situation to improve the accuracy of judgment, which should be known to those skilled in the art.

[0113] Please refer to Figure 3 , which is the first embodiment diagram of the shooting method for automatically tracking a target object provided by the embodiment of the present application. When the user needs to shoot a video of a moving target object, the user can hold a part of the second screen, first take multi-angle photos of the target object through the camera, or select multiple pictures including the target object from the album, or perform multi-angle shooting of the target object, input the target object into the electronic device, or input the name of the target object into the electronic device through voice or text, or manually click on the target object on the current captured image of the electronic device; when starting to shoot, the driving member will automatically adjust the rotation angle between the first screen and the second screen and automatically track the target object to ensure that the target object in the moving state can always be at the center of the captured image.

[0114] Please refer to Figure 4, which is the second embodiment diagram of the shooting method for automatically tracking a target object provided by the embodiments of the present application. When a user needs to take a selfie, the second screen can be fixed on a common mobile phone stand to ensure that the first screen can rotate freely. Similarly, the user can take multi-angle photos of himself / herself through the camera, or select relevant selfie pictures from the album, or perform angle shooting on himself / herself through the camera, so as to input his / her features into the electronic device. When starting to shoot, the driving member will automatically adjust the rotation angle between the first screen and the second screen, and automatically track the selfie-taker to ensure that the user can always be at the center of the shooting screen. Of course, the user can also control the camera to shoot the target object through voice commands, Bluetooth commands, etc. All the above shooting methods are feasible.

[0115] Please refer to Figure 5 , which is the third embodiment diagram of the shooting method for automatically tracking a target object provided by the embodiments of the present application. When a user needs to have a video chat or a video live broadcast, the second screen can also be fixed on the mobile phone stand to ensure that the first screen can rotate freely, and input the features of the video chat or video live broadcast participant into the electronic device. When starting to shoot, the driving member will automatically adjust the rotation angle between the first screen and the second screen, and automatically track the video chat or video live broadcast participant to ensure that the video chat or video live broadcast participant can always be at the center of the shooting screen. The present application will not elaborate too much on the above steps of ensuring that the user is at the center of the shooting screen.

[0116] Of course, the above shooting method for automatically tracking a target object provided by the present application is not limited to the above application embodiments, and can also be applied to other shooting scenarios that require automatic tracking of a target object. The present application does not make further restrictions on this.

[0117] The shooting method for automatically tracking a target object provided by the present application inputs the target object into the electronic device, extracts the features of the target object through the electronic device, and determines in real time whether the target object is at the center of the current shooting screen during the shooting process. When it is determined that the target object is not at the center of the current shooting screen, the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the center of the shooting screen. The present application can automatically track the target object to ensure that the target object is at the center of the shooting screen, providing a stable and coherent shooting experience for the user.

[0118] Based on the above shooting method for automatically tracking a target object, the present application provides a shooting system for automatically tracking a target object. Please refer to Figure 6 , which is the structural schematic diagram of the shooting system for automatically tracking a target object provided by the embodiments of the present application. The shooting system includes an extraction unit, a response unit, a judgment unit, and a control unit.

[0119] Among them, an extraction unit is configured to input a target object into an electronic device and extract features of the target object;

[0120] A response unit is configured to control the camera to capture the target object in response to a received shooting instruction;

[0121] A judgment unit is configured to judge whether the target object is at the center of the current shooting screen;

[0122] A control unit is configured to control the first screen to rotate relative to the second screen until the target object is adjusted to the center of the shooting screen when the target object is not at the center of the current shooting screen; and is further configured to continue to control the camera to capture the target object when the target object is at the center of the current shooting screen.

[0123] For other details of the technical solutions implemented by the units in the shooting system for automatically tracking a target object provided in the above embodiments, reference may be made to the description in the shooting method for automatically tracking a target object in the above embodiments, which will not be elaborated here.

[0124] It should be noted that the embodiments in this specification are all described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the embodiments may be referred to each other. For system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts may refer to the partial description of the method embodiments.

[0125] Please refer to Figure 7 , which is a schematic structural diagram of a computer device provided in an embodiment of the present application. The computer device 70 includes a processor 71 and a memory 72 coupled to the processor 71.

[0126] The memory 72 stores a computing program. When the computer program is executed by the processor 71, the processor 71 is caused to execute the steps of the actuarial facultative reinsurance method based on artificial intelligence in the above embodiments.

