Apparatus and method for controlling camera for relaying sports game, and recording medium having command recorded therein

Abstract

According to at least one embodiment of the present disclosure, an apparatus for controlling a camera for relaying a sports game may be proposed. The apparatus according to the present disclosure may detect, on the basis of video data of a target sports game, whether an event has occurred in the corresponding sports game, and control a camera to track and capture an object for the event that has occurred.

Description

Device, method and recording medium recording commands for controlling a camera for broadcasting a sports game

[0001] The present disclosure relates to a technique for controlling a camera for broadcasting a sports game.

[0002] One or more cameras may be used to broadcast a sports event. Each camera is positioned at various locations relative to the playing space of the sporting event, and can capture various objects within the playing space, such as players, balls, and spectators, based on a field of view (FOV) dictated by predetermined shooting settings.

[0003] Meanwhile, in sports, events can occur frequently that change the flow of the game or influence the outcome. Based on these events, more vivid broadcasts can be provided.

[0004] At least one embodiment of the present disclosure provides a technology for detecting whether an event has occurred based on video data of a sports game, and controlling a camera to track and photograph a related object when the event has occurred.

[0005] In one aspect of the present disclosure, a device for controlling a camera for broadcasting a sports game may be proposed. The device according to the present disclosure comprises: a communication circuit; one or more processors; And one or more memories storing instructions executed by the one or more processors, wherein, upon execution of the instructions, the one or more processors are configured to receive first image data of a target sporting event from one or more cameras through the communication circuit, detect whether a first event has occurred in the target sporting event based on the first image data, and in response to detecting the occurrence of the first event, determine a first camera among the one or more cameras capable of tracking and photographing a first object for the first event according to one or more predetermined first shooting settings (each of the one or more first shooting settings of the first camera can indicate one or more FOVs of the first camera), determine a second shooting setting indicating a first FOV capable of photographing the first object among the one or more first shooting settings of the first camera based on a position of the first object within the playing space of the target sporting event, and transmit a control signal to the first camera through the communication circuit that instructs to photograph the first object according to the second shooting setting. Can be.

[0006] In one embodiment, the first image data may indicate an image set including one or more images obtained by dividing an image of the target sporting event captured by the one or more cameras into predetermined frame units.

[0007] In one embodiment, the first object for the first event may include at least one of a player, a ball, or a spectator of the target sporting event.

[0008] In one embodiment, the one or more processors may be configured to generate motion data indicating movement of one or more objects within the game space based on the first image data, and detect whether the first event occurs in the game, based on the motion data.

[0009] In one embodiment, the one or more processors may be configured to detect whether the first event has occurred in the target sporting event based on the motion data, determine whether any one of the one or more objects is located in a specific area within the playing space based on the motion data, and, in response to determining that any one of the one or more objects is located in the specific area within the playing space, determine that the first event has occurred in the target sporting event and determine an object located in the specific area within the playing space as the first object to be tracked and photographed.

[0010] In one embodiment, the one or more processors may be configured to detect whether the first event has occurred in the target sporting event based on the motion data, determine whether any one of the one or more objects continues a specific movement for a predetermined period of time based on the motion data, and, in response to determining that any one of the one or more objects continues the specific movement for the predetermined period of time, determine that the first event has occurred in the target sporting event and determine an object continuing the specific movement within the sporting event space as the first object to be photographed by tracking it.

[0011] In one embodiment, the one or more processors may be configured to generate game situation data indicating a game situation of the target sport game based on the first image data, and detect whether the first event occurs in the target sport game based on the game situation data.

[0012] In one embodiment, the one or more processors may be configured to detect whether the first event has occurred in the target sports game based on the game situation data, generate score data indicating a score and a score acquisition time of each of one or more objects in the game space based on the game situation data, determine based on the score data whether any one of the one or more objects has earned a score before a predetermined time, and in response to determining that any one of the one or more objects has earned a score before the predetermined time, determine that the first event has occurred in the target sports game and determine an object that has earned a score before the predetermined time as the first object to be photographed.

[0013] In one embodiment, the one or more processors may be configured to detect whether the first event has occurred in the target sports game based on the game situation data, generate rule violation data indicating the number of rule violations and rule violation times of each of one or more objects in the game space based on the game situation data, determine based on the rule violation data whether any one of the one or more objects has been involved in a rule violation before a predetermined time, and determine, in response to determining that any one of the one or more objects has been involved in a rule violation before the predetermined time, that the first event has occurred in the target sports game and determine the object involved in the rule violation before the predetermined time as the first object.

[0014] In one embodiment, the one or more processors may be configured to detect whether the first event has occurred in the target sporting event by obtaining audio data of the target sporting event (the audio data may indicate the time and magnitude of sound generated at each location of one or more areas within the sporting space), and detecting whether the first event has occurred in the target sporting event based on the first image data and the audio data.

[0015] In one embodiment, the one or more processors may be configured to detect whether a first event has occurred in the target sports game based on the first image data and the sound data, generate frame-by-frame position data indicating frame-by-frame positions of one or more objects within the sports space based on the first image data (the frame-by-frame position data may include frame-by-frame three-dimensional coordinates of each of the one or more objects), compare, at the positions of each of the one or more objects, a loudness at a first point in time of the target sports game with a loudness at a second point in time that is a predetermined time after the first point in time, and determine that the first event has occurred in the target sports game in response to the loudness at the second point in time being greater than or equal to the loudness at the first point in time at any one of the positions of each of the one or more objects, and determine, as the first object, an object at a position where the loudness at the second point in time is greater than or equal to the loudness at the first point in time among the one or more objects.

[0016] In one embodiment, each of the one or more first shooting settings of the first camera may include a value indicating at least one of a target event; one or more tracked objects for the target event; or an FOV capable of capturing the one or more tracked objects. Additionally, the value indicating the FOV capable of capturing the one or more tracked objects may include at least one of a vertical rotation angle, a horizontal rotation angle, or a zoom factor.

[0017] In one embodiment, the one or more processors may be configured to input first camera control data of the target sporting event into a learning model trained to determine camera shooting settings in the sporting event before the start of the target sporting event, and to obtain the one or more first shooting settings of the first camera as an output of the learning model. In addition, the first camera control data may include at least one of first event data indicating one or more events that may occur in the event of the target sporting event and a tracking target object for each event; first location data indicating a position of the one or more cameras that will shoot the target sporting event; or first performance data indicating a performance of the one or more cameras that will shoot the target sporting event.

[0018] In one embodiment, the performance data may indicate at least one of a vertical rotation range, a horizontal rotation range, or a zoom magnification range of each of the one or more cameras.

[0019] In one embodiment, the learning model may be a model trained using, as learning data, second camera control data of another sporting event of the same type as the target sporting event and shooting settings indicating a FOV of a camera that captured an object for an event that occurred in the other sporting event. In addition, the second camera control data may include at least one of second event data indicating one or more events that occurred in the other sporting event and a tracking target object for each event; second position data indicating a position of one or more cameras that captured the other sporting event; or second performance data indicating a performance of one or more cameras that captured the other sporting event.

[0020] In one embodiment, the one or more processors may be configured to receive third image data of the target sporting event captured according to the second shooting settings from the first camera via the communication circuit, and generate a highlight image of the target sporting event based on the third image data.

[0021] In one embodiment, the one or more processors may be configured to receive, from the first camera via the communication circuit, second image data of the target sporting event captured according to the second shooting settings, and detect, based on the second image data, whether a second event different from the first event has occurred in the target sporting event, and in response to detecting the occurrence of the second event, determine whether there is a shooting setting indicating a second FOV capable of capturing a second object for the second event among the one or more first shooting settings of the first camera (a size of the second object in the second FOV may be larger than a size of the second object in the first FOV), and in response to determining that there is a shooting setting indicating the second FOV among the one or more first shooting settings of the first camera, transmit a control signal to the first camera instructing to capture the second object according to the shooting setting indicating the second FOV.

[0022] In one embodiment, the one or more processors receive second image data of the target sporting event photographed according to the second shooting settings from the first camera through the communication circuit, and detect whether a second event different from the first event has occurred based on the second image data, receive third image data of the target sporting event photographed according to the second shooting settings from the first camera through the communication circuit, and detect whether a second event different from the first event has occurred based on the third image data, and in response to detecting the occurrence of the second event, determine whether there is a shooting setting indicating a second FOV capable of shooting a second object for the second event among the one or more first shooting settings of the first camera (the size of the second object in the second FOV may be larger than the size of the second object in the first FOV), and determine that there is no shooting setting indicating a second FOV capable of shooting the second object among the one or more first shooting settings of the first camera. In response to that, a second camera capable of photographing the second object is determined according to a shooting setting indicating a third FOV that at least partially overlaps the second FOV among the one or more cameras, and a control signal instructing the second camera to photograph the second object according to the shooting setting indicating the third FOV is transmitted to the second camera through the communication circuit.

[0023] In one aspect of the present disclosure, a method for controlling a camera for broadcasting a sports event may be proposed. The method according to the present disclosure may be a method performed by a device including one or more processors and one or more memories storing instructions to be executed by the one or more processors. The method according to the present disclosure may include the steps of: receiving, by the one or more processors, first image data of a target sports event from one or more cameras; detecting, based on the first image data, whether a first event has occurred in the target sports event; and, in response to detecting the occurrence of the first event, determining, from among the one or more cameras, a first camera capable of tracking and capturing a first object for the first event according to one or more predetermined first shooting settings, each of the one or more first shooting settings of the first camera being capable of indicating one or more FOVs of the first camera. The method may include: determining a second shooting setting that indicates a first FOV capable of shooting the first object among the one or more first shooting settings of the first camera based on the position of the first object within the game space of the target sports game; and transmitting a control signal to the first camera that indicates shooting the first object according to the second shooting setting.

[0024] In one aspect of the present disclosure, a non-transitory computer-readable recording medium having recorded thereon commands for controlling a camera for broadcasting a sports game may be proposed. The instructions recorded on a non-transitory computer-readable recording medium according to the present disclosure are instructions to be executed by one or more processors, which, when executed by the one or more processors, cause the one or more processors to receive first image data of a target sporting event from one or more cameras, detect whether a first event has occurred in the target sporting event based on the first image data, and in response to detecting the occurrence of the first event, determine a first camera among the one or more cameras capable of tracking and photographing a first object for the first event according to one or more predetermined first shooting settings (each of the one or more first shooting settings of the first camera can indicate one or more FOVs of the first camera), determine a second shooting setting indicating a first FOV capable of photographing the first object among the one or more first shooting settings of the first camera based on a position of the first object within the playing space of the target sporting event, and transmit a control signal instructing to photograph the first object according to the second shooting setting. You can have it transmitted to the first camera.

[0025] According to at least one embodiment of the present disclosure, a more dynamic sports game broadcast can be realized by detecting whether an event has occurred based on video data of a sports game and controlling a camera to track and photograph a related object when an event has occurred.

[0026] The effects according to the technical idea of ​​the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person skilled in the art from the description of the specification.

[0027] Figure 1 is a drawing showing the operation process of a device according to one embodiment of the present disclosure.

[0028] FIG. 2 is a block diagram of a device according to one embodiment of the present disclosure.

[0029] FIGS. 3A, 3B, and 3C are diagrams showing FOVs indicated by the shooting settings of a camera according to one embodiment of the present disclosure.

[0030] Figure 4 is a diagram showing video data of a sports game.

[0031] Figure 5 is a diagram showing video data of a sports game.

[0032] FIG. 6A and FIG. 6B are diagrams illustrating a process of generating motion data of an object according to one embodiment of the present disclosure.

[0033] FIG. 7A and FIG. 7B are diagrams illustrating a process of controlling a camera to track and photograph an object for an event according to one embodiment of the present disclosure.

[0034] Figure 8 is a diagram illustrating a learning model trained to determine camera shooting settings in a sports game.

[0035] FIG. 9 is a diagram illustrating a method for controlling a camera for broadcasting a sports game according to one embodiment of the present disclosure.

[0036] Fig. 10 is a drawing showing a process of controlling a camera for broadcasting a soccer game according to the method of Fig. 9.

[0037] Fig. 11 is a drawing showing a process of controlling a camera for broadcasting a basketball game according to the method of Fig. 9.

[0038] Fig. 12 is a drawing showing a process of controlling a camera for broadcasting a tennis match according to the method of Fig. 9.

[0039] Fig. 13 is a drawing showing a process of controlling a camera for broadcasting a baseball game according to the method of Fig. 9.

[0040] Fig. 14 is a drawing showing a process of controlling a camera for broadcasting a track and field event according to the method of Fig. 9.

[0041] The various embodiments described in this disclosure are exemplified for the purpose of clearly explaining the technical concept of this disclosure and are not intended to be limited to specific embodiments. The technical concept of this disclosure includes various modifications, equivalents, alternatives, and embodiments selectively combined from all or part of the embodiments described in this disclosure. Furthermore, the scope of the technical concept of this disclosure is not limited to the various embodiments presented below or the specific descriptions thereof.

[0042] Terms used in this disclosure, including technical or scientific terms, unless otherwise defined, may have the meaning commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0043] In this disclosure, expressions such as "includes," "may include," "comprises," "may have," "has," and "may have" indicate the presence of a target feature (e.g., a function, operation, or component), but do not exclude the presence of other additional features. In other words, such expressions should be understood as open-ended terms that imply the possibility of including other embodiments.

[0044] In this disclosure, singular expressions may include plural meanings unless the context clearly indicates otherwise, and the same applies to singular expressions described in the claims.

