WO2018030017A1 - Moving body detection unit and care support system - Google Patents

Moving body detection unit and care support system Download PDF

Info

Publication number
WO2018030017A1
WO2018030017A1 PCT/JP2017/023637 JP2017023637W WO2018030017A1 WO 2018030017 A1 WO2018030017 A1 WO 2018030017A1 JP 2017023637 W JP2017023637 W JP 2017023637W WO 2018030017 A1 WO2018030017 A1 WO 2018030017A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
detection unit
image
subject
living room
Prior art date
Application number
PCT/JP2017/023637
Other languages
French (fr)
Japanese (ja)
Inventor
楠田　将之
Original Assignee
コニカミノルタ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by コニカミノルタ株式会社 filed Critical コニカミノルタ株式会社
Priority to JP2018532866A priority Critical patent/JP6984601B2/en
Publication of WO2018030017A1 publication Critical patent/WO2018030017A1/en

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/113—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb occurring during breathing

Definitions

  • the present invention relates to a moving body detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving body in the living room, and a care support system including the moving body detection unit.
  • a detection device for detecting various behaviors of a monitored person such as an elderly person (hereinafter referred to as “subject” in the sense of a detection target) has been proposed in a care facility.
  • the imaging range of an imaging camera that images the floor surface from the ceiling of the subject's room is separated and identified into a plurality of areas (for example, a bed area and a floor area).
  • the detection area determination unit detects the presence and operation of the subject and detects that the subject is in a predetermined state in the predetermined area or over the predetermined area and its adjacent area
  • the determination processing section A notification to that effect is sent to the supervisor.
  • the supervisor can cope with various behavior patterns of the subject. For example, when a long-time stationary state of the subject on the floor is detected and a notification to that effect is given to the supervisor, the supervisor falls on the subject's floor or falls from the bed. Can be dealt with.
  • JP 2001-307246 A (refer to claims 1 and 6, paragraphs [0001], [0030] to [0033], FIG. 1 and the like)
  • FIG. 13A schematically shows a state where the subject Q stands at a position far away on the floor surface 500b from the camera 501 installed in the ceiling 500a of the living room 500, and FIG. An image taken by the camera 501 at that time is shown.
  • FIG. 14A schematically shows a state where the subject Q is falling at a position close to the floor surface 500b from the camera 501 installed in the ceiling portion 500a of the living room 500 (for example, directly below the camera 501).
  • FIG. 14B shows an image taken by the camera 501 at that time.
  • the camera 501 captures the interior of the living room 500 at a wide angle.
  • Patent Document 1 in a configuration in which a subject's fall is detected based on a two-dimensional image and elapsed time from a ceiling-mounted camera, for example, the subject is located far away from the camera in the room. Even when standing and standing still, if the state continues for a long time, it may happen that it is erroneously detected as “falling”, and it is impossible to accurately detect the falling of the subject.
  • a state detection unit that detects the respiratory state of a subject by emitting and receiving radio waves for the purpose of managing the biological information (respiratory state, etc.) of the subject in a nursing facility or a hospital.
  • Devices equipped with Doppler sensors
  • the present invention has been made to solve the above-described problems, and its object is to provide a moving object detection unit capable of accurately detecting a fall of a subject in a living room with a simple configuration, and its To provide a care support system including a motion detection unit.
  • a moving object detection unit is a moving object detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving object in the living room, and acquires an image by photographing the living room.
  • a care support system includes the above-described moving body detection unit and a management server that receives and manages information transmitted from the moving body detection unit.
  • the numerical value range includes the values of the lower limit A and the upper limit B.
  • FIG. 1 is an explanatory diagram showing a schematic configuration of a care support system 1 of the present embodiment.
  • the care support system 1 is a system for supporting the daily life of a cared person living in a care facility or a patient admitted to a hospital (nurse), and is also referred to as a monitoring system.
  • the cared person and the cared person are objects to be supported by the care support system 1, that is, a target person (subject) managed by recognition or detection in the image recognition system 20 or the radio wave detection unit 30 described later.
  • a target person subject
  • the care support system 1 is constructed in a care facility will be described.
  • the staff station 100 is a so-called stuffing station for caregivers who support the lives of the care recipients who spend at the care facilities.
  • the staff station 100 is provided with a management server 100a and a display unit 100b.
  • the management server 100a is a terminal device that is communicably connected to a later-described moving object detection unit 10 installed in the living room 101 via the communication line 200, and includes a central processing unit (CPU; Central Processing Unit). Composed.
  • the communication line 200 is configured by, for example, a wired LAN (Local Area Network), but may be a wireless LAN.
  • the management server 100a receives various types of information (for example, a captured image in the living room 101 and biological information of the care recipient (for example, information indicating a breathing state)) transmitted from the moving object detection unit 10 via the communication line 200. And the received information is displayed on the display unit 100b. Thereby, the caregiver of the care facility can grasp the health status of the care recipient by looking at the information displayed on the display unit 100b.
  • the display unit 100b can be configured by a display of a personal computer, for example.
  • the management server 100a displays the moving object detection unit.
  • At least one living room 101 is provided in a care facility, and FIG. 1 shows a case where two living rooms 101 are provided as an example.
  • one bed 102 used by the care recipient is installed in the living room 101.
  • a plurality of beds 102 corresponding to each of the care recipients are installed.
  • FIG. 2 is an explanatory diagram schematically showing the inside of the living room 101 in which the moving object detection unit 10 is installed.
  • the moving body detection unit 10 is installed on the ceiling portion 101 a of each living room 101 and is communicably connected to a communication line 200.
  • the living room 101 is a multi-bed room in which a plurality of beds 102 are installed, one moving body detection unit 10 is installed for one bed 102.
  • FIG. 3 is a block diagram showing a schematic configuration of the moving object detection unit 10.
  • the moving body detection unit 10 is a unit that detects information of a cared person (subject) as a moving body in the living room 101, and includes an image recognition system 20, a radio wave detection unit 30, and a unit control unit 40. Details of the image recognition system 20 will be described later. Since the moving body detection unit 10 includes various sensors such as the above-described radio wave detection unit 30 and an optical detection unit 23 described later, it is also called a sensor box.
  • the radio wave detection unit 30 is a sensor (state detection unit) that detects the state of the cared person in the living room 101 by radiating and receiving radio waves.
  • the radio wave detection unit 30 is configured by a microwave Doppler sensor for individually detecting biological information of a cared person by radiating and receiving radio waves.
  • the radio wave detection unit 30 includes a radiation unit and a reception unit (not shown). For example, microwaves in a 24 GHz band are radiated toward the bed in each room, and reflected waves that are reflected by the care recipient and are Doppler shifted. Receive. Thereby, the radio wave detection unit 30 can detect the care receiver's breathing state, sleep state, heart rate, and the like as biological information from the received reflected waves.
  • the radio wave detection unit 30 functions as a microscopic motion detection unit that detects microscopic motion of a care recipient (subject).
  • the unit control unit 40 controls the operations of the image recognition system 20 and the radio wave detection unit 30, and performs image processing and signal processing on information obtained from the image recognition system 20 and the radio wave detection unit 30, and results obtained Is a control board that outputs to the management server 100a as information on the status of the care recipient.
  • the unit control unit 40 controls the radiation frequency of the radio wave radiated from the radio wave detection unit 30, and details of this point will be described later.
  • the unit control unit 40 includes a main control unit 41, an information processing unit 42, an interface unit 43, a storage unit 24, and an image recognition unit 25.
  • the storage unit 24 and the image recognition unit 25 are provided in the unit control unit 40 here, but may be provided independently of the unit control unit 40. Details of the storage unit 24 and the image recognition unit 25 will be described later.
  • the main control unit 41 is composed of a CPU that controls the operation of each unit in the moving object detection unit 10.
  • the information processing unit 42 and the image recognition unit 25 may be configured by the above-described CPU (may be integrated with the main control unit 41), or may be another arithmetic unit or a circuit that performs a specific process. It may be configured.
  • the information processing unit 42 performs predetermined processing on information (for example, image data) output from the optical detection unit 23 (to be described later) of the image recognition system 20 and information (for example, data on the respiratory state) output from the radio wave detection unit 30. Signal processing based on the algorithm is performed. Information obtained by the signal processing is used for image recognition in the image recognition system 20 (particularly, the image recognition unit 25).
  • the network cable (not shown) of the communication line 200 is electrically connected to the interface unit 43.
  • Information relating to the status of the cared person detected by the moving object detection unit 10 based on images and microwaves is transmitted to the management server 100a via the interface unit 43 and the communication line 200.
  • the image recognition system 20 includes an illumination unit 21, an illumination control unit 22, and an optical detection unit 23.
  • the illumination unit 21 includes an LED (LightLEDEmitting Diode) that emits infrared light (for example, near-infrared light) to enable photographing in the dark, and is provided at the center of the ceiling 101a of the living room 101. Located to illuminate the interior of the living room 101.
  • the illumination unit 21 has a plurality of LEDs and illuminates a floor surface 101b (see FIG. 2) in the living room 101 and a wall connecting the ceiling portion 101a and the floor surface 101b.
  • the illumination control unit 22 controls illumination (infrared light emission) by the illumination unit 21.
  • the optical detection unit 23 is an imaging unit that captures an image of the interior of the living room 101 under the illumination of the illumination unit 21 and is configured by a camera, for example.
  • FIG. 4 is a block diagram illustrating a detailed configuration of the optical detection unit 23, and FIG. 5 schematically illustrates an example of an image acquired by photographing with the optical detection unit 23.
  • the optical detection unit 23 is disposed adjacent to the illumination unit 21 in the central portion of the ceiling 101a of the living room 101, and acquires an image of an immediately above viewpoint with a viewing direction directly below by photographing.
  • the optical detection unit 23 includes a lens 51, an image sensor 52, an AD (analog / digital) conversion unit 53, an image processing unit 54, and a control calculation unit 55.
  • the lens 51 is, for example, a fixed focus lens, and is configured by a general super wide angle lens or fisheye lens.
  • a lens having a diagonal angle of view of 150 ° or more can be used.
  • the entire living room 101 can be photographed from the ceiling 101 a toward the floor surface 101 b, and the cared person in the living room 101 and the entire room can be photographed without blind spots. It becomes possible.
  • the imaging element 52 is configured by an image sensor such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Metal Oxide Semiconductor).
  • the image sensor 52 is configured by removing the IR cut filter so that the state of the cared person can be detected as an image even in a dark environment.
  • An output signal from the image sensor 52 is input to the AD conversion unit 53.
  • the AD conversion unit 53 receives an analog image signal of an image captured by the image sensor 52 and converts the analog image signal into a digital image signal.
  • the digital image signal output from the AD conversion unit 53 is input to the image processing unit 54.
  • the image processing unit 54 receives the digital image signal output from the AD conversion unit 53 and executes image processing such as black correction, noise correction, color interpolation, and white balance on the digital image signal. .
  • a signal after image processing output from the image processing unit 54 is input to the image recognition unit 25.
  • the control calculation unit 55 executes calculations such as AE (Automatic Exposure) related to the control of the image sensor 52 and controls the image sensor 52 such as exposure time and gain. Moreover, the control calculating part 55 performs control while performing calculations, such as a suitable light quantity setting and light distribution setting, with respect to the illumination part 21, as needed.
  • the control calculation unit 55 may have the function of the illumination control unit 22 described above.
  • the image recognition system 20 described above further includes the storage unit 24 and the image recognition unit 25 described above.
  • the storage unit 24 is a memory that stores a control program executed by the unit control unit 40 and various types of information, and includes, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a nonvolatile memory, and the like.
