Video shooting method, electronic device, apparatus, system and medium

Abstract

The present disclosure provides a video shooting method, apparatus, device and system, belonging to the technical field of image acquisition. The method includes: when a first device and a second device determine to shoot a video together, establishing a first coordinate axis and sending the first coordinate axis to a server, where the first coordinate axis is used to calibrate the coordinate axes of other devices shooting the video together; sending a first original video collected based on the first coordinate axis to the server, where the first original video is a video of collecting an image of a first object at a target position; receiving a target video shot together sent by the server; where the target video shot together is synthesized based on the first original video, an image of a second object and dynamic information of the second object, the second object is the object being shot in a second original video collected by the second device, and the dynamic information of the second object indicates the change in the pose of the image of the second object over time. Based on the technical solution provided by the embodiments of the present disclosure, the problem that the current video shooting method is not flexible enough can be solved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of video shooting, and particularly relates to a video shooting method, an electronic device, a device, a system and a medium. Background Art

[0002] With the development of image shooting technology, users can use electronic devices to shoot various video images, and users have more and more requirements for video shooting. For example, users expect to shoot videos jointly with friends in different places.

[0003] Currently, if two users are not in the same location, user A is at scenic spot 1. User A first takes an image at this scenic spot, user B takes an image, and then sends it to user A, so that a jointly taken photo of user A and user B can be obtained.

[0004] However, the above processing method can only obtain jointly taken static photos. If user A needs to shoot a video jointly with user B in a different place, professional post-processing is required, and a jointly taken video cannot be obtained in a timely manner. Therefore, the current video shooting method is not flexible enough. Summary of the Invention

[0005] The purpose of the embodiments of the present disclosure is to provide a video shooting method, an electronic device, a device, a system and a medium, which can solve the problem that the current video shooting method is not flexible enough.

[0006] To solve the above technical problems, the present disclosure is implemented as follows:

[0007] In a first aspect, an embodiment of the present disclosure provides a video shooting method, which is applied to a first device. The method includes: when it is determined that the first device and the second device jointly shoot a video, establishing a first coordinate axis and sending the first coordinate axis to a server, where the first coordinate axis is used to calibrate the coordinate axes of other jointly shooting devices; sending a first original video collected based on the first coordinate axis to the server, where the first original video is a video of collecting images of a first object at a target position; receiving and displaying a target jointly shot video sent by the server; where the target jointly shot video is synthesized based on the first original video, images of a second object, and dynamic information of the second object, the second object is the shooting object in a second original video collected by the second device, and the dynamic information of the second object indicates the change in the posture of the images of the second object over time.

[0008] Second aspect, embodiments of the present disclosure provide a video shooting device, which includes: an establishment module, a sending module, a receiving module, and a display module; the establishment module is configured to establish a first coordinate axis when a first device and a second device determine to shoot a video together; the sending module is configured to send the first coordinate axis to a server, and send a first original video collected based on the first coordinate axis to the server, where the first coordinate axis is used to calibrate the coordinate axes of other devices shooting together, and the first original video is a video of capturing an image of a first object at a target position; the receiving module is configured to receive a target co-shot video sent by the server; the display module is configured to display the target co-shot video sent by the server; wherein, the target co-shot video is synthesized based on the first original video, an image of a second object, and dynamic information of the second object, the second object is a shooting object in a second original video captured by the second device, and the dynamic information of the second object indicates the change in the posture of the image of the second object over time.

[0009] In the embodiments of the present disclosure, first, when the initiating device and the joining device determine to shoot together, the initiating device can establish a shooting coordinate axis and then send it to the server, so that the server can calibrate the shooting coordinate axis of the joining device based on the shooting coordinate axis of the initiating device, so as to unify the shooting of each shooting object in the same coordinate axis, and the proportion distortion of each shooting object in the synthesized co-shot video can be avoided. The initiating device sends the collected original video to the server, so that the server synthesizes a target co-shot video based on the first original video, the image of the second object, and the dynamic information of the second object. After the server returns the target co-shot video synthesized based on the content sent by each co-shot device, the synthesized video co-shot effect can be synchronously displayed during the shooting process, so that multi-user remote co-shot video can be realized, that is, multiple users in different spaces can complete the video shooting in one space at the same time, which simplifies the difficulty of remote co-shot video and improves the interestingness and flexibility of video shooting.

[0010] In a third aspect, an embodiment of the present disclosure provides a video shooting method, which is applied to a second device. The method includes: when it is determined to join a video co-shooting initiated by a first device, establishing a second coordinate axis for collecting video images, and sending the second coordinate axis to a server, so that the server calibrates the second coordinate axis according to the first coordinate axis of the first device; collecting a second original video based on the calibrated coordinate axis sent by the server; segmenting the image of a second object in the second original video, and obtaining dynamic information of the second object in the second original video, where the dynamic information of the second object indicates the change in the pose of the image of the second object over time; sending the segmented image of the second object and the dynamic information of the second object to the server; receiving and displaying the target co-shooting video sent by the server; where the target co-shooting video is synthesized based on a first original video, the image of the second object, and the dynamic information of the second object; and the first original video is a video in which the first device collects the image of a first object at a target position.

[0011] In a fourth aspect, an embodiment of the present disclosure provides a video shooting device. The device includes: a establishing module, a sending module, a collecting module, a segmenting module, an obtaining module, a receiving module, and a displaying module; the establishing module is configured to establish a second coordinate axis for collecting video images when it is determined to join a video co-shooting initiated by a first device; the sending module is configured to send the second coordinate axis to a server so that the server calibrates the second coordinate axis according to the first coordinate axis of the first device; the collecting module is configured to collect a second original video based on the calibrated coordinate axis sent by the server; the segmenting module is configured to segment the image of a second object in the second original video; the obtaining module is configured to obtain dynamic information of the second object in the second original video, where the dynamic information of the second object indicates the change in the pose of the image of the second object over time; the sending module is configured to send the segmented image of the second object and the dynamic information of the second object to the server; the receiving module is configured to receive the target co-shooting video sent by the server; the displaying module is configured to display the target co-shooting video sent by the server; where the target co-shooting video is synthesized based on a first original video, the image of the second object, and the dynamic information of the second object; and the first original video is a video in which the first device collects the image of a first object at a target position.

[0012] In an embodiment of the present disclosure, after the joining device determines to join the video co - shooting, the joining device can establish the shooting coordinate axes and transmit the shooting coordinate axes to the server, so that the server can proofread based on the coordinate axes of the initiating device and collect the video using the coordinate axes proofread by the server. During the shooting process, the joining device can segment the shooting object in the video while collecting, obtain the dynamic information of the shooting object, and transmit the segmented shooting object and the dynamic information of the shooting object to the server in real time, so that the server can combine the content transmitted by the joining device to synthesize the co - shooting video; after receiving the synthesized co - shooting video sent by the server, the joining device can display the synthesized co - shooting video, thereby realizing multi - user remote co - shooting of videos, that is, enabling multiple users in different spaces to complete the video shooting in one space at the same time, simplifying the difficulty of remote co - shooting of videos and enhancing the interest and flexibility of video shooting.

