Photographing method, apparatus and electronic device

Abstract

The application discloses a photographing method, a photographing device and electronic equipment, and belongs to the technical field of camera shooting. A photographing method executed by a first electronic device comprises the following steps: receiving first information sent by a second electronic device; wherein the first information comprises object feature information of a first object tracked and photographed by a gimbal camera; determining a target object from at least one object displayed on a photographing preview interface of the first electronic device according to the first information; and controlling the gimbal camera to track and photograph the target object.

Description

Technical Field

[0001] This application belongs to the field of camera technology, specifically relating to a shooting method, device, and electronic equipment. Background Technology

[0002] With the development of electronic devices and gimbal cameras, more and more users are using electronic devices to control gimbal cameras to track and photograph objects. During the tracking and photographing process, users may switch between the electronic devices controlling the gimbal camera.

[0003] However, when switching the electronic device that controls the gimbal camera, the switched electronic device needs to re-identify the object, and the user needs to re-select the tracking object through the switched electronic device, which causes the object tracking to be interrupted and affects the continuity of shooting. Summary of the Invention

[0004] The purpose of this application is to provide a shooting method, apparatus, and electronic device that can prevent the tracking of moving objects from being interrupted and improve the continuity of shooting.

[0005] In a first aspect, embodiments of this application provide a shooting method, executed by a first electronic device, the method comprising: Receive first information sent by a second electronic device; wherein the first information includes object feature information of a first object tracked and captured by a gimbal camera; Based on the first information, the target object is determined from at least one object displayed on the shooting preview interface of the first electronic device; Control the gimbal camera to track and capture the target object.

[0006] Secondly, embodiments of this application provide a shooting device, including: A receiving module is used to receive first information sent by a second electronic device; wherein the first information includes object feature information of a first object tracked and captured by a gimbal camera; The determining module is used to determine a target object from at least one object displayed on the shooting preview interface of the first electronic device based on the first information; The control module is used to control the gimbal camera to track and capture target objects.

[0007] Thirdly, embodiments of this application provide an electronic device, which includes a processor and a memory. The memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, they implement the steps of the shooting method provided in embodiments of this application.

[0008] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of the shooting method provided in embodiments of this application.

[0009] Fifthly, this application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the shooting method provided in this application.

[0010] Sixthly, embodiments of this application provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the steps of the shooting method provided in embodiments of this application.

[0011] In this embodiment, the first electronic device receives first information, including object feature information of a first object tracked and captured by a gimbal camera, sent by the second electronic device; based on the first information, it determines a target object from at least one object displayed on the shooting preview interface of the first electronic device; and controls the gimbal camera to track and capture the target object. Thus, the first electronic device can automatically control the gimbal camera to track objects selected by the user from the shooting preview interface of the second electronic device, without requiring the user to select the tracking object from the shooting preview interface of the first electronic device, preventing interruption of moving object tracking and improving the continuity of shooting. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating the shooting method provided in some embodiments of this application; Figure 2 This is a first schematic diagram illustrating the selection of a tracking object according to some embodiments of this application; Figure 3 These are schematic diagrams illustrating tracking and shooting scenarios provided in some embodiments of this application; Figure 4 This is a second schematic diagram illustrating the selection of tracking objects provided in some embodiments of this application; Figure 5 These are schematic diagrams illustrating the display of prompt information provided in some embodiments of this application; Figure 6 These are schematic diagrams of the imaging device provided in some embodiments of this application; Figure 7 These are schematic diagrams of the structure of an electronic device provided in some embodiments of this application; Figure 8 These are schematic diagrams of the hardware structure of electronic devices provided in some embodiments of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0014] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0015] The terminology used in the implementation section of this application is only for explaining specific embodiments of this application and is not intended to limit this application. The terminology involved in the embodiments of this application is explained below.

[0016] A pan-tilt camera is a camera device with a mechanism for horizontal and vertical rotation of the camera.

[0017] The shooting preview interface is the interface on the electronic device that displays the shooting screen in real time.

[0018] Tracking shooting involves the camera locking onto the target and capturing the image, ensuring that the target remains within the camera's image acquisition range at all times.

[0019] The following description, in conjunction with the accompanying drawings, details the imaging method, apparatus, and electronic equipment provided in this application through specific embodiments and application scenarios.

[0020] It should be noted that the shooting method provided in this application can be executed by a first electronic device, which can be a mobile phone, tablet computer, laptop computer, PDA, vehicle-mounted electronic device, or other electronic device. Some embodiments of this application use the first electronic device as the executing entity to illustrate the shooting method provided in this application.

[0021] The second electronic device in this application embodiment can be a mobile phone, tablet computer, laptop computer, handheld computer, vehicle electronic device, or other electronic device.

[0022] The shooting method provided in this application can be applied to scenarios where the control device of a gimbal camera is switched while tracking and shooting an object. One specific application scenario is switching the control device of the gimbal camera from a mobile phone to a tablet when tracking and shooting an athlete. Another specific application scenario is switching the control device of the gimbal camera from one mobile phone to another when tracking and shooting an athlete. When tracking and shooting a subject with a gimbal camera, when the electronic device receives a photo-taking command, it can store the image corresponding to the command to obtain a photo, thus capturing the subject. When the electronic device receives a video-recording command, it can record video of the tracked subject to obtain a video.

[0023] It should be noted that the above application scenario is only one example. In actual applications, other application scenarios may also be included. For example, when using a gimbal camera to track and film a football on a field, the control device for the gimbal camera may be switched from a mobile phone to a tablet.

[0024] Figure 1 This is a schematic flowchart of a shooting method provided in some embodiments of this application. The shooting method may include: Step 101: Receive first information sent by the second electronic device; wherein, the first information includes object feature information of the first object tracked and captured by the gimbal camera; In some embodiments of this application, the first object in the embodiments of this application includes, but is not limited to, objects such as people, vehicles, and basketballs.

