Method and apparatus for monitoring athletic facility using image recognition and artificial intelligence
The integration of image recognition and AI in the sports facility monitoring system addresses the challenge of detecting and responding to dangerous situations, ensuring user safety and efficient facility management by providing real-time alerts and prioritization of risk events.
Patent Information
- Application Number
- PCT/KR2024/014938
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-11-01
- Filing Date
- 2024-10-02
- Publication Date
- 2025-05-08
AI Technical Summary
Existing sports facilities face challenges in quickly recognizing and responding to dangerous situations, such as injuries from heavy exercise equipment, due to limitations in monitoring and alert systems.
A system utilizing image recognition and artificial intelligence to monitor sports facilities in real-time, detecting dangerous events by analyzing images of users and exercise equipment, and transmitting alerts to managers for timely intervention.
The system enables rapid identification and response to potential hazards, enhancing user safety and efficient operation of sports facilities by providing prioritized alerts and enabling effective management of risk events.
Smart Images

Figure KR2024014938_08052025_PF_FP_ABST
Abstract
Description
Method and device for monitoring sports facilities using image recognition and artificial intelligence
[0001] The present invention relates to a system for monitoring sports facilities using image recognition and artificial intelligence. Specifically, the invention relates to a system that monitors users of sports facilities in real time for abnormal or dangerous situations and promptly takes necessary measures, thereby ensuring the safety of users and facilitating the smooth operation of the facility.
[0002] In general, the number of people who want to take care of their health through home training rather than specialized exercise facilities such as gyms, training centers, and sports centers has been increasing recently. Accordingly, various home training equipment is being manufactured and sold, expanding the choices for consumers who want to exercise appropriately.
[0003] Additionally, although primarily intended for rehabilitation exercise, training equipment for people with congenital or acquired disabilities is also manufactured and sold, so it can be used for home training by people with disabilities who have a higher desire to exercise at home than non-disabled people.
[0004] However, in gyms, various pieces of exercise equipment can pose a threat to consumers seeking to exercise. For example, heavy dumbbells or barbells can easily cause injuries to consumers due to their weight if not handled properly. While dangerous situations often arise in gyms, the ability to respond to or prevent them is limited. Therefore, technologies that can quickly recognize and respond to these dangerous situations are emerging.
[0005] Recently, technologies related to smart cities and smart gym management have been advancing, and interest in these areas is growing. Consequently, market demand for these technologies is growing.
[0006] Prior art related to this includes Korean Patent Publication No. 10-2023-0039335 (2023-03-21).
[0007] The purpose of the present invention to solve the above problems is to provide a system for monitoring sports facilities using image recognition and artificial intelligence.
[0008] In order to solve the above-described problem, a device for monitoring a sports facility according to embodiments may include an image receiving unit that receives an image of the inside of the sports facility; an image processing unit that identifies a plurality of objects from the image and identifies information about the plurality of objects; an event detection unit that detects one or more risk events based on information about the plurality of objects; and a communication unit that transmits information about the detected event to a terminal device of an administrator.
[0009] Here, the plurality of objects may include user objects detected by the image processing unit and exercise equipment objects representing exercise equipment within the sports facility. In addition, the event detection unit according to the embodiments may detect a risk event by calculating a change in the position of the user object and a change in the position of the exercise equipment object.
[0010] Exercise equipment objects according to the embodiments can be preset by the terminal device of the manager.
[0011] Furthermore, the event detection unit according to the embodiments may detect a risk event based on: when the type of the first exercise equipment object is a treadmill type: analyzing an image of an area representing the first exercise equipment object to determine whether the first exercise equipment object is in an operating state; and generating a first risk event when the first exercise equipment object is in an operating state and the user's leg is not detected within the area of the first exercise equipment object.
[0012] In addition, the event detection unit according to the embodiments may generate a second risk event when the first exercise equipment object is in an operating state, the user's leg is detected within the first exercise equipment object area, and the speed of the user's head is greater than a preset value.
[0013] Furthermore, the event detection unit according to the embodiments may generate a third risk event when the type of exercise equipment of the second exercise equipment object is a weightlifting type: when a change in the speed of the second exercise equipment object is greater than a preset value and an area where the second exercise equipment object and the user object overlap is greater than a specific value.
[0014] Meanwhile, the event detection unit according to the embodiments may generate a fourth risk event when an exercise equipment object corresponding to an exercise equipment group of interest set by the administrator exists within a preset value from the first exercise equipment object.
[0015] Furthermore, the sports facility monitoring device according to the embodiments may further include a response management unit that calculates the risk level of one or more detected risk events and determines the priority of each risk event based on the calculated risk level, and the communication unit according to the embodiments may transmit information and priority for each risk event to the terminal device of the manager.
[0016] In addition, the response management unit according to the embodiments may determine the priority of the third risk event to be higher than the priority of the first risk event and the priority of the second risk event, and may determine the priority of the fourth risk event to be lower than the priority of the first risk event and the priority of the second risk event.
[0017] Furthermore, the image processing unit according to the embodiments confirms the number of the detected user objects, the communication unit transmits the number of the confirmed user objects to the terminal device of the manager, and the terminal device of the manager displays an image of each of the plurality of sports facilities, and an image of the sports facility corresponding to the maximum value among the numbers of user objects of each of the plurality of sports facilities can be enlarged and displayed.