  • storage part 24 has memorize
  • FIG. The sleeping region R is a region that is used by the care recipient in the living room 101 when sleeping, and more specifically, is a region in which the bed 102 is arranged in the living room 101. In the living room 101, a futon may be arranged instead of the bed 102. In this case, the area where the futon is arranged in the living room 101 is the sleeping area R.
  • the position information of the sleeping region R for example, the position coordinates (planar coordinates) of the sleeping region R when an arbitrary position in the living room 101 is set as the origin in a plane parallel to the floor surface 101b can be considered.
  • the position information of the sleeping region R may be set and input by the management server 100a, transmitted from the management server 100a to the moving object detection unit 10, and stored in the storage unit 24.
  • the image recognition unit 25 performs image recognition processing on the image data of the image acquired by the optical detection unit 23. More specifically, the image recognition unit 25 receives a signal after the image processing unit 54 of the optical detection unit 23 performs image processing, extracts the contour of the object, for example, and shapes it by a method such as pattern matching. An image recognition process for recognizing the image is executed. Thereby, the image recognition part 25 can recognize the state of the cared person in the living room 101.
  • the state of the cared person in the living room 101 is assumed to be rising, getting out of bed, entering the floor, falling over, and the like.
  • These cared person states are distinguished from minute movements (small movements of the body due to breathing, etc.) detected by the radio wave detection unit 30 in that they involve the size movements (body movements) of the cared person's body. Is done.
  • FIG. 6 schematically shows the imaging range of the optical detection unit 23 and the respiration detection range of the radio wave detection unit 30 when the moving object detection unit 10 is installed in the ceiling 101a of the living room 101 different from FIG. ing.
  • the area other than the bed 102 (sleeping area R) in the living room 101 it is necessary to detect the fall of the care recipient.
  • the fall detection based on the photographed image of the optical detector 23 installed on the ceiling the fall cannot be accurately detected when the cared person is far from the moving object detection unit 10 in the living room 101 as described above. is there.
  • the unit controller 40 detects the radio wave detection section. By switching the control of the radiation frequency with respect to 30, the presence or absence of the cared person's fall is detected (determined). The details will be described below.
  • the unit controller 40 controls the radiation frequency of the radio waves radiated from the radio wave detector 30.
  • the control of the radiation frequency there are a control by the first drive mode and a control by the second drive mode.
  • FIG. 7 schematically shows the frequency waveform of the first drive mode
  • FIG. 8 schematically shows the frequency waveform of the second drive mode.
  • the first drive mode is a mode in which the radio wave detection unit 30 is driven without modulation (without modulation) of the radiation frequency of the radio wave radiated from the radio wave detection unit 30. Both the CW (Continuous Wave) mode and the Doppler mode are used. be called.
  • the sensor sensitivity is high and the radio wave detection unit 30 can detect the care recipient's breathing. However, since the distance to the care receiver cannot be measured, the fall detection based on the distance is possible. Can not do.
  • the second drive mode is a mode for driving the radio wave detection unit 30 by modulating the radiation frequency, and is also called FMCW (Frequency-Modulated-Continuous-Wave) mode or distance measurement mode.
  • FMCW Frequency-Modulated-Continuous-Wave
  • the sensor Since the sensitivity is low, the radio wave detection unit 30 cannot detect respiration.
  • the distance D (m) between the radio wave detection unit 30 and the cared person is the frequency difference (beats) between the transmitted wave and the reflected wave. Frequency) and the like.
  • T Transmission time (s)
  • fw frequency sweep width (Hz)
  • the unit control unit 40 can determine whether the care receiver is standing or falling based on the magnitude of the distance D. For example, the height from the floor surface 101b of the living room 101 to the ceiling portion 101a is 2.4 m, the height of the care recipient is 1.65 m, and image recognition based on the image photographed by the optical detection unit 23 is performed. In the case where it is known that the cared person is directly below the moving object detection unit 10, when the distance D obtained by the above formula is 0.70 to 0.80 m, the cared person is It can be determined that the person is standing right below, and if the calculated distance D is 2.2 to 2.3 m, the care recipient can be determined to be in a state of falling right below the moving object detection unit 10. .
  • the distance between the moving object detection unit 10 and the cared person is relatively Since the distance D is relatively large when the cared person is falling, the presence or absence of the cared person can be determined based on the magnitude of the distance D.
  • the unit control unit 40 (particularly the main control unit 41) controls the radiation frequency in the first drive mode and the second drive mode based on the image acquired by the optical detection unit 23. I try to switch.
  • the entire operation of the moving object detection unit 10 including such control will be described.
  • FIG. 10 is a flowchart showing an operation flow in the moving object detection unit 10 of the present embodiment.
  • FIG. 11 schematically shows a state where the cared person P is on the bed 102
  • FIG. 12 schematically shows a state where the cared person P is not on the bed 102 (a state where the cared person P is separated from the bed 102). It shows.
  • the optical detection unit 23 captures an image of the interior of the living room 101 from the ceiling 101a toward the floor 101b (S1).
  • the image recognition unit 25 performs image recognition processing on the image data of the image, and recognizes the position of the care recipient P in the living room 101 (S2).
  • the unit control unit 40 determines the positional relationship between the care receiver P and the bed 102 (sleeping region R) on the image, and determines whether or not the care receiver P is on the bed 102 ( S3).
  • the storage unit 24 stores position information (position coordinates) of the bed 102 in the real space, but the position of the object that actually exists in the living room 101 and the object in the image obtained by photographing the inside of the living room 101. Therefore, the unit control unit 40 determines the position of the bed 102 on the image (the position corresponding to the position information on the image) from the position information stored in the storage unit 24. Can be grasped.
  • the unit control unit 40 drives the radio wave detection unit 30 in the first drive mode in which the radiation frequency is not modulated (see FIG. 11). S4). Thereby, the radio wave detection unit 30 can detect the biological information (for example, the breathing state) of the cared person P on the bed 102.
  • the unit control unit 40 drives the radio wave detection unit 30 in the second drive mode that modulates the radiation frequency. (S5).
  • the radio wave detection unit 30 can measure the distance to the cared person P, and the unit control unit 40 determines whether the cared person P has fallen as described above based on the measured distance. It becomes possible to judge.
  • the unit control unit 40 of the moving object detection unit 10 controls the radiation frequency of the radio wave radiated from the radio wave detection unit 30 based on the image acquired by the optical detection unit 23, and modulates the radiation frequency. Switching between the first driving mode that is not performed and the second driving mode that modulates the radiation frequency. Thereby, the radio wave detection unit 30 can perform respiration detection in the first drive mode and distance measurement in the second drive mode. At this time, the distance measured by the radio wave detection unit 30 is a distance obtained by a predetermined calculation and is substantially equal to the actual distance. Therefore, the unit controller 40 does not depend on the position of the cared person P in the living room 101 (whether the cared person P is close to or far from the moving object detection unit 10 in the living room 101).
  • the presence or absence of a fall can be accurately determined. Moreover, since the radio wave detection unit 30 that detects the breathing state of the cared person P is used for the fall detection, there is no need to separately provide a sensor dedicated to the fall detection, and the apparatus (moving object detection unit 10) With a simple configuration (using the existing configuration effectively), the fall of the care recipient P can be accurately detected.
  • the unit controller 40 determines the positional relationship between the position of the care recipient P and the bed 102 (sleeping region R) in the living room 101 based on the image acquired by the optical detector 23.
  • the control of the radiation frequency is switched according to the positional relationship. This makes it possible to reliably detect information to be detected (biological information or falls) depending on whether the care receiver P is on the bed 102 or not. That is, when the cared person P is on the bed 102, the control of the radiation frequency can be switched to the first drive mode to perform respiration detection. When the cared person P is not on the bed 102, the radiation is emitted.
  • the frequency control can be switched to the second drive mode to perform distance measurement and fall detection.
  • the unit control unit 40 uses the image recognition unit 25 on the image acquired by the optical detection unit 23. Based on the recognized position of the cared person P and the position of the bed 102 corresponding to the position information stored in the storage unit 24 and the image on the image, the positional relationship between the cared person P and the bed 102 (cared Whether the person P is on the bed 102 or not).
  • the unit controller 40 switches the control of the radiation frequency depending on whether or not the radiation frequency is modulated.
  • the radio wave detection unit 30 can detect the respiratory state of the care receiver P.
  • the unit control unit 40 can determine the care receiver based on the measured distance. It is possible to detect whether or not P has fallen.
  • the unit control unit 40 switches the control of the radiation frequency between the first drive mode and the second drive mode according to the positional relationship between the position of the care recipient P and the bed 102.
  • the radio wave detection unit 30 can detect the breathing state of the cared person P in the first drive mode and can measure the distance from the cared person P in the second drive mode. Therefore, the unit controller 40 can detect whether the care receiver P has fallen based on the distance measured in the second drive mode.
  • the care support system 1 of the present embodiment includes a moving body detection unit 10 and a management server 100a that receives and manages information transmitted from the moving body detection unit 10. Even in such a system, since the moving object detection unit 10 described above is included, a care receiver P is not provided regardless of the position of the care receiver P in the living room 101 without separately providing a sensor dedicated to fall detection. The effect of this embodiment that the presence / absence of falling can be detected with high accuracy can be obtained.
  • the unit control unit 40 may measure the distance from the care recipient and detect (determine) the presence or absence of a fall.
  • the moving object detection unit and the care support system of the present embodiment described above can be expressed as follows, and it can be said that the following effects can be obtained.
  • the moving body detection unit of the present embodiment is a moving body detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving body in the living room, and acquires an image by photographing the living room.
  • a state detection unit that detects the state of the subject by radiation and reception of radio waves, and a unit control unit that controls a radiation frequency of radio waves radiated from the state detection unit, the unit control unit includes: The control of the radiation frequency is switched based on the image acquired by the optical detection unit.
  • the optical detection unit included in the moving body detection unit images the room from the ceiling of the living room toward the floor.
  • the unit control unit switches the control of the radiation frequency of the radio wave radiated from the state detection unit based on the image acquired by the optical detection unit.
  • the state detection unit in the drive mode in which the radiation frequency is not modulated.
  • the state detection unit can be driven in a driving mode in which the radiation frequency is modulated.
  • the state detection unit can detect the biological information (for example, respiratory state) of the subject by radiating and receiving radio waves.
  • the state detection unit can measure the distance between the state detection unit (moving object detection unit) and the subject by radiating and receiving radio waves. Based on the measured distance, the unit control unit clearly distinguishes whether the subject is standing on the floor or whether the subject is standing or falling. can do.
  • the unit control unit switches the control of the radiation frequency based on the image acquired by the optical detection unit, so that the fall of the subject can be performed regardless of the position of the subject in the room. Presence / absence can be detected (judged) with high accuracy.
  • the same state detection unit can be used to detect the patient's biological information and falls, there is no need to provide a separate sensor dedicated to fall detection, and the fall of the subject can be accurately performed with a simple configuration. Can be detected.
  • the unit control unit determines the positional relationship between the position of the subject in the living room and the sleeping area where the bed or the futon is arranged in the living room based on the image, and according to the determined positional relationship
  • the control of the radiation frequency may be switched.
  • the unit control unit switches the control of the radiation frequency according to the positional relationship between the subject and the sleeping area in the room, Information to be detected (biological information or the presence or absence of a fall) can be reliably detected.
  • the moving body detection unit includes an image recognition unit that recognizes the position of the subject by performing an image recognition process on the image, and a storage unit that stores in advance the position information of the sleeping region in the living room.
  • the unit control unit further includes a position of the subject recognized by the image recognition unit, a position corresponding to the position information of the sleeping region stored in the storage unit and a position on the image. Based on this, the positional relationship may be determined.
