Live screen generation method, system, device and electronic equipment

Abstract

The embodiments of the present invention relate to the field of computer vision technology, and disclose a method, system, device and electronic device for generating a live broadcast picture. The method comprises: obtaining a current motion picture including a target athlete; determining the position and head rotation angle of the target athlete in the current motion picture; determining the position and viewing angle of the target athlete in a three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current motion picture; generating a live broadcast picture simulating the first-person perspective of the target athlete according to the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above manner, the embodiments of the present invention improve the user experience of live video broadcasting.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer vision technology, and specifically to a method, system, device and electronic device for generating a live broadcast image. Background Art

[0002] With the continuous development of Internet technology, live broadcasts of various sports events can enable viewers to watch sports events in real time and enhance their viewing experience.

[0003] For sports such as boxing matches, since the range of activities of athletes during the competition is relatively small, a better live broadcast effect can be achieved by shooting with a camera at a fixed position or by manual follow-up shooting during the live broadcast of the event. However, the inventors found in the process of implementing the embodiments of the present invention that for sports such as skiing competitions, since the range of activities of athletes during the competition is relatively large, a better live broadcast effect cannot be achieved by shooting with a camera at a fixed position or by manual follow-up shooting, and the user experience is poor when live broadcasting sports events. Summary of the invention

[0004] In view of the above problems, the embodiments of the present invention provide a method, system, device and electronic device for generating a live broadcast image, which are used to solve the problem of poor user experience of live video broadcast in the prior art.

[0005] According to one aspect of an embodiment of the present invention, a method for generating a live broadcast screen is provided, the method comprising:

[0006] Get the current sports picture including the target athlete;

[0007] Determine the position and head rotation angle of the target athlete in the current motion picture;

[0008] Determining the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture;

[0009] According to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a live broadcast picture simulating the first-person viewing angle of the target athlete is generated.

[0010] In an optional manner, the current motion picture includes a first current motion picture and a second current motion picture, and the first current motion picture and the second current motion picture are motion pictures collected based on different viewing angles.

[0011] In an optional manner, determining the position and head rotation angle of the target athlete in the current motion picture includes:

[0012] Identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture;

[0013] inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively;

[0014] The head rotation angle of the target athlete in the current motion picture is determined according to the preset rotation angle recognition model.

[0015] In an optional manner, before inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively, the method further includes:

[0016] Acquire a plurality of sample images of the target athlete's head at different rotation angles in three-dimensional space;

[0017] Determine the rotation angle of each sample image;

[0018] The preset rotation angle recognition model is generated according to the multiple sample images and the rotation angle of each sample image.

[0019] In an optional manner, the method further includes:

[0020] determining the height of the target athlete according to the position of the target athlete in the first current motion picture;

[0021] The camera is controlled to capture the second current motion picture based on the height of the target athlete.

[0022] In an optional manner, the head rotation angle includes a first rotation angle, a second rotation angle and a third rotation angle, and the first rotation angle, the second rotation angle and the third rotation angle are respectively rotation angles of the target athlete's head in different dimensions of the three-dimensional space;

[0023] Determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model comprises:

[0024] Identify the first current motion picture by using the preset rotation angle identification model to determine the first rotation angle and the second rotation angle;

[0025] The second current motion picture is identified by using the preset rotation angle identification model to determine the third rotation angle.

[0026] According to another aspect of an embodiment of the present invention, a system for generating live images of a skiing competition is provided, the system comprising: a server and a camera; the server is used to:

[0027] Acquire a current motion picture including a target athlete captured by the camera;

[0028] Determine the position and head rotation angle of the target athlete in the current motion picture;

[0029] Determining the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture;

[0030] According to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a live broadcast picture simulating the first-person viewing angle of the target athlete is generated.

[0031] According to another aspect of an embodiment of the present invention, a device for generating a live screen of a skiing competition is provided, the device comprising:

[0032] An acquisition module, used to acquire the current motion picture including the target athlete;

[0033] A first determination module is used to determine the position and head rotation angle of the target athlete in the current motion picture;

[0034] A second determination module is used to determine the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture;

[0035] The generation module is used to generate a live broadcast picture simulating the first-person perspective of the target athlete according to the position and perspective of the target athlete in the three-dimensional panoramic picture.