[0018] With this configuration, the device according to the embodiments enables managers and users of the sports facility to quickly recognize unexpected or dangerous situations occurring within the sports facility and to quickly respond to the situation.
[0019] In addition, the device according to the embodiments with this configuration ensures the safety of users of the sports facility and helps users to use the sports facility safely.
[0020] Furthermore, the device according to the embodiments with this configuration can minimize the occurrence of unexpected risks and achieve efficient risk response by controlling the number of supplementary or rescue personnel to be concentrated only in a single risk event.
[0021] In addition, the device according to the embodiments with this configuration enables the manager to efficiently monitor multiple sports facilities and, when a risk occurs, to induce an appropriate response according to the severity of the risk, thereby managing the safety of the overall sports facilities.
[0022] Furthermore, the event detection unit according to the embodiments can check in real time a third exercise equipment object existing within a first area within a sports facility, and if a body part of a first user exists within an area representing the third exercise equipment object and a second user different from the first user is identified within a safe margin distance from the location of the third exercise equipment, a fifth risk event can be generated.
[0023] In addition, if a body part of the first user exists within an area related to a fourth exercise machine existing at a fixed location within a second area within a sports facility according to embodiments, and a second user different from the first user is identified within a safety margin distance from the location of the fourth exercise machine, a sixth risk event can be generated.
[0024] Furthermore, the event detection unit according to the embodiments can identify a first user object within a third area related to a golf practice facility within the sports facility, and when the position of the hand of the first user and the position of the exercise equipment related to golf are within a specific distance, and a second user different from the first user is identified within a safety margin distance from the position of the first user, a seventh risk event can be generated.
[0025] With this configuration, the terminal device according to the embodiments enables the administrator to quickly recognize a risk event and quickly devise a countermeasure for the risk event, thereby more quickly handling threats to the user's safety.
[0026] Figure 1 shows an example of the configuration of a sports facility monitoring system according to embodiments (hereinafter referred to as “system according to embodiments”).
[0027] FIG. 2 is a flowchart showing an example of a sports facility monitoring device according to embodiments (hereinafter referred to as “device according to embodiments”).
[0028] FIG. 3 is a diagram illustrating a method for detecting a risk event in real time by identifying user objects and exercise equipment objects according to embodiments.
[0029] FIG. 4 is a drawing of a method in which a device according to embodiments simultaneously monitors multiple sports facilities and provides related information to a manager's terminal device.
[0030] FIG. 5 is an example of a hardware configuration diagram of a device that performs a sports facility monitoring method according to embodiments.
[0031] A device for monitoring a sports facility according to embodiments may include an image receiving unit that receives an image of the inside of the sports facility, an image processing unit that identifies a plurality of objects from the image and identifies information about the plurality of objects, an event detection unit that detects one or more risk events based on information about the plurality of objects, and a communication unit that transmits information about the detected event to a terminal device of an administrator.
[0032] The present invention is susceptible to various modifications and embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention. Throughout the description of each drawing, similar reference numerals have been used to designate similar components.
[0033] Terms such as "first," "second," "A," and "B" may be used to describe various components, but the components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a "second component," and similarly, a second component may also be referred to as a "first component." The term "and / or" encompasses any combination of multiple related items described herein or any item among multiple related items described herein.
[0034] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.
[0035] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.
[0036] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.
[0037] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.
[0038] Figure 1 shows an example of the configuration of a sports facility monitoring system according to embodiments (hereinafter referred to as “system according to embodiments”).
[0039] Systems according to embodiments detect emergency situations or dangerous situations from footage of sports facilities and provide information about such situations to administrators. Systems according to embodiments can further determine whether an emergency situation or dangerous situation is an emergency, and based on the risk assessment, recommend emergency measures or provide related information to relevant agencies (e.g., emergency rooms, police, fire departments, etc.) (104).
[0040] A system according to embodiments includes one or more photographing devices (101) for photographing a sports facility. The sports facility may be photographed by one photographing device (101) or by a plurality of photographing devices (101).
[0041] The system according to the embodiments transmits the captured video(s) to the device (100) according to the embodiments via a network or internal computer network. The device (100) according to the embodiments analyzes the video in real time at the sports facility and confirms the occurrence of an event. For example, the device (100) according to the embodiments analyzes the video in real time to detect an emergency or dangerous situation at the sports facility.
[0042] When the device (100) according to the embodiments detects an unexpected or dangerous situation, it transmits information about the detected dangerous situation to the terminal device (102) of the manager. When a dangerous or unexpected situation occurs within a sports facility, the device (100) according to the embodiments can notify not only the terminal device (102) of the manager but also the user(s) (103) using the sports facility of the detected dangerous situation. When the device (100) according to the embodiments detects an urgent situation, i.e., a high level of risk, it can notify the relevant emergency-related organizations (104) of the detected dangerous situation.
[0043] With this configuration, the device (100) according to the embodiments enables managers and users of the sports facility to quickly recognize unexpected or dangerous situations occurring within the sports facility and to quickly respond to the situation.
[0044] In addition, the device (100) according to the embodiments with this configuration ensures the safety of users of the sports facility and helps users to use the sports facility safely.