  • the unit control unit Since the position information of the sleeping region is stored in the storage unit in advance, the unit control unit stores the position information corresponding to the stored sleeping region position information on the image and the subject recognized by the image recognition unit. Based on the position, the positional relationship between the subject and the sleeping area in the living room can be reliably determined.
  • the unit control unit may switch the control of the radiation frequency depending on whether or not the radiation frequency is modulated.
  • the state detection unit can detect the biological information of the subject by emitting and receiving radio waves.
  • the state detection unit can measure the distance between the state detection unit and the subject by radiating and receiving radio waves. As a result, the unit control unit can detect (determine) whether or not the subject has fallen based on the measured distance.
  • the unit control unit modulates the radiation frequency according to the positional relationship between the position of the subject and the sleeping area, the first drive mode in which the radiation frequency is not modulated, and the radiation frequency is modulated.
  • the second driving mode may be switched.
  • the unit control unit switches the control of the radiation frequency between the first drive mode and the second drive mode in accordance with the positional relationship, so that the state detection unit can detect the subject in the first drive mode.
  • the biological information can be detected, and the distance between the state detection unit and the subject can be measured in the second drive mode.
  • the unit control unit can detect (determine) whether or not the subject has fallen based on the distance measured in the second drive mode.
  • the care support system of the present embodiment includes the above-described moving body detection unit and a management server that receives and manages information transmitted from the moving body detection unit.
  • the above-described effects can be obtained in the care support system including the moving object detection unit and the management server.
  • the present invention can be used for a care support system that supports the daily life of a subject such as a care recipient in a living room.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physiology (AREA)
  • Dentistry (AREA)
  • Alarm Systems (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Analysis (AREA)

Abstract

A moving body detection unit is installed in a ceiling portion of a living space, and detects information about a subject as a moving body in the living space. The moving body detection unit is provided with an optical detection section that photographs the interior of the living space to acquire an image, a state detection section that detects the state of the subject by emitting and receiving radio waves, and a unit control section that controls the emission frequency of radio waves emitted from the state detection section. The unit control section switches control of the emission frequency on the basis of the image acquired by the optical detection section (S1 to S5).

Description

動体検知ユニットおよびケアサポートシステムMotion detection unit and care support system
　本発明は、居室の天井部に設置され、居室内の動体としての被検者の情報を検知する動体検知ユニットと、その動体検知ユニットを含むケアサポートシステムとに関するものである。 The present invention relates to a moving body detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving body in the living room, and a care support system including the moving body detection unit.
　従来から、介護施設において、老人などの被監視者（以下、検知対象という意味で「被検者」と称する）の各種行動を検知するための検知装置が提案されている。例えば、特許文献１の検知装置では、被検者の居室の天井部から床面を撮像する撮像カメラの撮像範囲を複数の領域（例えばベッド領域、床領域）に分離識別し、各領域での被検者の存在および動作を検知領域判断部にて検知し、所定の領域で、もしくは所定の領域とその隣接領域にわたって、被検者が所定の状態にあることを検知すると、判定処理部が監視者側へその旨の発報を行うようにしている。これにより、監視者は、被検者の様々な行動パターンに対処することが可能となる。例えば、床面上での被検者の長時間の静止が検知され、その旨が監視者側に発報されると、監視者は被検者の床面上での転倒やベッドからの転落に対して対処することが可能となる。 2. Description of the Related Art Conventionally, a detection device for detecting various behaviors of a monitored person such as an elderly person (hereinafter referred to as “subject” in the sense of a detection target) has been proposed in a care facility. For example, in the detection apparatus of Patent Document 1, the imaging range of an imaging camera that images the floor surface from the ceiling of the subject's room is separated and identified into a plurality of areas (for example, a bed area and a floor area). When the detection area determination unit detects the presence and operation of the subject and detects that the subject is in a predetermined state in the predetermined area or over the predetermined area and its adjacent area, the determination processing section A notification to that effect is sent to the supervisor. As a result, the supervisor can cope with various behavior patterns of the subject. For example, when a long-time stationary state of the subject on the floor is detected and a notification to that effect is given to the supervisor, the supervisor falls on the subject's floor or falls from the bed. Can be dealt with.
特開２００１－３０７２４６号公報（請求項１、６、段落〔０００１〕、〔００３０〕～〔００３３〕、図１等参照）JP 2001-307246 A (refer to claims 1 and 6, paragraphs [0001], [0030] to [0033], FIG. 1 and the like)
　ところで、図１３Ａは、居室５００の天井部５００ａに設置したカメラ５０１から床面５００ｂ上で遠く離れた位置において、被検者Ｑが立っている状態を模式的に示しており、図１３Ｂは、そのときのカメラ５０１で撮影した画像を示している。また、図１４Ａは、居室５００の天井部５００ａに設置したカメラ５０１から床面５００ｂ上で近い位置（例えばカメラ５０１の真下）において、被検者Ｑが転倒している状態を模式的に示しており、図１４Ｂは、そのときのカメラ５０１で撮影した画像を示している。天井部５００ａにカメラ５０１を設置して居室５００内を監視するシステムでは、カメラ５０１が居室５００内を広角で撮影するため、撮影画像の周辺部の歪みが大きくなる。このため、図１３Ｂおよび図１４Ｂを比べて分かるように、カメラ５０１から遠距離の位置で立っている被検者Ｑと、カメラ５０１から近距離の位置で転倒している被検者Ｑとが、画像上で同じように見え、これらを画像認識によって区別することが困難となる。 Incidentally, FIG. 13A schematically shows a state where the subject Q stands at a position far away on the floor surface 500b from the camera 501 installed in the ceiling 500a of the living room 500, and FIG. An image taken by the camera 501 at that time is shown. FIG. 14A schematically shows a state where the subject Q is falling at a position close to the floor surface 500b from the camera 501 installed in the ceiling portion 500a of the living room 500 (for example, directly below the camera 501). FIG. 14B shows an image taken by the camera 501 at that time. In a system in which the camera 501 is installed on the ceiling 500a and the interior of the living room 500 is monitored, the camera 501 captures the interior of the living room 500 at a wide angle. Therefore, as can be seen by comparing FIG. 13B and FIG. 14B, the subject Q standing at a position far from the camera 501 and the subject Q falling at a position near the camera 501 fall. They look the same on the image, making it difficult to distinguish them by image recognition.
　したがって、特許文献１のように、天井設置のカメラによる２次元画像と経過時間とに基づいて被検者の転倒を検知する構成では、例えば、居室内でカメラから遠く離れた位置で被検者が立って静止している状態でも、その状態が長時間続くと、「転倒」と誤検知される場合が起こり得ることになり、被検者の転倒を精度よく検知することができなくなる。 Therefore, as in Patent Document 1, in a configuration in which a subject's fall is detected based on a two-dimensional image and elapsed time from a ceiling-mounted camera, for example, the subject is located far away from the camera in the room. Even when standing and standing still, if the state continues for a long time, it may happen that it is erroneously detected as “falling”, and it is impossible to accurately detect the falling of the subject.
　また、近年では、介護施設や病院などにおいて、被検者の生体情報（呼吸状態など）を管理することを目的として、電波の放射および受信によって、被検者の呼吸状態を検知する状態検知部（ドップラーセンサ）を備えた装置が利用されつつある。居室内での被検者の転倒を精度よく検知するにあたって、このような状態検知部を利用することができれば、転倒検知専用のセンサを別途設ける必要がなく、装置の簡単な構成で被検者の転倒を検知できるため、望ましい。 In recent years, a state detection unit that detects the respiratory state of a subject by emitting and receiving radio waves for the purpose of managing the biological information (respiratory state, etc.) of the subject in a nursing facility or a hospital. Devices equipped with (Doppler sensors) are being used. If such a state detection unit can be used to accurately detect the fall of the subject in the room, there is no need to provide a separate sensor dedicated to fall detection, and the subject can be configured with a simple configuration of the apparatus. It is desirable because it can detect the fall of
　本発明は、上記の問題点を解決するためになされたもので、その目的は、簡単な構成で、居室内での被検者の転倒を精度よく検知することができる動体検知ユニットと、その動体検知ユニットを含むケアサポートシステムとを提供することにある。 The present invention has been made to solve the above-described problems, and its object is to provide a moving object detection unit capable of accurately detecting a fall of a subject in a living room with a simple configuration, and its To provide a care support system including a motion detection unit.
　本発明の一側面に係る動体検知ユニットは、居室の天井部に設置され、居室内の動体としての被検者の情報を検知する動体検知ユニットであって、居室内を撮影して画像を取得する光学検出部と、電波の放射および受信によって、被検者の状態を検知する状態検知部と、前記状態検知部から放射される電波の放射周波数を制御するユニット制御部とを備え、前記ユニット制御部は、前記光学検出部にて取得された前記画像に基づいて、前記放射周波数の制御を切り替える。 A moving object detection unit according to an aspect of the present invention is a moving object detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving object in the living room, and acquires an image by photographing the living room. An optical detection unit, a state detection unit that detects the state of the subject by radiation and reception of radio waves, and a unit control unit that controls a radiation frequency of radio waves radiated from the state detection unit, A control part switches control of the said radiation frequency based on the said image acquired in the said optical detection part.
　本発明の他の側面に係るケアサポートシステムは、上述した動体検知ユニットと、前記動体検知ユニットから送信される情報を受信して管理する管理サーバーとを含む。 A care support system according to another aspect of the present invention includes the above-described moving body detection unit and a management server that receives and manages information transmitted from the moving body detection unit.
　上記の構成によれば、簡単な構成で、居室内での被検者の位置によらずに、被検者の転倒の有無を精度よく検知（判断）することができる。 According to the above configuration, it is possible to accurately detect (determine) whether or not the subject has fallen with a simple configuration regardless of the position of the subject in the room.
本発明の実施の一形態に係るケアサポートシステムの概略の構成を示す説明図である。It is explanatory drawing which shows the structure of the outline of the care support system which concerns on one Embodiment of this invention. 上記ケアサポートシステムの動体検知ユニットが設置された居室内の様子を模式的に示す説明図である。It is explanatory drawing which shows typically the mode in the living room where the moving body detection unit of the said care support system was installed. 上記動体検知ユニットの概略の構成を示すブロック図である。It is a block diagram which shows the schematic structure of the said moving body detection unit. 上記動体検知ユニットが有する光学検出部の詳細な構成を示すブロック図である。It is a block diagram which shows the detailed structure of the optical detection part which the said moving body detection unit has. 上記光学検出部での撮影によって取得された画像の一例を模式的に示す説明図である。It is explanatory drawing which shows typically an example of the image acquired by imaging | photography with the said optical detection part. 上記光学検出部の撮影範囲と、電波検出部の呼吸検知範囲とを模式的に示す説明図である。It is explanatory drawing which shows typically the imaging | photography range of the said optical detection part, and the respiration detection range of an electromagnetic wave detection part. 第１の駆動モードの周波数の波形を模式的に示す説明図である。It is explanatory drawing which shows typically the waveform of the frequency of a 1st drive mode. 第２の駆動モードの周波数の波形を模式的に示す説明図である。It is explanatory drawing which shows typically the waveform of the frequency of a 2nd drive mode. 上記第２の駆動モードにおける送信波および反射波の一例を示す説明図である。It is explanatory drawing which shows an example of the transmission wave in the said 2nd drive mode, and a reflected wave. 上記動体検知ユニットにおける動作の流れを示すフローチャートである。It is a flowchart which shows the flow of operation | movement in the said moving body detection unit. 被介護者がベッド上にいる状態を模式的に示す説明図である。It is explanatory drawing which shows typically the state where a cared person is on the bed. 被介護者がベッド上にいない状態を模式的に示す説明図である。It is explanatory drawing which shows typically the state where a cared person is not on the bed. 居室の天井部に設置したカメラから床面上で遠く離れた位置において、被検者が立っている状態を模式的に示す説明図である。It is explanatory drawing which shows typically the state in which the subject is standing in the position far away on the floor surface from the camera installed in the ceiling part of the living room. 上記カメラで被検者を撮影した画像を示す説明図である。It is explanatory drawing which shows the image which image | photographed the subject with the said camera. 上記カメラから床面上で近い位置において、被検者が転倒している状態を模式的に示す説明図である。It is explanatory drawing which shows typically the state in which the subject has fallen in the position near on the floor surface from the said camera. 上記カメラで被検者を撮影した画像を示す説明図である。It is explanatory drawing which shows the image which image | photographed the subject with the said camera.