[0013] In a fifth aspect, an embodiment of the present disclosure provides a video shooting method applied to a server. The method includes: when a first device and a second device determine to co - shoot a video, receiving a first coordinate axis sent by the first device and a second coordinate axis sent by the second device; based on the first coordinate axis, proofreading the second coordinate axis and sending the proofread coordinate axis to the second device, so that the second device can collect video images based on the proofread coordinate axis; receiving a first original video sent by the first device, an image of a second object sent by the second device, and the dynamic information of the second object, where the first original video is a video of collecting an image of a first object at a target position; synthesizing a target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object; and sending the target co - shooting video to the first device and the second device.

[0014] Sixth aspect, an embodiment of the present disclosure provides a video shooting device, which includes: a receiving module, a calibration module, a sending module, and a synthesizing module; the receiving module is configured to receive a first coordinate axis sent by the first device and a second coordinate axis sent by the second device when the first device and the second device determine to shoot a collaborative video; the calibration module is configured to calibrate the second coordinate axis based on the first coordinate axis; the sending module is configured to send the calibrated coordinate axis to the second device so that the second device can collect video images based on the calibrated coordinate axis; the receiving module is configured to receive a first original video sent by the first device, an image of a second object sent by the second device, and dynamic information of the second object, where the first original video is a video of collecting an image of a first object at a target position; the synthesizing module is configured to synthesize a target collaborative video based on the first original video, the image of the second object, and the dynamic information of the second object; the sending module is configured to send the target collaborative video to the first device and the second device.

[0015] In an embodiment of the present disclosure, when each device determines to participate in a remote video collaboration, after the server receives the coordinate axes sent by each device, it can calibrate the coordinate axes of other participating devices based on the coordinate axis of the initiating device and transmit the calibrated coordinate axes to the participating devices; then, the server can synthesize the collaborative video based on the original videos, the segmented shooting objects, and the dynamic information of the segmented shooting objects received from each collaborative device and synchronize it to each collaborative device, so as to realize multi-user remote collaborative video shooting, that is, it can enable multiple users in different spaces to complete video shooting in one space at the same time, simplify the difficulty of remote collaborative video shooting, and improve the interest and flexibility of video shooting.

[0016] Seventh aspect, an embodiment of the present disclosure provides an electronic device, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps of the video shooting method as described in the first aspect or the second aspect.

[0017] Eighth aspect, an embodiment of the present disclosure provides a server, which includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor. When the program or instruction is executed by the processor, it implements the steps of the video shooting method as described in the third aspect.

[0018] In a ninth aspect, an embodiment of the present disclosure provides a shooting system, including a first device, a second device, and a server. The first device is configured to perform the steps of the video shooting method described in the first aspect, the second device is configured to perform the steps of the video shooting method described in the second aspect, and the server is configured to perform the steps of the video shooting method described in the third aspect.

[0019] In a tenth aspect, an embodiment of the present disclosure provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the video shooting method described in the first aspect, the second aspect, or the third aspect are implemented.

[0020] In an eleventh aspect, an embodiment of the present disclosure provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the video shooting method described in the first aspect, the second aspect, or the third aspect.

[0021] In a twelfth aspect, an embodiment of the present disclosure provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the steps of the video shooting method described in the first aspect, the second aspect, or the third aspect. Description of the Drawings

[0022] Figure 1 It is a schematic diagram of a video shooting scenario provided by an embodiment of the present disclosure;

[0023] Figure 2 It is one of the flowcharts of the video shooting method provided by an embodiment of the present disclosure;

[0024] Figure 3 It is another flowchart of the video shooting method provided by an embodiment of the present disclosure;

[0025] Figure 4 It is yet another flowchart of the video shooting method provided by an embodiment of the present disclosure;

[0026] Figure 5 It is still another flowchart of the video shooting method provided by an embodiment of the present disclosure;

[0027] Figure 6 It is one of the possible structural diagrams of the video shooting device provided by an embodiment of the present disclosure;

[0028] Figure 7 It is another possible structural diagram of the video shooting device provided by an embodiment of the present disclosure;

[0029] Figure 8 It is yet another possible structural diagram of the video shooting device provided by an embodiment of the present disclosure

[0030] Figure 9 A possible structural schematic diagram of an electronic device provided by an embodiment of the present disclosure;

[0031] Figure 10 A possible structural schematic diagram of a server device provided by an embodiment of the present disclosure;

[0032] Figure 11 A hardware schematic diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0033] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some, but not all, of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

[0034] The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such used data may be interchanged under appropriate circumstances so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same category, and the number of objects is not limited. For example, the first object may be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means an "or" relationship between the associated objects before and after.

[0035] Next, the video shooting method provided by the embodiments of the present disclosure will be described in detail in conjunction with the accompanying drawings, through specific embodiments and their application scenarios.

[0036] Figure 1 A schematic diagram of a video shooting scenario provided by an embodiment of the present disclosure, as Figure 1 shown in, includes device 100, device 101 and server 102; wherein, device 100 initiates a video co - shooting to device 101. Device 100 performs video co - shooting with device 101 through the server. Server 102 is a server of a cloud platform providing video co - shooting services.

[0037] Among them, the above - mentioned device can be an electronic device such as a mobile phone, a camera, a drone, etc. The co - shooting devices can be electronic devices with different geographical locations or electronic devices with the same geographical location, and the present disclosure does not make specific limitations in this regard.

[0038] For ease of understanding, in the embodiments of the present disclosure, an example is given where the first device is the initiating device for video co - shooting, and the second device is the device that joins the video co - shooting initiated by the first device. In actual applications, the devices that join the video co - shooting initiated by the first device may include at least one device, and the embodiments of the present disclosure do not make specific limitations in this regard.

[0039] Figure 2 It is a schematic flowchart of a video shooting method provided by the embodiments of the present disclosure. This method is applied to an electronic device that initiates video co - shooting. Taking the first device as an example, as Figure 2 shown, this method may include the following S201 to S203:

[0040] S201. When the first device and the second device determine video co - shooting, the first device establishes a first coordinate axis and sends the first coordinate axis to the server.

[0041] Among them, the first coordinate axis is used to calibrate the coordinate axes of other co - shooting devices.

[0042] Exemplarily, in the embodiments of the present disclosure, the coordinate axes of each device in the co - shot video are respectively three - dimensional space coordinate axes of the horizontal (x), vertical (y), and depth (z) axes established by each device based on plane detection technology.

[0043] Specifically, each device independently selects point cloud data for establishing the coordinate axis. Point cloud data refers to a set of vectors in a three - dimensional coordinate system.

[0044] It can be understood that using the first coordinate axis to calibrate the coordinate axes of other co - shooting devices can make the coordinate axis information of other co - shooting devices correspond to the coordinate axis information of the device that initiates co - shooting. Each co - shooting device can collect videos based on the coordinate axes calibrated by the first device. Each co - shooting device uses the corresponding coordinate axis information for image acquisition, which can facilitate accurately determining the positional relationship of each co - shooting object and make the synthesis effect between the shooting objects in the co - shot video more realistic.

