Fall detection system and fall detection method

Abstract

Detects user falls without using audio sensors. [Solution] The fall detection device 4 includes a user-side atmospheric pressure value acquisition unit 11 that acquires the user-side atmospheric pressure value output by a wearable sensor 2 attached to the user P's torso B, a reference-side atmospheric pressure value acquisition unit 12 that acquires the reference-side atmospheric pressure value output by a reference-side atmospheric pressure sensor 3 installed in the user P's living space S, and a state determination unit 13 that detects a fall of the user P based on the user-side atmospheric pressure value and the reference-side atmospheric pressure value.

Description

Technical Field

[0001] The present invention relates to a fall detection system and a fall detection method. Background Art

[0002] Patent Document 1 discloses a fall detection method in which a user wears a wearable sensor including an audio sensor and an acceleration sensor, an apparent fall of the user is detected based on an output of the acceleration sensor, and when the audio sensor detects a groan from the user after the fall, the apparent fall is determined to be an actual fall. Prior Art Documents Patent Documents

[0003] Patent Document 1 Japanese National Publication of International Patent Application No. 2022-544757 Summary of the Invention Problems to be Solved by the Invention

[0004] In the configuration of the above-mentioned Patent Document 1, it is necessary to detect a user's groan using an audio sensor, so an audio sensor has been indispensable.

[0005] An object of the present disclosure is to provide a technique for detecting a user's fall without using an audio sensor. Means for Solving the Problems

[0006] A fall detection system is provided, which includes: a user-side pressure value acquisition means for acquiring a user-side pressure value output by a user-side pressure detector attached to the user; a reference-side pressure value acquisition means for acquiring a reference-side pressure value output by a reference-side pressure detector installed in the user's living space; and a fall detection means for detecting the user's fall based on the user-side pressure value and the reference-side pressure value. With the above configuration, a user's fall can be detected without using an audio sensor.

[0007] The reference-side pressure detector may be installed at a higher position than the user-side pressure detector when the user is lying down on the floor of the living space. With the above configuration, it is possible to detect the user falling over based on the relative magnitudes of the user-side pressure value and the reference-side pressure value.

[0008] The reference-side pressure detector may be installed at approximately the same height as the user-side pressure detector when the user is lying down on a bed provided in the living space. With the above configuration, when the absolute value of the difference between the user-side pressure value and the reference-side pressure value is less than a predetermined value, it is possible to detect that the user is sleeping in a lying position on the bed provided in the living space.

[0009] The reference-side pressure detector may be installed so as to be lower than the user-side pressure detector when the user is lying down on a bed provided in the living space. With the above configuration, it is possible to easily determine whether the user is sleeping in a lying position on the bed or whether the user has fallen over, based on the relationship between the user-side pressure value and the reference-side pressure value.

[0010] A fall detection method is provided, in which a computer acquires a user-side atmospheric pressure value output by a user-side atmospheric pressure detector attached to the user, acquires a reference-side atmospheric pressure value output by a reference-side atmospheric pressure detector installed in the user's living space, and detects the user's fall based on the user-side atmospheric pressure value and the reference-side atmospheric pressure value. According to the above method, a user's fall can be detected without using an audio sensor. [Effects of the Invention]

[0011] According to this disclosure, it is possible to detect a user's fall without using an audio sensor. [Brief explanation of the drawing]

[0012] [Figure 1] This is a schematic diagram of a fall detection system. (First Embodiment) [Figure 2] This is a functional block diagram of the fall detection device. (First Embodiment) [Figure 3] This is the control flow for the fall detection device. (First Embodiment) [Figure 4] This is a functional block diagram of the fall detection device. (First Embodiment) [Figure 5] This is the control flow for the fall detection device. (First Embodiment) [Figure 6] This is a schematic diagram of the fall detection system. (Second Embodiment) [Modes for carrying out the invention]

[0013] The present invention will be described below through embodiments of the invention, but the invention claimed is not limited to the following embodiments. Furthermore, not all of the configurations described in the embodiments are necessarily essential as means of solving the problem. For clarity of explanation, the following descriptions and drawings have been omitted and simplified as appropriate. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations have been omitted where necessary.

