WO2020255948A1 - Play analysis device, play analysis method, and computer program - Google Patents

Play analysis device, play analysis method, and computer program Download PDF

Info

Publication number
WO2020255948A1
WO2020255948A1 PCT/JP2020/023558 JP2020023558W WO2020255948A1 WO 2020255948 A1 WO2020255948 A1 WO 2020255948A1 JP 2020023558 W JP2020023558 W JP 2020023558W WO 2020255948 A1 WO2020255948 A1 WO 2020255948A1
Authority
WO
WIPO (PCT)
Prior art keywords
action
play
blocker
attack
analysis
Prior art date
Application number
PCT/JP2020/023558
Other languages
French (fr)
Japanese (ja)
Inventor
純子 上田
優麻 片山
井村　康治
Original Assignee
パナソニックＩｐマネジメント株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2020255948A1 publication Critical patent/WO2020255948A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B69/00—Training appliances or apparatus for special sports
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
    • A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion

Definitions

  • This disclosure relates to a play analyzer, a play analysis method, and a computer program.
  • Patent Document 1 requires training of a scorer (analyst), which is a drawback of Data Volley software, and the data accuracy is low because the position information of each competitor is input by visual subjective judgment.
  • a scouting system that solves problems such as these and improves the operability of analysts is disclosed. Specifically, accurate position information of each competitor is acquired by using image analysis, and the input competition situation, each position information of each competitor, and a still image of a desired scene are associated with the storage device. The operability of the analyst is improved by constructing a database and displaying each position of each competitor, a still image of a desired scene, and a competition situation.
  • the non-limiting examples of the present disclosure contribute to the provision of a technique capable of analyzing a specific action such as a block in detail.
  • the play analysis device is a play analysis device that analyzes the play of a ball game, and is a receiving unit that receives a plurality of images of the play and a moving body of the ball game in the plurality of images.
  • the first action related to the ball game and the second action after the first action are detected based on the trajectory of the ball game, and based on the image between the first action and the second action.
  • a control unit that detects a player who has performed a third action between the first action and the second action and displays an analysis result regarding the third action in the play.
  • FIG. 1 shows an example of a play analysis system according to an embodiment.
  • the play analysis system 1 is a system that analyzes a video of a ball game and recognizes a player who has performed an action on a moving body used in the ball game.
  • the moving body used in a ball game is typically a ball.
  • the moving body may be a shuttle or the like used for badminton.
  • volleyball which is one of the ball games
  • the play analysis system 1 can be applied to various ball games such as soccer, baseball, table tennis, basketball, tennis, rugby, American football, lacrosse, or badminton.
  • the play analysis system 1 can also be applied to a moving body having a shape that does not fit the concept of "sphere" such as an ice hockey pack. That is, the play analysis system 1 can be applied to any competition as long as the score or victory or defeat is determined by a team composed of a plurality of people performing an action on a moving body.
  • the play analysis system 1 includes a plurality of cameras 3 (3A, 3B, 3C, 3D), a play analysis device 100, a display device 210, and an operation device 220.
  • the plurality of cameras 3 are installed at different positions from each other.
  • each camera 3 is installed at a position where the court 10 can be photographed from a high place with different viewpoints (angles of view).
  • four cameras 3 are installed in FIG. 1, any number of cameras 3 may be installed as long as there are two or more cameras.
  • the three-dimensional position of the ball can be calculated.
  • the camera 3 is communicably connected to the play analyzer 100 via wire or wireless.
  • the camera 3 captures the play of the ball game and generates moving image data.
  • the camera 3 transmits the moving image data to the play analyzer 100.
  • the moving image data a plurality of frame images are composed of MP4, H. 264, H. It may be compressed based on a standard such as 265 or Motion JPEG.
  • the display device 210 is communicably connected to the play analysis device 100 via a wired or wireless device, and displays data output from the play analysis device 100.
  • the display device 210 is, for example, a liquid crystal display or an organic EL display.
  • the operation device 220 is communicably connected to the play analysis device 100 via wire or wireless, and accepts operations from the user.
  • the operation device 220 transmits the content of the operation to the play analysis device 100.
  • the operating device 220 is, for example, a keyboard, a mouse, a microphone, and / or a touch panel.
  • the operating device 220 and the display device 210 may be integrated devices.
  • the play analysis device 100 can be configured by a single PC, it may be configured by a plurality of PCs in order to distribute the load of the entire play analysis process.
  • a capture PC that captures video data of each camera (3A to 3D) and stores a frame image (still image) for each camera, and an analysis processing PC that receives a frame image from this capture PC and performs play analysis processing. It is possible to adopt a configuration divided into.
  • the "user" in the present embodiment may be any user of the play analysis system 1, may be a person involved in the competition such as a coach, a manager, a staff member, or a player, or may be a person other than the user. There may be.
  • the play analysis device 100 identifies the action of each player based on the moving image data transmitted from each camera 3.
  • Player actions in the case of volleyball are, for example, serve, reception (receive against serve), toss, attack, block, and dig (receive against attack).
  • the player who performed the action may be referred to as an "actor".
  • the center point of the surface of the coat 10 is the origin O
  • the axis parallel to the surface of the coat 10 and parallel to the net 11 is the X axis
  • the surface of the coat 10 The axis parallel to the net 11 and perpendicular to the net 11 is the Y axis
  • the axis perpendicular to the surface of the coat 10 is the Z axis.
  • the X-axis has a positive direction away from the referee 12 and a negative direction closer to the referee 12.
  • the Y-axis has a positive direction in the left direction and a negative direction in the right direction when viewed from the referee 12.
  • the Z-axis has a positive direction away from the surface of the coat 10. That is, the Z-axis coordinate z corresponds to the height of the coat 10 from the surface.
  • FIG. 2 shows a configuration example of the play analyzer 100.
  • the play analysis device 100 includes a reception unit 101, a trajectory calculation unit 103, an action detection unit 104, a blocker detection unit 105, a play information generation unit 106, a play analysis unit 107, and an information storage unit 108.
  • the locus calculation unit 103, the action detection unit 104, the blocker detection unit 105, the play information generation unit 106, and the play analysis unit 107 may be included in the control unit 102.
  • the receiving unit 101 receives moving image data from each of the cameras 3A to 3D and stores it in the information storage unit 108.
  • the locus calculation unit 103 applies, for example, the method of Non-Patent Document 1 to a plurality of frame images 111 constituting the moving image data, and three-dimensionally reduces the ball at the shooting time of the frame image 111 (hereinafter referred to as “frame time”). Calculate the position (x, y, z) and speed. Then, the locus calculation unit 103 generates the ball locus information 112 in association with the frame time, the three-dimensional position of the ball, and the velocity, and stores the ball locus information 112 in the information storage unit 108.
  • the action detection unit 104 detects which player performed what action at what timing based on the change in the trajectory of the ball indicated by the ball trajectory information. The details of the action detection unit 104 will be described later.
  • the blocker detection unit 105 determines a player (blocker) who has performed a block action between the toss and the attack based on the frame image 111 between the toss detected by the action detection unit 104 and the attack after the toss. To detect.
  • the blocker detection unit 105 generates the detected blocker information 114 and stores it in the information storage unit 108. Note that "toss” is an example of the first action, "attack” is an example of the second action, and "block” is an example of the third action. The details of the blocker detection unit 105 will be described later.
  • the play information generation unit 106 generates play information 115 based on the ball trajectory information 112, the action information 113, and the blocker information 114, and stores the play information 115 in the information storage unit 108.
  • FIG. 3 shows an example of play information 115.
  • the play information generation unit 106 relates the action information associated with the action frame time (T-15), the action type “toss” and the actor number “2”, and the action frame time (T-15) in the ball trajectory information 112.
  • the row L2 of the play information 115 is generated by using the time ball coordinates (x, y, z) and the ball velocity S.
  • the play information generation unit 106 has the action information 113 associated with the action frame time T, the action type “attack” and the actor number “14”, and the ball coordinates (x) at the action frame time T in the ball trajectory information 112.
  • T , y T , z T ) and ball velocity ( ST ) are used to generate line L4 of play information 115. That is, the play information 115 includes information indicating when, which player performed what action, and information indicating the movement of the ball at that time in the play of the ball game.
  • the play information generation unit 106 associates the blocker information 114 generated by the blocker detection unit 105 with the play information 115 from the toss to the attack.
  • the blocker information 114 includes the number of blocks, the first blocker number indicating the uniform number of the first blocker, the first blocker position indicating the position of the first blocker, and the back of the second blocker.
  • the second blocker number indicating the number, the second blocker position indicating the position of the second blocker, the third blocker number indicating the uniform number of the third blocker, and the third blocker position indicating the position of the third blocker. Including. If the number of detected blockers is less than 3, the undetected column may be blank.
  • the play information generation unit 106 may generate play information 115 that does not have a part of the items shown in FIG.
  • the play information generation unit 106 does not have to include items that are not used by the play analysis unit 107, which will be described later, in the play information 115.
  • the play analysis unit 107 analyzes the player's play from various viewpoints based on the play information 115, and generates and displays the play analysis result information which is the analysis result. The details of the play analysis unit 107 will be described later.
  • the action detection unit 104 calculates the trajectory of the ball from the three-dimensional position and speed of the ball for each frame time included in the ball trajectory information, and the calculated change in the trajectory of the ball, the three-dimensional position and speed of the ball, and predetermined conditions.
  • the time of the frame image 111 in which the action occurred (hereinafter referred to as “action frame time”) and the action type in which the action occurred are specified based on the rules of the ball game that match the above (S101).
  • the trajectory of the ball detected first at the start of analysis has a movement component in the Y-axis direction (the long side direction of the court shown in FIG. 1), and the velocity component of the ball in the Y-axis direction. Is within a predetermined range, the action type "serve” is detected.
  • the action detection unit 104 when the trajectory of the ball straddles the coordinates where the net 11 exists on the Y axis after the "serve", and the change in the three-dimensional position of the ball changes from descending to ascending (that is, Z).
  • the action type "reception" is detected.
  • the action to receive "serve” is “reception", so the judgment based on such rules can distinguish between “reception” and “dig”.
  • the action detection unit 104 also detects the action types "toss” and "attack” in the same manner. For example, if the trajectory (Z coordinate) of the ball changes from descending to ascending after detecting the reception or dig, the action type "toss” is detected. In addition, two actions have already been detected after the ball has crossed the net, the Y coordinate of the ball is within 150 cm from the net, the trajectory (Z coordinate) of the ball changes from descending to ascending, and then constant. When the ball speed in the frame is 40 km / h or more, the action type "attack" is detected.
  • the Y coordinate of the ball is within 70 cm from the net and two or more of the movement amounts of each coordinate change within 15 frames after the attack is detected (for example, the average movement amount of the past 3 frames and the movement amount). If the difference from the movement amount of the latest position is greater than or equal to the threshold value, it is judged that there has been a change), and the action type "block" is detected.
  • the action detection unit 104 sets the detection range of the actor for the frame image 111 (hereinafter referred to as "action frame”) at the action frame time and the time in the vicinity thereof (S102).
  • the action detection unit 104 recognizes the actor area from the detection range of the actor, and recognizes the uniform number of the actor from the actor area (S103).
  • the uniform number may be read as another term such as "actor number” or "uniform number”.
  • the action detection unit 104 generates action information 113 in which the action frame time, the action type, and the uniform number are associated with each other, and stores the action information 113 in the information storage unit 108 (S104).
  • the blocker detection unit 105 generates blocker information 114 and stores it in the information storage unit 108.
  • the blocker information 114 includes the number of blocks, information on the blocker (hereinafter referred to as “blocker information”), and an attack evaluation.
  • the blocker information includes the uniform numbers of the first to third blockers and the information indicating the positions of the first to third blockers.
  • the blocker is not necessarily limited to the player who jumped for the block.
  • the attack evaluation in the block information indicates whether or not the corresponding attack has scored. For example, the attack evaluation “ ⁇ ” shown in FIG. 3 indicates that the corresponding attack has become a score. In other words, an attack rating of " ⁇ " indicates that the block failed.
  • the blocker detection unit 105 has blocker information 114 at the timing when the player of the opponent team tosses (hereinafter referred to as “blocker information at the time of toss”) and blocker information 114 at the timing when the player of the opponent team attacks (hereinafter “attack”). "Time blocker information”) and may be generated.
  • the blocker detection unit 105 selects the frame image 111 of the two cameras 3 on the blocker side at the action frame time when the action detection unit 104 detects the toss (S201).
  • the frame image 111 of the camera 3 on the blocker side at the action frame time when the toss is detected is referred to as a “toss image”.
  • the blocker detection unit 105 extracts a partial image for detecting the blocker (hereinafter referred to as "blocker partial image") from each of the two toss images (S202).
  • the blocker detection unit 105 estimates the joints of a person for each of the two blocker partial images extracted in S202, and identifies the candidate position of the blocker's neck (S203).
  • the blocker detection unit 105 may specify a candidate position for the head of the blocker instead of the neck.
  • the blocker detection unit 105 may specify the position of the neck by averaging the positions of the head and both shoulders. As a result, even if one position is missing, the position of the person can be stably specified. Further, the blocker detection unit 105 may determine which direction the player is facing by using the positions of both shoulders, and may exclude the player who is not facing the direction of the net from the blocker candidates.
  • the blocker detection unit 105 determines the same player based on the candidate positions of the two blockers specified in S203, and identifies three or less blockers and their positions (S204). For example, the blocker detection unit 105 nets from a combination in which the distance between the vectors of the candidate positions of the two blockers is equal to or less than the threshold value and the neck position has a plausible height (for example, 1.5 m to 2.5 m). Select a combination that is close to.
  • the blocker detection unit 105 extracts the blocker image from the blocker partial image based on the joint position estimated in S203 of the blocker specified in S204, and recognizes the blocker uniform number (S205).
  • the blocker detection unit 105 generates blocker information at the time of tossing based on the position of the blocker specified in S204 and the uniform number of the blocker recognized in S104 (S206).
  • the blocker detection unit 105 selects the frame image 111 of the two cameras 3 on the blocker side at the action frame time of the attack after the toss detected by the action detection unit 104 (S207).
  • the frame image 111 of the camera 3 on the blocker side at the action frame time when the attack is detected is referred to as an “attack image”.
  • the blocker detection unit 105 extracts a blocker partial image from each of the two attack images (S208).
  • the density of blockers is higher during attack than during toss. Therefore, if the blocker partial image is extracted from the attack image as in the case of toss, there is a possibility that the individual blockers cannot be properly identified in the joint estimation of S208. Therefore, as illustrated in FIG. 6, the blocker detection unit 105 may extract the blocker partial image from the attack image by a method different from the extraction of the blocker partial image from the toss image. The details will be described later.
  • the blocker detection unit 105 estimates the joints of the person for each of the two blocker partial images extracted in S208, and identifies the candidate position of the blocker's neck (S209).
  • the blocker detection unit 105 determines the same player based on the candidate positions of the two blockers specified in S209, and identifies three or less blockers and their positions (S210).
  • the range of heights at which the neck position is plausible in this case may be wider than the range in the case of S204. This is to identify the blocker that is jumping.
  • the blocker detection unit 105 extracts the blocker image from the blocker partial image based on the joint position estimated in S209 of the blocker specified in S210, and recognizes the blocker uniform number (S211).
  • the blocker detection unit 105 generates blocker information at the time of attack based on the position of the blocker specified in S210 and the uniform number of the blocker recognized in S211 (S212).
  • the camera 3A located on the right side is referred to as a “right blocker side camera” and is located on the left side.
  • Camera 3B is referred to as "left blocker side camera”.
  • the blocker partial image extracted from the toss image is referred to as "toss blocker partial image” 310 (see FIG. 6).
  • the size and extraction range of the blocker partial image 310 at the time of tossing with respect to the toss image are set as follows, for example.
  • the following settings may be calibrated in advance before the match and may be fixed throughout the match.
  • the upper end of the net end (that is, the left end of the net) farther (that is, the back side) from the right blocker side camera in the toss image is set.
  • the upper left corner of the blocker partial image at the time of tossing see FIG. 6.
  • the upper end of the net end (that is, the right end of the net) farther (that is, the back side) from the left blocker side camera in the toss image is used.
  • the upper right corner of the blocker partial image 310 at the time of tossing is the length in the X direction of the toss blocker partial image 310.
  • the width is W.
  • the height H of the blocker partial image 310 at the time of tossing is set to a predetermined number of pixels. For example, when the height of the valley support is about 150 pixels to 250 pixels on the image, the height H of the blocker partial image 310 at the time of tossing is set to 300 pixels.
  • a toss blocker partial image 310 is extracted from a total of three frame images 111 including the frame image 111 at the start of toss and the frame images 111 before and after the frame image 111.
  • attack blocker partial image 320 (see FIG. 6).
  • attack blocker partial image 320 the blocker partial image extracted from the attack image
  • FIG. 7 when the length of the net 11 in the X direction is divided into three and the direction of the net 11 is viewed from behind the court on the blocker 21 side, the central divided section is referred to as the “central section”. It is described as 330C, the left division section is described as “left section” 330L, and the right division range is described as “right section” 330R.
  • the extraction range of the blocker partial image 320 at the time of attack with respect to the attack image is determined according to the position of the ball in the attack image, as illustrated below.
  • the blocker partial image 320 at the time of attack with respect to the attack image of the right blocker side camera is extracted as follows. That is, in the attack image, when the ball is located in the right section 330R, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located at the upper right end as shown in FIG. 8A. On the other hand, in the attack image, when the ball is located in the central section 330C or the left section 330L, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located in the upper center as shown in FIG. 8B. To. -The blocker partial image 320 at the time of attack with respect to the attack image of the left blocker side camera is extracted as follows.
  • the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located at the upper left end as shown in FIG. 8C.
  • the attack image when the ball is located in the central section 330C or the right section 330R, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located in the upper center as shown in FIG. 8D.
  • the width W and height H of the blocker partial image 320 at the time of attack are set to a predetermined number of pixels. For example, the width W and height H of the blocker partial image 320 at the time of attack are set to 450 pixels and 300 pixels.
  • the blocker partial image 320 at the time of attack is extracted from a total of three frame images 111 including the frame image 111 at the start of the attack and the frame images 111 before and after the frame image 111. That is, a total of six attack blocker partial images 320 are extracted from the frame images of the right blocker side camera and the right blocker side camera.
  • the play analysis unit 107 analyzes the player's play from various viewpoints based on the play information 115, and generates and displays the play analysis result information which is the analysis result. Next, some examples of play analysis result information are shown.
  • FIG. 9 shows a display example of a toss chart including the number of blocks.
  • the toss chart is an example of play analysis information.
  • the play analysis unit 107 generates and displays a toss chart including the number of blocks based on the play information 115.
  • the “ ⁇ ” mark 401 indicates the position where the toss was performed, and the number 402 in the vicinity of the mark 401 indicates the number of blocks performed for the toss.
  • the play analysis unit 107 displays the mark 401 at the position of the ball coordinates associated with the action type “toss” in the play information 115.
  • the play analysis unit 107 displays the number of blocks associated with the action type "toss” with a number 402 in the vicinity of the mark 401.
  • the number 402 may be displayed in the mark 401 of " ⁇ ".
  • the play analysis unit 107 may display a mark 401 having a different color or pattern depending on the number of blocks, instead of displaying the number 402.
  • the play analysis unit 107 may filter the display or non-display of the mark 401 according to the number of blocks. For example, when the user sets a filtering threshold value of 3 or more blocks, the play analysis unit 107 hides the ⁇ mark 401 associated with the number of blocks less than 3, and corresponds to the number of blocks 3 or more. The attached mark 401 is displayed.
  • ⁇ Block count graph> 10A and 10B show a display example of a graph showing the number of successes and failures of blocks.
  • the graph is an example of play analysis information.
  • the play analysis unit 107 displays a bar graph showing the number of successes and failures of blocks for each blocker based on the play information 115. For example, in the play information 115, the play analysis unit 107 determines that the block was successful when the action type that occurred next to the action type "attack" is "block" and the evaluation of the attack is not ⁇ . .. In the play information 115, the play analysis unit 107 determines that the block has failed if the evaluation of the action is ⁇ , or if the action type that occurs next to the action type “attack” is other than “block”. The play analysis unit 107 generates the bar graph shown in FIG. 10A by counting the number of successes and failures for each blocker.
  • the play analysis unit 107 displays a bar graph showing the number of successes and failures of blocks for each combination of blockers that flew against the attack based on the play information 115. For example, the play analysis unit 107 generates the bar graph shown in FIG. 10B by counting the number of successes and failures described above for each combination of blockers.
  • the graph showing the number of successful blocks may be painted in a different color or pattern from the graph showing the number of failed blocks.
  • ⁇ Attack direction chart> 11A and 11B show a display example of the attack direction chart.
  • the attack direction chart the trajectories of a plurality of attacks performed by one player during play are duplicated.
  • the attack direction chart is an example of play analysis information.
  • the play analysis unit 107 has a line (hereinafter referred to as “attack course”) 411 (411A, 411B, 411C) indicating the trajectory of the attacked ball, which has a different shape or a shape depending on the number of blocks for the attack. Display in color.
  • the play analysis unit 107 displays the attack course 411A of one block as a dotted line, the attack course 411B of two blocks as a alternate long and short dash line, and the attack course 411C of three blocks as a solid line. ..
  • the number of blocks for an attack is specified by the number of blocks associated with the action type "attack" in the play information 115.
  • the play analysis unit 107 displays the attack course 411 that has been scored in a different shape or color from the attack course 411 that has not been scored. For example, as shown in FIG. 11A, the play analysis unit 107 displays the scored attack course 411 with a thicker line than the non-scoring attack course 411. Whether or not the attack is a score is specified by whether or not the attack evaluation of the play information 115 is ⁇ .
  • the play analysis unit 107 may filter the display of the attack course 411 by the number of blocks.
  • FIG. 11B shows an example in which a part of the attack course 411 is hiddenly filtered from the attack direction chart shown in FIG. 11A by the operation of a user who specifies less than three blocks.
  • the play analysis unit 107 may filter the display of the attack course 411 by the operation of the user who specifies whether or not the attack is linked to the score. Further, the play analysis unit 107 may filter the display of the attack course by a combination of whether or not the attack is linked to the score and the number of blocks.
  • ⁇ Blocker position and attack course> 12A, 12B and 12C show an example of display of the blocker position and the attack course.
  • the blocker position and attack course are examples of play analysis result information.
  • the play analysis unit 107 displays the attack direction chart shown in FIG. 11A or FIG. 11B, and accepts the selection of the attack course from the user.
  • the play analysis unit 107 displays the uniform number and the position 421 of the blocker corresponding to the selected attack course 411, as shown in FIG. 12A. This allows the user to recognize at a glance where the attack has pulled out of the block. The blocker's uniform number does not have to be displayed.
  • the play analysis unit 107 displays the movement locus 422 of the toss ball and / or the movement locus 423A and 423B of the blocker corresponding to the selected attack course 411C.
  • the movement locus 423A of the blocker may be a straight line connecting the blocker position at the time of tossing and the blocker position at the time of attack.
  • the movement locus 423B of the blocker may continuously connect the blocker positions for each frame image 111 from the time of toss to the time of attack.
  • FIG. 12C by displaying the movement locus of the blocker in detail, the effect of a feint or the like on the blocker can be analyzed.
  • FIG. 13 shows a display example of the blocker center of gravity position and the attack course 411.
  • the position of the center of gravity of the blocker is, for example, the position of the blocker when there is one blocker, the midpoint of the positions of the two blockers when there are two blockers, and the position of the blocker when there are three blockers. It is the center of gravity of a triangle whose apex is the position of a human blocker.
  • the play analysis unit 107 displays an attack direction chart as shown in FIG. 11A or FIG. 11B, and accepts the user to select the attack course 411.
  • the play analysis unit 107 indicates the movement locus 422 of the toss ball and / or a plurality of blockers (avant-garde) corresponding to the selected attack course 411, as shown in FIG.
  • the movement locus 432 of the center of gravity position 431 of 3 people) is displayed.
  • the movement locus 432 of the center of gravity position 431 of the blocker is calculated based on each blocker position for each frame image 111 from toss to attack. This makes it possible to grasp the movement of the entire blocker from toss to attack.
  • FIG. 14 is a diagram for explaining the relationship between the position of the center of gravity of the blockers (three york-gardes) at the time of toss and the filtering for the toss chart.
  • the play analysis unit 107 sets a plurality of sections 441 in which the net width is divided.
  • the play analysis unit 107 identifies at least one tossed blocker center of gravity position 431 belonging to the selected section 441.
  • the play analysis unit 107 displays the toss mark 401 associated with the blocker center of gravity position 431 at the time of the specified toss on the toss chart as shown in FIG. 9, and hides the other toss marks 401. Perform filtering. This allows the user to analyze the relationship between the position of the entire blocker (center of gravity position) and the toss.
  • the play analyzer 100 includes a receiving unit 101 and a control unit 102.
  • the receiving unit 101 receives a plurality of frame images 111 captured by the plurality of cameras 3.
  • the control unit 102 detects a "toss” (first action) and an “attack” (second action) after the "toss” based on the ball trajectory information 112 of the ball during volleyball play. , Detects the player (blocker) who performed the "block” (third action) between the "toss” and the "attack” based on the frame image 111 between the "toss” and the "attack”. Display the analysis result for the block. With this configuration, the supervisor or the like can analyze the "block” from the displayed analysis result.
  • control unit 102 may display the position where the "toss” was performed and the number of players who "blocked” the "toss” at the position. This configuration allows the user to analyze how many blocks have been made to the toss.
  • control unit 102 may display a graph showing the number of successes and / or failures of the "block” for each player who performed the "block". This configuration allows the user to analyze the success and / or failure of each player's "block”.
  • control unit 102 may display a graph showing the number of successes and / or failures of the "block” for each combination of a plurality of players who have performed the "block".
  • the control unit 102 may display the trajectory of the "attacked” ball in a different manner depending on the number of players who "block” the "attack”. For example, the control unit 102 may filter and display the trajectory of the “attacked” ball as an analysis result according to the operation of the user who specifies the number of players who have performed the “block”. For example, the control unit 102 may filter and display the trajectory of the “attacked” ball as an analysis result according to the user's operation of specifying whether or not the “attack” is linked to the score. With this configuration, the user can analyze the number of blocks for an attack.
  • control unit 102 may display the trajectory of the "attacked” ball and the position of the player who "blocked” at the timing when the "attack” was performed. Further, the control unit 102 may display the movement locus of the player who performed the “block” from the "toss” to the "attack”. With this configuration, the user can analyze the position and movement trajectory of the blocker with respect to the attack.
  • control unit 102 may display the locus of the "attacked” ball and the movement locus of the center of gravity position specified based on the positions of the plurality of players who have performed the "block". With this configuration, the user can analyze the movement trajectory of the entire blocker with respect to the attack.
  • control unit 102 filters and displays the position where the "toss” is performed based on the position of the center of gravity specified from the positions of the plurality of players who performed the "block” at the timing of the "toss”. Good.
  • the user can analyze the relationship between the position of the entire blocker (position of the center of gravity) and the toss.
  • FIG. 15 is a diagram showing a hardware configuration of a computer that realizes the functions of each device by a program.
  • the computer 3100 includes an input device 3101 such as a keyboard or mouse and a touch pad, an output device 3102 such as a display or a speaker, a CPU (Central Processing Unit) 3103, a GPU (Graphics Processing Unit) 3104, and a ROM (Read Only Memory) 3105.
  • Read information from a recording medium such as RAM (Random Access Memory) 3106, hard disk device or storage device 3107 such as SSD (Solid State Drive), DVD-ROM (Digital Versatile Disk Read Only Memory) or USB (Universal Serial Bus) memory.
  • a reading device 3108 and a transmitting / receiving device 3109 that communicates via a network are provided, and each unit is connected by a bus 3110.
  • the reading device 3108 reads the program from the recording medium on which the program for realizing the function of each of the above devices is recorded, and stores the program in the storage device 3107.
  • the transmission / reception device 3109 communicates with the server device connected to the network, and stores the program downloaded from the server device for realizing the function of each device in the storage device 3107.
  • the CPU 3103 copies the program stored in the storage device 3107 to the RAM 3106, and sequentially reads and executes the instructions included in the program from the RAM 3106, whereby the functions of the above devices are realized.
  • the receiving unit 101 may be realized by the transmitting / receiving device 3109.
  • the control unit 102 may be realized by the CPU 3103 and / or the GPU 3104.
  • the information storage unit 108 may be realized by the RAM 3106 and / or the storage device 3107.
  • LSI is an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip so as to include a part or all of them. Although it is referred to as LSI here, it may be referred to as IC, system LSI, super LSI, or ultra LSI depending on the degree of integration.
  • the method of making an integrated circuit is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor.
  • An FPGA Field Programmable Gate Array
  • a reconfigurable processor that can reconfigure the connection and settings of circuit cells inside the LSI may be used.
  • One aspect of the present disclosure is useful for analyzing the play of ball games.
  • Play analysis system 3 3A, 3B, 3C, 3D camera 10 coat 11 net 12 referee 21 blocker 100 play analysis device 101 receiver 102 control unit 103 trajectory calculation unit 104 action detection unit 105 blocker detection unit 106 play information generation unit 107 Play analysis unit 108 Information storage unit 111 Frame image 112 Ball trajectory information 113 Action information 114 Blocker information 115 Play information 210 Display device 220 Operation device

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

This play analysis device comprises: a receiving unit 101 which receives a plurality of frame images 111 in which play is captured; and a control unit 102 which detects a first action relating to a ball game and a second action after the first action on the basis of the trajectory of a moving body for the ball game in the plurality of frame images 111, detects a player carrying out a specified action between the first action and the second action on the basis of the frame images 111 between the first action and the second action, and displays an analysis result relating to the specified action in relation to the play.

