CN108854031A

CN108854031A - The method and relevant apparatus of exercise data are analyzed by unmanned camera work

Info

Publication number: CN108854031A
Application number: CN201810526356.7A
Authority: CN
Inventors: 不公告发明人
Original assignee: Shenzhen Zhen Di Information Technology Co Ltd
Current assignee: Shenzhen Zhen Di Information Technology Co Ltd
Priority date: 2018-05-29
Filing date: 2018-05-29
Publication date: 2018-11-23

Abstract

The invention discloses a kind of methods for analyzing exercise data, and for the unmanned camera in a motion analysis system, this method includes：Shoot the movement of a sportsman；And the electronic device of the Wireless transceiver motion film into the motion analysis system, for analyzing the data in the motion film, to generate motion analysis report.Movement of this method convenient for the sportsman of capture grand movement, such as football, basketball, the movement such as skiing improve existing exercise data analysis, use and be collected into correct and effective Athletess data, and then reinforce the performance of sportsman.

Description

Method for analyzing motion data by unmanned photography and related device

Technical Field

The invention relates to a method for analyzing sports data, in particular to a method for analyzing sports data of athletes by unmanned photography technology.

Background

At present, a sensor worn by an athlete is generally adopted for analyzing the athletic data of the athlete to detect the athletic of the athlete or a camera with a fixed position is used for shooting the athletic of the athlete, so that the aim of collecting the athletic data of the athlete is fulfilled, and the collected athletic data is further analyzed to realize the training plan of the athlete. However, current methods of collecting athletic data have their deficiencies.

For example, wearing too many sensors may reduce the comfort of the athlete. In addition, the wearing of the sensor affects the movement and posture of the sport, and the real sport data of the athlete cannot be collected. However, an athlete may not collect enough athletic data if he or she wears too few sensors.

On the other hand, if a fixed camera is used, it may not be possible to capture the movements of a wide range of sports such as soccer, basketball, skiing, etc. Therefore, there is a need for improvement in the analysis of athletic data, so as to collect correct and effective athletic data of athletes, thereby enhancing the performance of athletes.

Disclosure of Invention

It is therefore a primary object of the present invention to provide a method for analyzing athletic data of athletes by unmanned photography, so as to solve the above problems.

The invention discloses a method for analyzing motion data, which is used for an unmanned photographing device in a motion analysis system, and comprises the following steps: shooting a motion of an athlete; and wirelessly transmitting the motion picture to an electronic device in the motion analysis system for analyzing data in the motion picture to generate a motion analysis report.

The invention discloses a method for analyzing motion data, which is used for an electronic device in a motion analysis system, and comprises the following steps: establishing a sports training database containing a plurality of motion parameters corresponding to a plurality of standard motions in at least one sport; wirelessly receiving a motion picture from a unmanned camera device in the motion analysis system; selecting a key frame from the received motion picture; extracting an action feature from the key frame; and performing a matching operation on the motion characteristic according to one of the plurality of standard motions in the exercise training database.

The invention discloses a unmanned photographic device for motion analysis, which is used for analyzing motion data, and comprises: a storage unit for storing a program code related to a process; and a processing unit, coupled to the storage unit, for processing the program code to execute the process; wherein, the process comprises: shooting a motion of an athlete; and wirelessly transmitting the motion picture to an electronic device for analyzing data in the motion picture to generate a motion analysis report.

The invention discloses an electronic device for analyzing motion, which is used for analyzing motion data and comprises: one or more processors; and a memory; wherein the memory stores instructions executable by the one or more processors, the instructions being arranged to perform: establishing a sports training database containing a plurality of motion parameters corresponding to a plurality of standard motions in at least one sport; wirelessly receiving a motion picture from a unmanned photographing device; selecting a key frame from the received motion picture; extracting an action feature from the key frame; and performing a matching operation on the motion characteristic according to one of the plurality of standard motions in the exercise training database.

Drawings

Fig. 1 is a schematic diagram of a motion analysis system according to an embodiment of the invention.

Fig. 2 is a schematic view of a display screen of a terminal device according to an embodiment of the invention.

Fig. 3 is a schematic diagram of an electronic device according to an embodiment of the invention.

FIG. 4 is a flowchart of an embodiment of a process.

Fig. 5 is a schematic diagram illustrating a photographing operation of an unmanned photographing apparatus according to an embodiment of the invention.

FIG. 6 is a flow chart of a process according to an embodiment of the present invention.

FIG. 7 is a diagram illustrating a data analysis operation of a server according to an embodiment of the present invention.

Fig. 8-12 are schematic diagrams illustrating a display operation of a terminal device according to an embodiment of the invention.

