Camera control method, electronic equipment, storage medium and computer program product

Abstract

The invention provides a camera control method, an electronic device, a storage medium and a computer program product, and the method comprises the steps: enabling a sound box to respond to a first voice instruction issued by a target user, and determining the user position information of the target user based on a local microphone array; the sound box determines an initial angle correction parameter based on the user position information and the equipment position information of the camera, and sends the initial angle correction parameter to the camera; the camera adjusts the posture of the camera based on the initial angle correction parameter, takes a plurality of sample photos after adjustment, and sends the sample photos to the loudspeaker box; the sound box sends the plurality of sample photos to the server to obtain a target angle correction parameter returned by the server, and sends the target angle correction parameter to the camera; the target angle correction parameter is determined by the server based on a plurality of sample photos; and the camera adjusts the posture of the camera based on the target angle correction parameter, and executes a shooting task after adjustment. According to the scheme, the shooting difficulty is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a camera control method and device, electronic equipment, computer-readable storage medium, and computer program product. Background Art

[0002] The rise of short video platforms has stimulated the public's enthusiasm for filming. More and more creators use mobile phones, tablets, cameras and other video devices to shoot videos and then upload short videos to the platform. The traditional shooting method requires one person to act as a photographer, and the cameraman uses the camera device to shoot videos and photos for another person. In this case, if someone needs to be in the shot, at least two people are needed to complete the shooting.

[0003] The relevant scheme provides a video shooting method based on voice recognition, which determines the shooting time by identifying the voice content of the video shooting person, and then starts shooting the shooting person; and when the voice content is recognized to indicate to stop shooting, the shooting work can be stopped.

[0004] The relevant scheme can realize the shooting work when there is only one person. However, the relevant scheme is mainly used for shooting scenes where the shooting personnel are in a specific position. When the shooting personnel are not in a specific position, one person needs to stand in front of the camera to take pictures and check the shooting effect, and then adjust the posture of the camera device. Only after repeated adjustments can the ideal shooting effect be obtained. It can be seen that the relevant scheme requires manual adjustment of the camera posture, which is time-consuming and labor-intensive, and greatly increases the difficulty of shooting. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a camera control method and electronic equipment, storage medium, and computer program product, which are used to improve the automation level of the camera process and reduce the difficulty of shooting in a scenario where one person completes the shooting work.

[0006] On the one hand, the present application provides a camera control method, which is applied to a control system, wherein the control system includes a speaker, a server, and a camera, including:

[0007] The speaker determines the user location information of the target user based on the local microphone array in response to the first voice command issued by the target user; wherein the first voice command instructs to start the camera task;

[0008] The speaker determines an initial angle correction parameter based on the user position information and the device position information of the camera, and sends the initial angle correction parameter to the camera;

[0009] The camera adjusts its own posture based on the initial angle correction parameter, takes a number of sample photos after the adjustment, and sends the number of sample photos to the speaker;

[0010] The speaker sends the sample photos to the server to obtain the target angle correction parameters returned by the server, and sends the target angle correction parameters to the camera; wherein the target angle correction parameters are determined by the server based on the sample photos;

[0011] The camera adjusts its own posture based on the target angle correction parameter and performs a shooting task after the adjustment.

[0012] In one embodiment, the method further comprises:

[0013] During the camera shooting process, the speaker obtains the currently shot video frame from the camera multiple times, and sends each obtained video frame as a sample photo to the server to obtain the target angle correction parameter updated by the server based on the sample photo;

[0014] The speaker sends the updated target angle correction parameter to the camera;

[0015] The camera adjusts its own posture based on the updated target angle correction parameter.

[0016] In one embodiment, the speaker is equipped with an RFID reader, and the camera carries an RFID tag;

[0017] The step of acquiring the device location information comprises:

[0018] The speaker identifies the RFID tag carried by the camera through the RFID reader to determine the device location information.