Description

プレイ分析装置、プレイ分析方法、及び、コンピュータプログラムPlay analyzer, play analysis method, and computer program
　本開示は、プレイ分析装置、プレイ分析方法、及び、コンピュータプログラムに関する。 This disclosure relates to a play analyzer, a play analysis method, and a computer program.
　従来、バレーボール分析ソフトウェアとして「Data Volley」が市販され、このソフトウェアに精通したアナリストの主観的判断に基づいて、チームの選手の状況をデータ化する技術が知られている。 Conventionally, "Data Volley" has been marketed as volleyball analysis software, and a technique for digitizing the situation of team players based on the subjective judgment of an analyst who is familiar with this software is known.
　特許文献１には、Data Volleyのソフトウェアの欠点であるスコアラー（アナリスト）のトレーニングが必要であること、各競技者の位置情報が視覚による主観的判断により入力されているためデータ精度が低いことなどの問題点を解決し、アナリストの操作性を向上させたスカウティングシステムが開示されている。具体的には、画像解析を用いて正確な各競技者の位置情報を取得し、入力された競技状況、各競技者のそれぞれの位置情報、所望のシーンの静止画像とを関連付けて記憶装置にデータベースを構築し、各競技者の各位置、所望のシーンの静止画像、競技状況を表示することにより、アナリストの操作性を向上させるものである。 Patent Document 1 requires training of a scorer (analyst), which is a drawback of Data Volley software, and the data accuracy is low because the position information of each competitor is input by visual subjective judgment. A scouting system that solves problems such as these and improves the operability of analysts is disclosed. Specifically, accurate position information of each competitor is acquired by using image analysis, and the input competition situation, each position information of each competitor, and a still image of a desired scene are associated with the storage device. The operability of the analyst is improved by constructing a database and displaying each position of each competitor, a still image of a desired scene, and a competition situation.
特開２００４－３５１０９７号公報Japanese Unexamined Patent Publication No. 2004-351907
　従来の技術は、バレーボールで言えば、サーブレシーブの瞬間に関するシーンの画像を順次取り込み、各選手の技能評価を入力する。そして、レシーブ回数及びレシーブ成功率等を選手ごとに集計し、その集計結果を一覧表示する。バレーボールの関係者（例えば、監督、コーチ、スタッフ及び選手等）は、この一覧表示された集計結果から、チーム内の強み及び弱みを把握する。 In volleyball, the conventional technology sequentially captures images of scenes related to the moment of serve receive and inputs the skill evaluation of each player. Then, the number of times of receiving, the success rate of receiving, etc. are totaled for each player, and the totaled results are displayed in a list. Volleyball players (eg, managers, coaches, staff, players, etc.) will understand the strengths and weaknesses of the team from the aggregated results displayed in this list.
　しかしながら、従来の技術では、例えばブロックといった特定のアクションを詳細に分析することは困難である。 However, with conventional technology, it is difficult to analyze a specific action such as a block in detail.
　本開示の非限定的な実施例は、例えばブロックといった特定のアクションを詳細に分析できる技術の提供に資する。 The non-limiting examples of the present disclosure contribute to the provision of a technique capable of analyzing a specific action such as a block in detail.
　本開示の一態様に係るプレイ分析装置は、球技のプレイを分析するプレイ分析装置であって、前記プレイを撮影した複数の画像を受信する受信部と、前記複数の画像における前記球技の移動体の軌跡に基づいて、前記球技に関する第１のアクションと前記第１のアクションの後の第２のアクションとを検出し、前記第１のアクションと前記第２のアクションとの間の画像に基づいて、前記第１のアクションと前記第２のアクションとの間に第３のアクションを行った選手を検出し、前記プレイにおける前記第３のアクションに関する分析結果を表示する制御部と、を備える。 The play analysis device according to one aspect of the present disclosure is a play analysis device that analyzes the play of a ball game, and is a receiving unit that receives a plurality of images of the play and a moving body of the ball game in the plurality of images. The first action related to the ball game and the second action after the first action are detected based on the trajectory of the ball game, and based on the image between the first action and the second action. A control unit that detects a player who has performed a third action between the first action and the second action and displays an analysis result regarding the third action in the play.
　なお、これらの包括的または具体的な態様は、システム、装置、方法、集積回路、コンピュータプログラム、または、記録媒体で実現されてもよく、システム、装置、方法、集積回路、コンピュータプログラムおよび記録媒体の任意な組み合わせで実現されてもよい。 It should be noted that these comprehensive or specific embodiments may be realized in a system, device, method, integrated circuit, computer program, or recording medium, and the system, device, method, integrated circuit, computer program, and recording medium. It may be realized by any combination of.
　本開示の非限定的な実施例によれば、例えばブロックといった特定のアクションを行った選手を詳細に分析できる。 According to the non-limiting examples of the present disclosure, it is possible to analyze in detail a player who has performed a specific action such as a block.
　本開示の一態様における更なる利点および効果は、明細書および図面から明らかにされる。かかる利点および／または効果は、いくつかの実施形態並びに明細書および図面に記載された特徴によってそれぞれ提供されるが、１つまたはそれ以上の同一の特徴を得るために必ずしも全てが提供される必要はない。 Further advantages and effects in one aspect of the present disclosure will be apparent from the specification and drawings. Such advantages and / or effects are provided by some embodiments and features described in the specification and drawings, respectively, but not all need to be provided in order to obtain one or more identical features. There is no.
一実施の形態に係るプレイ分析システムの構成例を示す図である。It is a figure which shows the configuration example of the play analysis system which concerns on one Embodiment. 一実施の形態に係るプレイ分析装置の構成例を示す図である。It is a figure which shows the structural example of the play analyzer which concerns on one Embodiment. 一実施の形態に係るプレイ情報の一例を示す図である。It is a figure which shows an example of the play information which concerns on one Embodiment. 一実施の形態に係るアクション検出部の処理例を示すフローチャートである。It is a flowchart which shows the processing example of the action detection part which concerns on one Embodiment. 一実施の形態に係るブロッカー検出部の処理例を示すフローチャートである。It is a flowchart which shows the processing example of the blocker detection part which concerns on one Embodiment. 一実施の形態に係るブロック部分画像の抽出領域の例を示す図である。It is a figure which shows the example of the extraction area of the block partial image which concerns on one Embodiment. 一実施の形態に係るコートの分割の一例を示す図である。It is a figure which shows an example of the division of the coat which concerns on one Embodiment. 一実施の形態に係るアタック画像から抽出されたブロック部分画像の第１例を示す図である。It is a figure which shows the 1st example of the block partial image extracted from the attack image which concerns on one Embodiment. 一実施の形態に係るアタック画像から抽出されたブロック部分画像の第２例を示す図である。It is a figure which shows the 2nd example of the block partial image extracted from the attack image which concerns on one Embodiment. 一実施の形態に係るアタック画像から抽出されたブロック部分画像の第３例を示す図である。It is a figure which shows the 3rd example of the block partial image extracted from the attack image which concerns on one Embodiment. 一実施の形態に係るアタック画像から抽出されたブロック部分画像の第４例を示す図である。It is a figure which shows the 4th example of the block partial image extracted from the attack image which concerns on one Embodiment. 一実施の形態に係るトスチャートの表示例を示す図である。It is a figure which shows the display example of the toss chart which concerns on one Embodiment. 一実施の形態に係る選手毎のブロックの成功及び失敗の回数を示すグラフの一例である。It is an example of a graph showing the number of successes and failures of blocks for each player according to one embodiment. 一実施の形態に係る選手の組み合わせ毎のブロックの成功及び失敗の回数を示すグラフの一例である。It is an example of a graph showing the number of successes and failures of blocks for each combination of players according to one embodiment. 一実施の形態に係るアタックのディレクションチャートの第１の表示例を示す図である。It is a figure which shows the 1st display example of the attack direction chart which concerns on one Embodiment. 一実施の形態に係るアタックのディレクションチャートの第２の表示例を示す図である。It is a figure which shows the 2nd display example of the attack direction chart which concerns on one Embodiment. 一実施の形態に係るブロッカー位置及びアタックコースの第１の表示例を示す図である。It is a figure which shows the blocker position and the 1st display example of the attack course which concerns on one Embodiment. 一実施の形態に係るブロッカー位置及びアタックコースの第２の表示例を示す図である。It is a figure which shows the 2nd display example of the blocker position and the attack course which concerns on one Embodiment. 一実施の形態に係るブロッカー位置及びアタックコースの第３の表示例を示す図である。It is a figure which shows the 3rd display example of the blocker position and the attack course which concerns on one Embodiment. 一実施の形態に係るブロッカー重心位置及びアタックコースの表示例を示す図である。It is a figure which shows the display example of the blocker center of gravity position and the attack course which concerns on one Embodiment. 一実施の形態に係るトス時のブロッカー重心位置と、トスチャートに対するフィルタリングとの関係を説明するための図である。It is a figure for demonstrating the relationship between the blocker center of gravity position at the time of toss which concerns on one Embodiment, and filtering with respect to a toss chart. 本開示の実施の形態に係るハードウェアの構成例を示す図である。It is a figure which shows the configuration example of the hardware which concerns on embodiment of this disclosure.
　以下、図面を適宜参照して、本発明の実施の形態について、詳細に説明する。但し、必要以上に詳細な説明は省略する場合がある。例えば、既によく知られた事項の詳細説明や実質的に同一の構成に対する重複説明を省略する場合がある。これは、以下の説明が不必要に冗長になるのを避け、当業者の理解を容易にするためである。 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings as appropriate. However, more detailed explanation than necessary may be omitted. For example, detailed explanations of already well-known matters and duplicate explanations for substantially the same configuration may be omitted. This is to avoid unnecessary redundancy of the following description and to facilitate the understanding of those skilled in the art.
　なお、添付図面および以下の説明は、当業者が本開示を十分に理解するために提供されるのであって、これらにより特許請求の範囲に記載の主題を限定することは意図されていない。 It should be noted that the accompanying drawings and the following description are provided for those skilled in the art to fully understand the present disclosure, and are not intended to limit the subject matter described in the claims.
（一実施の形態）
＜プレイ分析システム＞
　図１は、一実施の形態に係るプレイ分析システムの一例を示す。 (One Embodiment)
<Play analysis system>
FIG. 1 shows an example of a play analysis system according to an embodiment.
　プレイ分析システム１は、球技を撮影した映像を解析し、球技に用いられる移動体に対してアクションを行った選手を認識するシステムである。球技に用いられる移動体は、典型的にはボールである。しかし、移動体は、バドミントンに用いられるシャトル等であってもよい。本実施の形態では、球技の１つであるバレーボールを例に説明する。ただし、プレイ分析システム１は、サッカー、野球、卓球、バスケットボール、テニス、ラグビー、アメリカンフットボール、ラクロス、又はバドミントンなど、様々な球技に適用可能である。また、プレイ分析システム１は、アイスホッケーのパック等、「球」の概念に当てはまらない形状の移動体にも適用可能である。すなわち、プレイ分析システム１は、複数人から構成されるチームが移動体に対するアクションを行うことにより点数又は勝敗が決定される競技であれば、どのような競技にも適用可能である。 The play analysis system 1 is a system that analyzes a video of a ball game and recognizes a player who has performed an action on a moving body used in the ball game. The moving body used in a ball game is typically a ball. However, the moving body may be a shuttle or the like used for badminton. In the present embodiment, volleyball, which is one of the ball games, will be described as an example. However, the play analysis system 1 can be applied to various ball games such as soccer, baseball, table tennis, basketball, tennis, rugby, American football, lacrosse, or badminton. The play analysis system 1 can also be applied to a moving body having a shape that does not fit the concept of "sphere" such as an ice hockey pack. That is, the play analysis system 1 can be applied to any competition as long as the score or victory or defeat is determined by a team composed of a plurality of people performing an action on a moving body.
　プレイ分析システム１は、複数のカメラ３（３Ａ、３Ｂ、３Ｃ、３Ｄ）、プレイ分析装置１００、表示装置２１０、及び、操作装置２２０を備える。 The play analysis system 1 includes a plurality of cameras 3 (3A, 3B, 3C, 3D), a play analysis device 100, a display device 210, and an operation device 220.
　複数のカメラ３は、互いに異なる位置に設置される。例えば、図１に示すように、各カメラ３は、高所からコート１０を異なる視点（画角）で撮影できる位置に設置される。なお、図１では４台のカメラ３が設置されているが、２台以上であれば、何台のカメラ３が設置されてもよい。２台以上のカメラ３を用いることにより、ボールの３次元位置を算出できる。 The plurality of cameras 3 are installed at different positions from each other. For example, as shown in FIG. 1, each camera 3 is installed at a position where the court 10 can be photographed from a high place with different viewpoints (angles of view). Although four cameras 3 are installed in FIG. 1, any number of cameras 3 may be installed as long as there are two or more cameras. By using two or more cameras 3, the three-dimensional position of the ball can be calculated.
　カメラ３は、有線又は無線を介してプレイ分析装置１００と通信可能に接続される。カメラ３は、球技のプレイを撮影し、動画データを生成する。カメラ３は、動画データを、プレイ分析装置１００へ送信する。動画データは、複数のフレーム画像が、ＭＰ４、Ｈ．２６４、Ｈ．２６５、又は、Ｍｏｔｉｏｎ　ＪＰＥＧといった規格に基づいて圧縮されたものであってよい。 The camera 3 is communicably connected to the play analyzer 100 via wire or wireless. The camera 3 captures the play of the ball game and generates moving image data. The camera 3 transmits the moving image data to the play analyzer 100. As for the moving image data, a plurality of frame images are composed of MP4, H. 264, H. It may be compressed based on a standard such as 265 or Motion JPEG.
　表示装置２１０は、有線又は無線を介してプレイ分析装置１００と通信可能に接続されており、プレイ分析装置１００から出力されるデータを表示する。表示装置２１０は、例えば、液晶ディスプレイ又は有機ＥＬディスプレイ等である。 The display device 210 is communicably connected to the play analysis device 100 via a wired or wireless device, and displays data output from the play analysis device 100. The display device 210 is, for example, a liquid crystal display or an organic EL display.
