JP7433504B1 - Determination device, determination method and computer program - Google Patents

Abstract

[Problem] To make it possible to obtain information regarding movement in a competition without attaching a sensor to a moving object. [Solution] A moving object that detects a moving object image that is an image of the moving object in each of a plurality of stadium images obtained by photographing a plurality of moving objects moving in a competition from a plurality of viewpoints at the same timing. an image detection unit, and a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, which are images of the same moving object. a position determination unit that determines the position of the moving body in three-dimensional space based on the position determination unit; and a value of the speed of the mobile body is calculated based on the amount of time change in the position of the three-dimensional space determined by the position determination unit. A determination device comprising: a related information acquisition unit. [Selection diagram] Figure 1

Description

The present invention relates to a determination device, a determination method, and a computer program.

Conventionally, competitions such as bicycle races, horse races, and car races have been held in which moving objects (eg, bicycles, racehorses, and automobiles) compete for travel time and ranking. Such competitions have many spectators, and techniques have been proposed for providing information about the competition to the spectators. For example, Patent Document 1 discloses a technique that determines whether a predetermined contestant is a contestant who has been subject to deliberation and has not been disqualified, and outputs the number of times the contestant has been subject to non-disqualification deliberation.

Japanese Patent Application Publication No. 2018-116331

However, the information provided to spectators at competitions was not always sufficient. For example, even if it is desired to provide information regarding the movement of a moving object (such as speed and acceleration), it may be difficult to attach sensors due to the circumstances of the competition or the moving object. In such cases, it may be difficult to obtain information regarding the movement of the mobile object. Such a problem similarly occurs in competitions where the moving object is a person (for example, sprinting, skating, etc.).

The present invention has been made in view of the above-mentioned circumstances, and provides a technology that makes it possible to obtain information regarding movement without attaching sensors to a moving object during a competition.

One aspect of the present invention is to detect a moving body image that is an image of the moving body in each of a plurality of stadium images obtained by photographing a plurality of moving bodies moving in a competition from a plurality of viewpoints at the same timing. a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, the plurality of moving object images being images of the same moving object; a position determination unit that determines the position of the moving body in three-dimensional space based on the body image; and a position determination unit that determines the speed of the mobile body based on the amount of time change in the position of the three-dimensional space determined by the position determination unit. The determination device includes a related information acquisition unit that calculates a value.

One aspect of the present invention is the above determination device, in which the position determination unit detects a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images. Based on a plurality of moving object images that are images of the same moving object, a first position indicating the position of the moving object in three-dimensional space is determined, and a straight line including a predetermined reference position and the first position is determined. and the floor surface of the stadium where the competition is held, is determined as the position of the moving object in the three-dimensional space.

One aspect of the present invention is the determination device described above, further comprising a video generation section that generates a video including an image related to the value of the speed of the moving object acquired by the related information acquisition section.

One aspect of the present invention is the above-mentioned determination device, in which the video generation unit generates an image that includes images related to speed values of the mobile objects only for some of the mobile objects selected from among the mobile objects. generate.

One aspect of the present invention is to detect a moving body image that is an image of the moving body in each of a plurality of stadium images obtained by photographing a plurality of moving bodies moving in a competition from a plurality of viewpoints at the same timing. a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, the plurality of moving object images being images of the same moving object; a position determination step of determining the position of the moving body in three-dimensional space based on the body image; and determining the speed of the mobile body based on the amount of time change in the position of the three-dimensional space determined in the position determination step. This determination method includes a related information acquisition step of calculating a value.

One aspect of the present invention is to detect a moving body image that is an image of the moving body in each of a plurality of stadium images obtained by photographing a plurality of moving bodies moving in a competition from a plurality of viewpoints at the same timing. a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, the plurality of moving object images being images of the same moving object; a position determination unit that determines the position of the moving body in three-dimensional space based on the body image; and a position determination unit that determines the speed of the mobile body based on the amount of time change in the position of the three-dimensional space determined by the position determination unit. This is a computer program for causing a computer to function as a determination device including a related information acquisition unit that calculates a value.

According to the present invention, it is possible to obtain information regarding the movement of a moving object in a race without having to attach a sensor to the moving object.

