Video generation method, device, electronic device and storage medium

Abstract

The present application provides a video generation method, device, electronic device and storage medium, which relates to the field of image processing technology. The method includes obtaining the current viewer perspective and current viewer position of the viewer in the target scene; finding at least one target camera in the same direction as the current viewer perspective according to the current viewer perspective, current viewer position, field of view directions of multiple cameras and distances of multiple cameras from the target intersection; calculating the current view angle between the target camera and the viewer according to the current viewer perspective, current viewer position, field of view directions of each target camera, distances of each target camera from the target intersection and the position of the target intersection; offsetting the video picture captured by the target camera according to the current view angle between the target camera and the viewer; generating the target video picture based on the offset video picture. The method, device, electronic device and storage medium provided in the present application can realize arbitrary view angle switching of the video.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a video generation method, device, electronic device and storage medium. Background Art

[0002] With the popularity of live broadcasts and short videos, people have a higher demand for video viewing formats. Panoramic video is a technology that has emerged under this demand, but panoramic video is mainly used for range recording. During the viewing process, the audience can only watch from a specified angle and cannot interact with the scene. For example, in a panoramic video showing a study, the audience cannot approach the desk lamp to see the brand of the desk lamp, nor can they go around the other side of the desk to see what the other side of the desk lamp looks like. The audience's perspective is limited to the position of the shooting equipment, and they cannot approach the object of interest, nor can they look at the same object from a different angle.

[0003] Therefore, how to provide an effective solution to facilitate arbitrary video viewing angle switching has become a difficult problem to be solved in the prior art. Summary of the invention

[0004] In a first aspect, an embodiment of the present application provides a video generation method, comprising:

[0005] Obtain the current viewer perspective and current viewer position of the viewer in the target scene;

[0006] According to the current viewer's viewing angle, the current viewer's position, the viewing directions of multiple cameras, and the distances between the multiple cameras and the target intersection point, at least one target camera with the same direction as the current viewer's viewing angle is found from the multiple cameras;

[0007] Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0008] offsetting the video image captured by at least one of the target cameras according to the angle between the at least one target camera and the current viewing angle of the audience;

[0009] Generate a target video picture based on the offset video picture;

[0010] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0011] In a possible design, generating a target video picture based on the offset video picture includes:

[0012] If at least one of the target cameras is a camera, the video picture obtained after the offset is used as the target video picture;

[0013] If at least one of the target cameras is a plurality of cameras, the plurality of video frames obtained after the offset are spliced ​​to obtain the target video frame.

[0014] In a possible design, before obtaining the current viewer perspective and the current viewer position of the viewer in the target scene, the method further includes:

[0015] In response to the user's adjustment operation, the viewer's perspective and / or position in the target scene is adjusted.

[0016] In a possible design, before adjusting the viewing angle and / or position of the viewer in the target scene in response to the user's adjustment operation, the method further includes:

[0017] Initialize the viewer's perspective and position in the target scene.

[0018] In one possible design, the method further includes:

[0019] Calculating a distance between at least one of the target cameras and the current viewer position;

[0020] Before or after shifting the video image captured by at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience, the method further includes:

[0021] Zooming in and out the video image captured by at least one of the target cameras according to the distance between at least one of the target cameras and the current viewer position;

[0022] The step of generating a target video picture based on the offset video picture includes:

[0023] Based on the offset and scaled video images, a target video image is obtained.

[0024] In a possible design, according to the angle between the at least one target camera and the current viewing angle of the audience, the video image captured by the at least one target camera is offset, including:

[0025] Calculating an offset angle of a video image corresponding to at least one of the target cameras according to an angle between at least one of the target cameras and a current viewing angle of the audience;

[0026] The video picture captured by at least one of the target cameras is shifted according to the shift angle of the video picture corresponding to at least one of the target cameras.

[0027] In one possible design, the method further includes:

[0028] Receive the field of view directions of the multiple cameras, the distances of the multiple cameras from the target intersection, and the identification numbers of the multiple cameras uploaded by a third-party device connected to the multiple cameras.