[0036] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0037] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute the operation of the above-mentioned live screen generation method.

[0038] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, wherein at least one executable instruction is stored in the storage medium. When the executable instruction is executed on an electronic device, the electronic device executes the operation of the above-mentioned live screen generation method.

[0039] In an embodiment of the present invention, during the movement of the target athlete, the target athlete is photographed to obtain a current movement picture containing the target athlete; the position of the target athlete in the current movement picture and the head rotation angle can be determined by performing image recognition on the current movement picture; the position and viewing angle of the target athlete in the three-dimensional panoramic picture can be further determined based on the position and viewing angle of the head of the target athlete in the current movement picture; and a live broadcast picture simulating the first-person perspective of the target athlete can be generated based on the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above-mentioned implementation manner, a live broadcast picture simulating the first-person perspective of the target athlete can be generated by including the current movement picture of the target athlete, thereby improving the user experience when the user watches the live video.

[0040] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0042] Figure 1 A schematic diagram showing a flow chart of a method for generating a live broadcast screen provided by an embodiment of the present invention;

[0043] Figure 2 A schematic diagram showing the structure of a live broadcast screen generation system provided by an embodiment of the present invention is shown;

[0044] Figure 3 A schematic diagram showing the structure of a live broadcast screen generating device provided by an embodiment of the present invention is shown;

[0045] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0046] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0047] Figure 1 The flowchart of the live screen generation method according to the embodiment of the present invention is shown, and the method is executed by an electronic device. The memory of the electronic device is used to store at least one executable instruction, and the executable instruction enables the processor of the electronic device to execute the operation of the live screen generation method.

[0048] like Figure 1 As shown, the method comprises the following steps:

[0049] Step 110: Acquire the current motion picture including the target athlete.

[0050] Among them, the target athlete in the embodiment of the present invention generally refers to an athlete in a sports event. The position of the target athlete in the sports event is constantly moving. For example, during a skiing competition, the target athlete starts from a starting point and passes through the ski track to the end of the competition. During the movement of the target athlete, the target athlete can be photographed by a camera to generate a current motion picture containing the target athlete. The camera has a network unit, and the current motion picture can be uploaded to the network through the network unit. Further, the current motion picture containing the target athlete can be obtained.

[0051] In an optional manner, the current motion picture includes a first current motion picture and a second current motion picture, and the first current motion picture and the second current motion picture are motion pictures collected based on different viewing angles. For example, in a ski jumping competition, a side camera and a front camera are respectively set at the side of the track and the end of the track, the side camera faces the direction of the track and changes the shooting angle of view as the target athlete moves, and the front camera faces the direction of the platform and changes the shooting angle of view as the target athlete moves. The first current motion picture can be collected by the side camera, and the second current motion picture can be collected by the front camera. Further, when collecting the second current motion picture by the front camera, the height where the target athlete is located can be first determined, and the front camera is controlled to collect the second current motion picture at the height where the target athlete is located. When collecting the second current motion picture by the front camera, the height of the target athlete can also be determined according to the position of the target athlete in the first current motion picture. For example, in a ski jumping scene, a spatial rectangular coordinate system is established, the platform position is determined as the origin position, the top of the platform position is determined as the positive direction of the Z axis, the extension direction of the snow track is determined as the positive direction of the Y axis, and the left or right side of the platform position is set as the positive direction of the X axis. Assuming that the ski jumping venue is a 100*100*100 box, the position coordinates of the front camera may be, for example, (0, 100, 100), and the position coordinates of the side camera may be, for example, (100, 100, 50).

[0052] Step 120: Determine the position and head rotation angle of the target athlete in the current motion picture.