[0045] S202. The first device sends the first original video collected based on the first coordinate axis to the server.

[0046] Among them, the first original video is a video of the first device collecting images of the first object at the target position.

[0047] Exemplarily, during the process of co - shooting the video, the first device can collect the original video while sending the original video collected by the first device to the server in real time. The original video includes video information such as the shooting object, sound, and background environment captured by the first device.

[0048] S203. The first device receives and displays the target collaborative video sent by the server.

[0049] The target collaborative video is synthesized based on the first original video, the image of the second object, and the dynamic information of the second object. The second object is the shooting object in the second original video collected by the second device, and the dynamic information of the second object indicates the change in the posture of the image of the second object over time.

[0050] Specifically, the first device can receive and display in real time the collaborative video sent by the server in real time.

[0051] It can be understood that the second original video is the original video shot by the second device based on the coordinate axis calibrated according to the first coordinate axis.

[0052] Exemplarily, the first user (the user corresponding to the first device) expects to shoot a video at the target location. The first user can invite the second user (the user corresponding to the second device) to shoot a collaborative video.

[0053] The second user can be at the target location or not. The embodiments of the present disclosure do not make specific limitations on this.

[0054] It can be understood that after the second user determines to shoot a collaborative video with the first user, the first device can establish a three-dimensional coordinate axis and send the three-dimensional coordinate axis of the first device to the server, so that the server can use the three-dimensional coordinate axis of the first device to calibrate the three-dimensional coordinate axes of other devices participating in the collaboration.

[0055] For the video shooting method provided by the embodiments of the present disclosure, first, when the initiating device and the joining device determine to collaborate, the initiating device can establish a shooting coordinate axis and then send it to the server, so that the server can calibrate the shooting coordinate axes of the joining devices based on the shooting coordinate axis of the initiating device, so as to unify the shooting of each shooting object in the same coordinate axis, and the proportion distortion of each shooting object in the synthesized collaborative video can be avoided. The initiating device sends the collected original video to the server, so that the server synthesizes the target collaborative video based on the first original video, the image of the second object, and the dynamic information of the second object. After the server returns the target collaborative video synthesized based on the content sent by each collaborative device, the synthesized video collaboration effect can be synchronously displayed during the shooting process, so that multi-user off-site collaborative video can be realized, that is, multiple users in different spaces can complete the video shooting in one space at the same time, simplifying the difficulty of off-site collaborative video and enhancing the fun and flexibility of video shooting.

[0056] Optionally, Figure 3Schematic flowchart of a video shooting method provided by an embodiment of the present disclosure. This method is applied to an electronic device participating in a video collaboration. Taking the second device as an example for illustration, as Figure 3 shown in

[0057] S301, when it is determined to join the video collaboration initiated by the first device, the second device establishes a second coordinate axis for collecting video images and sends the second coordinate axis to the server, so that the server calibrates the second coordinate axis according to the first coordinate axis of the first device.

[0058] S302, the second device collects a second original video based on the calibrated coordinate axis sent by the server.

[0059] S303, the second device segments the image of the second object in the second original video and obtains the dynamic information of the second object in the second original video.

[0060] Among them, the dynamic information of the second object indicates the change situation of the posture of the image of the second object over time.

[0061] Exemplarily, the second object can be a person or other objects that can make actions, such as animals, dolls played by people, etc.

[0062] Exemplarily, when the second object is a person, the second device performs human body parsing on the person in the video frame, and based on the high-resolution background matting technology, extracts the second object in the video frame; and, the second device based on human body pose key point detection (pose estimation) to real-time track the limb positions of the second object, so as to obtain the real-time dynamic information of the second object.

[0063] It can be understood that the second device can collect videos in real time and perform the above-mentioned processing on video frames in real time.

[0064] S304, the second device sends the segmented image of the second object and the dynamic information of the second object to the server.

[0065] S305, the second device receives and displays the target collaborative video sent by the server.

[0066] Among them, the target collaborative video is synthesized based on the first original video, the image of the second object and the dynamic information of the second object; the first original video is the video of the first device collecting the image of the first object at the target position.

[0067] Based on this solution, after the joining device determines to join the video co - shooting, the joining device can establish the shooting coordinate axes and transmit the shooting coordinate axes to the server, so that the server can proofread based on the coordinate axes of the initiating device and collect the video using the coordinate axes proofread by the server. During the shooting process, the joining device can segment the shooting object in the video while collecting, obtain the dynamic information of the shooting object, and transmit the segmented shooting object and the dynamic information of the shooting object to the server in real - time, so that the server can combine the content transmitted by the joining device to synthesize the co - shooting video; after receiving the synthesized co - shooting video sent by the server, the joining device can display the synthesized co - shooting video, thereby enabling multi - user remote co - shooting of videos, that is, allowing users in multiple different spaces to complete the video shooting in one space at the same time, simplifying the difficulty of remote co - shooting of videos and enhancing the interestingness and flexibility of video shooting.

[0068] Optionally, in the embodiments of the present disclosure, the second device may also transmit the second original video collected by the second device to the server, and the server performs the above - mentioned segmentation processing and acquisition of dynamic information on the second original video.

[0069] Optionally, Figure 4 is a schematic flowchart of a video shooting method provided by an embodiment of the present disclosure. This method is applied to the server of a cloud platform that provides video co - shooting services. As Figure 4 shown in, this method may include the following S401 to S405:

[0070] S401. When the first device and the second device determine the co - shooting video, the server receives the first coordinate axes sent by the first device and the second coordinate axes sent by the second device.

[0071] S402. The server proofreads the second coordinate axes based on the first coordinate axes and sends the proofread coordinate axes to the second device, so that the second device can collect video images based on the proofread coordinate axes.

[0072] S403. The server receives the first original video sent by the first device, the image of the second object and the dynamic information of the second object sent by the second device.

[0073] Among them, the first original video is the video of the first device collecting the image of the first object at the target position.

[0074] S404. The server synthesizes the target co - shooting video based on the first original video, the image of the second object and the dynamic information of the second object.

[0075] S405. The server sends the target co - shooting video to the first device and the second device.

[0076] It can be understood that after the server synthesizes the target co-shot video based on the content transmitted in real time by the first device and the second device, the server can synchronize the synthesized target co-shot video to the first device and the second device. Then, the audio in the first original video, the background in the first original video, the first object, and the second object can be synchronously output in the first device and the second device.

[0077] Based on this solution, when each device determines to join the off-site video co-shot, after the server receives the coordinate axes sent by each device, the server can calibrate the coordinate axes of other joining devices based on the coordinate axes of the initiating device, and transmit the calibrated coordinate axes to the joining devices; then, the server can synthesize the co-shot video based on the original videos, the segmented shooting objects, and the dynamic information of the segmented shooting objects transmitted by each co-shot device, and synchronize it to each co-shot device, thereby enabling multi-user off-site co-shot videos, that is, allowing multiple users in different spaces to complete the video shooting in one space at the same time, simplifying the difficulty of off-site co-shot videos, and enhancing the interest and flexibility of video shooting.

