Method and device for generating live broadcast images of competition players

Abstract

The present application discloses a method and device for generating a live broadcast screen of a match that follows a contestant. The method determines a first contestant corresponding to a target contestant according to target Beidou positioning; determines a target viewing angle according to a positional relationship between the target contestant and the first contestant; and determines a target live broadcast screen according to the target viewing angle and target Beidou positioning. Since a virtual target viewing angle is determined according to a positional relationship between a target contestant and a first contestant corresponding to the target contestant, a target live broadcast screen showing the on-site situation of the target contestant is determined according to the target viewing angle and target Beidou positioning. Thus, compared to the prior art that presents the situation of the event site through a field map and a contestant positioning icon, the present application can simulate a live broadcast screen with characters and an environment that directly presents the on-site situation with a contestant as the core shooting target using a target viewing angle, thereby improving the live broadcast effect and the audience's viewing experience.

Description

Technical Field

[0001] The present application relates to the technical field of information processing, and particularly relates to a method and device for generating a live broadcast image of a competition that follows a competition player. Background Art

[0002] Currently, there are problems of lack of coverage or unstable network signals in the areas involved in many outdoor competition activities. In the prior art, when there is stable coverage of conventional network signals, the images obtained by the network cameras arranged at the competition venue are used as the live broadcast images. When there is no stable coverage of conventional network signals, the competition venue map and the player positioning icons are used as the live broadcast images. However, when the audience wants to only view the on-site situation of a single participating player, in the area with stable coverage of conventional network signals, due to the limited number of cameras arranged in the wild, it is impossible to take pictures with the participating player as the core shooting target throughout the process. In the area without stable coverage of conventional network signals, the competition venue map and the player positioning icons are even less able to enable the audience to see the on-site situation of the participating player, resulting in poor live broadcast effects and a bad viewing experience for the audience. Summary of the Invention

[0003] The present application proposes a method and device for generating a live broadcast image of a competition that follows a competition player to solve the problem of poor viewing experience for the audience caused by the inability to take pictures with the participating player as the core shooting target throughout the process, and to improve the live broadcast effect and the viewing experience of the audience.

[0004] In a first aspect, an embodiment of the present application provides a method for generating a live broadcast image of a competition that follows a competition player, which is applied to a server of a competition live broadcast system. The method includes:

[0005] Determine a first competition player corresponding to the target competition player according to the target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competition player, and the first competition player is a competition player participating in the same competition event whose distance from the target competition player is within a preset target range;

[0006] Determine a target viewing angle according to the positional relationship between the target competition player and the first competition player, where the target viewing angle is a virtual viewing angle with the target competition player as the core shooting target;

[0007] Determine a target live broadcast image according to the target viewing angle and the target Beidou positioning, where the target live broadcast image is used to represent the on-site situation of the target competition player at the target Beidou position.

[0008] In a second aspect, an embodiment of the present application provides a device for generating a live broadcast image of a competition that follows a competition player, which is applied to a server of a competition live broadcast system. The device includes:

[0009] The first processing unit is configured to determine a first competing athlete corresponding to the target competing athlete according to the target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competing athlete, and the first competing athlete is a competing athlete who participates in the same competition event and whose distance from the target competing athlete is within a preset target range; determine a target perspective according to the positional relationship between the target competing athlete and the first competing athlete, where the target perspective is a virtual perspective with the target competing athlete as the core shooting target.

[0010] The second processing unit is configured to determine a target live broadcast image according to the target perspective and the target Beidou positioning, where the target live broadcast image is used to represent the on-site situation of the target competing athlete at the target Beidou position.

[0011] In a third aspect, an embodiment of the present application provides a server, including a processor, a memory, and one or more programs, where the one or more programs are stored in the memory and are configured to be executed by the processor, and the programs include instructions for performing the steps in the method according to any one of the first aspects.

[0012] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer programs / instructions are stored, and when the computer programs / instructions are executed by a processor, the steps of the method according to any one of the first aspects are implemented.

[0013] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer programs / instructions, and when the computer programs / instructions are executed by a processor, some or all of the steps of the method according to any one of the first aspects of the embodiments of the present application are implemented.

[0014] It can be seen that in this application, the server determines the first competing athlete corresponding to the target competing athlete according to the target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competing athlete, and the first competing athlete is a competing athlete participating in the same competition event whose distance from the target competing athlete is within a preset target range; determines the target perspective according to the positional relationship between the target competing athlete and the first competing athlete, where the target perspective is a virtual perspective centered on the target competing athlete for shooting the target; determines the target live broadcast image according to the target perspective and the target Beidou positioning, and the target live broadcast image is used to represent the on-site situation of the target competing athlete at the target Beidou position. Since the virtual target perspective is determined according to the positional relationship between the target competing athlete and the first competing athlete corresponding to the target competing athlete, and then the target live broadcast image representing the on-site situation of the target competing athlete is determined according to the target perspective and the target Beidou positioning. Thus, compared with the prior art of presenting the event site through the stadium map and athlete positioning icons, this application can simulate a live broadcast image that directly presents the on-site situation with a person and the environment centered on the participating athlete for shooting from the target perspective, thereby improving the live broadcast effect and the viewing experience of the audience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a schematic structural diagram of a sports event live broadcast system provided by an embodiment of the present application;

[0017] Figure 2 It is a schematic structural diagram of a server in a sports event live broadcast system provided by an embodiment of the present application;

[0018] Figure 3 It is a schematic flowchart of a method for generating a live broadcast image of following a competing athlete in a sports event provided by an embodiment of the present application;

[0019] Figure 4 It is a schematic diagram of a scene of a method for generating a live broadcast image of following a competing athlete in a sports event provided by an embodiment of the present application;

[0020] Figure 5 It is a block diagram of the functional units of a device for generating a live broadcast image of following a competing athlete in a sports event provided by an embodiment of the present application;

[0021] Figure 6It is a functional unit composition block diagram of another live event broadcast screen generation device for following a competition player provided by an embodiment of the present application;

[0022] Figure 7 It is a structural block diagram of a server provided by an embodiment of the present application. Specific embodiments

[0023] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present application.

