JP7300668B2 - Play analysis device and play analysis method - Google Patents

Description

The present disclosure relates to a sports play analysis device and a play analysis method.

"Data Volley" is known as volleyball analysis software. Data Volley is used by analysts familiar with the software, who enter data into Data Volley that describes the condition of the team's players based on subjective judgment.

Patent Literature 1 discloses a scouting system with improved operability for analysts. Specifically, in Patent Document 1, the position information of each player is acquired using image analysis, and the input player situation, each position information of each player, and a still image of a desired scene are associated. It is disclosed that a database is constructed in a storage device by means of a player, and each player's position, a still image of a desired scene, and the player's situation are displayed. This invention solves the problems of Data Volley's software that the training of scorers (analysts) is required and the data accuracy is low because each player's position information is input by visual and subjective judgment.

In addition, conventional volleyball analysis software sequentially captures images of receiving scenes for serves, inputs skill evaluations of each player, and aggregates and displays the number of times each player has received, success rate of receiving, and the like. A user (such as a team manager) analyzes the team's strengths and weaknesses by looking at the aggregated results.

JP 2004-351097 A

Xina CHENG, Norikazu IKOMA, Masaaki HONDA and Takeshi IKENAGA "Multi-view 3D Ball Tracking with Abrupt Motion Adaptive System Model, Anti-occlusion Observation and Spatial Density based Recovery in Sports Analysis", IEICE TRANS. FUNDAMENTALS, VOL.E94-A, NO.1 JANUARY 2011

In the above-described conventional technology, for example, by sequentially capturing images at the moment of the setter's toss and inputting the skill evaluation of each player, each position of each player, a still image of a desired scene, the play situation, etc. can be displayed. However, it is difficult to immediately confirm the scene to be analyzed from the analysis results (analysis information and analysis images) obtained based on the skill evaluation of each player.

An object of the present disclosure is to provide a play analysis device and a play analysis method that can immediately confirm a scene to be analyzed from sports play analysis results.

A play analysis device according to an aspect of the present disclosure is a play analysis device that analyzes a sports play and generates a play analysis image, and analyzes a player's play using a play video to generate play information. and an analysis image generation unit for generating, as the play analysis image, a plurality of situation images representing the play situation of the player regarding common action types in the sport based on the play information and displaying them on a display device. and a video reproduction unit that reproduces a play video corresponding to the situation image in accordance with a user's operation for selecting at least one of the situation images.

A play analysis method according to an aspect of the present disclosure is a play analysis method in which a computer executes a program to analyze a sports play and generate a play analysis image. Play analysis is performed to generate play information, and based on the play information, as the play analysis image, a plurality of situation images representing the player's play situation regarding common action types in the sport are generated and displayed on a display device. Then, according to the user's operation for selecting at least one of the situation images, play video corresponding to the situation image is reproduced.

In addition, these general or specific aspects may be realized by systems, devices, methods, integrated circuits, computer programs, or recording media. may be realized by any combination of

According to the present disclosure, it is possible to immediately confirm the analysis target scene from the sports play analysis result.

It is a figure which shows the outline|summary of the play analysis system which concerns on embodiment. It is a figure which shows the example of a structure of the play analysis apparatus which concerns on embodiment. It is a figure which shows the example of UI (User Interface) which the play analysis apparatus which concerns on embodiment produces|generates. It is a figure which shows the example of the play information which concerns on embodiment. FIG. 10 is a diagram showing an example of a toss play analysis image according to the embodiment; It is a figure which shows an example of the play analysis image of the serve which concerns on embodiment. FIG. 12 is a diagram showing an example of another play analysis image of serve according to the embodiment; FIG. 10 is a diagram showing an example of continuous reproduction of play videos of a toss according to the embodiment; FIG. 10 is a diagram showing an example of simultaneous playback of play videos of a serve according to the embodiment; 7 is a flowchart showing play video reproduction processing according to the embodiment; It is a figure which shows an example of the sport applicable as analysis object of the play analysis apparatus which concerns on the modification of embodiment. It is a figure which shows an example of the sport applicable as analysis object of the play analysis apparatus which concerns on the modification of embodiment. FIG. 11 is a diagram showing an example of a ski play analysis image according to a modification of the embodiment; FIG. 11 is a diagram showing an example of simultaneous playback of ski play videos according to a modification of the embodiment; It is a figure showing an example of hardware constitutions concerning an embodiment of this indication.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid unnecessary verbosity in the following description and to facilitate understanding by those skilled in the art.

It should be noted that the accompanying drawings and the following description are provided for a thorough understanding of the present disclosure by those skilled in the art and are not intended to limit the claimed subject matter.