[0029] In a second aspect, an embodiment of the present application provides a video generating device, including:

[0030] An acquisition module, used to acquire the current viewer perspective and current viewer position of the viewer in the target scene;

[0031] A search module, configured to find at least one target camera with the same direction as the current viewer's view from the multiple cameras according to the current viewer's view, the current viewer's position, the view directions of the multiple cameras, and the distances between the multiple cameras and the target intersection point;

[0032] A calculation module, configured to calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current viewing angle of the audience, the current position of the audience, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0033] An offset module, used for offsetting the video image captured by at least one of the target cameras according to the angle between the at least one of the target cameras and the current viewing angle of the audience;

[0034] A generation module, used for generating a target video picture based on the offset video picture;

[0035] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the bus;

[0037] Memory, used to store computer programs;

[0038] The processor is used to execute the program stored in the memory to implement the following process:

[0039] Obtain the current viewer perspective and current viewer position of the viewer in the target scene;

[0040] According to the current viewer's viewing angle, the current viewer's position, the viewing directions of multiple cameras, and the distances between the multiple cameras and the target intersection point, at least one target camera with the same direction as the current viewer's viewing angle is found from the multiple cameras;

[0041] Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0042] offsetting the video image captured by at least one of the target cameras according to the angle between the at least one target camera and the current viewing angle of the audience;

[0043] Generate a target video picture based on the offset video picture;

[0044] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0045] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the following process is implemented:

[0046] Obtain the current viewer perspective and current viewer position of the viewer in the target scene;

[0047] According to the current viewer's viewing angle, the current viewer's position, the viewing directions of multiple cameras, and the distances between the multiple cameras and the target intersection point, at least one target camera with the same direction as the current viewer's viewing angle is found from the multiple cameras;

[0048] Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0049] offsetting the video image captured by at least one of the target cameras according to the angle between the at least one target camera and the current viewing angle of the audience;

[0050] Generate a target video picture based on the offset video picture;

[0051] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0052] At least one of the above technical solutions adopted in one or more embodiments of the present application can achieve the following beneficial effects:

[0053] By first finding the target camera with the same direction as the current viewer's perspective, and calculating the angle between the target camera and the viewer's current perspective, the video image captured by at least one target camera is offset based on the angle between the target camera and the viewer's current perspective, and the target video image is generated based on the offset video image. In this way, the displayed video image can change with the viewer's perspective, so that the video can be switched at any perspective, and the interaction between the viewer and the scene can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The drawings described herein are used to provide a further understanding of this document and constitute a part of this document. The exemplary embodiments and descriptions of this document are used to explain this document and do not constitute an improper limitation on this document. In the drawings:

[0055] Figure 1 A schematic diagram of an application environment for a video generation method, device, electronic device, and storage medium provided in one embodiment of the present application.

[0056] Figure 2 A flowchart of a video generation method provided by one embodiment of the present application.

[0057] Figure 3 A schematic diagram of the structure of an electronic device provided for one embodiment of the present application.

[0058] Figure 4 A schematic diagram of the structure of a video generating device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to facilitate switching of arbitrary video viewing angles, an embodiment of the present application provides a video generation method, device, electronic device and storage medium, which can cause the displayed video picture to change as the viewer's viewing angle changes, so as to facilitate switching of arbitrary video viewing angles.

[0060] First, in order to more intuitively understand the solution provided by the embodiment of the present application, Figure 1 , the system architecture of the video generation solution provided in the embodiment of the present application is described.

[0061] like Figure 1 As shown in FIG. 1 , it is a schematic diagram of the application environment of the video generation method, device, electronic device and storage medium provided by one or more embodiments of the present application. Figure 1As shown, the third-party device is connected to multiple cameras and is communicatively connected to the video playback device. The field of view directions of the multiple cameras are all oriented toward the same area in the target scene, and the center lines of the fields of view of the multiple cameras have a common intersection, namely the target intersection. The third-party device can send data such as the field of view directions of the multiple cameras, the identification numbers of the multiple cameras, the distances of the multiple cameras from the target intersection, the videos captured by the multiple cameras, and the number of the multiple cameras to the video playback device. The third-party device may be, but is not limited to, a server, a personal computer or other device for data aggregation and forwarding, the video playback device may be, but is not limited to, a personal computer, a smart phone, a tablet computer, a smart TV or other device with video playback function, and the identification number may be a number or device code that uniquely identifies the camera.

[0062] The video generation method provided in the embodiment of the present application will be described in detail below.

[0063] The video generation method provided in the embodiment of the present application can be applied to a video playback device. For ease of description, unless otherwise specified, the embodiments of the present application are described with the video playback device as the execution subject.

[0064] It can be understood that the execution entity does not constitute a limitation on the embodiments of the present application.