[0025] In some embodiments of this application, the first object of the embodiment of this application can be a moving object, that is, an object whose position changes over time.

[0026] In some embodiments of this application, the second electronic device can communicate with a gimbal camera, and the image captured by the gimbal camera is displayed in the shooting preview interface of the second electronic device. The second electronic device can activate a shooting tracking function, and identify moving objects in the shooting preview interface of the second electronic device through an image recognition algorithm. The user selects from the identified moving objects, and the selected object is used as the tracking object, which is the first object in the embodiments of this application. The second electronic device controls the gimbal camera to track and shoot the tracking object.

[0027] In some embodiments of this application, when identifying moving objects in the shooting preview interface of the second electronic device, region information for each moving object can also be obtained. This region information includes the vertex coordinates of the bounding box containing the moving object. The vertex coordinates of the bounding box include the coordinates of the upper left corner and the lower right corner. Typically, the upper left corner vertex of the shooting preview image is the origin of the coordinate system, with the positive X-axis pointing to the right and the positive Y-axis pointing downwards.

[0028] In some embodiments of this application, the vertex coordinates of the bounding box of a moving object can be represented as (x1, y1, x2, y2), where (x1, y1) are the coordinates of the upper left corner of the bounding box of the moving object, and (x2, y2) are the coordinates of the lower right corner of the bounding box of the moving object. For example, the size of the captured preview image is 1920×1080 pixels, and the region information of a certain moving object in the captured preview image is (900, 500, 1000, 6000), where (900, 500) are the coordinates of the upper left corner of the bounding box of the moving object, and (1000, 600) are the coordinates of the upper right corner of the bounding box of the moving object.

[0029] For example, such as Figure 2 As shown, Figure 2 This is a first schematic diagram illustrating the selection of tracking objects provided in some embodiments of this application. Figure 2 In the process, the second electronic device uses an image recognition algorithm to identify three moving objects and their corresponding bounding boxes in the shooting preview interface. The three moving objects are object 201, object 202, and object 203. When the user selects object 202, object 202 is selected as the tracking object.

[0030] In some embodiments of this application, the object feature information in these embodiments may include at least one of the following: depth feature information, texture feature information, color feature information, and semantic feature information.

[0031] In some embodiments of this application, the depth feature information may include a depth map, a disparity map, the spatial coordinates of each pixel, and a depth gradient; the texture feature information may include texture contrast, orientation consistency, and local binary mode; the color feature information may include color space representation, color statistics, color space layout, and color names; and the semantic feature information may include entity category, entity attributes, and contextual relationships.

[0032] In some embodiments of this application, the object feature information in these embodiments may include only depth feature information, or only texture feature information, or only color feature information, or only semantic feature information.

[0033] In some embodiments of this application, the object feature information in the embodiments of this application may include depth feature information and texture feature information, or, may include depth feature information and color feature information, or, may include depth feature information and semantic feature information, or, may include texture feature information and color feature information, or, may include texture feature information and semantic feature information, or may include color feature information and semantic feature information.

[0034] In some embodiments of this application, the object feature information in the embodiments of this application may include depth feature information, texture feature information and color feature information, or may include depth feature information, texture feature information and semantic feature information, or may include texture feature information, color feature information and semantic feature information, or may include depth feature information, color feature information and semantic feature information, or may include texture feature information, color feature information and semantic feature information.

[0035] In some embodiments of this application, the object feature information may include depth feature information, texture feature information, color feature information, and semantic feature information.

[0036] Once the second electronic device identifies the object being tracked, it can extract the depth features of the object through a deep neural network, determine the color features of the object through the hue-saturation-value (HSV) color distribution of the bounding box containing the object, extract the texture features of the object through Local Binary Patterns (LBP), and extract the semantic features of the object through a neural network model for extracting semantic features.

[0037] In some embodiments of this application, when the object in the embodiments of this application is a person, the object feature information in the embodiments of this application may further include: key point features, wherein the key point features may include the location and confidence level of each human body key point. Key point features can be extracted using a human key point detection model.

[0038] In some embodiments of this application, the second electronic device can fuse the depth feature information, color feature information, texture feature information and semantic feature information of the tracked object to obtain the fused feature information of the tracked object.

[0039] In some embodiments of this application, when fusing the depth feature information, color feature information, texture feature information and semantic feature information of the tracked object, the depth feature information, color feature information, texture feature information and semantic feature information of the tracked object can be spliced ​​together to obtain the fused feature information of the tracked object.

[0040] The second electronic device can continuously detect whether it receives access requests from other electronic devices. When an access request is detected, it establishes a communication link with the electronic device corresponding to the received access request through the local network, and sends first information to the electronic device corresponding to the received access request through this communication link. This communication link can be established using the WebSocket protocol. In a local area network environment, communication links established using the WebSocket protocol have low transmission latency, typically less than 10 milliseconds (ms).

[0041] For example, the first electronic device is a tablet, and the second electronic device is a mobile phone. The mobile phone can activate the shooting and tracking function, identify objects in the shooting preview interface of the mobile phone through an image recognition algorithm, and the user selects the identified objects as the tracking objects. The mobile phone controls the gimbal camera to track and shoot the tracking objects. When the user connects the tablet to the same WiFi network as the mobile phone, the tablet automatically broadcasts an access request to the local area network corresponding to that WiFi network; after receiving the access request, the mobile phone establishes a WebSocket connection with the tablet and sends the first information to the tablet through the WebSocket connection.

[0042] In some embodiments of this application, the second electronic device may employ a reliable transmission mechanism to send the first information. For example, if no confirmation of receipt is received from the first electronic device within a first time period, the first information is retransmitted, and the data packet is retransmitted a maximum of 3 times.

[0043] For example, the first electronic device is a tablet, and the second electronic device is a mobile phone. The mobile phone sends a first message to the tablet via a WebSocket connection. After receiving the first message, the tablet replies to confirm receipt. After receiving the confirmation, the mobile phone confirms that the first message was sent successfully.

