Fall detection device and system thereof

Abstract

To provide a fall detection technique with improved accuracy.SOLUTION: The present invention relates to a fall detection device and a system thereof, and includes a human body sensing unit that senses a motion and a state of a monitoring target to accurately and quickly detect a fall of a user through real-time monitoring, generates the motion and the state as sensing information, and transmits the sensing information to a control unit, a storage unit that stores simulation information for a motion of a human body occurring when the user falls and a fall determination algorithm based on a displacement amount from the sensing information sensed by the human body sensing unit, and a control unit that controls an operation of each component, determines whether the monitoring target falls through the sensing information, the simulation information, and the fall determination algorithm, and generates a determination signal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a fall detection device and system thereof, and more particularly to a technology capable of accurately and quickly detecting a user's fall through real-time monitoring. [Background technology]

[0002] Falls are a common type of accident that occurs primarily among the elderly, and are particularly common among the elderly, who tend to recover slowly, resulting in serious after-effects.

[0003] In order to prevent such falls, a technology has been proposed in which a monitoring device is installed in the living space of the elderly and worn by the elderly.

[0004] Here, a fixed-type monitoring device determines whether a person has fallen by detecting a sudden drop in the person's position or a decrease in movement. However, this technology has the problem of making false fall determinations because it only monitors the person's movement and activity.

[0005] Other conventional technologies use wearable devices worn by users to detect falls and determine accidents based on the user's pulse and location signals. However, these wearable devices require frequent charging, and users often forget to charge them or find it inconvenient, resulting in low utilization. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Korean Patent Registration No. 10-1438002 [Patent Document 2] Korean Patent Publication No. 10-2016-0080046 Summary of the Invention [Problem to be solved by the invention]

[0007] The present invention has been created to solve the above-mentioned conventional problems, and aims to provide a fall detection technology that can reliably prevent a user from falling and can improve accuracy through continuous data updates. [Means for solving the problem]

[0008] In order to achieve the above-mentioned object, in an embodiment of the present invention, a fall detection device is installed in a specific location and detects falls of a monitored person, and includes a human body detection unit that detects the movements and state of the monitored person, generates this as detection information, and transmits it to a control unit; a storage unit that stores simulation information regarding the human body movements that occur when a fall occurs and an algorithm that determines whether a fall has occurred based on the amount of displacement from the detection information detected by the human body detection unit; and a control unit that controls the operation of each component, determines whether the monitored person has fallen based on the detection information, the simulation information, and the fall determination algorithm, and generates a determination signal.

[0009] In this embodiment, the human body detection unit can use detection means including one or more of visible light, infrared light, radar, or laser reflection measurement, which can separate the monitored person from the background and distinguish the monitored joints.

[0010] In this embodiment, when one or more monitoring targets are detected, the human body detection unit can assign a unique identification ID to each monitoring target.

[0011] In this embodiment, the joint divisions may be head, elbow and wrist joints for the upper torso of the monitored person, knee and ankle joints for the lower torso, and the upper torso and lower torso.

[0012] In this embodiment, the fall determination algorithm can determine whether a fall has occurred based on a combination of the displacement per unit time of each joint of the monitored person, the angle between the joints, and the stop time.

[0013] In this embodiment, the fall detection algorithm can determine that a fall has occurred if the height of the joint of the monitored person drops suddenly or if the height of the joint is detected to drop gradually over a predetermined period of time, and if no further movement occurs over a predetermined period of time.

[0014] In this embodiment, the fall detection algorithm determines that there is a possibility of a fall if the change in joint height of the monitored person is 30 cm or more and the final height reaches less than 20 cm, and can determine that a fall has occurred if a movement of 20 cm or more occurs within a predetermined time period and the joint height does not increase to 20 cm or more.

[0015] In this embodiment, the control unit compares the detection information with the simulation information to see if it is similar, and if it is similar, determines whether a fall has occurred, and compares the detection information with the simulation information to see if it is similar, and if it is not similar, determines whether a fall has occurred using a fall determination algorithm.