　操作装置２２０は、有線又は無線を介してプレイ分析装置１００と通信可能に接続されており、ユーザからの操作を受け付ける。操作装置２２０は、操作の内容を、プレイ分析装置１００へ送信する。操作装置２２０は、例えば、キーボード、マウス、マイク及び／又はタッチパネル等である。操作装置２２０及び表示装置２１０は、一体型の装置であってもよい。また、プレイ分析装置１００は、単一のＰＣで構成することができるが、プレイ分析処理全体の負荷分散のため、複数台のＰＣで構成してもよい。例えば、各カメラ（３Ａ～３Ｄ）の動画データを取り込んで、カメラごとのフレーム画像（静止画）を格納するキャプチャＰＣと、このキャプチャＰＣからフレーム画像を受け取ってプレイ分析処理を行う分析処理ＰＣとに分割した構成を採用することができる。なお、本実施の形態における「ユーザ」は、プレイ分析システム１の利用者であれば誰でもよく、コーチ、監督、スタッフ及び選手といった競技の関係者であってもよいし、それ以外の者であってもよい。 The operation device 220 is communicably connected to the play analysis device 100 via wire or wireless, and accepts operations from the user. The operation device 220 transmits the content of the operation to the play analysis device 100. The operating device 220 is, for example, a keyboard, a mouse, a microphone, and / or a touch panel. The operating device 220 and the display device 210 may be integrated devices. Further, although the play analysis device 100 can be configured by a single PC, it may be configured by a plurality of PCs in order to distribute the load of the entire play analysis process. For example, a capture PC that captures video data of each camera (3A to 3D) and stores a frame image (still image) for each camera, and an analysis processing PC that receives a frame image from this capture PC and performs play analysis processing. It is possible to adopt a configuration divided into. The "user" in the present embodiment may be any user of the play analysis system 1, may be a person involved in the competition such as a coach, a manager, a staff member, or a player, or may be a person other than the user. There may be.
　プレイ分析装置１００は、各カメラ３から送信された動画データに基づき、各選手のアクションを特定する。バレーボールの場合における選手のアクションは、例えば、サーブ、レセプション（サーブに対するレシーブ）、トス、アタック、ブロック、及び、ディグ（アタックに対するレシーブ）である。以下、アクションを行った選手を「アクター」と表現する場合がある。 The play analysis device 100 identifies the action of each player based on the moving image data transmitted from each camera 3. Player actions in the case of volleyball are, for example, serve, reception (receive against serve), toss, attack, block, and dig (receive against attack). Hereinafter, the player who performed the action may be referred to as an "actor".
　なお、本実施の形態では、図１に示すように、コート１０の面の中心点を原点Ｏとし、コート１０の面と平行かつネット１１と平行な軸をＸ軸とし、コート１０の面と平行かつネット１１と垂直な軸をＹ軸とし、コート１０の面と垂直な軸をＺ軸とする。Ｘ軸は、審判１２から離れる方向を正方向とし、審判１２に近づく方向を負方向とする。Ｙ軸は、審判１２から見て、左方向を正方向とし、右方向を負方向とする。Ｚ軸は、コート１０の面から離れる方向を正方向とする。つまりＺ軸の座標ｚは、コート１０の面からの高さに相当する。 In the present embodiment, as shown in FIG. 1, the center point of the surface of the coat 10 is the origin O, the axis parallel to the surface of the coat 10 and parallel to the net 11 is the X axis, and the surface of the coat 10 The axis parallel to the net 11 and perpendicular to the net 11 is the Y axis, and the axis perpendicular to the surface of the coat 10 is the Z axis. The X-axis has a positive direction away from the referee 12 and a negative direction closer to the referee 12. The Y-axis has a positive direction in the left direction and a negative direction in the right direction when viewed from the referee 12. The Z-axis has a positive direction away from the surface of the coat 10. That is, the Z-axis coordinate z corresponds to the height of the coat 10 from the surface.
＜プレイ分析装置＞
　図２は、プレイ分析装置１００の構成例を示す。 <Play analyzer>
FIG. 2 shows a configuration example of the play analyzer 100.
　プレイ分析装置１００は、受信部１０１、軌跡算出部１０３、アクション検出部１０４、ブロッカー検出部１０５、プレイ情報生成部１０６、プレイ分析部１０７、及び、情報格納部１０８を有する。なお、軌跡算出部１０３、アクション検出部１０４、ブロッカー検出部１０５、プレイ情報生成部１０６、及び、プレイ分析部１０７は、制御部１０２に含まれてよい。 The play analysis device 100 includes a reception unit 101, a trajectory calculation unit 103, an action detection unit 104, a blocker detection unit 105, a play information generation unit 106, a play analysis unit 107, and an information storage unit 108. The locus calculation unit 103, the action detection unit 104, the blocker detection unit 105, the play information generation unit 106, and the play analysis unit 107 may be included in the control unit 102.
　受信部１０１は、カメラ３Ａ～３Ｄのそれぞれから、動画データを受信し、情報格納部１０８に格納する。 The receiving unit 101 receives moving image data from each of the cameras 3A to 3D and stores it in the information storage unit 108.
　軌跡算出部１０３は、動画データを構成する複数のフレーム画像１１１に対して、例えば非特許文献１の手法を適用し、フレーム画像１１１の撮影時刻（以下「フレーム時刻」という）におけるボールの３次元位置（ｘ，ｙ，ｚ）及び速度を算出する。そして、軌跡算出部１０３は、フレーム時刻とボールの３次元位置と速度とを対応付けてボール軌跡情報１１２を生成し、情報格納部１０８に格納する。 The locus calculation unit 103 applies, for example, the method of Non-Patent Document 1 to a plurality of frame images 111 constituting the moving image data, and three-dimensionally reduces the ball at the shooting time of the frame image 111 (hereinafter referred to as “frame time”). Calculate the position (x, y, z) and speed. Then, the locus calculation unit 103 generates the ball locus information 112 in association with the frame time, the three-dimensional position of the ball, and the velocity, and stores the ball locus information 112 in the information storage unit 108.
　アクション検出部１０４は、ボール軌跡情報によって示されるボールの軌跡変化に基づいて、どの選手がどのタイミングでどのようなアクションを行ったかを検出する。なお、アクション検出部１０４の詳細については後述する。 The action detection unit 104 detects which player performed what action at what timing based on the change in the trajectory of the ball indicated by the ball trajectory information. The details of the action detection unit 104 will be described later.
　ブロッカー検出部１０５は、アクション検出部１０４によって検出されたトスと、トス後のアタックとの間のフレーム画像１１１に基づいて、トスとアタックとの間にブロックの行動を行った選手（ブロッカー）を検出する。ブロッカー検出部１０５は、検出したブロッカー情報１１４を生成し、情報格納部１０８に格納する。なお、「トス」は第１のアクションの一例であり、「アタック」は第２のアクションの一例であり、「ブロック」は第３のアクションの一例である。また、ブロッカー検出部１０５の詳細については後述する。 The blocker detection unit 105 determines a player (blocker) who has performed a block action between the toss and the attack based on the frame image 111 between the toss detected by the action detection unit 104 and the attack after the toss. To detect. The blocker detection unit 105 generates the detected blocker information 114 and stores it in the information storage unit 108. Note that "toss" is an example of the first action, "attack" is an example of the second action, and "block" is an example of the third action. The details of the blocker detection unit 105 will be described later.
　プレイ情報生成部１０６は、ボール軌跡情報１１２、アクション情報１１３及びブロッカー情報１１４に基づいて、プレイ情報１１５を生成し、情報格納部１０８に格納する。図３にプレイ情報１１５の一例を示す。例えば、プレイ情報生成部１０６は、アクションフレーム時刻（Ｔ－１５）、アクション種別「トス」及びアクター番号「２」を対応付けるアクション情報と、ボール軌跡情報１１２における当該アクションフレーム時刻（Ｔ－１５）のときのボール座標（ｘ，ｙ，ｚ）及びボール速度Ｓと、を用いて、プレイ情報１１５の行Ｌ２を生成する。例えば、プレイ情報生成部１０６は、アクションフレーム時刻Ｔ、アクション種別「アタック」及びアクター番号「１４」とを対応付けるアクション情報１１３と、ボール軌跡情報１１２における当該アクションフレーム時刻Ｔのときのボール座標（ｘＴ，ｙＴ，ｚＴ）及びボール速度（ＳＴ）と、を用いて、プレイ情報１１５の行Ｌ４を生成する。すなわち、プレイ情報１１５は、球技のプレイにおいて、いつ、どの選手がどのようなアクションを行ったかを示す情報と、そのときのボールの動きを示す情報と、を含む。 The play information generation unit 106 generates play information 115 based on the ball trajectory information 112, the action information 113, and the blocker information 114, and stores the play information 115 in the information storage unit 108. FIG. 3 shows an example of play information 115. For example, the play information generation unit 106 relates the action information associated with the action frame time (T-15), the action type “toss” and the actor number “2”, and the action frame time (T-15) in the ball trajectory information 112. The row L2 of the play information 115 is generated by using the time ball coordinates (x, y, z) and the ball velocity S. For example, the play information generation unit 106 has the action information 113 associated with the action frame time T, the action type “attack” and the actor number “14”, and the ball coordinates (x) at the action frame time T in the ball trajectory information 112. T , y T , z T ) and ball velocity ( ST ) are used to generate line L4 of play information 115. That is, the play information 115 includes information indicating when, which player performed what action, and information indicating the movement of the ball at that time in the play of the ball game.
　また、プレイ情報生成部１０６は、プレイ情報１１５における、トスからアタックまでの間に、ブロッカー検出部１０５が生成したブロッカー情報１１４を対応付ける。例えば、ブロッカー情報１１４は、図３に示すように、ブロック枚数、１人目のブロッカーの背番号を示す第１ブロッカー番号、１人目のブロッカーの位置を示す第１ブロッカー位置、２人目のブロッカーの背番号を示す第２ブロッカー番号、２人目のブロッカーの位置を示す第２ブロッカー位置、３人目のブロッカーの背番号を示す第３ブロッカー番号、及び、３人目のブロッカーの位置を示す第３ブロッカー位置を含む。なお、検出されたブロッカーが３人未満の場合、未検出の欄は空白であってよい。 Further, the play information generation unit 106 associates the blocker information 114 generated by the blocker detection unit 105 with the play information 115 from the toss to the attack. For example, as shown in FIG. 3, the blocker information 114 includes the number of blocks, the first blocker number indicating the uniform number of the first blocker, the first blocker position indicating the position of the first blocker, and the back of the second blocker. The second blocker number indicating the number, the second blocker position indicating the position of the second blocker, the third blocker number indicating the uniform number of the third blocker, and the third blocker position indicating the position of the third blocker. Including. If the number of detected blockers is less than 3, the undetected column may be blank.
　また、プレイ情報生成部１０６は、図３に示す項目の一部を有しないプレイ情報１１５を生成してもよい。例えば、プレイ情報生成部１０６は、後述するプレイ分析部１０７によって使用されない項目を、プレイ情報１１５に含めなくてもよい。 Further, the play information generation unit 106 may generate play information 115 that does not have a part of the items shown in FIG. For example, the play information generation unit 106 does not have to include items that are not used by the play analysis unit 107, which will be described later, in the play information 115.
　プレイ分析部１０７は、プレイ情報１１５に基づいて、選手のプレイを様々な観点から分析し、その分析結果であるプレイ分析結果情報を生成及び表示する。なお、プレイ分析部１０７の詳細については後述する。 The play analysis unit 107 analyzes the player's play from various viewpoints based on the play information 115, and generates and displays the play analysis result information which is the analysis result. The details of the play analysis unit 107 will be described later.
＜アクション検出部の詳細＞
　次に、図４に示すフローチャート参照して、アクション検出部１０４の処理例を説明する。 <Details of action detection unit>
Next, a processing example of the action detection unit 104 will be described with reference to the flowchart shown in FIG.
　アクション検出部１０４は、ボール軌跡情報に含まれるフレーム時刻毎のボールの３次元位置及び速度からボールの軌跡を算出し、その算出したボールの軌跡変化、ボールの３次元位置、速度、所定の条件に合致した球技のルールなどに基づいて、アクションが発生したフレーム画像１１１の時刻（以下「アクションフレーム時刻」という）と、発生したアクション種別とを特定する（Ｓ１０１）。 The action detection unit 104 calculates the trajectory of the ball from the three-dimensional position and speed of the ball for each frame time included in the ball trajectory information, and the calculated change in the trajectory of the ball, the three-dimensional position and speed of the ball, and predetermined conditions. The time of the frame image 111 in which the action occurred (hereinafter referred to as “action frame time”) and the action type in which the action occurred are specified based on the rules of the ball game that match the above (S101).
　例えば、アクション検出部１０４は、解析開始の最初に検出されたボールの軌跡がＹ軸方向（図１に示すコートの長辺方向）の移動成分を有し、当該Ｙ軸方向のボールの速度成分が所定の範囲内である場合、アクション種別「サーブ」を検出する。例えば、アクション検出部１０４は、「サーブ」の後にボールの軌跡がＹ軸においてネット１１の存在する座標を跨ぎ、かつ、ボールの３次元位置の変化が下降から上昇に転じた場合（すなわち、Ｚ軸方向の座標の変化がプラスに転じた場合）、アクション種別「レセプション」を検出する。バレーボールのルール上、「サーブ」を受けるアクションは「レセプション」であるので、このようなルールに基づく判定により、「レセプション」と「ディグ」とを区別できる。アクション検出部１０４は、アクション種別「トス」及び「アタック」についても同様に検出する。例えば、レセプションもしくはディグを検出した後に、ボールの軌道（Ｚ座標）が下降から上昇に変化している場合、アクション種別「トス」を検出する。また、ボールがネットを超えてきた後にすでに２つのアクションを検出しており、ボールのＹ座標がネットから１５０ｃｍ以内で、ボールの軌道（Ｚ座標)が下降から上昇に変化しており、その後一定フレーム内でのボール速度が４０ｋｍ／ｈ以上の場合、アクション種別「アタック」を検出する。また、アタックを検出した後１５フレーム以内に、ボールのＹ座標がネットから７０ｃｍ以内で、各座標の移動量のうち２つ以上に変化があった場合（例えば過去３フレームの平均移動量と、最新位置の移動量との差が閾値以上の場合、変化があったと判断)、アクション種別「ブロック」を検出する。 For example, in the action detection unit 104, the trajectory of the ball detected first at the start of analysis has a movement component in the Y-axis direction (the long side direction of the court shown in FIG. 1), and the velocity component of the ball in the Y-axis direction. Is within a predetermined range, the action type "serve" is detected. For example, in the action detection unit 104, when the trajectory of the ball straddles the coordinates where the net 11 exists on the Y axis after the "serve", and the change in the three-dimensional position of the ball changes from descending to ascending (that is, Z). When the change in the coordinates in the axial direction turns positive), the action type "reception" is detected. According to the rules of volleyball, the action to receive "serve" is "reception", so the judgment based on such rules can distinguish between "reception" and "dig". The action detection unit 104 also detects the action types "toss" and "attack" in the same manner. For example, if the trajectory (Z coordinate) of the ball changes from descending to ascending after detecting the reception or dig, the action type "toss" is detected. In addition, two actions have already been detected after the ball has crossed the net, the Y coordinate of the ball is within 150 cm from the net, the trajectory (Z coordinate) of the ball changes from descending to ascending, and then constant. When the ball speed in the frame is 40 km / h or more, the action type "attack" is detected. Also, if the Y coordinate of the ball is within 70 cm from the net and two or more of the movement amounts of each coordinate change within 15 frames after the attack is detected (for example, the average movement amount of the past 3 frames and the movement amount). If the difference from the movement amount of the latest position is greater than or equal to the threshold value, it is judged that there has been a change), and the action type "block" is detected.