[0019] In one embodiment, the initial angle correction parameters include an initial left-right rotation angle, an initial up-down rotation angle, and an initial imaging rotation angle;

[0020] The speaker determines an initial angle correction parameter based on the user position information and the device position information of the camera, including:

[0021] The speaker determines an initial left-right rotation angle based on the user position information and the device position information, and sets the initial up-down rotation angle and the initial imaging rotation angle to zero to obtain the initial angle correction parameter.

[0022] In one embodiment, taking a number of sample photos after adjustment includes:

[0023] The camera takes sample photos respectively at multiple specified elevation angles to obtain multiple sample photos.

[0024] In one embodiment, the sample photo carries its corresponding camera posture information;

[0025] The speaker sends the sample photos to the server to obtain the target angle correction parameters returned by the server, including:

[0026] The speaker sends the plurality of sample photos to the server;

[0027] The server determines a target angle correction parameter based on the image position of the target user in each sample photo and the camera posture information corresponding to each sample photo, and sends the parameter to the speaker.

[0028] In one embodiment, the camera adjusts its own posture based on the target angle correction parameter, and performs the shooting task after the adjustment:

[0029] The camera adjusts its own posture based on the target angle correction parameter, and returns adjustment completion information to the speaker;

[0030] The speaker plays a start recording message and sends a start recording instruction to the camera;

[0031] The camera executes a shooting task in response to the start shooting instruction.

[0032] In one embodiment, the method further comprises:

[0033] The speaker controls the camera to stop the video recording task in response to the second voice instruction sent by the target user; wherein the second voice instruction instructs to stop the video recording task.

[0034] In one embodiment, the method further comprises:

[0035] During the camera shooting process, the sound box determines the time interval for acquiring video frames based on a slow start algorithm.

[0036] In one embodiment, an interval initial value and an interval threshold value are set in the slow start algorithm, and the time interval is initially the interval initial value;

[0037] The speaker determines the time interval for acquiring video frames based on a slow start algorithm, including:

[0038] When the speaker obtains the updated target angle correction parameter each time, if the target angle correction parameter indicates not to adjust the camera posture, the time interval is updated by the following formula:

[0039] If param_ss≤ssthresh / 2, param_ss=param_ss*2;

[0040] If ssthresh / 2<param_ss<ssthresh, param_ss=param_ss+congest_avoid_step;

[0041] If ssthresh≤param_ss, param_ss=init_ss;

[0042] If the target angle correction parameter indicates adjusting the camera's posture, the time interval is updated by the following formula:

[0043] param_ss = init_ss;

[0044] Among them, the param_ss is the time interval; the init_ss is the interval initial value; the congest_avoid_step is the interval step; and the ssthresh is the interval threshold value.

[0045] In one embodiment, the method further comprises:

[0046] If the target user is not in the video frame, the server sends a specific parameter as the target angle correction parameter to the speaker; the specific parameter indicates that the target user is not in the video frame;

[0047] When the speaker determines that the target angle correction parameter is a specific parameter, the speaker plays a warning message instructing the user to return to the camera.

[0048] Furthermore, the present application provides an electronic device, the electronic device comprising:

[0049] processor;

[0050] a memory for storing processor-executable instructions;

[0051] Wherein, the processor is configured to execute the above-mentioned camera control method applied to the speaker or the server or the camera.

[0052] Furthermore, the present application provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by a processor to complete the above-mentioned camera control method applied to a speaker or a server or a camera.

[0053] In addition, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned camera control method applied to a speaker or a server or a camera.

[0054] In the present application scheme, the speaker can determine the user location information of the target user when responding to the first voice command instructing to start the shooting task, and determine the initial angle correction parameters of the camera based on the user location information and the device location information of the camera. The initial angle correction parameters correspond to the relative position relationship between the target user and the camera, so that the camera can make preliminary adjustments to its own posture based on the initial angle correction parameters; after the adjustment, the camera can take a number of sample photos and send them to the speaker, so that the speaker hands the sample photos to the server for processing; the server can determine the target angle correction parameters based on the sample photos to instruct the camera to further adjust its own posture; the speaker can send the target angle correction parameters returned by the server to the camera, so that the camera further adjusts its own posture, and performs the shooting task after the adjustment to obtain a good shooting effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.