[0016] In this embodiment, the control unit may further perform an operation of merging data on which the presence or absence of a fall is determined using the fall determination algorithm into simulation information.

[0017] In this embodiment, the device further includes a communication unit that communicates with an external network via wired or wireless communication, and the communication unit can upload simulation information merged by the control unit to the external network and receive simulation information merged and uploaded by other fall detection devices from the external network.

[0018] In this embodiment, the device further includes a temperature detection unit that measures the indoor temperature, generates temperature information, and transmits it to a control unit. The control unit generates a fire alarm if the temperature information is 60 degrees Celsius or higher, and the communication unit can upload the fire alarm to an external network.

[0019] In this embodiment, the device further includes a photographing unit that photographs the interior of the room and transmits the photographs to a control unit, and the control unit can further perform the operation of uploading the images photographed by the photographing unit to an external network via the communication unit when it generates a fire alarm and a fall detection signal.

[0020] In order to achieve the above-mentioned object, according to another embodiment of the present invention, a fall detection system is a system installed at a specific location and detects falls of a monitored person, and includes a network that provides wired and wireless communication paths between each device, the fall detection device, a service server that generates simulation information for human body movements that occur when a fall occurs, transmits it to connected fall detection devices, and transmits the newly merged simulation information transmitted from the connected fall detection devices to all connected fall detection devices, and a rescue server that requests the dispatch of rescue personnel to the location where a fall is detected in the fall detection device. [Effects of the Invention]

[0021] According to the present invention, a fall detection technique can be provided that can detect the amount and speed of movement of each joint joint of a person to be monitored and accurately determine whether or not a fall has occurred.

[0022] Furthermore, according to the present invention, by updating the fall information collected by another fall detection device, more stable and various types of fall detection are possible. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a block diagram of a fall detection device according to an embodiment of the present invention. [Figure 2] 1 is a block diagram of a fall detection system according to an embodiment of the present invention. [Figure 3] 4 is a flowchart of fall detection according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

[0025] In the following description of the present invention, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. Furthermore, the terms used below are terms established in consideration of the functions of the present invention, and these terms may vary depending on the intentions or practices of the manufacturer of the product, and the definitions of the terms should be based on the overall content of this specification.

[0026] (Fall detection device) The fall detection device according to the present invention will be described below with reference to the attached FIG.

[0027] FIG. 1 is a block diagram of a fall detection device according to an embodiment of the present invention.

[0028] As shown in FIG. 1, the fall detection device 100 of this embodiment includes a human body detection unit 110, a storage unit 120, an audio unit 130, a communication unit 140, a control unit 150, and a power supply unit 190, and is installed in a specific location such as a living space to detect a fall by a monitored person.

[0029] The human body detection unit 110 detects the movement and state of the monitored person, generates this as detection information, and transmits it to the control unit 150. The human body detection unit 110 may use a detection means including one or more of visible light, infrared light, radar, or laser reflection light measurement, which can distinguish the joints of the monitored person, and detects the monitored person by separating them from the background. In the case of a visible light detection means, separation of the monitored person from the background can be achieved by detecting phase differences or by acquiring three-dimensional information using two or more cameras. In the case of infrared light, separation can be achieved by the temperature difference between the heat generated by the human body and surrounding objects. In the case of radar or laser reflection light, separation of the monitored person from the background can be achieved by distance measurement. Such separation of the monitored person from the background can reduce detection errors due to the background and improve accuracy.

[0030] The camera can photograph negatively monitored persons in a negative manner, thereby protecting personal information.

[0031] Furthermore, when one or more monitoring targets are detected, the human body detection unit 110 preferably assigns a unique identification ID to each monitoring target. Such classification of monitoring targets can be performed based on the monitoring targets' physical characteristics (height, body type, joint size, etc.), which allows detection of multiple monitoring targets.

[0032] Here, the joint segments are preferably the head, elbow, and wrist joints for the upper torso of the monitored person, the knee and ankle joints for the lower torso, and the upper and lower torso. Such joint segments can be added or removed depending on the situation and need, but adding too many joint segments can increase the burden on hardware, and removing too many joint segments can decrease detection accuracy.