(Embodiment)
<Play analysis system>
First, an overview of a play analysis system according to one embodiment will be described with reference to FIG.

The play analysis system 1 is a system that analyzes a play video of a sport and reproduces the play video based on the analysis result. A sport may or may not be a ball game. A moving body used in ball games is typically a ball, but may be a shuttle or the like used in badminton. In this embodiment, volleyball, which is one of the ball games, will be described as an example. However, the play analysis system 1 is applicable to general ball games such as soccer, baseball, table tennis, basketball, tennis, rugby, American football, lacrosse, or badminton, as well as sports other than ball games such as skiing, ski jumping, track and field, and judo. It is possible. The play analysis system 1 can also be applied to moving bodies that do not fit the concept of "sphere", such as ice hockey pucks, curling stones, archery arrows, track and field spears, and hammers. In other words, the play analysis system 1 can be applied to any sport in which scores or wins and losses are determined by actions of a team composed of a plurality of people or individuals.

The play analysis system 1 includes a plurality of cameras 3 (3A, 3B, 3C, 3D), a display device 4, an input device 5, and a play analysis device 100.

A plurality of cameras 3 are installed at different positions. For example, as shown in FIG. 1, each camera 3 is installed at a position where the court 10 can be photographed from a different viewpoint (angle of view) from a high place. Although the number of cameras 3 is four in FIG. 1, the present embodiment is not limited to this, and the number of cameras 3 may be any number as long as it is two or more. By using two or more cameras 3, the three-dimensional position of the ball can be calculated.

Each camera 3 is communicably connected to the play analysis device 100 via wire or wireless. Each camera 3 captures the situation during the ball game and generates a captured image. Then, each camera 3 generates a moving image frame 201 (see FIG. 2) from a plurality of captured images. Each camera 3 then transmits the video frame 201 to the play analysis device 100 . The moving image frame 201 is composed of a plurality of photographed images, for example, MP4, H.264, etc. 264, H. H.265, or compressed based on a standard such as Motion JPEG.

The display device 4 is communicably connected to the play analysis device 100 via a wire or wirelessly, and displays an image output from the play analysis device 100 . The display device 4 is, for example, a liquid crystal display or an organic EL display.

The input device 5 is communicably connected to the play analysis device 100 via a wire or wirelessly, receives an operation from the user, and transmits the operation information to the play analysis device 100 . The input device 5 is, for example, a keyboard, mouse, microphone and/or touch panel. Note that the input device 5 and the display device 4 may be an integrated device.

The play analysis device 100 uses the moving image frames captured by each camera 3 to identify the player who performed the action on the ball. In volleyball, actions performed on the ball include serves, receptions, digs, tosses, attacks, and blocks. Hereinafter, a player who performs an action on the ball may be referred to as an "actor".

In the present embodiment, as shown in FIG. 1, the center point of the surface of the court 10 is the origin O, the axis parallel to the surface of the court 10 and parallel to the net 11 is the X axis, and the surface of the court 10 is parallel. The axis perpendicular to the net 11 is the Y-axis, and the axis perpendicular to the surface of the court 10 is the Z-axis. Regarding the X-axis, the direction away from the referee 12 is the positive direction, and the direction closer to the referee 12 is the negative direction. As for the Y-axis, the left direction as viewed from the referee 12 is the positive direction, and the right direction is the negative direction. The positive direction of the Z-axis is the direction away from the surface of the court 10 . That is, the Z-axis coordinate corresponds to the height from the court 10 surface.

<Play analysis device>
Next, the play analysis device 100 will be described with reference to FIG.

The play analysis device 100 includes a video reception unit 101 , a play analysis unit 102 , a UI control unit 103 , an analysis image generation unit 104 , a video reproduction unit 105 and a storage unit 106 .

The video receiving unit 101 receives moving image frames 201 transmitted from each of the cameras 3A to 3D and stores them in the storage unit 106. FIG.

The play analysis unit 102 analyzes a player's play using a play video composed of a plurality of continuous video frames 201, and generates play information 202 representing the player's play situation. The play analysis unit 102 then stores the play information 202 in the storage unit 106 . Details of the play analysis unit 102 will be described later.

The UI control unit 103 generates a UI 2000 as shown in FIG. 3 and displays it on the display device 4. FIG. Also, the UI control unit 103 receives an operation on the UI 2000 through the input device 5 .

The analysis image generation unit 104 generates a situation image 2110 representing the play situation of the player selected for analysis. The analysis image generation unit 104 then generates a play analysis image 2100 including the situation image 2110 and displays it on the UI 2000 . Details of the play analysis image 2100 and the analysis image generator 104 will be described later.