[0044] In some embodiments of this application, the second electronic device can upload each newly generated first information to a cloud server for storage.

[0045] In some embodiments of this application, when the second electronic device receives an access request from the first electronic device and the first electronic device is always connected to the internet and online, the second electronic device can reacquire the object feature information of the tracked object and send the reacquired object feature information of the tracked object back to the first electronic device. When the first electronic device disconnects from the internet and then reconnects, the first electronic device retrieves the most recently stored object feature information of the tracked object from the cloud server, performs a version check on the object feature information of the tracked object, and sends the version check result to the second electronic device or the cloud server. Based on the version check result, the second electronic device or the cloud server sends the differential object feature information of the tracked object to the first electronic device. The differential object feature information is the difference between the object feature information of the tracked object currently reacquired by the second electronic device and the object feature information of the tracked object most recently stored by the cloud server.

[0046] For example, if a tablet goes offline for 5 minutes because a user enters an elevator, when the tablet reconnects to the network, it retrieves the object feature information of the most recently stored tracked object from the cloud server. After checking the version of the object feature information, it finds that the version of the object feature information is 35. However, the latest version of the object feature information of the tracked object that the mobile phone retrieves is 42. Therefore, the mobile phone needs to synchronize the differential object feature information corresponding to the 7 missing versions to the tablet.

[0047] In this embodiment, the device can be reconnected after going offline. The differential update mechanism can reduce the amount of data transmission, improve the efficiency of determining the tracked object, and thus improve the efficiency of tracking moving objects.

[0048] Step 102: Based on the first information, determine the target object from at least one object displayed on the shooting preview interface of the first electronic device; In some embodiments of this application, step 102 may include: determining the feature similarity between the object feature information of the first object and the object feature information of each of at least one object; and determining the object corresponding to the maximum feature similarity as the target object.

[0049] In some embodiments of this application, the first electronic device can extract the fusion feature information of the first object from the received first information; identify the object in the shooting preview interface of the first electronic device using an image recognition algorithm; extract the depth feature information of each object using a deep neural network; determine the color feature information of each object using HSV color distribution; extract the texture feature information of each object using LBP; extract the semantic feature information of each object using a neural network model for extracting semantic features; and fuse the depth feature information, color feature information, texture feature information, and semantic feature information of each object to obtain the fusion feature information of each object. The first electronic device calculates the cosine similarity between the fusion feature information of the first object and the fusion feature information of each object in the shooting preview interface of the first electronic device, uses this cosine similarity as the feature similarity, and determines the object corresponding to the maximum feature similarity as the target object.

[0050] For example, the first electronic device is a tablet and the second electronic device is a mobile phone.

[0051] The tablet detects three objects from its shooting preview interface: object A, object B, and object C. The cosine similarity between the fused feature information of objects A, B, and C and the fused feature information of the first object sent from the mobile phone is calculated. Assuming the cosine similarity between object A and the first object is 0.92, the cosine similarity between object B and the first object is 0.35, and the cosine similarity between object C and the first object is 0.28, then object A is identified as the target object.

[0052] In this embodiment of the application, target matching is performed using multi-dimensional features, which can improve the accuracy of target identification.

[0053] In some embodiments of this application, the first information further includes trajectory information of the first object and a first tracking confidence level corresponding to the first object; the trajectory information is the historical movement trajectory of the first object in the shooting preview interface of the second electronic device; the first tracking confidence level is used to measure the tracking quality of the first object; accordingly, step 102 may include: determining the feature similarity between the object feature information of the first object and the object feature information of each object in at least one object; determining the first matching degree between the position information of each object and the first position information; wherein, the first position information is the position information predicted based on the trajectory information; determining the second matching degree between the movement direction of each object and the direction corresponding to the trajectory information; determining the third matching degree between the second tracking confidence level corresponding to each object and the first tracking confidence level; and determining the target object from at least one object based on the feature similarity, the first matching degree, the second matching degree, and the third matching degree.

[0054] After the user selects a tracking object from the shooting preview interface of the second electronic device, the device can extract the depth feature information of the tracking object through a deep neural network, determine the color feature information of the tracking object through the HSV color distribution of the bounding box containing the tracking object, extract the texture feature information of the tracking object through LBP, extract the semantic feature information of the tracking object through a neural network model for extracting image semantic features, and extract the key point features of the object through a key point detection model. The depth feature, color feature, texture feature, semantic feature, and key point feature of the tracking object are then fused to obtain the fused feature information of the tracking object. The device continuously records the position changes of the tracking object in consecutive frames, forming the tracking trajectory of the tracking object. Based on the tracking trajectory, the device predicts the position of the tracking object in future frames.

[0055] For example, suppose the object being tracked is a runner whose movement trajectory in the shooting preview interface is: [(450, 300), (452, 298), (455, 295), (459, 291), (464, 286), ...]; the horizontal speed Vx is 2.5 pixels / frame and the vertical speed Vy is -3.2 pixels / frame. Then, the runner moves to the upper right in the shooting preview image of the second electronic device, and it is predicted that after 3 frames, the center of the bounding box corresponding to the runner will be near (470, 275).

[0056] In some embodiments of this application, after obtaining the bounding box and tracking trajectory of the tracked object, the tracking confidence of the tracked object can be determined.

[0057] In some embodiments of this application, the tracking confidence of an object can be determined by the following formula (1): (1) In formula (1), For the tracking confidence of the object, The contrast between the object's bounding box and the background of the shooting preview interface. For the smoothness of the object's tracking trajectory, The probability that an object is occluded. , and As weight, , and The sum is 1. , and It can be configured according to actual needs, for example, It is 0.4. It is 0.3. The value is 0.3. Since the tracking confidence of an object is obtained by weighting the contrast between the object's bounding box and the background of the shooting preview interface, the smoothness of the object's tracking trajectory, and the probability of the object being occluded, the weighted tracking confidence can characterize the tracking quality of the object. The contrast between the object's bounding box and the background of the shooting preview interface can characterize the object's sharpness, the smoothness of the object's tracking trajectory can characterize the object's stability, and the probability of the object being occluded can characterize the occlusion risk.