[0053] Wherein, after obtaining the current motion picture, the current motion picture can be identified by a picture recognition algorithm to determine the position of the target athlete in the current motion picture and the head rotation angle. When determining the position and head rotation angle of the target athlete in the current motion picture, the first current motion picture can be identified to determine the position of the target athlete in the first current motion picture, and the position of the target athlete in the first current motion picture is determined as the position of the target athlete in the current motion picture, for example, through a subject recognition method, the position of the target athlete in the first current motion picture is expressed as (Yc, Zc); further, the first current motion picture and the second current motion picture are respectively input into a preset rotation angle recognition model, and the head rotation angle of the target athlete in the current motion picture is determined according to the preset rotation angle recognition model. Further, before the first current motion picture and the second current motion picture are respectively input into the preset rotation angle recognition model, multiple sample images of the target athlete's head at different rotation angles in three-dimensional space can also be obtained to determine the rotation angle of each sample image; a preset rotation angle recognition model is generated according to multiple sample images and the rotation angle of each sample image.

[0054] The head rotation angle of the target athlete includes a first rotation angle, a second rotation angle and a third rotation angle, and the first rotation angle, the second rotation angle and the third rotation angle are respectively the rotation angles of the target athlete's head in different dimensions of the three-dimensional space. When determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model, the first current motion picture is recognized by the preset rotation angle recognition model to determine the first rotation angle and the second rotation angle; and the second current motion picture is recognized by the preset rotation angle recognition model to determine the third rotation angle.

[0055] Among them, the preset rotation angle recognition model can be, for example, a recognition model based on the SIFT (Scale invariant feature Transform) algorithm. In the ski jumping competition scene, after the competition starts, before each athlete goes on the field, through the head information collection device, under the premise that the athlete wears formal equipment, the 360-degree static information of the target athlete's head is collected through the circular eight-direction camera. Through the rotation of the circular eight-direction camera in the X-axis, Y-axis and Z-axis of the spatial coordinate system respectively, the rotation of the target athlete's head in the X-axis, Y-axis and Z-axis is simulated, and the head of the target athlete is photographed by the high-speed shutter of the circular eight-direction camera, and the X-axis, Y-axis and Z-axis angles corresponding to the rotation of each photo are recorded and stored in the corresponding database. Further, a preset rotation angle recognition model is generated according to the photos and corresponding rotation angles stored in the corresponding database. When the head rotation angle of the target athlete is determined by the preset rotation angle recognition model, the photo that best matches the current motion picture is determined by the SIFT algorithm, and the rotation angle corresponding to the best matching photo is determined as the head rotation angle of the target athlete in the current motion picture.

[0056] Step 130: Determine the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture.

[0057] Since the side camera shoots the target athlete from the side, the position (0, Yc, Zc) of the target athlete in the three-dimensional panoramic picture can be determined according to the position (Yc, Zc) of the target athlete in the first current motion picture. The viewing angle (Xr, Yr, Zr) of the target athlete in the three-dimensional panoramic picture can be determined according to the first rotation angle Xr, the second rotation angle Yr and the third rotation angle Zr of the target athlete in the current motion picture.

[0058] Step 140: Generate a live broadcast picture simulating the first-person perspective of the target athlete according to the position and perspective of the target athlete in the three-dimensional panoramic picture.

[0059] Among them, according to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a frame in the three-dimensional panoramic picture can be uniquely determined. When generating a live broadcast picture, if the current time is T1, according to the position and viewing angle of the target athlete in the three-dimensional panoramic picture corresponding to the time T1, a live broadcast picture simulating the first-person perspective of the target athlete at the time T1 can be generated. According to the time interval between different frames of the live broadcast picture, the live broadcast picture simulating the first-person perspective of the target athlete at the next time T2 is continuously generated to output the video stream to the terminal device that displays the live broadcast picture.

[0060] In an embodiment of the present invention, during the movement of the target athlete, the target athlete is photographed to obtain a current movement picture containing the target athlete; the position of the target athlete in the current movement picture and the head rotation angle can be determined by performing image recognition on the current movement picture; the position and viewing angle of the target athlete in the three-dimensional panoramic picture can be further determined based on the position and viewing angle of the head of the target athlete in the current movement picture; and a live broadcast picture simulating the first-person perspective of the target athlete can be generated based on the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above-mentioned implementation manner, a live broadcast picture simulating the first-person perspective of the target athlete can be generated by including the current movement picture of the target athlete, thereby improving the user experience when the user watches the live video.

[0061] Figure 2 FIG. 2 shows a schematic diagram of the structure of a live broadcast screen generation system according to an embodiment of the present invention. Figure 2 As shown, the system 200 includes: a server 210 and at least one camera 220 .