[0078] For ease of understanding, the following takes the data interaction process among the first device, the second device, and the server in shooting a co-shot video as an example to illustrate the video shooting method provided by the embodiments of the present disclosure.

[0079] Figure 5 The interaction flow diagram of the video shooting method provided by the embodiments of the present disclosure is shown in Figure 5 as shown, and may include the following S501 to S513:

[0080] S501. When the first device and the second device determine to co-shot a video, the first device establishes a first coordinate axis and sends the first coordinate axis to the server.

[0081] Among them, the first coordinate axis is used to calibrate the coordinate axes of other co-shot videos.

[0082] S502. When the second device determines to join the video co-shot initiated by the first device, the second device establishes a second coordinate axis for collecting video images and sends the second coordinate axis to the server, so that the server calibrates the second coordinate axis according to the first coordinate axis of the first device.

[0083] Exemplarily, the first device and the second device can establish horizontal (x), vertical (y), and depth (z) through plane detection.

[0084] S503. When the first device and the second device determine to co-shot a video, the server receives the first coordinate axis sent by the first device and the second coordinate axis sent by the second device.

[0085] S504: The server calibrates the second coordinate axis based on the first coordinate axis, and sends the calibrated coordinate axis to the second device, so that the second device captures a video image based on the calibrated coordinate axis.

[0086] Exemplarily, the server uses the coordinate axis of the first device as a reference coordinate axis and adjusts the scale of the coordinate axis of the second device to achieve correspondence with the coordinate axis information of the first device.

[0087] S505: The first device sends a first original video captured based on a first coordinate axis to a server.

[0088] The first original video is a video capturing an image of a first object at a target location.

[0089] S506: The second device captures a second original video based on the calibrated coordinate axis sent by the server.

[0090] S507: The second device segments the image of the second object in the second original video, and obtains dynamic information of the second object in the second original video.

[0091] The dynamic information of the second object indicates changes in the posture of the image of the second object over time.

[0092] S508: The second device sends the segmented image of the second object and dynamic information of the second object to the server.

[0093] S509: The server receives the first original video sent by the first device, the image of the second object sent by the second device, and the dynamic information of the second object.

[0094] S510: The server synthesizes a target combined video based on the first original video, the image of the second object, and the dynamic information of the second object.

[0095] S511. The server sends a target co-shot video to the first device and the second device.

[0096] S512: The first device receives and displays the target synchronized video sent by the server.

[0097] S513: The second device receives and displays the target synchronized video sent by the server.

[0098] It can be understood that during the shooting process, the first device and the second device can synchronously display the synthesized combined video, thereby improving the user's combined video shooting experience.

[0099] Based on this solution, when each device determines a co-shot video, each co-shot device can respectively establish coordinate axes in a three-dimensional space, and each co-shot device sends the established coordinate axes to the server. The server calibrates the coordinate axes of the joining devices based on the coordinate axes of the initiating device and returns them to each joining device, so that each co-shot device can perform video shooting with unified coordinate axes. The initiating device transmits the captured original video to the server, and the joining devices transmit the images of the shooting objects and the dynamic information of the shooting objects to the server. The server synthesizes the target co-shot video based on the content transmitted by each co-shot device and synchronizes it to each co-shot device. Each co-shot device synchronously displays the synthesized co-shot video, thereby enabling multi-user remote co-shot video, that is, allowing multiple users in different spaces to complete video shooting in one space at the same time, simplifying the difficulty of remote co-shot video and enhancing the fun and flexibility of video shooting.

[0100] Optionally, in the video shooting method provided by the embodiments of the present disclosure, before S501 described above, S514 below may further be included. Furthermore, before S502 described above, S515 and S516 below may further be included:

[0101] S514. When the first device logs in to the target shared account and receives a video co-shot input, the first device sends a video co-shot request message to the second device.

[0102] Wherein, the video co-shot request message includes a login entry for the target shared account.

[0103] Exemplarily, the login entry for the target shared account can be in the form of a QR code or in the form of a link. The embodiments of the present disclosure do not make specific limitations thereto.

[0104] Exemplarily, the video co-shot input received by the first device can be an input by the user in the shooting preview interface of the first device, where a virtual control for initiating video co-shot can be displayed in the shooting preview interface.

[0105] It can be understood that the video co-shot input may include an input for selecting an invited co-shot user.

[0106] S515. The second device receives the video co-shot request message sent by the first device.

[0107] S516. The second device logs in to the target shared account based on the video co-shot request message to join the video co-shot initiated by the first device.

[0108] Wherein, if the second device logs in to the target shared account, it indicates that the second device joins the video co-shot initiated by the first device.

[0109] For example, the second device can recognize the QR code sent by the first device, or can jump to the login interface of the target shared account through the user's input of the link. The second user can log in to the target shared account, thereby joining the video shooting initiated by the first device.

[0110] Exemplarily, the first device can log in to the account of the first user's cloud shooting platform. When the first user determines to invite the second user to shoot a video together, the first device generates a link or a QR code including the login entry of the target shared account and sends the link or the QR code to the second device.

[0111] It can be understood that after the second device logs in to the target shared account, the first user and the second user enter the cloud shared ID mode, and the server in the cloud can perform synthesis processing on the video content shot by the first device and the second device.

[0112] Based on this solution, when the first device logs in to the target shared account and receives a video co-shooting input, the first device sends a video co-shooting request message to the second device to invite the second device to join the video co-shooting initiated by the first device. After the second device determines to log in to the target shared account, it means that the second device has joined the video co-shooting initiated by the first device, so that the server can conveniently determine which devices the video is synthesized based on the content transmitted by those devices according to the devices in the target shared account.

[0113] Optionally, in the embodiments of the present disclosure, the video co-shooting request message may further include at least one of location information and shooting scene information. Among them, the location information indicates the geographical location where the first device initiates the video co-shooting, and the shooting scene information indicates the shooting background where the first device initiates the video co-shooting.

[0114] Exemplarily, when the user of the first device initiates a video co-shooting, the user can select to send at least one of the location information and the shooting scene information to the devices of other users to be co-shot.

[0115] It can be understood that after the second device receives the video co-shooting request message, the second device can display the co-shooting information of the first device. If the video co-shooting request message includes location information, the second device can prompt the user of the second device about the geographical location where the co-shooting will take place. If the video co-shooting request message includes shooting scene information, the second device can display the shooting background where the first device initiates the video co-shooting. Thus, the user of the second device can determine whether to join the video co-shooting based on the displayed co-shooting information.

[0116] Based on this solution, when the video co-shooting request message sent by the first device includes at least one of location information and shooting information, it can prompt the users of other co-shooting devices to be joined about the geographical location and shooting scene where the co-shooting will take place, so that the video co-shooting is more flexible.

[0117] Optionally, in the video shooting method provided by the embodiments of the present disclosure, the above S510 may be specifically executed through the following S51a to S51c:

[0118] S51a. The server obtains the first depth information of the joint points of the first object in the first original video based on the first coordinate axis, and obtains the second depth information of the joint points of the second object.

[0119] S51b. The server determines the front-back position relationship between the first object and the second object according to the first depth information and the second depth information.