[0045] In this disclosure, expressions such as “first,” “second,” or “first,” “second,” etc., unless the context indicates otherwise, are used to distinguish one object from another when referring to multiple similar objects, and do not limit the order or importance among the objects.

[0046] In this disclosure, expressions such as “A, B, and C,” “A, B, or C,” “A, B, and / or C,” or “at least one of A, B, and C,” “at least one of A, B, or C,” “at least one of A, B, and / or C,” “at least one selected from A, B, and C,” “at least one selected from A, B, or C,” “at least one selected from A, B, and / or C,” etc., can refer to each listed item or all possible combinations of the listed items. For example, “at least one selected from A and B” can refer to (1) A, (2) at least one of A, (3) B, (4) at least one of B, (5) at least one of A and at least one of B, (6) at least one of A and B, (7) at least one of B and A, and (8) both A and B.

[0047] In this disclosure, the expression “based on or according to” is used to describe one or more factors that influence a decision, act of judgment, or action described in a phrase or sentence containing the expression, and the expression does not exclude additional factors that influence the decision, act of judgment, or action.

[0048] In the present disclosure, determining C information based on A information and B information means taking A information and B information into consideration in determining C information, and does not exclude that other information besides A information and B information is additionally considered.

[0049] In the present disclosure, the expression that a component (e.g., a first component) is “connected” or “connected” to another component (e.g., a second component) may mean that the component is directly connected or connected to the other component, as well as connected or connected via a new other component (e.g., a third component).

[0050] In the present disclosure, “configured to” may have the meaning of “set to”, “having the ability to”, “modified to”, “made to”, “capable of”, etc., depending on the context. The expression is not limited to the meaning of “specifically designed in hardware”, and for example, a processor configured to perform a specific operation may mean a special purpose computer structured through programming to perform the specific operation.

[0051] In the present disclosure, a "learning model" may be designed to implement the structure of a human brain on a computer, and may include a plurality of network nodes that simulate neurons of a human neural network and have weights. The plurality of network nodes simulate the synaptic activity of neurons that exchange signals through synapses and may have connections among themselves. In the learning model, the plurality of network nodes may be located at layers of different depths and exchange data according to convolutional connections. For example, the learning model may be an artificial neural network model, a time series analysis model, etc. Here, the time series analysis model is a model that analyzes time series data, and may be a recurrent neural network (RNN) model, a long short-term memory (LSTM) model, or an Autoregressive Integrated Moving Average (ARIMA) model. Meanwhile, the present disclosure is not limited thereto, and various types of models for analyzing data may be used.

[0052] In the present disclosure, a “training process” may mean a process in which a learning model extracts and analyzes features (patterns) of input data and output data pairs of learning data, repeats the process of deriving correlations between input and output data, and optimizes parameters of the learning model based on the correlations between input and output data.

[0053] In the present disclosure, an “inference process” may mean a process in which a learning model applies a previously learned pattern to new input data to generate output data as a result of prediction or classification of the input data.

[0054] Hereinafter, various embodiments of the present disclosure will be described with reference to the attached drawings. In the attached drawings and the description of the drawings, identical or substantially equivalent components may be assigned the same reference numerals. Furthermore, in the description of various embodiments below, duplicate descriptions of identical or corresponding components may be omitted, but this does not mean that the corresponding components are not included in the embodiments.

[0055] FIG. 1 is a diagram illustrating an operation process of a device (100) according to one embodiment of the present disclosure. In the present disclosure, the device (100) may be a device (e.g., a server) that controls a camera for broadcasting a sports game.

[0056] In one embodiment, each of the one or more cameras (121, 122, 123, 124, 125, 126) can capture a game space (110) of a sporting event according to one or more shooting settings indicating different FOVs, thereby generating image data (130) of the sporting event. That is, each of the one or more cameras (121, 122, 123, 124, 125, 126) has one or more predetermined shooting settings and can capture the game space (110) based on the FOV indicated by one of them. Here, the FOV of each camera (121, 122, 123, 124, 125, 126) can correspond to a portion of the game space (110). For example, when a camera photographs a game space (110) according to a shooting setting that indicates FOV, it can be expressed that the camera photographs the game space (110) based on the FOV indicated by the shooting setting. In addition, when a camera photographs the game space (110) based on the FOV, it can be expressed that the camera photographs an area corresponding to the FOV within the game space (110). Meanwhile, in the present disclosure, FOV may mean a range photographed by an image sensor of a camera. For example, FOV may be referred to as a term having the same or similar meaning, such as AOV (Angle Of View), field of view, angle of view, etc. In addition, in the present disclosure, a shooting setting that indicates FOV may be referred to as a term having the same or similar meaning, such as a FOV setting, preset, etc. that controls the camera so that the image sensor of the camera can photograph the FOV.

[0057] In one embodiment, the playing space (110) may refer to a predetermined three-dimensional space related to a sports game. Specifically, the playing space (110) may include an area where a sports game takes place, an area where objects of the sports game may be located, an area where stadium facilities (e.g., an electronic scoreboard) may be located, etc. Here, the area where a sports game takes place may include a court, a playing surface (e.g., a table tennis table), etc., which are areas that serve as a basis for various judgments related to score and conceded points. For example, an object may include at least one of a player, a ball, an audience member, a referee, an analyst, or a stadium facility (e.g., an electronic scoreboard) within the playing space (110).

[0058] In one embodiment, at least some of the one or more cameras (121, 122, 123, 124, 125, 126) may be fixed cameras and others may be tracking cameras.

[0059] For example, a fixed camera may be a camera that captures a game space (110) in a fixed state according to a single shooting setting that indicates a FOV. Here, the shooting setting of the fixed camera may include a value that indicates a zoom ratio. The fixed camera may capture the game space (110) based on the FOV indicated by the shooting setting. Meanwhile, the fixed camera is the main camera of a sports game, and the position of the tracking camera or the position of an object to be tracked and captured by the tracking camera within the game space (110) may be expressed based on the position of the fixed camera.

[0060] For example, a tracking camera may be a camera that is mounted on a control motor that can rotate up, down, left, and right by a certain range and tracks and photographs an object (115) within a playing space (110) according to one or more shooting settings that indicate different FOVs. Here, each of the one or more shooting settings of the tracking camera may include a value indicating at least one of an event, a tracking target object for the event, or a FOV. For example, a value indicating the FOV may include at least one of a vertical rotation angle, a horizontal rotation angle, or a zoom factor. The tracking camera may photograph the playing space (110) or the tracking target object within the playing space (110) based on the FOV indicated by the shooting settings.

[0061] For example, each camera (121, 122, 123, 124, 125, 126) can capture a game space (110) or an object (115) within the game space (110) at a predetermined frame rate (e.g., 120 fps) based on an FOV indicated by the shooting settings, thereby generating video data (130) of a sports game. Here, the video data (130) can indicate an image set including one or more images obtained by dividing a video of a sports game captured by one or more cameras (121, 122, 123, 124, 125, 126) into predetermined frame rates (e.g., 120 fps).

[0062] In one embodiment, the device (110) can detect whether an event has occurred in a target sporting event, and if the occurrence of the event is detected, control at least one of the cameras (121, 122, 123, 124, 125, 126) to track and capture an object corresponding to the event. Here, the target sporting event may refer to one or more sporting events in which the occurrence of an event is to be detected and a camera controlled based on the detection result. In addition, the occurrence of an event may mean that a series of actions or situations affecting the flow or outcome of the game have occurred. In other words, the event may mean that the event has occurred immediately before or a predetermined time before the time at which the device (110) detects the occurrence of the event. For example, the occurrence of an event may mean that a situation related to the flow of the game, such as the start or end of the game, has occurred. If a sporting event consists of one or more games, and the outcome of each game determines the overall outcome of the game (win or loss), the occurrence of an event may mean that a specific situation related to the flow of the game has occurred, such as the start of the game, the start of the game, the end of the game, or the end of the game. For example, the occurrence of an event may mean that a specific situation affecting the outcome of the game has occurred. For example, the occurrence of an event may mean that a situation has occurred in which one or more objects (115) within the game space (110) are located in a specific area (e.g., a scoring area) within the game space (110). For example, the occurrence of an event may mean that a situation has occurred in which one or more objects (115) within the game space (110) continue a specific movement (e.g., moving toward the scoring area) for a predetermined period of time. For example, the occurrence of an event may mean that a situation has occurred in which one or more objects (115) within the game space (110) scores a point.For example, the occurrence of an event may mean that one or more objects (115) within the playing space (110) have committed a rule violation. The above examples are merely intended to illustrate the meaning of the occurrence of an event, and the present disclosure is not limited thereto. In addition to the examples described above, the occurrence of an event may mean that a specific action or situation has occurred that affects the flow or outcome of the game, such as a score, a rule violation (e.g., a foul, a penalty), a player substitution, a timeout, the start of the game, the end of the game, a new record, a player injury, or a video review request. For more vivid sports game broadcasting, when the occurrence of such an event is detected, it is necessary to track and film the relevant objects. To this end, the device (110) may perform at least some of the following actions in response to detecting the occurrence of an event.

[0063] For example, the device (100) can receive video data (130) of a target sporting event from one or more cameras (121, 122, 123, 124, 125, 126). For example, the device (100) can detect whether an event has occurred in the target sporting event based on the video data (130).

[0064] For example, when detecting the occurrence of an event in a target sports game, the device (100) may generate data (“motion data”) (150) indicating the movement of one or more objects (115) within the playing space (110) based on image data (130). Here, the motion data (150) may include metrics indicating the movement of the object (115) within the playing space (110) of the target sports game, such as a moving direction, a moving speed, a moving time, and a moving trajectory. Specifically, the device (100) may generate data (“frame-by-frame position data”) (140) indicating the frame-by-frame position of one or more objects (115) within the playing space (110) based on image data (130). Here, the frame-by-frame position data (140) may include frame-by-frame three-dimensional coordinates where one or more objects (115) are located within the playing space (110). The device (100) can generate motion data (150) based on frame-by-frame position data (140). The device (100) can detect whether an event occurs in a target sports game based on the motion data (150).

[0065] For example, when detecting the occurrence of an event in a target sports game, the device (100) may generate data (“game situation data”) (160) indicating the game situation of the target sports game based on the image data (130). Here, the game situation data (160) may include indicators indicating the game situation of the target sports game, such as the game progress time, score, number of rule violations, game leading time, and referee decision results in the target sports game. Specifically, the device (100) may determine an image in which an object (115) indicating the game situation (e.g., an electronic scoreboard) is captured from a set of images included in the image data (130). For example, the object (115) indicating the game situation may be an object displaying indicators indicating the game situation of the target sports game, such as the game progress time, score, number of rule violations, game leading time, and referee decision results in the target sports game. The device (100) may generate the game situation data (160) based on an image in which an object (115) indicating the game situation is captured. The device (100) can detect whether an event occurs in a target sports game based on game situation data (160).

[0066] Additionally or alternatively, the device (100) may receive game situation data (160) from an external device to detect whether an event occurs in the target sporting event. Here, the external device may be a terminal (e.g., a game operation pad) of an analyst or referee of the target sporting event. The game situation data (160) received from the external device may include indicators indicating the game situation of the target sporting event, such as the game progress time, score, number of rule violations, game leading time, and referee decision results. The device (100) may detect whether an event occurs in the target sporting event based on the game situation data (160) received from the external device.

[0067] Additionally or alternatively, the device (100) can detect whether an event occurs in a target sports game based on game situation data (160) generated based on image data (130) and game situation data (160) received from an external device.

[0068] Additionally or alternatively, the device (100) may acquire data indicating the occurrence time and magnitude of sounds generated at one or more locations within the game space (110) of the target sporting event, when detecting whether an event occurs in the target sporting event (“sound data”). For example, at least some of the one or more cameras (121, 122, 123, 124, 125, 126) may be equipped with a device or interface (e.g., a microphone) for recording sounds, and the image data (130) may include sound data of the target sporting event. In this case, the device (100) may acquire the sound data of the target sporting event based on the image data (130). Alternatively, the device (100) may also receive the sound data from an external device equipped with a device or interface (e.g., a microphone) for recording sounds of the target sporting event. The device (100) may detect whether an event occurs in the target sporting event based on the image data (130) and the sound data.

[0069] For example, in response to detecting the occurrence of an event, the device (100) may determine, among one or more cameras (121, 122, 123, 124, 125, 126), a camera ("target camera") capable of tracking and capturing an object ("target object") for the event that occurred according to one or more predetermined shooting settings. That is, the device (100) may determine, among one or more cameras (121, 122, 123, 124, 125, 126), a camera having shooting settings that indicate an FOV capable of tracking and capturing the target object as a target camera for controlling the camera to track and capture the target object.

[0070] For example, the device (100) may determine a shooting setting (“target shooting setting”) that indicates an FOV from which the target object can be captured among one or more shooting settings of the target camera based on the location of the target object within the game space (110). That is, if the target camera was capturing the game space (110) according to any one of the one or more shooting settings, the device (100) may determine to convert the existing shooting setting of the target camera to the target shooting setting.

[0071] For example, the device (100) may transmit a control signal (180) to the target camera, which instructs to photograph a target object according to the target shooting settings. Accordingly, the target camera, which has received the control signal (180) from the device (100), may convert the existing shooting settings into the target shooting settings, and track and photograph the game space (110) or the target object within the game space (110) based on the FOV indicated by the target shooting settings. If the target camera is a tracking camera, the device (100) may also transmit a control signal (180) to the control motor of the target camera, which instructs to photograph the target object according to the target shooting settings. Accordingly, the control motor of the target camera, which has received the control signal (180) from the device (100), may adjust the up / down rotation angle, left / right rotation angle, zoom magnification, etc. of the target camera according to the target shooting settings, and control the target camera so that the target camera tracks and photographs the target object based on the FOV, which is the adjustment result.