1 is a schematic block diagram showing the system configuration of a determination system 100 of the present invention. 2 is a diagram showing a specific example of installation of the imaging system 10. FIG. 2 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20. FIG. FIG. 3 is a diagram showing a specific example of an image of a moving object used as training data. 3 is a flowchart showing a specific example of processing by the learning device 20. FIG. 3 is a schematic block diagram showing a specific example of the functional configuration of a determination device 30. FIG. FIG. 3 is a diagram showing a specific example of mobile object information. FIG. 3 is a diagram showing a specific example of a stadium image. FIG. 3 is a diagram showing a specific example of a moving object image. 3 is a diagram illustrating a specific example of processing by a first position determination unit 333. FIG. 3 is a diagram illustrating a specific example of processing by a second position determination unit 334. FIG. It is a diagram showing a specific example of a video generated after the end of the competition among the videos generated by the video generation unit 336. 3 is a flowchart showing a specific example of the flow of processing by the control unit 33. FIG. 1 is a diagram schematically showing an example of a hardware configuration of an information processing device 90 applied to this embodiment.

FIG. 1 is a schematic block diagram showing the system configuration of a determination system 100 of the present invention. The determination system 100 determines information regarding the movement of a moving body (hereinafter referred to as "movement information") based on an image obtained by capturing a moving body (hereinafter referred to as "competition image"). used when A moving object is an object that moves in a competition. When the competition is a bicycle race or a bicycle race, the moving object is a bicycle driven (operated) by a competitor. When the competition is a horse race such as horse racing, the moving object is a racehorse ridden by a jockey. If the sport is one in which people run, such as short-distance running, middle-distance running, or long-distance running, the moving object is the person himself. When the competition is a boat race, the moving object is a boat operated by a person. When the competition is a skating competition (speed skating, short track, etc.), the moving object is a person moving on skates.

The determination system 100 includes a plurality of imaging systems 10, a learning device 20, and a determination device 30. The plurality of imaging systems 10 and the determination device 30 are communicably connected via a network 70. The learning device 20 and the determination device 30 may be communicably connected via the network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may be configured by combining a plurality of networks.

The imaging system 10 is installed in a stadium where a competition is held, and captures an image of a space including a moving body moving within the stadium (hereinafter referred to as a "stadium image"). The imaging system 10 is configured using an imaging device such as a still camera or a video camera. The imaging system 10 may continuously capture still images at predetermined time intervals, or may capture moving images. The imaging device of the imaging system 10 may be installed to capture an image of the stadium from a predetermined viewpoint position at a predetermined angle of view, and camera calibration may be performed in advance.

FIG. 2 is a diagram showing a specific example of installation of the imaging system 10. FIG. 2 shows a track 81 and a viewpoint 101 formed by the imaging system 10 as a specific example of a stadium. A viewpoint 101 indicates a viewpoint when photographing is performed by the imaging system 10. An imaging system 10 is set for each viewpoint 101. The plurality of imaging systems 10 may image overlapping spaces from different positions, for example in one stadium. The imaging system 10 transmits data indicating the stadium image obtained by imaging to the determination device 30. For example, the imaging system 10 transfers the data of the captured stadium image to the determination device 30 in such a way that the time lag from the timing when the data of the stadium image is obtained through imaging until the data of the stadium image is transmitted is as short as possible. You may also send it to

FIG. 3 is a schematic block diagram showing a specific example of the functional configuration of the learning device 20. As shown in FIG. The learning device 20 is configured using, for example, an information processing device such as a personal computer or a server device. The learning device 20 includes a communication section 21, a storage section 22, and a control section 23.

The communication unit 21 is a communication device. The communication unit 21 may be configured as a network interface, for example. The communication unit 21 performs data communication with other devices via the network 70 under the control of the control unit 23 . The communication unit 21 may be a device that performs wireless communication or may be a device that performs wired communication.

The storage unit 22 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may function as a teacher data storage unit 221 and a trained model storage unit 222, for example.

The teacher data storage unit 221 stores teacher data used in learning processing executed in the learning device 20. The teacher data stored in the teacher data storage unit 221 includes an image of a moving object. The teacher data may be a combination of an image of a moving object or an image of an object other than a moving object, and label information indicating whether the image is an image of a moving object. The image of the moving object used as the teacher data is an image of the target moving object detected using the trained model. As the images of moving objects used for the training data, it is desirable that images of various moving objects taken in the target competition are used.