　本発明の実施の一形態について、図面に基づいて説明すれば、以下の通りである。なお、本明細書において、数値範囲をＡ～Ｂと表記した場合、その数値範囲に下限Ａおよび上限Ｂの値は含まれるものとする。 An embodiment of the present invention will be described below with reference to the drawings. In this specification, when the numerical range is expressed as A to B, the numerical value range includes the values of the lower limit A and the upper limit B.
　〔ケアサポートシステム〕
　図１は、本実施形態のケアサポートシステム１の概略の構成を示す説明図である。ケアサポートシステム１は、介護施設に入居している被介護者や、病院に入院している患者（被看護者）の日常の生活を支援するためのシステムであり、見守りシステムとも呼ばれている。被介護者および被看護者は、ケアサポートシステム１による支援の対象、つまり、後述する画像認識システム２０や電波検出部３０での認識や検出等によって管理される対象者（被検者）である。ここでは、例として、ケアサポートシステム１が介護施設内で構築されている場合について説明する。 [Care Support System]
FIG. 1 is an explanatory diagram showing a schematic configuration of a care support system 1 of the present embodiment. The care support system 1 is a system for supporting the daily life of a cared person living in a care facility or a patient admitted to a hospital (nurse), and is also referred to as a monitoring system. . The cared person and the cared person are objects to be supported by the care support system 1, that is, a target person (subject) managed by recognition or detection in the image recognition system 20 or the radio wave detection unit 30 described later. . Here, as an example, a case where the care support system 1 is constructed in a care facility will be described.
　介護施設には、スタッフステーション１００および居室１０１が設けられている。スタッフステーション１００は、介護施設で過ごす被介護者の生活をサポートする介護者のいわゆる詰め所である。このスタッフステーション１００には、管理サーバー１００ａおよび表示部１００ｂが設けられている。管理サーバー１００ａは、通信回線２００を介して、居室１０１に設置される後述の動体検知ユニット１０と通信可能に接続される端末装置であり、中央演算処理装置（ＣＰＵ；Central Processing Unit）を含んで構成される。なお、通信回線２００は、例えば有線ＬＡＮ（Local Area Network）で構成されるが、無線ＬＡＮであっても勿論構わない。 In the nursing facility, a staff station 100 and a living room 101 are provided. The staff station 100 is a so-called stuffing station for caregivers who support the lives of the care recipients who spend at the care facilities. The staff station 100 is provided with a management server 100a and a display unit 100b. The management server 100a is a terminal device that is communicably connected to a later-described moving object detection unit 10 installed in the living room 101 via the communication line 200, and includes a central processing unit (CPU; Central Processing Unit). Composed. The communication line 200 is configured by, for example, a wired LAN (Local Area Network), but may be a wireless LAN.
　管理サーバー１００ａは、通信回線２００を介して、動体検知ユニット１０から送信される各種の情報（例えば居室１０１内の撮影画像や被介護者の生体情報（例えば呼吸状態を示す情報））を受信して管理するとともに、受信した情報を表示部１００ｂに表示する処理を行う。これにより、介護施設の介護者は、表示部１００ｂに表示された情報を見て、被介護者の健康状態等を把握することができる。表示部１００ｂは、例えばパーソナルコンピュータのディスプレイで構成することができる。また、後述する画像認識システム２０での画像認識処理により、被介護者が床面に転倒するなど、被介護者の動作が異常であることが認識されたときには、管理サーバー１００ａは、動体検知ユニット１０からその旨の情報を受信して、動体検知ユニット１０の光学検出部２３で取得される居室１０１内の撮影画像のデータを、介護者が所有する携帯端末に送信し、被介護者の異常を介護者に知らせることも可能である。なお、動体検知ユニット１０から管理サーバー１００ａへの画像データの送信時、および管理サーバー１００ａから上記携帯端末への画像データの送信時には、画像の容量、サイズ、解像度などが適宜調整される。 The management server 100a receives various types of information (for example, a captured image in the living room 101 and biological information of the care recipient (for example, information indicating a breathing state)) transmitted from the moving object detection unit 10 via the communication line 200. And the received information is displayed on the display unit 100b. Thereby, the caregiver of the care facility can grasp the health status of the care recipient by looking at the information displayed on the display unit 100b. The display unit 100b can be configured by a display of a personal computer, for example. In addition, when it is recognized that the care receiver's operation is abnormal, such as the care receiver falls down on the floor surface, by the image recognition process in the image recognition system 20 described later, the management server 100a displays the moving object detection unit. 10 is transmitted to the mobile terminal owned by the caregiver and the data of the captured image in the living room 101 acquired by the optical detection unit 23 of the moving object detection unit 10 is received. It is also possible to inform the caregiver. Note that, when image data is transmitted from the moving body detection unit 10 to the management server 100a and when image data is transmitted from the management server 100a to the portable terminal, the capacity, size, resolution, and the like of the image are appropriately adjusted.
　居室１０１は、介護施設において少なくとも１つ設けられており、図１では例として居室１０１が２つ設けられている場合を示している。居室１０１内には、被介護者が使用するベッド１０２が１つ設置されている。なお、１つの居室１０１内に被介護者が二人以上入居する場合、被介護者の各々に対応する複数のベッド１０２が設置される。 At least one living room 101 is provided in a care facility, and FIG. 1 shows a case where two living rooms 101 are provided as an example. In the living room 101, one bed 102 used by the care recipient is installed. In addition, when two or more care recipients move in one living room 101, a plurality of beds 102 corresponding to each of the care recipients are installed.
　図２は、動体検知ユニット１０が設置された居室１０１内の様子を模式的に示す説明図である。図１および図２に示すように、動体検知ユニット１０は、各居室１０１の天井部１０１ａに設置され、通信回線２００と通信可能に接続されている。居室１０１が複数のベッド１０２が設置された多床室である場合、動体検知ユニット１０は、１つのベッド１０２に対して１つ設置される。 FIG. 2 is an explanatory diagram schematically showing the inside of the living room 101 in which the moving object detection unit 10 is installed. As shown in FIGS. 1 and 2, the moving body detection unit 10 is installed on the ceiling portion 101 a of each living room 101 and is communicably connected to a communication line 200. When the living room 101 is a multi-bed room in which a plurality of beds 102 are installed, one moving body detection unit 10 is installed for one bed 102.
　〔動体検知ユニット〕
　次に、上記した動体検知ユニット１０の詳細について説明する。図３は、動体検知ユニット１０の概略の構成を示すブロック図である。動体検知ユニット１０は、居室１０１内の動体としての被介護者（被検者）の情報を検知するユニットであり、画像認識システム２０、電波検出部３０およびユニット制御部４０を備えている。なお、画像認識システム２０の詳細については後述する。動体検知ユニット１０は、上記の電波検出部３０をはじめ、後述する光学検出部２３など、種々のセンサを備えていることから、センサボックスとも呼ばれる。 [Motion detection unit]
Next, the details of the moving object detection unit 10 will be described. FIG. 3 is a block diagram showing a schematic configuration of the moving object detection unit 10. The moving body detection unit 10 is a unit that detects information of a cared person (subject) as a moving body in the living room 101, and includes an image recognition system 20, a radio wave detection unit 30, and a unit control unit 40. Details of the image recognition system 20 will be described later. Since the moving body detection unit 10 includes various sensors such as the above-described radio wave detection unit 30 and an optical detection unit 23 described later, it is also called a sensor box.
　電波検出部３０は、電波の放射および受信によって、居室１０１内での被介護者の状態を検知するセンサ（状態検知部）である。本実施形態では、電波検出部３０は、電波を放射および受信して被介護者の生体情報を個別に検出するためのマイクロ波ドップラーセンサによって構成される。電波検出部３０は、不図示の放射部および受信部を備えており、例えば２４ＧＨｚ帯のマイクロ波を各居室のベッドに向けて放射し、被介護者にて反射してドップラーシフトした反射波を受信する。これにより、電波検出部３０は、受信した反射波から被介護者の呼吸状態や睡眠状態、心拍数などを生体情報として検出することができる。 The radio wave detection unit 30 is a sensor (state detection unit) that detects the state of the cared person in the living room 101 by radiating and receiving radio waves. In the present embodiment, the radio wave detection unit 30 is configured by a microwave Doppler sensor for individually detecting biological information of a cared person by radiating and receiving radio waves. The radio wave detection unit 30 includes a radiation unit and a reception unit (not shown). For example, microwaves in a 24 GHz band are radiated toward the bed in each room, and reflected waves that are reflected by the care recipient and are Doppler shifted. Receive. Thereby, the radio wave detection unit 30 can detect the care receiver's breathing state, sleep state, heart rate, and the like as biological information from the received reflected waves.
　なお、被介護者が呼吸しているとき（睡眠中も含む）、被介護者の呼吸による体の微小な動き（微体動）が生じる。このため、被介護者の呼吸状態や睡眠状態を検出することは、被介護者の微体動を検出するのと同じである。このことから、電波検出部３０は、被介護者（被検者）の微体動を検出する微体動検出部として機能しているとも言うことができる。 In addition, when the cared person is breathing (including during sleep), minute movements of the body due to the cared person's breathing (micromotion) occur. For this reason, detecting the care recipient's breathing state and sleep state is the same as detecting the care receiver's micromotion. From this, it can also be said that the radio wave detection unit 30 functions as a microscopic motion detection unit that detects microscopic motion of a care recipient (subject).
　ユニット制御部４０は、画像認識システム２０および電波検出部３０の動作を制御するとともに、画像認識システム２０および電波検出部３０から得た情報に対して画像処理や信号処理を行い、得られた結果を被介護者の状態に関する情報として管理サーバー１００ａに出力する制御基板である。また、ユニット制御部４０は、電波検出部３０から放射される電波の放射周波数を制御するが、この点の詳細については後述する。 The unit control unit 40 controls the operations of the image recognition system 20 and the radio wave detection unit 30, and performs image processing and signal processing on information obtained from the image recognition system 20 and the radio wave detection unit 30, and results obtained Is a control board that outputs to the management server 100a as information on the status of the care recipient. The unit control unit 40 controls the radiation frequency of the radio wave radiated from the radio wave detection unit 30, and details of this point will be described later.
　ユニット制御部４０は、主制御部４１、情報処理部４２、インターフェース部４３、記憶部２４および画像認識部２５を備えている。記憶部２４および画像認識部２５は、ここではユニット制御部４０に設けられているが、ユニット制御部４０とは独立して設けられていてもよい。なお、記憶部２４および画像認識部２５の詳細については後述する。 The unit control unit 40 includes a main control unit 41, an information processing unit 42, an interface unit 43, a storage unit 24, and an image recognition unit 25. The storage unit 24 and the image recognition unit 25 are provided in the unit control unit 40 here, but may be provided independently of the unit control unit 40. Details of the storage unit 24 and the image recognition unit 25 will be described later.