[0120] S51c. The server synthesizes the image of the second object and the first original video information based on the position relationship between the first object and the second object and the dynamic information of the second object to obtain the target co-shot video.

[0121] Exemplarily, when determining the position relationship of the co-shot objects, the server first obtains the joint points of each shooting object based on the human pose key point detection; then, based on the first coordinate axis, projects the joint points of each object vertically onto the z-axis (the axis in the depth direction); finally, determines the front-back relationship through the coordinate values of the joint points of each object on the z-axis.

[0122] It should be noted that in the embodiments of the present disclosure, when the server synthesizes the co-shot video, it can adjust the left-right relationship of the shooting objects to make the fused co-shot video more natural and vivid.

[0123] Based on this solution, the server can obtain the depth information of each object based on the unified coordinate axis of the co-shot initiating device to determine the front-back position relationship of each object, and synthesize the co-shot video based on the determined front-back position relationship, which can make the video of remote co-shot closer to the real co-shot effect.

[0124] Optionally, in the video shooting method provided by the embodiments of the present disclosure, the above S510 may specifically include the following S51d:

[0125] S51d. If it is detected that the actions of the first object and the second object satisfy the preset interaction actions, the server fuses the interaction actions of the first object and the second object according to the preprocessing corresponding to the preset interaction actions.

[0126] It can be understood that the server can pre-store the action behaviors during video shooting interaction and the fusion methods corresponding to the preset interaction actions.

[0127] Exemplarily, the preset interaction actions may include actions such as putting one's arm around someone's shoulder, hugging, holding hands, and preset figures gestured. The preset figure may be a figure formed by the combined actions of two people in the shape of a heart.

[0128] Based on this solution, when the server synthesizes a co-shot video, the server determines whether the actions of the first object and the second object conform to the preset interactive actions. If so, when synthesizing the video, the preset action processing corresponding to the preset interactive action can be performed on the contacted part, which can make the interaction between the first object and the second object in the synthesized video more natural and the fusion of the contact positions more realistic.

[0129] Optionally, in the video shooting method provided by the embodiments of the present disclosure, after S512 described above, the following S517 to S519 may further be included:

[0130] S517. When the shooting is completed, the first device sends an indication message indicating that the video co-shot is completed to the server.

[0131] Among them, the indication message indicating that the video co-shot is completed may include at least one of a video public state, an account public state, and location information; the video public state indicates whether the target co-shot video is publicly released, the account public state indicates whether other accounts can view the co-shot video released by the target shared account, and the location information indicates the shooting location of the target co-shot video.

[0132] S518. The server receives the indication message indicating that the video co-shot is completed sent by the first device.

[0133] S519. When the indication message indicates that the video public state is publicly released, the server releases the target co-shot video.

[0134] It should be noted that after the video co-shot is completed, each device participating in the co-shot can save the co-shot video locally.

[0135] Optionally, the second device may also send an indication message indicating that the video shooting is completed to the server based on the user's operation.

[0136] It can be understood that the account in the indication message indicating that the video co-shot is completed sent by the first device is the account of the first user logged in to the first device, and the account in the indication message indicating that the video co-shot is completed sent by the second device is the account of the second user logged in to the second device. That is, both the first user and the second user can choose whether to publicly release the target co-shot video.

[0137] Based on this solution, after the collaborative video shooting is completed, the devices participating in the collaboration can send video collaboration completion indication information to the server to indicate whether the server publicly releases the target collaborative video, indicate the public status of the collaborative videos of the accounts of each device, and indicate the collaboration location of the target collaborative video. When it is indicated in the indication information that the public status of the target collaborative video is publicly released, the server can publicly release the target collaborative video, enabling users of other accounts to view the target collaborative video. The server recommends and displays the target collaborative video for devices with the same location information, improving the flexibility of video release, increasing the probability that the released collaborative video is viewed by other users, and enhancing the usage experience of the releasing users.

[0138] Optionally, in the video shooting method provided by this embodiment of the present disclosure, before the above S501, the following S520 to S526 may further be included:

[0139] S520. The first device obtains the target information of the first device.

[0140] Wherein, the target information includes at least one of the location information of the first device and the preview image displayed on the shooting interface of the first device.

[0141] S521. The first device sends the target information to the server.

[0142] S522. The server receives the target information sent by the first device.

[0143] S523. The server obtains the collaborative video that matches the target information from the publicly released collaborative videos.

[0144] S524. The server sends the collaborative video that matches the target information from the publicly released collaborative videos to the first device.

[0145] S525. The first device receives the collaborative video that matches the target information from the publicly released collaborative videos sent by the server.

[0146] S526. The first device recommends and displays the collaborative video that matches the target information from the publicly released collaborative videos.

[0147] Based on this solution, before a user of the first device initiates a video duet, the first device can, according to the target information of the first device, obtain a duet video that matches the target information from publicly available duet videos and recommend it to the user for browsing. For example, the first device can recommend and display a duet video that matches the current location information of the first device, or recommend and display a duet video that matches the preview image in the shooting preview interface of the first device, or recommend and display a duet video that matches both the location information and the preview image of the first device. This enables the shooting user to quickly understand the duet videos previously shot by other users at the current location, provides a duet reference close to the current shooting scene, and enhances the user's video shooting experience and video browsing experience.

[0148] It should be noted that for the video shooting method provided in this embodiment of the present disclosure, the execution subject may be a video shooting device, or a control module in the video shooting device for executing the video shooting method. In this embodiment of the present disclosure, the example of the video shooting device executing the video shooting method is used to illustrate the video shooting device provided in this embodiment of the present disclosure.

[0149] Figure 6 FIG. is a possible structural schematic diagram of a video shooting device provided in an embodiment of the present disclosure. As Figure 6 shown in the figure, the video shooting device 600 includes: a establishing module 601, a sending module 602, a receiving module 603, and a display module 604; the establishing module 601 is configured to establish a first coordinate axis when the first device and the second device determine a video duet; the sending module 602 is configured to send the first coordinate axis to the server and send a first original video collected based on the first coordinate axis to the server, where the first coordinate axis is used to calibrate the coordinate axes of other duet devices, and the first original video is a video of collecting an image of a first object at a target location; the receiving module 603 is configured to receive a target duet video sent by the server; the display module 604 is configured to display the target duet video sent by the server; wherein, the target duet video is synthesized based on the first original video, an image of a second object, and dynamic information of the second object, the second object is a shooting object in a second original video collected by the second device, and the dynamic information of the second object indicates the change in the posture of the image of the second object over time.

[0150] Optionally, the sending module is further configured to, before sending the first coordinate axis to the server, send a video duet request message to the second device when logging in to a target shared account and receiving a video duet input; wherein, the video duet request message includes a login entry for the target shared account; if the second device logs in to the target shared account, it indicates that the second device joins the video duet initiated by the first device.

[0151] Optionally, the video co - shooting request message further includes at least one of location information and shooting scene information; wherein, the location information indicates the geographical location where the first device initiates video co - shooting, and the shooting scene information indicates the shooting background where the first device initiates video co - shooting.