[0058] For example, the contrast between the bounding box of a tracked object and the background of the captured preview image is 0.85, the smoothness of the tracking trajectory of the tracked object is 0.78, and the probability of the tracked object being occluded is 0.15. It is 0.4. It is 0.3. The confidence level of the tracking object is 0.829, which can be obtained by formula (1) above.

[0059] After the second electronic device obtains the fusion feature information, trajectory information and tracking confidence of the tracked object, the second electronic device sends the fusion feature information, trajectory information and tracking confidence of the tracked object to the first electronic device.

[0060] After receiving the fusion feature information, trajectory information and tracking confidence of the tracked object sent by the second electronic device, the first electronic device performs object detection on its shooting preview interface and calculates the feature similarity between the fusion feature information of each detected object and the fusion feature information of the tracked object sent by the second electronic device.

[0061] The first electronic device determines the trajectory of each detected object, predicts the center position of the bounding box corresponding to each object based on the trajectory, and predicts the center position of the bounding box of the tracked object based on the trajectory information of the tracked object sent by the second electronic device; and determines a first matching degree based on the predicted center position of the bounding box corresponding to each object and the predicted center position of the bounding box of the tracked object.

[0062] In some embodiments of this application, when determining the first matching degree based on the center position of the bounding box corresponding to each predicted object and the center position of the bounding box of the predicted tracked object, the center position of the bounding box of the predicted tracked object can be adjusted according to the ratio of the shooting preview interface of the first electronic device and the shooting preview interface of the second electronic device to obtain the position of the center position of the bounding box of the tracked object in the shooting preview interface of the first electronic device. The first matching degree is determined based on the position of the center position of the bounding box of the tracked object in the shooting preview interface of the first electronic device and the center position of the bounding box corresponding to each predicted object.

[0063] In some embodiments of this application, the first matching degree can be determined by the following formula (2): (2) In formula (2), The first match degree, To determine the center position of the bounding box of the tracking object, the corresponding position in the shooting preview interface of the first electronic device. This represents the center position of the bounding box corresponding to the predicted i-th object. This refers to the diagonal length of the preview interface of the first electronic device.

[0064] The first electronic device determines the trajectory of each detected object, determines the direction of motion of each object based on the trajectory, and matches the determined direction of motion of each object with the direction of motion corresponding to the trajectory information of the tracked object sent by the second electronic device to obtain a second matching degree.

[0065] In some embodiments of this application, when matching the determined motion direction of each object with the motion direction corresponding to the trajectory information of the tracked object sent by the second electronic device to obtain the second matching degree, the cosine value of the angle between the two motion directions can be used as the second matching degree.

[0066] The first electronic device determines the tracking confidence level of each detected object, and matches the determined tracking confidence level of each object with the tracking confidence level of the tracked object sent by the second electronic device to obtain a third matching degree. The process by which the first electronic device determines the tracking confidence level of each detected object is similar to the process by which the second electronic device determines the tracking confidence level of the tracked object in the above embodiments. Therefore, this embodiment will not elaborate on the process here, but the specific process can be referred to the description in the above embodiments.

[0067] In some embodiments of this application, when matching the tracking confidence of each determined object with the tracking confidence of the tracked object sent by the second electronic device to obtain a third matching degree, the absolute value of the difference between the two tracking confidences can be taken as the third matching degree.

[0068] In some embodiments of this application, determining a target object from at least one object based on feature similarity, a first matching degree, a second matching degree, and a third matching degree may include: performing a weighted summation of the feature similarity, the first matching degree, the second matching degree, and the third matching degree to obtain a matching score between each object and a first object; and determining the object corresponding to the maximum matching score as the target object.

[0069] For example, suppose there are four objects, A, B, C, and D. The feature similarity, first match, second match, and third match between object A and the tracked object are 0.94, 0.88, 0.91, and 0.85, respectively; the feature similarity, first match, second match, and third match between object B and the tracked object are 0.42, 0.25, 0.38, and 0.3, respectively; and the feature similarity, first match, second match, and third match between object C and the tracked object are 0.38, 0.65, 0.22, and 0.35, respectively. The feature similarity, first matching degree, second matching degree, and third matching degree between object D and the tracked object are 0.28, 0.15, 0.18, and 0.2, respectively; the weights corresponding to feature similarity, first matching degree, second matching degree, and third matching degree are 0.4, 0.2, 0.2, and 0.2, respectively. Therefore, the overall matching degree of object A is 0.904, the overall matching degree of object B is 0.354, the overall matching degree of object C is 0.396, and the overall matching degree of object D is 0.218. Object A is determined as the target object.

[0070] In this embodiment of the application, target matching is performed using a multi-dimensional matching method, which can improve the reliability of target matching.

[0071] In this embodiment, the user does not need to manually reselect the tracking target. The tracking target can be automatically determined through object matching. The tracking target will not be lost during device switching, thereby improving target tracking efficiency and the continuity of shooting.

[0072] Step 103: Control the gimbal camera to track and capture the target object.

[0073] In some embodiments of this application, when the first electronic device controls the gimbal camera to track and capture a target object, the first electronic device can activate a tracking algorithm and control the attitude of the gimbal camera through the tracking algorithm so that the target object is within the image acquisition range of the gimbal camera.

[0074] In this embodiment, the first electronic device receives first information, including object feature information of a first object tracked and captured by a gimbal camera, sent by the second electronic device; based on the first information, it determines a target object from at least one object displayed on the shooting preview interface of the first electronic device; and controls the gimbal camera to track and capture the target object. Thus, the first electronic device can automatically control the gimbal camera to track objects selected by the user from the shooting preview interface of the second electronic device, eliminating the need for the user to select the tracking object from the shooting preview interface of the first electronic device. This prevents interruption of moving object tracking and improves the continuity of shooting.