　アクション検出部１０４は、アクションフレーム時刻及びその近傍の時刻のフレーム画像１１１（以下「アクションフレーム」という）に対して、アクターの検出範囲を設定する（Ｓ１０２）。 The action detection unit 104 sets the detection range of the actor for the frame image 111 (hereinafter referred to as "action frame") at the action frame time and the time in the vicinity thereof (S102).
　アクション検出部１０４は、アクターの検出範囲からアクター領域を認識し、そのアクター領域からアクターのユニフォームの背番号を認識する（Ｓ１０３）。なお、背番号は、「アクター番号」又は「ユニフォーム番号」といった他の用語に読み替えられてもよい。 The action detection unit 104 recognizes the actor area from the detection range of the actor, and recognizes the uniform number of the actor from the actor area (S103). The uniform number may be read as another term such as "actor number" or "uniform number".
　アクション検出部１０４は、アクションフレーム時刻と、アクション種別と、背番号とを対応付けたアクション情報１１３を生成し、情報格納部１０８に格納する（Ｓ１０４）。 The action detection unit 104 generates action information 113 in which the action frame time, the action type, and the uniform number are associated with each other, and stores the action information 113 in the information storage unit 108 (S104).
＜ブロッカー検出部の詳細＞
　ブロッカー検出部１０５は、ブロッカー情報１１４を生成して情報格納部１０８に格納する。ブロッカー情報１１４は、図３に示す通り、ブロック枚数、ブロッカーに関する情報（以下「ブロッカー情報」という）、及び、アタック評価を含む。ブロッカー情報は、第１から第３のブロッカーの背番号、及び、第１から第３のブロッカーの位置を示す情報を含む。なお、ブロッカーは、必ずしもブロックのためにジャンプした選手に限られない。ブロック情報におけるアタック評価は、対応するアタックが得点になったか否かを示す。例えば、図３に示すアタック評価「○」は、対応するアタックが得点になったことを示す。別言すると、アタック評価「○」は、ブロックが失敗したことを示す。 <Details of blocker detector>
The blocker detection unit 105 generates blocker information 114 and stores it in the information storage unit 108. As shown in FIG. 3, the blocker information 114 includes the number of blocks, information on the blocker (hereinafter referred to as “blocker information”), and an attack evaluation. The blocker information includes the uniform numbers of the first to third blockers and the information indicating the positions of the first to third blockers. The blocker is not necessarily limited to the player who jumped for the block. The attack evaluation in the block information indicates whether or not the corresponding attack has scored. For example, the attack evaluation “◯” shown in FIG. 3 indicates that the corresponding attack has become a score. In other words, an attack rating of "○" indicates that the block failed.
　ブロッカー検出部１０５は、相手チームの選手がトスを行ったタイミングのブロッカー情報１１４（以下「トス時ブロッカー情報」という）と、相手チームの選手がアタックを行ったタイミングのブロッカー情報１１４（以下「アタック時ブロッカー情報」という）と、を生成してよい。 The blocker detection unit 105 has blocker information 114 at the timing when the player of the opponent team tosses (hereinafter referred to as “blocker information at the time of toss”) and blocker information 114 at the timing when the player of the opponent team attacks (hereinafter “attack”). "Time blocker information") and may be generated.
＜ブロッカー検出部の処理例＞
　次に、図５に示すフローチャートを参照して、ブロッカー検出部１０５の処理例を説明する。 <Processing example of blocker detector>
Next, a processing example of the blocker detection unit 105 will be described with reference to the flowchart shown in FIG.
　ブロッカー検出部１０５は、アクション検出部１０４がトスを検出したアクションフレーム時刻における、ブロッカー側の２台のカメラ３のフレーム画像１１１を選択する（Ｓ２０１）。以下、トスを検出したアクションフレーム時刻における、ブロッカー側のカメラ３のフレーム画像１１１を、「トス画像」と表記する。 The blocker detection unit 105 selects the frame image 111 of the two cameras 3 on the blocker side at the action frame time when the action detection unit 104 detects the toss (S201). Hereinafter, the frame image 111 of the camera 3 on the blocker side at the action frame time when the toss is detected is referred to as a “toss image”.
　ブロッカー検出部１０５は、２つのトス画像から、それぞれ、ブロッカーを検出するための部分画像（以下「ブロッカー部分画像」という）を抽出する（Ｓ２０２）。 The blocker detection unit 105 extracts a partial image for detecting the blocker (hereinafter referred to as "blocker partial image") from each of the two toss images (S202).
　ブロッカー検出部１０５は、Ｓ２０２で抽出した２つのブロッカー部分画像のそれぞれに対して人物の関節推定を行い、ブロッカーの首の候補位置を特定する（Ｓ２０３）。なお、ブロッカー検出部１０５は、首に代えてブロッカーの頭の候補位置を特定してもよい。或いは、ブロッカー検出部１０５は、頭と両肩の位置を平均し、首の位置を特定してもよい。これにより、仮に１つの位置が欠落しても、安定的に人物の位置を特定できる。また、ブロッカー検出部１０５は、両肩の位置を用いて選手がどちらを向いているかを判定し、ネットの方向を向いていない選手を、ブロッカーの候補から除外してもよい。 The blocker detection unit 105 estimates the joints of a person for each of the two blocker partial images extracted in S202, and identifies the candidate position of the blocker's neck (S203). The blocker detection unit 105 may specify a candidate position for the head of the blocker instead of the neck. Alternatively, the blocker detection unit 105 may specify the position of the neck by averaging the positions of the head and both shoulders. As a result, even if one position is missing, the position of the person can be stably specified. Further, the blocker detection unit 105 may determine which direction the player is facing by using the positions of both shoulders, and may exclude the player who is not facing the direction of the net from the blocker candidates.
　ブロッカー検出部１０５は、Ｓ２０３で特定した２つのブロッカーの候補位置に基づいて、同一選手判定を行い、３名以下のブロッカーとその位置を特定する（Ｓ２０４）。例えば、ブロッカー検出部１０５は、２つのブロッカーの候補位置のベクトル間距離が閾値以下、かつ、首の位置が尤もらしい高さ（例えば１．５ｍから２．５ｍ）になる組み合わせの中から、ネットに近い組み合わせを選択する。 The blocker detection unit 105 determines the same player based on the candidate positions of the two blockers specified in S203, and identifies three or less blockers and their positions (S204). For example, the blocker detection unit 105 nets from a combination in which the distance between the vectors of the candidate positions of the two blockers is equal to or less than the threshold value and the neck position has a plausible height (for example, 1.5 m to 2.5 m). Select a combination that is close to.
　ブロッカー検出部１０５は、Ｓ２０４で特定したブロッカーのＳ２０３で推定した関節位置に基づいて、ブロッカー部分画像から、ブロッカーの画像を抽出し、ブロッカーの背番号を認識する（Ｓ２０５）。 The blocker detection unit 105 extracts the blocker image from the blocker partial image based on the joint position estimated in S203 of the blocker specified in S204, and recognizes the blocker uniform number (S205).
　ブロッカー検出部１０５は、Ｓ２０４で特定したブロッカーの位置及びＳ１０４で認識したブロッカーの背番号に基づき、トス時ブロッカー情報を生成する（Ｓ２０６）。 The blocker detection unit 105 generates blocker information at the time of tossing based on the position of the blocker specified in S204 and the uniform number of the blocker recognized in S104 (S206).
　ブロッカー検出部１０５は、アクション検出部１０４が検出した、上記トス後のアタックのアクションフレーム時刻における、ブロッカー側の２台のカメラ３のフレーム画像１１１を選択する（Ｓ２０７）。以下、アタックを検出したアクションフレーム時刻における、ブロッカー側のカメラ３のフレーム画像１１１を、「アタック画像」と表記する。 The blocker detection unit 105 selects the frame image 111 of the two cameras 3 on the blocker side at the action frame time of the attack after the toss detected by the action detection unit 104 (S207). Hereinafter, the frame image 111 of the camera 3 on the blocker side at the action frame time when the attack is detected is referred to as an “attack image”.
　ブロッカー検出部１０５は、２つのアタック画像から、それぞれ、ブロッカー部分画像を抽出する（Ｓ２０８）。ここで、ブロッカーの密集度は、トス時よりもアタック時の方が高い。そのため、トス時と同じようにアタック画像からブロッカー部分画像を抽出すると、Ｓ２０８の関節推定において個々のブロッカーを適切に特定できない可能性がある。そこで、ブロッカー検出部１０５は、図６に例示するように、トス画像からのブロッカー部分画像の抽出とは異なる方法で、アタック画像からブロッカー部分画像を抽出してよい。なお、詳細については後述する。 The blocker detection unit 105 extracts a blocker partial image from each of the two attack images (S208). Here, the density of blockers is higher during attack than during toss. Therefore, if the blocker partial image is extracted from the attack image as in the case of toss, there is a possibility that the individual blockers cannot be properly identified in the joint estimation of S208. Therefore, as illustrated in FIG. 6, the blocker detection unit 105 may extract the blocker partial image from the attack image by a method different from the extraction of the blocker partial image from the toss image. The details will be described later.
　ブロッカー検出部１０５は、上述と同様に、Ｓ２０８で抽出した２つのブロッカー部分画像のそれぞれに対して人物の関節推定を行い、ブロッカーの首の候補位置を特定する（Ｓ２０９）。 In the same manner as described above, the blocker detection unit 105 estimates the joints of the person for each of the two blocker partial images extracted in S208, and identifies the candidate position of the blocker's neck (S209).
　ブロッカー検出部１０５は、Ｓ２０９で特定した２つのブロッカーの候補位置に基づいて、同一選手判定を行い、３名以下のブロッカーとその位置を特定する（Ｓ２１０）。この場合の首の位置が尤もらしい高さの範囲は、Ｓ２０４の場合の範囲よりも広くてよい。ジャンプしているブロッカーを特定するためである。 The blocker detection unit 105 determines the same player based on the candidate positions of the two blockers specified in S209, and identifies three or less blockers and their positions (S210). The range of heights at which the neck position is plausible in this case may be wider than the range in the case of S204. This is to identify the blocker that is jumping.
　ブロッカー検出部１０５は、Ｓ２１０で特定したブロッカーのＳ２０９で推定した関節位置に基づいて、ブロッカー部分画像から、ブロッカーの画像を抽出し、ブロッカーの背番号を認識する（Ｓ２１１）。 The blocker detection unit 105 extracts the blocker image from the blocker partial image based on the joint position estimated in S209 of the blocker specified in S210, and recognizes the blocker uniform number (S211).
　ブロッカー検出部１０５は、Ｓ２１０で特定したブロッカーの位置及びＳ２１１で認識したブロッカーの背番号に基づき、アタック時ブロッカー情報を生成する（Ｓ２１２）。 The blocker detection unit 105 generates blocker information at the time of attack based on the position of the blocker specified in S210 and the uniform number of the blocker recognized in S211 (S212).
＜トス画像からブロッカー部分画像を抽出＞
　トス画像からブロッカー部分画像を抽出する処理の一例を説明する。本処理は、図５のＳ２０２の処理に相当する。 <Extract blocker partial image from toss image>
An example of the process of extracting the blocker partial image from the toss image will be described. This process corresponds to the process of S202 in FIG.
　以下、図７に示すように、ブロッカー２１側のコート１０の後方からネット１１の方向を見た場合に、右側に位置するカメラ３Ａを「右のブロッカー側カメラ」と表記し、左側に位置するカメラ３Ｂを「左のブロッカー側カメラ」と表記する。また、トス画像から抽出されるブロッカー部分画像を「トス時ブロッカー部分画像」３１０（図６参照）と表記する。 Hereinafter, as shown in FIG. 7, when the direction of the net 11 is viewed from behind the court 10 on the blocker 21 side, the camera 3A located on the right side is referred to as a “right blocker side camera” and is located on the left side. Camera 3B is referred to as "left blocker side camera". Further, the blocker partial image extracted from the toss image is referred to as "toss blocker partial image" 310 (see FIG. 6).
　トス画像に対するトス時ブロッカー部分画像３１０のサイズ及び抽出範囲は、例えば、以下のように設定される。なお、以下の設定は、試合前に予めキャリブレーションされ、１試合を通じて固定的であってよい。 The size and extraction range of the blocker partial image 310 at the time of tossing with respect to the toss image are set as follows, for example. The following settings may be calibrated in advance before the match and may be fixed throughout the match.
　・右のブロッカー側カメラのトス画像に対するトス時ブロッカー部分画像３１０の抽出では、トス画像における、右のブロッカー側カメラから遠い方（つまり奧側）のネット端（つまりネットの左端）の上端を、トス時ブロッカー部分画像の左上端とする（図６参照）。
　・左のブロッカー側カメラのトス画像に対するトス時ブロッカー部分画像３１０の抽出では、トス画像における、左のブロッカー側カメラから遠い方（つまり奧側）のネット端（つまりネットの右端）の上端を、トス時ブロッカー部分画像３１０の右上端とする。
　・トス画像における、ブロッカー側カメラから遠い方（奧側）のネット端から、当該ブロッカー側カメラから近い方（手前側）のネット端までのＸ方向の長さを、トス時ブロッカー部分画像３１０の幅Ｗとする。
　・トス時ブロッカー部分画像３１０の高さＨを所定のピクセル数とする。例えば、画像上でバレー支柱の高さが１５０ピクセルから２５０ピクセル程度の場合、トス時ブロッカー部分画像３１０の高さＨを３００ピクセルとする。
　・トス開始時のフレーム画像１１１及びその前後のフレーム画像１１１を含む合計３つのフレーム画像１１１から、トス時ブロッカー部分画像３１０を抽出する。 In the extraction of the blocker partial image 310 at the time of tossing with respect to the toss image of the right blocker side camera, the upper end of the net end (that is, the left end of the net) farther (that is, the back side) from the right blocker side camera in the toss image is set. The upper left corner of the blocker partial image at the time of tossing (see FIG. 6).
In the extraction of the blocker partial image 310 at the time of tossing with respect to the toss image of the left blocker side camera, the upper end of the net end (that is, the right end of the net) farther (that is, the back side) from the left blocker side camera in the toss image is used. The upper right corner of the blocker partial image 310 at the time of tossing.
-The length in the X direction from the net end far from the blocker side camera (back side) to the net end closer to the blocker side camera (front side) in the toss image is the length in the X direction of the toss blocker partial image 310. The width is W.
The height H of the blocker partial image 310 at the time of tossing is set to a predetermined number of pixels. For example, when the height of the valley support is about 150 pixels to 250 pixels on the image, the height H of the blocker partial image 310 at the time of tossing is set to 300 pixels.
A toss blocker partial image 310 is extracted from a total of three frame images 111 including the frame image 111 at the start of toss and the frame images 111 before and after the frame image 111.
＜アタック画像からブロッカー部分画像を抽出＞
　アタック画像からブロッカー部分画像を抽出する例を説明する。本抽出処理は、図５のＳ２０８に相当する。 <Extract blocker partial image from attack image>
An example of extracting a blocker partial image from an attack image will be described. This extraction process corresponds to S208 in FIG.
　以下、アタック画像から抽出されるブロッカー部分画像を「アタック時ブロッカー部分画像」３２０（図６参照）と表記する。ここで、図７に示すように、ネット１１のＸ方向の長さを３分割し、ブロッカー２１側のコートの後方からネット１１の方向を見た場合における、中央の分割区間を「中央区間」３３０Ｃと表記し、左側の分割区間を「左区間」３３０Ｌと表記し、右側の分割範囲を「右区間」３３０Ｒと表記する。 Hereinafter, the blocker partial image extracted from the attack image will be referred to as "attack blocker partial image" 320 (see FIG. 6). Here, as shown in FIG. 7, when the length of the net 11 in the X direction is divided into three and the direction of the net 11 is viewed from behind the court on the blocker 21 side, the central divided section is referred to as the “central section”. It is described as 330C, the left division section is described as "left section" 330L, and the right division range is described as "right section" 330R.