FIG. 4 is a diagram showing a specific example of an image of a moving object used as training data. For example, if the target competition is a cycling competition, it is desirable to use images of various athletes pedaling bicycles in the competition. FIG. 4 shows an image obtained by photographing the back of a bicycle athlete from behind. Furthermore, it is desirable that the images of the moving object used for the training data be images of the moving object taken from various angles. Robustness can be improved by using such images as training data. For example, when the center of the image is used as position information on the image plane of the detection result of an image of a moving object, the image of the moving object used as training data is an image in which the center of the moving object is located at the center. is preferably used.

The trained model storage unit 222 stores a trained model obtained by a learning process using the teacher data stored in the teacher data storage unit 221.

The control unit 23 is configured using a processor such as a CPU (Central Processing Unit) and a memory (main storage device). The control unit 23 functions as an information control unit 231 and a learning control unit 232 when a processor executes a program. Note that all or part of each function of the control unit 23 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, semiconductor storage devices (such as SSDs: Solid State Drives), and hard disks and semiconductor storages built into computer systems. It is a storage device such as a device. The above program may be transmitted via a telecommunications line.

The information control unit 231 controls input and output of information. For example, the information control unit 231 acquires teacher data from another device (an information processing device or a storage medium) and records it in the teacher data storage unit 221. For example, the information control unit 231 transmits the trained model stored in the trained model storage unit 222 to another device (for example, the determination device 30).

The learning control unit 232 executes learning processing using the teacher data stored in the teacher data storage unit 221. As a specific example of such learning processing, for example, supervised learning for classification such as a support vector machine, random forest, neural network, etc. may be used. The learning control unit 232 generates a trained model for determining whether an input image includes an image of a moving object, by performing supervised learning, for example. The learning control unit 232 records the generated learned model in the learned model storage unit 222. The learned model obtained by the learning control unit 232 may be transmitted to the determination device 30 and recorded in the determination model storage unit 321 of the determination device 30. By giving an image as an input to such a trained model, it is possible to obtain as an output a value indicating whether or not the image includes an image of a moving object.

FIG. 5 is a flowchart showing a specific example of the processing of the learning device 20. First, the information control unit 231 acquires teacher data (step S101). The teacher data may be input by the user, may be obtained through communication from another information device, or may be obtained from a recording medium connected to the learning device 20, for example. The learning control unit 232 executes a learning process using the teacher data and records the learned model in the learned model storage unit 222 (step S102).

FIG. 6 is a schematic block diagram showing a specific example of the functional configuration of the determination device 30. The determination device 30 is configured using, for example, an information processing device such as a personal computer or a server device. The determination device 30 includes a communication section 31, a storage section 32, and a control section 33.

The communication unit 31 is a communication device. The communication unit 31 may be configured as a network interface, for example. The communication unit 31 performs data communication with other devices via the network 70 under the control of the control unit 33 . The communication unit 31 may be a device that performs wireless communication or may be a device that performs wired communication.

The storage unit 32 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 32 stores data used by the control unit 33. The storage unit 32 may function as, for example, a determination model storage unit 321, an imaging device information storage unit 322, a spatial information storage unit 323, a moving object image information storage unit 324, and a moving object information storage unit 325.

The judgment model storage unit 321 stores a judgment model used when the moving object image detection unit 332 detects an image of a moving object (hereinafter referred to as a “moving object image”) from the stadium image. The determination model may be, for example, information on a learned model generated by performing the above-described learning process in advance. Such a learning process may be executed, for example, by another device (for example, the learning device 20) or by the own device (the determination device 30). The determination model may be, for example, pattern information indicating a pattern of an image of a moving object to be detected. Such pattern information can be used, for example, in pattern matching processing to detect a moving object image. The determination model may be configured in any manner as long as it can detect moving object images.

The imaging device information storage unit 322 stores information regarding the imaging device of each imaging system 10 used in the determination system 100 (hereinafter referred to as “imaging device information”). The imaging device information may include, for example, camera parameters of the imaging device. The camera parameters include, for example, three-dimensional coordinate values indicating the viewpoint position of the imaging device, information indicating the angle of view, and the like.