[0075] In this embodiment, switching the control of the gimbal camera from the second electronic device to the first electronic device only takes about 150 millimeters. Compared with the 30 to 60 seconds required in related technologies to switch the control of the gimbal camera from the second electronic device to the first electronic device, the time required to switch the control of the gimbal camera from the second electronic device to the first electronic device can be reduced, the device switching efficiency can be improved, and thus the tracking of moving objects can be prevented from being interrupted, thereby improving the continuity of shooting.

[0076] In some embodiments of this application, the first information further includes the first attitude information of the gimbal camera; wherein, the first attitude information includes pitch angle and yaw angle; the first electronic device includes a gimbal controller, which is used to control the gimbal camera; accordingly, before step 103, the shooting method provided in the embodiments of this application may further include: setting the attitude information of the gimbal camera in the gimbal controller to the first attitude information.

[0077] In some embodiments of this application, the second electronic device may also send the attitude information of the gimbal camera to the first electronic device, and the first electronic device sets the attitude information of the gimbal camera in its gimbal controller to the attitude information of the gimbal camera sent by the second electronic device.

[0078] For example, after the user selects the tracking object through the shooting preview interface of the second electronic device, the second electronic device obtains the attitude information of the gimbal camera in its gimbal controller. Assuming that the attitude information of the gimbal camera in the gimbal controller of the second electronic device is: "pitch angle is -15.5°, yaw angle is 8.2°", the second electronic device sends the attitude information of the gimbal camera "pitch angle -15.5°, yaw angle 8.2°" to the first electronic device, and the first electronic device sets the pitch angle of the gimbal camera in its gimbal controller to -15.5° and the yaw angle to 8.2°.

[0079] In this embodiment of the application, the first electronic device sets the attitude information of the gimbal camera in its gimbal controller by using the attitude information of the gimbal camera in its gimbal controller sent by the second electronic device, which enables accurate tracking of the object.

[0080] In some embodiments of this application, when the first information includes object feature information of the first object tracked and captured by the gimbal camera, but does not include trajectory information of the first object and tracking confidence level corresponding to the first object, step 103 may include: controlling the gimbal camera to track and capture the target object when the maximum feature similarity is greater than or equal to the first threshold.

[0081] In some embodiments of this application, the first threshold can be set according to actual needs, and the value range of the first threshold can be from 0.75 to 1.

[0082] In some embodiments of this application, the tracking object may be lost, meaning the tracking object is not within the acquisition range of the gimbal camera. For example, during the process from when User1 selects the tracking object from the shooting preview interface of the second electronic device to when the first electronic device receives the first information sent by the second electronic device, User2, who is holding the gimbal camera, turns around, resulting in the tracking object selected by User1 not being within the acquisition range of the gimbal camera. The tracking object is not present in the shooting preview interface of the first electronic device. At this time, there is no object in the shooting preview interface of the first electronic device with a feature similarity greater than or equal to the first threshold of the object feature information of the tracking object. If the gimbal camera is controlled to track and shoot the determined target object, the objects tracked and shot by the gimbal camera before and after will be inconsistent.

[0083] To ensure that the object tracked and captured by the gimbal camera is consistent, the maximum feature similarity needs to be compared with a first threshold. When the maximum feature similarity is greater than or equal to the first threshold, it indicates that the target object and the object selected by the user are the same object, and the gimbal camera is controlled to track and capture the target object.

[0084] In some embodiments of this application, when the first information includes object feature information of the first object tracked and captured by the gimbal camera, trajectory information of the first object, and tracking confidence level corresponding to the first object, step 103 may include: controlling the gimbal camera to track and capture the target object when the maximum matching score is greater than or equal to the second threshold.

[0085] In some embodiments of this application, the tracking object may be lost, meaning the tracking object is not within the acquisition range of the gimbal camera. For example, during the process from when User1 selects the tracking object from the shooting preview interface of the second electronic device to when the first electronic device receives the first information sent by the second electronic device, User2, who is holding the gimbal camera, turns around, resulting in the tracking object selected by User1 not being within the acquisition range of the gimbal camera. The tracking object is not present in the shooting preview interface of the first electronic device. At this time, there is no object in the shooting preview interface of the first electronic device with a matching score greater than or equal to the second threshold. If the gimbal camera is controlled to track and shoot the determined target object, the objects tracked and shot by the gimbal camera before and after will be inconsistent.

[0086] To ensure that the object tracked and captured by the gimbal camera is consistent, the maximum matching score needs to be compared with the second threshold. When the maximum matching score is greater than or equal to the second threshold, it means that the target object and the object selected by the user are the same object, and the gimbal camera is controlled to track and capture the target object.

[0087] In this embodiment of the application, by controlling whether the gimbal camera tracks and captures the target object through a threshold, it is possible to ensure that the object tracked and captured by the gimbal camera is consistent before and after.

[0088] In some embodiments of this application, if the maximum feature similarity is less than a first threshold or the maximum matching score is less than a second threshold, the first electronic device may display a prompt message to indicate that the tracked object is lost and ask the user to reselect the tracked object.

[0089] In some embodiments of this application, before controlling the gimbal camera to track and photograph the target object when the maximum matching score is greater than or equal to the second threshold, the shooting method provided in the embodiments of this application may further include: determining the second threshold according to the shooting scene information; wherein, different shooting scene information corresponds to different second thresholds.

[0090] In some embodiments of this application, the second threshold corresponding to a standard shooting scene can be 0.75, the second threshold corresponding to a complex shooting scene can be 0.65, and the second threshold corresponding to a professional shooting scene can be 0.85.

[0091] This application does not limit the method used to determine the shooting scene information; any available method can be applied to this application. For example, a neural network model for scene recognition can be used to identify the captured image to obtain the shooting scene information; another example is to obtain the shooting mode of the gimbal camera and determine the shooting scene information based on the gimbal camera's shooting mode. For example, if the gimbal camera's shooting mode is a professional shooting mode, the determined shooting scene information is a professional shooting scene; if the gimbal camera's shooting mode is a standard shooting mode, the determined shooting scene information is a standard shooting scene.