　主制御部４１は、動体検知ユニット１０内の各部の動作を制御するＣＰＵで構成されている。情報処理部４２および画像認識部２５は、上記のＣＰＵで構成されてもよいし（主制御部４１と一体化されていてもよいし）、他の演算部や、特定の処理を行う回路で構成されてもよい。 The main control unit 41 is composed of a CPU that controls the operation of each unit in the moving object detection unit 10. The information processing unit 42 and the image recognition unit 25 may be configured by the above-described CPU (may be integrated with the main control unit 41), or may be another arithmetic unit or a circuit that performs a specific process. It may be configured.
　情報処理部４２は、画像認識システム２０の後述する光学検出部２３から出力される情報（例えば画像データ）や、電波検出部３０から出力される情報（例えば呼吸状態に関するデータ）に対して、所定のアルゴリズムに基づいた信号処理を行う。信号処理によって得られた情報は、画像認識システム２０（特に画像認識部２５）での画像認識に利用される。 The information processing unit 42 performs predetermined processing on information (for example, image data) output from the optical detection unit 23 (to be described later) of the image recognition system 20 and information (for example, data on the respiratory state) output from the radio wave detection unit 30. Signal processing based on the algorithm is performed. Information obtained by the signal processing is used for image recognition in the image recognition system 20 (particularly, the image recognition unit 25).
　インターフェース部４３には、通信回線２００のネットワークケーブル（不図示）が電気的に接続される。画像やマイクロ波に基づいて動体検知ユニット１０が検出した被介護者の状態に関する情報は、インターフェース部４３および通信回線２００を介して管理サーバー１００ａに送信される。 The network cable (not shown) of the communication line 200 is electrically connected to the interface unit 43. Information relating to the status of the cared person detected by the moving object detection unit 10 based on images and microwaves is transmitted to the management server 100a via the interface unit 43 and the communication line 200.
　次に、画像認識システム２０の詳細について説明する。画像認識システム２０は、照明部２１、照明制御部２２および光学検出部２３を備えている。 Next, details of the image recognition system 20 will be described. The image recognition system 20 includes an illumination unit 21, an illumination control unit 22, and an optical detection unit 23.
　照明部２１は、暗闇での撮影を可能にすべく、赤外線（例えば近赤外光）を発光するＬＥＤ（Light Emitting Diode）を含んで構成されており、居室１０１の天井部１０１ａの中央部に位置して、居室１０１内を照明する。例えば、照明部２１は、複数のＬＥＤを有しており、居室１０１内の床面１０１ｂ（図２参照）や、天井部１０１ａと床面１０１ｂとをつなぐ壁を照明する。照明部２１による照明（赤外線の発光）の制御は、照明制御部２２によって行われる。 The illumination unit 21 includes an LED (LightＬＥＤEmitting Diode) that emits infrared light (for example, near-infrared light) to enable photographing in the dark, and is provided at the center of the ceiling 101a of the living room 101. Located to illuminate the interior of the living room 101. For example, the illumination unit 21 has a plurality of LEDs and illuminates a floor surface 101b (see FIG. 2) in the living room 101 and a wall connecting the ceiling portion 101a and the floor surface 101b. The illumination control unit 22 controls illumination (infrared light emission) by the illumination unit 21.
　光学検出部２３は、照明部２１の照明のもとで居室１０１内を撮影して画像を取得する撮像部であり、例えばカメラで構成される。図４は、光学検出部２３の詳細な構成を示すブロック図であり、図５は、光学検出部２３での撮影によって取得された画像の一例を模式的に示している。光学検出部２３は、居室１０１の天井部１０１ａの中央部に、照明部２１と隣接して配置されており、撮影によって視野方向が直下である直上視点の画像を取得する。この光学検出部２３は、レンズ５１、撮像素子５２、ＡＤ（analog/digital）変換部５３、画像処理部５４および制御演算部５５を備えている。 The optical detection unit 23 is an imaging unit that captures an image of the interior of the living room 101 under the illumination of the illumination unit 21 and is configured by a camera, for example. FIG. 4 is a block diagram illustrating a detailed configuration of the optical detection unit 23, and FIG. 5 schematically illustrates an example of an image acquired by photographing with the optical detection unit 23. The optical detection unit 23 is disposed adjacent to the illumination unit 21 in the central portion of the ceiling 101a of the living room 101, and acquires an image of an immediately above viewpoint with a viewing direction directly below by photographing. The optical detection unit 23 includes a lens 51, an image sensor 52, an AD (analog / digital) conversion unit 53, an image processing unit 54, and a control calculation unit 55.
　レンズ５１は、例えば固定焦点レンズであり、一般的な超広角レンズや魚眼レンズで構成されている。超広角レンズとしては、対角画角が１５０°以上のレンズを用いることができる。これにより、図５で示したように、天井部１０１ａから床面１０１ｂに向かって居室１０１の全体を撮影することが可能となり、居室１０１内の被介護者と部屋全体とを死角レスで撮影することが可能となる。 The lens 51 is, for example, a fixed focus lens, and is configured by a general super wide angle lens or fisheye lens. As the super wide angle lens, a lens having a diagonal angle of view of 150 ° or more can be used. As a result, as shown in FIG. 5, the entire living room 101 can be photographed from the ceiling 101 a toward the floor surface 101 b, and the cared person in the living room 101 and the entire room can be photographed without blind spots. It becomes possible.
　撮像素子５２は、例えばＣＣＤ（Charge Coupled Device）やＣＭＯＳ（Complementary Metal Oxide Semiconductor）といったイメージセンサで構成されている。撮像素子５２は、真っ暗な環境でも被介護者の状態が画像として検出できるように、ＩＲカットフィルタを除去して構成されている。撮像素子５２からの出力信号は、ＡＤ変換部５３に入力される。 The imaging element 52 is configured by an image sensor such as a CCD (Charge Coupled Device) or CMOS (Complementary Metal Metal Oxide Semiconductor). The image sensor 52 is configured by removing the IR cut filter so that the state of the cared person can be detected as an image even in a dark environment. An output signal from the image sensor 52 is input to the AD conversion unit 53.
　ＡＤ変換部５３は、撮像素子５２によって撮像された画像のアナログの画像信号を受信し、そのアナログの画像信号をデジタルの画像信号に変換する。ＡＤ変換部５３から出力されるデジタルの画像信号は、画像処理部５４に入力される。 The AD conversion unit 53 receives an analog image signal of an image captured by the image sensor 52 and converts the analog image signal into a digital image signal. The digital image signal output from the AD conversion unit 53 is input to the image processing unit 54.
　画像処理部５４は、ＡＤ変換部５３から出力されるデジタルの画像信号を受信し、そのデジタルの画像信号に対して、例えば黒補正、ノイズ補正、色補間、ホワイトバランスなどの画像処理を実行する。画像処理部５４から出力される画像処理後の信号は、画像認識部２５に入力される。 The image processing unit 54 receives the digital image signal output from the AD conversion unit 53 and executes image processing such as black correction, noise correction, color interpolation, and white balance on the digital image signal. . A signal after image processing output from the image processing unit 54 is input to the image recognition unit 25.
　制御演算部５５は、撮像素子５２の制御に関する例えばＡＥ（Automatic Exposure）などの演算を実行するとともに、撮像素子５２に対して露光時間やゲインなどの制御を実行する。また、制御演算部５５は、必要に応じて、照明部２１に対して好適な光量設定や配光設定などの演算を実行するとともに、制御を実行する。なお、制御演算部５５に、上述の照明制御部２２の機能を持たせるようにしてもよい。 The control calculation unit 55 executes calculations such as AE (Automatic Exposure) related to the control of the image sensor 52 and controls the image sensor 52 such as exposure time and gain. Moreover, the control calculating part 55 performs control while performing calculations, such as a suitable light quantity setting and light distribution setting, with respect to the illumination part 21, as needed. The control calculation unit 55 may have the function of the illumination control unit 22 described above.
　上記した画像認識システム２０は、さらに、上述した記憶部２４および画像認識部２５を備えている。 The image recognition system 20 described above further includes the storage unit 24 and the image recognition unit 25 described above.
　記憶部２４は、ユニット制御部４０が実行する制御プログラムや各種の情報を記憶するメモリであり、例えばＲＡＭ（Random Access Memory）、ＲＯＭ（Read Only Memory）、不揮発性メモリなどで構成されている。 The storage unit 24 is a memory that stores a control program executed by the unit control unit 40 and various types of information, and includes, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a nonvolatile memory, and the like.
　また、本実施形態では、記憶部２４は、居室１０１内の就寝領域Ｒ（図６参照）の位置情報を予め記憶している。なお、就寝領域Ｒとは、居室１０１内で被介護者が就寝時に利用する領域であり、より具体的には、居室１０１内でベッド１０２が配置される領域である。居室１０１内には、ベッド１０２の代わりに布団が配置されてもよいが、この場合、居室１０１内で布団が配置される領域が就寝領域Ｒとなる。就寝領域Ｒの位置情報としては、例えば、床面１０１ｂに平行な面内で、居室１０１内の任意の位置を原点としたときの就寝領域Ｒの位置座標（平面座標）を考えることができる。なお、就寝領域Ｒの位置情報は、管理サーバー１００ａにて設定入力され、管理サーバー１００ａから動体検知ユニット１０に送信されて記憶部２４に記憶されてもよい。 Moreover, in this embodiment, the memory | storage part 24 has memorize | stored beforehand the positional information on the sleeping area R (refer FIG. 6) in the living room 101. FIG. The sleeping region R is a region that is used by the care recipient in the living room 101 when sleeping, and more specifically, is a region in which the bed 102 is arranged in the living room 101. In the living room 101, a futon may be arranged instead of the bed 102. In this case, the area where the futon is arranged in the living room 101 is the sleeping area R. As the position information of the sleeping region R, for example, the position coordinates (planar coordinates) of the sleeping region R when an arbitrary position in the living room 101 is set as the origin in a plane parallel to the floor surface 101b can be considered. The position information of the sleeping region R may be set and input by the management server 100a, transmitted from the management server 100a to the moving object detection unit 10, and stored in the storage unit 24.
　画像認識部２５は、光学検出部２３にて取得された画像の画像データに対して画像認識処理を行う。より具体的には、画像認識部２５は、光学検出部２３の画像処理部５４が画像処理を実行した後の信号を受信し、例えば対象物の輪郭を抽出してパターンマッチング等の手法で形状を認識する画像認識処理を実行する。これにより、画像認識部２５は、居室１０１内にいる被介護者の状態を認識することができる。 The image recognition unit 25 performs image recognition processing on the image data of the image acquired by the optical detection unit 23. More specifically, the image recognition unit 25 receives a signal after the image processing unit 54 of the optical detection unit 23 performs image processing, extracts the contour of the object, for example, and shapes it by a method such as pattern matching. An image recognition process for recognizing the image is executed. Thereby, the image recognition part 25 can recognize the state of the cared person in the living room 101.
　ここで、居室１０１内にいる被介護者の状態としては、起床、離床、入床、転倒などが想定される。これらの被介護者の状態は、被介護者の体の大きさ動作（体動）を伴う点で、電波検出部３０で検出される微体動（呼吸等による体の微小な動き）と区別される。 Here, the state of the cared person in the living room 101 is assumed to be rising, getting out of bed, entering the floor, falling over, and the like. These cared person states are distinguished from minute movements (small movements of the body due to breathing, etc.) detected by the radio wave detection unit 30 in that they involve the size movements (body movements) of the cared person's body. Is done.