[0056] Figure 1 A schematic diagram of the architecture of a control system provided in one embodiment of the present application;

[0057] Figure 2 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application;

[0058] Figure 3 A schematic diagram of a flow chart of a camera control method provided in an embodiment of the present application;

[0059] Figure 4 A flowchart of a tracking and shooting method provided in one embodiment of the present application. DETAILED DESCRIPTION

[0060] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0061] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0062] Figure 1 Schematic diagram of a control system provided in an embodiment of the present application. Figure 1 As shown, the control system includes a camera 20, a speaker 30 and a server 40; the speaker 30 can interact with the camera 20 and the server 40 respectively to realize the control process of the camera 20; the server 40 can be a host, a server, a server cluster or a cloud computing center, and can execute corresponding computing tasks in response to the instructions sent by the speaker 30.

[0063] like Figure 2 As shown, this embodiment provides an electronic device 1, including: at least one processor 11 and a memory 12, Figure 2 A processor 11 is taken as an example. The processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11. The instructions are executed by the processor 11 so that the electronic device 1 can execute all or part of the process of the method in the following embodiment. In one embodiment, the electronic device 1 can be a camera 20, a speaker 30 or a server 40 in a control system, which is used to execute the camera control method.

[0064] The memory 12 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0065] The present application also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by the processor 11 to complete the camera control method provided in the present application and applied to a camera, a speaker or a server.

[0066] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the camera control method provided in the present application and applied to a camera, a speaker or a server.

[0067] See also Figure 3 , is a flow chart of a camera control method provided by an embodiment of the present application, such as Figure 3As shown, the method may include the following steps 310 - 350 .

[0068] Step 310: The speaker determines the user location information of the target user based on the local microphone array in response to the first voice instruction issued by the target user; wherein the first language instruction instructs to start the camera task.

[0069] This solution is applied to a control system, which may include a speaker, a server, and a camera.

[0070] The target users are those who shoot the video through the control system and are also the people who appear in the video during the shooting process.

[0071] When video shooting is required, the target user can speak a first voice command to the speaker to start the shooting task. For example, the first voice command can be "start video shooting", "please shoot video", "start shooting task", etc.

[0072] The speaker can recognize the voice command issued by the target user and parse the voice command. On the one hand, if the voice command cannot be parsed, a prompt tone indicating that it cannot be recognized can be played. For example: "Unable to recognize the command, please explain again", "Can't hear clearly, please say it again", etc. So that the target user re-issues the first voice command. This process can continue for many times until the speaker can accurately recognize the voice command issued by the target user. On the other hand, if the voice command is parsed as the first voice command, the speaker can determine the user position information of the target user based on the local microphone array. Among them, the local microphone array of the speaker includes at least three microphones; the user position information can characterize the position of the target user relative to the speaker. For example, a plane coordinate system is established with the speaker as the coordinate origin, and the user position information can be determined as user(x,y). Here, the specific implementation method of determining the relative position of the speaker by the microphone array can refer to the existing technology and will not be repeated here.

[0073] In one embodiment, when the speaker is started, it can connect to the camera through the network, generate the public key and private key of the RSA algorithm, and send the public key to the camera. The subsequent communication between the speaker and the camera can be carried out in an encrypted state, thereby improving the security factor of the network communication.

[0074] Step 320: The speaker determines initial angle correction parameters based on the user position information and the device position information of the camera, and sends the initial angle correction parameters to the camera.

[0075] The device position information represents the position of the camera relative to the sound box. Exemplarily, the device position information may be the coordinates camera (x, y) in a plane coordinate system established with the sound box as the coordinate origin.