[0092] In the embodiments of this application, the threshold can be dynamically adjusted according to different shooting scenarios, which can meet the tracking shooting needs under different shooting scenarios and improve the accuracy of tracking shooting.

[0093] In some embodiments of this application, the first electronic device and the second electronic device can enter a collaborative tracking mode. In collaborative tracking mode, the first electronic device and the second electronic device can synchronize a tracking status at regular intervals; the first electronic device and the second electronic device can independently evaluate the tracking confidence level, and when the tracking confidence level of one electronic device is low, the other electronic device takes over the tracking control; when one electronic device detects a tracking anomaly, such as the tracked object being obscured or not in the shooting preview interface, it can notify the other electronic device to take over the tracking control.

[0094] In some embodiments of this application, when an electronic device successfully takes over tracking control, the tracking screen is uninterrupted, and the user-perceived switching delay is lower than a preset threshold, the switching of the control device is determined to be complete.

[0095] In this embodiment, collaborative tracking and abnormal switching between two electronic devices are supported, thereby improving the robustness of tracking.

[0096] The following describes the shooting method provided in the embodiments of this application with specific examples.

[0097] For example, such as Figure 3 As shown, Figure 3 These are schematic diagrams illustrating tracking and shooting scenarios provided in some embodiments of this application. Figure 3 In the scenario, User A uses a handheld gimbal camera to film athletes at a sports field. User B's mobile phone is connected to the gimbal camera, and the phone's preview screen displays the image captured by the gimbal camera. Assume the image includes three athletes: Athlete X, Athlete Y, and Athlete Z. Figure 4 As shown, Figure 4 This is a second schematic diagram illustrating the selection of tracking objects provided in some embodiments of this application. Figure 4 In the video, user B selects athlete X as the subject to be tracked and filmed via their mobile phone. The mobile phone then controls the gimbal camera to track and film athlete X through its gimbal controller.

[0098] When User B wants to control the gimbal camera using their tablet, the tablet establishes communication connections with both the gimbal camera and the mobile phone. The tablet's preview interface displays the image captured by the gimbal camera. When the user triggers a device switch via their mobile phone, the phone displays a prompt message, such as... Figure 5 As shown, Figure 5 These are schematic diagrams illustrating the display of prompt information provided in some embodiments of this application. Figure 5 In the process, prompt 501 asks "Switch control of the gimbal camera to the tablet?" When the user clicks the "Confirm Switch" control 502, the control device switch is triggered. The mobile phone obtains the feature information of athlete X and sends this feature information, along with the gimbal camera's posture information, to the tablet. After receiving athlete X's feature information, the tablet obtains the feature information of each object in the shooting preview interface, calculates the feature similarity between each object's feature information and athlete X's feature information, and when the maximum feature similarity is greater than or equal to 0.75, the tablet sets the gimbal camera's posture information in its gimbal controller to the posture information of the gimbal camera sent by the mobile phone, and controls the gimbal camera to track and shoot the object corresponding to the maximum feature similarity. When the user clicks the "Do Not Switch" control 503, the mobile phone continues to control the gimbal camera.

[0099] For example, as described above Figure 3The illustrated tracking and filming scenario involves User A holding a gimbal camera and filming athletes in a sports field. User B's mobile phone is connected to the gimbal camera, and the phone's preview interface displays the image captured by the gimbal camera. Assuming the image includes three athletes, X, Y, and Z, User B selects athlete X as the subject to be tracked and filmed via their mobile phone. The phone then controls the gimbal camera to track and film athlete X through its gimbal controller, as described above. Figure 4 As shown.

[0100] When User B wants to control the gimbal camera using their tablet, the tablet establishes communication connections with both the gimbal camera and the mobile phone. The tablet's preview screen displays the image captured by the gimbal camera. When the user triggers a device switch via their mobile phone, the phone displays the image as described above. Figure 5 The prompt message shown indicates that when the user clicks the above... Figure 5 After the "Confirm Switch" control 502 is activated, the control device switch is triggered. The mobile phone obtains the feature information of athlete X and sends the feature information, trajectory information, corresponding tracking confidence score, and gimbal camera attitude information of athlete X to the tablet. After receiving the feature information, trajectory information, corresponding tracking confidence score, and gimbal camera attitude information of athlete X, the tablet obtains the feature information of each object in its shooting preview interface, calculates the feature similarity between the feature information of each object and the feature information of athlete X, and determines the matching degree between the position information of each object and the position information of athlete X, the matching degree between the movement direction of each object and the direction corresponding to the position information of athlete X, and the matching degree between the tracking confidence score of each object and the tracking confidence score of athlete X. Through the feature information and the above three matching degrees, the matching score between each object and athlete X is determined, and a second threshold is determined according to the shooting scene information. When the maximum matching score is greater than or equal to the second threshold determined according to the shooting scene information, the tablet sets the attitude information of the gimbal camera in its gimbal controller to the attitude information of the gimbal camera sent by the mobile phone, and controls the gimbal camera to track and shoot the object corresponding to the maximum matching score. After the user clicks the "Do not switch" control 503, they can continue to control the gimbal camera using their mobile phone.

[0101] The shooting method provided in this application can be executed by a shooting device. This application uses a shooting device executing the shooting method as an example to illustrate the shooting device provided in this application.

[0102] Figure 6 This is a schematic diagram of the structure of a shooting device provided in some embodiments of this application. The shooting device 600 includes: The receiving module 601 is used to receive first information sent by the second electronic device; wherein, the first information includes object feature information of a first object tracked and captured by the gimbal camera; The determining module 602 is used to determine a target object from at least one object displayed on the shooting preview interface of the first electronic device based on the first information; The control module 603 is used to control the gimbal camera to track and capture target objects.