The spatial information storage unit 323 stores information (hereinafter referred to as "competition space information") indicating the space of the stadium used in the competition that is the target of processing by the determination system 100. The competition space information may include, for example, three-dimensional information about a floor surface (for example, the surface of a track 81 described later) on which a competition is held in a stadium. For example, when the competition is a bicycle competition, the competition space information may include three-dimensional information about the road surface of a track on which a moving object (bicycle) runs in the competition. Note that the three-dimensional information included in the camera parameters in the imaging device information and the three-dimensional information indicated by the competition space information may be expressed in the same coordinate system, or may be expressed in coordinate systems that can be converted into each other. good.

The moving object image information storage unit 324 stores information regarding each moving object image detected from the stadium image. The moving object image information storage unit 324 stores, for each moving object image, information indicating the stadium image where the moving object image was detected and identification information indicating the moving object (for example, athlete number, bib number, athlete name, movement (body name, etc.) and information indicating the position of the moving object image on the image plane (for example, x and y coordinate values) are stored in association with each other. The information indicating the stadium image includes, for example, information indicating which imaging system 10 has captured the image (for example, identification information indicating the imaging system 10), and information related to the timing at which the stadium image was captured ( For example, frame number, elapsed time, etc.).

The moving body information storage unit 325 stores information regarding each moving body determined at each predetermined timing. FIG. 7 is a diagram showing a specific example of mobile object information. The mobile information includes a plurality of mobile information records. The mobile information record includes a frame number, elapsed time, player number, position information, speed, and absolute time.

The frame number is information indicating the imaging timing of the stadium image in which the moving object image that is the basis of the information included in the moving object information record is detected. The frame number may be, for example, a number indicating the number of frames of a moving image captured as a stadium image. The elapsed time is the time that has passed since a certain predetermined timing. For example, the predetermined timing may be the time that has passed since imaging started. In this case, it is desirable that the timing of starting imaging in each imaging system 10 be synchronized. The predetermined timing may be the timing at which a competition (for example, a race or a match) is started.

The player number is a specific example of identification information for each moving object, and is a number assigned in advance to each moving object (player). In the example of FIG. 7, moving object information records regarding moving objects detected at each imaging timing are continuously recorded, and a moving object information record at the next imaging timing is recorded. Therefore, in the example of FIG. 7, it can be seen that four moving objects are participating in one competition (race).

The position information indicates the position information of each moving object in three-dimensional space detected at each imaging timing. In this embodiment, first position information and second position information are used as the position information, as will be described later. The location information included in the mobile information record may be, for example, second location information. It is desirable that the position information used as the three-dimensional position information of the mobile object in subsequent processing be recorded as the position information of the mobile object information record.

The speed indicates the moving speed of each moving object in the three-dimensional space detected at each imaging timing. The absolute time indicates the time at each imaging timing. The absolute time may include information indicating the day.

The control unit 33 is configured using a processor such as a CPU and a memory. The control unit 33 has an information control unit 331, a moving object image detection unit 332, a first position determination unit 333, a second position determination unit 334, a related information acquisition unit 335, and a video generation unit 336 by the processor executing the program. functions as Note that all or part of each function of the control unit 33 may be realized using hardware such as an ASIC, a PLD, or an FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, semiconductor storage devices (such as SSDs), and storage devices such as hard disks and semiconductor storage devices built into computer systems. It is a device. The above program may be transmitted via a telecommunications line.

The information control unit 331 acquires a stadium image from the imaging system 10. The information control unit 331 transmits information on the video data generated by the video generation unit 336 to other devices such as terminal devices used by viewers of the competition. Such exchange of information between the information control unit 331 and other devices may be performed by communication by the communication unit 31, for example.

The moving body image detection unit 332 detects a moving body image from the stadium image by using the determination model stored in the determination model storage unit 321. The moving object image detection unit 332 detects moving object images equal to or less than the number of participating moving objects from each stadium image at predetermined time intervals after the start of the competition, for example. When the moving object image detection unit 332 detects more moving object image candidates than the participating moving objects from one stadium image (a stadium image captured by one imaging system 10), For example, moving object images may be detected from among these moving object image candidates in descending order of likelihood (a value indicating the likelihood of being an image of a moving object), with the maximum number of moving objects appearing.

The moving object image detection unit 332 obtains in advance a difference image between a stadium image (hereinafter referred to as a "background image") captured by each imaging system 10 before the start of the competition and a stadium image to be processed, and calculates the difference. A moving object image may be detected in an image (an image of a portion that is different from the background image). With this configuration, it becomes possible to detect a moving object image from a stadium image with higher accuracy. In this case, for example, background images photographed in advance by each imaging system 10 may be stored in the storage unit 32.

