Method for using dynamic trajectory analysis system for exerciser

Abstract

The method for using a dynamic trajectory analysis system for an exerciser uses technologies such as computer vision, edge artificial intelligence (AI), machine learning, and human factors engineering, in conjunction with a smart mobile communication device to perform the following: automatically capturing and recording images of posture of the exerciser during the exercise process; and further analyzing a sport event, sport behavior, and sport equipment in the images, and then obtaining a key information for providing assistance in optimizing the exercise process. The method uses edge AI models to achieve real-time prediction of objective physical performance of objects such as a human body, sport equipment, and a ball in a real environment. A prediction result is presented in a data format and visualized manner, providing a user with a real-time feedback and analysis information.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present disclosure claims priority to a Taiwan Patent Application No. 113121129 filed on Jun. 6, 2024, the disclosures of which are incorporated in their entirety by reference herein.BACKGROUND OF THE DISCLOSUREField of the Disclosure

[0002] The present disclosure particularly relates to a method for using a dynamic trajectory analysis system for an exerciser, wherein the method is capable of real-time recording and analysis of dynamic trajectories.Brief Description of Related Art

[0003] In daily human life, whether for health, interests, or even profession, “exercise” plays a significant role. Ball sports, in particular, are highly popular and beloved by many. In most ball sports, an exerciser needs to invest physical strength, posture, and skills. For a professional athlete, optimizing these aspects typically involves assistance from a professional coach. However, for an average individual without professional information support and professional coaching, he / she can only rely on self-observation and adjustment during an exercise process to further optimize, for example, his / her posture and skills. This process is not only slow but also lacks scientific and data-driven basis, often leading to poor progress and diminished willingness to continue exercising for the individual exerciser. Moreover, improper adjustment can potentially cause physical injury to the exerciser. Accordingly, there are currently assistance tools and applications (APPs) available on the market that can assist the individual exerciser in optimizing his / her exercise process. For example, a baseball batting cage provides image shooting to record striking posture of a batter. For another example, a golf driving range offers a ball striking tracker that shoots swing posture of a golfer, and records direction and distance of a ball after it is struck. This information further serves as a reference for the golfer to adjust his / her striking posture. Following the above description, related detection application systems also exist. For example, Republic of China Patent No. TWI782649B, titled “Badminton Smash Measurement System and Method” discloses a system and method for measuring changes in direction and speed of a shuttlecock during a smash by a player playing badminton, providing a reference for the player to optimize his / her technique. For example, U.S. Pat. No. 11,638,853B2, titled “Augmented Cognition Methods And Apparatus For Contemporaneous Feedback In Psychomotor Learning” discloses a method for extracting a dynamic jointed skeleton model during an exercise process of an exerciser to create a scalable reference model for using in training. However, the various types of related application systems currently available on the market are all developed for professional athletes. These systems are costly and have limited widespread use. The key lies in wide variety of sports. Construction of various sport detection systems and devices combined in related applications are expensive. Additionally, data, results, and adjustment recommendations produced by these systems require further assistance from professional coaches, making these systems impractical for individual users. Accordingly, how to promote widespread adoption of this type of sport assistance system to further enhance human physical and mental health development is a pressing problem that needs to be solved at this stage.SUMMARY OF THE DISCLOSURE

[0004] In view of the aforementioned problem, a main object of the present disclosure is to provide a method for using a dynamic trajectory analysis system for an exerciser which is convenient and easy to operate, capable of recording dynamic posture during an exercise process, and able to quickly and in real-time generate an analysis result and a feedback information.

[0005] In order to achieve the aforementioned object, the method for using the dynamic trajectory analysis system for the exerciser in the present disclosure mainly uses integrated technologies such as computer vision, edge artificial intelligence (AI), machine learning, and human factors engineering, in conjunction with a smart mobile communication device to perform the following: automatically capturing and recording images of posture of the exerciser during the exercise process; and analyzing a sport event, sport behavior, and sport equipment in the images, and then obtaining a key information for providing assistance in optimizing the exercise process. The method uses edge AI models or cloud AI models to achieve real-time prediction of objective physical performance of objects such as a human body, sport equipment, and a ball in a real environment. A prediction result is presented in a data format and visualized manner, providing a user with a real-time feedback and analysis information.BRIEF DESCRIPTION OF THE DRAWINGS

[0006] FIG. 1 is a schematic diagram of a system architecture according to the present disclosure.