The video reproduction unit 105 reproduces the play video 2200 corresponding to the selected situation image 2110 on the UI 2000 according to the user's operation to select the situation image 2110 of the play analysis image 2100 . In addition, the video playback unit 105 can adjust the playback time according to the user's operation for setting the playback time of the play video 2200, and can hold the set playback time as a set value. The video reproducing unit 105 may have a function of reproducing real-time video being captured by the cameras 3A to 3D and recorded video of past play as the play video 2200. FIG. Details of the video reproduction unit 105 will be described later.

<Details of play analysis department>
Next, the details of the play analysis unit 102 will be described.

First, the play analysis unit 102 applies the method disclosed in Non-Patent Document 1, for example, to a plurality of moving image frames 201 stored in the storage unit 106, and determines the time at which the moving image frame 201 was shot (hereinafter referred to as " Calculate the three-dimensional position (x, y, z) and velocity of the ball at the "frame time"). Then, the play analysis unit 102 associates the frame time with the three-dimensional position and speed of the ball to generate the ball trajectory information 203 and stores it in the storage unit 106 .

Also, the play analysis unit 102 determines from the ball trajectory information 203 whether or not an action has occurred with respect to the ball. For example, the play analysis unit 102 calculates the trajectory of the ball from the three-dimensional position and velocity of the ball for each frame time included in the ball trajectory information 203 . Then, the play analysis unit 102 determines that an action on the ball has occurred when the calculated change in the trajectory of the ball satisfies a predetermined condition. When the play analysis unit 102 determines that an action has occurred, the play analysis unit 102 generates action information 204 by associating the frame time when the action occurred (hereinafter referred to as "action frame time") with the type of the action that occurred, Stored in the storage unit 106 .

Note that the play analysis unit 102 may determine the action type based on changes in the trajectory of the ball, the three-dimensional position and speed of the ball, sports rules, and the like. Action types in volleyball include serve, reception (receiving on serve), digging (receiving on attack), toss, attack, and block. For example, the play analysis unit 102 determines that the trajectory of the ball detected for the first time from the start of the analysis has a movement component in the Y-axis direction (long side direction of the court shown in FIG. 1), and the velocity component of the ball in the Y-axis direction is If it is within the predetermined range, the action type is determined as "serve". As another example, the play analysis unit 102 determines that the trajectory of the ball straddles the coordinates of the net 11 on the Y-axis after the "serve" and the change in the three-dimensional position of the ball changes from falling to rising (i.e. , when the change in the coordinate in the Z-axis direction turns positive), the action type is determined to be "reception". According to the rules of volleyball, the action of receiving a "serve" is a "reception", so making decisions based on such rules makes it possible to distinguish between a "reception" and a "dig".

Similarly, the play analysis unit 102 determines another action type based on determination criteria according to sports rules when the change in the trajectory of the ball, the movement of the player, and the like match predetermined conditions.

In the above description, three-dimensional information is used to determine whether an action has occurred. However, two-dimensional or one-dimensional information may be used to determine whether an action has occurred. For example, when judging the occurrence of a "serve" under the above conditions, it is possible to make the judgment only from the analysis start time and the information in the Y-axis direction without using the information in the X-axis direction and the Z-axis direction.

The play analysis unit 102 selects, from among the plurality of video frames 201 stored in the storage unit 106, the video frame corresponding to the action frame time included in the action information 204 and the frame time near the action frame time. Select the video frame to be used as the action frame. Next, the play analysis unit 102 detects an area in which the player (person) is captured (hereinafter referred to as "player area") from the action frame. For example, the play analysis unit 102 detects a player area from within the detection area using a player detection model (neural network) obtained by learning a plurality of player images during a game by deep learning. Then, the play analysis unit 102 recognizes the actor's uniform number from the action frame. For example, the play analysis unit 102 recognizes the actor's uniform number from within the detection area using a uniform number detection model (neural network) learned by deep learning from numerical images of uniforms of a plurality of players. Next, the play analysis unit 102 generates actor information 205 by associating the action frame time with the uniform number of the recognized actor, and stores the generated actor information 205 in the storage unit 106 .

The play analysis unit 102 associates the ball trajectory information 203 , the action information 204 , and the actor information 205 to generate play information 202 and stores it in the storage unit 106 . For example, when the action information 204 associates the action frame time T with the action type "attack", and the actor information 205 associates the action frame time T with the actor's uniform number "14", the play The analysis unit 102 generates play information 202 as shown in FIG. That is, as shown in FIG. 4, the play analysis unit 102 generates play information 202 in which the action type "attack" and the uniform number "14" of the actor are associated with the frame time T of the ball trajectory information 203. Generate. As a result, the user or other device uses the play information 202 to determine whether the player (actor) with the uniform number “14” is at the ball at the three-dimensional position (x _T , y _T , z _T ) at the frame time T. On the other hand, it can be known that the "attack" of the speed " _ST (km/h)" has been performed.