[0014] In the following embodiments, the description will be divided into multiple sections or embodiments where necessary for convenience. Unless otherwise specified, these are not unrelated, and one may be a modification, application, detailed explanation, or supplementary explanation of part or all of the other. Furthermore, in the following embodiments, when referring to the number of elements (including number, numerical value, quantity, and range), unless otherwise specified or clearly limited to a specific number in principle, it is not limited to that specific number, and may be greater than or less than that number.

[0015] Furthermore, in the following embodiments, the components (including operation steps, etc.) are not necessarily essential unless specifically stated or considered to be fundamentally essential. Similarly, in the following embodiments, when referring to the shape or positional relationship of components, etc., it shall include those substantially similar to or resembling their shape, etc., unless specifically stated or considered to be fundamentally different. The same applies to the numbers, etc. (including number, numerical value, quantity, and range) mentioned above.

[0016] (First Embodiment) Hereinafter, a first embodiment of the present disclosure will be described with reference to Figures 1 to 3. Figure 1 shows a schematic diagram of the fall detection system 1. As shown in Figure 1, the fall detection device 4 (fall detection system) includes a user-side pressure value acquisition unit 11 (user-side pressure value acquisition means) that acquires the user-side pressure value output by a wearable sensor 2 (user-side pressure detector) attached to the torso B of user P, a reference-side pressure value acquisition unit 12 (reference-side pressure value acquisition means) that acquires the reference-side pressure value output by a reference-side pressure sensor 3 (reference-side pressure detector) installed in the living space S of user P, and a state determination unit 13 (fall detection means) that detects a fall of user P based on the user-side pressure value and the reference-side pressure value. The wearable sensor 2 is a specific example of a user-side pressure detector. The reference-side pressure sensor 3 is a specific example of a reference-side pressure detector. The wearable sensor 2 and the reference side pressure sensor 3 are typically configured to communicate bidirectionally with the fall detection device 4 using short-range wireless communication technologies such as Bluetooth® or NFC (Near Field Communication).

[0017] Figure 1 shows a user P lying down on a bed D placed on the floor F of a living space S with a solid line, and a user P who has fallen from the bed D onto the floor F with a dashed line. The fall detection device 4 determines, as an example, whether user P is lying down on the bed D or has fallen from the bed D onto the floor F.

[0018] In the present embodiment, the wearable sensor 2 is, as an example, worn on the chest of the trunk B of the user P for use. Alternatively, the wearable sensor 2 may be worn on the back of the trunk B of the user P, or may be worn on the epigastrium (mizo-ochi) of the trunk B of the user P. The wearable sensor 2 typically includes an atmospheric pressure sensor, a 3-axis gyro sensor, and a 3-axis acceleration sensor. The wearable sensor 2 measures the atmospheric pressure at the wearable sensor 2 using the atmospheric pressure sensor, and outputs the measurement result to the fall detection device 4 as a user-side atmospheric pressure value. Further, the wearable sensor 2 generates attitude information (pitch, roll, yaw) of the wearable sensor 2 using the 3-axis gyro sensor and the 3-axis acceleration sensor, and outputs the attitude information to the fall detection device 4.

[0019] As an example, the reference-side atmospheric pressure sensor 3 is used by being fixed to the bed D. Specifically, the reference-side atmospheric pressure sensor 3 is installed at approximately the same height as the wearable sensor 2 attached to the trunk B of the user P who is sleeping in a recumbent position on the bed D. However, alternatively, the reference-side atmospheric pressure sensor 3 may be fixed to furniture such as a desk or sofa (not shown) installed in the living space S, or to a wall surface. The reference-side atmospheric pressure sensor 3 measures the atmospheric pressure at the reference-side atmospheric pressure sensor 3, and outputs the measurement result to the fall detection device 4 as a reference-side atmospheric pressure value.

[0020] Here, the installation height of the reference-side atmospheric pressure sensor 3 will be described. As described above, the reference-side atmospheric pressure sensor 3 is installed at approximately the same height as the wearable sensor 2 attached to the trunk B of the user P who is sleeping in a recumbent position on the bed D. This means that the reference-side atmospheric pressure sensor 3 is installed to be higher than the wearable sensor 2 attached to the trunk B of the user P when the user P has fallen and is in a recumbent position on the floor F.