　図６は、図５とは異なる居室１０１の天井部１０１ａに動体検知ユニット１０が設置されたときの、光学検出部２３の撮影範囲と、電波検出部３０の呼吸検知範囲とを模式的に示している。居室１０１内でベッド１０２（就寝領域Ｒ）以外の領域では、被介護者の転倒を検知する必要がある。このとき、天井設置の光学検出部２３の撮影画像に基づく転倒検知では、被介護者が居室１０１内で動体検知ユニット１０から遠い位置にいるときに転倒を精度よく検知できないことは前述の通りである。このため、本実施形態では、被介護者が居室１０１内でベッド１０２以外の領域にいるとき、つまり、被介護者の転倒を検知すべき状態であるときに、ユニット制御部４０が電波検出部３０に対する放射周波数の制御を切り替えることによって、被介護者の転倒の有無を検知（判断）するようにしている。以下、その詳細について説明する。 FIG. 6 schematically shows the imaging range of the optical detection unit 23 and the respiration detection range of the radio wave detection unit 30 when the moving object detection unit 10 is installed in the ceiling 101a of the living room 101 different from FIG. ing. In the area other than the bed 102 (sleeping area R) in the living room 101, it is necessary to detect the fall of the care recipient. At this time, in the fall detection based on the photographed image of the optical detector 23 installed on the ceiling, the fall cannot be accurately detected when the cared person is far from the moving object detection unit 10 in the living room 101 as described above. is there. For this reason, in this embodiment, when the care receiver is in an area other than the bed 102 in the living room 101, that is, when the care receiver is to be detected to fall, the unit controller 40 detects the radio wave detection section. By switching the control of the radiation frequency with respect to 30, the presence or absence of the cared person's fall is detected (determined). The details will be described below.
　〔ユニット制御部の制御について〕
　ユニット制御部４０（特に主制御部４１）は、電波検出部３０から放射される電波の放射周波数を制御する。放射周波数の制御としては、第１の駆動モードによる制御と、第２の駆動モードによる制御とがある。 [Control of the unit controller]
The unit controller 40 (particularly the main controller 41) controls the radiation frequency of the radio waves radiated from the radio wave detector 30. As the control of the radiation frequency, there are a control by the first drive mode and a control by the second drive mode.
　図７は、第１の駆動モードの周波数の波形を模式的に示しており、図８は、第２の駆動モードの周波数の波形を模式的に示している。第１の駆動モードは、電波検出部３０から放射される電波の放射周波数を無変調として（変調せずに）電波検出部３０を駆動するモードであり、ＣＷ（Continuous Wave）モードまたはドップラーモードとも呼ばれる。第１の駆動モードによる駆動では、センサ感度が高く、電波検出部３０による被介護者の呼吸検知が可能となるが、その反面、被介護者との距離を測定できないため、距離に基づく転倒検知を行うことができない。 FIG. 7 schematically shows the frequency waveform of the first drive mode, and FIG. 8 schematically shows the frequency waveform of the second drive mode. The first drive mode is a mode in which the radio wave detection unit 30 is driven without modulation (without modulation) of the radiation frequency of the radio wave radiated from the radio wave detection unit 30. Both the CW (Continuous Wave) mode and the Doppler mode are used. be called. In the drive in the first drive mode, the sensor sensitivity is high and the radio wave detection unit 30 can detect the care recipient's breathing. However, since the distance to the care receiver cannot be measured, the fall detection based on the distance is possible. Can not do.
　一方、第２の駆動モードは、放射周波数を変調して電波検出部３０を駆動するモードであり、ＦＭＣＷ（Frequency Modulated Continuous Wave）モードまたは距離計測モードとも呼ばれる。第２の駆動モードによる駆動では、電波検出部３０と被介護者との距離を測定できるため、測定した距離の大小に基づいて被介護者の転倒を検知することができるが、その反面、センサ感度が低いため、電波検出部３０での呼吸検知ができなくなる。 On the other hand, the second drive mode is a mode for driving the radio wave detection unit 30 by modulating the radiation frequency, and is also called FMCW (Frequency-Modulated-Continuous-Wave) mode or distance measurement mode. In the driving in the second driving mode, since the distance between the radio wave detection unit 30 and the cared person can be measured, the fall of the cared person can be detected based on the measured distance, but on the other hand, the sensor Since the sensitivity is low, the radio wave detection unit 30 cannot detect respiration.
　ここで、例えば、図９に示すように、周波数を直線的に変化させた場合、電波検出部３０と被介護者までの距離Ｄ（ｍ）は、送信波と反射波との周波数差（ビート周波数）等から求めることができる。具体的には、距離Ｄは、以下の式で求められる。
　　Ｄ＝（ｃ・Ｔ・ｆＢ）／（２・ｆｗ）
　ただし、
　　ｃ：光速（＝３×１０8）（ｍ／ｓ）
　　Ｔ：送信時間（ｓ）
　　ｆＢ：ビート周波数（＝送信波の周波数－反射波の周波数）（Ｈｚ）
　　ｆｗ：周波数掃引幅（Ｈｚ） Here, for example, as shown in FIG. 9, when the frequency is changed linearly, the distance D (m) between the radio wave detection unit 30 and the cared person is the frequency difference (beats) between the transmitted wave and the reflected wave. Frequency) and the like. Specifically, the distance D is obtained by the following equation.
D = (c · T · fB) / (2 · fw)
However,
c: speed of light (= 3 × 10 8 ) (m / s)
T: Transmission time (s)
fB: Beat frequency (= frequency of transmitted wave−frequency of reflected wave) (Hz)
fw: frequency sweep width (Hz)
　距離Ｄが求められると、ユニット制御部４０は、距離Ｄの大小に基づいて、被介護者が立っている状態か、転倒している状態かを判断できる。例えば、居室１０１の床面１０１ｂから天井部１０１ａまでの高さが２．４ｍであり、被介護者の身長が１．６５ｍであり、光学検出部２３にて撮影された画像に基づく画像認識により、被介護者が動体検知ユニット１０の真下にいることが分かっている場合において、上記式によって求めた距離Ｄが０．７０～０．８０ｍであった場合、被介護者は動体検知ユニット１０の真下で立っている状態であると判断でき、求めた距離Ｄが２．２～２．３ｍであった場合、被介護者は動体検知ユニット１０の真下で転倒している状態であると判断できる。同様にして、被介護者が動体検知ユニット１０から離れた位置にいる場合でも、被介護者が立っていると、動体検知ユニット１０と被介護者（例えば頭部）との距離が相対的に小さく、被介護者が転倒していると上記距離Ｄが相対的に大きくなるため、距離Ｄの大小に基づいて、被介護者の転倒の有無を判断することができる。 When the distance D is obtained, the unit control unit 40 can determine whether the care receiver is standing or falling based on the magnitude of the distance D. For example, the height from the floor surface 101b of the living room 101 to the ceiling portion 101a is 2.4 m, the height of the care recipient is 1.65 m, and image recognition based on the image photographed by the optical detection unit 23 is performed. In the case where it is known that the cared person is directly below the moving object detection unit 10, when the distance D obtained by the above formula is 0.70 to 0.80 m, the cared person is It can be determined that the person is standing right below, and if the calculated distance D is 2.2 to 2.3 m, the care recipient can be determined to be in a state of falling right below the moving object detection unit 10. . Similarly, even when the cared person is located away from the moving object detection unit 10, when the cared person is standing, the distance between the moving object detection unit 10 and the cared person (for example, the head) is relatively Since the distance D is relatively large when the cared person is falling, the presence or absence of the cared person can be determined based on the magnitude of the distance D.
　本実施形態では、ユニット制御部４０（特に主制御部４１）は、光学検出部２３にて取得された画像に基づいて、放射周波数の制御を第１の駆動モードと第２の駆動モードとで切り替えるようにしている。以下、そのような制御も含めて、動体検知ユニット１０全体の動作について説明する。 In the present embodiment, the unit control unit 40 (particularly the main control unit 41) controls the radiation frequency in the first drive mode and the second drive mode based on the image acquired by the optical detection unit 23. I try to switch. Hereinafter, the entire operation of the moving object detection unit 10 including such control will be described.
　図１０は、本実施形態の動体検知ユニット１０における動作の流れを示すフローチャートである。また、図１１は、被介護者Ｐがベッド１０２上にいる状態を模式的に示し、図１２は、被介護者Ｐがベッド１０２上にいない状態（ベッド１０２から離れている状態）を模式的に示している。まず、光学検出部２３は、居室１０１内を天井部１０１ａから床面１０１ｂに向かって撮影し、画像を取得する（Ｓ１）。次に、画像認識部２５は、上記画像の画像データに対して画像認識処理を行い、居室１０１内での被介護者Ｐの位置を認識する（Ｓ２）。そして、ユニット制御部４０は、上記画像上での被介護者Ｐとベッド１０２（就寝領域Ｒ）との位置関係を判断し、被介護者Ｐがベッド１０２上にいるか、いないかを判断する（Ｓ３）。 FIG. 10 is a flowchart showing an operation flow in the moving object detection unit 10 of the present embodiment. FIG. 11 schematically shows a state where the cared person P is on the bed 102, and FIG. 12 schematically shows a state where the cared person P is not on the bed 102 (a state where the cared person P is separated from the bed 102). It shows. First, the optical detection unit 23 captures an image of the interior of the living room 101 from the ceiling 101a toward the floor 101b (S1). Next, the image recognition unit 25 performs image recognition processing on the image data of the image, and recognizes the position of the care recipient P in the living room 101 (S2). Then, the unit control unit 40 determines the positional relationship between the care receiver P and the bed 102 (sleeping region R) on the image, and determines whether or not the care receiver P is on the bed 102 ( S3).
　なお、記憶部２４には、実空間でのベッド１０２の位置情報（位置座標）が記憶されているが、居室１０１内に実在する物体の位置と、その居室１０１内を撮影した画像における上記物体の位置とは対応関係にあるため、ユニット制御部４０は、記憶部２４に記憶された上記位置情報から、上記画像上でのベッド１０２の位置（上記画像上で上記位置情報と対応する位置）を把握することが可能である。 Note that the storage unit 24 stores position information (position coordinates) of the bed 102 in the real space, but the position of the object that actually exists in the living room 101 and the object in the image obtained by photographing the inside of the living room 101. Therefore, the unit control unit 40 determines the position of the bed 102 on the image (the position corresponding to the position information on the image) from the position information stored in the storage unit 24. Can be grasped.
　Ｓ３にて、被介護者Ｐがベッド１０２上にいると判断した場合（図１１参照）、ユニット制御部４０は、放射周波数を無変調する第１の駆動モードで電波検出部３０を駆動する（Ｓ４）。これにより、電波検出部３０はベッド１０２上にいる被介護者Ｐの生体情報（例えば呼吸状態）を検知することが可能となる。 When it is determined in S3 that the cared person P is on the bed 102 (see FIG. 11), the unit control unit 40 drives the radio wave detection unit 30 in the first drive mode in which the radiation frequency is not modulated (see FIG. 11). S4). Thereby, the radio wave detection unit 30 can detect the biological information (for example, the breathing state) of the cared person P on the bed 102.