<Play analysis image>
Next, as specific examples of the play analysis images 2100, a toss play analysis image 2100A and a serve play analysis image 2100B will be described with reference to FIGS.

As shown in FIG. 5, the toss play analysis image 2100A is an image for analyzing the toss play of the analysis target player (typically the setter). The toss play analysis image 2100A is based on the front zone of the target player's court. Note that this front zone can be set to an arbitrary area (for example, the extension range of the default front zone + 1 m) by the user's operation. As shown in FIG. 6, the serve play analysis image 2100B is an image for analyzing the serve play of a player to be analyzed (typically, a player other than the setter). The play analysis image 2100B of the serve is based on the entire court. Note that the user can operate the cursor button 2120 of the play analysis image 2100 to rotate (invert, rotate 90 degrees, etc.) the area of the play analysis image 2100 with respect to the court.

<Details of analysis image generator>
Next, the details of the analysis image generation unit 104 will be described.

First, when generating the toss play analysis image 2100A, the analysis image generation unit 104 generates the play information 202 whose uniform number is the number of the analysis target player and whose action type is “toss” from the storage unit 106. to get Next, the analysis image generation unit 104 identifies the position where the analysis target player performed the toss from the ball coordinates of the acquired play information 202 . Then, as shown in FIG. 5, the analysis image generation unit 104 generates a play analysis image 2100A in which a circular situation image 2110A (2110) is arranged at the position where the target player performed the toss.

Further, when generating a play analysis image 2100B of a serve, the analysis image generation unit 104 retrieves from the storage unit 106 the play information 202 whose uniform number is the number of the player to be analyzed and whose action type is "serve". to get Next, the analysis image generation unit 104 identifies the trajectory of the ball served by the analysis target player from the ball coordinates of the acquired play information 202 . Then, as shown in FIG. 6, the analysis image generation unit 104 generates a play analysis image 2100B in which a linear situation image 2110B (2110) is arranged on the trajectory of the ball served by the target player.

From the play analysis image 2100 of the toss and serve described above, the user can visually grasp and analyze the play of the target player's toss and serve. It should be noted that the toss situation image 2110A may be displayed in a form that represents the play situation of the toss, in addition to the position where the toss was made. Toss play conditions include, for example, the type of toss, the speed of the ball during the toss, the height of the ball during the toss, and the movement distance of the ball during the toss. Further, the serve situation image 2110B may have a display form that represents the play situation of the serve other than the trajectory of the ball. The play status of the serve includes, for example, the type of serve, the speed of the ball of the serve, and the height of the hitting point. Examples of display forms that represent the play status of a toss or serve include shape, color, size, and a combination of multiple shapes. Further, as shown in FIG. 7, a play analysis image 2100B (2100) of a serve in which the serve passes over the net 11 when the court 10 is viewed from the side may be generated.

Note that the play analysis image 2100 for toss and serve may be displayed by the user performing the following operation.
(Step S11) When the user presses a toss analysis button (not shown) or a serve analysis button (not shown) on the UI 2000, the UI control unit 103 displays a list of players.
(Step S12) The user selects a player for toss or serve analysis from the displayed list of players.
(Step S<b>13 ) The analysis image generation unit 104 acquires a plurality of pieces of play information 202 regarding the selected target player from the storage unit 106 . When displaying the toss play analysis image 2100</b>A, the analysis image generation unit 104 extracts the play information 202 whose action type is toss from the acquired play information 202 . Then, analysis image generating section 104 identifies the ball coordinates of the extracted play information 202 as the position where the toss was performed, and generates play analysis image 2100A of the toss. On the other hand, when displaying the serve play analysis image 2100B, the analysis image generation unit 104 extracts the play information 202 whose action type is serve from the acquired play information 202 . Then, the analysis image generating unit 104 identifies the ball coordinates of the extracted play information 202 as the trajectory of the ball during the serve, and generates a serve play analysis image 2100B.
(Step S<b>14 ) The analysis image generation unit 104 displays the generated play analysis image 2100</b>A for the toss or the play analysis image 2100</b>B for the serve on the UI 2000 .

<Details of the video playback part>
Next, details of the video playback unit 105 will be described.