[0021] Figure 2 shows a functional block diagram of the fall detection device 4. As shown in Figure 2, the fall detection device 4 includes a processor 4a, memory 4b, communication interface 4c, input interface 4d, and LCD 4e (Liquid Crystal Display). The processor 4a has access to memory 4b. The processor 4a communicates with the wearable sensor 2 and the reference barometric pressure sensor 3 via the communication interface 4c. The processor 4a reads and executes the program stored in memory 4b. In this way, the processor 4a makes the hardware, including the processor 4a, memory 4b, and communication interface 4c, function as the posture information acquisition unit 10, the user-side barometric pressure value acquisition unit 11, the reference-side barometric pressure value acquisition unit 12, the state determination unit 13, and the determination result output unit 14. The fall detection device 4 may consist of a single device or may be realized by distributed processing using multiple devices.

[0022] The posture information acquisition unit 10 acquires posture information from the wearable sensor 2.

[0023] The user-side atmospheric pressure value acquisition unit 11 is a specific example of a means for acquiring user-side atmospheric pressure values. The user-side atmospheric pressure value acquisition unit 11 acquires user-side atmospheric pressure values ​​from the wearable sensor 2.

[0024] The reference-side pressure value acquisition unit 12 is a specific example of a reference-side pressure value acquisition means. The reference-side pressure value acquisition unit 12 acquires the reference-side pressure value from the reference-side pressure sensor 3.

[0025] The state determination unit 13 is a specific example of a fall detection means. The state determination unit 13 determines the state of user P based on posture information, user-side atmospheric pressure value, and reference-side atmospheric pressure value. The state of user P refers to the type of posture of user P, whether or not user P has fallen, and other aspects of user P's state. Specifically, it is as follows:

[0026] The state determination unit 13 determines whether user P is lying down based on the posture information from the wearable sensor 2. The state determination unit 13 determines that user P is sleeping in a lying position on bed D if user P is lying down and the absolute value of the difference between the user's side pressure value and the reference side pressure value is less than a predetermined value. The state determination unit 13 determines that user P has fallen over if user P is lying down, the absolute value of the difference between the user's side pressure value and the reference side pressure value is greater than or equal to a predetermined value, and furthermore, the user's side pressure value is higher than the reference side pressure value. The state determination unit 13 determines that wearable sensor 2 or reference side pressure sensor 3 is malfunctioning if user P is lying down, the absolute value of the difference between the user's side pressure value and the reference side pressure value is greater than or equal to a predetermined value, and furthermore, the user's side pressure value is lower than the reference side pressure value. The state determination unit 13 determines that if user P is not lying down, user P is neither asleep nor has fallen, and user P is sitting or standing.

[0027] The judgment result output unit 14 outputs the judgment result from the state judgment unit 13 to the LCD 4e.

[0028] Next, the operation flow of the fall detection device 4 will be explained with reference to Figure 3. Figure 3 shows the operation flow of the fall detection device 4.

[0029] First, the posture information acquisition unit 10 acquires posture information from the wearable sensor 2 (S100). Next, the user-side atmospheric pressure value acquisition unit 11 acquires the user-side atmospheric pressure value from the wearable sensor 2 (S110). Next, the reference-side atmospheric pressure value acquisition unit 12 acquires the reference-side atmospheric pressure value from the reference-side atmospheric pressure sensor 3 (S120). Next, the state determination unit 13 determines the state of user P based on the posture information, user-side atmospheric pressure value, and reference-side atmospheric pressure value (S130). The state of user P includes whether or not user P has fallen. Then, the determination result output unit 14 outputs the determination result from the state determination unit 13 to the LCD 4e (S140), and the process returns to step S100.

[0030] The first embodiment of this disclosure has been described above. The first embodiment has the following features.