[0007] FIG. 2 is a schematic flowchart of execution of a method according to the present disclosure.

[0008] FIG. 3 is a schematic diagram of execution (1) according to the present disclosure.

[0009] FIG. 4 is a schematic diagram of execution (2) according to the present disclosure.

[0010] FIG. 5 is a diagram of another preferred embodiment (1) according to the present disclosure.

[0011] FIG. 6 is a schematic flowchart of execution of the preferred embodiment (1).

[0012] FIG. 7 is a diagram of another preferred embodiment (2) according to the present disclosure.

[0013] FIG. 8 is a schematic flowchart of execution of the preferred embodiment (2).

[0014] FIG. 9 is a schematic diagram of an execution result of the preferred embodiment (2).

[0015] FIG. 10 is a diagram of another preferred embodiment (3) according to the present disclosure.

[0016] FIG. 11 is a schematic diagram of execution of the preferred embodiment (3).

[0017] FIG. 12 is a diagram of another preferred embodiment (4) according to the present disclosure.DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

[0018] Referring to FIG. 1, in the present disclosure, a dynamic trajectory analysis system 1 for an exerciser mainly has a smart mobile communication device 10 which has a central processing unit (CPU) 11, and an image capturing module 12, an image recognition module 13, an image analysis module 14, an event database 15, and a model database 16 informationally connected to the CPU 11. The smart mobile communication device 10 is installed with an application (APP) 2 that drives execution of the method described in the present disclosure. During execution, the present disclosure uses edge artificial intelligence (AI) models to achieve real-time prediction of objective physical performance of objects such as a human body, sport equipment, and a ball in a real environment. A prediction result is presented in a data format and visualized manner, providing a user with a real-time feedback and analysis information. Components are as follows:

[0019] (1) The CPU 11 refers to a CPU with computing capabilities. The CPU 11 may also be or further operate in conjunction with a graphics processing unit (GPU).

[0020] (2) The image capturing module 12 is, for example, a camera lens.

[0021] (3) The image recognition module 13 can be an algorithm or an integrated circuit module in which an algorithm is written. When the algorithm is executed in conjunction with a model database 16, comparison is performed on the dynamic image data according to at least one predetermined feature. Upon computation, the comparison causes recognition to be performed on images in the content of the dynamic image data to, for example, recognize a human, an object, and an action in the images. In the present disclosure, the image recognition module 13 in conjunction with one or more machine learning models stored in the model database 16 (such as a sport type model 161, a sport behavior model 162, a ball equipment model 163, but not limited thereto), performs sport event recognition, sport behavior recognition, and sport equipment recognition on the dynamic image data.

[0022] (4) The image analysis module 14 can be an algorithm or an integrated circuit module in which an algorithm is written. The algorithm is executed in conjunction with one or more machine learning models stored in the model database 16. Upon computation, the algorithm causes behavioral feature analysis to be performed on the content of the dynamic image data. For example, body rotation, swing direction, and swing angles during a swinging process of a baseball batter are analyzed.

[0023] (5) The event database 15 can be a hard disk drive (HDD), a solid-state disk (SSD) or a virtual memory for storing digital data. In the present disclosure, the event database 15 is mainly used to store a video file recorded during an exercise process of the exerciser, and various sport informations, parameters, analysis results, etc., obtained upon analysis.

[0024] (6) The model database 16 is mainly used in conjunction with the image recognition module 13 and the image analysis module 14. The model database 16 stores at least one machine learning model. In an embodiment of the present disclosure, the model database 16 stores at least a sport type model 161, a sport behavior model 162, and a ball equipment model 163. In addition, the model database 16 can store various other machine learning models related to sports.