FIG. 8 is a diagram showing a specific example of a stadium image. FIG. 9 is a diagram showing a specific example of a moving object image. As shown in FIG. 8, the image of the stadium (sport stadium image 800) captured by the imaging system 10 is the subject of processing by the moving body image detection unit 332. The moving object image detection unit 332 detects the moving object image 801 in the stadium image 800. The size of the moving object image 801 may vary depending on the moving object. In the example of FIG. 9, seven moving object images are detected in one stadium image 800.

The moving body image detection unit 332 determines which participating moving body is an image of each moving body image detected in each stadium image. For example, if each participating moving object has an object of a different color (e.g. bib, uniform, body hair, car body, etc.), each moving object image will be assigned an image of which moving object based on the color. It may be determined whether there is. In such a case, for example, a color histogram is generated for each moving object image, and it is determined which moving object each moving object image belongs to based on the histogram and the color of each moving object. It's okay. For example, if each of the participating moving objects has a different appearance pattern (e.g., shape, pattern, number, character, etc.), a feature value indicating the appearance pattern is acquired in each moving object image. , it may be determined which moving object each moving object image is based on the feature amount.

For each detected moving object image, the moving object image detection unit 332 includes information indicating the stadium image in which the moving object image was detected, identification information indicating the moving object, and the position of the moving object image on the image plane. The information indicating the information is recorded in the moving object image information storage unit 324 in association with the information. The position of the moving object image on the image plane may be expressed using a predetermined position of the moving object image. For example, the position of the upper left corner of the moving object image may be used as the position of the moving object image on the image plane, or the position of the center of the moving object image may be used as the position of the moving object image on the image plane. Good too.

The first position determining unit 333 determines a first position indicating the position of each moving object in the three-dimensional space based on the detection result of the moving object image. The first position indicates a position where a part of the detected moving object image exists in three-dimensional space. As part of the moving body image, for example, the center portion of the moving body image may be used, the upper left portion of the moving body image may be used, or another portion may be used.

FIG. 10 is a diagram showing a specific example of processing by the first position determination unit 333. In the determination system 100, the same moving object is imaged from a plurality of viewpoints 101. For example, the stadium image 800_1 is generated when a moving object is imaged from the first viewpoint 101_1, and the moving object image 801_1 is detected at a position (X1, Y1) on the image plane. The position on the image plane indicates the position of a portion of the above-mentioned moving body image. A stadium image 800_2 and a stadium image 800_3 are also generated at the second viewpoint 101_2 and the third viewpoint 101_3, respectively. The first position determining unit 333 determines which part of the moving object is located based on the position on the image plane of the moving object image in the stadium image 800 taken at each viewpoint 101 and the camera parameters of the imaging device at each viewpoint 101. The position (Xr, Yr, Zr) in three-dimensional space is calculated. The position calculated through such processing is the first position 103. Such processing can be executed if there is the above information on at least two viewpoints 101, but it may be calculated using the above information on three or more viewpoints 101 as shown in FIG.

The second position determining unit 334 determines the second position of each moving body in the three-dimensional space based on the first position of each moving body. The second position is a position related to each first position, and indicates a position in a three-dimensional space at a predetermined height from the level of the floor surface where the competition is played in the stadium. For example, the position in three-dimensional space on the surface of the floor where the competition is played may be determined as the second position.

FIG. 11 is a diagram illustrating a specific example of processing by the second position determination unit 334. The second position determination unit 334 emits a straight line vector from a predetermined reference position 102 predetermined in the three-dimensional space toward the first position 103, and the straight line vector that has passed through the first position 103 is placed on the three-dimensional space. A point that intersects with the surface of the track 81 modeled in advance (for example, a running road surface) is determined as a second position (Xc, Yc, Zc) 104. In other words, the second position determination unit 334 determines the intersection of the straight line including the predetermined reference position 102 and the first position 103 and the surface of the track 81 as the second position.