　一方、Ｓ３にて、被介護者Ｐがベッド１０２上にいないと判断した場合（図１２参照）、ユニット制御部４０は、放射周波数を変調する第２の駆動モードで電波検出部３０を駆動する（Ｓ５）。これにより、電波検出部３０は、被介護者Ｐとの距離を測定することが可能となり、ユニット制御部４０は、測定した距離に基づいて、上述のように被介護者Ｐの転倒の有無を判断することが可能となる。 On the other hand, when it is determined in S3 that the care receiver P is not on the bed 102 (see FIG. 12), the unit control unit 40 drives the radio wave detection unit 30 in the second drive mode that modulates the radiation frequency. (S5). Thereby, the radio wave detection unit 30 can measure the distance to the cared person P, and the unit control unit 40 determines whether the cared person P has fallen as described above based on the measured distance. It becomes possible to judge.
　なお、図１０のフローチャートでは、Ｓ１からＳ４またはＳ５までの処理を一巡しか示していないが、Ｓ４またはＳ５の後、Ｓ１に戻って以降の処理を繰り返すことにより、常時、呼吸検知または転倒検知を行うことができる。 In the flowchart of FIG. 10, the process from S1 to S4 or S5 is shown only once. However, after S4 or S5, the process returns to S1 and the subsequent processes are repeated, so that respiration detection or fall detection is always performed. It can be carried out.
　以上のように、動体検知ユニット１０のユニット制御部４０は、光学検出部２３にて取得された画像に基づいて、電波検出部３０から放射される電波の放射周波数の制御を、放射周波数を変調しない第１の駆動モードと、放射周波数を変調する第２の駆動モードとで切り替える。これにより、電波検出部３０によって、第１の駆動モードによる呼吸検知と、第２の駆動モードによる距離測定とを行うことができる。このとき、電波検出部３０にて測定される距離は、所定の演算によって求められる距離であり、実際の距離にほぼ等しい。したがって、ユニット制御部４０は、居室１０１内での被介護者Ｐの位置によらずに（被介護者Ｐが居室１０１内で動体検知ユニット１０に近い位置にいても遠い位置にいても）、測定した距離に基づいて転倒の有無を精度よく判断することができる。しかも、転倒検知の際には、被介護者Ｐの呼吸状態を検知する電波検出部３０を利用しているため、転倒検知専用のセンサを別途設ける必要がなく、装置（動体検知ユニット１０）の簡単な構成で（現存の構成を有効利用して）、被介護者Ｐの転倒を精度よく検知することができる。 As described above, the unit control unit 40 of the moving object detection unit 10 controls the radiation frequency of the radio wave radiated from the radio wave detection unit 30 based on the image acquired by the optical detection unit 23, and modulates the radiation frequency. Switching between the first driving mode that is not performed and the second driving mode that modulates the radiation frequency. Thereby, the radio wave detection unit 30 can perform respiration detection in the first drive mode and distance measurement in the second drive mode. At this time, the distance measured by the radio wave detection unit 30 is a distance obtained by a predetermined calculation and is substantially equal to the actual distance. Therefore, the unit controller 40 does not depend on the position of the cared person P in the living room 101 (whether the cared person P is close to or far from the moving object detection unit 10 in the living room 101). Based on the measured distance, the presence or absence of a fall can be accurately determined. Moreover, since the radio wave detection unit 30 that detects the breathing state of the cared person P is used for the fall detection, there is no need to separately provide a sensor dedicated to the fall detection, and the apparatus (moving object detection unit 10) With a simple configuration (using the existing configuration effectively), the fall of the care recipient P can be accurately detected.
　また、ユニット制御部４０は、光学検出部２３にて取得された画像に基づいて、居室１０１内での被介護者Ｐの位置とベッド１０２（就寝領域Ｒ）との位置関係を判断し、判断した位置関係に応じて、放射周波数の制御を切り替えている。これにより、被介護者Ｐがベッド１０２上にいるか、いないかに応じて、検知すべき情報（生体情報または転倒）を確実に検知することができる。つまり、被介護者Ｐがベッド１０２上にいる場合は、放射周波数の制御を第１の駆動モードに切り替えて呼吸検知を行うことができ、被介護者Ｐがベッド１０２上にいない場合は、放射周波数の制御を第２の駆動モードに切り替えて距離測定および転倒検知を行うことができる。 Further, the unit controller 40 determines the positional relationship between the position of the care recipient P and the bed 102 (sleeping region R) in the living room 101 based on the image acquired by the optical detector 23. The control of the radiation frequency is switched according to the positional relationship. This makes it possible to reliably detect information to be detected (biological information or falls) depending on whether the care receiver P is on the bed 102 or not. That is, when the cared person P is on the bed 102, the control of the radiation frequency can be switched to the first drive mode to perform respiration detection. When the cared person P is not on the bed 102, the radiation is emitted. The frequency control can be switched to the second drive mode to perform distance measurement and fall detection.
　また、居室１０１内でのベッド１０２の位置情報が記憶部２４に予め記憶されているため、ユニット制御部４０は、光学検出部２３にて取得された画像上での、画像認識部２５にて認識された被介護者Ｐの位置と、記憶部２４に記憶された上記位置情報と画像上で対応するベッド１０２の位置とに基づいて、被介護者Ｐとベッド１０２との位置関係（被介護者Ｐがベッド１０２上にいるか、いないか）を確実に判断することができる。 Further, since the position information of the bed 102 in the living room 101 is stored in the storage unit 24 in advance, the unit control unit 40 uses the image recognition unit 25 on the image acquired by the optical detection unit 23. Based on the recognized position of the cared person P and the position of the bed 102 corresponding to the position information stored in the storage unit 24 and the image on the image, the positional relationship between the cared person P and the bed 102 (cared Whether the person P is on the bed 102 or not).
　また、ユニット制御部４０は、放射周波数の制御を、放射周波数の変調の有無によって切り替えている。これにより、放射周波数を変調しない制御（第１の駆動モード）では、電波検出部３０にて被介護者Ｐの呼吸状態を検知することが可能となる。一方、放射周波数を変調する制御（第２の駆動モード）では、電波検出部３０が被介護者Ｐとの距離を測定できるため、ユニット制御部４０は、測定した距離に基づいて、被介護者Ｐの転倒の有無を検知することが可能となる。 Further, the unit controller 40 switches the control of the radiation frequency depending on whether or not the radiation frequency is modulated. Thereby, in the control (first driving mode) in which the radiation frequency is not modulated, the radio wave detection unit 30 can detect the respiratory state of the care receiver P. On the other hand, in the control for modulating the radiation frequency (second drive mode), since the radio wave detection unit 30 can measure the distance to the care receiver P, the unit control unit 40 can determine the care receiver based on the measured distance. It is possible to detect whether or not P has fallen.
　また、ユニット制御部４０は、被介護者Ｐの位置とベッド１０２との位置関係に応じて、放射周波数の制御を第１の駆動モードと第２の駆動モードとで切り替えている。これにより、電波検出部３０は、第１の駆動モードにおいて被介護者Ｐの呼吸状態を検知し、第２の駆動モードにおいて被介護者Ｐとの距離を測定することができる。したがって、ユニット制御部４０は、第２の駆動モードで測定された距離に基づいて、被介護者Ｐの転倒の有無を検知することが可能となる。 The unit control unit 40 switches the control of the radiation frequency between the first drive mode and the second drive mode according to the positional relationship between the position of the care recipient P and the bed 102. Thereby, the radio wave detection unit 30 can detect the breathing state of the cared person P in the first drive mode and can measure the distance from the cared person P in the second drive mode. Therefore, the unit controller 40 can detect whether the care receiver P has fallen based on the distance measured in the second drive mode.
　また、本実施形態のケアサポートシステム１は、動体検知ユニット１０と、動体検知ユニット１０から送信される情報を受信して管理する管理サーバー１００ａとを含む構成である。このようなシステムにおいても、上述した動体検知ユニット１０を含んでいるため、転倒検知専用のセンサを別途設けることなく、居室１０１内での被介護者Ｐの位置によらずに、被介護者Ｐの転倒の有無を精度よく検知できるという本実施形態の効果を得ることができる。 Further, the care support system 1 of the present embodiment includes a moving body detection unit 10 and a management server 100a that receives and manages information transmitted from the moving body detection unit 10. Even in such a system, since the moving object detection unit 10 described above is included, a care receiver P is not provided regardless of the position of the care receiver P in the living room 101 without separately providing a sensor dedicated to fall detection. The effect of this embodiment that the presence / absence of falling can be detected with high accuracy can be obtained.
　なお、以上では、動体検知ユニット１０と被介護者との距離の測定（演算）を、電波を送受信する電波検出部３０自体で行う例について説明したが、距離の演算は、ユニット制御部４０にて行ってもよい。つまり、電波検出部３０から出力される情報に基づいて、ユニット制御部４０が被介護者との距離を測定し、転倒の有無を検知（判断）する構成であってもよい。 In the above, the example in which the measurement (calculation) of the distance between the moving object detection unit 10 and the care recipient is performed by the radio wave detection unit 30 itself that transmits and receives radio waves has been described. However, the distance calculation is performed by the unit control unit 40. You may go. That is, based on the information output from the radio wave detection unit 30, the unit control unit 40 may measure the distance from the care recipient and detect (determine) the presence or absence of a fall.
　以上、本発明の実施形態につき説明したが、本発明の範囲はこれに限定されるものではなく、発明の主旨を逸脱しない範囲で種々の変更を加えて実施することができる。 The embodiment of the present invention has been described above, but the scope of the present invention is not limited to this, and various modifications can be made without departing from the spirit of the invention.
　以上で説明した本実施形態の動体検知ユニットおよびケアサポートシステムは、以下のように表現することができ、これによって以下の作用効果を奏すると言うことができる。 The moving object detection unit and the care support system of the present embodiment described above can be expressed as follows, and it can be said that the following effects can be obtained.
　本実施形態の動体検知ユニットは、居室の天井部に設置され、居室内の動体としての被検者の情報を検知する動体検知ユニットであって、居室内を撮影して画像を取得する光学検出部と、電波の放射および受信によって、被検者の状態を検知する状態検知部と、前記状態検知部から放射される電波の放射周波数を制御するユニット制御部とを備え、前記ユニット制御部は、前記光学検出部にて取得された前記画像に基づいて、前記放射周波数の制御を切り替える。 The moving body detection unit of the present embodiment is a moving body detection unit that is installed on a ceiling portion of a living room and detects information on a subject as a moving body in the living room, and acquires an image by photographing the living room. A state detection unit that detects the state of the subject by radiation and reception of radio waves, and a unit control unit that controls a radiation frequency of radio waves radiated from the state detection unit, the unit control unit includes: The control of the radiation frequency is switched based on the image acquired by the optical detection unit.
　動体検知ユニットは居室の天井部に設置されているため、動体検知ユニットが備える光学検出部は、居室の天井部から床面に向かって居室内を撮影することになる。ユニット制御部は、光学検出部にて取得された画像に基づいて、状態検知部から放射される電波の放射周波数の制御を切り替える。これにより、ユニット制御部は、例えば、上記画像から、被検者が居室内で特定の位置（例えばベッドの上）にいると判断した場合には、放射周波数を変調しない駆動モードで状態検知部を駆動し、被検者が他の位置（例えば床面上の位置）にいると判断した場合には、放射周波数を変調する駆動モードで状態検知部を駆動することができる。前者の場合、状態検知部は、電波の放射および受信によって被検者の生体情報（例えば呼吸状態）を検知することができる。一方、後者の場合、状態検知部は、電波の放射および受信によって状態検知部（動体検知ユニット）と被検者との距離を測定することができる。そして、ユニット制御部は、測定した距離に基づき、床面上で被検者がどの位置にいても、そこで被検者が立っている状態か、転倒している状態かを明確に区別して判断することができる。 Since the moving body detection unit is installed on the ceiling of the living room, the optical detection unit included in the moving body detection unit images the room from the ceiling of the living room toward the floor. The unit control unit switches the control of the radiation frequency of the radio wave radiated from the state detection unit based on the image acquired by the optical detection unit. Thereby, for example, when the unit control unit determines from the above image that the subject is in a specific position (for example, on the bed) in the room, the state detection unit in the drive mode in which the radiation frequency is not modulated. When the subject is determined to be in another position (for example, a position on the floor surface), the state detection unit can be driven in a driving mode in which the radiation frequency is modulated. In the former case, the state detection unit can detect the biological information (for example, respiratory state) of the subject by radiating and receiving radio waves. On the other hand, in the latter case, the state detection unit can measure the distance between the state detection unit (moving object detection unit) and the subject by radiating and receiving radio waves. Based on the measured distance, the unit control unit clearly distinguishes whether the subject is standing on the floor or whether the subject is standing or falling. can do.