Wherein the reference numerals are as follows:

101	unmanned photographing device
		102	Base station
103	Server
		104	Terminal device
105	Exercise analysis report
		20	Electronic device
200	Processing apparatus
		210	Storage unit
220	Communication interface unit
		214	Program code
40、60	Flow path
		400-430、501-505、600-660、701-704	Sub-step
81、91	Title window
		82、92	List window
1-7、83、93、122、122a-122b	Image window
		84、94	Bottom window
B1-B5	Push-button

Detailed Description

Fig. 1 is a schematic diagram of a motion analysis system according to an embodiment of the invention. The motion analysis system includes an unmanned camera 101, a base station 102, a server 103 (optionally configured in the motion analysis system), and a terminal device 104. The unmanned camera device 101 may be a drone or an unmanned ship, and the terminal device 104 may be a mobile phone or a tablet computer, but is not limited thereto. In addition, the unmanned photographing apparatus 101, the base station 102, the server 103 and the terminal apparatus 104 are compatible with wireless communication systems, such as lte technology and wlan technology. As shown in fig. 1, the unmanned camera 101 is an unmanned aerial vehicle for capturing the motion of the athlete, wherein the unmanned camera 101 can perform a Tracking-shooting mode on the athlete according to a visual Tracking algorithm, such as a Kernel Correlation Filter (KCF) and a Tracking-Learning-Detection (TLD), or capture the athlete in a surround-shooting mode for the purpose of collecting the motion data of the athlete. Further, the unmanned photographing apparatus 101 transmits a motion picture including the collected motion data to the base station 102, and then the base station 102 transmits the motion picture to the terminal apparatus 104. Therefore, the user can watch the sports film of the athlete in real time through the terminal device 104. The terminal device 104 stores a motion training database in advance, which includes a plurality of motion parameters corresponding to a plurality of standard motions in at least one motion. It is noted that the sports training database is built by collecting sports data from various sports such as table tennis, badminton, pool tennis, basketball, soccer, swimming, skiing, etc. Therefore, the terminal device 104 can analyze the collected exercise data in real time according to the exercise training database to generate the exercise analysis report 105.

In one embodiment, the terminal device 104 transmits the motion picture received from the unmanned photographing device 101 to the server 103. Server 103 pre-stores a motion training database for performing non-real-time analysis on the motion picture received from terminal 104 (e.g., when terminal 104 is not wirelessly connected to bs 102) to generate motion analysis report 105. In this embodiment, the server 103 transmits the motion analysis report 105 to the terminal device 104 for displaying the motion analysis report 105 to the user for viewing.

Fig. 2 is a schematic diagram of a display screen of a terminal device 104 according to an embodiment of the invention. As shown in fig. 2, the terminal device 104 not only displays real-time sports films of the athlete, but also provides sports selection items (such as skiing, soccer, swimming, and basketball), current speed items, shooting mode items (such as tracking shooting mode or surround shooting mode), and report generation items. Therefore, the user can view the performance of the athlete on the terminal device 104 through the unmanned photographing device 101. It is noted that the unmanned camera 101 may take pictures in front of, behind, or to the side of the athlete. In this embodiment, the unmanned photographing device 101 photographs from the front of the athlete.

Fig. 3 is a schematic diagram of an electronic device 20 according to an embodiment of the invention. The electronic apparatus 20 may be the unmanned photographing device 101, the server 103, or the terminal device 104 in fig. 1. The electronic device 20 includes a processing apparatus 200, a storage unit 210, and a communication interface unit 220. The processing device 200 may be a microprocessor or an application-specific integrated circuit (ASIC). The storage unit 210 may be any data storage device for storing a program code 214, and the program code 214 is read and executed by the processing device 200. For example, the storage unit 210 may be a Subscriber Identity Module (SIM), a read-only memory (ROM), a flash memory (flash memory), a random-access memory (RAM), a compact disc read-only memory (CD-ROM/DVD-ROM), a magnetic tape (magnetic tape), a hard disk (hard disk), an optical data storage device (optical data storage device), and the like, but is not limited thereto. The communication interface unit 220 may be a wireless transceiver, which exchanges wireless signals according to the processing result of the processing device 200.

FIG. 4 is a flow chart of a process 40 according to an embodiment of the present invention. The process 40 may be used in the unmanned camera device 101 of fig. 1 for collecting motion data. The process 40 can be compiled into the program code 214, stored in the storage unit 210, and processed by the processing device 200. The process 40 comprises the following steps:

step 400, start.