First, when the user performs a predetermined operation on the UI 2000 while the play analysis image 2100 is displayed on the UI 2000, the video playback unit 105 displays, for example, a playback time setting button (not shown) on the UI 2000. do. Then, when the user presses the playback time setting button, the video playback unit 105 displays a list (not shown) of settable playback times. The playback time displayed in the list includes, for example, the moment the target player touches the ball, a predetermined time before contact with the ball, a predetermined time after contact with the ball, a predetermined time including before and after contact with the ball, and There is an entire rally with actions to be analyzed. Note that the user may be allowed to set the playback time in units of seconds. Also, without setting the playback time by the user, for example, the automatic playback time from the selected action to the next action can be held as a default, or the user's favorite playback time can be held as a default for each action. , may require no user operation.

After the user sets the playback time, when the user performs an operation on the predetermined situation image 2110, the video playback unit 105 plays back the play video 2200 corresponding to this operation for the playback time set by the user. Also, when the user does not set the playback time, the video playback unit 105 plays back the play video 2200 with the same playback time as the previous playback. Note that the play video 2200 may always be played back for the same length of time without providing the video playback unit 105 with a function that allows the user to set the playback time.

For example, as shown in FIG. 5, when the user U performs a single selection operation P1 to select one situation image 2110A in a state where the toss play analysis image 2100A is displayed, the video playback unit 105 The play information 202 used to generate the image 2110A is specified. The single selection operation P1 includes a tap operation with a finger or a stylus of the user U, a contact operation for a predetermined time, or a click operation using a mouse. Note that when the single selection operation P1 is performed, the display form of the selected situation image 2110A may be changed so that the user can easily confirm whether or not the predetermined situation image 2110A has been selected. . The display form to be changed includes color, size, line type, and combinations thereof.

Next, based on the specified play information 202, the video playback unit 105 recognizes the frame time at which the toss was performed. Then, the video reproducing unit 105 reproduces the play video 2200 based on the recognized frame time.

Further, as shown in FIG. 5, when the user U performs the first multiple selection operation P2 of selecting a plurality of situation images 2110A, the video reproduction unit 105 reproduces each situation image 2110A similarly to the single selection operation P1. Recognize the frame time at which the toss corresponding to The first multiple selection operation P2 includes an area selection operation of surrounding at least part of each situation image 2110A with the user U's finger, stylus, or cursor. Note that when the first multiple selection operation P2 is performed, by displaying a loop-shaped selection area mark MC1 indicating the selection area or by changing the display form of the selected situation image 2110A, a predetermined The user may be able to easily check whether or not the situation image 2110A of is selected. The display form to be changed includes color, size, line type, and combinations thereof.

Then, based on the recognized frame time, the video reproducing unit 105 continuously reproduces the play video 2200 corresponding to each situation image 2110A one by one. For example, as shown in FIG. 8, the video playback unit 105 successively plays play videos 2200 corresponding to two situation images 2110A one by one.

Further, as shown in FIG. 6, when the user U performs a single selection operation P1 of selecting one situation image 2110B in a state where the play analysis image 2100B of the serve is displayed, the video reproduction unit 105 performs a toss. The play video 2200 of the serve corresponding to the situation image 2110B is reproduced in the same manner as in the case of reproducing the play video 2200 of .

Also, when the user U performs the second multiple selection operation P3 of selecting a plurality of situation images 2110B, the video playback unit 105 recognizes the frame time at which the serve corresponding to each situation image 2110B is performed. The second multiple selection operation P3 includes a tap operation and a click operation performed on a plurality of situation images 2110B at predetermined intervals. A finger or a stylus of the user U can be used for the tap operation, and a mouse can be used for the click operation. By changing the display form of the selected situation image 2110B when the second multiple selection operation P3 is performed, the user can easily confirm whether or not the predetermined situation image 2110B has been selected. You may make it possible. The display form to be changed includes color, size, line type, and combinations thereof. FIG. 6 illustrates a configuration for thickening lines.

Then, based on the recognized frame time, the video reproducing unit 105 arranges and simultaneously reproduces the play video 2200 corresponding to each situation image 2110B. For example, as shown in FIG. 9, the video reproduction unit 105 arranges the play videos 2200 corresponding to the two situation images 2110B horizontally and reproduces them simultaneously. In this simultaneous reproduction, the two images to be reproduced are reproduced simultaneously with reference to the moment when an action occurs in the two images to be reproduced. In this way, when two playback target videos are played back simultaneously with reference to the moment when an action occurs, for example, if the playback time is set from 2 seconds before the moment of the selected action to 1 second after the next action, The reproduction end timing of the reproduction target video may be different.
Also, when the playback times of two videos to be played are different, one of the videos to be compared may be played back slowly or quickly to match the timing from the start to the end. This makes it possible to more clearly compare differences in player postures. The speed ratio between slow playback and quick playback may be clearly displayed on the screen to clarify the difference in action speed. By adopting such a playback form, for example, when comparing from toss to attack in volleyball, the posture at the moment of the attack is good, but it takes a long time to reach that point, so the play is held on to the block. It is possible to grasp the situation.