[0065] like Figure 2 As shown, the video generation method provided in the embodiment of the present application may include the following steps:

[0066] Step S201, obtaining the current viewer's perspective and current viewer position in the target scene.

[0067] In the embodiment of the present application, when the video playback device starts to play the video image captured by the camera, it can first initialize the viewer's vision and position in the target scene. The user of the video playback device can initiate an adjustment operation for the viewer's vision and / or position, and the video playback device responds to the user's adjustment operation and adjusts the viewer's perspective and / or position in the target scene.

[0068] After each response to the user's adjustment operation, the video playback device can re-acquire the current viewer perspective and current viewer position of the viewer in the target scene.

[0069] Step S202, according to the current viewer's view angle, the current viewer's position, the field of view directions of the multiple cameras and the distances from the multiple cameras to the target intersection, find at least one target camera with the same direction as the current viewer's view angle from the multiple cameras.

[0070] In the embodiment of the present application, the third-party device is connected to multiple cameras and can send data such as the field of view directions of the multiple cameras, the identification numbers of the multiple cameras, the distances of the multiple cameras from the target intersection, the videos captured by the multiple cameras, and the number of the multiple cameras to the video playback device. The video playback device can find at least one target camera with the same direction as the current viewer's view from the multiple cameras according to the current viewer's view, the current viewer's position, the field of view directions of the multiple cameras, and the distances of the multiple cameras from the target intersection.

[0071] Among them, in the target scene, the center line of the current audience's viewing angle is just within the field of view of one or more cameras, and the one or more cameras can be called target cameras with the same direction as the current audience's viewing angle.

[0072] It should be noted that when a third-party device sends videos captured by multiple cameras to a video playback device, it is necessary to use a unified clock generator to synchronously send the videos captured by multiple cameras to the video playback device to ensure that the multiple video images received by the video playback device maintain clock synchronization, so as to avoid the video images being inconsistent with the actual situation due to clock asynchrony during subsequent image splicing.

[0073] Step S203, calculating the angle between at least one target camera and the current viewing angle of the viewer according to the current viewer viewing angle, the current viewer position, the viewing direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point.

[0074] The angle between the target camera and the current viewing angle of the audience may be the angle between the center line of the field of view of the target camera and the center line of the current viewing angle of the audience.

[0075] In the embodiment of the present application, the target intersection is the center point of the target scene, and its position is known. When calculating the current viewing angle between the at least one target camera and the audience, the centerline direction of the field of view of each target camera can be determined based on the field of view direction of each target camera in the at least one target camera, and the position of each target camera can be determined based on the centerline direction of the field of view of each target camera, the distance of each target camera from the target intersection, and the position of the target intersection. Then, based on the position of each target camera, the centerline direction of the field of view of each target camera, the centerline direction of the current audience's viewing angle, and the current audience position, the current viewing angle between each target camera and the audience is calculated.

[0076] Step S204: offset the video image captured by at least one target camera according to the included angle between at least one target camera and the current viewing angle of the audience.

[0077] Specifically, the offset angle of the video picture corresponding to each target camera can be calculated first according to the angle between each target camera in at least one target camera and the current viewing angle of the audience, and then the video picture captured by each target camera is offset according to the offset angle of the video picture corresponding to each target camera.

[0078] In a possible design, the video playback device can also calculate the distance between each target camera and the current viewer position according to the current viewer position and the position of each target camera. Before or after the video picture captured by at least one target camera is offset, the video picture captured by each target camera can be scaled according to the distance between each target camera and the current viewer position. Specifically, the video picture captured by each target camera can be enlarged, and the greater the distance between the target camera and the current viewer position, the greater the magnification. In this way, the size of the object in the scaled video picture is consistent with the size of the object captured from the current viewer position, thereby avoiding video picture distortion.

[0079] Step S205: generating a target video picture based on the shifted video picture.

[0080] Specifically, if at least one target camera is one camera, the video picture obtained after the offset is used as the target video picture. If at least one target camera is multiple cameras, the multiple video pictures obtained after the offset are spliced ​​to obtain the target video picture.

[0081] Among them, splicing video images is an existing technology and is not specifically described in the embodiments of the present application.

[0082] In a possible design, if the video images captured by each target camera are scaled, when the target video image is obtained, the target video image can be generated based on the offset and scaled video image. That is, if at least one target camera is a single camera, the video image obtained after offset and scaling is used as the target video image, and if at least one target camera is multiple cameras, the multiple video images obtained after offset and scaling are spliced ​​to obtain the target video image.