[0103] In some embodiments of this application, the determining module 602 is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each object in at least one object; The object with the highest feature similarity is identified as the target object.

[0104] In some embodiments of this application, the control module 603 is specifically used for: When the maximum feature similarity is greater than or equal to the first threshold, control the gimbal camera to track and capture the target object.

[0105] In some embodiments of this application, the first information further includes trajectory information of the first object and a first tracking confidence level corresponding to the first object; wherein, the trajectory information is the historical movement trajectory of the first object in the shooting preview interface of the second electronic device; the first tracking confidence level is used to characterize the tracking quality of the first object; Accordingly, module 602 is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each object in at least one object; Determine the first matching degree between the location information of each object and the first location information; wherein, the first location information is the location information predicted based on the trajectory information; Determine the second degree of matching between the motion direction of each object and the direction corresponding to the trajectory information; Determine the third matching degree between the second tracking confidence and the first tracking confidence for each object; The target object is determined from at least one object based on feature similarity, first matching degree, second matching degree, and third matching degree.

[0106] In some embodiments of this application, the determining module 602 is specifically used for: The feature similarity, first matching degree, second matching degree and third matching degree are weighted and summed to obtain the matching score between each object and the first object; The object corresponding to the highest matching score is identified as the target object.

[0107] In some embodiments of this application, the control module 603 is specifically used for: If the maximum matching score is greater than or equal to the second threshold, control the gimbal camera to track and capture the target object.

[0108] In some embodiments of this application, the determining module 602 is further configured to: Determine the second threshold based on the shooting scene information; Different shooting scene information corresponds to different second thresholds.

[0109] In some embodiments of this application, the first information further includes first attitude information of the gimbal camera; wherein, the first attitude information includes pitch angle and yaw angle; the first electronic device includes a gimbal controller, which is used to control the gimbal camera; The imaging device provided in this application embodiment also includes: The setting module is used to set the attitude information of the gimbal camera in the gimbal controller as the first attitude information.

[0110] In some embodiments of this application, the object feature information includes at least one of the following: Depth feature information, texture feature information, color feature information, semantic feature information.

[0111] The shooting device in this application embodiment can be an electronic device or a component of an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM or self-service machine, etc. The embodiments of this application do not specifically limit it.

[0112] The shooting device in this application embodiment can be a device with an operating system. The operating system can be Android, iOS, or other possible operating systems, and this application embodiment does not specifically limit it.

[0113] The imaging device provided in this application embodiment can achieve... Figures 1 to 5 The various processes implemented in the shooting method embodiment will not be described again here to avoid repetition.

[0114] Optionally, such as Figure 7 As shown, this application embodiment also provides an electronic device 700, including a processor 701 and a memory 702. The memory 702 stores a program or instructions that can run on the processor 701. When the program or instructions are executed by the processor 701, they implement the various steps of the shooting method embodiment provided in this application embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0115] Figure 8 These are schematic diagrams of the hardware structure of electronic devices according to some embodiments of this application.

[0116] The electronic device 800 includes, but is not limited to, components such as: radio frequency unit 801, network module 802, audio output unit 803, input unit 804, sensor 805, display unit 806, user input unit 807, interface unit 808, memory 809, and processor 810.

[0117] Those skilled in the art will understand that the electronic device 800 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 810 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 8 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0118] The processor 810 is configured to: receive first information sent by the second electronic device; wherein the first information includes object feature information of a first object tracked and captured by the gimbal camera; determine a target object from at least one object displayed on the shooting preview interface of the electronic device 800 according to the first information; and control the gimbal camera to track and capture the target object.

[0119] In some embodiments of this application, the processor 810 is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each object in at least one object; The object with the highest feature similarity is identified as the target object.

[0120] In some embodiments of this application, the processor 810 is specifically used for: When the maximum feature similarity is greater than or equal to the first threshold, control the gimbal camera to track and capture the target object.

[0121] In some embodiments of this application, the first information further includes trajectory information of the first object and a first tracking confidence level corresponding to the first object; wherein, the trajectory information is the historical movement trajectory of the first object in the shooting preview interface of the second electronic device; the first tracking confidence level is used to characterize the tracking quality of the first object; Accordingly, the processor 810 is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each object in at least one object; Determine the first matching degree between the location information of each object and the first location information; wherein, the first location information is the location information predicted based on the trajectory information; Determine the second degree of matching between the motion direction of each object and the direction corresponding to the trajectory information; Determine the third matching degree between the second tracking confidence and the first tracking confidence for each object; The target object is determined from at least one object based on feature similarity, first matching degree, second matching degree, and third matching degree.

[0122] In some embodiments of this application, the processor 810 is specifically used for: The feature similarity, first matching degree, second matching degree and third matching degree are weighted and summed to obtain the matching score between each object and the first object; The object corresponding to the highest matching score is identified as the target object.

[0123] In some embodiments of this application, the processor 810 is specifically used for: If the maximum matching score is greater than or equal to the second threshold, control the gimbal camera to track and capture the target object.

[0124] In some embodiments of this application, the processor 810 is also used for: Determine the second threshold based on the shooting scene information; Different shooting scene information corresponds to different second thresholds.

[0125] In some embodiments of this application, the first information further includes first attitude information of the gimbal camera; wherein, the first attitude information includes pitch angle and yaw angle; the electronic device 800 includes a gimbal controller, which is used to control the gimbal camera; Accordingly, the processor 810 is also used for: Set the attitude information of the gimbal camera in the gimbal controller as the first attitude information.

[0126] In some embodiments of this application, the object feature information includes at least one of the following: Depth feature information, texture feature information, color feature information, semantic feature information.

[0127] It should be understood that, in this embodiment, the input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042. The GPU 8041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 806 may include a display panel 8061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 807 includes at least one of a touch panel 8071 and other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0128] The memory 809 can be used to store software programs and various data. The memory 809 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 809 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 809 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0129] Processor 810 may include one or more processing units; optionally, processor 810 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 810.