[0033] The storage unit 120 stores simulation information relating to the movement of the human body that occurs when a fall occurs, and a fall determination algorithm based on the amount of displacement from the detection information detected by the human body detection unit 110 .

[0034] The simulation information includes fall test data prepared by the manufacturer and data on whether a fall has occurred or not determined by other fall detection devices. Such simulation information may be stored when the product is first manufactured, and new simulation information may be added via the communication unit 140 as needed.

[0035] The fall detection algorithm determines whether a person has fallen based on a combination of the displacement per unit time of each joint of the monitored person, the angle between the joints, and the pause time. For example, the fall detection algorithm can determine a fall if it detects that the lower torso has moved downward at a rate of 30 cm or more per second, and then if the monitored person's movement is not detected for a predetermined period of time (e.g., 10 seconds or more). In another case, if the monitored person twists their torso joints, it can determine this as pain from falling and determine this as a fall. This fall detection algorithm is supplemented and corrected as fall cases accumulate, thereby increasing its accuracy. Information confirmed as a fall in other fall detection devices can be added to the fall cases via the communication unit 140.

[0036] Here, the fall detection algorithm may determine a fall if a sudden drop in the monitored person's joint height or a gradual drop in joint height for a predetermined period of time is detected and no further movement occurs for the predetermined period of time. That is, a fall may occur when a person falls from a high position and then suddenly drops, or when a person gradually lowers their posture due to dizziness, etc., and by detecting this and then not moving for a predetermined period of time (e.g., 10 minutes or more), it can detect a fall or fainting due to other factors. More specifically, the fall detection algorithm may determine a possibility of a fall if the monitored person's joint height changes by 30 cm or more and the final height reaches less than 20 cm, and may determine a fall if a movement of 20 cm or more occurs for a predetermined period of time or if the joint height does not increase by 20 cm or more.

[0037] The human body detection unit emits microwaves into the monitored area, receives the reflected microwaves, and performs image modeling of the detection area, thereby detecting fast falls, slow falls, or falls behind an object within the detection area.

[0038] On the other hand, in the toilet area where camera photography is not possible, an infrared detection unit is additionally installed, and if the fall detection algorithm determines that the head position is lower than the knee position, it determines that a structure is necessary because the person being monitored has fainted or for other reasons.

[0039] The audio unit 130 collects sounds generated in the fall detection area and transmits sounds transmitted from outside. When the sound unit 130 collects sounds such as the squirming voice of the person being monitored, this can be used to determine whether the person has fallen and, if necessary, to transmit a request for assistance from the person being monitored to the outside. The sound transmitted from the outside via the audio unit 130 can be used to communicate with the person being monitored.

[0040] The communication unit 140 communicates with an external network via wired or wireless communication. The communication unit 140 uploads simulation information merged by the control unit 150 to the external network and receives simulation information merged and uploaded by other fall detection devices from the external network. In addition, as necessary, the communication unit 140 transmits sound collected in the fall detection area by the sound unit 130 to the outside, and receives sound transmitted from the outside and transmits it to the sound unit 130. In addition, the communication unit 140 can request the dispatch of an ambulance or the like from an external rescue server based on a determination signal generated by the control unit 150.

[0041] The control unit 150 controls the operation of each component, determines whether the monitored person has fallen based on the detection information, simulation information, and fall determination algorithm, and generates a determination signal. To explain the operation of the control unit 150 in more detail, the control unit 150 compares the detection information with the simulation information to determine whether it is similar to the detection information, and if so, determines whether a fall has occurred. The control unit 150 also compares the detection information with the simulation information to determine whether it is similar to the detection information, and if not, determines whether a fall has occurred using the fall determination algorithm. Here, the control unit 150 further performs an operation of merging data on which a fall has been determined using the fall determination algorithm into simulation information, and the merged simulation information is transmitted to the outside via the communication unit 140, which can help improve the accuracy of the simulation information.