　アタック画像に対するアタック時ブロッカー部分画像３２０の抽出範囲は、以下に例示するように、アタック画像におけるボールの位置に応じて決まる。 The extraction range of the blocker partial image 320 at the time of attack with respect to the attack image is determined according to the position of the ball in the attack image, as illustrated below.
　・右のブロッカー側カメラのアタック画像に対するアタック時ブロッカー部分画像３２０は、次のように抽出される。すなわち、アタック画像において、ボールが右区間３３０Ｒに位置する場合、図８Ａに示すように、右上端にボールＰが位置するように、アタック画像からアタック時ブロッカー部分画像３２０が抽出される。一方、アタック画像において、ボールが中央区間３３０Ｃ又は左区間３３０Ｌに位置する場合、図８Ｂに示すように、上部中央にボールＰが位置するように、アタック画像からアタック時ブロッカー部分画像３２０が抽出される。
　・左のブロッカー側カメラのアタック画像に対するアタック時ブロッカー部分画像３２０は、次のように抽出される。すなわち、アタック画像において、ボールが左区間３３０Ｌに位置する場合、図８Ｃに示すように、左上端にボールＰが位置するように、アタック画像からアタック時ブロッカー部分画像３２０が抽出される。一方、アタック画像において、ボールが中央区間３３０Ｃ又は右区間３３０Ｒに位置する場合、図８Ｄに示すように、上部中央にボールＰが位置するように、アタック画像からアタック時ブロッカー部分画像３２０が抽出される。
　・アタック時ブロッカー部分画像３２０の幅Ｗ及び高さＨと所定のピクセル数とする。例えば、アタック時ブロッカー部分画像３２０の幅Ｗ及び高さＨを４５０ピクセル及び３００ピクセルとする。
　・アタック開始時のフレーム画像１１１及びその前後のフレーム画像１１１を含む合計３つのフレーム画像１１１から、アタック時ブロッカー部分画像３２０が抽出される。すなわち、右のブロッカー側カメラ及び右のブロッカー側カメラのフレーム画像から、合計６個のアタック時ブロッカー部分画像３２０が抽出される。 -The blocker partial image 320 at the time of attack with respect to the attack image of the right blocker side camera is extracted as follows. That is, in the attack image, when the ball is located in the right section 330R, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located at the upper right end as shown in FIG. 8A. On the other hand, in the attack image, when the ball is located in the central section 330C or the left section 330L, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located in the upper center as shown in FIG. 8B. To.
-The blocker partial image 320 at the time of attack with respect to the attack image of the left blocker side camera is extracted as follows. That is, in the attack image, when the ball is located in the left section 330L, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located at the upper left end as shown in FIG. 8C. On the other hand, in the attack image, when the ball is located in the central section 330C or the right section 330R, the blocker partial image 320 at the time of attack is extracted from the attack image so that the ball P is located in the upper center as shown in FIG. 8D. To.
The width W and height H of the blocker partial image 320 at the time of attack are set to a predetermined number of pixels. For example, the width W and height H of the blocker partial image 320 at the time of attack are set to 450 pixels and 300 pixels.
The blocker partial image 320 at the time of attack is extracted from a total of three frame images 111 including the frame image 111 at the start of the attack and the frame images 111 before and after the frame image 111. That is, a total of six attack blocker partial images 320 are extracted from the frame images of the right blocker side camera and the right blocker side camera.
　このようにしてアタック画像からブロック部分画像を抽出することにより、ブロック部分画像内において、個々のブロッカーが占める割合が大きくなる。これにより、Ｓ２０９の関節推定において個々のブロッカーを適切に特定できる可能性が向上する。 By extracting the block partial image from the attack image in this way, the proportion of each blocker in the block partial image becomes large. This increases the possibility that individual blockers can be properly identified in the joint estimation of S209.
＜プレイ分析部の詳細＞
　プレイ分析部１０７は、プレイ情報１１５に基づいて、選手のプレイを様々な観点から分析し、その分析結果であるプレイ分析結果情報を生成及び表示する。次に、プレイ分析結果情報の幾つかの例を示す。 <Details of Play Analysis Department>
The play analysis unit 107 analyzes the player's play from various viewpoints based on the play information 115, and generates and displays the play analysis result information which is the analysis result. Next, some examples of play analysis result information are shown.
＜トスチャート＞
　図９は、ブロック枚数を含むトスチャートの表示例を示す。トスチャートはプレイ分析情報の一例である。 <Toss chart>
FIG. 9 shows a display example of a toss chart including the number of blocks. The toss chart is an example of play analysis information.
　図９に示すように、プレイ分析部１０７は、プレイ情報１１５に基づき、ブロック枚数を含むトスチャートを生成及び表示する。図９において、「○」のマーク４０１は、トスが行われた位置を示し、マーク４０１の近傍の数字４０２は、そのトスに対して行われたブロック枚数を示す。例えば、プレイ分析部１０７は、プレイ情報１１５において、アクション種別「トス」に対応付けられているボール座標の位置にマーク４０１を表示する。そして、プレイ分析部１０７は、そのアクション種別「トス」に対応付けられているブロック枚数を、そのマーク４０１の近傍の数字４０２で表示する。なお、数字４０２は、「○」のマーク４０１の中に表示されてもよい。或いは、プレイ分析部１０７は、数字４０２の表示に代えて、ブロック枚数に応じて異なる色又は模様のマーク４０１を表示してもよい。 As shown in FIG. 9, the play analysis unit 107 generates and displays a toss chart including the number of blocks based on the play information 115. In FIG. 9, the “◯” mark 401 indicates the position where the toss was performed, and the number 402 in the vicinity of the mark 401 indicates the number of blocks performed for the toss. For example, the play analysis unit 107 displays the mark 401 at the position of the ball coordinates associated with the action type “toss” in the play information 115. Then, the play analysis unit 107 displays the number of blocks associated with the action type "toss" with a number 402 in the vicinity of the mark 401. The number 402 may be displayed in the mark 401 of "◯". Alternatively, the play analysis unit 107 may display a mark 401 having a different color or pattern depending on the number of blocks, instead of displaying the number 402.
　プレイ分析部１０７は、ブロック枚数に応じて、マーク４０１の表示又は非表示をフィルタリングしてよい。例えば、プレイ分析部１０７は、ユーザからフィルタリングの閾値としてブロック枚数３以上が設定された場合、３未満のブロック枚数が対応付けられている○マーク４０１を非表示にし、３以上のブロック枚数が対応付けられているマーク４０１を表示する。 The play analysis unit 107 may filter the display or non-display of the mark 401 according to the number of blocks. For example, when the user sets a filtering threshold value of 3 or more blocks, the play analysis unit 107 hides the ○ mark 401 associated with the number of blocks less than 3, and corresponds to the number of blocks 3 or more. The attached mark 401 is displayed.
＜ブロック回数グラフ＞
　図１０Ａ及び図１０Ｂは、ブロックの成功及び失敗の回数を示すグラフの表示例を示す。当該グラフはプレイ分析情報の一例である。 <Block count graph>
10A and 10B show a display example of a graph showing the number of successes and failures of blocks. The graph is an example of play analysis information.
　図１０Ａに示すように、プレイ分析部１０７は、プレイ情報１１５に基づき、ブロッカー毎のブロックの成功及び失敗の回数を示す棒グラフを表示する。例えば、プレイ分析部１０７は、プレイ情報１１５において、アクション種別「アタック」の次に発生したアクション種別が「ブロック」の場合、かつ、アタックの評価が○でない場合に、ブロックが成功したと判定する。プレイ分析部１０７は、プレイ情報１１５において、アクションの評価が○の場合、もしくは、アクション種別「アタック」の次に発生したアクション種別が「ブロック」以外の場合、ブロックが失敗したと判定する。プレイ分析部１０７は、この成功と失敗の回数をブロッカー毎にカウントすることにより、図１０Ａに示す棒グラフを生成する。 As shown in FIG. 10A, the play analysis unit 107 displays a bar graph showing the number of successes and failures of blocks for each blocker based on the play information 115. For example, in the play information 115, the play analysis unit 107 determines that the block was successful when the action type that occurred next to the action type "attack" is "block" and the evaluation of the attack is not ◯. .. In the play information 115, the play analysis unit 107 determines that the block has failed if the evaluation of the action is ◯, or if the action type that occurs next to the action type “attack” is other than “block”. The play analysis unit 107 generates the bar graph shown in FIG. 10A by counting the number of successes and failures for each blocker.
　図１０Ｂに示すように、プレイ分析部１０７は、プレイ情報１１５に基づき、アタックに対して飛んだブロッカーの組み合わせ毎のブロックの成功及び失敗の回数を示す棒グラフを表示する。例えば、プレイ分析部１０７は、上記の成功と失敗の回数をブロッカーの組み合わせ毎にカウントすることにより、図１０Ｂに示す棒グラフを生成する。 As shown in FIG. 10B, the play analysis unit 107 displays a bar graph showing the number of successes and failures of blocks for each combination of blockers that flew against the attack based on the play information 115. For example, the play analysis unit 107 generates the bar graph shown in FIG. 10B by counting the number of successes and failures described above for each combination of blockers.
　図１０Ａ及び図１０Ｂに示すように、ブロックの成功回数を示すグラフは、ブロックの失敗回数を示すグラフと異なる色又は模様でペイントされてよい。 As shown in FIGS. 10A and 10B, the graph showing the number of successful blocks may be painted in a different color or pattern from the graph showing the number of failed blocks.
＜アタックのディレクションチャート＞
　図１１Ａ及び図１１Ｂは、アタックのディレクションチャートの表示例を示す。例えば、アタックのディレクションチャートには、一人の選手がプレイ中に行った複数のアタックの軌跡が重複表示される。アタックのディレクションチャートはプレイ分析情報の一例である。 <Attack direction chart>
11A and 11B show a display example of the attack direction chart. For example, in the attack direction chart, the trajectories of a plurality of attacks performed by one player during play are duplicated. The attack direction chart is an example of play analysis information.
　図１１Ａに示すように、プレイ分析部１０７は、アタックされたボールの軌跡を示す線（以下「アタックコース」という）４１１（４１１Ａ、４１１Ｂ、４１１Ｃ）を、アタックに対するブロック枚数に応じて異なる形状又は色で表示する。例えば、図１１Ａに示すように、プレイ分析部１０７は、ブロック１枚のアタックコース４１１Ａを点線で、ブロック２枚のアタックコース４１１Ｂを一点鎖線で、ブロック３枚のアタックコース４１１Ｃを実線で表示する。アタックに対するブロック枚数は、プレイ情報１１５におけるアクション種別「アタック」に対応付けられているブロック枚数によって特定される。 As shown in FIG. 11A, the play analysis unit 107 has a line (hereinafter referred to as “attack course”) 411 (411A, 411B, 411C) indicating the trajectory of the attacked ball, which has a different shape or a shape depending on the number of blocks for the attack. Display in color. For example, as shown in FIG. 11A, the play analysis unit 107 displays the attack course 411A of one block as a dotted line, the attack course 411B of two blocks as a alternate long and short dash line, and the attack course 411C of three blocks as a solid line. .. The number of blocks for an attack is specified by the number of blocks associated with the action type "attack" in the play information 115.
　また、プレイ分析部１０７は、得点になったアタックコース４１１を、得点にならなかったアタックコース４１１と異なる形状又は色で表示する。例えば、図１１Ａに示すように、プレイ分析部１０７は、得点になったアタックコース４１１を、得点にならなかったアタックコース４１１よりも太い線で表示する。得点になったアタックであるか否かは、プレイ情報１１５のアタック評価が○であるか否かによって特定される。 In addition, the play analysis unit 107 displays the attack course 411 that has been scored in a different shape or color from the attack course 411 that has not been scored. For example, as shown in FIG. 11A, the play analysis unit 107 displays the scored attack course 411 with a thicker line than the non-scoring attack course 411. Whether or not the attack is a score is specified by whether or not the attack evaluation of the play information 115 is ◯.
　また、プレイ分析部１０７は、アタックコース４１１の表示を、ブロック枚数によってフィルタリングしてよい。図１１Ｂは、図１１Ａに示すアタックのディレクションチャートから、ブロック３枚未満を指定するユーザの操作によって、アタックコース４１１の一部を非表示にフィルタリングした場合の例を示す。 Further, the play analysis unit 107 may filter the display of the attack course 411 by the number of blocks. FIG. 11B shows an example in which a part of the attack course 411 is hiddenly filtered from the attack direction chart shown in FIG. 11A by the operation of a user who specifies less than three blocks.
　なお、プレイ分析部１０７は、アタックコース４１１の表示を、得点に結びついたアタックであるか否かを指定するユーザの操作によってフィルタリングをしてもよい。また、プレイ分析部１０７は、アタックコースの表示を、得点に結びついたアタックであるか否かと、ブロック枚数と、の組み合わせによってフィルタリングしてもよい。 Note that the play analysis unit 107 may filter the display of the attack course 411 by the operation of the user who specifies whether or not the attack is linked to the score. Further, the play analysis unit 107 may filter the display of the attack course by a combination of whether or not the attack is linked to the score and the number of blocks.
＜ブロッカー位置及びアタックコース＞
　図１２Ａ、図１２Ｂ及び図１２Ｃは、ブロッカー位置及びアタックコースの表示例を示す。ブロッカー位置及びアタックコースは、プレイ分析結果情報の一例である。 <Blocker position and attack course>
12A, 12B and 12C show an example of display of the blocker position and the attack course. The blocker position and attack course are examples of play analysis result information.
　プレイ分析部１０７は、図１１Ａ又は図１１Ｂに示したアタックのディレクションチャートを表示し、ユーザからアタックコースの選択を受け付ける。プレイ分析部１０７は、アタックコース４１１が選択された場合、図１２Ａに示すように、その選択されたアタックコース４１１に対応するブロッカーの背番号及び位置４２１を表示する。これにより、ユーザは、アタックがブロックの何処を抜いたのかを一目で認識できる。なお、ブロッカーの背番号は、表示されなくてもよい。 The play analysis unit 107 displays the attack direction chart shown in FIG. 11A or FIG. 11B, and accepts the selection of the attack course from the user. When the attack course 411 is selected, the play analysis unit 107 displays the uniform number and the position 421 of the blocker corresponding to the selected attack course 411, as shown in FIG. 12A. This allows the user to recognize at a glance where the attack has pulled out of the block. The blocker's uniform number does not have to be displayed.
　また、図１２Ｂ及び図１２Ｃに示すように、プレイ分析部１０７は、その選択されたアタックコース４１１Ｃに対応する、トスのボールの移動軌跡４２２、及び／又は、ブロッカーの移動軌跡４２３Ａ、４２３Ｂを表示する。図１２Ｂに示すように、ブロッカーの移動軌跡４２３Ａは、トス時のブロッカー位置とアタック時のブロッカー位置とを直線で結んだものであってよい。或いは、図１２Ｃに示すように、ブロッカーの移動軌跡４２３Ｂは、トス時からアタック時までのフレーム画像１１１毎のブロッカー位置を連続で結んだものであってよい。図１２Ｃに示すように、ブロッカーの移動軌跡を詳細に表示することにより、ブロッカーに対するフェイントなどの効果を分析できる。 Further, as shown in FIGS. 12B and 12C, the play analysis unit 107 displays the movement locus 422 of the toss ball and / or the movement locus 423A and 423B of the blocker corresponding to the selected attack course 411C. To do. As shown in FIG. 12B, the movement locus 423A of the blocker may be a straight line connecting the blocker position at the time of tossing and the blocker position at the time of attack. Alternatively, as shown in FIG. 12C, the movement locus 423B of the blocker may continuously connect the blocker positions for each frame image 111 from the time of toss to the time of attack. As shown in FIG. 12C, by displaying the movement locus of the blocker in detail, the effect of a feint or the like on the blocker can be analyzed.
＜ブロッカー重心位置及びアタックコース＞
　図１３は、ブロッカー重心位置及びアタックコース４１１の表示例を示す。ブロッカー重心位置は、例えば、ブロッカーが１人の場合、そのブロッカーの位置であり、ブロッカーが２人の場合、その２人のブロッカーの位置の中点であり、ブロッカーが３人の場合、その３人のブロッカーの位置を頂点とする三角形の重心点である。 <Blocker center of gravity position and attack course>