[0062] Among them, the server 210 is used to: obtain the current motion picture including the target athlete captured by the camera; determine the position and head rotation angle of the target athlete in the current motion picture; determine the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current motion picture; and generate a live broadcast picture simulating the first-person perspective of the target athlete according to the position and viewing angle of the target athlete in the three-dimensional panoramic picture.

[0063] In an embodiment of the present invention, during the movement of the target athlete, the target athlete is photographed through a camera to obtain a current movement picture containing the target athlete; the position of the target athlete in the current movement picture and the head rotation angle can be determined by performing image recognition on the current movement picture; the position and viewing angle of the target athlete in the three-dimensional panoramic picture can be further determined based on the position and viewing angle of the head of the target athlete in the current movement picture; a live broadcast picture simulating the first-person perspective of the target athlete can be generated based on the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above-mentioned implementation, a live broadcast picture simulating the first-person perspective of the target athlete can be generated by including the current movement picture of the target athlete, thereby improving the user experience when the user watches the live video.

[0064] Figure 3 FIG. 2 shows a schematic diagram of the structure of a live broadcast screen generating device according to an embodiment of the present invention. Figure 3 As shown, the device 300 includes: an acquisition module 310 , a first determination module 320 , a second determination module 330 and a generation module 340 .

[0065] Among them, the acquisition module 310 is used to acquire the current motion picture containing the target athlete; the first determination module 320 is used to determine the position and head rotation angle of the target athlete in the current motion picture; the second determination module 330 is used to determine the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current motion picture; the generation module 340 is used to generate a live broadcast picture simulating the first-person perspective of the target athlete according to the position and viewing angle of the target athlete in the three-dimensional panoramic picture.

[0066] In an optional manner, the current motion picture includes a first current motion picture and a second current motion picture, and the first current motion picture and the second current motion picture are motion pictures collected based on different viewing angles.

[0067] In an optional manner, the first determining module 320 is used to:

[0068] Identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture;

[0069] inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively;

[0070] The head rotation angle of the target athlete in the current motion picture is determined according to the preset rotation angle recognition model.

[0071] In an optional manner, the first determination module 320 is used to: before inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively, obtain a plurality of sample images of the target athlete's head at different rotation angles in a three-dimensional space;

[0072] Determine the rotation angle of each sample image;

[0073] The preset rotation angle recognition model is generated according to the multiple sample images and the rotation angle of each sample image.

[0074] In an optional manner, the acquisition module 310 is used to:

[0075] determining the height of the target athlete according to the position of the target athlete in the first current motion picture;

[0076] The camera is controlled to capture the second current motion picture based on the height of the target athlete.

[0077] In an optional manner, the head rotation angle includes a first rotation angle, a second rotation angle and a third rotation angle, wherein the first rotation angle, the second rotation angle and the third rotation angle are respectively rotation angles of the target athlete's head in different dimensions of the three-dimensional space; the first determination module 320 is used to:

[0078] Identify the first current motion picture by using the preset rotation angle identification model to determine the first rotation angle and the second rotation angle;

[0079] The second current motion picture is identified by using the preset rotation angle identification model to determine the third rotation angle.

[0080] In an embodiment of the present invention, during the movement of the target athlete, the target athlete is photographed to obtain a current movement picture containing the target athlete; the position of the target athlete in the current movement picture and the head rotation angle can be determined by performing image recognition on the current movement picture; the position and viewing angle of the target athlete in the three-dimensional panoramic picture can be further determined based on the position and viewing angle of the head of the target athlete in the current movement picture; and a live broadcast picture simulating the first-person perspective of the target athlete can be generated based on the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above-mentioned implementation manner, a live broadcast picture simulating the first-person perspective of the target athlete can be generated by including the current movement picture of the target athlete, thereby improving the user experience when the user watches the live video.

[0081] Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the electronic device.

[0082] like Figure 4 As shown, the electronic device may include: a processor (processor) 402 , a communication interface (Communications Interface) 404 , a memory (memory) 406 , and a communication bus 408 .

[0083] The processor 402, the communication interface 404, and the memory 406 communicate with each other via the communication bus 408. The communication interface 404 is used to communicate with other devices such as a client or other server network elements. The processor 402 is used to execute the program 410, which can specifically execute the relevant steps in the above-mentioned embodiment of the method for generating a live screen.