[0045] The device (100) according to the embodiments can detect a plurality of objects in an image acquired from a photographing device (101) that photographs a sports facility. The objects may include, for example, exercise equipment or users included in the image, and the objects may also include exercise equipment set by a terminal device (103) of an administrator. For example, when the administrator registers information (e.g., model name, etc.) about exercise equipment placed in a sports facility in the electronic device (100) according to the embodiments using the terminal device (103), the electronic device (100) according to the embodiments can extract the location, moving speed, change in speed, etc. of the exercise equipment (i.e., objects) in the sports facility based on the registered information. That is, the device (100) according to the embodiments can capture one or more exercise equipment objects representing exercise equipment from the image.
[0046] The electronic device (100) according to the embodiments can further capture a user object representing a user using a sports facility from an image. The user object may be captured by an image recognition function built into the electronic device (100) according to the embodiments, or may be captured directly based on an image (e.g., a face or body photo) directly registered by the user.
[0047] Meanwhile, in addition to the video, the camera device (101) can further detect overall temperature information of the sports facility, areas with high temperatures (for example, if a fire breaks out at a specific location, the temperature at that location is sharply higher than other areas, so this area is captured), areas with low temperatures, brightness information, etc. The camera device (101) transmits the detected information to the electronic device (100), and the electronic device can comprehensively analyze the detected information to further determine whether an emergency or dangerous situation has occurred.
[0048] With this configuration, the device according to the embodiments can control the number of supplementary or rescue personnel to be concentrated only on a single risk event, thereby minimizing the occurrence of unexpected risks and achieving efficient risk response.
[0049] In addition, the device according to the embodiments with this configuration enables the manager to efficiently monitor multiple sports facilities and, when a risk occurs, to induce an appropriate response according to the severity of the risk, thereby managing the safety of the overall sports facilities.
[0050] Below, examples of the structure of a sports facility monitoring device (100) according to embodiments and specific examples of its operation method are described.
[0051] FIG. 2 is a flowchart showing an example of a sports facility monitoring device according to embodiments (hereinafter referred to as “device according to embodiments”).
[0052] A device (200) according to embodiments may include at least one of an image receiving unit (201), an image processing unit (202), an event determining unit (203), an event learning unit (204), a communication unit (205), and a response management unit (206).
[0053] The image receiving unit (201) can receive images(s) taken of the inside of a sports facility from the photographing device (101) of FIG. 1, etc. In addition to the images, the image receiving unit (201) can also receive information (e.g., temperature information, brightness information, etc.) about the images received from the photographing device (101). The image receiving unit (201) can receive one or more images for one sports facility.
[0054] The image processing unit (202) can analyze one or more images received from the image receiving unit (201) to detect multiple objects included in the one or more images. The multiple objects include, for example, exercise equipment objects representing exercise equipment or user objects representing users. The image processing unit (202) can include an object detection model that detects a specific object or body (e.g., a specific object or body preset by an administrator, a specific object or body directly registered by a user) within an image or video. For example, an administrator can store information about staff(s) of a sports facility in the device (200) according to embodiments using the administrator's terminal device, and the device (200) according to embodiments can check the position, speed, and change in speed of the staff(s) in the image in real time based on this information. Similarly, the administrator can preset information about objects placed within the sports facility (e.g., dumbbells, barbells, machines, treadmills, or specific areas of treadmills, etc.), and the device (200) can check this.
[0055] Additionally, the administrator can specify a region of interest for specific exercise equipment within a gym. For example, since treadmills are rarely moved within a gym, the administrator can directly define a region representing the treadmill belt. The device (200) automatically monitors the region of interest defined by the administrator.
[0056] The event determination unit (203) checks the current situation of the objects captured by the image processing unit (202) and / or the current situation of the area of interest. The event determination unit (203) analyzes the current situation of the objects and / or the current situation of the area of interest to predict whether a dangerous event exists. The event determination unit (203) may include an artificial intelligence model that predicts whether a dangerous event exists based on the above-described situation. The event determination unit (203) inputs an image, information about objects captured in the image, and other necessary information into the artificial intelligence model to predict whether a dangerous event exists, the type of the dangerous event, the location of the dangerous event, the risk level of the dangerous event, etc. In order for the event determination unit (203) to predict a dangerous event, the event learning unit (204) learns the artificial intelligence model included in the event determination unit (203).
[0057] The communication unit (205) can transmit information about a risk event predicted by the event judgment unit (203) (e.g., the location of occurrence of the risk event, the type of the risk event, the risk level of the risk event) to the administrator's terminal device or an agency related to an emergency situation.
[0058] Meanwhile, the communication unit (205) can provide information on the number of users of the sports facility, waiting time for using the sports facility, guidance information on the sports facility, and information on events related to the sports facility to the terminal devices of users of the sports facility.
[0059] The response management unit (206) generates information on measures to be taken in response to risk event(s) determined by the event determination unit (203). Meanwhile, the response management unit (206) according to embodiments may adjust the deployment of employees working at a specific sports facility by utilizing the frequency of occurrence of risk events and the location of occurrence of risk events within the specific sports facility.
[0060] For example, in response to a risk event in which a treadmill continues to operate even when there is no user, the response management unit (206) can check the current status (e.g., busy, free, etc.) of the staff(s) of the sports facility in order of proximity to the treadmill and provide a notification to the terminal device of the appropriate staff.