[0152] Optionally, the sending module is further configured to, after the receiving module receives the target co - shooting video sent by the server, and when shooting is completed, send indication information of the completion of video co - shooting to the server; the indication information includes at least one of a video public status, an account public status, and location information; wherein, the video public status indicates whether the target co - shooting video is publicly released, the account public status indicates whether other accounts can view the co - shooting videos released by the target sharing account, and the location information indicates the shooting location of the target co - shooting video.

[0153] Optionally, the video shooting device further includes an acquisition module; the acquisition module is configured to, before sending the video co - shooting request message to the second device, acquire target information of the first device, the target information includes at least one of location information and a preview image of the shooting interface; the display module is further configured to recommend and display co - shooting videos that match the target information among publicly available co - shooting videos.

[0154] The embodiments of the present disclosure provide a video shooting device. First, when the video shooting device and the joining device determine co - shooting, the video shooting device can establish a shooting coordinate axis and then send it to the server, so that the server can calibrate the shooting coordinate axis of the joining device based on the shooting coordinate axis of the video shooting device, so as to enable each shooting object to shoot in the same coordinate axis, and the proportion distortion of each shooting object in the synthesized co - shooting video can be avoided. The video shooting device sends the collected original video to the server, so that the server synthesizes a target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object. After the server returns the target co - shooting video synthesized based on the content sent by each co - shooting device, the synthesized video co - shooting effect can be synchronously displayed during the shooting process, so that multi - user remote co - shooting of videos can be realized, that is, multiple users in different spaces can complete the video shooting in one space at the same time, simplifying the difficulty of remote co - shooting of videos and enhancing the interest and flexibility of video shooting.

[0155] Figure 7 A possible structural schematic diagram of a video shooting device provided by the embodiments of the present disclosure is as Figure 7As shown in the figure, the video shooting device 700 includes: a establishing module 701, a sending module 702, a collecting module 703, a splitting module 704, an obtaining module 705, a receiving module 706, and a displaying module 707; the establishing module 701 is configured to establish a second coordinate axis for collecting video images when it is determined to join the video co-shooting initiated by the first device; the sending module 702 is configured to send the second coordinate axis to the server so that the server proofreads the second coordinate axis according to the first coordinate axis of the first device; the collecting module 703 is configured to collect a second original video based on the proofread coordinate axis sent by the server; the splitting module 704 is configured to split the image of the second object in the second original video; the obtaining module 705 is configured to obtain the dynamic information of the second object in the second original video, and the dynamic information of the second object indicates the change in the posture of the image of the second object over time; the sending module 702 is configured to send the split image of the second object and the dynamic information of the second object to the server; the receiving module 706 is configured to receive the target co-shot video sent by the server; the displaying module 707 is configured to display the target co-shot video sent by the server; wherein, the target co-shot video is synthesized based on the first original video, the image of the second object, and the dynamic information of the second object; the first original video is a video of the first device collecting the image of the first object at the target location.

[0156] Optionally, the video shooting device further includes: a logging-in module; the receiving module is further configured to receive the video co-shooting request message sent by the first device before the sending module sends the second coordinate axis to the server, and the video co-shooting request message includes the login entry of the target shared account; the logging-in module is configured to log in to the target shared account based on the video co-shooting request message to join the video co-shooting initiated by the first device.

[0157] An embodiment of the present disclosure provides a video shooting device. After the video shooting device determines to join a video collaboration shooting, the video shooting device can establish a shooting coordinate axis and transmit the shooting coordinate axis to the server, so that the server can perform calibration based on the coordinate axis of the initiating device and collect the video using the coordinate axis calibrated by the server. During the shooting process, the video shooting device can segment the shooting object in the video while collecting, obtain the dynamic information of the shooting object, and transmit the segmented shooting object and the dynamic information of the shooting object to the server in real time, so that the server can synthesize the collaborative shooting video by combining the content transmitted by the video shooting device; after receiving the synthesized collaborative shooting video sent by the server, the video shooting device can display the synthesized collaborative shooting video, thereby realizing multi-user remote collaborative shooting of videos, that is, enabling multiple users in different spaces to complete the video shooting in one space at the same time, simplifying the difficulty of remote collaborative shooting of videos and enhancing the interestingness and flexibility of video shooting.

[0158] Figure 8 FIG. is a possible structural schematic diagram of a video shooting device provided by an embodiment of the present disclosure, as Figure 8 shown in FIG., the video shooting device 800 includes: a receiving module 801, a calibration module 802, a sending module 803, and a synthesizing module 804; the receiving module 801 is configured to receive a first coordinate axis sent by the first device and a second coordinate axis sent by the second device when the first device and the second device determine to shoot a collaborative video; the calibration module 802 is configured to calibrate the second coordinate axis based on the first coordinate axis; the sending module 803 is configured to send the calibrated coordinate axis to the second device so that the second device can collect video images based on the calibrated coordinate axis; the receiving module 801 is configured to receive a first original video sent by the first device, an image of a second object sent by the second device, and the dynamic information of the second object, where the first original video is a video of collecting an image of a first object at a target position; the synthesizing module 804 is configured to synthesize a target collaborative shooting video based on the first original video, the image of the second object, and the dynamic information of the second object; the sending module 803 is configured to send the target collaborative shooting video to the first device and the second device.

[0159] Optionally, the synthesizing module is specifically configured to: obtain first depth information of the joints of the first object in the first original video based on the first coordinate axis, and obtain second depth information of the joints of the second object; determine the front-back position relationship between the first object and the second object according to the first depth information and the second depth information; synthesize the image of the second object and the first original video information based on the position relationship between the first object and the second object and the dynamic information of the second object to obtain the target collaborative shooting video.

[0160] Optionally, the synthesis module is specifically configured to: if it is detected that the actions of the first object and the second object satisfy a preset interaction action, fuse the interaction actions of the first object and the second object according to the preprocessing corresponding to the preset interaction action.

[0161] Optionally, the video shooting device further includes: a publishing module; a receiving module, further configured to, after the sending module sends the target co-shot video to the first device and the second device, receive indication information indicating that the video co-shooting is completed sent by the first device, where the indication information indicates at least one of a video public state, an account public state, and location information; a publishing module, configured to publish the target co-shot video when the indication information indicates that the video public state is publicly released; where the video public state indicates whether the target co-shot video is publicly released, the account public state indicates whether other accounts can view the co-shot video published by the target shared account, and the location information indicates the shooting location of the target co-shot video.

[0162] Optionally, the receiving module is further configured to receive target information sent by the first device, where the target information includes at least one of the location information of the first device and a preview image displayed on the shooting interface of the first device; an obtaining module, further configured to obtain a co-shot video that matches the target information in the publicly released co-shot videos according to the target information.

[0163] The embodiment of the present disclosure provides a video shooting device. When each device determines to join an off-site video co-shooting, after the video shooting device receives the coordinate axes sent by each device, it can calibrate the coordinate axes of other joining devices based on the coordinate axes of the initiating device, and transmit the calibrated coordinate axes to the joining devices; thereafter, the video shooting device can synthesize a co-shot video based on the original videos, the segmented shooting objects, and the dynamic information of the segmented shooting objects transmitted by each co-shooting device, and synchronize it to each co-shooting device, so that multi-user off-site co-shot videos can be realized, that is, multiple users in different spaces can complete the video shooting in one space at the same time, simplifying the difficulty of off-site co-shot videos and enhancing the interest and flexibility of video shooting.