[0024] Terms such as "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0025] Referring to "embodiment" in this article means that a specific feature, structure or characteristic described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0026] The "and / or" in the embodiments of the present application describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist simultaneously; B exists alone. Among them, A and B can be singular or plural.

[0027] In the embodiments of the present application, the symbol " / " can represent that the associated objects before and after are an "or" relationship. In addition, the symbol " / " can also represent a division sign, that is, perform a division operation. For example, A / B can represent A divided by B.

[0028] The "at least one (piece)" or its similar expression in the embodiments of the present application refers to any combination of these items, including any combination of a single item (piece) or plural items (pieces), meaning one or more, and "more than one" means two or more. For example, at least one (piece) of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0029] In the embodiments of the present application, "equal to" can be used in combination with "greater than" and is applicable to the technical solutions adopted when it is greater than, or can also be used in combination with "less than" and is applicable to the technical solutions adopted when it is less than. When "equal to" is used in combination with "greater than", it is not used in combination with "less than"; when "equal to" is used in combination with "less than", it is not used in combination with "greater than".

[0030] To better understand the solutions of the embodiments of the present application, the terminal devices, related concepts, and background that may be involved in the embodiments of the present application will be introduced below.

[0031] Beidou positioning: The receiver in a terminal device capable of Beidou satellite positioning can continuously capture and receive navigation signals from Beidou satellites. These signals contain the orbital parameters of the satellites, time information, and necessary navigation messages. By processing and calculating these signals, a high-precision positioning function can be achieved.

[0032] In many outdoor event areas, there are problems of no conventional network signal coverage or unstable network signals. In the prior art, when there is stable coverage of conventional network signals, the pictures obtained by the network cameras arranged at the competition venue are used as the live broadcast pictures. When there is no stable coverage of conventional network signals, the competition venue map and the player positioning icons are used as the live broadcast pictures. However, when the audience wants to only watch the live situation of a single participating player, in the area with stable coverage of conventional network signals, due to the limited number of cameras arranged in the wild, it is impossible to take pictures with this participating player as the core shooting target throughout the process. In the area without stable coverage of conventional network signals, the competition venue map and the player positioning icons cannot enable the audience to see the live situation of this participating player, resulting in poor live broadcast effects and a poor viewing experience for the audience.

[0033] To solve the above problems, an embodiment of the present application provides a method and device for generating a live broadcast image of a competition following a contestant. The method determines a virtual target perspective based on the position relationship between the target contestant and the first contestant corresponding to the target contestant before, and thus determines a target live broadcast image representing the on-site situation of the target contestant according to the target perspective and the target Beidou positioning. In this way, compared with the prior art of presenting the on-site situation of the competition through a stadium map and a contestant positioning icon, the present application can simulate a live broadcast image with a target perspective that directly presents the on-site situation, including people and the environment, and takes the participating contestant as the core shooting target, thereby improving the live broadcast effect and the viewing experience of the audience.

[0034] Please refer to Figure 1 , Figure 1 which is a schematic structural diagram of a live broadcast system for a competition provided by an embodiment of the present application. As Figure 1 shown, the live broadcast system 100 includes a terminal device 110 and a server 120. The terminal device 110 is communicatively connected to the server 120. The server 120 can be a single server or a server group composed of multiple servers. The terminal device 110 can be a mobile phone terminal, a Beidou satellite watch, a Beidou box, etc.

[0035] In the daily use of the live broadcast system 100, the server 120 determines the first contestant corresponding to the target contestant according to the target Beidou positioning. The target Beidou positioning is used to indicate the current position of the target contestant. The first contestant is a contestant participating in the same competition event whose distance from the target contestant is within a preset target range; determines the target perspective according to the position relationship between the target contestant and the first contestant. The target perspective is a virtual perspective with the target contestant as the core shooting target; determines the target live broadcast image according to the target perspective and the target Beidou positioning. The target live broadcast image is used to represent the on-site situation of the target contestant at the target Beidou position.

[0036] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a server in a live broadcast system for a competition provided by an embodiment of the present application. As Figure 3As shown, the server 120 includes a processor 210 and a memory 220, and the processor 210 is communicatively connected to the memory 220. Among them, one or more programs are stored in the memory 220, and the one or more programs are configured to be executed by the processor 210. The function of the one or more programs is to determine a first competing athlete corresponding to the target competing athlete according to the target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competing athlete, and the first competing athlete is a competing athlete participating in the same competition event whose distance from the target competing athlete is within a preset target range; determine a target viewing angle according to the positional relationship between the target competing athlete and the first competing athlete, where the target viewing angle is a virtual viewing angle for shooting a target with the target competing athlete as the core; determine a target live broadcast image according to the target viewing angle and the target Beidou positioning, where the target live broadcast image is used to represent the on-site situation of the target competing athlete at the target Beidou position.