And step 410, judging whether to shoot the movement of the athlete in a tracking shooting mode or a surrounding shooting mode according to the moving speed of the athlete.

Step 420, wirelessly transmitting the motion picture to the server 103 or the terminal device 104.

And step 430, ending.

According to the process 40, the unmanned photographing device 101 autonomously decides to photograph the motion of the athlete using the tracking photographing mode or the surround photographing mode. Specifically, the unmanned photographing device 101 determines a photographing mode according to the movement speed of the athlete, and collects movement data of the athlete.

By using a visual tracking algorithm (e.g., a kernel correlation filter or tracking learning detection), the unmanned camera 101 can ensure that the teleoperator is always kept at the center of the shooting field of view, so that the motion data of the teleoperator can be captured during the whole motion process. To achieve this, the user needs to manually control the interface of the terminal device 104 so that the unmanned photographing device 101 obtains a default relative position between the athlete and the unmanned photographing device 101. Further, the unmanned photographing device 101 calculates the offset amount based on the default relative position and the real-time relative position (calculated from the height and angle of the camera of the unmanned photographing device 101), so that the unmanned photographing device 101 can adjust the position and angle of the camera based on the offset amount, and the unmanned photographing device 101 can maintain the photographing position of the athlete at the default relative position regardless of the tracking photographing mode or the surrounding photographing mode.

In one embodiment, the unmanned camera 101 may be a blank camera for capturing a player's performance on a playing field, such as a soccer, basketball, or ski game. In another embodiment, the unmanned camera device 101 may be an unmanned boat for capturing the athlete's performance of the sport under the water, such as diving or swimming.

Fig. 5 is a schematic diagram illustrating a photographing operation of the unmanned photographing device 101 according to the embodiment of the invention. In detail, the unmanned photographing device 101 selects a target (i.e., a sportsman) to perform photographing of a motion picture (step 501). In addition, the unmanned photographing device 101 detects the moving speed V of the athlete (step 502). In this embodiment, the moving speed V is calculated from the position coordinates of the player in two adjacent frames of the movie. After obtaining the moving speed V, the unmanned photographing device 101 determines whether the moving speed V is greater than a default threshold value T (step 503). If the moving speed V is greater than the default threshold T (e.g., the athlete is in a fast moving state), the unmanned photographing device 101 determines to photograph the athlete using the tracking photographing mode (step 504). On the other hand, if the moving speed V is less than the default threshold value T (e.g., the athlete is in a stopped state), the unmanned photographing device 101 determines to photograph the athlete using the surround photographing mode (step 505)

FIG. 6 is a flow chart of a process 60 according to an embodiment of the present invention. The process 60 may be applied to the server 103 or the terminal device 104 in fig. 1 for data analysis. The process 60 can be compiled into the program code 214, stored in the storage unit 210, and processed by the processing device 200. The process 60 comprises the following steps:

and step 600, starting.

Step 610, establish a motion training database including a plurality of motion parameters corresponding to a plurality of standard motions in at least one motion.

In step 620, a motion picture is wirelessly received from the unmanned camera device 101.

A key frame is selected 630 from the received motion picture.

In step 640, an action feature is extracted from the key frame.

Step 650, performing a matching operation on the motion characteristic according to a standard motion of the plurality of standard motions in the exercise training database.

And step 660, ending.

According to the process 60, the server 103 or the terminal device 104 stores an offline exercise training database for performing matching calculation on the player's motion. It should be noted that the motion characteristics are extracted from only the key frames in the motion picture, so as to reduce the amount of data for performing the matching operation, thereby improving the data analysis efficiency of the server 103 or the terminal device 104.

Fig. 7 is a schematic diagram illustrating a data analysis operation of a server 103 or a terminal device 104 according to an embodiment of the present invention. Server 103 or terminal device 104 selects a key frame (step 701). In detail, the server 103 or the terminal device 104 calculates the amount of change between the current frame and the previous frame in the movie. When the variation is larger than the predetermined threshold, the server 103 or the terminal device 104 determines that the current frame is the key frame. The variation may be calculated directly based on the change in the gray scale map or indirectly based on the change in the characteristic. Next, the server 103 or the terminal device 104 extracts the motion feature X from the key frame (step 702). In order to perform the matching calculation, the server 103 or the terminal device 104 needs to determine a corresponding standard operation in the exercise training database. In brief, the server 103 or the terminal device 104 classifies the captured motion feature X into one of the motions 1-N by comparing the similarity between the motion feature X and a plurality of standard motions in the exercise training database (step 703). The server 103 or the terminal device 104 then scores the retrieved action characteristics (step 704). The scoring result may be a scoring level a-D, which is a degree of similarity between the action feature X and the corresponding standard action for the server 103 or the terminal device 104 to score. Therefore, each selected key frame will get a scoring result, and then the server 103 or the terminal device 104 will generate a motion analysis report according to the scoring result.