[0025] Following the above description, the smart mobile communication device 10 can be, for example, a smart phone or a tablet computer that is convenient for the user to carry. The smart mobile communication device 10 has at least one image capturing module 12 that can capture and record images. In addition, the smart mobile communication device 10 is installed with an application (APP) 2 that drives execution of the method described in the present disclosure. Upon execution, the APP 2 can, for example, be used to drive the image capturing module 12 to capture, shoot, and record images. In an embodiment, the smart mobile communication device 10 can be connected to a remote server via information or communication to transmit the shot images to the remote server for storage or additional cloud computing. The remote server can perform recognition and analysis on the images and store the images. Furthermore, in one embodiment, the smart mobile communication device 10 can also be a customized information device that is compact, portable, and equipped with computing, program execution, and communication transmission capabilities. For example, the smart mobile communication device 10 can be an information device capable of executing the dynamic trajectory analysis system 1 for the exerciser as described in the present disclosure.

[0026] Referring to FIGS. 2 and 3, when a user wants to execute the dynamic trajectory analysis system 1 for the exerciser in the present disclosure, he / she can first set up the smart mobile communication device 10 at a specific location P1 relative to an exerciser P (in this embodiment, a right-handed baseball batter). This specific location P1 allows the image capturing module 12 to shoot an entire action process using a focal distance and range of the image capturing module 12. Upon completion of setting up the smart mobile communication device 10, the user can then activate the smart mobile communication device 10 and run APP 2 to start executing the dynamic trajectory analysis system 1 for the exerciser in the present disclosure. Additionally, the method S for using the dynamic trajectory analysis system for the exerciser is as follows:

[0027] (1) An image capture initiation operation S1: The image capturing module 12 is activated to perform image capture on a physical body of the exerciser P. This involves recording (i.e., image capture) a process of the exerciser P from preparation to completion of striking to obtain dynamic image data V1.

[0028] (2) An image recognition operation S2: Following the above description, the image recognition module 13 performs recognition on content of the dynamic image data V1. In the present disclosure, the image recognition module 13, in conjunction with a first model M1, performs “sport event recognition” S21 to recognize what type of sport is depicted in the content of the dynamic image data V1, and upon completion of the “sport event recognition” S21, generate a “sport event type” A, such as baseball or golf. In the present disclosure, an example of “baseball batting” is used for illustration. As mentioned above, the first model M1 refers to the sport type model 161 in FIG. 1. In the present disclosure, the first model M1 is a machine learning model for sport event recognition, which integrates key knowledge of specific sports and is trained with over ten thousand independent sports events. During the “sport event recognition” S21, the first model M1 can automatically determine a type and sequence of a sport event. The image recognition module 13, in conjunction with a second model M2, performs “sport behavior recognition” S22 and “sport equipment recognition” S23 to recognize sport behavior (e.g., batting) and sport equipment (e.g., a bat) in the content of the dynamic image data V1, and upon completion of “sport behavior recognition” S22 and “sport equipment recognition” S23, generate “raw data” B. Moreover, the second model M2 refers to the sport behavior model 162 or the ball equipment model 163 in FIG. 2. The second model M2 employs a machine vision algorithm. Through analysis of over ten thousand independent sports events and sports-specific knowledge, the second model M2 can perform processing tasks such as synchronous recognition of objects such as a human body, sport equipment, and a ball, noise elimination, and behavioral feature determination at the same time, and generate the raw data B. Following the above description, the image recognition module 13 further generates an “event to be analyzed” S24 by combining the “sport event type” A and the “raw data” B. Furthermore, during this operation, based on the “sport event type” A, feedback such as “adjustment of shooting parameters” can be provided upon computation to achieve a better shooting effect.