FIG. 13 shows a display example of the blocker center of gravity position and the attack course 411. The position of the center of gravity of the blocker is, for example, the position of the blocker when there is one blocker, the midpoint of the positions of the two blockers when there are two blockers, and the position of the blocker when there are three blockers. It is the center of gravity of a triangle whose apex is the position of a human blocker.
　プレイ分析部１０７は、図１１Ａ又は図１１Ｂに示すようなアタックのディレクションチャートを表示し、ユーザからアタックコース４１１の選択を受け付ける。プレイ分析部１０７は、アタックコース４１１が選択された場合、図１３に示すように、その選択されたアタックコース４１１に対応する、トスのボールの移動軌跡４２２、及び／又は、複数のブロッカー（前衛３人）の重心位置４３１の移動軌跡４３２を表示する。ブロッカーの重心位置４３１の移動軌跡４３２は、トスからアタックまでのフレーム画像１１１毎の各ブロッカー位置に基づいて算出される。これにより、トスからアタックまでの間における、ブロッカー全体の動きを把握できる。 The play analysis unit 107 displays an attack direction chart as shown in FIG. 11A or FIG. 11B, and accepts the user to select the attack course 411. When the attack course 411 is selected, the play analysis unit 107 indicates the movement locus 422 of the toss ball and / or a plurality of blockers (avant-garde) corresponding to the selected attack course 411, as shown in FIG. The movement locus 432 of the center of gravity position 431 of 3 people) is displayed. The movement locus 432 of the center of gravity position 431 of the blocker is calculated based on each blocker position for each frame image 111 from toss to attack. This makes it possible to grasp the movement of the entire blocker from toss to attack.
＜トス時のブロッカー重心位置を用いたトスチャートのフィルタリング＞
　図１４は、トス時のブロッカー（前衛３人の）重心位置と、トスチャートに対するフィルタリングと、の関係を説明するための図である。 <Filtering the toss chart using the blocker center of gravity position during toss>
FIG. 14 is a diagram for explaining the relationship between the position of the center of gravity of the blockers (three avant-gardes) at the time of toss and the filtering for the toss chart.
　例えば、プレイ分析部１０７は、ネット幅を分割した複数の区間４４１を設定する。ユーザが複数の区間４４１のうちの１つを選択すると、プレイ分析部１０７は、その選択された区間４４１に属する少なくとも１つのトス時のブロッカー重心位置４３１を特定する。そして、プレイ分析部１０７は、図９に示すようなトスチャートに対して、その特定したトス時のブロッカー重心位置４３１に対応付けられているトスマーク４０１を表示し、それ以外のトスマーク４０１を非表示にするフィルタリングを行う。これにより、ユーザは、ブロッカー全体の位置（重心位置）と、トスとの関係を分析できる。 For example, the play analysis unit 107 sets a plurality of sections 441 in which the net width is divided. When the user selects one of the plurality of sections 441, the play analysis unit 107 identifies at least one tossed blocker center of gravity position 431 belonging to the selected section 441. Then, the play analysis unit 107 displays the toss mark 401 associated with the blocker center of gravity position 431 at the time of the specified toss on the toss chart as shown in FIG. 9, and hides the other toss marks 401. Perform filtering. This allows the user to analyze the relationship between the position of the entire blocker (center of gravity position) and the toss.
（本開示のまとめ）
　本開示の一態様に係るプレイ分析装置１００は、受信部１０１及び制御部１０２を有する。受信部１０１は、複数のカメラ３が撮影した複数のフレーム画像１１１を受信する。制御部１０２は、バレーボールのプレイ中のボールのボール軌跡情報１１２に基づいて、「トス」（第１のアクション）と、「トス」の後の「アタック」（第２のアクション）とを検出し、「トス」と「アタック」との間のフレーム画像１１１に基づいて、「トス」と「アタック」との間に「ブロック」（第３のアクション）を行った選手（ブロッカー）を検出し、ブロックに関する分析結果を表示する。この構成により、監督等は、表示された分析結果から、「ブロック」を分析できる。 (Summary of this disclosure)
The play analyzer 100 according to one aspect of the present disclosure includes a receiving unit 101 and a control unit 102. The receiving unit 101 receives a plurality of frame images 111 captured by the plurality of cameras 3. The control unit 102 detects a "toss" (first action) and an "attack" (second action) after the "toss" based on the ball trajectory information 112 of the ball during volleyball play. , Detects the player (blocker) who performed the "block" (third action) between the "toss" and the "attack" based on the frame image 111 between the "toss" and the "attack". Display the analysis result for the block. With this configuration, the supervisor or the like can analyze the "block" from the displayed analysis result.
　制御部１０２は、分析結果として、「トス」が行われた位置と、当該位置の「トス」に対して「ブロック」を行った選手の数と、を表示してよい。この構成により、ユーザは、トスに対して何枚のブロックが行われたかを分析できる。 As an analysis result, the control unit 102 may display the position where the "toss" was performed and the number of players who "blocked" the "toss" at the position. This configuration allows the user to analyze how many blocks have been made to the toss.
　制御部１０２は、分析結果として、「ブロック」を行った選手毎の、「ブロック」の成功及び／又は失敗の回数を示すグラフを表示してよい。この構成により、ユーザは、各選手の「ブロック」の成功及び／又は失敗を分析できる。 As an analysis result, the control unit 102 may display a graph showing the number of successes and / or failures of the "block" for each player who performed the "block". This configuration allows the user to analyze the success and / or failure of each player's "block".
　制御部１０２は、分析結果として、「ブロック」を行った複数の選手の組み合わせ毎の、「ブロック」の成功及び／又は失敗の回数を示すグラフを表示してよい。この構成により、ユーザは、選手の組み合わせによる「ブロック」の成功及び／又は失敗を分析できる。 As an analysis result, the control unit 102 may display a graph showing the number of successes and / or failures of the "block" for each combination of a plurality of players who have performed the "block". With this configuration, the user can analyze the success and / or failure of the "block" by the combination of players.
　制御部１０２は、分析結果として、「アタック」されたボールの軌跡を、当該「アタック」に対して「ブロック」を行った選手の数に応じて異なる態様にて表示してよい。例えば、制御部１０２は、分析結果として、「アタック」されたボールの軌跡を、「ブロック」を行った選手の数を指定するユーザの操作に応じてフィルタリング表示してよい。例えば、制御部１０２は、分析結果として、「アタック」されたボールの軌跡を、「アタック」が得点に結びついたか否かを指定するユーザの操作に応じてフィルタリング表示してもよい。この構成により、ユーザは、アタックに対するブロック枚数を分析できる。 As an analysis result, the control unit 102 may display the trajectory of the "attacked" ball in a different manner depending on the number of players who "block" the "attack". For example, the control unit 102 may filter and display the trajectory of the “attacked” ball as an analysis result according to the operation of the user who specifies the number of players who have performed the “block”. For example, the control unit 102 may filter and display the trajectory of the “attacked” ball as an analysis result according to the user's operation of specifying whether or not the “attack” is linked to the score. With this configuration, the user can analyze the number of blocks for an attack.
　制御部１０２は、分析結果として、「アタック」されたボールの軌跡と、当該「アタック」が行われたタイミングで「ブロック」を行った選手の位置と、を表示してよい。さらに、制御部１０２は、「ブロック」を行った選手の、「トス」から「アタック」までの間の移動軌跡を表示してよい。この構成により、ユーザは、アタックに対するブロッカーの位置及び移動軌跡を分析できる。 As an analysis result, the control unit 102 may display the trajectory of the "attacked" ball and the position of the player who "blocked" at the timing when the "attack" was performed. Further, the control unit 102 may display the movement locus of the player who performed the "block" from the "toss" to the "attack". With this configuration, the user can analyze the position and movement trajectory of the blocker with respect to the attack.
　制御部１０２は、分析結果として、「アタック」されたボールの軌跡と、「ブロック」を行った複数の選手の位置に基づいて特定される重心位置の移動軌跡と、を表示してよい。この構成により、ユーザは、アタックに対するブロッカー全体の移動軌跡を分析できる。 As an analysis result, the control unit 102 may display the locus of the "attacked" ball and the movement locus of the center of gravity position specified based on the positions of the plurality of players who have performed the "block". With this configuration, the user can analyze the movement trajectory of the entire blocker with respect to the attack.
　制御部１０２は、分析結果として、「トス」が行われた位置を、「トス」のタイミングにて「ブロック」を行った複数の選手の位置から特定される重心位置に基づいてフィルタリング表示してよい。この構成により、ユーザは、ブロッカー全体の位置（重心位置）と、トスとの関係を分析できる。 As an analysis result, the control unit 102 filters and displays the position where the "toss" is performed based on the position of the center of gravity specified from the positions of the plurality of players who performed the "block" at the timing of the "toss". Good. With this configuration, the user can analyze the relationship between the position of the entire blocker (position of the center of gravity) and the toss.
　以上、本開示に係る実施の形態について図面を参照して詳述してきたが、上述したプレイ分析装置１００の機能は、コンピュータプログラムにより実現され得る。 Although the embodiments according to the present disclosure have been described in detail with reference to the drawings, the functions of the play analyzer 100 described above can be realized by a computer program.
　図１５は、各装置の機能をプログラムにより実現するコンピュータのハードウェア構成を示す図である。このコンピュータ３１００は、キーボード又はマウス、タッチパッド等の入力装置３１０１、ディスプレイ又はスピーカー等の出力装置３１０２、ＣＰＵ（Central Processing Unit）３１０３、ＧＰＵ（Graphics Processing Unit）３１０４、ＲＯＭ（Read Only Memory）３１０５、ＲＡＭ（Random Access Memory）３１０６、ハードディスク装置又はＳＳＤ（Solid State Drive）等の記憶装置３１０７、ＤＶＤ－ＲＯＭ（Digital Versatile Disk Read Only Memory）又はＵＳＢ（Universal Serial Bus）メモリ等の記録媒体から情報を読み取る読取装置３１０８、ネットワークを介して通信を行う送受信装置３１０９を備え、各部はバス３１１０により接続される。 FIG. 15 is a diagram showing a hardware configuration of a computer that realizes the functions of each device by a program. The computer 3100 includes an input device 3101 such as a keyboard or mouse and a touch pad, an output device 3102 such as a display or a speaker, a CPU (Central Processing Unit) 3103, a GPU (Graphics Processing Unit) 3104, and a ROM (Read Only Memory) 3105. Read information from a recording medium such as RAM (Random Access Memory) 3106, hard disk device or storage device 3107 such as SSD (Solid State Drive), DVD-ROM (Digital Versatile Disk Read Only Memory) or USB (Universal Serial Bus) memory. A reading device 3108 and a transmitting / receiving device 3109 that communicates via a network are provided, and each unit is connected by a bus 3110.
　そして、読取装置３１０８は、上記各装置の機能を実現するためのプログラムを記録した記録媒体からそのプログラムを読み取り、記憶装置３１０７に記憶させる。あるいは、送受信装置３１０９が、ネットワークに接続されたサーバ装置と通信を行い、サーバ装置からダウンロードした上記各装置の機能を実現するためのプログラムを記憶装置３１０７に記憶させる。 Then, the reading device 3108 reads the program from the recording medium on which the program for realizing the function of each of the above devices is recorded, and stores the program in the storage device 3107. Alternatively, the transmission / reception device 3109 communicates with the server device connected to the network, and stores the program downloaded from the server device for realizing the function of each device in the storage device 3107.
　そして、ＣＰＵ３１０３が、記憶装置３１０７に記憶されたプログラムをＲＡＭ３１０６にコピーし、そのプログラムに含まれる命令をＲＡＭ３１０６から順次読み出して実行することにより、上記各装置の機能が実現される。 Then, the CPU 3103 copies the program stored in the storage device 3107 to the RAM 3106, and sequentially reads and executes the instructions included in the program from the RAM 3106, whereby the functions of the above devices are realized.
　例えば、受信部１０１は、送受信装置３１０９によって実現されてよい。例えば、制御部１０２は、ＣＰＵ３１０３及び／又はＧＰＵ３１０４によって実現されてよい。例えば、情報格納部１０８は、ＲＡＭ３１０６及び／又は記憶装置３１０７によって実現されてよい。 For example, the receiving unit 101 may be realized by the transmitting / receiving device 3109. For example, the control unit 102 may be realized by the CPU 3103 and / or the GPU 3104. For example, the information storage unit 108 may be realized by the RAM 3106 and / or the storage device 3107.
　上記の実施の形態の説明に用いた各機能ブロックは、典型的には集積回路であるＬＳＩとして実現される。これらは個別に１チップ化されてもよいし、一部又は全てを含むように１チップ化されてもよい。ここでは、ＬＳＩとしたが、集積度の違いにより、ＩＣ、システムＬＳＩ、スーパーＬＳＩ、ウルトラＬＳＩと呼称されることもある。 Each functional block used in the description of the above embodiment is typically realized as an LSI which is an integrated circuit. These may be individually integrated into one chip, or may be integrated into one chip so as to include a part or all of them. Although it is referred to as LSI here, it may be referred to as IC, system LSI, super LSI, or ultra LSI depending on the degree of integration.
　また、集積回路化の手法はＬＳＩに限るものではなく、専用回路又は汎用プロセッサで実現してもよい。ＬＳＩ製造後に、プログラムすることが可能なＦＰＧＡ（Field Programmable Gate Array）、又は、ＬＳＩ内部の回路セルの接続や設定を再構成可能なリコンフィギュラブル・プロセッサを利用してもよい。 Further, the method of making an integrated circuit 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 the connection and settings of circuit cells inside the LSI may be used.
　さらには、半導体技術の進歩又は派生する別技術によりＬＳＩに置き換わる集積回路化の技術が登場すれば、当然、その技術を用いて機能ブロックの集積化を行ってもよい。バイオ技術の適用等が可能性としてありえる。 Furthermore, if an integrated circuit technology that replaces an LSI appears due to advances in semiconductor technology or another technology derived from it, it is naturally possible to integrate functional blocks using that technology. There is a possibility of applying biotechnology.
　２０１９年６月２０日出願の特願２０１９－１１４８８６の日本出願に含まれる明細書、図面および要約書の開示内容は、すべて本願に援用される。 The disclosures of the specifications, drawings and abstracts contained in the Japanese application of Japanese Patent Application No. 2019-114886 filed on June 20, 2019 are all incorporated herein by reference.
　本開示の一態様は、球技のプレイの分析に有用である。 One aspect of the present disclosure is useful for analyzing the play of ball games.
　１　プレイ分析システム
　３、３Ａ、３Ｂ、３Ｃ、３Ｄ　カメラ
　１０　コート
　１１　ネット
　１２　審判
　２１　ブロッカー
　１００　プレイ分析装置
　１０１　受信部
　１０２　制御部
　１０３　軌跡算出部
　１０４　アクション検出部
　１０５　ブロッカー検出部
　１０６　プレイ情報生成部
　１０７　プレイ分析部
　１０８　情報格納部
　１１１　フレーム画像
　１１２　ボール軌跡情報
　１１３　アクション情報
　１１４　ブロッカー情報
　１１５　プレイ情報
　２１０　表示装置
　２２０　操作装置 1 Play analysis system 3, 3A, 3B, 3C, 3D camera 10 coat 11 net 12 referee 21 blocker 100 play analysis device 101 receiver 102 control unit 103 trajectory calculation unit 104 action detection unit 105 blocker detection unit 106 play information generation unit 107 Play analysis unit 108 Information storage unit 111 Frame image 112 Ball trajectory information 113 Action information 114 Blocker information 115 Play information 210 Display device 220 Operation device