[0076] The device location information can be pre-configured in the speaker memory. In this scenario, it can be assumed that the relative position between the camera and the speaker remains basically unchanged. In one embodiment, considering that the positions of the camera and the speaker may be adjusted according to shooting needs during a specific application, the latest device location information of the camera can be determined before executing step 320. In this case, the speaker can be equipped with an RFID (Radio Frequency Identification) reader, and the camera can be equipped with an RFID tag. The speaker can identify the RFID tag carried by the camera through the RFID reader to determine the device location information.

[0077] After obtaining the user position information and the device position information of the camera, the speaker can determine the relative position relationship between the target user and the camera, and then determine the initial angle correction parameter based on the relative position relationship and the initial orientation of the camera on the horizontal plane. The initial angle correction parameter is used to instruct the camera to adjust its own posture so that the image captured by the camera can place the target user in a suitable position (for example, so that the face of the target user is located in the center of the image). After obtaining the initial angle correction parameter, the speaker can send the initial angle correction parameter to the camera. The initial orientation of the camera on the horizontal plane can be synchronized to the speaker when the speaker establishes a network connection with the camera.

[0078] The initial angle correction parameters include the initial left-right rotation angle, the initial up-down rotation angle and the initial imaging rotation angle.

[0079] Among them, a spatial rectangular coordinate system is established with the position of the camera as the origin, the XOY plane is parallel to the horizontal plane, and the Z axis is perpendicular to the horizontal plane. Left and right rotation means that the camera head rotates left or right on a plane parallel to the horizontal plane with the Z axis as the rotation axis, and the initial left and right rotation angle is the angle of left and right rotation during the initial adjustment. For example, the initial left and right rotation angle is 10 degrees, indicating that the camera head needs to rotate 10 degrees to the right on a plane parallel to the horizontal plane with the Z axis as the rotation axis; or, the initial left and right rotation angle is -15 degrees, indicating that the camera head needs to rotate 15 degrees to the left on a plane parallel to the horizontal plane with the Z axis as the rotation axis.

[0080] Up and down rotation means that the camera head rotates upward or downward, and the plane of camera movement during rotation is perpendicular to the XOY plane. The initial up and down rotation angle is the angle of up and down rotation during initial adjustment. For example, the initial up and down rotation angle is 30 degrees, indicating that the camera head needs to be rotated 30 degrees upward; or the initial up and down rotation angle is -20 degrees, indicating that the camera head needs to be rotated 20 degrees downward.

[0081] Imaging rotation refers to the rotation of the camera's head to the left or right around the axis perpendicular to the image plane where the imaging is located. The purpose of imaging rotation is to ensure that the imaging angle of the photograph taken is reasonable. For example: through imaging rotation, the imaging effect is changed from a tilted state to a horizontal state. The initial imaging rotation angle is the angle of the imaging rotation during the initial adjustment. For example, the initial imaging rotation angle is 20 degrees, indicating that the camera's head needs to be rotated 20 degrees to the right around the axis perpendicular to the image plane where the imaging is located; or, the initial imaging rotation angle is -20 degrees, indicating that the camera's head needs to be rotated 20 degrees to the left around the axis perpendicular to the image plane where the imaging is located.

[0082] Step 330: The camera adjusts its own posture based on the initial angle correction parameter, takes a number of sample photos after the adjustment, and sends the number of sample photos to the speaker.

[0083] The posture of the camera is determined by three angles corresponding to the camera head, which are a first angle corresponding to a left-right rotation angle, a second angle corresponding to an up-down rotation angle, and a third angle corresponding to an imaging rotation angle.

[0084] After obtaining the initial angle correction parameters, the camera can adjust its own posture based on the initial angle correction parameters. In other words, the first angle is adjusted by the initial left-right rotation angle, the second angle is adjusted by the initial up-down rotation angle, and the third angle is adjusted by the initial imaging rotation angle. After the adjustment, several photos are taken as sample photos, and the sample photos taken are sent to the speaker. Here, the sample photos can be one or more, which can be configured as needed.