[0164] The video shooting device in the embodiments of the present disclosure can be a device, or a component, an integrated circuit, or a chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a wearable device, a UMPC (ultra-mobile personal computer), a netbook, or a PDA (personal digital assistant), etc., and the non-mobile electronic device can be a server, a NAS (Network Attached Storage), a PC (personal computer), a TV (television), a teller machine, or a self-service machine, etc. The embodiments of the present disclosure do not make specific limitations.

[0165] The video shooting device in the embodiments of the present disclosure can be a device with an operating system. The operating system can be the Android operating system, the iOS operating system, or other possible operating systems. The embodiments of the present disclosure do not make specific limitations.

[0166] The video shooting device provided by the embodiments of the present disclosure can implement Figures 1 to 5 each process implemented by the method embodiments. To avoid repetition, details are not described herein again.

[0167] Optionally, as Figure 9 shown, the embodiments of the present disclosure further provide an electronic device 900, including a processor 901, a memory 902, a program or instruction stored in the memory 902 and executable on the processor 901. When the program or instruction is executed by the processor 901, it implements each process of the above-mentioned video shooting method embodiment and can achieve the same technical effect. To avoid repetition, details are not described herein again.

[0168] It should be noted that the electronic device in the embodiments of the present disclosure includes the above-mentioned mobile electronic device and non-mobile electronic device.

[0169] Optionally, as Figure 10 shown, the embodiments of the present disclosure further provide an electronic device 1000, including a processor 1001, a memory 1002, a program or instruction stored in the memory 1002 and executable on the processor 1001. When the program or instruction is executed by the processor 1001, it implements each process of the above-mentioned video shooting method embodiment and can achieve the same technical effect. To avoid repetition, details are not described herein again.

[0170] Figure 11Schematic diagram of the hardware structure of an electronic device according to an embodiment of the present disclosure.

[0171] The electronic device 1100 includes, but is not limited to: a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109, and a processor 1110, etc.

[0172] Those skilled in the art can understand that the electronic device 1100 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 1110 through a power management system, so as to realize functions such as management of charging, discharging, and power consumption management through the power management system. Figure 11 The structure of the electronic device shown does not limit 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.

[0173] It should be understood that in the embodiment of the present disclosure, the input unit 1104 may include a GPU (Graphics Processing Unit) 1141 and a microphone 1142. The graphics processor 1141 processes the image data of still pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1106 may include a display panel 1161, and the display panel 1161 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 1171 and other input devices 1172. The touch panel 1171 is also called a touch screen. The touch panel 1171 may include two parts: a touch detection device and a touch controller. The other input devices 1172 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here. The memory 1109 may be used to store software programs and various data, including but not limited to application programs and operating systems. The processor 1110 may integrate an application processor and a modulation and demodulation processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, and the modulation and demodulation processor mainly processes wireless communication. It can be understood that the above modulation and demodulation processor may not be integrated into the processor 1110.

[0174] The embodiment of the present disclosure provides an electronic device, which realizes each process of the first device or the second device in the above video shooting method embodiment when executed, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0175] An embodiment of the present disclosure provides a shooting system, including a first device, a second device, and a server. The first device is configured to perform the steps of the first device in the above embodiment of the video shooting method. The second device is configured to perform the steps of the second device in the above embodiment of the video shooting method. The server is configured to perform the steps of the server in the above embodiment of the video shooting method.

[0176] An embodiment of the present disclosure further provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above embodiment of the video shooting method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0177] An embodiment of the present disclosure provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute each process of the above embodiment of the video shooting method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0178] Wherein, the processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, or optical disc, etc.

[0179] Another embodiment of the present disclosure provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is configured to run a program or instruction to implement each process of the above embodiment of the video shooting method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0180] It should be understood that the chip mentioned in the embodiment of the present disclosure may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0181] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present disclosure is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0182] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present disclosure.

[0183] The embodiments of the present disclosure have been described above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present disclosure, those of ordinary skill in the art can also make many forms without departing from the purpose of the present disclosure and the scope protected by the claims, and all of them belong to the protection scope of the present disclosure.

Claims

1. A video shooting method, applied to a first device, characterized in that, the method includes: When the first device and the second device determine to shoot a video together, establish a first coordinate axis and send the first coordinate axis to the server, where the first coordinate axis is used to calibrate the coordinate axes of other devices shooting the video together; Send a first original video collected based on the first coordinate axis to the server, where the first original video is a video of capturing an image of a first object at a target position; Receive and display the target collaborative video sent by the server; wherein, the target collaborative video is synthesized based on the first original video, an image of a second object, and dynamic information of the second object, and the second object is the shooting object in a second original video captured by the second device according to the coordinate axis calibrated based on the first coordinate axis, and the dynamic information of the second object indicates the change in the pose of the image of the second object over time; wherein, synthesizing the target collaborative video based on the first original video, the image of the second object, and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object satisfy a preset interaction action, then according to the preprocessing corresponding to the preset interaction action, fuse the interaction actions of the first object and the second object; the preset interaction action is that there is a contact part between the first object and the second object.

2. The method according to claim 1, characterized in that, before sending the first coordinate axis to the server, the method further includes: When logging in to a target shared account and receiving a video shooting together input, send a video shooting together request message to the second device; wherein, the video shooting together request message includes a login entry for the target shared account; if the second device logs in to the target shared account, it indicates that the second device joins the video shooting together initiated by the first device.

3. The method according to claim 2, characterized in that, the video shooting together request message further includes at least one of location information and shooting scene information; wherein, the location information indicates the geographical location where the first device initiates the video shooting together, and the shooting scene information indicates the shooting background where the first device initiates the video shooting together.

4. The method according to claim 1, characterized in that, after receiving the target collaborative video sent by the server, the method further includes: When the shooting is completed, send an indication information of the completion of the video shooting together to the server; the indication information includes at least one of a video public status, an account public status, and location information; wherein, the video public status indicates whether the target collaborative video is publicly released, the account public status indicates whether other accounts can view the collaborative videos released by the target shared account, and the location information indicates the shooting position of the target collaborative video.

5. The method according to any one of claims 2 to 4, characterized in that, before sending the video shooting together request message to the second device, the method further includes: Obtain the target information of the first device and send the target information to the server, so that the server can obtain the co - production videos that match the target information in the publicly available co - production videos, where the target information includes at least one of location information and a preview image of the shooting interface; Receive the co - production videos that match the target information in the publicly available co - production videos sent by the server, and recommend and display the co - production videos that match the target information in the publicly available co - production videos.