[0037] The following introduces a method for generating a live broadcast image of a competition event that follows a competing athlete provided by an embodiment of the present application.

[0038] Please refer to Figure 3 , Figure 3 which is a flowchart of a method for generating a live broadcast image of a competition event that follows a competing athlete provided by an embodiment of the present application, and is applied to the server 120 in a competition live broadcast system 100 as shown in Figure 1 The competition live broadcast system 100 includes a terminal device 110 and a server 120. The terminal device 110 is communicatively connected to the server 120. The server 120 can be a single server or a server group composed of multiple servers. The terminal device 110 can be a mobile phone terminal, a Beidou satellite watch, a Beidou box, etc.; as shown in Figure 3 The method includes the following steps:

[0039] Step S301, determine a first competing athlete corresponding to the target competing athlete according to the target Beidou positioning.

[0040] Among them, the target Beidou positioning is used to indicate the current position of the target competing athlete, and the first competing athlete is a competing athlete participating in the same competition event whose distance from the target competing athlete is within a preset target range.

[0041] Among them, the target Beidou positioning is captured by the terminal device 110 and the navigation signal received from the Beidou satellite is processed and calculated. The terminal device 110 forwards the target Beidou positioning to the server 120 through the Beidou short message function via the Beidou satellite.

[0042] Step S302, determine a target viewing angle according to the positional relationship between the target competing athlete and the first competing athlete.

[0043] Among them, the target perspective is a virtual perspective with the target competition player as the core shooting target.

[0044] In a possible embodiment, the determining the target perspective according to the positional relationship between the target competition player and the first competition player includes: obtaining the target digital human corresponding to the target competition player and the first digital human corresponding to the first competition player, where the target digital human is used to represent the image of the target competition player when performing the competition event, and the first digital human is used to represent the image of the first competition player when performing the competition event; determining the target placement position of the target digital human and the first placement position of the first digital human according to the positional relationship between the target competition player and the first competition player; determining a plurality of first perspectives with the target competition player as the shooting target, and each first perspective in the plurality of first perspectives has the target competition player as the shooting center; determining the target perspective from the plurality of first perspectives according to the target placement position and the first placement position.

[0045] Among them, the method for determining the target digital human includes the following steps: obtaining a preset initial digital human and the pre-stored image data of the target competition player, where the pre-stored image data is used to represent the personal image of the target competition player; updating the initial digital human according to the pre-stored image data to obtain the target digital human.

[0046] Among them, the pre-stored image data is determined according to the pre-collected image or image video of the target competition player, and specifically, it can be obtained by performing image recognition and information extraction on the image or image video of the target competition player.

[0047] Among them, the updating the initial digital human according to the pre-stored image data to obtain the target digital human specifically can be modifying the texture data of the initial digital human according to the pre-stored image data.

[0048] Among them, the method for determining the first digital human is the same as the method for determining the target digital human.

[0049] It can be seen that, in this example, the positional relationship between the corresponding target digital human and the first digital human is determined according to the positional relationship between the target competition player and the first competition player. Then, the target perspective is determined from multiple first perspectives with the target competition player as the shooting center based on the positional relationship between the target digital human and the first digital human. Subsequently, the target live broadcast screen showing the on-site situation of the target competition player is determined according to the target perspective and the target Beidou positioning. In this way, compared with the prior art of presenting the on-site situation of the event through the stadium map and the player positioning icons, the present application can simulate a live broadcast screen that directly presents the on-site situation with people and the environment and takes the participating player as the core shooting target from the target perspective, thereby improving the live broadcast effect and the viewing experience of the audience.

[0050] In a possible embodiment, the determining the target perspective from the multiple first perspectives according to the target placement position and the first placement position includes: determining the occlusion rate corresponding to each first perspective according to the target placement position and the first placement position, where the occlusion rate is used to indicate the occlusion situation of the first competition player to the target competition player in the corresponding first perspective; and determining the target perspective from the multiple first perspectives according to the occlusion rate corresponding to each first perspective.

[0051] Among them, the determining the occlusion rate corresponding to each first perspective according to the target placement position and the first placement position, for example, may be: in the picture obtained from the first perspective X, the first digital human at the first placement position occludes 60% of the surface area of the target digital human at the target placement position, then the occlusion rate corresponding to the first perspective X is 60%.

[0052] Among them, the determining the target perspective from the multiple first perspectives according to the occlusion rate corresponding to each first perspective may specifically be: determining the first perspective with the smallest corresponding occlusion rate among the multiple first perspectives as the target perspective.

[0053] It can be seen that, in this example, the occlusion rate of each first perspective is determined according to the target placement position and the first placement position. Then, the target perspective is determined from the multiple first perspectives according to the occlusion rate of each first perspective. Subsequently, the target live broadcast screen showing the on-site situation of the target competition player is determined according to the target perspective and the target Beidou positioning. In this way, compared with the prior art of presenting the on-site situation of the event through the stadium map and the player positioning icons, the present application can simulate a live broadcast screen that directly presents the on-site situation with people and the environment and takes the participating player as the core shooting target from the target perspective, thereby improving the live broadcast effect and the viewing experience of the audience.