Note that the single selection operation P1 for toss and serve may be an area selection operation surrounding at least part of one situation image 2110 . The single-choice operation P1 for toss and serve may be the same or different. At least one of the first multiple selection operation P2 and the second multiple selection operation P3 may be an operation of enclosing one situation image 2110 at a predetermined interval. When the second multiple selection operation P2 is performed on the toss situation image 2110A, the play videos 2200 may be displayed side by side and reproduced simultaneously, or may be reproduced continuously. The play video 2200 may be continuously reproduced when the first multiple selection operation P3 is performed on the serving situation image 2110B. The play videos 2200 may be played back simultaneously by arranging the play videos 2200 vertically, or by making one of the two play videos 2200 translucent and superimposing it on the other video and playing it back simultaneously.

<Processing flow>
Next, the play video reproduction processing flow in the play analysis device 100 will be described with reference to the flowchart shown in FIG.

First, the play analysis unit 102 generates play information 202 using the moving image frames 201 stored in the storage unit 106, and stores the play information 202 in the storage unit 106 (S1).

The analysis image generation unit 104 recognizes the player to be analyzed and the type of action according to the user's operation (S2). Then, the analysis image generation unit 104 generates a play analysis image 2100 corresponding to the analysis target player and action type, and displays it on the UI 2000 (S3).

The video playback unit 105 sets the playback time of the play video 2200 according to the user's operation (S4).The setting of the playback time can be omitted. In that case, a preset default playback time is read out and automatically set. This default playback time can be changed according to the user's operation. Next, the video playback unit 105 recognizes the selection operation of the situation image 2110 by the user (S5). Next, the video playback unit 105 selects the play video 2200 to be played and the playback mode (continuous playback or simultaneous playback when playing multiple play videos 2200) based on the selection operation recognized in S5. Specify (S6). Then, the video reproduction unit 105 reproduces the play video 2200 in the reproduction mode specified in S6 and in the reproduction time set in S4 (S7). Then, the flow ends (END).

<Summary of embodiment>
In this embodiment, play analysis device 100 receives video frames 201 from cameras 3A to 3D, analyzes a player's play using play video 2200 composed of a plurality of video frames 201, and obtains play information 202. Generate. Next, play analysis device 100 generates situation image 2110 representing the play situation based on play information 202 and displays it on display device 4 . Then, the play analysis device 100 reproduces the play video 2200 corresponding to the situation image 2110 according to the operation of the user U who selects the situation image 2110 . For example, when the user U performs a single selection operation P1 for selecting one situation image 2110A, the play analysis device 100 reproduces the play video 2200 corresponding to the situation image 2110A.

As a result, the user U can immediately check the play video 2200 to be analyzed after performing the selection operation of the situation image 2110 indicating the sports play analysis result.

Further, in the present embodiment, play analysis device 100 adjusts the playback time of play video 2200 according to the user's operation for setting the playback time of play video 2200 .

Thereby, the user U can selectively check the play scene that he/she wants to check.

Further, in the present embodiment, play analysis device 100 selects an area including a plurality of situation images 2110 according to first multiple selection operation P2 by user U who selects an area including a plurality of situation images 2110. 2200 is played continuously.

Thereby, the user U can continuously confirm the plurality of play videos 2200 by a simple operation of performing the first multiple selection operation P2. Further, if an operation surrounding a plurality of situation images 2110 is applied as the first multiple selection operation P2, the user U can confirm a plurality of play videos 2200 by performing one simple operation.

Further, in the present embodiment, play analysis device 100 generates play video 2200 corresponding to each of a plurality of situation images 2110 according to second multiple selection operation P3 by the user for individually selecting a plurality of situation images 2110. Simultaneous playback.

As a result, the user U can simultaneously check a plurality of play videos 2200 with a simple operation of performing the second multiple selection operation P3. In addition, the user U can compare the differences in the plays of the plurality of play videos 2200, and can easily grasp the good points and bad points of the plays. Further, when displaying a situation image 2110 having a maximum length equal to or greater than a predetermined value, such as the linear situation image 2110B related to the serve, if a tap operation is applied as the second multiple selection operation P3, the situation image 2110 can be displayed. The operation range can be reduced compared to the operation surrounding the .