[0072] In sports, events that can alter the flow of the game or influence the outcome can occur frequently. To provide a more vivid broadcast, it's necessary to detect these events in real time and, once detected, quickly capture and film various objects, such as the movements of relevant players, the ball, and the reactions of the audience.

[0073] According to the technology for controlling a camera for broadcasting a sports game of the present disclosure, a device (100) analyzes video data (130) generated during a sports game to detect whether an event has occurred, determines a target camera for controlling the camera to track and photograph a target object for the event when the event occurs, and then quickly converts the shooting settings of the target camera to target shooting settings that indicate an FOV capable of shooting the target object. Through this, dynamic and realistic sports game broadcasting can be realized.

[0074] FIG. 2 is a block diagram of a device (100) according to one embodiment of the present disclosure. In one embodiment, the device (100) may include one or more processors (210), one or more memories (220), and / or communication circuits (230) as elements. In one embodiment, at least one of the elements of the device (100) may be omitted, or another element may be added to the device (100). In one embodiment, additionally or alternatively, some of the elements may be implemented in an integrated manner, or may be implemented as a single or multiple entities. One or more processors (210) may be referred to as a processor (210). The expression “processor (210)” may mean a set of one or more processors, unless the context clearly indicates otherwise. One or more memories (220) may be referred to as a memory (220). The expression "memory (220)" may mean a set of one or more memories, unless the context clearly indicates otherwise. At least some of the components inside / outside the device (100) may be connected to each other via a bus, a general purpose input / output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI), and may exchange information (data, signals, etc.).

[0075] In one embodiment, the processor (210) may control at least one component of the device (100) connected to the processor (210) by executing instructions (e.g., code, software, program, etc.). In addition, the processor (210) may perform various operations such as calculations, processing, data generation, and processing related to the present disclosure. In addition, the processor (210) may load data from or store data in the memory (220). For example, the processor (210) may detect whether an event occurs in a target sporting event based on image data (130) of the target sporting event. In addition, in response to detecting the occurrence of an event, the processor (210) may determine a target camera capable of tracking and photographing a target object for the event, determine a target shooting setting that indicates an FOV capable of photographing the target object among one or more shooting settings of the target camera, and generate a control signal (180) that instructs to photograph the target object according to the target shooting setting. The processor (210) can control the communication circuit (230) to transmit the generated control signal (180) to the target camera or the control motor of the target camera.

[0076] In one embodiment, the memory (220) can store various data. The data stored in the memory (220) is data acquired, processed, or used by at least one component of the device (100), and may include instructions (e.g., code, software, programs, etc.). The memory (220) may include volatile and / or non-volatile memory. The instructions or programs are software stored in the memory (220), and may include an operating system for controlling the resources of the device (100), applications, and / or middleware that provides various functions to applications so that the applications can utilize the resources of the device (100). For example, the memory (220) may store instructions that cause the processor (210) to perform operations when executed by the processor (210). The memory (220) may store video data (130), motion data (150), game situation data (160), audio data, etc. of a target sports game. In addition, the memory (220) may store camera control data of the target sporting event, including event data indicating one or more events that may occur in the target sporting event and objects to be tracked for each event, position data indicating the positions of one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sporting event, performance data indicating the performance of one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sporting event, etc. In addition, the memory (220) may store video data of another sporting event of the same event as the target sporting event, motion data indicating the movement of one or more objects (115) within the game space of another sporting event, game situation data indicating game situations of another sporting event, sound data of another sporting event, etc.In addition, the memory (220) may store camera control data of other sports games, including event data indicating one or more events that occurred in other sports games and objects to be tracked for each event, position data indicating the positions of one or more cameras that filmed other sports games, performance data indicating the performance of one or more cameras that filmed the target sports games, etc. In one embodiment, the processor (210) may control the communication circuit (230) to obtain game situation data (160) of the target sports game, game situation data of other sports games, etc. from an external device. In this way, data obtained from an external device may also be stored in the memory (220).

[0077] In one embodiment, the communication circuit (230) may perform wireless or wired communication between the device (100) and another server, or between the device (100) and another device. For example, the communication circuit (230) may perform wireless communication according to a method such as enhanced Mobile Broadband (eMBB), Ultra Reliable Low-Latency Communications (URLLC), Massive Machine Type Communications (MMTC), Long-Term Evolution (LTE), LTE-A (LTE Advance), New Radio (NR), Universal Mobile Telecommunications System (UMTS), Global System for Mobile communications (GSM), Code Division Multiple Access (CDMA), Wideband CDMA (WCDMA), Wireless Broadband (WiBro), Wireless Fidelity (WiFi), Bluetooth, Near Field Communication (NFC), Global Positioning System (GPS), or Global Navigation Satellite System (GNSS). For example, the communication circuit (230) can perform wired communication according to a method such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), RS-232 (Recommended Standard-232), or POTS (Plain Old Telephone Service). For example, the communication circuit (230) can be used to perform communication with one or more cameras (121, 122, 123, 124, 125, 126) or external devices. The communication circuit (230) can be implemented as a circuit or chip configured to perform data transmission and reception.

[0078] In one embodiment, the device (100) may further include an input / output interface. The input / output interface may be omitted from the device (100) depending on the embodiment. For example, the input / output interface may include an input device and / or an output device. The input device may receive various data from a user of the device (100) and transmit the input data to at least one component of the device (100). The output device may receive various data output by at least one component of the device (100) and provide (display) the data to the user in an audiovisual form. For example, the input device may include a mouse, a keyboard, a touch pad, etc. For example, the output device may include a display, a projector, a hologram, etc.

[0079] In one embodiment, the device (100) may be a device of various forms. For example, the device (100) may be a computer device, a back-end server, a front-end server, a portable communication device, a portable multimedia device, a wearable device, a device according to a combination of the aforementioned devices, or a chip, board, circuit, etc. within the aforementioned devices. However, the device (100) of the present disclosure is not limited to the aforementioned devices.

[0080] FIGS. 3A to 3C are diagrams illustrating FOVs indicated by camera shooting settings according to one embodiment of the present disclosure. In one embodiment, each camera (121, 122, 123, 124, 125, 126) may have one or more shooting settings. Here, each of the one or more shooting settings may include a value indicating at least one of a target event, a tracking target object for the target event, or an FOV capable of shooting the tracking target object.

[0081] For example, a value indicating a target event may include an event identifier (e.g., event number, event name), etc. For example, a value indicating a target object to be tracked may include an object identifier (e.g., object number, object name), the number of objects, etc.

[0082] For example, a value indicating a FOV that can capture a tracking target object may include a vertical rotation angle, a horizontal rotation angle, a zoom magnification, etc. That is, an event corresponds to one or more shooting settings, one shooting setting corresponds to one event, and each shooting setting may include a value indicating at least one of a corresponding target event, a tracking target object for the target event, or an FOV that can capture the tracking target object. In this way, the shooting settings corresponding to the event may be expressed as event-specific shooting settings. Specifically, at least one of the one or more event-specific shooting settings of each camera (121, 122, 123, 124, 125, 126) may correspond to an event that occurred in a sports game, and at least one of the one or more cameras ((121, 122, 123, 124, 125, 126) may be controlled to track and capture a tracking target object for the event according to the event-specific shooting setting corresponding to the event.

[0083] Figure 3a is a drawing showing a view of the game space (110) based on the Z-axis in a three-dimensional plane. For convenience of explanation, camera 1 (121) among one or more cameras (122, 123, 124, 125, 126) is assumed to be a tracking camera, and the explanation will be centered on camera 1 (121).

[0084] In one embodiment, each of one or more shooting settings of camera 1 (121) is configured to have a maximum FOV (R) of camera 1 (121). a ) can be directed to a portion of the FOV.

[0085] For example, a value indicating the FOV that can capture a tracked object for a target event included in each of one or more shooting settings of camera 1 (121) is the maximum FOV (R) of camera 1 (121). a ) can indicate a FOV (R1) which is a part of the camera 1 (121). Here, the maximum FOV (Ra) of the camera 1 (121) can be determined based on position data indicating the position of the camera 1 (121) with respect to the game space (110) or performance data indicating the performance of the camera 1 (121). For example, the position data of the camera 1 (121) can indicate the three-dimensional coordinates of the camera 1 (121) with respect to a certain vertex of the game space (110), the three-dimensional coordinates of the adjacent cameras of the camera 1 (121) (e.g., camera 2 (122), camera 6 (126)), etc. For example, the performance data of the camera 1 (121) can indicate the up / down rotation range indicating the maximum up / down rotation angle of the camera 1 (121), the left / right rotation range indicating the maximum left / right rotation angle, the zoom ratio range indicating the maximum zoom ratio and the minimum zoom ratio, etc. Meanwhile, in FIG. 3a, it is assumed that camera 1 (121) is a tracking camera, but the same explanation can be applied to the cameras among the remaining cameras (122, 123, 124, 125, 126) shown in FIG. 3a that are tracking cameras.

[0086] Figure 3b is a drawing showing a view of the game space (110) based on the Z-axis in three dimensions. For convenience of explanation, camera 3 (123) among one or more cameras (122, 123, 124, 125, 126) is assumed to be a fixed camera, and the explanation will be centered on camera 3 (123).

[0087] In one embodiment, the shooting settings of camera 3 (123) are set to the maximum FOV (R) of camera 3 (123). c) can be indicated. Here, the maximum FOV (Rc) of camera 3 (123) can be determined based on the position data of camera 3 (123) or the performance data of camera 3 (123) with respect to the game space (110). For example, the position data of camera 3 (123) can indicate the three-dimensional coordinates of camera 3 (123) with respect to a certain vertex of the game space (110), the three-dimensional coordinates of an adjacent camera of camera 3 (123) (e.g., camera 2 (122), camera 4 (124)), etc. For example, the performance data of camera 3 (123) can indicate the zoom ratio range that indicates the maximum zoom ratio and minimum zoom ratio of camera 3 (123). Additionally or alternatively, the shooting settings of camera 3 (123) may include a value indicating an FOV that is a portion of the maximum FOV (Rc) of camera 3 (123). For example, the value indicating an FOV that is a portion of the maximum FOV (Rc) of camera 3 (123) may include a zoom factor. In this case, camera 3 (123) may capture the playing space (110) according to the shooting settings indicating an FOV that is a portion of the maximum FOV (Rc). Meanwhile, although FIG. 3B has been described assuming that camera 3 (123) is a fixed camera, the same description may also be applied to cameras that are fixed cameras among the remaining cameras (121, 122, 124, 125, 126) illustrated in FIG. 3B.

[0088] Figure 3c is a drawing showing a view of the game space (110) based on the Y-axis in three dimensions. For convenience of explanation, the explanation will focus on camera 1 (121), camera 5 (125), and camera 6 (126) among one or more cameras (122, 123, 124, 125, 126).

[0089] In one embodiment, camera 1 (121) can capture the playing space (110) or a target object within the playing space (110) based on an FOV (R1) indicated by one or more shooting settings. Camera 5 (125) can capture the playing space (110) or a target object within the playing space (110) based on an FOV (R5) indicated by one or more shooting settings. Camera 6 (126) can capture the playing space (110) or a target object within the playing space (110) based on an FOV (R6) indicated by one or more shooting settings. In this way, one or more cameras (122, 123, 124, 125, 126) can cooperate to capture target objects for a sporting event or an event occurring at a sporting event at various FOVs.

[0090] FIG. 4 is a diagram illustrating video data (130) of a sports game. In one embodiment, each of one or more cameras (121, 122, 123, 124, 125, 126) may capture a target object for a game space (110) or an event within the game space (110) at a predetermined frame rate (e.g., 120 fps) based on an FOV indicated by one or more shooting settings to generate video data (130). For example, the video data (130) may indicate an image set including one or more images (401, 402, 403, 404, 405) obtained by dividing a video of a sports game captured by one or more cameras (121, 122, 123, 124, 125, 126) into frame units. In the case of a ball game, one or more images (401, 402, 403, 404, 405) may capture target objects such as players, balls, referees, spectators, coaches, and stadium facilities (e.g., scoreboards, scoreboards). For example, one or more images (401, 402, 403, 404, 405) may be used to generate motion data (150) of an object (115) within a playing space (110) of a sports game and game situation data (160) of the sports game. For example, an image (403) in which the scores of each of one or more objects (115) within a playing space (110) are captured may be used to generate game situation data (160).

[0091] FIG. 5 is a diagram illustrating video data (130) of a sports game. In one embodiment, each of one or more cameras (121, 122, 123, 124, 125, 126) can capture a target object for a game space (110) or an event within the game space (110) at a predetermined frame rate (e.g., 120 fps) in an FOV indicated by one or more shooting settings to generate video data (130). For example, the video data (130) can indicate an image set including one or more images (501, 502, 503, 504, 505) obtained by dividing a video of a sports game captured by one or more cameras (121, 122, 123, 124, 125, 126) into frames. In the case of a non-ball sport, one or more images (501, 502, 503, 504, 505) may capture players, referees, spectators, coaches, etc. as target objects. For example, one or more images (501, 502, 503, 504, 505) may be used to generate motion data (150) of an object (115) within a playing space (110) of the sporting event and game situation data (160) of the sporting event. For example, an image (504) of a situation in which one of one or more objects (115) within a playing space (110) performs a specific movement (e.g., hitting another object) may be used to generate game situation data (160) indicating a scoring situation of the sporting event. For example, an image (501) of a situation in which one or more objects (115) within a game space (110) are located in a specific area (e.g., an area a predetermined distance away from another object) can be used to generate game situation data (160) indicating a game start situation.