[0061] For example, if the head speed of a user using a treadmill exercise machine (e.g., a user located within a certain distance from the treadmill) changes rapidly, the response management unit (206) may provide a notification to a nearby employee's terminal device because the user may be in a dangerous situation.
[0062] For example, if a user using heavy exercise equipment is located under the heavy exercise equipment, the response management unit (206) provides a notification to the terminal of a nearby employee or manager within a certain distance from the exercise equipment, as this is a critical risk situation.
[0063] With this configuration, the device according to the embodiments enables managers and users of the sports facility to quickly recognize unexpected or dangerous situations occurring within the sports facility and to quickly respond to the situation.
[0064] In addition, the device according to the embodiments with this configuration ensures the safety of users of the sports facility and helps users to use the sports facility safely.
[0065] Furthermore, the device according to the embodiments with this configuration can minimize the occurrence of unexpected risks and achieve efficient risk response by controlling the number of supplementary or rescue personnel to be concentrated only in a single risk event.
[0066] In addition, the device according to the embodiments with this configuration enables the manager to efficiently monitor multiple sports facilities and, when a risk occurs, to induce an appropriate response according to the severity of the risk, thereby managing the safety of the overall sports facilities.
[0067] FIG. 3 is a diagram illustrating a method for detecting a risk event in real time by identifying user objects and exercise equipment objects according to embodiments.
[0068] Specifically, FIG. 3 illustrates an image of the interior of a sports facility received by a device according to embodiments. Referring to FIG. 3, the device according to embodiments can identify multiple objects from the image.
[0069] Referring to FIG. 3, the plurality of objects include exercise equipment objects (301a, 302a, 303a) representing exercise equipment (301, 302, 303), and user objects (304a, 305a) representing users (304, 305).
[0070] Meanwhile, the exercise equipment object (301a, 302a, 303a) may refer to an area representing the exercise equipment (301, 302, 303) itself (for example, a barbell such as 302 or a dumbbell such as 303), but may also refer to an area of interest directly set by the administrator as a part of the exercise equipment (for example, a belt area of a treadmill such as 301). That is, the administrator may set basic information about the exercise equipment (for example, model name, photo, size, etc.) so that the device according to the embodiments can extract it by relying on an image recognition model, but may also set a fixed area. For example, since a treadmill exercise equipment is usually not moved for a long time, the belt area of the treadmill is likely to be fixed, and therefore, the administrator may directly set that area for convenience.
[0071] Additionally, user objects (304a, 305a) may also refer to areas that identify users (304, 305). For example, referring to FIG. 3, user 304 is positioned on a treadmill, indicating that he or she is using or planning to use the treadmill. Additionally, user 305 is positioned below a barbell (302).
[0072] Here, the device according to the embodiments may simply rely on an image recognition model to extract user objects (304a, 305a), but may also monitor the identity of the recognized user by linking with a database storing information about users while utilizing the image recognition model. For example, if the device according to the embodiments detects a first user object but the identity of the user is unknown, the device may wait until the user's face is revealed, and when the face is revealed, the device may link with the database to extract information about the user's identity. Thereafter, the movement of the user object can be continuously tracked while maintaining information about the user.
[0073] Meanwhile, the database section described above may utilize the SHA-256 encryption method and an administrator-approved access control method to protect personal information and ensure data security. Furthermore, the device according to the embodiments may include a security section capable of efficiently managing and backing up information stored in the database to prevent the loss of important information.
[0074] The device according to the embodiments can verify the identities of users of a sports facility by analyzing user objects (304a, 305a) according to the above-described method, and can notify the administrator's terminal device of information about inappropriate users. For example, the device according to the embodiments can analyze user objects (304a, 305a) to identify users who are not using the sports facility legally, and can transmit this information to the administrator's terminal device so that measures can be taken against such users.
[0075] The device according to the embodiments can calculate the number of users currently in a sports facility by capturing user objects within the sports facility in real time. If the number of users exceeds a certain value, the device according to the embodiments can determine that the sports facility is crowded and provide a notification to the administrator's terminal device to prohibit or restrict access to certain equipment or areas of the sports facility.
[0076] Meanwhile, a risk event may also occur in a situation like the diagram shown in FIG. 3. For example, if a treadmill continues to operate without a user, there is a risk of serious injury when a new user uses the treadmill. Therefore, an electronic device according to embodiments can detect such a potential risk situation and generate a first risk event. In response to the generated first risk event, the device according to embodiments can provide a notification to a terminal device of an employee located near the treadmill or notify a manager of the first risk event indicating that "a potential risk exists for a treadmill user."
[0077] For example, a device according to embodiments may analyze an image of an object (301a) representing a first treadmill to determine whether the first treadmill is currently operating. If the device determines that the first treadmill is currently operating, it may determine whether the user's foot is within the area of the object (301a) representing the first treadmill. If not, the device according to embodiments may generate a first risk event and notify an administrator.
[0078] On the other hand, if user 304 falls while using the second treadmill (301'), user 304 may be seriously injured. In such a case, the device according to the embodiments needs to notify the terminal device of this fact.