(Modification of Embodiment)
Although specific examples of the present disclosure have been described in detail above, these are only examples, and the specific examples illustrated above may be variously modified and changed.

For example, as a sport to be analyzed, the one shown in FIG. 11 can be exemplified as a sport that can display the content of a technique as a situation image. As shown in FIG. 5 of the above-described embodiment, the technique shown in FIG. 11 can represent the type of technique, the situation when the technique is performed, etc. by the display form of the situation image such as circular or polygonal. Also, as sports to be analyzed, the one shown in FIG. 12 can be exemplified as a situation image in a graph format. As shown in FIG. 6 of the above-described embodiment, the technique shown in FIG. 12 can represent, for example, the movement trajectory of a moving object or a player, or the play environment such as water flow or wind direction, by means of a line display form. . Note that the play analysis unit 102 may generate the play information 202 corresponding to the contents of various sports so that the analysis image generation unit 104 generates the situation images having the contents shown in FIGS. 11 and 12 .

Also, in a sport as shown in FIG. 12, when using a situation image in which the trajectory of movement of a player is expressed in a graph format, the video playback unit 105 selects a part of the trajectory of movement according to the user's operation. A play video 2200 corresponding to a portion of the selected movement trajectory may be reproduced.

Specifically, first, based on the play information 202, the analysis image generating unit 104 generates linear situation images 2110C and 2110D (2110) showing the skiing situation of the player in the ski rotation event, as shown in FIG. , and a flag mark MF are displayed on the UI 2000 . In this state, when the user U performs a first partial selection operation P4 for selecting a part of the situation images 2110C and 2110D, the video playback unit 105 reproduces the frame of the skiing section RS1 corresponding to the selected part. Recognize time. The first partial selection operation P4 includes an area selection operation of enclosing a portion of the situation images 2110C and 2110D with the user U's finger, stylus, or cursor. Note that when the first partial selection operation P4 is performed, a loop-shaped selection area mark MC1 indicating the selection area is displayed, or the display form of the selection portion on the situation images 2110C and 2110D is changed. By doing so, the user may be able to easily check the selection range. The display form to be changed includes color, size, line type, and combinations thereof. Then, as shown in FIG. 14, the video reproducing unit 105 arranges and simultaneously reproduces the play videos 2200 of the skiing section RS1 selected by the first partial selection operation P4.

Further, the video reproducing unit 105 recognizes a second partial selection operation P5 different from the first partial selection operation P4 in a state where the play analysis images 2100C and 2100D shown in FIG. 13 are displayed. The second partial selection operation P5 includes a tracing operation of tracing a part of the situation images 2110C and 2110D. Note that, when the second partial selection operation P5 is performed, by displaying a tracing mark MC2 indicating the traced trajectory or by changing the display form of the selected portion on the situation images 2110C and 2110D, , the selection range may be easily confirmed by the user. Then, the video reproducing unit 105 continuously reproduces the play video 2200 of the traced running section.

In the state where the play analysis images 2100C and 2100D are displayed, when the first partial selection operation P4 is recognized, the play video 2200 may be continuously reproduced, or the second partial selection operation P5 may be performed. is recognized, the play video 2200 may be played back simultaneously.

As described above, by making play video 2200 to be reproduced only in the movement section of the player specified based on the first partial selection operation P4 and the second partial selection operation P5, the user U can You can selectively check the play scene you want to check.

In the above embodiments and modifications, the situation images 2110 that can be collectively selected may be analysis results of common action types in a plurality of different play videos 2200 of the same sport. For example, if the sport to be analyzed is volleyball, the situation images 2110 that can be collectively selected may be analysis results of the common action type "toss" in a plurality of different play videos 2200, as described above. The same applies to the action types "serve", "reception", "attack" and "block". Further, for example, when the sport to be analyzed is the “ski spin event”, the situation images 2110 that can be collectively selected are the analysis results of the common action type “turn” in the plurality of different play videos 2200, as described above. you can Further, for example, when the sport to be analyzed is figure skating, the situation images 2110 that can be collectively selected may be analysis results of the common action type “Lutz” in a plurality of different play videos 2200 . Thereby, the user can easily compare and reproduce a plurality of different play videos 2200 of a common action type.

In the above embodiments and modifications, the plurality of play videos 2200 reproduced based on one play analysis image 2100 may be the plays of different players, or the same player or different players in different games. It may be a play, or it may be a play of a different action type.
Further, for example, when the sport to be analyzed is volleyball, when the play video 2200 is played back for types such as serve and attack, it is possible to superimpose a flow line image representing the movement trajectory of the ball. In this way, by superimposing flow line images (single-color solid lines, dotted lines, highlight lines, shadowed flow lines, etc.) on the actual video, it is possible to obtain a dramatic effect on the reproduced video, and the user can see the video. can instantly grasp the situation of the whole play such as serve and attack.