[0092] FIG. 6A is a diagram illustrating a process for generating motion data (150) of an object (115) according to one embodiment of the present disclosure. For convenience of explanation, the object (115) of FIG. 6A is assumed to be a player (115) within a playing space (110) of a sports game.

[0093] In one embodiment, the processor (210) can generate frame-by-frame position data (140) of a player (115) within a game space (110) based on one or more images in which a video of a sporting event is divided into frames.

[0094] In one embodiment, the processor (210) can determine frame-by-frame three-dimensional coordinates of a player (115) from one or more images included in an image set indicated by the image data (130), and generate frame-by-frame position data (140) indicating the determined three-dimensional coordinates and the corresponding time. Here, the three-dimensional coordinates can be composed of an X (x-axis) value, a Y (y-axis) value, and a Z (z-axis) value in units of pixels.

[0095] For example, the processor (210) can determine the two-dimensional coordinates of the player (115) in each of one or more images included in the set of images indicated by the image data (130).

[0096] For example, the two-dimensional coordinates of the player (115) may be any one of one or more two-dimensional coordinates forming an outline of the player (115) or a center point of one or more such two-dimensional coordinates.

[0097] For example, the two-dimensional coordinate of the player (115) may be one or more two-dimensional coordinates indicating a specific part of the player, or may be the midpoint of one or more such two-dimensional coordinates. For example, the specific part may refer to a part of the overall form of the player (115) that is predetermined to be photographed in a sports game, such as the hand, face, or leg of the player (115). The specific part may vary depending on the sport. For example, in a ball game, the specific part of the player (115) may be a part that directly or indirectly makes contact with the ball and the player (115). For example, in table tennis, which is a ball game, the specific part of the player (115) may be a hand holding a racket. Alternatively, in a non-ball game, the specific part of the player (115) may be a part of the overall form of the player (115) that is related to scoring. For example, in boxing, which is a non-ball game, the specific part of the player (115) may be the hand of the player (115). Taking track and field, a non-ball sport, as an example, a specific part of an athlete (115) may be the athlete's (115) leg.

[0098] For example, the processor (210) may determine the three-dimensional coordinates of the player (115) based on the two-dimensional coordinates of the player (115) in each of one or more images. For example, the processor (210) may convert the two-dimensional coordinates of the player (115) in each of one or more images corresponding to a specific frame into three-dimensional coordinates of the player (115) in the specific frame based on the positions and shooting settings of each of one or more cameras (121, 122, 123, 124, 125, 126) that generated the one or more images corresponding to the specific frame. Meanwhile, the processor (210) may determine the three-dimensional coordinates of the player (115) from one or more images included in the image set indicated by the image data (130) using various computer vision algorithms, but the present disclosure is not limited thereto.

[0099] In one embodiment, the processor (210) may generate motion data (150) that instructs the movement of the player (115) based on frame-by-frame position data (140) of the player (115).

[0100] For example, the motion data (150) of the player (115) may include indicators indicating the movement of the player (115), such as the movement direction, movement speed, movement time (e.g., t seconds), movement trajectory, and posture change of the player (115). Here, each indicator included in the motion data (150) may be numerical data or categorical data. For example, the motion data (150) of the player (115) may include a value indicating at least one of the movement direction, movement speed, movement time, and movement trajectory for the player (115) moving from a first position (X, Y, Z) to a second position (X', Y', Z'). In addition, the motion data (150) of the player (115) may also include a value indicating a posture change indicating that the player (115) changed from a first posture to a second posture.

[0101] FIG. 6b is a diagram illustrating a process of generating motion data (150) of an object (115) according to one embodiment of the present disclosure. For convenience of explanation, the object (115) of FIG. 6b is assumed to be a ball (115) within a playing space (110) of a sports game.

[0102] In one embodiment, the processor (210) can generate frame-by-frame position data (140) of a ball (115) within a playing space (110) based on one or more images in which a video of a sports game is divided into frames.

[0103] In one embodiment, the processor (210) can determine frame-by-frame three-dimensional coordinates of a ball (115) from one or more images included in an image set indicated by image data (130), and generate frame-by-frame position data (140) indicating the determined three-dimensional coordinates and the corresponding time. Here, the three-dimensional coordinates can be composed of an X (x-axis) value, a Y (y-axis) value, and a Z (z-axis) value in units of pixels.

[0104] For example, the processor (210) can determine the two-dimensional coordinates of the ball (115) in each of one or more images included in the image set indicated by the image data (130).

[0105] For example, the two-dimensional coordinate of the ball (115) may be any one of one or more two-dimensional coordinates constituting the outline of the ball (115) or the midpoint of one or more such two-dimensional coordinates.

[0106] For example, the processor (210) can determine the three-dimensional coordinates of the ball (115) based on the two-dimensional coordinates of the ball (115) in each of one or more images. For example, the processor (210) can convert the two-dimensional coordinates of the ball (115) in each of one or more images corresponding to a specific frame into three-dimensional coordinates of the ball (115) in the specific frame based on the positions and shooting settings of each of one or more cameras (121, 122, 123, 124, 125, 126) that generated one or more images corresponding to the specific frame. Meanwhile, the processor (210) can determine the three-dimensional coordinates of the ball (115) from one or more images included in the image set indicated by the image data (130) using various computer vision algorithms, and the present disclosure is not limited thereto.

[0107] In one embodiment, the processor (210) can generate motion data (150) indicating movement of the ball (115) based on frame-by-frame position data (140) of the ball (115) within the playing space (110) of a sports game.

[0108] For example, the motion data (150) of the ball (115) may include indicators indicating the movement of the ball (115), such as the moving direction, moving speed, moving time (e.g., t seconds), moving trajectory, spin direction, and spin count of the ball (115). Here, each indicator included in the motion data (150) of the ball (115) may be numerical data or categorical data. For example, the motion data (150) of the ball (115) may include a value indicating at least one of the moving direction, moving speed, moving time, moving trajectory, spin direction, and spin count regarding the movement of the ball (115) from a first position (X, Y, Z) to a second position (X', Y', Z').

[0109] Meanwhile, the processor (210) may generate motion data (150) of an object (115) within a playing space (110) of a sporting event depending on the type of sporting event. For example, in the case of a ball game, the processor (210) may generate motion data (150) of a player (115) and motion data (150) of a ball (115) within a playing space (110) of the sporting event according to the aforementioned method. Alternatively, in the case of a non-ball game, the processor (210) may generate motion data (150) of a player (115) within a playing space (110) of the sporting event according to the aforementioned method. In addition, although the player and the ball are described as examples of the object (115) in FIGS. 6A and 6B , the present disclosure is not limited thereto. Even if the object (115) is a spectator, referee, coach, etc. in the game space (110), the processor (210) can generate motion data (150) of the object (115) according to the method described above.

[0110] FIGS. 7A and 7B are diagrams illustrating a process of controlling a camera to track and photograph an object (170) for an event according to one embodiment of the present disclosure. In one embodiment, the processor (210) may detect the occurrence of an event based on image data (130) of a target sports game, and control at least one of one or more cameras (121, 122, 123, 124, 125, 126) to track and photograph a target object (170) among one or more objects (115) within a game space (110) when the event occurs.

[0111] In one embodiment, the processor (210) may, in response to detecting the occurrence of an event in a target sporting event, determine a target camera capable of capturing a target object (170) for the event that occurred according to one or more shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). For example, the processor (210) may determine a target camera having a shooting setting indicating an FOV capable of capturing the target object (170) among one or more cameras (121, 122, 123, 124, 125, 126). For convenience of explanation, in FIG. 7A, it is assumed that camera 1 (121) is a target camera capable of capturing the target object (170), but the present disclosure is not limited thereto. Among the remaining cameras (122, 123, 124, 125, 126), there may be a camera capable of photographing the target object (170), and the following description may be equally applicable to such cameras. For example, if there are at least two cameras capable of photographing the target object (170), the processor (210) may determine such cameras as target cameras and perform the following operations for each camera.

[0112] In one embodiment, the processor (210) may determine, based on the location of the target object (170) within the game space (110), a target shooting setting indicating an FOV capable of shooting the target object (170) among one or more shooting settings of camera 1 (121). For example, each of the one or more shooting settings of camera 1 (121) may include a value indicating a target event, a target object to be tracked for the target event, an FOV capable of shooting the tracked object, etc. The processor (210) may determine, as a target shooting setting, a shooting setting including a value indicating an event occurring in a target sporting event as a target event, a value indicating the target object (170) as a tracked object, and a value indicating an FOV capable of shooting the target object (170). Additionally or alternatively, each of the one or more shooting settings of camera 1 (121) may include a value indicating a ranking. For example, if there are at least two shooting settings that indicate an FOV capable of shooting a target object (170) among one or more shooting settings of camera 1 (121), the processor (210) may determine a shooting setting with a higher ranking among such shooting settings as the target shooting setting. As another example, if there are at least two shooting settings that indicate an FOV capable of shooting a target object (170) among one or more shooting settings of camera 1 (121), the processor (210) may determine such shooting settings as the target shooting settings.

[0113] In one embodiment, the processor (210) may transmit a control signal (180) to camera 1 (121) instructing to photograph an object (170) according to target photographing settings. Camera 1 (121) may photograph the target object (170) based on the FOV (R1') indicated by the target photographing settings according to the control signal (180). For example, if the control signal (180) instructs to photograph the target object (170) according to at least two of one or more photographing settings of camera 1 (121), camera 1 (121) may photograph the target object (170) according to a higher-priority photographing setting among the at least two photographing settings indicated by the control signal (180) and subsequently photograph the target object (170) according to a lower-priority photographing setting. In addition, camera 1 (121) may transmit image data of a target sports game photographed according to the target photographing settings to the device (110).

[0114] Meanwhile, while camera 1 (121) tracks and photographs the target object (170) according to the target shooting settings, the target object (170) may move within the game space (110). For example, the target object (170) may move out of the FOV (R1') indicated by the target shooting settings within the game space (110). In this case, the flow of tracking and photographing the target object (170) may be interrupted. To prevent this, the processor (210) may determine, based on image data of the target sports game photographed according to the target shooting settings, whether the target object (170) has moved out of the FOV (R1') indicated by the target shooting settings or whether only a portion of the entire shape of the target object (170) has been photographed in the FOV (R1'). The processor (210) may determine, in response to determining that the target object (170) has moved out of the FOV (R1') indicated by the target shooting settings or that only a portion of the entire shape of the target object (170) has been captured in the FOV (R1'), whether one or more shooting settings of camera 1 (121) has a shooting setting that indicates an FOV capable of capturing the moving target object (170). The processor (210) may redetermine, in response to determining that one or more shooting settings of camera 1 (121) has a shooting setting that indicates an FOV capable of capturing the moving target object (170), the shooting setting that indicates an FOV capable of capturing the moving target object (170). The processor (210) may transmit a control signal (180) to camera 1 (121) that instructs to capture the moved target object (170) according to the redetermined target shooting setting. Camera 1 (121) can capture a moving target object (170) based on the FOV (R1'') indicated by the target shooting setting re-determined according to the control signal (180).Additionally, camera 1 (121) can transmit video data of a target sports game captured according to the re-determined target shooting settings to the device (110).

[0115] In response to determining that there is no shooting setting indicating an FOV capable of capturing the moving target object (170) among one or more shooting settings of camera 1 (121), the processor (210) may re-determine a target camera capable of capturing the moving target object (170) according to one or more shooting settings among the remaining one or more cameras (122, 123, 124, 125, 126). For example, the processor (210) may re-determine a target camera having a shooting setting indicating an FOV capable of capturing the moving target object (170) among the remaining one or more cameras (122, 123, 124, 125, 126). For convenience of explanation, in FIG. 7B, it is assumed that camera 5 (125) is re-determined as a target camera capable of capturing the moving target object (170), but the present disclosure is not limited thereto. Among the remaining cameras (122, 123, 124, 126), there may be a camera capable of photographing the target object (170), and the following description may be equally applicable to such cameras. For example, if there are at least two cameras capable of photographing the moving target object (170), the processor (210) may re-determine such cameras as target cameras and perform the following operations for each camera.

[0116] In one embodiment, the processor (210) may determine a target shooting setting that indicates an FOV for shooting the moved target object (170) among one or more shooting settings of the camera 5 (125) based on the location of the moved target object (170) within the game space (110). The processor (210) may transmit a control signal (180) to the camera 5 (125) that instructs to shoot the moved target object (170) according to the target shooting setting. The camera 5 (125), which was shooting the game space (110) based on the FOV (R5), may shoot the moved target object (170) based on the FOV (R5') indicated by the target shooting setting according to the control signal (180). In addition, the camera 5 (125) may transmit image data of the target sports game shot according to the target shooting setting to the device (110). In this way, dynamic sports game broadcasting is possible by quickly changing the camera that will capture the target object (170) and the shooting settings of the camera in response to the occurrence of an event and the movement of the target object (170).

[0117] FIG. 8 is a diagram illustrating a learning model (800) trained to determine camera shooting settings in a sports game. In one embodiment, the learning model (800) may be a model that is trained to determine camera shooting settings in a sports game using learning data (810) for other sports games during the learning process, and generates output data (830) indicating camera shooting settings in a target sports game from input data (820) for the target sports game during the inference process.

[0118] For example, the processor (210) may input the first camera control data of the target sporting event as input data (810) to the learning model (800) before the start of the target sporting event (before receiving the video data (130) of the target sporting event), and obtain one or more shooting settings of each of one or more cameras (121, 122, 123, 124, 125, 126) as output data (830) of the learning model (800).