[0084] Specifically, the program 410 may include program code including computer executable instructions.

[0085] The processor 402 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the electronic device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0086] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0087] Program 410 can be specifically called by processor 402 to enable the electronic device to perform the following operations:

[0088] Get the current sports picture including the target athlete;

[0089] Determine the position and head rotation angle of the target athlete in the current motion picture;

[0090] Determining the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture;

[0091] According to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a live broadcast picture simulating the first-person viewing angle of the target athlete is generated.

[0092] In an optional manner, the current motion picture includes a first current motion picture and a second current motion picture, and the first current motion picture and the second current motion picture are motion pictures collected based on different viewing angles.

[0093] In an optional manner, the program 410 may be specifically called by the processor 402 to enable the electronic device to perform the following operations:

[0094] Identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture;

[0095] inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively;

[0096] The head rotation angle of the target athlete in the current motion picture is determined according to the preset rotation angle recognition model.

[0097] In an optional manner, the program 410 may be specifically called by the processor 402 to enable the electronic device to perform the following operations:

[0098] Before respectively inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model, a plurality of sample images of the target athlete's head at different rotation angles in three-dimensional space are obtained; the rotation angle of each sample image is determined; and the preset rotation angle recognition model is generated according to the plurality of sample images and the rotation angle of each sample image.

[0099] In an optional manner, the program 410 may be specifically called by the processor 402 to enable the electronic device to perform the following operations:

[0100] determining the height of the target athlete according to the position of the target athlete in the first current motion picture;

[0101] The camera is controlled to capture the second current motion picture based on the height of the target athlete.

[0102] In an optional manner, the head rotation angle includes a first rotation angle, a second rotation angle, and a third rotation angle, wherein the first rotation angle, the second rotation angle, and the third rotation angle are respectively rotation angles of the target athlete's head in different dimensions of the three-dimensional space; the program 410 can be specifically called by the processor 402 to enable the electronic device to perform the following operations:

[0103] Identify the first current motion picture by using the preset rotation angle identification model to determine the first rotation angle and the second rotation angle;

[0104] The second current motion picture is identified by using the preset rotation angle identification model to determine the third rotation angle.

[0105] In an embodiment of the present invention, during the movement of the target athlete, the target athlete is photographed to obtain a current movement picture containing the target athlete; the position of the target athlete in the current movement picture and the head rotation angle can be determined by performing image recognition on the current movement picture; the position and viewing angle of the target athlete in the three-dimensional panoramic picture can be further determined based on the position and viewing angle of the head of the target athlete in the current movement picture; and a live broadcast picture simulating the first-person perspective of the target athlete can be generated based on the position and viewing angle of the target athlete in the three-dimensional panoramic picture. In the above-mentioned implementation manner, a live broadcast picture simulating the first-person perspective of the target athlete can be generated by including the current movement picture of the target athlete, thereby improving the user experience when the user watches the live video.

[0106] An embodiment of the present invention provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is executed on an electronic device, the electronic device executes the live screen generation method in any of the above method embodiments.

[0107] An embodiment of the present invention provides a live broadcast screen generation device, which is used to execute the live broadcast screen generation method.

[0108] An embodiment of the present invention provides a computer program, which can be called by a processor to enable an electronic device to execute the live screen generation method in any of the above method embodiments.

[0109] An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are run on a computer, the computer executes the live screen generation method in any of the above method embodiments.

[0110] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other equipment. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description made to specific languages ​​above is for disclosing the best mode of the present invention.

[0111] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0112] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than those expressly recited in each claim.

[0113] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0114] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for generating a live broadcast screen, characterized in that: The method comprises: Acquire a current motion picture including a target athlete; the current motion picture includes a first current motion picture and a second current motion picture, wherein the first current motion picture and the second current motion picture are motion pictures acquired based on different viewing angles; wherein the first current motion picture is acquired by a side camera, and the second current motion picture can be acquired by a front camera, and when the second current motion picture is acquired by the front camera, the height of the target athlete is determined according to the position of the target athlete in the first current motion picture, and the front camera is controlled to acquire the second current motion picture at the height of the target athlete; Determine the position and head rotation angle of the target athlete in the current motion picture; the determining the position and head rotation angle of the target athlete in the current motion picture comprises: identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture; inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively; determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model; the preset rotation angle recognition model is, for example, a recognition model based on a SIFT algorithm; Determining the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture; According to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a live broadcast picture simulating the first-person viewing angle of the target athlete is generated.