[0054] In a possible embodiment, determining the target perspective from the multiple first perspectives according to the occlusion rate corresponding to each first perspective includes: determining the front camera entry rate of the person corresponding to each first perspective, where the front camera entry rate of the person is used to characterize the entry situation of the front of the target competition player in the corresponding first perspective; determining the first perspectives among the multiple first perspectives where the corresponding front camera entry rate of the person is greater than a target threshold as second perspectives, obtaining at least one second perspective; and determining the second perspective with the lowest corresponding occlusion rate among the at least one second perspective as the target perspective.

[0055] Among them, determining the front camera entry rate of the person corresponding to each first perspective is obtained by performing human face recognition on the images acquired from each first perspective. For example, in the image acquired from the first perspective X, if 75% of the front of the target is in the camera, then the front camera entry rate of the person corresponding to the first perspective X is 75%.

[0056] Among them, please refer to Figure 4 , Figure 4 is a schematic diagram of the scene of a method for generating a live broadcast image of following a competition player provided by an embodiment of the present application. As Figure 4 shown, the first competition player 402 is on the right side of the target competition player 401. The front camera entry rate corresponding to the first perspective 411 among the multiple first perspectives 410 is 75%, and the occlusion rate is 0%.

[0057] It can be seen that in this example, by determining the front camera entry rate of the person corresponding to each first perspective and then screening according to the front camera entry rate of the person and the occlusion rate, the quality of the target live broadcast image is further improved. In this way, compared with the prior art where the competition site is presented through a stadium map and player positioning icons, the present application can simulate a live broadcast image with a person and an environment directly presenting the on-site situation with the participating player as the core shooting target from the target perspective, thereby improving the live broadcast effect and the viewing experience of the audience.

[0058] Step S303, determining the target live broadcast image according to the target perspective and the target Beidou positioning.

[0059] Among them, the target live broadcast image is used to characterize the on-site situation of the target competition player at the target Beidou position.

[0060] In a possible embodiment, determining the target live broadcast image according to the target perspective and the target Beidou positioning includes: determining a target environmental image according to the target Beidou positioning and a geographical environment library, where the geographical environment library is used to indicate the geographical environment along the event route corresponding to the target competition player, and the target environmental image is used to represent the geographical environment corresponding to the target Beidou positioning; obtaining the target motion data of the target competition player and the first motion data of the first competition player, where the target motion data is used to represent the current body motion condition of the target competition player, and the first motion data is used to represent the current body motion condition of the first competition player; determining a target motion image according to the target motion data and the target digital human, where the target motion image is used to represent the motion image of the target competition player when the body motion condition is the target motion data; determining a first motion image according to the first motion data and the first digital human, where the first motion image is used to represent the motion image of the first competition player when the body motion condition is the first motion data; determining the target live broadcast image according to the target environmental image, the target motion image, the first motion image, and the target perspective.

[0061] Among them, the geographical environment library is pre-constructed, and the construction process of the geographical environment library includes the following steps: determining a plurality of collection points according to the event route; determining the collection Beidou positioning corresponding to each collection point among the plurality of collection points, where the collection Beidou positioning is used to indicate the position of the corresponding collection point; obtaining a plurality of collection tasks according to the collection tasks corresponding to the collection Beidou positioning corresponding to each collection point; sending the plurality of collection tasks to the route scanning subsystem so that the route scanning subsystem sends a plurality of environmental slice alignment data groups to the server; receiving the plurality of environmental slice alignment data groups; constructing the geographical environment library corresponding to the event route according to the plurality of environmental slice alignment data groups.

[0062] Among them, the route scanning subsystem includes a management terminal, a route scanning device, and a Beidou positioning terminal. The management terminal is communicatively connected to the route scanning device and the Beidou positioning terminal. The route scanning device is communicatively connected to the Beidou positioning terminal. The Beidou positioning terminal is used to determine the target Beidou positioning. The management terminal in the route scanning subsystem receives the multiple collection tasks and performs the following operations for the multiple collection tasks: when it is detected by the Beidou positioning terminal that the target Beidou positioning is the collection Beidou positioning corresponding to the currently processed collection task, the route scanning device is used to perform image collection on the position indicated by the target Beidou positioning to obtain environmental image slices; the environmental image slices are aligned with the target Beidou positioning to obtain an environmental slice alignment data group, completing the currently processed collection task, and then performing the next collection task; repeating the above steps until all the multiple collection tasks are completed to obtain multiple environmental slice alignment data groups; and sending the multiple environmental slice alignment data groups to the server.

[0063] Among them, for the event route, the software system provides a route scanning function. The administrator of the event organizer can log in to the administrator account through the management terminal, such as a mobile phone, and enter the function interface through the event APP. The function interface is provided with a "route scanning function". When this function is enabled, a Beidou positioning terminal binding interface pops up on the mobile phone, requesting to bind a Beidou positioning terminal. After the device binding is completed, it continues to jump to the route scanning device binding interface, requesting to bind a route scanning device for this route scanning event. The route scanning device can be, for example, a camera, etc. After the binding operation is completed, the mobile phone reminds the administrator to complete the multiple collection tasks. For the currently processed collection task, the mobile phone prompts the administrator through the visual interface to use the route scanning device to perform image collection at the position indicated by the collection Beidou positioning corresponding to the currently processed collection task. After the administrator completes the image collection, the mobile phone aligns the collected environmental image slices with the target Beidou positioning for collecting the environmental image slices to obtain the environmental slice alignment data group for the currently processed collection task, and thus repeats this process to obtain multiple environmental slice alignment data groups.