[0119] For example, the first camera control data may include event data (“first event data”) indicating one or more events that may occur in the subject of the target sporting event and target objects to be tracked for each event, position data (“first position data”) indicating the positions of one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sporting event, performance data (“first performance data”) indicating the performance of one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sporting event, etc. Here, the first performance data may indicate an up / down rotation range indicating a maximum up / down rotation angle of each of the one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sporting event, a left / right rotation range indicating a maximum left / right rotation angle, a zoom ratio range indicating a maximum zoom ratio and a minimum zoom ratio, etc.

[0120] For example, each of the one or more shooting settings determined by the learning model (800) may include values ​​indicating a target event, a target object to be tracked for the target event, an FOV for capturing the target object to be tracked, etc. For example, a value indicating a target event may include an event identifier (e.g., an event number, an event name), etc. For example, a value indicating a target object to be tracked may include an object identifier (e.g., an object number, an object name), a number of objects, etc. For example, a value indicating a FOV for capturing the target object to be tracked may include a vertical rotation angle, a horizontal rotation angle, a zoom magnification, etc. Additionally or alternatively, each of the one or more shooting settings may further include a rank.

[0121] In one embodiment, during the learning process, the learning model (800) may be a model trained using video data of another sporting event as learning data (810). Here, the other sporting event may refer to one or more sporting events of the same type as the target sporting event.

[0122] For example, video data from another sporting event may refer to video from another sporting event captured by one or more cameras, each controlled by one or more administrators (e.g., camera operators). For example, video data from another sporting event may refer to video from another sporting event captured by one or more administrators directly controlling the cameras according to a predetermined broadcast scenario. Here, the broadcast scenario may be defined by a cue sheet that records one or more cues for broadcast screen transitions, graphic exposures, advertisements, replays, data content, etc.

[0123] For example, the learning model (800) may be a model trained by analyzing video data of another sporting event to generate second camera control data of the other sporting event, and using the second camera control data and the shooting settings that indicate the FOV of the camera that filmed the object for the event that occurred in the other sporting event as learning data (810). Here, the shooting settings that indicate the FOV of the target camera that filmed the target object for the event that occurred in the other sporting event may include the up / down rotation angle, left / right rotation angle, zoom magnification, etc. of the target camera as a result of the manager directly (manually) controlling the target camera to film the target object. In other words, the learning model (800) may be a model trained to determine the shooting settings of the camera through learning data (810) that has as input / output pairs the shooting settings of the camera that filmed the object for the event and the event that occurred in the other sporting event.

[0124] For example, the second camera control data may include event data (“second event data”) indicating one or more events that occurred in another sporting event and objects to be tracked for each event, location data (“second location data”) indicating the locations of one or more cameras that filmed another sporting event, or performance data (“second performance data”) indicating the performance of one or more cameras that filmed another sporting event. Here, the second performance data may indicate a vertical rotation range indicating a maximum vertical rotation angle of each of one or more cameras that filmed another sporting event, a horizontal rotation range indicating a maximum horizontal rotation angle, a zoom range indicating a maximum zoom ratio and a minimum zoom ratio, and the like.

[0125] Meanwhile, in the inference process, the processor (210) inputs the first camera control data of the target sports event into the learned learning model (800) as described above, so as to obtain one or more shooting settings of each of one or more cameras (121, 122, 123, 124, 125, 126) that will film the target sports event as output data (830) of the learning model (800). That is, the processor (210) can obtain one or more output settings of any one of the one or more cameras (121, 122, 123, 124, 125, 126) using the learning model (800).

[0126] Additionally or alternatively, the learning model (800) may be a model trained to determine (select) a target shooting setting from among one or more shooting settings of a camera. For example, it may be a model trained using, as learning data (810), second camera control data and shooting settings indicating an FOV of a camera that captured an object for an event that occurred in another sporting event. While capturing a target sporting event using one or more cameras (121, 122, 123, 124, 125, 126), the processor (210) may input an identifier (e.g., name, number) of an event that occurred in the target sporting event and one or more shooting settings of a target camera that can track and capture a target object (170) for the event as input data (820) of the learning model (800), and may obtain, as output data (830) of the learning model (800), a target shooting setting indicating an FOV for capturing the target object (170) from among the one or more shooting settings of the target camera. That is, the processor (210) can determine in real time the optimal target shooting settings of the target camera for shooting the target object (170) for an event using the learning model (800).

[0127] FIG. 9 is a diagram illustrating a method (900) for controlling a camera for broadcasting a sports game according to one embodiment of the present disclosure. The method (900) of the present disclosure can be performed by a device (100).

[0128] At step S910, the processor (210) can receive video data (130) (“first video data (130)”) of a target sports game from one or more cameras (121, 122, 123, 124, 125, 126).

[0129] At step S920, the processor (210) can detect whether an event (“first event”) occurs in the target sports game based on the first image data (130).

[0130] In one embodiment, in detecting whether a first event occurs in a target sporting event, the processor (210) generates motion data (150) indicating movement of one or more objects (115) within a sporting space (110) based on first image data, and detects whether a first event occurs in the target sporting event based on the motion data (150).

[0131] For example, in detecting whether a first event has occurred in a target sports game based on motion data (150), the processor (210) may determine, based on the motion data (150), whether any one of one or more objects (115) is located in a specific area within the playing space (110). For example, the specific area may be an area that serves as a standard for various judgments related to the flow of the game, such as the start of the game, the start of the game, the end of the game, or the result of the game, such as the score or win or loss of the game. In response to determining that any one of the one or more objects (115) is located in the specific area, the processor (210) may determine that a first event has occurred in the target sports game and determine an object (115) located in the specific area to be tracked and photographed as a target object (170) (“first object (170)”).

[0132] For example, in detecting whether a first event has occurred in a target sporting event based on motion data (150), the processor (210) may determine, based on the motion data (150), whether any one of the one or more objects (115) continues a specific movement for a predetermined period of time. For example, the specific movement may be an action related to the flow of the game, such as the start of the game, the start of the game, the end of the game, or the result of the game, such as the score or win or loss of the game. For example, the specific movement may be an action of a player dribbling the ball into the opposing team's defensive zone, an action of a player requesting a timeout, an action of a player exchanging the ball with an opposing player (rally), etc. In response to determining that any one of the one or more objects (115) continues a specific movement for a predetermined period of time, the processor (210) may determine that a first event has occurred in the target sporting event and determine the object (115) continuing the specific movement to be tracked and photographed as the first object (170).

[0133] In one embodiment, in detecting whether a first event occurs in a target sports game, the processor (210) may generate game situation data (160) indicating the game situation of the target sports game based on video data (130) of the target sports game, and detect whether the first event occurs in the target sports game based on the game situation data (160). Alternatively, the processor (210) may receive game situation data (160) indicating the game situation of the target sports game from an external device.

[0134] For example, in detecting whether a first event has occurred in a target sports game based on game situation data (160), the processor (210) may generate score data indicating a score and a score acquisition time of each of one or more objects (115) within the game space (110) based on the game situation data (160). The processor (210) may determine, based on the score data, whether any one of the one or more objects (115) has scored a score before a predetermined time. In response to determining that any one of the one or more objects (115) has scored a score before a predetermined time, the processor (210) may determine that a first event has occurred in the target sports game and determine at least one of the object (115) that has scored a score or the object (115) that has not scored a score as the first object (170) to be tracked and photographed. That is, if a player has scored a point before a predetermined time within the game space (110), the processor (210) may determine that a first event in which the player has scored a point has occurred, and may determine at least one of the player who has scored a point or the opposing player who has not scored a point as the first object (170) to be tracked and photographed by the camera.

[0135] For example, in detecting whether a first event occurs in a target sports game based on game situation data (160), the processor (210) may generate game time data indicating the game progress time based on the game situation data (160). The processor (210) may determine whether the target sports game has started or ended based on the game time data. In response to determining that the target sports game has not yet started, the processor (210) may determine that a first event has occurred in which one or more objects (115) within the game space (110) warm up, and may determine at least one of the one or more objects (115) within the game space (110) as the first object (170) to be tracked and photographed by a camera. In response to determining that the target sporting event has ended, the processor (210) may determine that a first event that the target sporting event has ended has occurred, and may determine a specific object (115) (e.g., a table) within the playing space (110) as the first object (170) to be photographed by the camera. Alternatively, the processor (210) may determine that a first event that the target sporting event has ended has occurred, and may determine at least one of the object (115) that won the event or the object (115) that lost the event based on score data as the first object (170) to be tracked and photographed by the camera. That is, the processor (210) may determine at least one of the player (coach) of the winning team or the player (coach) of the losing team in the target sporting event as the first object (170) to be tracked and photographed by the camera.

[0136] For example, in detecting whether a first event has occurred in a target sporting event based on match situation data (160), the processor (210) may generate rule violation data indicating the number of rule violations (e.g., fouls, penalties) and the time of rule violations of each of one or more objects (115) within the sporting space (110) based on the match situation data (160). The processor (210) may determine, based on the rule violation data, whether any one of the one or more objects (115) was involved in a rule violation before a predetermined time. In response to determining that any one of the one or more objects (115) was involved in a rule violation before a predetermined time, the processor (210) may determine that a first event involving a rule violation has occurred in the target sporting event and determine the object (115) involved in the rule violation as the first object (170) to be tracked and photographed by a camera. That is, the processor (210) can determine at least one of a player who committed a foul against an opposing player or an opposing player who was fouled in a target sports game as the first object (170) to be tracked and photographed by the camera.

[0137] In one embodiment, when detecting whether a first event occurs in a target sporting event, the processor (210) may detect whether an event occurs in the target sporting event based on audio data of the target sporting event. Here, the audio data may indicate the time and magnitude of sound generated at one or more locations within the sporting space (110). The processor (210) may generate audio data based on first image data (130) of the target sporting event or receive audio data from an external device.

[0138] For example, the processor (210) may determine the location of one or more objects (115) within the playing space based on the first image data (130) of the target sports game. The processor (210) may compare, at the location of each of the one or more objects (115), the sound level at a first point in time of the target sports game with the sound level at a second point in time after a predetermined time has elapsed from the first point in time, based on the sound data. Referring to object 1 among the one or more objects (115), the processor (210) may compare, at the location of object 1 within the playing space, the sound level generated at the first point in time during the playing time of the target sports game with the sound level generated at the second point in time. The processor (210) determines that a first event in which a sound becomes louder has occurred in the target sporting event in response to determining that the sound level at a second point in time is greater than or equal to the sound level at a first point in time at any one of the positions of one or more objects (115), and determines an object (115) at a position where the sound level at the second point in time is greater than or equal to the sound level at the first point in time among the one or more objects (115) as the first object (170) to be tracked and photographed by the camera. That is, the processor (210) can compare sounds generated at positions of spectators within the playing space (110) and determine an spectator at a position where a loud sound is generated due to shouting, etc., as the first object (170) to be photographed by the camera.

[0139] At step S930, the processor (210) may determine a camera ("first camera") capable of tracking and capturing a first object (170) for the first event according to one or more predetermined shooting settings ("one or more first shooting settings") among one or more cameras (121, 122, 123, 124, 125, 126) in response to detecting the occurrence of the first event. Here, each of the one or more first shooting settings of the first camera may indicate one or more FOVs of the first camera. That is, at step S930, the processor (210) may determine a first camera having at least one shooting setting indicating an FOV capable of capturing the first object (170) for the first event among the one or more cameras (121, 122, 123, 124, 125, 126).

[0140] Meanwhile, prior to steps S910 to S930, the processor (210) may input first camera control data of the target sporting event into a learning model (800) trained to determine camera shooting settings in a sporting event, thereby obtaining one or more first shooting settings of the first camera as an output of the learning model (800). That is, before the start of the target sporting event, the processor (210) may input first camera control data of the target sporting event into the learning model (800), thereby obtaining one or more first shooting settings of the first camera as an output of the learning model (800).

[0141] At step S940, the processor (210) may determine (select) a shooting setting (“second shooting setting”) that indicates an FOV (“first FOV”) that can capture the first object (170) among one or more first shooting settings of the first camera based on the location of the first object (170) within the game space (110) of the target sporting event.

[0142] In one embodiment, if there are at least two shooting settings that indicate an FOV capable of shooting a first object (170) among one or more first shooting settings of the first camera, the processor (210) may select a shooting setting with a higher ranking among such shooting settings.

[0143] In one embodiment, the processor (210) inputs an identifier of a first event and one or more first shooting settings of a first camera into a learning model (800) trained to determine (select) one of one or more shooting settings of a camera in a sports game, so as to obtain, as an output of the learning model (800), a second shooting setting indicating a first FOV capable of shooting a first object (170) from among the one or more first shooting settings of the first camera.

[0144] At step S950, the processor (210) can transmit a control signal (180) to the first camera instructing it to photograph the first object (170) according to the second photographing settings.

[0145] Additionally, the processor (210) can receive image data (“second image data”) of a target sports game captured from the first camera according to the second shooting settings.

[0146] For example, the processor (210) may generate a highlight video of a target sporting event based on the second image data. Alternatively, the processor (210) may transmit the second image data to an external device, thereby causing the external device to generate a highlight video of the target sporting event based on the second image data. For example, the highlight video may be a replay video.