[0042] The temperature detection unit 160 measures the indoor temperature, generates temperature information, and transmits it to the control unit 150. This makes it possible to prevent a fire that may break out as the indoor temperature continues to increase due to the monitored person losing consciousness or the malfunction of cooking appliances. At this time, the control unit 150 generates a fire alarm if the temperature information is 60 degrees Celsius or higher, and the communication unit 140 uploads the fire alarm to an external network to prevent damage to human life and property due to the fire.

[0043] The photographing unit 170 photographs the interior of the room and transmits the photograph to the control unit 150. At this time, when the control unit generates a fire alarm or a fall detection signal, it further performs an operation of uploading the image photographed by the photographing unit 170 to an external network via the communication unit 140. Such a configuration of the photographing unit 170 allows the rescue system and guardians to more clearly confirm the condition of the person being monitored and the environmental condition.

[0044] An unexplained reference numeral 190 denotes a power supply unit 190, which supplies the power necessary for the operation of each component. The power supply unit 190 preferably operates by receiving power from a household power source, and preferably further includes a backup battery in case of an emergency such as a power outage.

[0045] (Fall detection system) A fall detection system 200 according to an embodiment of the present invention will be described below with reference to the accompanying FIG.

[0046] FIG. 2 is a block diagram of a fall detection system according to an embodiment of the present invention.

[0047] As shown in FIG. 2, the fall detection system 200 according to this embodiment includes a fall detection device 100, a user terminal 210, a rescue server 220, a service server 230, and a network 250, and is installed at a specific location to detect a fall of a monitored person.

[0048] The network 250 provides wired and wireless communication paths between the devices.

[0049] The fall detection device 100 is a device according to the above-described embodiment, and detects a fall of a fall monitoring target person.

[0050] The rescue server 220 requests the dispatch of rescue personnel to the location where a fall is detected by the fall detection device 100. The rescue server 220 is a component that manages various types of rescue systems such as police, fire departments, and medical institutions.

[0051] The service server 230 generates simulation information regarding the movements of the human body that occur when falling, transmits it to the connected fall detection device 100, and transmits newly merged simulation information transmitted from the connected fall detection device 100 to the connected fall detection device 100.

[0052] (Example of use) An example of use of the fall detection system according to the present invention will be described below with reference to the accompanying drawings.

[0053] FIG. 3 is a flow chart of fall detection according to the present invention.

[0054] The service server 230 uses actual people as virtual fall monitoring targets to demonstrate falls according to various virtual fall situations. Information about these demonstrations is collected using motion capture or the like and distributed to the storage unit 120 of the fall detection device 100 (S110).

[0055] The fall detection device 100 detects a fall of a person to be monitored or a fire in a monitored area via the human body detection unit 110 (S120).

[0056] The control unit 150 of the fall detection device 100 determines whether or not a fall has occurred or whether or not a fire has occurred using the simulation information and a fall determination algorithm (S130).

[0057] If it is determined that a fall or an accident has occurred, the fall detection device 100 generates an accident signal and transmits this to the network 250. The accident signal transmitted to the network 250 is transmitted to the rescue server 220 and the user terminal 210, which activates the rescue system and transmits the situation to the user terminal 210 used by the guardian or the like of the person being monitored.

[0058] Thereafter, the service server 230 collects fall determination information from the fall detection devices 100, and if there is new information, it updates the previously distributed information and distributes it to all connected fall detection devices 100, and the fall detection devices 100 update the fall data (S150). As a result, new information for fall detection is continuously updated, and the accumulation of this information improves the accuracy of fall detection.

[0059] Specific embodiments of the present invention have been described above.

[0060] However, it should be understood by those skilled in the art that the spirit and scope of the present invention are not particularly limited to such specific examples, and that various modifications and variations are possible within the scope that does not change the gist of the present invention.