[0064] Among them, after the management terminal completes the multiple collection tasks, it can return to an area covered by a regular network. On the mobile phone APP side, click to complete the collection and upload all the recorded videos, and upload the multiple environmental slice alignment data groups to the server through a regular network, such as a wifi network.

[0065] Among them, in the geographical environment library, each Beidou positioning corresponds to at least one environmental image slice. According to the at least one environmental image slice, scene modeling is performed to obtain the basic environmental image corresponding to each Beidou positioning.

[0066] Wherein, determining the target motion image based on the target motion data and the target digital human includes: obtaining the historical motion data of the target contestant, the historical motion data is used to characterize the physical motion conditions of the target contestant in the past when performing the target event; determining the historical motion data as training data to obtain a target digital twin model; previewing the target digital twin model according to target meteorological information and route status information to obtain the target motion state of the target contestant when the physical motion condition is the target motion data; determining the target motion image based on the target motion state and the target digital human. Wherein, the target meteorological information includes weather conditions, temperature, precipitation, etc., and the weather conditions include sunny days, rainy days, cloudy days, rain turning to sunny days, etc. The route status information includes road flatness, road dryness and wetness, road visibility, etc.

[0067] Wherein, the target motion data includes the motion duration of the target contestant, etc.

[0068] Wherein, the target motion data is recorded by the terminal device 110 during the game and forwarded to the server 120 via the Beidou satellite through the Beidou short message function.

[0069] Wherein, the target digital twin model refers to the model object that provides decision support for the entity object in the digital space during the digital twin process.

[0070] Wherein, determining the historical motion data as training data to obtain a target digital twin model includes: obtaining a preset initial digital twin model; determining the historical motion data as training data, performing incremental learning on the initial digital twin model, and obtaining the target digital twin model.

[0071] Wherein, determining the historical motion data as training data, performing incremental learning on the initial digital twin model, and obtaining the target digital twin model includes: opening a target thread, and using the historical motion data in the target thread to train the initial digital twin model based on an incremental learning method.

[0072] Wherein, the target digital twin model is previewed according to the target meteorological information and route status information to obtain the target motion state of the target contestant when the physical motion condition is the target motion data, including: obtaining the preview result of the target digital twin model; constructing a motion state dynamic change model corresponding to the target digital twin model according to the preview result; and determining the target motion state according to the target motion data and the motion state dynamic change model.

[0073] Among them, the rehearsal result is a plurality of target digital twin models corresponding one by one to multiple stages of the target project.

[0074] Among them, constructing the dynamic change model of the motion state corresponding to the target digital twin model according to the rehearsal result includes: combining the plurality of target digital twin models according to the time sequence to obtain the dynamic change model of the motion state.

[0075] Among them, determining the target motion state according to the target motion data and the dynamic change model of the motion state, for example, can be to input the motion duration in the target motion data, such as 6 hours, into the dynamic change model of the motion state, and the dynamic change model of the motion state outputs the calculated motion state of the target user continuously exercising for 6 hours, such as a breathing rate of 25 times per minute, a heart rate of 140 times per minute, a sweating volume of 1000 ml, and a physical state of being relatively tired.

[0076] Among them, the step of determining the first motion image according to the first motion data and the first digital human is the same as the above step of determining the target motion image according to the target motion data and the target digital human, that is, obtaining the first motion state through the first digital twin model corresponding to the first competition player, and thus obtaining the first motion image, which will not be elaborated here.

[0077] Among them, determining the target live broadcast screen according to the target environment image, the target motion image, the first motion image and the target perspective, for example, can be to input the target environment image, the target motion image, the first motion image and the target perspective into a preset generative AI model to obtain the target live broadcast screen.

[0078] It can be seen that in this example, the target environment image is determined according to the target Beidou positioning and the geographical environment library, and then the target motion image of the target competition player is determined according to the target motion data and the target digital human, and the first motion image is determined according to the first motion data and the first digital human. Thus, the target live broadcast screen is determined according to the target environment image, the target motion image, the first motion image and the target perspective. In this way, compared with the situation of presenting the event site through the stadium map and the player positioning icon in the prior art, the present application can simulate a live broadcast screen with a target perspective that directly presents the on-site situation, including people and the environment, and takes the participating players as the core shooting target, thereby improving the live broadcast effect and the viewing experience of the audience.

[0079] In a possible embodiment, determining the target live broadcast screen according to the target environment image, the target motion image, the first motion image, and the target viewing angle includes: placing the target motion image and the first motion image in the target environment image to obtain a target on-site image; capturing an image of the target digital human in the target on-site image according to the target viewing angle to obtain the target live broadcast screen.

[0080] Among them, the target environment image is obtained through 3D stereoscopic modeling. The target motion image is the target digital human presenting the target motion state, and the first motion image is the first digital human presenting the first motion state.

[0081] It can be seen that in this example, the target motion image and the first motion image are placed in the target environment image to obtain a target on-site image, and then an image of the target digital human in the target on-site image is captured according to the target viewing angle to obtain the target live broadcast screen. In this way, compared with the situation of presenting the event site through the stadium map and the player positioning icon in the prior art, the present application can simulate a live broadcast screen with the participating players as the core shooting target that directly presents the on-site situation including people and the environment from the target viewing angle, thereby improving the live broadcast effect and the viewing experience of the audience.