[0079] Accordingly, the device according to the embodiments can continuously analyze the second treadmill exercise equipment if the user's (304) foot is within the exercise equipment object (301b) representing the second treadmill. That is, if the second treadmill (301') is operating (i.e., whether the treadmill is operating is confirmed by analyzing an area such as 301b) and the foot of a specific user (304) is within the area of the object (301b) representing the second treadmill (301'), it is confirmed that the user (304) is using the treadmill. In this situation, if the speed of the head of the user (304) is higher than a specific reference value or the change in speed is higher than a specific reference value, it can be inferred that a dangerous situation has occurred for the user. Therefore, in this case, the device according to the embodiments can generate a second risk event, which is a 'treadmill user injury risk event'.
[0080] Meanwhile, in a situation like the drawing shown in FIG. 3, user 305 may have been exposed to an unexpected dangerous situation while exercising with a barbell. If user 305 loses strength while exercising with a barbell (302), causing the barbell (302) to fall suddenly, and as a result, the user (305) does not move or the positions of the user (305) and the barbell (302) are very close to each other and do not separate, it can be inferred that the situation is sufficiently dangerous.
[0081] Accordingly, the device according to the embodiments may generate a third risk event, that is, 'occurrence of risk of injury to the user of the weightlifting machine', if the overlapping area between the user object (305a) area representing the user 305 and the object area (302a) of the weightlifting machine (e.g., a weightlifting machine similar to a barbell or dumbbell) (302) is greater than a certain value or the overlapping area is greater than a certain ratio with respect to the user's area. The device according to the embodiments may, in response to the third risk event, notify the manager or transmit a notification to the terminal devices of surrounding employees.
[0082] Meanwhile, when using a treadmill, users can walk down to the end of the treadmill after using it. However, if another piece of exercise equipment is present during this process, the user could be injured while walking down. Generally speaking, if the first and second exercise equipment are positioned within a certain distance, a potentially dangerous situation can arise.
[0083] Accordingly, the device according to the embodiments can identify a group of exercise equipment (e.g., barbells, dumbbells, foam rollers, kettlebells, dumbbells, gym balls, etc.) that may impede the movement of the user among the types of exercise equipment. This group may be set by the administrator or may be initialized with exercise equipment such as the examples described above. The device according to the embodiments can generate a fourth risk event indicating 'the presence of potential risk related to the treadmill' when the exercise equipment corresponding to the group is located within a certain distance from the treadmill (or, when the exercise equipment corresponding to the group is located in the path that the treadmill user moves along after using it). The device according to the embodiments can notify the administrator in response to the fourth risk event or transmit a notification to the terminal devices of nearby employees.
[0084] In addition, the device according to the embodiments can identify a specific area within a sports facility (e.g., an area with a lot of heavy exercise equipment, an area for weight exercises such as dumbbells and barbells). The area may include a free weight area, a weight machine area, a golf practice area, etc. The free weight area is an area where small equipment such as dumbbells, barbells, and gym balls are present so that users can freely use the equipment at a desired location, and can be set by the manager. The weight machine area is an area where machine-type exercise equipment such as a bench press or a Smith machine that guides users to lift or lower heavy weight plates in a certain posture is gathered, and can be set by the manager. The golf practice area is an area that encompasses golf hitting equipment and screens so that users can practice their golf swings, and can be set by the manager.
[0085] The device according to the embodiments can monitor the location of exercise equipment and the surrounding areas in real time within such a zone. If there are other users or other equipment within a safe margin from the exercise equipment within the zone, the device according to the embodiments can generate a risk event, notify the manager of the risk event, or send a notification to the terminal devices of nearby employees.
[0086] Specifically, when exercising within the free weight area, a safe distance must be maintained from other users. Allowing users to exercise without maintaining a safe distance not only causes inconvenience to other users, but also poses a risk of injury. Therefore, the device according to the embodiments must track the location of exercise equipment (dumbbells, barbells, gym balls, etc.) within the free weight area in real time.
[0087] First, the device according to the embodiments checks in real time whether each piece of exercise equipment is being used by a user. For example, the device according to the embodiments can determine that the exercise equipment is being used by the user if the exercise equipment is located extremely close to a specific body part of a specific user (e.g., within 10 cm). Furthermore, if a specific body part of the user is present within the area of the exercise equipment object and remains there for a certain period of time, the device can determine that the exercise equipment is being used by the user.
[0088] In this case, the device according to the embodiments can change the status information of the exercise equipment to the "in use" state. If the location of the exercise equipment remains unchanged, it moves a certain distance away from the user who was using it, and a certain amount of time has passed since then, the device according to the embodiments can change the status information of the exercise equipment back to the "not in use" state.
[0089] If the exercise equipment is being used by a user (i.e., the exercise equipment has a status of "in use"), the device according to the embodiments checks whether other users are within a safety margin distance (e.g., the safety margin distance may be initialized to 91 cm) from the exercise equipment. If other users are within the safety margin distance, the device according to the embodiments may generate a fifth risk event.
[0090] At this time, the safety margin distance may be initialized to 91 cm for all exercise equipment, but may also be set differently depending on the characteristics of the exercise equipment. For example, if the exercise equipment is light (under 5 kg), the safety margin distance should be set relatively small, but if it is heavy (over 5 kg), the safety margin distance should be set high in proportion to the weight. Accordingly, the device according to the embodiments can check the weight information of the exercise equipment and set the safety margin for the exercise equipment in proportion to the weight of the exercise equipment.