[0085] Step 340: The speaker sends several sample photos to the server to obtain the target angle correction parameters returned by the server, and sends the target angle correction parameters to the camera; wherein the target angle correction parameters are determined by the server based on the several sample photos.

[0086] The speaker can send several sample photos sent by the camera to the server, and the server determines the target angle correction parameters based on the sample photos. Here, the target angle correction parameters are parameters required for the camera to further adjust the posture. The target angle correction parameters may include the target left and right rotation angle, the target up and down rotation angle, and the target imaging rotation angle. The server can identify the position of the target user in the sample photo through the recognition algorithm, determine whether the position of the target user is ideal, and then calculate the target angle correction parameters when the target user is in the ideal position in the picture (for example: let the target user's face be in the center of the picture). The server can send the calculated target angle correction parameters to the speaker.

[0087] After the sound box obtains the target angle correction parameter, it can send the target angle correction parameter to the camera.

[0088] Step 350: The camera adjusts its own posture based on the target angle correction parameter and performs the shooting task after the adjustment.

[0089] After the camera obtains the target angle correction parameters, it can further adjust its own posture according to the target angle correction parameters. In other words, the first angle is adjusted by the target left and right rotation angle, the second angle is adjusted by the target up and down rotation angle, and the third angle is adjusted by the target imaging rotation angle, so as to perform the shooting task after the adjustment.

[0090] Through the above measures, the speaker can determine the user location information of the target user when responding to the first voice command instructing to start the shooting task, and determine the initial angle correction parameter of the camera based on the user location information and the device location information of the camera. The initial angle correction parameter corresponds to the relative position relationship between the target user and the camera, so that the camera can make preliminary adjustments to its own posture based on the initial angle correction parameter; after the adjustment, the camera can take a number of sample photos and send them to the speaker, so that the speaker will hand over the sample photos to the server for processing; the server can determine the target angle correction parameter based on the sample photos to instruct the camera to further adjust its own posture; the speaker can send the target angle correction parameter returned by the server to the camera, so that the camera further adjusts its own posture, and performs the shooting task after the adjustment to obtain a good shooting effect.

[0091] In one embodiment, when determining the initial angle correction parameters, the speaker can determine the initial left and right rotation angle based on the user position information and the device position information, and set the initial up and down rotation angle and the initial imaging rotation angle to zero to obtain the initial angle correction parameters.

[0092] Since the user position information and device position information can determine the relative position relationship between the target user and the camera on the horizontal plane, the speaker can determine the initial left-right rotation angle based on the relative position relationship, so that the camera can include the target user in the camera's field of view after rotating left-right at the initial left-right rotation angle. However, since the speaker cannot know the relationship between the target user's face and the camera's field of view in the vertical direction in the initial state, and cannot know the imaging effect, the initial up-down rotation angle and the initial imaging rotation angle can be set to zero, and the camera does not need to be rotated in the vertical direction or around the axis of the image plane, which will be adjusted later.

[0093] In one embodiment, when executing step 330 to take sample photos, the camera can take sample photos at multiple specified elevation angles to obtain multiple sample photos. Here, the specified elevation angle can be configured based on experience. Exemplarily, the specified elevation angle can be 45 degrees, 0 degrees, and -45 degrees, that is, the sample photos are taken when the second angle is 45 degrees, 0 degrees, and -45 degrees respectively.

[0094] The sample photos taken at multiple specified elevation angles can ensure that the imaging effects presented by the multiple sample photos can effectively reflect the relative position relationship between the target user and the camera in the vertical direction, so that the subsequent server can accurately calculate the target angle correction parameters with multiple sample photos.

[0095] In one embodiment, the sample photo carries the corresponding camera posture information, in other words, the sample photo carries the first angle, the second angle and the third angle of the camera when shooting. In addition, the sample photo may also carry the device location information.