[0147] For example, the processor (210) may determine, based on the second image data, whether the first object (170) is outside the first FOV indicated by the second shooting settings or whether only a portion of the entire shape of the first object (170) was captured in the first FOV. Here, whether the first object (170) is outside the first FOV indicated by the second shooting settings may mean whether the first object (170) exists in the image captured based on the first FOV. If the first object (170) does not exist in the image captured based on the first FOV, the processor (210) may determine that the first object (170) is outside the first FOV indicated by the second shooting settings. In addition, whether only a part of the entire shape of the first object (170) was captured in the first FOV may mean whether a shape less than a predetermined ratio (e.g., 30%) of the entire shape of the first object (170) was captured in the image captured based on the first FOV. If a shape less than a predetermined ratio (e.g., 30%) of the entire shape of the first object (170) was captured in the image captured based on the first FOV, the processor (210) may determine that only a part of the entire shape of the first object (170) was captured in the first FOV. If the first object (170) is out of the first FOV indicated by the second shooting setting or only a part of the entire shape of the first object (170) was captured in the first FOV, the processor (210) may determine whether there is another shooting setting among one or more first shooting settings of the first camera that indicates an FOV capable of capturing the first object (170). In response to determining that there are other shooting settings that dictate the FOV that can capture the first object (170), the processor (210) can transmit a control signal (180) to the first camera that dictates the first object (170) for the other shooting.In response to determining that there is no other shooting setting that indicates an FOV capable of shooting the first object (170), the processor (210) may determine another camera from among one or more cameras (121, 122, 123, 124, 125, 126) capable of shooting the first object (170), determine a shooting setting from among one or more first shooting settings of the determined other camera that indicates an FOV capable of shooting the first object (170), and transmit a control signal (180) to the determined other camera that instructs the camera to shoot the first object (170) according to the determined shooting setting.

[0148] For example, the processor (210) may detect, based on the second image data, whether an event different from the first event (“second event”) occurs in the target sports game. Here, the second event may mean a secondary situation caused by the first event. For example, if the first event is a game-ending event, the occurrence of the second event may mean that a situation occurred in which a player, spectator, etc. performed a special action (e.g., facial expression, gesture) following the game-ending event. In response to detecting the occurrence of the second event, the processor (210) may determine whether, among one or more first shooting settings of the first camera, there is a shooting setting that indicates an FOV (“second FOV”) that can capture a second object for the second event. Here, the size of the second object in the second FOV may be larger than the size of the second object in the first FOV. That is, the processor (210) may determine whether the first camera has a shooting setting for capturing a close-up of the second object. The processor (210) may, in response to determining that there is a shooting setting indicating a second FOV among one or more first shooting settings of the first camera, transmit a control signal (180) to the first camera that instructs the first camera to shoot a second object according to the shooting setting indicating the second FOV. Alternatively, the processor (210) may, in response to determining that there is no shooting setting indicating a second FOV among one or more first shooting settings of the first camera, determine a camera (the “second camera”) that can determine a second object according to a shooting setting indicating an FOV (“third FOV”) that at least partially overlaps the second FOV among one or more cameras (121, 122, 123, 124, 125, 126). The processor (210) may transmit a control signal (180) to the second camera that instructs the second camera to shoot a second object according to the shooting setting indicating the third FOV.This enables more dynamic sports game broadcasts by instantly capturing and filming objects for a second event that occurs secondarily due to a first event.

[0149] The method (900) proposed in this disclosure is not limited to sports, and can be applied to various sports, including ball games and non-ball games. The data provided as examples to illustrate the method (900) can be modified to suit the characteristics of each sport.

[0150] Below, an example of a soccer match is described.

[0151] FIG. 10 is a diagram illustrating a process for controlling a camera for broadcasting a soccer game according to the method (900) of FIG. 9. In one embodiment, the processor (210) may perform the method (900) to control a camera in a soccer game.

[0152] At step S910, the processor (210) can receive first image data (130) of the target soccer game from one or more cameras (121, 122, 123, 124, 125, 126).

[0153] At step S920, the processor (210) can detect whether a first event occurs in the target soccer game based on the first image data (130).

[0154] In one embodiment, in detecting whether a first event occurs in a target soccer game, the processor (210) generates motion data (150) indicating the movement of one or more objects (1010, 1020, 1030, 1040) within a game space (110) based on the first image data (130), and can detect whether a first event occurs in the target soccer game based on the motion data (150). In FIG. 10, the objects (1010, 1020) are players (1010, 1020) belonging to a first team of the target soccer game, the object (1030) is a player (1030) belonging to a second team, and the object (1040) is a ball (1040).

[0155] For example, the motion data (150) may include indicators indicating the movement of the player (1010, 1020, 1030) in the target soccer game, such as the movement direction, movement speed, movement time, movement trajectory, reaction time, posture, dribble, pass, and shooting.

[0156] For example, the motion data (150) may include indicators indicating the movement of the ball (1040), such as the movement direction, movement speed, movement time, movement trajectory, vertical launch angle, left and right direction angle, and number of spins of the ball (1040) in the target soccer game.

[0157] For example, in detecting whether a first event has occurred in a target soccer game based on motion data (150), the processor (210) may determine, based on the motion data (150), whether any one of one or more objects (1010, 1020, 1030, 1040) continues a specific movement for a predetermined period of time. Referring to the example of FIG. 10, if a player (1010) belonging to the first team dribbles the ball (1040) and continues to advance into the second team's defensive area for a predetermined period of time, the processor (210) may determine that a scoring opportunity event has occurred in the target soccer game, and may determine the player (1010) belonging to the first team and the ball (1040) as the first object (170) to be tracked and photographed. Additionally, the processor (210) can also determine another player (1020) belonging to the first team running from the opposite side of the player (1010) into the second team's defensive area as the first object (170) to be tracked and photographed.

[0158] At step S930, in response to detecting the occurrence of the first event, the processor (210) may determine a first camera capable of tracking and photographing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). Referring to the example of FIG. 10, the processor (210) may determine camera 5 (125) capable of tracking and photographing a player (1010) and a ball (1040) as the first camera. Additionally, the processor (210) may determine camera 2 (122) capable of tracking and photographing a player (1020) as the first camera.

[0159] At step S940, the processor (210) may determine (select) a second shooting setting indicating a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the position of the first object (170) within the game space (110) of the target soccer game. Referring to the example of FIG. 10, the processor (210) may determine a second shooting setting indicating a first FOV (R5') capable of shooting the player (1010) and the ball (1040) from among one or more first shooting settings of the camera 5 (125). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R2') capable of shooting the player (1120) from among one or more first shooting settings of the camera 2 (122).

[0160] At step S950, the processor (210) may transmit a control signal (180) to the first camera, which instructs to photograph the first object (170) according to the second shooting settings. Referring to the example of FIG. 10, the processor (210) may transmit a control signal (180) to the camera 5 (125), which instructs to photograph the player (1010) and the ball (1040) according to the second shooting settings indicating the first FOV (R5'). In addition, the processor (210) may transmit a control signal (180) to the camera 2 (122), which instructs to photograph the player (1020) according to the second shooting settings indicating the first FOV (R2'). Through this, camera 5 (125) can track and film the player (1010) and the ball (1040) based on the first FOV (R5') indicated by the second shooting setting, and camera 2 (122) can track and film the player (1020) based on the first FOV (R2') indicated by the second shooting setting.

[0161] Below, an example of a basketball game is described.

[0162] FIG. 11 is a diagram illustrating a process for controlling a camera for broadcasting a basketball game according to the method (900) of FIG. 9. In one embodiment, the processor (210) may perform the method (900) to control a camera in a basketball game.

[0163] At step S910, the processor (210) can receive first image data (130) of the target basketball game from one or more cameras (121, 122, 123, 124, 125, 126).

[0164] At step S920, the processor (210) can detect whether a first event occurs in the target basketball game based on the first image data (130).

[0165] In one embodiment, in detecting whether a first event occurs in a target basketball game, the processor (210) generates motion data (150) indicating movement of one or more objects (1110, 1120, 1130, 1140) within a game space (110) based on first image data (130), and can detect whether a first event occurs in the target basketball game based on the motion data (150). In FIG. 11, the objects (1110, 1120) are players (1110, 1120) belonging to a first team in the target basketball game, the object (1130) is a player (1130) belonging to a second team, and the object (1140) is a ball (1140).

[0166] For example, the motion data (150) may include indicators indicating the movement of the player (1110, 1120, 1130) in the target basketball game, such as the movement direction, movement speed, movement time, movement trajectory, reaction time, posture, dribbling, passing, shooting, and rebounding.

[0167] For example, the motion data (150) may include indicators indicating the movement of the ball (1140) in the target basketball game, such as the movement direction, movement speed, movement time, movement trajectory, vertical launch angle, left and right direction angle, and number of spins.

[0168] For example, in detecting whether a first event has occurred in a target basketball game based on motion data (150), the processor (210) may determine, based on the motion data (150), whether any one of one or more objects (1110, 1120, 1130, 1140) is located in a specific area within the playing space (110). Referring to the example of FIG. 11, if a player (1110) belonging to the first team dribbles the ball (1140) in the defensive area of ​​the first team within the playing space (110) and faces a player (1130) belonging to the second team, and another player (1120) belonging to the first team requests a pass to the player (1110) while being located in the defensive area of ​​the second team within the playing space (110), the processor (210) may determine that a pass opportunity event has occurred and determine the player (1120) belonging to the first team as the first object (170) to be tracked and photographed by a camera. Additionally, the processor (210) can determine the ball (1140) as the first object (170) to be tracked and photographed by the camera.

[0169] At step S930, in response to detecting the occurrence of a first event, the processor (210) may determine a first camera capable of tracking and photographing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). Referring to the example of FIG. 11, the processor (210) may determine camera 5 (125) capable of tracking and photographing a player (1120) as the first camera. Additionally, the processor (210) may determine camera 4 (124) capable of tracking and photographing a ball (1140) as the first camera.

[0170] At step S940, the processor (210) may determine (select) a second shooting setting indicating a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the position of the first object (170) within the game space (110) of the target basketball game. Referring to the example of FIG. 11, the processor (210) may determine a second shooting setting indicating a first FOV (R5') capable of shooting the player (1120) from among one or more first shooting settings of the camera 5 (125). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R4') capable of shooting the ball (1140) from among one or more first shooting settings of the camera 4 (124).

[0171] At step S950, the processor (210) may transmit a control signal (180) to the first camera, which instructs to photograph the first object (170) according to the second shooting settings. Referring to the example of FIG. 11, the processor (210) may transmit a control signal (180) to the camera 5 (125), which instructs to photograph the player (1220) according to the second shooting settings indicating the first FOV (R5'). In addition, the processor (210) may transmit a control signal (180) to the camera 4 (124), which instructs to photograph the ball (1240) according to the second shooting settings indicating the first FOV (R4'). Through this, camera 5 (125) can track and film a player (1220) based on the first FOV (R5') indicated by the second shooting setting, and camera 4 (124) can track and film a ball (1240) based on the first FOV (R4') indicated by the second shooting setting.

[0172] Below, an example of a tennis match is described.

[0173] FIG. 12 is a diagram illustrating a process for controlling a camera for broadcasting a tennis match according to the method (900) of FIG. 9. In one embodiment, the processor (210) may perform the method (900) to control the camera in a tennis match. Meanwhile, a tennis match may consist of one or more sets (games), and the outcome of the tennis match may be determined by the outcome of each set.

[0174] At step S910, the processor (210) can receive first image data (130) of the target tennis match from one or more cameras (121, 122, 123, 124, 125, 126).

[0175] At step S920, the processor (210) can detect whether a first event occurs in a target tennis match based on the first image data (130).

[0176] In one embodiment, in detecting whether a first event occurs in a target tennis match, the processor (210) generates match situation data (160) indicating a match situation of the target tennis match based on the first image data (130), and can detect whether a first event occurs in the target tennis match based on the match situation data (160). In FIG. 12, an object (1210) is a player (1210) of the first team, an object (1220) is a player (1220) of the second team, an object (1230) is a ball (1230), an object (1240) is a coach (1240) of the first team, and an object (1250) is a coach (1250) of the second team.

[0177] For example, the match situation data (160) may include indicators indicating the match situation of the target tennis match, such as the match progress time, rule violations by each team, set (game) scores of each team (player), scores of each team (player) per set, and referee decision results.

[0178] For example, in detecting whether a first event has occurred in a target tennis match based on match situation data (160), the processor (210) may generate score data indicating the score and the time of score acquisition of each player (1210, 1220) based on the match situation data (160). The processor (210) may determine whether any of the players (1210, 1220) has scored a point before a predetermined time based on the score data. In response to determining that the player (1210) of the first team has scored a point, the processor (210) may determine that a scoring event has occurred and determine the player (1210) as the first object (170) to be tracked and photographed. Additionally, the processor (210) may determine the player (1220) of the second team who has not scored a point as the first object (170) to be tracked and photographed. Additionally, the processor (210) may track and determine the coach (1240) of the first team as the first object (170) to be photographed. Additionally, the processor (210) may track and determine the coach (1250) of the second team as the first object (170) to be photographed.

[0179] At step S930, in response to detecting the occurrence of the first event, the processor (210) may determine a first camera capable of tracking and photographing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). Referring to the example of FIG. 12, the processor (210) may determine camera 2 (122), capable of tracking and photographing a player (1210), as the first camera. In addition, the processor (210) may determine camera 4 (124), capable of tracking and photographing a player (1220), as the first camera. In addition, the processor (210) may determine camera 5 (125), capable of tracking and photographing a coach (1240), as the first camera. Additionally, the processor (210) can determine camera 1 (121) capable of tracking and photographing the coach (1250) as the first camera.