[0083] In summary, the video generation method provided by the embodiment of the present application first finds the target camera in the same direction as the current viewer's perspective, and calculates the current view angle between the target camera and the viewer, and then based on the current view angle between the target camera and the viewer, the video screen captured by at least one target camera is offset, and based on the offset video screen, the target video screen is generated. In this way, the displayed video screen can change with the change of the viewer's perspective, so as to facilitate the arbitrary view angle switching of the video and realize the interaction between the audience and the scene. At the same time, when the third-party device sends the video captured by multiple cameras to the video playback device, the video captured by multiple cameras is synchronously sent to the video playback device to ensure that the multiple video screens received by the video playback device maintain clock synchronization, so as to avoid the video screen from being inconsistent with the actual situation due to clock asynchronization during subsequent screen splicing. In addition, the video screen captured by each target camera can also be scaled according to the distance between each target camera and the current viewer's position, so that the size of the object in the scaled video screen is consistent with the size of the object captured from the current viewer's position, thereby avoiding video screen distortion.

[0084] Figure 3 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0085] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0086] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0087] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a video generation device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0088] Obtain the current viewer perspective and current viewer position of the viewer in the target scene;

[0089] According to the current viewer's viewing angle, the current viewer's position, the viewing directions of multiple cameras, and the distances between the multiple cameras and the target intersection point, at least one target camera with the same direction as the current viewer's viewing angle is found from the multiple cameras;

[0090] Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0091] offsetting the video image captured by at least one of the target cameras according to the angle between the at least one target camera and the current viewing angle of the audience;

[0092] Generate a target video picture based on the offset video picture;

[0093] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0094] The above application Figure 3The method performed by the video generation device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in one or more embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with one or more embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0095] The electronic device may also perform Figure 2 The method and the video generation device are implemented in Figure 3 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0096] Of course, in addition to software implementation, the electronic device of the present application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0097] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to execute Figure 2 The method of the embodiment shown is specifically used to perform the following operations:

[0098] Obtain the current viewer perspective and current viewer position of the viewer in the target scene;

[0099] According to the current viewer's viewing angle, the current viewer's position, the viewing directions of multiple cameras, and the distances between the multiple cameras and the target intersection point, at least one target camera with the same direction as the current viewer's viewing angle is found from the multiple cameras;

[0100] Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0101] offsetting the video image captured by at least one of the target cameras according to the angle between the at least one target camera and the current viewing angle of the audience;

[0102] Generate a target video picture based on the offset video picture;

[0103] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0104] Figure 4 is a schematic diagram of the structure of a video generation device provided by an embodiment of the present application. Figure 4 In a software implementation, the video generating device includes:

[0105] An acquisition module, used to acquire the current viewer perspective and current viewer position of the viewer in the target scene;

[0106] A search module, configured to find at least one target camera with the same direction as the current viewer's view from the multiple cameras according to the current viewer's view, the current viewer's position, the view directions of the multiple cameras, and the distances between the multiple cameras and the target intersection point;

[0107] A calculation module, configured to calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current viewing angle of the audience, the current position of the audience, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point;

[0108] An offset module, used for offsetting the video image captured by at least one of the target cameras according to the angle between the at least one of the target cameras and the current viewing angle of the audience;

[0109] A generation module, used for generating a target video picture based on the offset video picture;

[0110] The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

[0111] In short, the above is only a preferred embodiment of this document and is not intended to limit the scope of protection of this document. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of this document should be included in the scope of protection of this document.

[0112] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0113] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0114] Each embodiment in this document is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A video generation method, characterized in that: include: Obtain the current viewer perspective and current viewer position of the viewer in the target scene; According to the current viewer's perspective, the current viewer's position, the field of view directions of the multiple cameras, and the distances between the multiple cameras and the target intersection, at least one target camera with the same direction as the current viewer's perspective is found from the multiple cameras; if the center line of the current viewer's perspective is just within the field of view of one or more cameras, then the one or more cameras can be called the target camera with the same direction as the current viewer's perspective; Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point; The video picture captured by at least one of the target cameras is offset according to the current viewing angle between at least one of the target cameras and the audience, specifically comprising: calculating the offset angle of the video picture corresponding to at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience; offsetting the video picture captured by at least one of the target cameras according to the offset angle of the video picture corresponding to at least one of the target cameras; Generate a target video picture based on the offset video picture; The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

2. The method according to claim 1, characterized in that The step of generating a target video picture based on the offset video picture includes: If at least one of the target cameras is a camera, the video picture obtained after the offset is used as the target video picture; If at least one of the target cameras is a plurality of cameras, the plurality of video frames obtained after the offset are spliced ​​to obtain the target video frame.