The second position 104 is defined as a position on the surface of the track 81 rather than a three-dimensional spatial position of the moving body itself. The coordinates of the predetermined reference position 102 are expressed as (Xvp, Yvp, Zvp) in FIG. The predetermined reference position 102 may be the viewpoint position of any one of the imaging systems 10, or may be a virtually determined position independent of the imaging system 10. The predetermined reference position 102 may be provided above the inside of the ring-shaped stadium (track) as shown in FIG. 11, or may be provided above the outside of the ring-shaped stadium. After calculating the position information of the second position, the second position determination unit 334 records the calculated position information as position information of the moving object information record. In addition, in FIGS. 10 and 11, the first position is defined as the back part of the moving body bent over, but the first position is not limited to such a position. For example, the first position may be set close to the center of the moving body.

The related information acquisition unit 335 acquires information related to the mobile bodies based on the second position of each mobile body determined by the second position determination unit 334. For example, the related information acquisition unit 335 may calculate the value of the speed of the moving object based on the amount of change over time in the second position. For example, the related information acquisition unit 335 may calculate the value of the acceleration of the moving body based on the amount of change over time in the second position. For example, the related information acquisition unit 335 may calculate the magnitude of the force being output by the moving body based on the value of the acceleration of the moving body.

The video generation unit 336 generates a video including an image representing information obtained through the processing of the control unit 33. Specific examples of information obtained by the processing of the control unit 33 include information such as the first position or second position, speed, acceleration, and magnitude of force of each moving body. The images generated by the image generation unit 336 include images generated in real time during the competition and images generated after the competition ends. FIG. 12 is a diagram showing a specific example of a video generated after the competition, among the videos generated by the video generation unit 336. FIG. 12 shows a display area 61 in which a moving image showing the state of the competition is displayed, a display area 62 in which an image showing a prediction of the line-up is displayed, and an image showing the speed of some moving objects (athletes). A display area 63 is shown, and a display area 64 is shown where a graph of time-series changes in speed of some moving objects (athletes) is displayed. Some of the moving objects (players) shown in the display area 64 may be selected by a person such as an administrator of the determination device 30, for example. In this case, the determination device 30 may include a user interface such as an input device and an output device, and the selection may be received via the user interface. In the display area 64, as a graph of time-series changes, a graph showing values up to the time of the moving image currently being displayed in the display area 61 and a graph showing values after that time are shown in different forms. Displayed.

FIG. 13 is a flowchart showing a specific example of the flow of processing by the control unit 33. The information control unit 331 acquires a stadium image (step S201). The moving object image detection unit 332 detects moving object images from each stadium image (step S202). The first position determining unit 333 determines the first position, which is the position of each moving object in the three-dimensional space, based on the position of each detected moving object image (step S203). The second position determining unit 334 determines the second position of each moving body, which is the position in the three-dimensional space, based on the first position of each moving body (step S204). The related information acquisition unit 335 obtains related information by using information such as the second position of each moving object (step S205). The video generation unit 336 generates a video using the acquired information (step S206). The video generation unit 336 outputs the generated video to a predetermined device. The predetermined device may be, for example, a distribution device that distributes video to multiple user terminals.

FIG. 14 is a diagram schematically showing an example of the hardware configuration of the information processing device 90 applied to this embodiment. The information processing device 90 includes a processor 91 , a main memory 92 , a communication interface 93 , an auxiliary memory 94 , an input/output interface 95 , and an internal bus 96 . The processor 91 , main memory 92 , communication interface 93 , auxiliary memory 94 , and input/output interface 95 are communicably connected to each other via an internal bus 96 . The information processing device 90 may be applied to the learning device 20 and the determination device 30, for example. In this case, for example, the communication unit 21 and the communication unit 31 may be configured using the communication interface 93. For example, the storage unit 22 and the storage unit 32 may be configured using an auxiliary storage device 94. Further, the control unit 23 and the control unit 33 may be configured using the processor 91 and the main storage device 92.

(Modified example)
The learning device 20 may be implemented using a plurality of information processing devices. For example, the learning device 20 may be implemented using a device such as a cloud. For example, in the learning device 20, the storage section 22 and the control section 23 may be implemented in different information processing devices. For example, the storage unit 22 of the learning device 20 may be distributed and implemented in a plurality of information processing devices. The determination device 30 may be implemented using a plurality of information processing devices. For example, the determination device 30 may be implemented using a device such as a cloud. For example, in the determination device 30, the storage section 32 and the control section 33 may be implemented in different information processing devices. For example, the storage unit 32 of the determination device 30 may be distributed and implemented in a plurality of information processing devices. For example, the control unit 33 of the determination device 30 may be distributed and implemented in a plurality of information processing devices.