[0082] In a possible embodiment, determining the target environment image according to the target Beidou positioning and the geographical environment database includes: querying the geographical environment database according to the target Beidou positioning to determine the basic environment image corresponding to the target Beidou position; determining the on-site environment information corresponding to the target Beidou positioning, where the on-site environment information is used to indicate the on-site environment situation of the current position of the target competition player; determining the target environment image according to the on-site environment information and the basic environment image.

[0083] Among them, the on-site environment information includes target meteorological information, and the target meteorological information is used to indicate the weather condition of the current position of the target competition player. Determining the target environment image according to the on-site environment information and the basic environment image includes: determining a target weather effect and a target light effect according to the target meteorological information; determining the target environment image according to the target weather effect, the target light effect, and the basic environment image.

[0084] Among them, the target meteorological information includes weather condition, temperature, precipitation, etc., and the weather condition includes sunny, rainy, cloudy, rain turning to sunny, etc.

[0085] Among them, the target weather effect and the target light effect are both special scene effects corresponding to the target weather information. For example, when the target weather information includes light rain, the target weather effect is light rain, and the target light effect is that the light is relatively dim.

[0086] Among them, determining the target environmental image according to the target weather effect, the target light effect, and the basic environmental image means correcting the original weather effect and light effect in the basic environmental image according to the target weather effect and the target light effect.

[0087] It can be seen that in this example, the selected basic environment is corrected according to the on-site environmental information corresponding to the target Beidou positioning, so as to determine the target environmental image, and then, based on this and according to the target perspective, the target live broadcast screen showing the on-site situation of the target competition player is determined. In this way, compared with the situation of presenting the event site through the stadium map and the player positioning icon in the prior art, the present application can simulate a live broadcast screen with a target perspective that directly presents the on-site situation, including people and the environment, with the participating player as the core shooting target, thereby improving the live broadcast effect and the viewing experience of the audience.

[0088] It can be seen that in the present application, the server determines the first competition player corresponding to the target competition player according to the target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competition player, and the first competition player is a competition player participating in the same competition event whose distance from the target competition player is within a preset target range; determines the target perspective according to the positional relationship between the target competition player and the first competition player, where the target perspective is a virtual perspective with the target competition player as the core shooting target; and determines the target live broadcast screen according to the target perspective and the target Beidou positioning, where the target live broadcast screen is used to represent the on-site situation of the target competition player at the target Beidou position. Since the virtual target perspective is determined according to the positional relationship between the target competition player and the first competition player corresponding to the target competition player, and then the target live broadcast screen showing the on-site situation of the target competition player is determined according to the target perspective and the target Beidou positioning. In this way, compared with the situation of presenting the event site through the stadium map and the player positioning icon in the prior art, the present application can simulate a live broadcast screen with a target perspective that directly presents the on-site situation, including people and the environment, with the participating player as the core shooting target, thereby improving the live broadcast effect and the viewing experience of the audience.

[0089] The above mainly introduced the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that in order for the controller to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments provided in this article, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0090] Consistent with the embodiments shown above, please refer to Figure 5 , Figure 5 which is a block diagram of the functional units of a live event video generation device for tracking competition players provided by an embodiment of the present application. As Figure 5 shown, the live event video generation device 500 for tracking competition players includes: a first processing unit 501, configured to determine a first competition player corresponding to the target competition player according to a target Beidou positioning, where the target Beidou positioning is used to indicate the current position of the target competition player, and the first competition player is a competition player participating in the same competition event whose distance from the target competition player is within a preset target range; determine a target viewing angle according to the positional relationship between the target competition player and the first competition player, where the target viewing angle is a virtual viewing angle with the target competition player as the shooting target; a second processing unit 502, configured to determine a target live video according to the target viewing angle and the target Beidou positioning, where the target live video is used to represent the on-site situation of the target competition player at the target Beidou position.

[0091] In a possible embodiment, in terms of determining the target viewing angle according to the positional relationship between the target competition player and the first competition player, the first processing unit 501 is specifically configured to: obtain a target digital human corresponding to the target competition player and a first digital human corresponding to the first competition player, where the target digital human is used to represent the image of the target competition player when performing the competition event, and the first digital human is used to represent the image of the first competition player when performing the competition event; determine a target placement position of the target digital human and a first placement position of the first digital human according to the positional relationship between the target competition player and the first competition player; determine a plurality of first viewing angles with the target competition player as the shooting target, where each first viewing angle in the plurality of first viewing angles has the target competition player as the shooting center; determine the target viewing angle from the plurality of first viewing angles according to the target placement position and the first placement position.

[0092] In a possible embodiment, in terms of determining the target viewing angle from the multiple first viewing angles according to the target placement position and the first placement position, the first processing unit 501 is specifically configured to: determine the occlusion rate corresponding to each first viewing angle according to the target placement position and the first placement position, where the occlusion rate is used to indicate the occlusion situation of the first contestant to the target contestant in the corresponding first viewing angle; determine the target viewing angle from the multiple first viewing angles according to the occlusion rate corresponding to each first viewing angle.

[0093] In a possible embodiment, in terms of determining the target viewing angle from the multiple first viewing angles according to the occlusion rate corresponding to each first viewing angle, the first processing unit 501 is specifically configured to: determine the front-facing entry rate of the person corresponding to each first viewing angle, where the front-facing entry rate of the person is used to characterize the entry situation of the front of the target contestant in the corresponding first viewing angle; determine the first viewing angles with the front-facing entry rate of the person greater than the target threshold among the multiple first viewing angles as the second viewing angles, obtaining at least one second viewing angle; determine the second viewing angle with the lowest occlusion rate among the at least one second viewing angle as the target viewing angle.