[0091] Additionally, the device according to the embodiments can create a wider safety margin distance the higher the heavier the exercise equipment is positioned. For example, if a 20kg barbell is being used by a user but is off the floor, the safety margin distance may be set small. However, if the user lifts the 20kg barbell and it is positioned 1.5m above the floor, this can be quite dangerous. Therefore, the safety margin distance can be increased proportionally to the height above the floor.
[0092] By setting the safety margin distance to dynamically change based on weight and position from the floor, as in the above method, the device according to the embodiments can quickly recognize risks arising from exercise equipment.
[0093] Likewise, when exercising within a weight machine area, a safe distance from other users must be maintained. The device according to the embodiments first determines whether exercise equipment, such as a bench press, is "in use" by a specific user. This determination is made using the same method as described above. If another user is identified within a safe distance (e.g., 91 cm) from the exercise equipment being "in use," the device according to the embodiments may generate a sixth risk event.
[0094] In addition, a safe distance must be maintained between users within the golf practice area. The device according to the embodiments first identifies the locations of users within the golf practice area in real time. Once users within the golf practice area are identified, it is possible to further identify whether the users are "practicing their swing." For example, the device according to the embodiments may change the status information of the user to "practicing their golf swing" if a specific body part (e.g., a hand) of the identified user is located extremely close to an exercise device (e.g., a golf club) (e.g., within 10 cm), or if the user's hand is continuously present within the exercise device object area for a specific period of time.
[0095] If a specific user's status information is "practicing a golf swing," it can be quite dangerous for other users to approach within a certain distance (e.g., within 1.5 m) of the user. Therefore, the device according to the embodiments may generate a seventh risk event if another user is identified within a safe margin distance from the user "practicing a golf swing." On the other hand, if another user is identified within a certain distance from the user "practicing a golf swing," but the user is identified as a manager or an employee of the sports facility (e.g., a personal trainer, golf pro, facility manager, etc.), the seventh risk event may not be generated.
[0096] In addition, the device according to the embodiments can set various risk events (eighth risk event, ninth risk event, etc.) through logic or conditional statements set by the administrator.
[0097] The device according to the embodiments can predict various risk events using an artificial intelligence model.
[0098] For example, an AI model can learn the correlation between the number of users and the type of risk events based on trends in the number of users at a sports facility. Based on this, a device according to the embodiments can use the AI model to predict expected risk events based on the number of users.
[0099] For example, an AI model can analyze the correlation between past weather data and past risk events to predict significant risk events likely to occur in response to the current weather. Based on this, a device according to the embodiments can predict expected risk events based on the current weather.
[0100] Here, the AI model may include an image recognition model for image recognition, but it may also include a deep learning model for learning time-series data that can predict risk events over time based on changes in specific variables. For example, the AI model may include Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and ARIMA models, which are suitable for learning the aforementioned time-series data. The AI model may also include a neural network model combining LSTM and GRU.
[0101] Meanwhile, the device according to the embodiments can calculate the risk level for each of various risk events. The operation of calculating the risk level can be performed, for example, by the event determination unit (203) of FIG. 2. The device according to the embodiments can calculate the risk level of risk events identified in the video and determine the priority for processing and resolving the risk events. For example, since a user may be crushed or struck by an actual heavy exercise machine, if emergency treatment or response is not provided quickly in such a situation, it may lead to a major accident. Accordingly, the priority of the third risk event may be set higher than that of the first risk event and the second risk event. In addition, since the first and second risk events are accidents that frequently occur among users who actually use the treadmill, the priority of the third risk event may be set higher than that of the fourth risk event.
[0102] With this configuration, the device according to the embodiments enables managers and users of the sports facility to quickly recognize unexpected or dangerous situations occurring within the sports facility and to quickly respond to the situation.
[0103] In addition, the device according to the embodiments with this configuration ensures the safety of users of the sports facility and helps users to use the sports facility safely.
[0104] Furthermore, the device according to the embodiments with this configuration can minimize the occurrence of unexpected risks and achieve efficient risk response by controlling the number of supplementary or rescue personnel to be concentrated only in a single risk event.
[0105] In addition, the device according to the embodiments with this configuration enables the manager to efficiently monitor multiple sports facilities and, when a risk occurs, to induce an appropriate response according to the severity of the risk, thereby managing the safety of the overall sports facilities.
[0106] FIG. 4 is a drawing of a method in which a device according to embodiments simultaneously monitors multiple sports facilities and provides related information to a manager's terminal device.
[0107] Specifically, this is a drawing showing a method in which a device (40) according to embodiments analyzes images taken of multiple sports facilities from a plurality of shooting devices (41), synthesizes the analysis results, and transmits them to a terminal device (42) of an administrator. The device (40) according to embodiments can comprehensively analyze multiple sports facilities, analyze images corresponding to each sports facility, and perform the operations of FIGS. 1 to 3 for each sports facility.
[0108] Accordingly, the device (40) according to the embodiments enables real-time management of risk events occurring in a specific sports facility based on analysis of each of the plurality of sports facilities.