Claims (14)

  1. 　球技のプレイを分析するプレイ分析装置であって、
    　前記プレイを撮影した複数の画像を受信する受信部と、
    　前記複数の画像における前記球技の移動体の軌跡に基づいて、前記球技に関する第１のアクションと前記第１のアクションの後の第２のアクションとを検出し、前記第１のアクションと前記第２のアクションとの間の画像に基づいて、前記第１のアクションと前記第２のアクションとの間に第３のアクションを行った選手を検出し、前記プレイにおける前記第３のアクションに関する分析結果を表示する制御部と、
    　を備える、プレイ分析装置。     A play analyzer that analyzes the play of ball games.
    A receiver that receives a plurality of images of the play and
    Based on the locus of the moving body of the ball game in the plurality of images, the first action related to the ball game and the second action after the first action are detected, and the first action and the second action are detected. Based on the image between the actions, the player who performed the third action between the first action and the second action is detected, and the analysis result regarding the third action in the play is obtained. The control unit to display and
    A play analyzer equipped with.
  2. 　前記制御部は、前記分析結果として、前記第１のアクションが行われた位置と、当該位置の前記第１のアクションに対して前記第３のアクションを行った選手の数と、を表示する、
    　請求項１に記載のプレイ分析装置。     As the analysis result, the control unit displays the position where the first action is performed and the number of athletes who have performed the third action with respect to the first action at the position.
    The play analyzer according to claim 1.
  3. 　前記制御部は、前記分析結果として、前記第３のアクションを行った選手毎の、前記第３のアクションの成功及び／又は失敗の回数を表示する、
    　請求項１に記載のプレイ分析装置。     As the analysis result, the control unit displays the number of successes and / or failures of the third action for each player who has performed the third action.
    The play analyzer according to claim 1.
  4. 　前記制御部は、前記分析結果として、前記第３のアクションを行った複数の選手の組み合わせ毎の、前記第３のアクションの成功及び／又は失敗の回数を表示する、
    　請求項１に記載のプレイ分析装置。     As the analysis result, the control unit displays the number of successes and / or failures of the third action for each combination of the plurality of athletes who have performed the third action.
    The play analyzer according to claim 1.
  5. 　前記制御部は、前記分析結果として、前記第２のアクションが行われた前記移動体の軌跡を、前記第２のアクションに対して前記第３のアクションを行った選手の数に応じて異なる態様にて表示する、
    　請求項１に記載のプレイ分析装置。     As a result of the analysis, the control unit sets the trajectory of the moving body on which the second action is performed, depending on the number of athletes who have performed the third action with respect to the second action. Display at,
    The play analyzer according to claim 1.
  6. 　前記制御部は、前記分析結果として、前記第２のアクションが行われた前記移動体の軌跡を、前記第３のアクションを行った選手の数を指定するユーザの操作に応じてフィルタリング表示する、
    　請求項５に記載のプレイ分析装置。     As a result of the analysis, the control unit filters and displays the locus of the moving body on which the second action has been performed according to an operation of a user who specifies the number of athletes who have performed the third action.
    The play analyzer according to claim 5.
  7. 　前記制御部は、前記分析結果として、前記第２のアクションが行われた前記移動体の軌跡を、前記第２のアクションが得点に結びついたか否かを指定するユーザの操作に応じてフィルタリング表示する、
    　請求項５に記載のプレイ分析装置。     As the analysis result, the control unit filters and displays the locus of the moving body on which the second action is performed according to the operation of the user who specifies whether or not the second action is linked to the score. ,
    The play analyzer according to claim 5.
  8. 　前記制御部は、前記分析結果として、前記第２のアクションが行われた前記移動体の軌跡と、前記第２のアクションが行われたタイミングで前記第３のアクションを行った選手の位置と、を表示する、
    　請求項１に記載のプレイ分析装置。     As a result of the analysis, the control unit determines the trajectory of the moving body on which the second action is performed, the position of the player who performed the third action at the timing when the second action is performed, and the position of the player who performed the third action. To display,
    The play analyzer according to claim 1.
  9. 　前記制御部は、前記第３のアクションを行った選手の、前記第１のアクションから前記第２のアクションまでの間の移動軌跡を表示する、
    　請求項８に記載のプレイ分析装置。     The control unit displays the movement locus of the player who has performed the third action from the first action to the second action.
    The play analyzer according to claim 8.
  10. 　前記制御部は、前記分析結果として、前記第２のアクションが行われた前記移動体の軌跡と、前記第３のアクションを行った複数の選手の位置に基づいて特定される重心位置の移動軌跡と、を表示する、
    　請求項１に記載のプレイ分析装置。     As a result of the analysis, the control unit has a movement locus of the center of gravity position specified based on the locus of the moving body on which the second action is performed and the positions of a plurality of athletes who have performed the third action. And, to display,
    The play analyzer according to claim 1.
  11. 　前記制御部は、前記分析結果として、前記第１のアクションが行われた位置を、前記第１のアクションのタイミングにて前記第３のアクションを行った複数の選手の位置から特定される重心位置に基づいてフィルタリング表示する、
    　請求項１に記載のプレイ分析装置。     As a result of the analysis, the control unit determines the position where the first action is performed from the positions of a plurality of athletes who have performed the third action at the timing of the first action. Filtering display based on,
    The play analyzer according to claim 1.
  12. 　前記球技はバレーボールであり、
    　前記第１のアクションはトスであり、
    　前記第２のアクションはアタックであり、
    　前記第３のアクションはブロックである、
    　請求項１に記載のプレイ分析装置。     The ball game is volleyball
    The first action is toss,
    The second action is attack,
    The third action is a block,
    The play analyzer according to claim 1.
  13. 　球技のプレイを分析するプレイ分析方法であって、
    　前記プレイを撮影した複数の画像を受信し、
    　前記複数の画像における前記球技の移動体の軌跡に基づいて、前記球技に関する第１のアクションと前記第１のアクションの後の第２のアクションとを検出し、前記第１のアクションと前記第２のアクションとの間の画像に基づいて、前記第１のアクションと前記第２のアクションとの間に第３のアクションを行った選手を検出し、前記プレイにおける前記第３のアクションに関する分析結果を表示する、
    　プレイ分析方法。     It is a play analysis method that analyzes the play of ball games.
    Receive a plurality of images of the play,
    Based on the locus of the moving body of the ball game in the plurality of images, the first action related to the ball game and the second action after the first action are detected, and the first action and the second action are detected. Based on the image between the actions, the player who performed the third action between the first action and the second action is detected, and the analysis result regarding the third action in the play is obtained. indicate,
    Play analysis method.
  14. 　球技のプレイを分析するコンピュータプログラムであって、
    　前記プレイを撮影した複数の画像を受信し、
    　前記複数の画像における前記球技の移動体の軌跡に基づいて、前記球技に関する第１のアクションと前記第１のアクションの後の第２のアクションとを検出し、前記第１のアクションと前記第２のアクションとの間の画像に基づいて、前記第１のアクションと前記第２のアクションとの間に第３のアクションを行った選手を検出し、前記プレイにおける前記第３のアクションに関する分析結果を表示する、
    　ことをコンピュータに実行させる、
    　コンピュータプログラム。     A computer program that analyzes the play of ball games
    Receive a plurality of images of the play,
    Based on the locus of the moving body of the ball game in the plurality of images, the first action related to the ball game and the second action after the first action are detected, and the first action and the second action are detected. Based on the image between the actions, the player who performed the third action between the first action and the second action is detected, and the analysis result regarding the third action in the play is obtained. indicate,
    Let the computer do that,
    Computer program.
PCT/JP2020/023558 2019-06-20 2020-06-16 Play analysis device, play analysis method, and computer program WO2020255948A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019-114886 2019-06-20
JP2019114886A JP7345108B2 (en) 2019-06-20 2019-06-20 Play analysis device, play analysis method, and computer program