[0094] In a possible embodiment, in terms of determining the target live broadcast image according to the target viewing angle and the target Beidou positioning, the second processing unit 502 is specifically configured to: determine the target environmental image according to the target Beidou positioning and the geographical environment library, where the geographical environment library is used to indicate the geographical environment along the event route corresponding to the target contestant, and the target environmental image is used to characterize the geographical environment corresponding to the target Beidou positioning; obtain the target motion data of the target contestant and the first motion data of the first contestant, where the target motion data is used to characterize the current body motion situation of the target contestant, and the first motion data is used to characterize the current body motion situation of the first contestant; determine the target motion image according to the target motion data and the target digital human, where the target motion image is used to characterize the motion image of the target contestant when the body motion situation is the target motion data; determine the first motion image according to the first motion data and the first digital human, where the first motion image is used to characterize the motion image of the first contestant when the body motion situation is the first motion data; determine the target live broadcast image according to the target environmental image, the target motion image, the first motion image, and the target viewing angle.

[0095] In a possible embodiment, when determining the target live broadcast screen according to the target environment image, the target motion image, the first motion image, and the target viewing angle, the second processing unit 502 is specifically configured to: place the target motion image and the first motion image in the target environment image to obtain a target on-site image; capture an image of the target digital human in the target on-site image according to the target viewing angle to obtain the target live broadcast screen.

[0096] In a possible embodiment, when determining the target environment image according to the target Beidou positioning and the geographical environment library, the second processing unit 502 is specifically configured to: query the geographical environment library according to the target Beidou positioning to determine the basic environment image corresponding to the target Beidou position; determine the on-site environment information corresponding to the target Beidou positioning, where the on-site environment information is used to indicate the on-site environment situation of the current position of the target competition player; and determine the target environment image according to the on-site environment information and the basic environment image.

[0097] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part, and will not be elaborated here.

[0098] In the case of adopting an integrated unit, as Figure 6 shown, Figure 6 is a functional unit composition block diagram of another event live broadcast screen generation device for following a competition player provided by an embodiment of the present application. In Figure 6 , the event live broadcast screen generation device 500 for following a competition player includes: a processing module 612 and a communication module 611. The processing module 612 is used to control and manage the actions of the event live broadcast screen generation device 500 for following a competition player. For example, it executes the steps of the first processing unit 501 and the second processing unit 502, and / or is used to execute other processes of the technologies described in this article. The communication module 611 is used to support the interaction between the event live broadcast screen generation device 500 for following a competition player and other devices. As Figure 6 shown, the event live broadcast screen generation device 500 for following a competition player may further include a storage module 613, and the storage module 613 is used to store the program code and data of the event live broadcast screen generation device 500 for following a competition player.

[0099] Among them, the processing module 612 can be a processor or a controller. For example, it can be a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The communication module 611 can be a transceiver, an RF circuit, or a communication interface, etc. The storage module 613 can be a memory.

[0100] Among them, all relevant contents of each scenario involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be repeated here. The above live event broadcast image generation device 500 for tracking a competition contestant can execute all of the above Figure 3 shown live event broadcast image generation method for tracking a competition contestant.

[0101] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium can be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0102] Figure 7 is a structural block diagram of a server provided by an embodiment of this application. As Figure 7As shown in the figure, the server 120 may include one or more of the following components: a processor 210, and a memory 220 coupled to the processor 210. The memory 220 may store one or more computer programs 221. The one or more computer programs 221 may be configured to implement the methods described in the above embodiments when executed by the one or more processors 210.

[0103] The processor 210 may include one or more processing cores. The processor 210 connects various parts within the entire server 120 using various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 220, and by calling data stored in the memory 220, the processor 210 performs various functions of the server 120 and processes data. Optionally, the processor 210 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 210 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing display content; the modem is used to process wireless communications. It can be understood that the above modem may not be integrated into the processor 210 and may be implemented separately through a communication chip.

[0104] The memory 220 may include random access memory (RAM) and may also include read-only memory (ROM). The memory 220 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 220 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for implementing at least one function (such as touch function, sound playback function, image playback function, etc.), and instructions for implementing the above method embodiments. The data storage area may also store data created during the use of the server 120.

[0105] It can be understood that the server 120 may include more or fewer structural elements than those shown in the above structural block diagram, which will not be limited herein. An embodiment of the present application provides a computer-readable storage medium, on which a computer program / instructions are stored, and when the computer program / instructions are executed by a processor, the steps of the method according to any possible embodiment are implemented.

[0106] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0107] In several embodiments provided by the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for example, the division of the unit is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0108] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0110] The integrated units implemented in the form of software functional units can be stored in a computer-readable storage medium. The above-mentioned software functional units stored in a storage medium include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute some steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, magnetic disks, optical discs, volatile memories, or non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM), etc., and various media that can store program codes.

[0111] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including combinations of the above different functions and implementation steps, including software and hardware implementation manners, all within the protection scope of the present invention.