[0096] When the speaker sends the sample photos to the server to obtain the target angle correction parameters, it can send several sample photos carrying camera posture information to the server. The server can determine the target angle correction parameters based on the image position of the target user in each sample photo and the camera posture information corresponding to each sample photo, and send the target angle correction parameters to the speaker.

[0097] Through this measure, the server can determine the target angle correction parameters required to obtain a good imaging effect based on the image position of the target user in each sample photo and the camera posture information corresponding to each sample photo.

[0098] In one embodiment, when executing step 350, the camera can adjust its own posture based on the target angle correction parameter, and after the adjustment is completed, return adjustment completion information to the speaker, wherein the adjustment completion information indicates that the camera has adjusted itself using the target angle correction parameter.

[0099] The speaker receives the adjustment completion information and can determine that the camera has completed the posture adjustment. At this time, the speaker can play a start recording message. The start recording message is used to prompt the target user that the camera will start recording. Exemplary, the start recording message can be "Please note that recording is about to start", "Recording will start after the countdown ends, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0", etc.

[0100] The sound box may send a start shooting instruction to the camera, and the start shooting instruction is used to instruct the camera to perform a shooting task. After receiving the start shooting instruction, the camera may respond to the start shooting instruction and perform the shooting task.

[0101] Through this measure, after the camera adjusts its posture, the speaker can notify the target user through voice broadcast, thereby reminding the target user to enter the shooting state.

[0102] In one embodiment, participating Figure 4 , is a flow chart of a tracking shooting method provided by an embodiment of the present application, such as Figure 4 As shown, the method may include the following steps 410 to 430.

[0103] Step 410: During the camera shooting process, the speaker obtains the currently shot video frame from the camera multiple times, and sends each obtained video frame as a sample photo to the server to obtain the target angle correction parameter updated by the server based on the sample photo.

[0104] During the camera shooting process, the target user may move. In order to avoid the target user leaving the lens and causing normal shooting, the speaker can obtain the current video frame shot by the camera as a sample photo at regular intervals and send the sample photo to the server, so that the server can recalculate the target angle correction parameters based on the sample photo.

[0105] Step 420: The speaker sends the updated target angle correction parameters to the camera.

[0106] After the speaker obtains the target angle correction parameter returned by the server, it can send the target angle correction parameter to the camera.

[0107] Step 430: The camera adjusts its own posture based on the updated target angle correction parameters.

[0108] The camera can adjust the first angle based on the target left and right rotation angle in the updated target angle correction parameters, adjust the second angle based on the target up and down rotation angle, and adjust the third angle based on the target imaging rotation angle, thereby completing the adjustment of its own posture and continuing to perform the shooting task after the adjustment.

[0109] Through the above measures, during the execution of the shooting task, the target user can be tracked to ensure that the target user in the shot video is always in an ideal position on the screen, thereby obtaining a good shooting effect.

[0110] In one embodiment, during the camera shooting process, when the speaker obtains the currently shot video frames from the camera multiple times, the time interval for obtaining the video frames can be determined based on the slow start algorithm, and then the time point for obtaining the video frames each time can be determined according to the time interval.

[0111] Through this measure, the speaker can dynamically adjust the acquisition and transmission frequency of video frames, thereby reducing network congestion caused by frequent communications.

[0112] In one embodiment, the interval initial value and the interval threshold value are set in the slow start algorithm, and the time interval is initially the interval initial value. Here, the interval initial value and the interval threshold value can be configured as needed. Exemplarily, the interval initial value is any one of 200 milliseconds, 250 milliseconds, and 300 milliseconds. The interval threshold value is any one of 5 seconds, 5.5 seconds, and 6 seconds.