[0029] (3) A behavioral feature data analysis operation S3: Following the above description, the image analysis module 14, in conjunction with a third model M3, subsequently further performs behavioral feature data analysis on the “event to be analyzed” S24. The third model M3 is a highly efficient machine learning model established through analysis of over ten thousand independent sports events and sports-specific knowledge, employing a machine vision algorithm. Referring also to FIG. 4, in this operation, the image analysis module 14 further analyzes the raw data of single-perspective images of the dynamic image data V1 to obtain behavioral feature data C, which includes, for example, rotation of human body posture, action angles, and objects such as the sport equipment, and the ball.

[0030] (4) A physical performance prediction operation S4: Following the above description, the image analysis module 14, in conjunction with the third model M3, further predicts objective physical performance of objects such as a human body, sport equipment, and a ball in a real environment based on the behavioral feature data C.

[0031] (5) A “reading interface S5” generation operation: Following the above description, the image analysis module 14 generates a reading interface S5 that arranges a prediction result in a data format and visualized manner and is presented on the smart mobile communication device 10, providing a user with a real-time feedback and analysis information. Preferably, the reading interface S5 can be, for example, any one of the following or a combination thereof: a data list, a statistical chart list, or a dashboard-style list. The reading interface S5 can also be presented by a computer device after being transmitted.

[0032] (6) As described above, the present disclosure mainly involves using the smart mobile communication device 10, set up at the appropriate location, to shoot the exercise process of the exerciser, thereby obtaining the dynamic image data V1. Then, the smart mobile communication device 10, in conjunction with the various machine learning models (edge AI) stored in the model database 16 on the device end, such as the sport type model 161, the sport behavior model 162, and the ball equipment model 163 in the embodiment of the present disclosure, performs edge computing to generate multiple key informations and data informations in real-time. Under a condition of using the smart mobile communication device 10 with high-end hardware specifications, real-time information feedback can be obtained. Furthermore, based on this, the system can further predict the objective physical performance of the objects such as the human body, the sport equipment and the ball in the real environment, providing the exerciser with optimization references. Additionally, the smart mobile communication device 10 can perform edge computing in conjunction with the built-in various machine learning models (edge AI). Alternatively, the smart mobile communication device 10 can further collaborate with a remote server and transmits the dynamic image data V1 to the remote server for additional cloud computing.

[0033] Referring to FIG. 5, the smart mobile communication device 10 further has a deep analysis module 17 and a sports-specific knowledge database 18, both informationally connected to the CPU 11. The sports-specific knowledge database 18 stores a large amount of specific knowledge for various types of sports, such as optimal posture, ball striking posture, and applicable ball equipment specifications corresponding to specific types of sports. But the present disclosure is not limited thereto.

[0034] Following the above description, referring to FIG. 6, the deep analysis module 17, in conjunction with the sports-specific knowledge database 18, performs a deep analysis operation S6 on the dynamic image data V1 in the event to be analyzed S24 after the image recognition operation S2. After the analysis is completed, a “key information extraction” operation S61 is performed to extract at least one key information D from the event to be analyzed S24. The key information D can be, for example, an action technique or sport performance. Furthermore, the deep analysis module 17 can extract a corresponding key information based on each different specific sport to provide a more targeted analysis result for the exerciser. For example, if the sport event type A of the event to be analyzed S24 is “baseball”, the key information D can be, for example, swing and striking posture, a swing angle, or a bat grip. Additionally, through the deep analysis operation S6 and use of a machine vision algorithm, images in the dynamic image data V1 can be analyzed, and a high-quality sport segment can be automatically extracted. The segment is precisely extracted based on a key movement or moment within the sport event, preserving the most valuable images for analysis.

[0035] Referring to FIG. 7, the smart mobile communication device 10 further has a time sorting module 19, which is informationally connected to the CPU 11. Referring also to FIG. 8, the time sorting module 19 performs an automatic time sorting operation S7 after the image recognition operation S2. The automatic time sorting operation S7 mainly arranges video segments of dynamic image data V1 in one or more events to be analyzed S24 in chronological order to generate a complete and smooth “training process record” S71 which the exerciser can replay and review later. Referring also to FIG. 9, time sorting for presentation of the generated “training process record” S71 can be further refined according to informations such as the sport event type, and rules, to present a training process that better meets needs of sport science.