Fig. 8-12 are schematic diagrams illustrating a display operation of a terminal device 104 according to an embodiment of the invention. As shown in FIG. 8, the screen of the terminal device 104 displays the operation of selecting a training game (step 1), wherein the screen display includes a title window 81, a list window 82, a video window 83, a bottom window 84, and buttons B1-B2. Button B1 is for a return to previous page command. The title window 81 displays the text "select training sport". The list window 82 displays pre-stored movements or movements established in the sports training database and may be displayed through a plurality of sub-windows (i.e., the video window 83). For example, each image window 83 displays a model of the training motion. In addition, the image window 83 further includes a check box for indicating whether the corresponding exercise motion is selected. Button B2 is an instruction for confirming a selection (e.g., a training exercise confirming a selection).

As shown in FIG. 9, the screen of the terminal device 104 displays the training exercises to be compared (step 2), wherein the screen display includes a title window 91, a list window 92, a video window 93, a bottom window 94, and buttons B1-B2. The title window 91 displays the text "select action". The list window 92 displays the standard motion in the selected motion in the motion training database and is displayed through a plurality of sub-windows (i.e., video window 93). For example, each shadow window 93 displays a model of a standard motion. In addition, the video window 93 further includes a check box for indicating whether the corresponding standard action is selected. Button B2 is an instruction for confirming a selection (e.g., a standard action for confirming a selection).

As shown in FIG. 10, the screen display of the terminal device 104 is prepared (step 3), wherein the screen display includes video windows 1-3 and buttons B1, B3. The image window 1 displays a live image of the athlete. The video window 2 displays a representative representation of the athlete or user, such as the representative representation of the standard action selected in step 2 above. The video window 3 shows a loading state indicating that the unmanned camera 101 is searching for an athlete. When the drone 101 completes the search, the video window 3 fades away and button B3 is displayed on the screen, wherein button B3 is directed to the next step.

As shown in FIG. 11, the data analysis operation of the terminal device 104 is performed on the screen (step 4), wherein the screen includes the video windows 1-7, the buttons B1, B4 and the widget W1. Button B4 is a command for data storage. The image window 5 displays the motion characteristics X collected by the unmanned photographing device 101, wherein the number of the image windows 5 is not limited to the number shown in fig. 11. In addition, the corresponding motion characteristic X may include an angle, a velocity, an angular velocity, and the like. The outer frame of the image window 5 may indicate the scoring results by different colors, such as the above-mentioned scoring levels A-D, wherein each scoring level is mapped to a specific color for the user to immediately know the performance of the athlete. The image window 6 displays key features of the standard motion in the exercise training database. The image window 7 displays the variation between the motion feature X and the key feature in the standard motion, wherein the variation can be displayed through text, but is not limited thereto. The widget W1 may include media playback functionality for controlling the playback of the video window 1-2.

As shown in fig. 12, the screen of the terminal device 104 displays the analysis result operation (step 5), wherein the screen display includes the image window 121-122 and the button B5. The image window 121 displays the analysis result of step 4 in text mode. The image window 122 can display the analysis result through another image window 122a-122 b. For example, the upper left of the image window 122a displays the image window 5 in fig. 11, and the upper right displays the image window 6 in fig. 11. In addition, the widget W1 in fig. 11 is disposed at the lower left of the video window 122a, and the similarity degree result/matching operation result is disposed at the lower right of the video window 122 a. The left side of the image window 122b displays the keyframes of the motion picture, and the right side displays the similarity results/matching operation results. Button B5 is a command for a dialog box to display text to save or close the screen.

All steps described above, including the steps/operations suggested, may be implemented by hardware, firmware (i.e., a combination of hardware devices and computer instructions, where data in the hardware devices is read-only software data), or electronic systems. The hardware may include analog, digital, and hybrid circuits (i.e., microcircuits, microchips, or silicon chips). The electronic system may include a System On Chip (SOC), a system in package (Sip), a Computer On Module (COM), and the electronic device 20.

In summary, the present invention provides an unmanned photographing apparatus capable of collecting motion data by determining whether to use a tracking photographing mode or a surround photographing mode, so as to obtain effective motion data and perform motion analysis of an athlete. In addition, the invention provides a sports data analysis method capable of reducing the calculation amount of the sports data, and a server can generate a sports analysis report and output the sports analysis report to a terminal device, so that a user can watch the performance of the athlete, and the training of the athlete is further assisted.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing motion data for an unmanned camera device in a motion analysis system, the method comprising:

shooting a motion of an athlete; and

wirelessly transmitting the motion picture to an electronic device in the motion analysis system for analyzing data in the motion picture to generate a motion analysis report.