[0180] At step S940, the processor (210) may determine (select) a second shooting setting indicating a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the position of the first object (170) within the match space (110) of the target tennis match. Referring to the example of FIG. 12, the processor (210) may determine a second shooting setting indicating a first FOV (R2') capable of shooting the player (1210) from among one or more first shooting settings of the camera 2 (122). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R4') capable of shooting the player (1220) from among one or more first shooting settings of the camera 4 (124). The processor (210) may determine a second shooting setting indicating a first FOV (R5') capable of shooting the coach (1240) from among one or more first shooting settings of the camera 5 (125). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R1') capable of shooting the coach (1250) from among one or more first shooting settings of the camera 1 (121).

[0181] At step S950, the processor (210) may transmit a control signal (180) to the first camera, which instructs to photograph the first object (170) according to the second shooting settings. Referring to the example of FIG. 12, the processor (210) may transmit a control signal (180) to the camera 2 (122), which instructs to photograph the player (1210) according to the second shooting settings indicating the first FOV (R2'). In addition, the processor (210) may transmit a control signal (180) to the camera 2 (122), which instructs to photograph the player (1220) according to the second shooting settings indicating the first FOV (R4'). Additionally, the processor (210) may transmit a control signal (180) to camera 5 (125) instructing it to photograph the coach (1240) according to a second shooting setting indicating a first FOV (R5'). Additionally, the processor (210) may transmit a control signal (180) to camera 1 (121) instructing it to photograph the coach (1250) according to a second shooting setting indicating a first FOV (R1'). Through this, camera 2 (1220) can track and film a player (1210) based on the first FOV (R2') indicated by the second shooting settings, camera 4 (124) can track and film a player (1220) based on the first FOV (R4') indicated by the second shooting settings, camera 5 (125) can track and film a coach (1240) based on the first FOV (R5') indicated by the second shooting settings, and camera 1 (121) can track and film a coach (1250) based on the first FOV (R1') indicated by the second shooting settings.

[0182] Hereinafter, an embodiment of a table tennis match will be described. Meanwhile, the processor (210) can perform a method (900) to control the camera of a table tennis match, similar to a tennis match. A table tennis match consists of one or more games, and the outcome of each game can determine the winner or loser of the match.

[0183] At step S910, the processor (210) can receive first image data (130) of the target table tennis match from one or more cameras (121, 122, 123, 124, 125, 126).

[0184] At step S920, the processor (210) can detect whether a first event occurs in the target table tennis match based on the first image data (130).

[0185] In one embodiment, in detecting whether a first event occurs in a target table tennis match, the processor (210) may generate motion data of one or more objects within a match space (110) of the target table tennis match based on first image data (130), and detect whether a first event occurs in the target table tennis match based on the motion data. In the target table tennis match, the objects may be a player of the first team, a player of the second team, a ball, a coach of the first team, a coach of the second team, etc.

[0186] For example, the processor (210) may determine that a first event has occurred in the target table tennis match in response to determining that one of a player of the first team, a player of the second team, or a ball is located in a target area based on motion data. For example, the processor (210) may determine that a serve preparation event has occurred in which one of a player of the first team or a player of the second team prepares a serve in response to determining that a ball is on the hand of one of a player of the first team or a player of the second team in response to determining that a serve preparation event has occurred in which one of a player of the first team or a player of the second team prepares a serve. The processor (210) may determine that at least one of a player preparing a serve, a ball on the hand of a player preparing a serve, or a player preparing to receive a serve is tracked by a camera and captured as a first object (170).

[0187] For example, the processor (210) may determine that a first event has occurred in the target table tennis match based on motion data, in response to determining that one of the players of the first team, the players of the second team, or the ball continues the target movement for a predetermined time (number of times). For example, the processor (210) may determine that a rally event has occurred in which the players of the first team and the players of the second team rally, in response to determining that one of the players of the first team, the players of the second team, or the ball continues the target movement for a predetermined time (number of times). The processor (210) may determine that at least one of the players of the first team, the players of the second team, or the ball is the first object (170) to be tracked and photographed by the camera. For example, in response to determining that either a player of the first team or a player of the second team has made a motion requesting a timeout for a predetermined amount of time based on motion data, the processor (210) may determine that a timeout event has occurred in which either a player of the first team or a player of the second team has requested a timeout. The processor (210) may determine that the player requesting the timeout or the coach of the opposing team of the player is the first object (170) to be tracked and filmed by the camera.

[0188] In one embodiment, when detecting whether a first event occurs in a target table tennis match, the processor (210) may generate match situation data (160) indicating the match situation of the target table tennis match based on the first image data. Alternatively, the processor (210) may receive match situation data (160) indicating the match situation of the target table tennis match from an external device. The processor (210) may detect whether a first event occurs in the target table tennis match based on the match situation data (160).

[0189] For example, the processor (210) may determine the progress time of the target table tennis match based on the match situation data (160). In response to determining that the target table tennis match has not yet started based on the progress time, the processor (210) may determine that a warm-up event has occurred in which players from the first team and players from the second team warm up before the start of the target table tennis match. The processor (210) may determine that at least one of the players from the first team or the players from the second team is the first object (170) to be tracked and photographed by the camera.

[0190] For example, the processor (210) may generate score data indicating the score and the time of score acquisition of each of the players of the first team and the players of the second team in the target table tennis match based on the match situation data (160). In response to determining that either the player of the first team or the player of the second team has scored a score before a predetermined time based on the score data, the processor (210) may determine that a scoring event in which either the player of the first team or the player of the second team has scored a score has occurred. That is, the processor (210) may determine that a rally end event in which the player of the first team and the player of the second team have finished playing a rally has occurred. In response to detecting the occurrence of the rally end event, the processor (210) may determine that at least one of the player who scored a score or the player who did not score a score is the first object (170) to be tracked and photographed by the camera. In response to determining that the score of either a player of the first team or a player of the second team is a predetermined value based on the score data, the processor (210) may determine that a game-ending event has occurred. In response to detecting the occurrence of the game-ending event, the processor (210) may determine that at least one of the player of the first team, the player of the second team, the coach of the first team, or the coach of the second team is the first object (170) to be tracked and photographed by the camera.

[0191] For example, the processor (210) may determine the progress time of a target table tennis match based on match situation data (160). In response to determining that the target table tennis match has ended based on the progress time, the processor (210) may determine that a match end event has occurred. In response to detecting the occurrence of a match end event, the processor (210) may determine a table tennis table within the match space (110) as an object to be captured by the camera.

[0192] At step S930, the processor (210) may determine a first camera capable of tracking and capturing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126) in response to detecting the occurrence of the first event. For example, one or more first shooting settings of the first camera may be configured as shown in the table below. Meanwhile, the examples below are merely examples for explaining the method (900) of the present disclosure, and the present disclosure is not limited thereto.

[0193] Shooting Setting Number Event Tracking Target Object FOV1 Start of game (warm-up) One or more players can be filmed with the upper body of one or more players positioned in the center FOV2 Preparation for serve after game starts Player preparing to serve Close-up filming of the face of the player preparing to serve FOV3 Ball in the hand of the player preparing to serve Close-up filming of the ball in the hand of the player preparing to serve FOV4 Player preparing to receive a serve Close-up filming of the face of the player preparing to receive the server FOV5 During a rally One or more players participating in a rally One or more players participating in a rally and the half court of the table tennis table in front of that player FOV6 Ball in motion during a rally One or more players participating in a rally and the half court of the table tennis table in front of that player FOV7 Players participating in a rally Both players participating in a rally FOV8 Score (end of rally) Player who scored Close-up filming of the face of the player who scored FOV9 Scored FOV10 to film the upper body of a player who scored a goal FOV11 to film a close-up of the face of a player who did not score FOV12 to film the upper body of a player who did not score Timeout Player who requested a timeout FOV13 to film the player who requested a timeout and the coach of the opposing team Game end Player who won by scoring a predetermined number of points in the game FOV14 to film the upper body of a player who won by scoring a predetermined number of points in the game Coach of the team to which the player who won by scoring a predetermined number of points in the game Coach of the team to which the player who won by scoring a predetermined number of points in the game FOV15 to film the upper body of a player who lost by scoring a predetermined number of points in the game FOV16 to film the upper body of a player who lost by scoring a predetermined number of points in the game Coach of the team to which the player who lost by scoring a predetermined number of points in the gameFOV17 that can film the coach of the team that the losing player belongs to. FOV that can film the table tennis table at the end of the game.

[0194] At step S940, the processor (210) may determine (select) a second shooting setting that indicates a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the position of the first object (170) within the match space (110) of the target table tennis match.

[0195] At step S950, the processor (210) can transmit a control signal (180) to the first camera instructing it to photograph the first object (170) according to the second photographing settings.

[0196] Below, an example of a baseball game is described.

[0197] FIG. 13 is a diagram illustrating a process for controlling a camera for broadcasting a baseball game according to the method (900) of FIG. 9. In one embodiment, the processor (210) may perform the method (900) to control a camera in a baseball game.

[0198] At step S910, the processor (210) can receive first image data (130) of the target baseball game from one or more cameras (121, 122, 123, 124, 125, 126).

[0199] At step S920, the processor (210) can detect whether a first event occurs in the target baseball game based on the first image data (130).

[0200] In one embodiment, in detecting whether a first event occurs in a target baseball game, the processor (210) generates motion data (150) indicating movement of one or more objects (1310, 1320, 1330, 1340, 1350) within a game space (110) based on the first image data (130), and can detect whether a first event occurs in the target baseball game based on the motion data (150). In FIG. 13, the object (1310) is a pitcher (1310), the object (1320) is a catcher (1320), the object (1330) is a batter (1330), the object (1340) is an umpire (1340), and the object (1350) is a ball (1350). For the convenience of explanation, the explanation will focus on the pitcher (1310) and the ball (1350).

[0201] For example, motion data (150) may include indicators indicating the movement of the pitcher (1310), such as the pitching posture and pitching time of the pitcher (1310) in the target baseball game.

[0202] For example, the motion data (150) may include indicators indicating the movement of the ball (1350), such as the moving direction, moving speed, moving time, moving trajectory, spin direction, and number of spins of the ball (1350) in the target baseball game.

[0203] For example, in detecting whether a first event occurs in a target baseball game based on motion data (150), the processor (210) may determine, based on the motion data (150), whether a pitcher (1310) continues a specific movement for a predetermined period of time. Referring to the example of FIG. 13, if a pitcher (1310) continues a pitching motion for a predetermined period of time, the processor (210) may determine that a pitching event has occurred in the target baseball game and may determine the ball (1350) to be tracked and photographed as the first object (170). In addition, the processor (210) may determine the catcher (1320) located opposite the pitcher (1310) to receive the ball (1350) as the first object (170) to be tracked and photographed.

[0204] At step S930, in response to detecting the occurrence of the first event, the processor (210) may determine a first camera capable of tracking and photographing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). Referring to the example of FIG. 13, the processor (210) may determine camera 5 (125) capable of tracking and photographing a ball (1350) as the first camera. Additionally, the processor (210) may determine camera 4 (124) capable of tracking and photographing a catcher (1320) as the first camera.

[0205] At step S940, the processor (210) may determine (select) a second shooting setting indicating a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the location of the first object (170) within the playing space (110) of the target baseball game. Referring to the example of FIG. 13, the processor (210) may determine a second shooting setting indicating a first FOV (R5') capable of shooting the ball (1350) from among one or more first shooting settings of the camera 5 (125). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R4') capable of shooting the catcher (1320) from among one or more first shooting settings of the camera 4 (124).

[0206] At step S950, the processor (210) may transmit a control signal (180) to the first camera, which instructs to photograph the first object (170) according to the second shooting settings. Referring to the example of FIG. 11, the processor (210) may transmit a control signal (180) to the camera 5 (125), which instructs to photograph the ball (1350) according to the second shooting settings indicating the first FOV (R5'). In addition, the processor (210) may transmit a control signal (180) to the camera 4 (124), which instructs to photograph the catcher (1320) according to the second shooting settings indicating the first FOV (R4'). Through this, camera 5 (125) can track and film the ball (1350) based on the first FOV (R5') indicated by the second shooting setting, and camera 4 (124) can track and film the catcher (1320) based on the first FOV (R4') indicated by the second shooting setting.

[0207] Below, examples of track and field events are described.

[0208] FIG. 14 is a diagram illustrating a process for controlling a camera for broadcasting a track and field event according to the method (900) of FIG. 9. In one embodiment, the processor (210) may perform the method (900) to control a camera in a track and field event.

[0209] At step S910, the processor (210) can receive first image data (130) of the target track and field event from one or more cameras (121, 122, 123, 124, 125, 126).

[0210] At step S920, the processor (210) can detect whether a first event occurs in the target track and field game based on the first image data (130).

[0211] In one embodiment, in detecting whether a first event occurs in a target track and field game, the processor (210) may generate motion data (150) indicating movement of one or more objects (1410, 1420, 1430) within a game space (110) based on first image data, and detect whether a first event occurs in the target track and field game based on the motion data (150). In FIG. 14, the objects (1410, 1420, 1430) may be players (1410, 1420, 1430) in the game, and the object (1440) may be a spectator (1440).

[0212] For example, motion data (150) may include indicators indicating the movement of the athlete (1410, 1420, 1430) in the target track and field event, such as the movement direction, movement speed, movement time, movement trajectory, posture change, movement distance, and distance remaining to the finish line.