[0036] Referring to FIG. 10, the smart mobile communication device 10 is further installed with an augmented reality (AR) APP 3. Using combined AR technology, the smart mobile communication device 10 intuitively presents a data information in the dynamic image data V1 in an AR manner to the user. Referring also to FIG. 11, the aforementioned data information can be, for example, a trajectory of a postural change of the exerciser P during exercise, a trajectory of ball striking posture, or a trajectory of a moving ball. In the present embodiment, movement trajectories of human joints, performance of the sport equipment, etc., can be visualized, assisting the exerciser P in analyzing the action technique and the sport performance and key comments can be recorded in text. Referring also to FIG. 2, in the present disclosure, the AR APP 3 can be further combined with a built-in sensor of the smart mobile communication device 10, such as a G-sensor, an accelerometer sensor, or a gyroscope. When the user sets up the smart mobile communication device 10, the AR APP 3 combined with the sensor can provide a visual prompt through an AR image to assist the user in adjusting parameters such as an angle and a distance of the smart mobile communication device 10 until the AR image meets requirements. This achieves a goal of excellently guiding the user to place the smart mobile communication device 10 in an optimal shooting position, ensuring that the shot images are clear and complete.

[0037] Referring to FIG. 12, the smart mobile communication device 10 can be further informationally connected to one or more social platforms 4. Accordingly, the user can organize, and output or publicly share content such as a high-quality sport event video (the dynamic image data), the key information of the sport event, and visualized AR data (the data information), to the one or more social platforms 4. Further, through connection and application of the one or more social platforms 4, the user can interact with an online peer or coach by sharing the visualized movement trajectories of human joints, performance of the sport equipment, etc., analysis of the action technique, the sport performance, and the key comments recorded in text.

[0038] In summary, a method for using a dynamic trajectory analysis system for an exerciser in the present disclosure mainly uses technologies such as computer vision, edge AI, machine learning, and human factors engineering, in conjunction with a smart mobile communication device to perform the following: automatically capturing and recording images of posture of the exerciser during an exercise process; and further analyzing a sport event, sport behavior, and sport equipment in the images, and then obtaining a key information for providing assistance in optimizing the exercise process. The method uses edge AI models to achieve real-time prediction of objective physical performance of objects such as a human body, sport equipment, and a ball in a real environment. A prediction result is presented in a data format and visualized manner, providing a user with a real-time feedback and analysis information. Accordingly, the present disclosure, upon implementation, can indeed achieve an object of providing the method for using the dynamic trajectory analysis system for the exerciser which is convenient and easy to operate, capable of recording dynamic posture during the exercise process, and able to quickly and in real-time generate an analysis result and a feedback information.

[0039] The above is only the preferred embodiments of the present disclosure, and is not intended to limit the present disclosure to the forms disclosed. Any modifications, equivalent alternatives, and improvements made within the spirit and the scope of present disclosure by persons skilled in the art should be included in the scope of claims of the present disclosure.REFERENCE NUMERALS IN DRAWINGS1 a dynamic trajectory analysis system for an exerciser

[0041] 10 a smart mobile communication device

[0042] 11 a CPU

[0043] 12 an image capturing module

[0044] 13 an image recognition module

[0045] 14 an image analysis module

[0046] 15 an event database

[0047] 16 a model database

[0048] 161 a sport type model

[0049] 162 a sport behavior model

[0050] 163 a ball equipment model

[0051] 17 a deep analysis module

[0052] 18 a sports-specific knowledge database

[0053] 19 a time sorting module

[0054] 2 APP

[0055] 3 AR APP

[0056] 4 one or more social platforms

[0057] A a sport event type

[0058] B raw data

[0059] C behavioral feature data

[0060] D a key information

[0061] P the exerciser

[0062] P1 a specific location

[0063] V1 dynamic image data

[0064] S a method for using the dynamic trajectory analysis system for the exerciser