2. The method according to claim 1, characterized in that: Before inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively, the method further includes: Acquire a plurality of sample images of the target athlete's head at different rotation angles in three-dimensional space; Determine the rotation angle of each sample image; The preset rotation angle recognition model is generated according to the multiple sample images and the rotation angle of each sample image.

3. The method according to any one of claims 1 to 2, characterized in that: The method further comprises: determining the height of the target athlete according to the position of the target athlete in the first current motion picture; The camera is controlled to capture the second current motion picture based on the height of the target athlete.

4. The method according to claim 1 or 2, characterized in that: The head rotation angle includes a first rotation angle, a second rotation angle and a third rotation angle, wherein the first rotation angle, the second rotation angle and the third rotation angle are respectively rotation angles of the target athlete's head in different dimensions of the three-dimensional space; Determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model comprises: Identify the first current motion picture by using the preset rotation angle identification model to determine the first rotation angle and the second rotation angle; The second current motion picture is identified by using the preset rotation angle identification model to determine the third rotation angle.

5. A live broadcast screen generation system, characterized in that: The system comprises: a server and a camera; the server is used for: Acquire a current motion picture including a target athlete captured by the camera; the current motion picture includes a first current motion picture and a second current motion picture, wherein the first current motion picture and the second current motion picture are motion pictures captured based on different viewing angles; wherein the first current motion picture is captured by a side camera, and the second current motion picture can be captured by a front camera, and when the second current motion picture is captured by the front camera, the height of the target athlete is determined according to the position of the target athlete in the first current motion picture, and the front camera is controlled to capture the second current motion picture at the height of the target athlete; Determine the position and head rotation angle of the target athlete in the current motion picture; the determining the position and head rotation angle of the target athlete in the current motion picture comprises: identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture; inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively; determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model; the preset rotation angle recognition model is, for example, a recognition model based on a SIFT algorithm; Determining the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture; According to the position and viewing angle of the target athlete in the three-dimensional panoramic picture, a live broadcast picture simulating the first-person viewing angle of the target athlete is generated.

6. A live broadcast screen generation device, characterized in that: The device comprises: An acquisition module is used to acquire a current motion picture including a target athlete; the current motion picture includes a first current motion picture and a second current motion picture, wherein the first current motion picture and the second current motion picture are motion pictures acquired based on different viewing angles; wherein the first current motion picture is acquired by a side camera, and the second current motion picture can be acquired by a front camera, and when the second current motion picture is acquired by the front camera, the height of the target athlete is determined according to the position of the target athlete in the first current motion picture, and the front camera is controlled to acquire the second current motion picture at the height of the target athlete; A first determination module is used to determine the position and head rotation angle of the target athlete in the current motion picture; the determination of the position and head rotation angle of the target athlete in the current motion picture includes: identifying the first current motion picture to determine the position of the target athlete in the first current motion picture, and determining the position of the target athlete in the first current motion picture as the position of the target athlete in the current motion picture; inputting the first current motion picture and the second current motion picture into a preset rotation angle recognition model respectively; determining the head rotation angle of the target athlete in the current motion picture according to the preset rotation angle recognition model; the preset rotation angle recognition model is an example of a recognition model based on a SIFT algorithm; A second determination module is used to determine the position and viewing angle of the target athlete in the three-dimensional panoramic picture according to the position and head rotation angle of the target athlete in the current sports picture; The generation module is used to generate a live broadcast picture simulating the first-person perspective of the target athlete according to the position and perspective of the target athlete in the three-dimensional panoramic picture.

7. An electronic device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the live broadcast image generation method as described in any one of claims 1-4.

8. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction. When the executable instruction is executed on the electronic device, the electronic device executes the operation of the live screen generation method as described in any one of claims 1 to 4.

Images