[0113] When the speaker obtains the time interval of the video frame based on the slow start algorithm, when the speaker obtains the updated target angle correction parameter each time, if the target angle correction parameter indicates not to adjust the posture of the camera, the time interval can be updated by the following formulas (1) to (3):

[0114] param_ss=param_ss*2,param_ss≤ssthresh / 2 (1)

[0115] param_ss=param_ss+congest_avoid_step,ssthresh / 2<param_ss<ssthresh(2)

[0116] param_ss=init_ss,ssthresh≤param_ss (3)

[0117] Wherein, param_ss is the time interval; init_ss is the initial value of the interval; congest_avoid_step is the interval step length, which can be configured as needed. Exemplarily, the interval step length is 300 milliseconds or 350 milliseconds; ssthresh is the interval threshold value.

[0118] According to the updating process of formulas (1) to (3), when the target angle correction parameter indicates that the camera does not need to adjust its posture (for example, the target left-right rotation angle, the target up-down rotation angle and the target imaging rotation angle are all zero), if the current time interval is not greater than half of the interval threshold value, the current time interval can be multiplied by 2 to obtain a new time interval; if the current time interval is greater than half of the interval threshold value and less than the interval threshold value, the current time interval can be added to the interval step to obtain a new time interval; if the current time interval is not less than the interval threshold value, the current time interval can be restored to the initial value of the interval.

[0119] In this case, if the target user remains basically motionless in front of the camera during the shooting process, the camera does not need to adjust its posture, and the time interval for the speaker to obtain sample photos is gradually increased. After reaching the interval threshold, it starts to update again from the initial interval value. Therefore, when the camera does not need to adjust its posture, the transmission frequency of the video frame can be reduced as much as possible, thereby reducing the probability of network congestion.

[0120] When the speaker obtains the time interval of the video frame based on the slow start algorithm, when the speaker obtains the updated target angle correction parameter each time, if the target angle correction parameter indicates adjusting the posture of the camera, the time interval can be updated by the following formula (4):

[0121] param_ss = init_ss (4)

[0122] Among them, param_ss is the time interval; init_ss is the initial value of the interval.

[0123] Therefore, when the camera needs to adjust its posture, it indicates that the target user has moved. At this time, it is necessary to obtain sample photos more frequently in order to determine new target angle correction parameters for subsequent posture adjustment, thereby facilitating accurate tracking of the target user.

[0124] In one embodiment, during the tracking shooting process, if there is no target user in the video frame, the server can send a specific parameter as a target angle correction parameter to the speaker. The specific parameter indicates that the target user is not in the video frame. The specific form of the specific parameter can be a special character, or a number predetermined to indicate that the target user has left the camera's field of view.

[0125] When the speaker determines that the target angle correction parameter is a specific parameter, it can play a warning message instructing the user to return to the camera, such as: "Please return to the camera", "Please note that you are no longer within the shooting range", etc.

[0126] This measure can be used to promptly warn the target user when he / she leaves the camera, so that the user can return to the camera and continue shooting.

[0127] In one embodiment, after the shooting task is completed, the target user can tell the speaker a second voice command to stop the shooting task. Exemplarily, the second voice command can be "stop video shooting", "end shooting", etc.

[0128] The speaker can respond to the second voice command sent by the target user and send a stop shooting command to the camera, thereby controlling the camera to stop the shooting task. Here, the stop shooting task instructs the camera to stop shooting.

[0129] Through this measure, during the shooting process, the user can conveniently stop video shooting at any time through voice control.

[0130] In several embodiments provided in the present application, the disclosed devices and methods may also be implemented in other ways. The device embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0131] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0132] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

Claims

1. A camera control method, applied to a control system, characterized in that: The control system includes a speaker, a server and a camera, including: The speaker determines the user location information of the target user based on the local microphone array in response to the first voice command issued by the target user; wherein the first voice command instructs to start the camera task; The speaker determines an initial angle correction parameter based on the user position information and the device position information of the camera, and sends the initial angle correction parameter to the camera; The camera adjusts its own posture based on the initial angle correction parameter, takes a number of sample photos after the adjustment, and sends the number of sample photos to the speaker; The speaker sends the sample photos to the server to obtain the target angle correction parameters returned by the server, and sends the target angle correction parameters to the camera; wherein the target angle correction parameters are determined by the server based on the sample photos; The camera adjusts its own posture based on the target angle correction parameter and performs a shooting task after the adjustment.