Claims

1. A method for generating live broadcast images of a match by following the players in the match, characterized in that: Applied to a server of a sports live broadcast system, the method comprises: Determine a first competitor corresponding to the target competitor according to the target Beidou positioning, wherein the target Beidou positioning is used to indicate the current position of the target competitor, and the first competitor is a competitor participating in the same event whose current distance from the target competitor is within a preset target range; A target digital person corresponding to the target contestant and a first digital person corresponding to the first contestant are obtained, the target digital person being used to represent the image of the target contestant when performing the competition event, and the first digital person being used to represent the image of the first contestant when performing the competition event; a target placement position of the target digital person and a first placement position of the first digital person are determined according to the positional relationship between the target contestant and the first contestant; a plurality of first perspectives with the target contestant as the shooting target are determined, each of the plurality of first perspectives having the target contestant as the shooting center; a target perspective is determined from the plurality of first perspectives according to the target placement position and the first placement position, the target perspective being a virtual perspective with the target contestant as the core shooting target; A target environment image is determined according to the target Beidou positioning and a geographic environment library, the geographic environment library is used to indicate the geographic environment along the competition route corresponding to the target contestant, and the target environment image is used to characterize the geographic environment corresponding to the target Beidou positioning; target motion data of the target contestant and first motion data of the first contestant are obtained, the target motion data is used to characterize the current physical motion condition of the target contestant, and the first motion data is used to characterize the current physical motion condition of the first contestant; a target motion image is determined according to the target motion data and the target digital human, and the target motion image is used to characterize the motion image of the target contestant when the physical motion condition is the target motion data; a first motion image is determined according to the first motion data and the first digital human, and the first motion image is used to characterize the motion image of the first contestant when the physical motion condition is the first motion data; a target live broadcast screen is determined according to the target environment image, the target motion image, the first motion image and the target viewing angle, and the target live broadcast screen is used to characterize the on-site situation of the target contestant at the target Beidou position.

2. The method according to claim 1, characterized in that The determining the target viewing angle from the multiple first viewing angles according to the target placement position and the first placement position includes: Determine, according to the target placement position and the first placement position, an occlusion rate corresponding to each first viewing angle, the occlusion rate being used to indicate an occlusion situation of the target player by the first player in the corresponding first viewing angle; The target viewing angle is determined from the multiple first viewing angles according to the occlusion rate corresponding to each first viewing angle.

3. The method according to claim 2, characterized in that The determining the target viewing angle from the multiple first viewing angles according to the occlusion rate corresponding to each first viewing angle includes: Determine a frontal camera ratio of a character corresponding to each first viewing angle, wherein the frontal camera ratio of a character is used to represent a frontal camera situation of the target contestant in the corresponding first viewing angle; Determine a first perspective among the multiple first perspectives, wherein the frontal exposure rate of the character is greater than a target threshold, as a second perspective, to obtain at least one second perspective; The second viewing angle corresponding to the lowest occlusion rate among the at least one second viewing angle is determined as the target viewing angle.

4. The method according to claim 3, characterized in that: The determining the target live broadcast picture according to the target environment image, the target motion image, the first motion image and the target viewing angle includes: Placing the target motion image and the first motion image in the target environment image to obtain a target scene image; The target digital human is image captured according to the target viewing angle to obtain the target live broadcast picture.

5. The method according to claim 4, characterized in that Determining the target environment image according to the target Beidou positioning and the geographic environment library includes: According to the target Beidou positioning, the geographic environment database is queried to determine the basic environment image corresponding to the target Beidou position; Determine on-site environment information corresponding to the target Beidou positioning, where the on-site environment information is used to indicate the on-site environment of the current position of the target contestant; The target environment image is determined according to the on-site environment information and the basic environment image.

6. A device for generating live broadcast images of a match for following contestants, characterized in that: A server applied to a sports live broadcast system, the device comprising: a first processing unit, configured to determine a first competitor corresponding to a target competitor according to a target Beidou positioning, wherein the target Beidou positioning is used to indicate a current position of the target competitor, wherein the first competitor is a competitor participating in the same competition event and whose current distance from the target competitor is within a preset target range; obtain a target digital person corresponding to the target competitor and a first digital person corresponding to the first competitor, wherein the target digital person is used to represent the image of the target competitor when performing the competition event, and the first digital person is used to represent the image of the first competitor when performing the competition event; determine a target placement position of the target digital person and a first placement position of the first digital person according to a positional relationship between the target competitor and the first competitor; determine a plurality of first perspectives with the target competitor as a shooting target, wherein each of the plurality of first perspectives has the target competitor as a shooting center; determine a target perspective from the plurality of first perspectives according to the target placement position and the first placement position, wherein the target perspective is a virtual perspective with the target competitor as a core shooting target; The second processing unit is used to determine a target environment image according to the target Beidou positioning and a geographic environment library, the geographic environment library is used to indicate the geographic environment along the competition route corresponding to the target contestant, and the target environment image is used to characterize the geographic environment corresponding to the target Beidou positioning; obtain the target motion data of the target contestant and the first motion data of the first contestant, the target motion data is used to characterize the current physical motion condition of the target contestant, and the first motion data is used to characterize the current physical motion condition of the first contestant; determine a target motion image according to the target motion data and the target digital human, the target motion image is used to characterize the motion image of the target contestant when the physical motion condition is the target motion data; determine a first motion image according to the first motion data and the first digital human, the first motion image is used to characterize the motion image of the first contestant when the physical motion condition is the first motion data; determine a target live broadcast screen according to the target environment image, the target motion image, the first motion image and the target viewing angle, the target live broadcast screen is used to characterize the on-site situation of the target contestant at the target Beidou position.

7. A server, characterized in that: The method comprises a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program / instruction is stored thereon, and when the computer program / instruction is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images