Publications (1)

Publication Number Publication Date
WO2020255948A1 true WO2020255948A1 (en) 2020-12-24

Family

ID=73994481

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/023558 WO2020255948A1 (en) 2019-06-20 2020-06-16 Play analysis device, play analysis method, and computer program

Country Status (2)

Country Link
JP (1) JP7345108B2 (en)
WO (1) WO2020255948A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7071018B1 (en) * 2021-02-16 2022-05-18 Ｎｅｃプラットフォームズ株式会社 Evaluation equipment, methods and programs
JP7144778B1 (en) * 2022-08-02 2022-09-30 シンメディクト株式会社 Competition Management Program, Competition Management Device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006122646A (en) * 2004-09-30 2006-05-18 Hiroshima Univ Information processing method, information processing device, scouting system, information processing program, and computer-readable recording medium
JP2007252697A (en) * 2006-03-24 2007-10-04 Hiroshima Univ Play data collection and analysis system and data collection and analysis program for volleyball game
US20150018990A1 (en) * 2012-02-23 2015-01-15 Playsight Interactive Ltd. Smart-court system and method for providing real-time debriefing and training services of sport games

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006122646A (en) * 2004-09-30 2006-05-18 Hiroshima Univ Information processing method, information processing device, scouting system, information processing program, and computer-readable recording medium
JP2007252697A (en) * 2006-03-24 2007-10-04 Hiroshima Univ Play data collection and analysis system and data collection and analysis program for volleyball game
US20150018990A1 (en) * 2012-02-23 2015-01-15 Playsight Interactive Ltd. Smart-court system and method for providing real-time debriefing and training services of sport games

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
IKENAGA, TAKESHI: "Sport Information Processing by using Vision Sensor", IEICE TECHNICAL REPORT, vol. 116, no. 344, 1 December 2016 (2016-12-01), pages 25 - 30 *
TAKAHASHI, SHIGEKI: "A note on player and ball tracking in volleyball videos and its application to event estimation", ITE TECHNICAL REPORT, vol. 34, no. 6, 15 February 2010 (2010-02-15), pages 17 - 21, XP055699954 *

Also Published As

Publication number Publication date
JP7345108B2 (en) 2023-09-15
JP2021000217A (en) 2021-01-07

Similar Documents

Publication Publication Date Title
JP7289080B2 (en) Ball game video analysis device and ball game video analysis method
US11049258B2 (en) Stereoscopic image capture with performance outcome prediction in sporting environments
CN108697922B (en) Sensing device and sensing method for baseball practice device, baseball practice device using the same, and control method thereof
JP6915701B2 (en) Extraction program, extraction method and information processing equipment
US11798318B2 (en) Detection of kinetic events and mechanical variables from uncalibrated video
US20180137363A1 (en) System for the automated analisys of a sporting match
JP2014512903A (en) Sensing device and sensing method used in virtual golf simulation device
KR20190031111A (en) Virtual tennis simulation system, sensing device and method for sensing process using the same
WO2020255948A1 (en) Play analysis device, play analysis method, and computer program
WO2020235339A1 (en) Play analyzing device, and play analyzing method
JP7113335B2 (en) Play analysis device and play analysis method
JP7113336B2 (en) Play analysis device and play analysis method
WO2020255716A1 (en) Play analysis device, play analysis method, and computer program
JP7164334B2 (en) Motion analysis device, motion analysis method and motion analysis program
WO2020071092A1 (en) Play analysis device and play analysis method
CN115845349A (en) General training method for ball game items for moving target detection based on deep learning technology and auxiliary referee system
JP7296546B2 (en) Play analysis device and play analysis method
WO2020230677A1 (en) Play analysis apparatus and play analysis method
WO2023106201A1 (en) Play analysis device, play analysis method, and computer-readable storage medium
Liu et al. Badminton Shot Event Detection and Feature Calculation from 3D Rally Video
Yan Design and Application of Basketball Tactical Drill System Based on Motion Trajectory Analysis Algorithm
WO2006002293A2 (en) Apparatus, method and computer program product for analysing flight of an object
WO2022056315A1 (en) System and method for capture and analysis of sporting performance data and broadcast of the same
JP2023044410A (en) Tactical analyzer and method for controlling the same, and control program
WO2023089520A1 (en) System for acquiring and analysing a sports performance

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20826525

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20826525

Country of ref document: EP

Kind code of ref document: A1