2. The method according to claim 1, characterized in that The method further comprises: During the camera shooting process, the speaker obtains the currently shot video frame from the camera multiple times, and sends each obtained video frame as a sample photo to the server to obtain the target angle correction parameter updated by the server based on the sample photo; The speaker sends the updated target angle correction parameter to the camera; The camera adjusts its own posture based on the updated target angle correction parameter.

3. The method according to claim 1, characterized in that The speaker is equipped with an RFID reader, and the camera carries an RFID tag; The step of obtaining the device location information comprises: The speaker identifies the RFID tag carried by the camera through the RFID reader to determine the device location information.

4. The method according to claim 1, characterized in that: The initial angle correction parameters include an initial left-right rotation angle, an initial up-down rotation angle, and an initial imaging rotation angle; The speaker determines an initial angle correction parameter based on the user position information and the device position information of the camera, including: The speaker determines an initial left-right rotation angle based on the user position information and the device position information, and sets the initial up-down rotation angle and the initial imaging rotation angle to zero to obtain the initial angle correction parameter.

5. The method according to claim 1, characterized in that The step of taking a number of sample photos after the adjustment includes: The camera takes sample photos respectively at multiple specified elevation angles to obtain multiple sample photos.

6. The method according to claim 1, characterized in that The sample photo carries the corresponding camera posture information; The speaker sends the sample photos to the server to obtain the target angle correction parameters returned by the server, including: The speaker sends the plurality of sample photos to the server; The server determines a target angle correction parameter based on the image position of the target user in each sample photo and the camera posture information corresponding to each sample photo, and sends the parameter to the speaker.

7. The method according to claim 1, characterized in that The camera adjusts its own posture based on the target angle correction parameter, and performs the shooting task after the adjustment: The camera adjusts its own posture based on the target angle correction parameter, and returns adjustment completion information to the speaker; The speaker plays a start recording message and sends a start recording instruction to the camera; The camera executes a shooting task in response to the start shooting instruction.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: The speaker controls the camera to stop the video recording task in response to the second voice instruction sent by the target user; wherein the second voice instruction instructs to stop the video recording task.

9. The method according to claim 2, characterized in that: The method further comprises: During the camera shooting process, the sound box determines the time interval for acquiring video frames based on a slow start algorithm.

10. The method according to claim 9, characterized in that The slow start algorithm sets an interval initial value and an interval threshold value, and the time interval is initially the interval initial value; The speaker determines the time interval for acquiring video frames based on a slow start algorithm, including: When the speaker obtains the updated target angle correction parameter each time, if the target angle correction parameter indicates not to adjust the camera posture, the time interval is updated by the following formula: If param_ss≤ssthresh / 2, param_ss=param_ss*2; If ssthresh / 2<param_ss<ssthresh, param_ss=param_ss+congest_avoid_step; If ssthresh≤param_ss, param_ss=init_ss; If the target angle correction parameter indicates adjusting the camera's posture, the time interval is updated by the following formula: param_ss = init_ss; Among them, the param_ss is the time interval; the init_ss is the interval initial value; the congest_avoid_step is the interval step; and the ssthresh is the interval threshold value.

11. The method according to claim 2, characterized in that The method further includes: if the target user is not in the video frame, the server sends a specific parameter as the target angle correction parameter to the speaker; the specific parameter indicates that the target user is not in the video frame; When the speaker determines that the target angle correction parameter is a specific parameter, the speaker plays a warning message instructing the user to return to the camera.

12. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; The processor is configured to execute the camera control method applied to a speaker, a server or a camera as described in any one of claims 1-11.

13. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program can be executed by a processor to complete the camera control method applied to a speaker or a server or a camera as described in any one of claims 1-11.

14. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the camera control method applied to a speaker, a server or a camera as described in any one of claims 1 to 11 is implemented.

Images