[0109] Meanwhile, the terminal device (42) of the manager according to the embodiments can display (400) a representative image or an entire image for each sports facility for the manager. At this time, the terminal device (42) of the manager according to the embodiments can temporarily allocate a large area for the sports facility where a risky event has occurred and display it in the first area (400a). At this time, the terminal device (42) of the manager can display information about the sports facility where the risky event has occurred (e.g., number of users, records of the risky event) in the second area (400b) together with the first area (400a). The terminal device (42) of the manager according to the embodiments can also allocate a small area for images of other sports facilities where a risky event has not occurred or where a risky event has occurred to a minor extent and display them in the third area (400c).
[0110] Meanwhile, the terminal device (42) of the manager according to the embodiments can display an image of a sports facility having a high priority risk event in the first area (400a) and display information about the risk event of the sports facility in the second area (400b).
[0111] With this configuration, the device according to the embodiments ensures the safety of users of the sports facility and helps users to use the sports facility safely.
[0112] With this configuration, the terminal device according to the embodiments enables the administrator to quickly recognize a risk event and quickly devise a countermeasure for the risk event, thereby more quickly handling threats to the user's safety.
[0113] In addition, the device according to the embodiments with this configuration enables the manager to efficiently monitor multiple sports facilities and, when a risk occurs, to induce an appropriate response according to the severity of the risk, thereby managing the safety of the overall sports facilities.
[0114] FIG. 5 is an example of a hardware configuration diagram of a device that performs a sports facility monitoring method according to embodiments.
[0115] A device (500) according to embodiments may include at least one of a processor (510), a memory (520), a transmitting / receiving device (or transceiver, 530), an input interface device (540), an output interface device (550), a storage device (560), and / or a bus (570).
[0116] A device (500) according to embodiments may include, for example, at least one processor (processor, 510); and a memory (memory, 520) that stores instructions that direct the at least one processor to perform at least one step.
[0117] Here, at least one step may include: receiving a video of the interior of a sports facility; identifying a plurality of objects from the video and identifying information about the plurality of objects; detecting one or more risk events based on the information about the plurality of objects; and transmitting information about the detected event to a terminal device of an administrator.
[0118] Meanwhile, the plurality of objects may include user objects detected by the image processing unit and exercise equipment objects representing exercise equipment within the sports facility.
[0119] The device (500) according to the embodiments can detect a risk event by calculating a change in the position of a user object and a change in the position of the exercise equipment object. At this time, the exercise equipment objects according to the embodiments can be preset by the terminal device of the administrator.
[0120] The device (500) according to the embodiments can detect a risk event based on: when the type of exercise equipment of the first exercise equipment object is a treadmill type: analyzing an image of an area representing the first exercise equipment object to determine whether the first exercise equipment object is in an operating state; and generating a first risk event when the first exercise equipment object is in an operating state and the user's leg is not detected within the area of the first exercise equipment object.
[0121] Furthermore, the device (500) according to the embodiments may generate a second risk event when the first exercise equipment object is in an operating state, the user's leg is identified within the first exercise equipment object area, and the speed of the user's head is greater than a preset value.
[0122] Furthermore, the device (500) according to the embodiments may generate a third risk event when the type of exercise equipment of the second exercise equipment object is a weightlifting type: when the change in the speed of the second exercise equipment object is greater than a preset value and the area where the second exercise equipment object and the user object overlap is greater than a specific value.
[0123] Additionally, the device (500) according to the embodiments may generate a fourth risk event when an exercise equipment object corresponding to an exercise equipment group of interest set by the administrator exists within a preset value from the first exercise equipment object.
[0124] The device (500) according to the embodiments may further include a response management unit that calculates the risk level of one or more detected risk events and determines the priority of each risk event based on the calculated risk level, and may transmit information and priority for each risk event to the terminal device of the manager.
[0125] The device (500) according to the embodiments may determine the priority of the third risk event to be higher than the priority of the first risk event and the priority of the second risk event, and may determine the priority of the fourth risk event to be lower than the priority of the first risk event and the priority of the second risk event.
[0126] Meanwhile, the device (500) according to the embodiments can check the number of detected user objects and transmit the number of checked user objects to the terminal device of the administrator.
[0127] At this time, the administrator's terminal device according to the embodiments can display images of each of the multiple sports facilities. In addition, the administrator's terminal device according to the embodiments can enlarge and display the image of the sports facility corresponding to the maximum number of user objects of each of the multiple sports facilities.
[0128] Furthermore, the event detection unit according to the embodiments can check in real time a third exercise equipment object existing within a first area within a sports facility, and if a body part of a first user exists within an area representing the third exercise equipment object and a second user different from the first user is identified within a safe margin distance from the location of the third exercise equipment, a fifth risk event can be generated.
[0129] In addition, if a body part of the first user exists within an area related to a fourth exercise machine existing at a fixed location within a second area within a sports facility according to embodiments, and a second user different from the first user is identified within a safety margin distance from the location of the fourth exercise machine, a sixth risk event can be generated.
[0130] Furthermore, the event detection unit according to the embodiments can identify a first user object within a third area related to a golf practice facility within the sports facility, and when the position of the hand of the first user and the position of the exercise equipment related to golf are within a specific distance, and a second user different from the first user is identified within a safety margin distance from the position of the first user, a seventh risk event can be generated.
[0131] The methods according to the present invention may be implemented in the form of program commands that can be executed through various computer means, and may be recorded on a computer-readable medium that is driven by a combination of all or part of the components (600 to 670) shown in FIG. 6. The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable medium may be those specifically designed and configured for the present invention, or may be those known and available to those skilled in the art of computer software.