[0061] Therefore, the above-described embodiments are provided to fully inform those skilled in the art of the present invention of the scope of the invention, and should be understood to be illustrative in all respects and not restrictive, and the present invention is defined only by the claims. [Explanation of symbols]

[0062] 100: Fall detection device 110: Human body detection unit 120: Storage area 130: Sound department 140: Communications Department 150: Control unit 160: Temperature detection unit 170: Photography Department 190: Power supply section 200: Fall detection system 210: User terminal 220:Rescue Server 230: Service server 250: Network

Claims

1. A device that is installed in a specific location and detects falls of a monitored person, a human body detection unit that detects the movement and state of the person being monitored, generates the detected information, and transmits it to a control unit; a storage unit that stores simulation information regarding human body movements that occur when a fall occurs and a fall determination algorithm based on the amount of displacement from the detection information detected by the human body detection unit; a control unit that controls the operation of each component, determines whether the monitoring target has fallen based on the detection information, the simulation information, and a fall determination algorithm, and generates a determination signal; The human body detection unit uses a detection means including one or more of visible light, infrared light, radar, and laser reflected light measurement that can classify the joints of the monitored object; When the detection means is visible light, it detects the phase difference and separates the monitored person from the background by acquiring three-dimensional information using two or more cameras; when it is infrared, it separates the monitored person from the background by the temperature difference between the heat generated by the human body and the surrounding objects; when it is radar or laser reflected light, it separates the monitored person from the background by measuring the distance; The fall detection device is characterized in that, when one or more monitoring subjects are detected, the human body detection unit classifies the monitoring subjects based on physical characteristics such as height, body type, and joint size of the monitoring subjects, and assigns a unique identification ID to each monitoring subject.

2. The fall detection device of claim 1, wherein the human body detection unit detects a fast fall, a slow fall, or a fall behind an object within the detection area by emitting microwaves into the monitored area, receiving the reflected microwaves, and performing image modeling of the detection area.

3. The fall detection device according to claim 1, wherein the joint classification distinguishes between the head, elbow and wrist joints for the upper torso of the monitored person, the knee and ankle joints for the lower torso, and the upper torso and the lower torso.

4. The fall determination algorithm includes:

4. The fall detection device according to claim 3, wherein a fall is determined based on a combination of the displacement per unit time of each joint of the monitored person, the angle between the joints, and the stop time.

5. The fall determination algorithm includes: The fall detection device of claim 3, characterized in that when a sudden decrease in joint height of the monitored person or a gradual decrease in joint height for a predetermined period of time is detected, if no further movement occurs for the predetermined period of time, it is determined that a fall has occurred.

6. The fall determination algorithm includes:

6. The fall detection device of claim 5, wherein when the change in joint height of the monitored person is 30 cm or more, if the final height reaches less than 20 cm, it is determined that there is a possibility of a fall, and if a movement of 20 cm or more occurs within a predetermined time and the joint height does not increase to 20 cm or more, it is determined that a fall has occurred.

7. The control unit comparing the detected information with the simulated information to determine whether there is any similarity between the detected information and the simulated information, and if there is any similarity, determining whether there will be a fall; The fall detection device according to claim 1, characterized in that the detection information is compared with the simulation information to determine whether it is similar, and if it is not similar, a fall determination algorithm is used to determine whether a fall has occurred.

8. The control unit The fall detection device according to claim 7, further comprising an operation of merging data on which the presence or absence of a fall is determined using the fall determination algorithm with simulation information.

9. Further comprising a communication unit for performing wired or wireless communication with an external network, The fall detection device of claim 7, characterized in that the communication unit uploads the simulation information merged by the control unit to an external network and receives simulation information merged and uploaded by another fall detection device from the external network.

10. The device further includes a temperature detector that measures the indoor temperature, generates temperature information, and transmits the temperature information to the controller. The control unit generates a fire alarm when the temperature information is equal to or greater than 60 degrees Celsius; The fall detection device according to claim 9 , wherein the communication unit uploads the fire alarm to an external network.

11. The camera further includes a camera unit that takes an image of the room and transmits the image to the controller, The fall detection device described in claim 10, characterized in that when the control unit generates a fire alarm and a fall determination signal, it further performs the operation of uploading images captured by the imaging unit to an external network via the communication unit.

Images