6. A video shooting method, applied to a second device, characterized in that, the method includes: When it is determined to join the video co - production initiated by the first device, establish a second coordinate axis for collecting video images, and send the second coordinate axis to the server, so that the server can calibrate the second coordinate axis according to the first coordinate axis of the first device; Collect a second original video based on the calibrated coordinate axis sent by the server; Segment the image of the second object in the second original video, and obtain the dynamic information of the second object in the second original video, where the dynamic information of the second object indicates the change in the posture of the image of the second object over time; Send the segmented image of the second object and the dynamic information of the second object to the server; Receive and display the target co - production video sent by the server; wherein, the target co - production video is synthesized based on a first original video, the image of the second object, and the dynamic information of the second object; the first original video is a video of the first device collecting the image of the first object at the target location; synthesizing the target co - production video based on the first original video, the image of the second object, and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object satisfy a preset interaction action, then according to the pre - processing corresponding to the preset interaction action, fuse the interaction actions of the first object and the second object; the preset interaction action is that there is a contact part between the first object and the second object.

7. The method according to claim 6, characterized in that, before sending the second coordinate axis to the server, the method further includes: Receive the video co - production request message sent by the first device, where the video co - production request message includes the login entry of the target shared account; Based on the video co - production request message, log in to the target shared account to join the video co - production initiated by the first device.

8. A video shooting method, applied to a server, characterized in that, the method includes: When the first device and the second device determine the co - production video, receive the first coordinate axis sent by the first device and the second coordinate axis sent by the second device; Based on the first coordinate axis, calibrate the second coordinate axis, and send the calibrated coordinate axis to the second device, so that the second device can collect video images based on the calibrated coordinate axis; Receive the first original video sent by the first device, the image of the second object sent by the second device, and the dynamic information of the second object, where the first original video is a video of capturing the image of the first object at the target location; Based on the first original video, the image of the second object, and the dynamic information of the second object, synthesize a target co - shooting video; wherein, the synthesizing the target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object satisfy a preset interaction action, then according to the pre - processing corresponding to the preset interaction action, fuse the interaction actions of the first object and the second object; the preset interaction action is that there is a contact part between the first object and the second object; Send the target co - shooting video to the first device and the second device.

9. The method according to claim 8, wherein, the synthesizing the target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object includes: Based on the first coordinate axis, obtain the first depth information of the joint points of the first object in the first original video, and obtain the second depth information of the joint points of the second object; According to the first depth information and the second depth information, determine the front - back position relationship between the first object and the second object; Based on the position relationship between the first object and the second object, and the dynamic information of the second object, synthesize the image of the second object and the first original video information to obtain the target co - shooting video.

10. The method according to claim 8, wherein, after sending the target co - shooting video to the first device and the second device, the method further includes: Receive the indication information sent by the first device indicating that the video co - shooting is completed, and the indication information indicates at least one of the video public state, the account public state, and the location information; When the indication information indicates that the video public state is publicly released, release the target co - shooting video; wherein, the video public state indicates whether the target co - shooting video is publicly released, the account public state indicates whether other accounts can view the co - shooting video released by the target sharing account, and the location information indicates the shooting location of the target co - shooting video.

11. A video shooting device, wherein, Applied to the first device, the video shooting device includes: an establishment module, a sending module, a receiving module, and a display module; The establishment module is used to establish a first coordinate axis when the first device and the second device determine video co - shooting; The sending module is used to send the first coordinate axis to the server, and send the first original video collected based on the first coordinate axis to the server, where the first coordinate axis is used to calibrate the coordinate axes of other co - shooting devices, and the first original video is a video of capturing the image of the first object at the target location; The receiving module is used to receive the target co - shooting video sent by the server; The display module is further configured to display the target co - shooting video sent by the server; Among them, the target co - shooting video is synthesized based on the first original video, the image of the second object, and the dynamic information of the second object. The second object is the shooting object in the second original video collected by the second device according to the second coordinate axis calibrated based on the first coordinate axis. The dynamic information of the second object indicates the change of the pose of the image of the second object over time. Among them, synthesizing the target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object meet the preset interaction actions, then according to the pre - processing corresponding to the preset interaction actions, fuse the interaction actions of the first object and the second object; the preset interaction action is that there is a contact part between the first object and the second object.

12. A video shooting device Characterized in that Applied to the second device, the video shooting device includes: a establishing module, a sending module, a collecting module, a splitting module, an obtaining module, a receiving module, and a display module; The establishing module is configured to establish a second coordinate axis for collecting video images when it is determined to join the video co - shooting initiated by the first device; The sending module is configured to send the second coordinate axis to the server so that the server calibrates the second coordinate axis according to the first coordinate axis of the first device; The collecting module is configured to collect a second original video based on the calibrated coordinate axis sent by the server; The splitting module is configured to split the image of the second object in the second original video; The obtaining module is configured to obtain the dynamic information of the second object in the second original video, and the dynamic information of the second object indicates the change of the pose of the image of the second object over time; The sending module is configured to send the split image of the second object and the dynamic information of the second object to the server; The receiving module is configured to receive the target co - shooting video sent by the server; The display module is configured to display the target co - shooting video sent by the server; Among them, the target co - shooting video is synthesized based on the first original video, the image of the second object, and the dynamic information of the second object; the first original video is the video of the first device collecting the image of the first object at the target position. Synthesizing the target co - shooting video based on the first original video, the image of the second object, and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object meet the preset interaction actions, then according to the pre - processing corresponding to the preset interaction actions, fuse the interaction actions of the first object and the second object; the preset interaction action is that there is a contact part between the first object and the second object.

13. A video shooting device Characterized in that Applied to the server, the video shooting device includes: a receiving module, a calibration module, a sending module, and a synthesis module; The receiving module is used to receive a first coordinate axis sent by the first device and a second coordinate axis sent by the second device when the first device and the second device determine to shoot a video together; The calibration module is used to calibrate the second coordinate axis based on the first coordinate axis; The sending module is used to send the calibrated coordinate axis to the second device, so that the second device captures the video image based on the calibrated coordinate axis; The receiving module is further used to receive a first original video sent by the first device, an image of a second object sent by the second device, and dynamic information of the second object, wherein the first original video is a video of capturing an image of the first object at a target position; The synthesis module is used to synthesize a target combined video based on the first original video, the image of the second object and the dynamic information of the second object; wherein, the synthesis of the target combined video based on the first original video, the image of the second object and the dynamic information of the second object includes: if it is detected that the actions of the first object and the second object meet the preset interactive action, then according to the preprocessing corresponding to the preset interactive action, the interactive action of the first object and the second object is merged; the preset interactive action is that the first object and the second object have a contact part; The sending module is used to send the target co-shot video to the first device and the second device.

14. An electronic device, It is characterized in that It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the video shooting method as described in any one of claims 1 to 5, or any one of 6 or 7.

15. A server, It is characterized in that It comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the video shooting method as described in any one of claims 8 to 10.

16. A photographing system, It is characterized in that The method comprises a first device, a second device and a server, wherein the first device is used to execute the steps of the video shooting method as described in any one of claims 1 to 5, the second device is used to execute the steps of the video shooting method as described in claim 6 or 7, and the server is used to execute the steps of the video shooting method as described in any one of claims 8 to 10.

17. A readable storage medium, It is characterized in that The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the video shooting method as described in any one of claims 1 to 5, 6 or 7, or any one of claims 8 to 10 are implemented.

Images