[0132] Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions may include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate with at least one software module to perform the operations of the present invention, and vice versa.
[0133] Additionally, the above-described method or device may be implemented by combining all or part of its configuration or function, or may be implemented separately.
[0134] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.
[0135] This invention provides a system for real-time monitoring and response to potential hazardous situations in sports facilities, thereby enhancing user safety and supporting the efficient operation of such facilities. In particular, it can be utilized in areas where image recognition and artificial intelligence are used to monitor the status of users and exercise equipment within a sports facility, detect hazardous events, and facilitate the prompt implementation of appropriate measures.
[0136] These characteristics can be implemented by computing devices and processors in the operation and use of sports facilities. This can be implemented by computing devices located in various types of sports facilities, such as health clubs, sports centers, and rehabilitation centers. Alternatively, the invention relates to a method that can be implemented by a server located outside of a sports facility.
Claims
1. In a device for monitoring sports facilities, A video receiving unit that receives video footage of the interior of a sports facility; An image processing unit that identifies multiple objects from the image and identifies information about the multiple objects; An event detection unit that detects one or more risk events based on information about the plurality of objects; and A communication unit that transmits information about the detected event to the administrator's terminal device; Sports facility monitoring device.
2. In paragraph 1, The above plurality of objects include user objects detected by the image processing unit and exercise equipment objects representing exercise equipment within the sports facility, The above event detection unit detects a risk event by calculating a change in the position of the user object and a change in the position of the exercise equipment object. Sports facility monitoring device.
3. In paragraph 2, The above exercise equipment objects are preset by the administrator's terminal device. Sports facility monitoring device.
4. In paragraph 3, The above event detection unit, if the type of the first exercise equipment object is a treadmill type: A step of analyzing an image of an area representing the first exercise equipment object to determine whether the first exercise equipment object is in an operational state; and A step of generating a first risk event when the first exercise equipment object is in an operating state and the user's leg is not detected within the area of the first exercise equipment object; Detecting risk events based on, Sports facility monitoring device.
5. In the fourth paragraph, the event detection unit When the first exercise equipment object is in operation, the user's leg is confirmed within the first exercise equipment object area, and the speed of the user's head is greater than a preset value, a second risk event is generated. Sports facility monitoring device.
6. In paragraph 4, The above event detection unit, if the type of the second exercise equipment object is a weight type: If the change in the speed of the second exercise equipment object is greater than a preset value and the area where the second exercise equipment object and the user object overlap is greater than a specific value, a third risk event is generated. Sports facility monitoring device.
7. In paragraph 6, the event detection unit If there is an exercise equipment object corresponding to the exercise equipment group of interest set by the administrator within a preset value from the first exercise equipment object, a fourth risk event is generated. Sports facility monitoring device.
8. In paragraph 7, the sports facility monitoring device Further comprising a response management unit that calculates the risk level of one or more of the detected risk events and determines the priority of each risk event based on the calculated risk level, The above communication unit transmits information and priority for each risk event to the administrator's terminal device. Sports facility monitoring device.
9. In paragraph 8, the response management unit Determine the priority of the third risk event as being higher than the priority of the first risk event and the priority of the second risk event, Deciding the priority of the fourth risk event to be lower than the priority of the first risk event and the priority of the second risk event, Sports facility monitoring device.
10. In paragraph 2, The above image processing unit checks the number of detected user objects, The above communication unit transmits the number of the confirmed user objects to the administrator's terminal device, The above manager's terminal device displays images of each of the multiple sports facilities, The image of the sports facility corresponding to the maximum number of user objects of each of the multiple sports facilities is enlarged and displayed. Sports facility monitoring device.
11. In the first paragraph, the event detection unit Check in real time the third exercise equipment object existing in the first area of the above sports facility, If a body part of the first user exists within the area representing the third exercise equipment object, and a second user different from the first user is identified within a safe margin distance from the location of the third exercise equipment, a fifth risk event is generated. Sports facility monitoring device.
12. In paragraph 1, If a body part of the first user exists within an area related to a fourth exercise machine existing at a fixed location within a second area within the above sports facility, and a second user different from the first user is identified within a safety margin distance from the location of the fourth exercise machine, a sixth risk event is generated; Sports facility monitoring device.
13. In the first paragraph, the event detection unit Check the first user object within the third zone related to the golf practice facility within the above sports facility, If the position of the hand of the first user and the position of the golf-related exercise equipment are within a certain distance, and a second user other than the first user is identified within a safety margin distance from the position of the first user, a seventh risk event is generated. Sports facility monitoring device.
14. A video receiving step for receiving a video of the interior of a sports facility; A step of confirming a plurality of objects from the above image and confirming information about the plurality of objects; A step of detecting one or more events based on information about the plurality of objects; and A step of transmitting information about the detected event to the administrator's terminal device; including; How to monitor sports facilities.
Citation Information
Patent Citations
Outdoor intelligent gymnasium management system
CN114241426A
Treadmill safe exercise method based on AI human body detection technology
CN115909412A
Fitness System
KR1020160020707A
Apparatus of detecting treadmill based image analysis and method of detecting emergency using the same
KR1020180077683A
Method and apparatus for detecting hazardous situations in fiteness center using neural network model
KR102386208B1