[0065] S1 an image capture initiation operation

[0066] S2 an image recognition operation

[0067] S21 sport event recognition

[0068] S22 sport behavior recognition

[0069] S23 sport equipment recognition

[0070] S24 an event to be analyzed

[0071] S3 a behavioral feature data analysis operation

[0072] S4 a physical performance prediction operation

[0073] S5 a reading interface

[0074] S6 a deep analysis operation

[0075] S6 key information extraction operation

[0076] S7 an automatic time sorting operation

[0077] S7 a training process record

[0078] M1 a first model

[0079] M2 a second model

[0080] M3 a third model

Claims

1. A method for using a dynamic trajectory analysis system for an exerciser, wherein after an image capturing module of a smart mobile communication device is activated, the smart mobile communication device performs image recording on a physical body of the exerciser to obtain dynamic image data, and performs real-time edge computing, comprising:an image recognition operation for performing, by an image recognition module in conjunction with a first model, sport event recognition on content of the dynamic image data and generating a sport event type upon completion of the sport event recognition, performing, by the image recognition module in conjunction with a second model, sport behavior recognition and sport equipment recognition on the dynamic image data to recognize sport behavior and sport equipment in the dynamic image data, and generating raw data upon completion of the sport behavior recognition and the sport equipment recognition, and generating an event to be analyzed by combining the sport event type and the raw data;a behavioral feature data analysis operation for performing, by an image analysis module in conjunction with a third model, behavioral feature data analysis on the event to be analyzed and generating behavioral feature data; anda physical performance prediction operation for predicting, by the image analysis module in conjunction with the third model, objective physical performance of a human body, sport equipment, and a ball in a real environment based on the behavioral feature data.

2. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein after the physical performance prediction operation is completed, a reading interface generation operation is subsequently performed, wherein the reading interface generation operation is for generating a reading interface that arranges the behavioral feature data and the objective physical performance in a data format and visualized manner, and is outputted and presented on the smart mobile communication device.

3. The method for using the dynamic trajectory analysis system for the exerciser of claim 2, wherein the reading interface is any one of the following or a combination thereof: a data list, a statistical chart list, or a dashboard-style list.

4. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein after the image recognition operation, a deep analysis operation is performed on the dynamic image data in the event to be analyzed by a deep analysis module of the smart mobile communication device in conjunction with a sports-specific knowledge database, wherein the deep analysis operation is for extracting a key information from the event to be analyzed, and the key information is any one of the following or a combination thereof: an action technique or sport performance.

5. The method for using the dynamic trajectory analysis system for the exerciser of claim 4, wherein through the deep analysis operation in conjunction with a machine vision algorithm, images in the dynamic image data are analyzed, and a precise segment is extracted based on a key movement or moment in the dynamic image data.

6. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein after the image recognition operation, an automatic time sorting operation is performed on segments of the dynamic image data in the event to be analyzed by a time sorting module of the smart mobile communication device, wherein the automatic time sorting operation is for arranging the segments of the dynamic image data in chronological order and generating a training process record.

7. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein a data information in the dynamic image data is presented in an augmented reality (AR) manner by an AR application (APP) installed on the smart mobile communication device, wherein the data information is any one of the following or a combination thereof: a trajectory of a postural change of the exerciser during exercise, a trajectory of ball striking posture, or a trajectory of a moving ball.

8. The method for using the dynamic trajectory analysis system for the exerciser of claim 7, wherein through an AR image, a visual prompt is provided by the AR APP combined with a built-in sensor of the smart mobile communication device to assist in adjusting an angle and a distance of the smart mobile communication device.

9. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein the smart mobile communication device is informationally connected to one or more social platforms to output or publicly share the dynamic image data, a key information, and a data information to the one or more social platforms.

10. The method for using the dynamic trajectory analysis system for the exerciser of claim 1, wherein the smart mobile communication device further collaborates with a remote server and transmits the dynamic image data to the remote server for cloud computing.

Images