As described above, the embodiments according to the present disclosure have been described in detail with reference to the drawings, and the functions of the play analysis device 100 described above can be realized by a computer program.

FIG. 15 is a diagram showing the hardware configuration of a computer that realizes the functions of each device by a program. This computer 3100 includes an input device 3101 such as a keyboard, mouse, or touch pad, an output device 3102 such as a display or speaker, a CPU (Central Processing Unit) 3103, a GPU (Graphics Processing Unit) 3104, a ROM (Read Only Memory) 3105, Read information from storage media such as RAM (Random Access Memory) 3106, hard disk drive or SSD (Solid State Drive) 3107, DVD-ROM (Digital Versatile Disk Read Only Memory) or USB (Universal Serial Bus) memory A reading device 3108 and a transmitting/receiving device 3109 for communicating via a network are provided, and each unit is connected by a bus 3110 .

Then, the reading device 3108 reads the program from the recording medium recording the program for realizing the functions of the respective devices, and stores the program in the storage device 3107 . Alternatively, the transmitting/receiving device 3109 communicates with a server device connected to the network, and causes the storage device 3107 to store the program for realizing the functions of the above devices downloaded from the server device.

Then, the CPU 3103 copies the program stored in the storage device 3107 to the RAM 3106, sequentially reads out instructions included in the program from the RAM 3106, and executes them, thereby realizing the functions of the respective devices.

Each functional block used in the description of the above embodiments is typically implemented as an LSI, which is an integrated circuit. These may be made into one chip individually, or may be made into one chip so as to include part or all of them. Although LSI is used here, it may also be called IC, system LSI, super LSI, or ultra LSI depending on the degree of integration.

Also, the method of circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after the LSI is manufactured, or a reconfigurable processor that can reconfigure connections and settings of circuit cells inside the LSI may be used.

Furthermore, if an integration technology that replaces the LSI appears due to advances in semiconductor technology or another technology derived from it, that technology may naturally be used to integrate the functional blocks. Application of biotechnology, etc. is possible.

One aspect of the present disclosure is useful in systems for analyzing sports.

1 play analysis system 3 (3A, 3B, 3C, 3D) camera 4 display device 5 input device 100 play analysis device 101 video reception unit 102 play analysis unit 103 UI control unit 104 analysis image generation unit 105 video reproduction unit 106 storage unit 201 Movie frame 202 Play information 203 Ball trajectory information 204 Action information 205 Actor information 2100, 2100A, 2100B, 2100C Play analysis images 2110, 2110A, 2110B, 2110C, 2110D Situation image 2200 Play image MC1 Selection area mark MC2 Tracing mark P1 Single selection operation P2 First multiple selection operation P3 Second multiple selection operation P4 First partial selection operation P5 Second partial selection operation

Claims (7)

A play analysis device that analyzes a sports play and generates a play analysis image,
a play analysis unit that analyzes the player's play using the play video and generates play information;
an analysis image generation unit that generates, as the play analysis image, a plurality of situation images representing the play situation of the player regarding a common action type in the sport based on the play information and displays them on a display device;
a video reproducing unit that reproduces a play video corresponding to the situation image in accordance with a user's operation for selecting at least one of the situation images;
A play analysis device. The video playback unit adjusts the playback time of the play video based on the playback time of the play video that can be set by the user.
The play analysis device according to claim 1. the sport is volleyball,
the common action type is toss or serve;
The play analysis device according to claim 1 . The video reproduction unit continuously reproduces the play video corresponding to each of the plurality of situation images in accordance with a user's operation for selecting an area including the plurality of situation images.
The play analysis device according to any one of claims 1 to 3 . The video reproduction unit simultaneously reproduces the play video corresponding to each of the plurality of situation images in accordance with a user's operation of individually selecting the plurality of situation images.
The play analysis device according to any one of claims 1 to 4 . The situation image represents the movement trajectory of the player as a play situation,
The video reproduction unit reproduces a play video corresponding to the selected part of the movement trajectory in accordance with a user's operation for selecting the part of the movement trajectory.
The play analysis device according to any one of claims 1 to 5 . A play analysis method in which a computer executes a program to analyze a sports play and generate a play analysis image,
Analyze the player's play using the play video to generate play information,
generating, as the play analysis image, a plurality of situation images representing the play situation of the player regarding a common action type in the sport based on the play information and displaying them on a display device;
playing back a play video corresponding to the situation image in accordance with a user's operation to select at least one of the situation images;
Play analysis method.

Images