The related information acquisition unit 335 of the determination device 30 described above acquired information related to the moving bodies based on the second position of each moving body. However, the related information acquisition unit 335 of the determination device 30 may acquire information related to the moving bodies based on the first position of each moving body.

Although the embodiments of the present invention have been described above in detail with reference to the drawings, the specific configuration is not limited to these embodiments, and includes designs within the scope of the gist of the present invention.

DESCRIPTION OF SYMBOLS 100... Judgment system, 101... Viewpoint, 102... Reference position, 103... First position, 104... Second position, 10... Imaging system, 20... Learning device, 21... Communication unit, 22... Storage unit, 221... Teacher data Storage section, 222... Learned model storage section, 23... Control section, 231... Information control section, 232... Learning control section, 30... Judgment device, 31... Communication section, 32... Storage section, 321... Judgment model storage section, 322... Imaging device information storage section, 323... Spatial information storage section, 324... Moving object image information storage section, 325... Moving object information storage section, 33... Control section, 331... Information control section, 332... Moving object image detection section , 333...First position determination unit, 334...Second position determination unit, 335...Related information acquisition unit, 336...Video generation unit, 800... Stadium image, 801...Moving object image, 81...Track

Claims (5)

a moving object image detection unit that detects a moving object image that is an image of the moving object in each of a plurality of stadium images obtained by photographing a plurality of moving objects moving in a competition from a plurality of viewpoints at the same timing; ,
Among the moving body images, the moving body images are detected from a plurality of stadium images taken at the same timing, and are images of the same moving body. a position determination unit that determines the position of the body in three-dimensional space;
a related information acquisition unit that calculates a value of the speed of the moving body based on the amount of time change in the position in the three-dimensional space determined by the position determination unit;
Equipped with
The position determination unit detects a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, and which are images of the same moving object. A first position indicating the position of the moving body in three-dimensional space is determined based on the above, and a straight line including a predetermined reference position and the first position is connected to the floor of the stadium where the competition is held. A determination device that determines a second position indicating an intersection as a position of the moving body in a three-dimensional space . The determination device according to claim 1, further comprising a video generation unit that generates a video including an image related to the speed value of the moving object acquired by the related information acquisition unit. The determination device according to claim 2 , wherein the video generation unit generates a video including images related to speed values of only some of the mobile objects selected from among the mobile objects. a moving object image detection step of detecting a moving object image that is an image of the moving object in each of a plurality of stadium images obtained by photographing a plurality of moving objects moving in a competition from a plurality of viewpoints at the same timing; ,
Among the moving body images, the moving body images are detected from a plurality of stadium images taken at the same timing, and are images of the same moving body. a position determination step of determining the position of the body in three-dimensional space;
a related information acquisition step of calculating a value of the speed of the moving body based on the amount of change over time of the position in the three-dimensional space determined in the position determination step;
has
In the position determination step, among the moving object images, a plurality of moving object images are detected from a plurality of stadium images taken at the same timing, and are images of the same moving object. A first position indicating the position of the moving object in three-dimensional space is determined based on the above, and a straight line including a predetermined reference position and the first position is connected to the floor of the stadium where the competition is held. A determination method that determines a second position indicating an intersection as a position of the moving body in a three-dimensional space . a moving object image detection unit that detects a moving object image that is an image of the moving object in each of a plurality of stadium images obtained by photographing a plurality of moving objects moving in a competition from a plurality of viewpoints at the same timing; ,
Among the moving body images, the moving body images are detected from a plurality of stadium images taken at the same timing, and are images of the same moving body. a position determination unit that determines the position of the body in three-dimensional space;
a related information acquisition unit that calculates a value of the speed of the moving object based on the amount of time change in the position in the three-dimensional space determined by the position determination unit;
Equipped with
The position determination unit detects a plurality of moving object images detected from a plurality of stadium images taken at the same timing among the moving object images, and which are images of the same moving object. A first position indicating the position of the moving object in three-dimensional space is determined based on the above, and a straight line including a predetermined reference position and the first position is connected to the floor of the stadium where the competition is held. A computer program for causing a computer to function as a determination device that determines a second position indicating an intersection as a position of the moving object in a three-dimensional space .

Images