[0127] Among them, the processor 71 may also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 71 may be an integrated circuit chip with signal processing capabilities. The processor 71 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0128] Please refer to Figure 8, Structural schematic diagram of the storage medium provided by the embodiments of the present application. The computer-readable storage medium of the embodiments of the present application stores a computer program 80. The computer program 80 is executed by a processor 71 to implement the actuarial facultative reinsurance method based on artificial intelligence in the above embodiments. Among them, the computer program 80 can be stored in the above storage medium in the form of a software product, including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or computer devices such as computers, servers, mobile phones, and tablets. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0129] In several embodiments provided by the present application, it should be understood that the disclosed terminals, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0130] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units. The above is only the implementation manner of the present application and does not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, is equally included in the patent protection scope of the present application.

[0131] The above embodiments are merely exemplary embodiments adopted to illustrate the principles of the embodiments of the present application. However, the embodiments of the present application are not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the embodiments of the present application, and these modifications and improvements are also regarded as the protection scope of the embodiments of the present application.

Claims

1. A shooting method for automatically tracking a target object, applied to an electronic device, characterized in that: The electronic device comprises a first screen provided with a camera and a second screen rotatably connected to the first screen, the first screen and the second screen are located on the same side of the electronic device, and the method comprises: Recording the target object into an electronic device and performing feature extraction on the target object; In response to the received shooting instruction, controlling the camera to shoot the target object; Determining whether the target object is at the center of the current shooting picture, and if it is determined that the target object is not at the center of the current shooting picture, controlling the first screen to rotate relative to the second screen until the target object is adjusted to the center of the shooting picture; If it is determined to be in the center of the current shooting picture, the camera continues to be controlled to shoot the target object.

2. The method for automatically tracking a target object according to claim 1, wherein: The step of recording the target object into the electronic device and extracting features of the target object includes: Taking multi-angle pictures of the target object through the camera, or selecting pictures containing the target object from the photo album of the electronic device as an information source, so as to extract features of the target object through the pictures of the target object; Alternatively, the name of the target object is input into the electronic device via voice or text, so that the electronic device automatically generates the features of the target object; Alternatively, manually clicking the target object on the current shooting screen of the electronic device to extract features of the target object; The characteristics of the target object include at least a first characteristic and a second characteristic.

3. The method for automatically tracking a target object as claimed in claim 2, wherein: Before determining whether the target object is at the center of the shooting picture, the method further includes: The first feature and the second feature of the current shooting picture are extracted in real time, and the first feature and the second feature of the current shooting picture are compared with the first feature and the second feature of the target object respectively to determine whether the target object is in the current shooting picture.

4. The method for automatically tracking a target object as claimed in claim 3, wherein: The step of determining whether the target object is in the current shooting picture includes: Compare the current camera shot picture with the extracted first feature and second feature to obtain the first feature similarity and the second feature similarity of the current shot picture; Assigning weights to the first feature and the second feature, and when the comprehensive similarity of the current shooting picture is higher than a preset similarity threshold, determining that the target object is in the current shooting picture; On the contrary, it is determined that the target object is not in the current shooting picture, and the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the shooting picture.

5. The method for automatically tracking a target object as claimed in claim 3, wherein: The step of determining whether the target object is located at the center of the current shooting picture includes: When the target object is in the shooting picture, determining the contour position coordinates of the target object in the current shooting picture based on the first feature of the target object; Determine the center position coordinates of the target object according to the average of a plurality of the contour position coordinates, and compare the center position coordinates with the center coordinates of the current shooting picture; When the difference between the center position coordinates and the center coordinates of the current shooting picture is less than a preset threshold, it is determined that the target object is at the center of the current shooting picture; On the contrary, the first screen is controlled to rotate relative to the second screen until the target object is adjusted to the center of the shooting screen.

6. The method for automatically tracking a target object as claimed in claim 2, wherein: The first feature is a shape feature of the target object, and the second feature is a color feature of the target object.

7. The method for automatically tracking a target object as claimed in claim 1, wherein: A driving member is disposed between the first screen and the second screen, and the driving member is used to control the first screen to rotate relative to the second screen and to make the first screen hover to a desired shooting angle.

8. A photographing system for automatically tracking a target object, used to execute the steps of the photographing method for automatically tracking a target object as claimed in any one of claims 1 to 7, characterized in that: The shooting system comprises: An extraction unit, used to record the target object into the electronic device and perform feature extraction on the target object; A response unit, configured to control the camera to shoot the target object in response to a received shooting instruction; A judging unit, used to judge whether the target object is in the center of the current shooting picture; A control unit, used for controlling the first screen to rotate relative to the second screen until the target object is adjusted to the center of the shooting picture when the target object is not at the center of the current shooting picture; and also used for continuing to control the camera to shoot the target object when the target object is at the center of the current shooting picture.

9. A computer device, characterized in that: The computer device includes a processor and a memory coupled to the processor, wherein a computing program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of the shooting method for automatically tracking a target object as described in any one of claims 1 to 7.

Images