2. The method of claim 1, wherein the step of capturing the motion of the athlete comprises:

according to a moving speed of the athlete, judging whether to shoot the movement of the athlete through a tracking shooting mode or a surrounding shooting mode.

3. The method of claim 2, wherein the method further comprises:

calculating the moving speed of the athlete in two adjacent frames of the motion picture according to a position coordinate corresponding to the athlete shot in the unmanned shooting device;

wherein, according to the moving speed of the athlete, the step of determining whether to shoot the motion of the athlete through the tracking shooting mode or the surrounding shooting mode comprises:

when the moving speed of the athlete is larger than a default threshold value, shooting the movement of the athlete by the tracking shooting mode; and

when the moving speed of the athlete is less than the default threshold value, the motion of the athlete is shot through the surround shooting mode.

4. The method of claim 2, wherein the method further comprises:

obtaining a default relative position between the athlete and the unmanned photographing device through the electronic equipment;

calculating an offset according to the default relative position and a real-time relative position calculated by a height and an angle of a camera of the unmanned photographing device; and

according to the offset, the position and the angle of the camera are adjusted, so that the motion position of the shot athlete can be maintained at the default relative position in the tracking shooting mode or the surrounding shooting mode.

5. The method of claim 1, wherein the method further comprises:

and wirelessly transmitting the motion film to a terminal device in the motion analysis system for playing the motion of the athlete in real time.

6. A method for analyzing motion data for an electronic device in a motion analysis system, the method comprising:

establishing a sports training database containing a plurality of motion parameters corresponding to a plurality of standard motions in at least one sport;

wirelessly receiving a motion picture from a unmanned camera device in the motion analysis system;

selecting a key frame from the received motion picture;

extracting an action feature from the key frame; and

and performing a matching operation on the motion characteristic according to one of the plurality of standard motions in the exercise training database.

7. The method of claim 6 wherein the step of selecting the key frame from the received motion picture comprises:

calculating a variation according to a current frame and a previous frame in the motion picture; and

when the variation is larger than a preset threshold, the current frame is judged as the key frame.

8. The method of claim 6, wherein the step of performing the matching operation on the motion feature according to the standard motion of the plurality of standard motions in the exercise training database comprises:

determining the standard action by comparing the action characteristics with the similarity degree between the plurality of standard actions in the exercise training database; and

and performing the matching operation on the action characteristic according to the determined standard action to generate a matching result.

9. The method of claim 8, wherein the method further comprises:

calculating the score of the action characteristic according to the matching result; and

generating a motion analysis report, wherein the motion analysis report comprises at least a scoring result related to the motion characteristic, a plurality of parameters related to the motion characteristic, and a plurality of parameters corresponding to the standard motion.

10. The method of claim 9, wherein the method further comprises:

displaying the exercise analysis report to a user for viewing; or

Transmitting the motion analysis report to a terminal device in the motion analysis system to display the motion analysis report for the user to view.

11. An unmanned photography device for motion analysis for analyzing motion data, the unmanned photography device comprising:

a storage unit for storing a program code related to a process; and

a processing unit, coupled to the storage unit, for processing the program code to execute the process;

wherein, the process comprises:

shooting a motion of an athlete; and

the motion picture is wirelessly transmitted to an electronic device for analyzing data in the motion picture to generate a motion analysis report.

12. The device of claim 11, wherein the process further comprises:

according to a moving speed of the athlete, judging whether a tracking shooting mode or a surrounding shooting mode is used for shooting the movement of the athlete.

13. The device of claim 12, wherein the process further comprises:

14. The device of claim 12, wherein the process further comprises:

15. An electronic device for motion analysis for analyzing motion data, the electronic device comprising: one or more processors; and the number of the first and second groups,

a memory; wherein,

the memory stores instructions executable by the one or more processors, the instructions being arranged to perform:

wirelessly receiving a motion picture from a unmanned photographing device;

selecting a key frame from the received motion picture;

extracting an action feature from the key frame; and

16. The electronic device of claim 15, wherein the process further comprises:

17. The electronic device of claim 15, wherein the process further comprises:

18. The electronic device of claim 17, wherein the process further comprises:

19. The electronic device of claim 18, wherein the process further comprises:

displaying the exercise analysis report to a user for viewing; or

Transmitting the motion analysis report to a terminal device to display the motion analysis report to the user for viewing.