[0213] For example, in detecting whether a first event has occurred in a target track and field game based on motion data (150), the processor (210) may determine, based on the motion data (150), whether any one of one or more objects (1410, 1420, 1430) is located in a specific area within the game space (110). Referring to the example of FIG. 14, if each of the players (1410, 1420, 1430) is located in an area where the remaining distance to the finish line is less than a predetermined distance, the processor (210) may determine that a competition event has occurred and may determine the players (1410) and (1420) as the first objects (170) to be tracked and photographed. Alternatively, the processor (210) may determine a specific part (e.g., a leg) of each of the players (1410) and (1420) as the first object (170) to be captured by tracking them. In addition, the processor (210) may determine a spectator (1440) as the first object (170) to be captured by tracking them.

[0214] At step S930, in response to detecting the occurrence of the first event, the processor (210) may determine a first camera capable of tracking and photographing a first object (170) for the first event according to one or more predetermined first shooting settings among one or more cameras (121, 122, 123, 124, 125, 126). Referring to the example of FIG. 14, the processor (210) may determine camera 5 (125) capable of tracking and photographing players (1410) and players (1420) as the first camera. Additionally, the processor (210) may determine camera 2 (122) capable of tracking and photographing spectators (1440) as the first camera.

[0215] At step S940, the processor (210) may determine (select) a second shooting setting indicating a first FOV capable of shooting the first object (170) from among one or more first shooting settings of the first camera based on the location of the first object (170) within the competition space (110) of the target track and field event. Referring to the example of FIG. 14, the processor (210) may determine a second shooting setting indicating a first FOV (R5') capable of shooting the player (1410) and the player (1420) from among one or more first shooting settings of the camera 5 (125). In addition, the processor (210) may determine a second shooting setting indicating a first FOV (R2') capable of shooting the spectator (1440) from among one or more first shooting settings of the camera 2 (122).

[0216] At step S950, the processor (210) may transmit a control signal (180) to the first camera, which instructs to photograph the first object (170) according to the second shooting settings. Referring to the example of FIG. 11, the processor (210) may transmit a control signal (180) to the camera 5 (125), which instructs to photograph the players (1410) and the players (1420) according to the second shooting settings indicating the first FOV (R5'). In addition, the processor (210) may transmit a control signal (180) to the camera 4 (124), which instructs to photograph the spectators (1440) according to the second shooting settings indicating the first FOV (R2'). Through this, camera 5 (125) can track and film the player (1510) and the player (1520) based on the first FOV (R5') indicated by the second shooting setting, and camera 2 (122) can track and film the spectator (1440) based on the first FOV (R2') indicated by the second shooting setting.

[0217] The methods according to the present disclosure may be implemented using a device having a computer or processor. While the steps of the methods are illustrated and described in a predetermined order in this disclosure, the steps may be performed in any order that can be arbitrarily combined according to the present disclosure, in addition to being performed sequentially. In one embodiment, at least some of the steps may be performed in parallel, iteratively, or heuristically. The present disclosure does not exclude variations or modifications to the methods. In one embodiment, at least some of the steps may be omitted, or other steps may be added.

[0218] Various embodiments of the present disclosure may be implemented as software recorded on a machine-readable recording medium. The software may be software for implementing the various embodiments of the present disclosure described above. The software may be inferred from various embodiments of the present disclosure by programmers skilled in the art to which the present disclosure pertains. For example, the software may be machine-readable instructions (e.g., code or code segments) or a program. The device may be a device capable of operating according to instructions called from a recording medium, such as a computer. In one embodiment, the device may be a device (100) according to embodiments of the present disclosure. In one embodiment, the processor of the device may execute the called instructions, causing components of the device to perform functions corresponding to the instructions. In one embodiment, the processor may be a processor (210) according to embodiments of the present disclosure. The recording medium may refer to a recording medium on which data is stored and readable by the device. The recording medium may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. In one embodiment, the recording medium may be memory (220). In one embodiment, the recording medium may also be implemented in a distributed form, such as in a network-connected computer system. Software may be distributed, stored, and executed in a computer system, etc. The recording medium may be a non-transitory recording medium. A non-transitory recording medium means a tangible medium regardless of whether data is stored semi-permanently or temporarily, and does not include a signal that is propagated transitorily.

[0219] Although the technical concept of the present disclosure has been described through various embodiments, the technical concept of the present disclosure encompasses various substitutions, modifications, and alterations that can be made within the scope understandable to those of ordinary skill in the art to which the present disclosure pertains. Furthermore, it should be understood that such substitutions, modifications, and alterations are included within the scope of the appended claims. Embodiments according to the present disclosure can be combined with each other. Each embodiment can be combined in various ways depending on the number of cases, and embodiments created by combining them also fall within the scope of the present disclosure.

Claims

communication circuit; one or more processors; and comprising one or more memories storing instructions executed by the one or more processors; Upon execution of the above instructions, the one or more processors, Receive first image data of a target sports event from one or more cameras through the above communication circuit, Based on the first image data, detecting whether a first event occurs in the target sports game, In response to detecting the occurrence of the first event, determining a first camera among the one or more cameras capable of tracking and capturing a first object for the first event according to one or more predetermined first shooting settings, wherein each of the one or more first shooting settings of the first camera indicates one or more FOVs (Field Of View) of the first camera; Based on the position of the first object within the playing space of the target sports game, a second shooting setting is determined that indicates a first FOV capable of shooting the first object among the one or more first shooting settings of the first camera, A device configured to transmit a control signal to the first camera, instructing the first camera to photograph the first object according to the second photographing settings, through the communication circuit. In the first paragraph, A device in which the first image data indicates an image set including one or more images obtained by dividing an image of the target sports game captured by the one or more cameras into predetermined frame units. In the first paragraph, A device wherein the first object for the first event comprises at least one of a player, a ball, or a spectator of the target sporting event. In the first paragraph, The one or more processors detect whether the first event occurs in the target sports game, Based on the first image data, motion data is generated that indicates the movement of one or more objects within the game space, A device configured to detect whether the first event occurs in the target sports game based on the motion data. In paragraph 4, The one or more processors detect whether the first event occurs in the target sports game based on the motion data. Based on the above motion data, determining whether any one of the one or more objects is located in a specific area within the game space; A device configured to determine that the first event has occurred in the target sporting event in response to determining that any one of the one or more objects is located in the specific area within the game space, and to track and determine the object located in the specific area within the game space as the first object to be photographed. In paragraph 4, The one or more processors detect whether the first event occurs in the target sports game based on the motion data. Based on the above motion data, determining whether any one of the one or more objects continues a specific movement for a predetermined period of time; A device configured to determine that the first event has occurred in the target sporting event in response to determining that any one of the one or more objects continues the specific movement for the predetermined period of time, and to track and determine the object continuing the specific movement within the sporting event space as the first object to be photographed. In the first paragraph, The one or more processors detect whether the first event occurs in the target sports game, Based on the first image data, game situation data indicating the game situation of the target sports game is generated, A device configured to detect whether the first event occurs in the target sports game based on the above game situation data. In paragraph 7, The one or more processors detect whether the first event occurs in the target sports game based on the game situation data. Based on the above game situation data, score data indicating the score and score acquisition time of each of one or more objects in the game space are generated, Based on the above score data, determine whether any one of the one or more objects has obtained a score before a predetermined time, A device configured to determine that the first event has occurred in the target sporting event and to determine the object that scored the point before the predetermined time as the first object to be tracked and photographed in response to determining that any one of the one or more objects has scored the point before the predetermined time. In paragraph 7, The one or more processors detect whether the first event occurs in the target sports game based on the game situation data. Based on the above game situation data, rule violation data indicating the number of rule violations and rule violation time of each of one or more objects in the game space is generated, Based on the above rule violation data, determine whether any one of the one or more objects was involved in a rule violation before a predetermined time, A device configured to determine that the first event occurred in the target sporting event and determine the object that was involved in the rule violation before the predetermined time, in response to determining that any one of the one or more objects was involved in the rule violation before the predetermined time, as the first object. In the first paragraph, The one or more processors detect whether the first event occurs in the target sports game, Acquire sound data of the above target sports event, wherein the sound data indicates the time and magnitude of sound generated at each location of one or more areas within the above game space, A device configured to detect whether a first event occurs in the target sports game based on the first image data and the audio data. In Article 10, The one or more processors detect whether a first event occurs in the target sports game based on the first image data and the sound data. Based on the first image data, generate frame-by-frame position data indicating the frame-by-frame position of one or more objects in the game space, wherein the frame-by-frame position data includes frame-by-frame three-dimensional coordinates of each of the one or more objects, Based on the above sound data and the frame-by-frame position data, at the location of each of the one or more objects, the loudness at a first point in time of the target sports game is compared with the loudness at a second point in time after a predetermined time has elapsed from the first point in time, A device configured to determine that the first event occurred in the target sporting event in response to a sound level at the second time point being greater than or equal to the sound level at the first time point at any one of the positions of each of the one or more objects, and to determine an object among the one or more objects at a position where the sound level at the second time point is greater than or equal to the sound level at the first time point as the first object. In the first paragraph, Each of said one or more first shooting settings of said first camera, Target event; One or more tracking target objects for the above target event; or Contains a value indicating at least one of the FOVs capable of photographing the one or more tracking target objects, A device wherein the value indicating the FOV capable of photographing the one or more tracking target objects includes at least one of a vertical rotation angle, a horizontal rotation angle, or a zoom factor. In the first paragraph, The one or more processors, prior to the start of the target sports game, A learning model trained to determine the shooting settings of a camera in a sports game is configured to input the first camera control data of the target sports game, and to obtain the one or more first shooting settings of the first camera as an output of the learning model. The above first camera control data is, First event data indicating one or more events that may occur in the above target sporting event and objects to be tracked for each event; First location data indicating the location of one or more cameras to film the target sport event; or A device comprising at least one of the first performance data indicating the performance of the one or more cameras for filming the target sporting event. In Article 13, A device wherein the performance data indicates at least one of a vertical rotation range, a horizontal rotation range, or a zoom ratio range of each of the one or more cameras. In Article 13, The above learning model is a model learned using as learning data the second camera control data of another sporting event of the same type as the target sporting event and the shooting settings indicating the FOV of the camera that shot the object for the event that occurred in the other sporting event. The above second camera control data is, Second event data indicating one or more events that occurred in the above other sporting event and the object to be tracked for each event; Second location data indicating the location of one or more cameras that filmed the other sporting event; or A device comprising at least one of the second performance data indicative of the performance of one or more cameras that filmed the other sporting event. In the first paragraph, One or more of the above processors, Receive third image data of the target sports game shot according to the second shooting settings from the first camera through the communication circuit, A device configured to generate a highlight video of the target sports game based on the third video data. In the first paragraph, One or more of the above processors, Receive second image data of the target sports game shot according to the second shooting settings from the first camera through the communication circuit, Based on the second image data, detecting whether a second event different from the first event occurs in the target sports game, In response to detecting the occurrence of the second event, determining whether there is a shooting setting among the one or more first shooting settings of the first camera that indicates a second FOV capable of shooting a second object for the second event, wherein a size of the second object in the second FOV is greater than a size of the second object in the first FOV; A device configured to transmit a control signal to the first camera instructing it to photograph the second object according to the photographing setting indicating the second FOV, in response to determining that there is a photographing setting indicating the second FOV among the one or more first photographing settings of the first camera. In the first paragraph, One or more of the above processors, Receive second image data of the target sports game shot according to the second shooting settings from the first camera through the communication circuit, Based on the second image data, detecting whether a second event different from the first event has occurred, Receive third image data of the target sports game shot according to the second shooting settings from the first camera through the communication circuit, Based on the third image data, detecting whether a second event different from the first event occurs, In response to detecting the occurrence of the second event, determining whether there is a shooting setting among the one or more first shooting settings of the first camera that indicates a second FOV capable of shooting a second object for the second event, wherein a size of the second object in the second FOV is greater than a size of the second object in the first FOV; In response to determining that there is no shooting setting indicating a second FOV capable of shooting the second object among the one or more first shooting settings of the first camera, a second camera capable of shooting the second object is determined according to a shooting setting indicating a third FOV that at least partially overlaps the second FOV among the one or more cameras, A device configured to transmit a control signal to the second camera instructing the second object to be photographed according to the shooting settings indicating the third FOV through the communication circuit. A method performed in a device comprising one or more processors and one or more memories storing instructions to be executed by the one or more processors, One or more of the above processors, A step of receiving first image data of a target sporting event from one or more cameras; A step of detecting whether a first event occurs in the target sports game based on the first image data; In response to detecting an occurrence of the first event, determining a first camera among the one or more cameras capable of tracking and photographing a first object for the first event according to one or more predetermined first shooting settings, wherein each of the one or more first shooting settings of the first camera indicates one or more FOVs of the first camera; A step of determining a second shooting setting that indicates a first FOV capable of shooting the first object among the one or more first shooting settings of the first camera based on the position of the first object within the game space of the target sports game; and A method comprising the step of transmitting a control signal to the first camera instructing the first object to be photographed according to the second photographing settings. In a non-transitory computer-readable recording medium having recorded thereon instructions to be executed by one or more processors, The above instructions, when executing the above instructions, cause the one or more processors to: Receive first video data of a target sporting event from one or more cameras, Based on the first image data, detecting whether a first event occurs in the target sports game, In response to detecting the occurrence of the first event, determining a first camera among the one or more cameras capable of tracking and photographing a first object for the first event according to one or more predetermined first shooting settings, wherein each of the one or more first shooting settings of the first camera indicates one or more FOVs of the first camera; Based on the position of the first object within the game space of the target sports game, a second shooting setting is determined that indicates a first FOV capable of shooting the first object among the one or more first shooting settings of the first camera, A non-transitory computer-readable recording medium that transmits a control signal to the first camera, instructing the first camera to photograph the first object according to the second photographing settings.

Images