3. The method according to claim 1, characterized in that Before obtaining the current viewer perspective and current viewer position of the viewer in the target scene, the method further includes: In response to the user's adjustment operation, the viewer's perspective and / or position in the target scene is adjusted.

4. The method according to claim 3, characterized in that Before adjusting the viewing angle and / or position of the viewer in the target scene in response to the user's adjustment operation, the method further includes: Initialize the viewer's perspective and position in the target scene.

5. The method according to claim 1, characterized in that: The method further comprises: Calculating a distance between at least one of the target cameras and the current viewer position; Before or after shifting the video image captured by at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience, the method further includes: Zooming in and out the video image captured by at least one of the target cameras according to the distance between at least one of the target cameras and the current viewer position; The step of generating a target video picture based on the offset video picture includes: Based on the offset and scaled video images, a target video image is obtained.

6. The method according to claim 1, characterized in that The method further comprises: Receive the field of view directions of the multiple cameras, the distances of the multiple cameras from the target intersection, and the identification numbers of the multiple cameras uploaded by a third-party device connected to the multiple cameras.

7. A video generating device, characterized in that: include: An acquisition module, used to acquire the current viewer perspective and current viewer position of the viewer in the target scene; A search module is used to find at least one target camera with the same direction as the current viewer's view from the multiple cameras according to the current viewer's view, the current viewer's position, the view field directions of the multiple cameras and the distances between the multiple cameras and the target intersection point; if the center line of the current viewer's view happens to be within the view field of one or more cameras, then the one or more cameras can be called the target camera with the same direction as the current viewer's view; A calculation module, configured to calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current viewing angle of the audience, the current position of the audience, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point; The offset module is used to offset the video picture captured by at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience, specifically comprising: calculating the offset angle of the video picture corresponding to at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience; offsetting the video picture captured by at least one of the target cameras according to the offset angle of the video picture corresponding to at least one of the target cameras; A generation module, used for generating a target video picture based on the offset video picture; The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

8. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the bus; Memory, used to store computer programs; The processor is used to execute the program stored in the memory to implement the following process: Obtain the current viewer perspective and current viewer position of the viewer in the target scene; According to the current viewer's perspective, the current viewer's position, the field of view directions of the multiple cameras, and the distances between the multiple cameras and the target intersection, at least one target camera with the same direction as the current viewer's perspective is found from the multiple cameras; if the center line of the current viewer's perspective is just within the field of view of one or more cameras, then the one or more cameras can be called the target camera with the same direction as the current viewer's perspective; Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point; The video picture captured by at least one of the target cameras is offset according to the current viewing angle between at least one of the target cameras and the audience, specifically comprising: calculating the offset angle of the video picture corresponding to at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience; offsetting the video picture captured by at least one of the target cameras according to the offset angle of the video picture corresponding to at least one of the target cameras; Generate a target video picture based on the offset video picture; The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the following process is implemented: Obtain the current viewer perspective and current viewer position of the viewer in the target scene; According to the current viewer's perspective, the current viewer's position, the field of view directions of the multiple cameras, and the distances between the multiple cameras and the target intersection, at least one target camera with the same direction as the current viewer's perspective is found from the multiple cameras; if the center line of the current viewer's perspective is just within the field of view of one or more cameras, then the one or more cameras can be called the target camera with the same direction as the current viewer's perspective; Calculate the angle between at least one of the target cameras and the current viewing angle of the audience according to the current audience viewing angle, the current audience position, the field of view direction of each target camera, the distance between each target camera and the target intersection point, and the position of the target intersection point; The video picture captured by at least one of the target cameras is offset according to the current viewing angle between at least one of the target cameras and the audience, specifically comprising: calculating the offset angle of the video picture corresponding to at least one of the target cameras according to the current viewing angle between at least one of the target cameras and the audience; offsetting the video picture captured by at least one of the target cameras according to the offset angle of the video picture corresponding to at least one of the target cameras; Generate a target video picture based on the offset video picture; The fields of view of the multiple cameras are all oriented toward the same area in the target scene, and the target intersection is a common intersection of the center lines of the fields of view of the multiple cameras.

Images