[0031] The fall detection device 4 (fall detection system) includes a user-side atmospheric pressure value acquisition unit 11 (user-side atmospheric pressure value acquisition means) that acquires the user-side atmospheric pressure value output by a wearable sensor 2 (user-side atmospheric pressure detector) attached to user P, a reference-side atmospheric pressure value acquisition unit 12 (reference-side atmospheric pressure value acquisition means) that acquires the reference-side atmospheric pressure value output by a reference-side atmospheric pressure sensor 3 (reference-side atmospheric pressure detector) installed in user P's living space S, and a state determination unit 13 (fall detection means) that detects a fall of user P based on the user-side atmospheric pressure value and the reference-side atmospheric pressure value. With the above configuration, a fall of user P can be detected without using an audio sensor.

[0032] Furthermore, the reference-side pressure sensor 3 is positioned higher than the wearable sensor 2 when user P is lying down on the floor F of the living space S. With this configuration, it is possible to detect user P falling based on the relative magnitudes of the user-side pressure value and the reference-side pressure value.

[0033] Furthermore, the reference-side pressure sensor 3 is installed at approximately the same height as the wearable sensor 2 when user P is lying down on bed D in living space S. With this configuration, when the absolute value of the difference between the user-side pressure value and the reference-side pressure value is less than a predetermined value, it is possible to detect that user P is sleeping in a lying position on bed D in living space S.

[0034] The first embodiment described above can be modified, for example, as follows:

[0035] In other words, in the first embodiment described above, the reference-side pressure sensor 3 was set at approximately the same height as the wearable sensor 2 when user P is lying down on bed D in living space S. However, alternatively, the reference-side pressure sensor 3 may be set lower than the wearable sensor 2 when user P is lying down on bed D in living space S. In other words, the reference-side pressure sensor 3 may be set higher than the wearable sensor 2 when user P is lying down on the floor F of living space S, and lower than the wearable sensor 2 when user P is lying down on bed D in living space S. This makes it easy to determine, based on the relative magnitudes of the user-side pressure value and the reference-side pressure value, whether user P is sleeping in a lying position on bed D or whether user P has fallen over. Furthermore, if the user's atmospheric pressure value is lower than the reference atmospheric pressure value, and the absolute value of the difference between the two is less than a predetermined value, it may be determined that user P is lying down on bed D and sleeping. If the absolute value of the difference between the two is greater than a predetermined value, it may be determined that user P is sitting or standing and not sleeping.

[0036] (Second Embodiment) Next, a second embodiment of the present disclosure will be described with reference to Figures 4 and 5. The following description will focus on the differences between this embodiment and the first embodiment, omitting any redundant explanations. Figure 4 is a functional block diagram of the fall detection device 4.

[0037] In the first embodiment described above, the wearable sensor 2 includes a barometric pressure sensor, a 3-axis gyro sensor, and a 3-axis accelerometer. The 3-axis gyro sensor and the 3-axis accelerometer are used to generate posture information for the wearable sensor 2, and this posture information is output to the fall detection device 4. In contrast, in this embodiment, the wearable sensor 2 does not include a 3-axis gyro sensor and a 3-axis accelerometer. Therefore, the wearable sensor 2 does not generate posture information. Correspondingly, as shown in Figure 4, the wearable sensor 2 does not include a posture information acquisition unit 10.

[0038] In the first embodiment described above, the state determination unit 13 determined the user P's posture based on the posture information from the wearable sensor 2. In contrast, in this embodiment, the state determination unit 13 estimates the user P's posture based on the user's atmospheric pressure value and the reference atmospheric pressure value. Specifically, the state determination unit 13 estimates that user P is lying down on the bed D when the absolute value of the difference between the user's atmospheric pressure value and the reference atmospheric pressure value is less than a predetermined value. The state determination unit 13 estimates that user P is sitting or standing when the absolute value of the difference between the user's atmospheric pressure value and the reference atmospheric pressure value is greater than or equal to the predetermined value, and the user's atmospheric pressure value is lower than the reference atmospheric pressure value. The state determination unit 13 determines that user P has fallen over when the absolute value of the difference between the user's atmospheric pressure value and the reference atmospheric pressure value is greater than or equal to the predetermined value, and the user's atmospheric pressure value is higher than the reference atmospheric pressure value. In this way, the posture information from the wearable sensor 2 can be omitted, and the user P's posture and state can be estimated based on the user's atmospheric pressure value and the reference atmospheric pressure value.