[0130] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the shooting method provided in this application and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0131] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0132] This application also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the shooting method provided in this application and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0133] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0134] This application also provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the shooting method embodiment provided in this application, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0135] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0136] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the shooting methods provided in the various embodiments of this application.

[0137] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A shooting method, performed by a first electronic device, characterized in that, The method includes: Receive first information sent by a second electronic device; wherein the first information includes object feature information of a first object tracked and captured by a gimbal camera; Based on the first information, a target object is determined from at least one object displayed on the shooting preview interface of the first electronic device; Control the gimbal camera to track and capture images of the target object.

2. The method according to claim 1, characterized in that, The step of determining the target object from at least one object displayed on the shooting preview interface of the first electronic device based on the first information includes: Determine the feature similarity between the object feature information of the first object and the object feature information of each of the at least one object; The object with the highest feature similarity is identified as the target object.

3. The method according to claim 2, characterized in that, The control of the gimbal camera to track and capture the target object includes: If the maximum feature similarity is greater than or equal to a first threshold, the gimbal camera is controlled to track and capture the target object.

4. The method according to claim 1, characterized in that, The first information also includes trajectory information of the first object and a first tracking confidence level corresponding to the first object; wherein, the trajectory information is the historical movement trajectory of the first object in the shooting preview interface of the second electronic device; the first tracking confidence level is used to characterize the tracking quality of the first object; The step of determining the target object from at least one object displayed on the shooting preview interface of the first electronic device based on the first information includes: Determine the feature similarity between the object feature information of the first object and the object feature information of each of the at least one object; Determine a first matching degree between the location information of each object and the first location information; wherein, the first location information is the location information predicted based on the trajectory information; Determine a second degree of matching between the motion direction of each object and the direction corresponding to the trajectory information; Determine the third matching degree between the second tracking confidence score and the first tracking confidence score for each object; The target object is determined from the at least one object based on the feature similarity, the first matching degree, the second matching degree, and the third matching degree.

5. The method according to claim 4, characterized in that, Determining the target object from the at least one object based on the feature similarity, the first matching degree, the second matching degree, and the third matching degree includes: The feature similarity, the first matching degree, the second matching degree, and the third matching degree are weighted and summed to obtain the matching score between each object and the first object; The object corresponding to the highest matching score is identified as the target object.

6. The method according to claim 5, characterized in that, The control of the gimbal camera to track and capture the target object includes: If the maximum matching score is greater than or equal to the second threshold, the gimbal camera is controlled to track and capture the target object.

7. The method according to claim 6, characterized in that, Before controlling the gimbal camera to track and capture the target object when the maximum matching score is greater than or equal to the second threshold, the method further includes: Determine the second threshold based on the shooting scene information; Different shooting scene information corresponds to different second thresholds.

8. The method according to claim 1, characterized in that, The first information also includes the first attitude information of the gimbal camera; wherein, the first attitude information includes pitch angle and yaw angle; the first electronic device includes a gimbal controller, which is used to control the gimbal camera; Before controlling the gimbal camera to track and capture the target object, the method further includes: The attitude information of the gimbal camera in the gimbal controller is set to the first attitude information.

9. The method according to claim 1, characterized in that, The object feature information includes at least one of the following: depth feature information, texture feature information, color feature information, and semantic feature information.

10. A shooting device, characterized in that, The device includes: A receiving module is used to receive first information sent by a second electronic device; wherein the first information includes object feature information of a first object tracked and captured by a gimbal camera; The determining module is configured to determine a target object from at least one object displayed on the shooting preview interface of the first electronic device based on the first information; The control module is used to control the gimbal camera to track and capture images of the target object.

11. The shooting device according to claim 10, characterized in that, The determining module is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each of the at least one object; The object with the highest feature similarity is identified as the target object.

12. The shooting device according to claim 11, characterized in that, The control module is specifically used for: If the maximum feature similarity is greater than or equal to a first threshold, the gimbal camera is controlled to track and capture the target object.

13. The shooting device according to claim 10, characterized in that, The first information also includes trajectory information of the first object and a first tracking confidence level corresponding to the first object; wherein, the trajectory information is the historical movement trajectory of the first object in the shooting preview interface of the second electronic device; the first tracking confidence level is used to characterize the tracking quality of the first object; The determining module is specifically used for: Determine the feature similarity between the object feature information of the first object and the object feature information of each of the at least one object; Determine a first matching degree between the location information of each object and the first location information; wherein, the first location information is the location information predicted based on the trajectory information; Determine a second degree of matching between the motion direction of each object and the direction corresponding to the trajectory information; Determine the third matching degree between the second tracking confidence score and the first tracking confidence score for each object; The target object is determined from the at least one object based on the feature similarity, the first matching degree, the second matching degree, and the third matching degree.

14. The shooting device according to claim 13, characterized in that, The determining module is specifically used for: The feature similarity, the first matching degree, the second matching degree, and the third matching degree are weighted and summed to obtain the matching score between each object and the first object; The object corresponding to the highest matching score is identified as the target object.

15. The shooting device according to claim 14, characterized in that, The control module is specifically used for: If the maximum matching score is greater than or equal to the second threshold, the gimbal camera is controlled to track and capture the target object.

16. The shooting device according to claim 15, characterized in that, The determining module is also used for: Determine the second threshold based on the shooting scene information; Different shooting scene information corresponds to different second thresholds.

17. The shooting device according to claim 10, characterized in that, The first information also includes the first attitude information of the gimbal camera; wherein, the first attitude information includes pitch angle and yaw angle; the first electronic device includes a gimbal controller, which is used to control the gimbal camera; The device further includes: The setting module is used to set the attitude information of the gimbal camera in the gimbal controller to the first attitude information.

18. The shooting device according to claim 10, characterized in that, The object feature information includes at least one of the following: depth feature information, texture feature information, color feature information, and semantic feature information.

19. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the shooting method as described in any one of claims 1-9.

Images