[0039] Next, the control flow of the tipping detection device 4 in the second embodiment will be described. Figure 5 shows the control flow of the tipping detection device 4. As shown in Figure 5, in this embodiment, the control flow of the tipping detection device 4 omits step S100 of the control flow of the first embodiment shown in Figure 3, and the other steps are the same as the control flow of the first embodiment. However, the processing by the state determination unit 13 is different as described above.

[0040] Although the present invention has been described above with reference to the first and second embodiments, the present invention is not limited thereto. Various modifications to the structure and details of the present invention can be made, as can be understood by those skilled in the art within the scope of the invention.

[0041] For example, as shown in Figure 6, the fall detection system 1 may include multiple reference-side pressure sensors 3. The multiple reference-side pressure sensors 3 may include, for example, a reference-side pressure sensor 3a installed on the floor F, a reference-side pressure sensor 3b installed on the bed D, and a reference-side pressure sensor 3c installed on the ceiling C. By arranging multiple reference-side pressure sensors 3 vertically at intervals from each other in this way, the actual height of the wearable sensor 2 attached to the user P's torso B can be estimated with high accuracy, typically by linear interpolation of the pressure.

[0042] In the above embodiment, the wearable sensor 2 is attached to the torso B of user P. However, the attachment position of the wearable sensor 2 is not limited to the torso B. The wearable sensor 2 may be attached to any part of user P, provided that the above-mentioned pressure difference Δp changes in accordance with changes in user P's posture. Therefore, for example, the attachment position of the wearable sensor 2 may be the head, shoulder, or thigh of user P.

[0043] In the above example, the program can be stored and supplied to the computer using various types of non-transitory computer-readable medium. Non-transitory computer-readable medium includes various types of tangible storage medium. Examples of non-transitory computer-readable medium include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives) and magneto-optical storage media (e.g., magneto-optical disks). Examples of non-transitory computer-readable medium further include CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM; examples of non-transitory computer-readable medium further include PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, and RAM (random access memory)). Alternatively, the program may be supplied to the computer by various types of transient computer-readable medium. Examples of transient computer-readable medium include electrical signals, optical signals, and electromagnetic waves. Temporary computer-readable media can supply programs to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels. [Explanation of Symbols]

[0044] 1. Fall detection system 2 Wearable Sensors 3. Reference side pressure sensor 3a Reference side pressure sensor 3b Reference side pressure sensor 3c Reference side pressure sensor 4. Tipping detection device 4a processor 4b Memory 4c communication interface 4D Input Interface 4e LCD 10 Posture information acquisition section 11. User-side pressure value acquisition unit 12. Reference side pressure value acquisition unit 13 State determination unit 14. Output section for judgment results B. Core C Ceiling D Bed F floor P User S living space

Claims

1. A means for acquiring user-side atmospheric pressure values ​​that acquires user-side atmospheric pressure values ​​output by a user-side atmospheric pressure detector attached to the user, A means for acquiring a reference side pressure value that acquires a reference side pressure value output by a reference side pressure detector installed in the user's living space, A fall detection means for detecting the user falling based on the user's side pressure value and the reference side pressure value, including, Fall detection system.

2. A fall detection system according to claim 1, The reference-side pressure detector is installed so as to be higher than the user-side pressure detector when the user is lying down on the floor of the living space. Fall detection system.

3. A fall detection system according to claim 2, The reference-side pressure detector is installed at approximately the same height as the user-side pressure detector when the user is lying down on a bed provided in the living space. Fall detection system.

4. A fall detection system according to claim 2, The reference-side pressure detector is installed so as to be lower than the user-side pressure detector when the user is lying down on a bed provided in the living space. Fall detection system.

5. Computers The user's atmospheric pressure value is obtained from the user's attached pressure detector. The reference pressure value output by the reference pressure detector installed in the user's living space is acquired. Based on the user's side pressure value and the reference side pressure value, the system detects the user falling over. Method for detecting falls.

Images