　このように、ユニット制御部が、光学検出部で取得された画像に基づいて、放射周波数の制御を切り替えることにより、居室内での被検者の位置によらずに、被検者の転倒の有無を精度よく検知（判断）することができる。しかも、同じ状態検知部を利用して、被検者の生体情報と転倒とを検知できるため、転倒検知専用のセンサを別途設ける必要がなく、簡単な構成で、被検者の転倒を精度よく検知することができる。 In this way, the unit control unit switches the control of the radiation frequency based on the image acquired by the optical detection unit, so that the fall of the subject can be performed regardless of the position of the subject in the room. Presence / absence can be detected (judged) with high accuracy. In addition, because the same state detection unit can be used to detect the patient's biological information and falls, there is no need to provide a separate sensor dedicated to fall detection, and the fall of the subject can be accurately performed with a simple configuration. Can be detected.
　前記ユニット制御部は、前記画像に基づいて、居室内での被検者の位置と、居室内でベッドまたは布団が配置される就寝領域との位置関係を判断し、判断した位置関係に応じて、前記放射周波数の制御を切り替えてもよい。 The unit control unit determines the positional relationship between the position of the subject in the living room and the sleeping area where the bed or the futon is arranged in the living room based on the image, and according to the determined positional relationship The control of the radiation frequency may be switched.
　例えば、被検者が就寝領域にいる場合は、被検者の転倒を検知する必要はなく、被検者の呼吸状態を検知することが望ましい。一方、被検者が就寝領域外にいる場合は、被検者の呼吸状態を検知する必要はなく、被検者の転倒を検知する必要がある。上記のように、ユニット制御部が、居室内での被検者と就寝領域との位置関係に応じて、放射周波数の制御を切り替えることにより、居室内での被検者の位置に応じて、検知すべき情報（生体情報または転倒の有無）を確実に検知することができる。 For example, when the subject is in the sleeping area, it is not necessary to detect the fall of the subject, and it is desirable to detect the breathing state of the subject. On the other hand, when the subject is outside the sleeping area, it is not necessary to detect the breathing state of the subject, and it is necessary to detect the fall of the subject. As described above, according to the position of the subject in the room, the unit control unit switches the control of the radiation frequency according to the positional relationship between the subject and the sleeping area in the room, Information to be detected (biological information or the presence or absence of a fall) can be reliably detected.
　前記動体検知ユニットは、前記画像に対して画像認識処理を行うことにより、前記被検者の位置を認識する画像認識部と、居室内の前記就寝領域の位置情報を予め記憶する記憶部とをさらに備え、前記ユニット制御部は、前記画像認識部にて認識された前記被検者の位置と、前記記憶部に記憶された前記就寝領域の前記位置情報と前記画像上で対応する位置とに基づいて、前記位置関係を判断してもよい。 The moving body detection unit includes an image recognition unit that recognizes the position of the subject by performing an image recognition process on the image, and a storage unit that stores in advance the position information of the sleeping region in the living room. The unit control unit further includes a position of the subject recognized by the image recognition unit, a position corresponding to the position information of the sleeping region stored in the storage unit and a position on the image. Based on this, the positional relationship may be determined.
　就寝領域の位置情報が記憶部に予め記憶されているため、ユニット制御部は、記憶された就寝領域の位置情報と画像上で対応する位置と、画像認識部にて認識された被検者の位置とに基づいて、居室内での被検者と就寝領域との位置関係を確実に判断することができる。 Since the position information of the sleeping region is stored in the storage unit in advance, the unit control unit stores the position information corresponding to the stored sleeping region position information on the image and the subject recognized by the image recognition unit. Based on the position, the positional relationship between the subject and the sleeping area in the living room can be reliably determined.
　前記ユニット制御部は、前記放射周波数の制御を、前記放射周波数の変調の有無によって切り替えてもよい。 The unit control unit may switch the control of the radiation frequency depending on whether or not the radiation frequency is modulated.
　ユニット制御部が放射周波数を変調しない制御では、状態検知部は、電波の放射および受信により、被検者の生体情報を検知することが可能となる。また、ユニット制御部が放射周波数を変調する制御では、状態検知部は、電波の放射および受信により、状態検知部と被検者との距離を測定できる。これにより、ユニット制御部は、測定した距離に基づいて、被検者の転倒の有無を検知（判断）することが可能となる。 In the control in which the unit control unit does not modulate the radiation frequency, the state detection unit can detect the biological information of the subject by emitting and receiving radio waves. In the control in which the unit control unit modulates the radiation frequency, the state detection unit can measure the distance between the state detection unit and the subject by radiating and receiving radio waves. As a result, the unit control unit can detect (determine) whether or not the subject has fallen based on the measured distance.
　前記ユニット制御部は、前記被検者の位置と前記就寝領域との前記位置関係に応じて、前記放射周波数の制御を、放射周波数を無変調とする第１の駆動モードと、放射周波数を変調する第２の駆動モードとで切り替えてもよい。 The unit control unit modulates the radiation frequency according to the positional relationship between the position of the subject and the sleeping area, the first drive mode in which the radiation frequency is not modulated, and the radiation frequency is modulated. The second driving mode may be switched.
　ユニット制御部が、上記位置関係に応じて、前記放射周波数の制御を第１の駆動モードと第２の駆動モードとで切り替えることにより、状態検知部は、第１の駆動モードにおいて被検者の生体情報を検知し、第２の駆動モードにおいて状態検知部と被検者との距離を測定することができる。これにより、ユニット制御部は、第２の駆動モードで測定された距離に基づいて、被検者の転倒の有無を検知（判断）することが可能となる。 The unit control unit switches the control of the radiation frequency between the first drive mode and the second drive mode in accordance with the positional relationship, so that the state detection unit can detect the subject in the first drive mode. The biological information can be detected, and the distance between the state detection unit and the subject can be measured in the second drive mode. As a result, the unit control unit can detect (determine) whether or not the subject has fallen based on the distance measured in the second drive mode.
　本実施形態のケアサポートシステムは、上述した動体検知ユニットと、前記動体検知ユニットから送信される情報を受信して管理する管理サーバーとを含んでいる。この場合、動体検知ユニットおよび管理サーバーを含むケアサポートシステムにおいて、上述の効果を得ることができる。 The care support system of the present embodiment includes the above-described moving body detection unit and a management server that receives and manages information transmitted from the moving body detection unit. In this case, the above-described effects can be obtained in the care support system including the moving object detection unit and the management server.
　本発明は、例えば居室内での被介護者等の被検者の日常の生活を支援するケアサポートシステムに利用可能である。 The present invention can be used for a care support system that supports the daily life of a subject such as a care recipient in a living room.
　　　１　　　ケアサポートシステム
　　１０　　　動体検知ユニット
　　２３　　　光学検出部
　　２４　　　記憶部
　　２５　　　画像認識部
　　３０　　　電波検出部（状態検知部）
　　４０　　　ユニット制御部
　１００ａ　　管理サーバー
　１０１　　　居室
　１０１ａ　　天井部
　１０２　　　ベッド
　　　Ｐ　　　被介護者（被検者）
　　　Ｒ　　　就寝領域 DESCRIPTION OF SYMBOLS 1 Care support system 10 Moving body detection unit 23 Optical detection part 24 Memory | storage part 25 Image recognition part 30 Radio wave detection part (state detection part)
40 Unit control unit 100a Management server 101 Living room 101a Ceiling part 102 Bed P Caregiver (examinee)
R sleeping area

Claims (6)

  1. 　居室の天井部に設置され、居室内の動体としての被検者の情報を検知する動体検知ユニットであって、
    　居室内を撮影して画像を取得する光学検出部と、
    　電波の放射および受信によって、被検者の状態を検知する状態検知部と、
    　前記状態検知部から放射される電波の放射周波数を制御するユニット制御部とを備え、
    　前記ユニット制御部は、前記光学検出部にて取得された前記画像に基づいて、前記放射周波数の制御を切り替える、動体検知ユニット。     A moving body detection unit that is installed on a ceiling of a living room and detects information of a subject as a moving body in the living room,
    An optical detector that captures an image of the room and acquires an image;
    A state detector that detects the state of the subject by emitting and receiving radio waves;
    A unit controller that controls the radiation frequency of the radio waves radiated from the state detector
    The unit control unit is a moving body detection unit that switches control of the radiation frequency based on the image acquired by the optical detection unit.
  2. 　前記ユニット制御部は、前記画像に基づいて、居室内での被検者の位置と、居室内でベッドまたは布団が配置される就寝領域との位置関係を判断し、判断した位置関係に応じて、前記放射周波数の制御を切り替える、請求項１に記載の動体検知ユニット。 The unit control unit determines the positional relationship between the position of the subject in the living room and the sleeping area where the bed or the futon is arranged in the living room based on the image, and according to the determined positional relationship The moving body detection unit according to claim 1, wherein the control of the radiation frequency is switched.
  3. 　前記画像に対して画像認識処理を行うことにより、前記被検者の位置を認識する画像認識部と、
    　居室内の前記就寝領域の位置情報を予め記憶する記憶部とをさらに備え、
    　前記ユニット制御部は、前記画像認識部にて認識された前記被検者の位置と、前記記憶部に記憶された前記就寝領域の前記位置情報と前記画像上で対応する位置とに基づいて、前記位置関係を判断する、請求項２に記載の動体検知ユニット。     An image recognition unit that recognizes the position of the subject by performing image recognition processing on the image;
    A storage unit that stores in advance position information of the sleeping area in the living room;
    The unit control unit is based on the position of the subject recognized by the image recognition unit, the position information of the sleeping region stored in the storage unit, and the corresponding position on the image, The moving object detection unit according to claim 2, wherein the positional relationship is determined.
  4. 　前記ユニット制御部は、前記放射周波数の制御を、前記放射周波数の変調の有無によって切り替える、請求項１から３のいずれかに記載の動体検知ユニット。 The moving object detection unit according to any one of claims 1 to 3, wherein the unit control unit switches the control of the radiation frequency depending on whether or not the radiation frequency is modulated.
  5. 　前記ユニット制御部は、前記被検者の位置と前記就寝領域との前記位置関係に応じて、前記放射周波数の制御を、放射周波数を無変調とする第１の駆動モードと、放射周波数を変調する第２の駆動モードとで切り替える、請求項２または３に記載の動体検知ユニット。 The unit control unit modulates the radiation frequency according to the positional relationship between the position of the subject and the sleeping area, the first drive mode in which the radiation frequency is not modulated, and the radiation frequency is modulated. The moving body detection unit according to claim 2, wherein the moving body detection unit switches between the second driving mode and the second driving mode.
  6. 　請求項１から５のいずれかに記載の動体検知ユニットと、
    　前記動体検知ユニットから送信される情報を受信して管理する管理サーバーとを含む、ケアサポートシステム。     The moving object detection unit according to any one of claims 1 to 5,
    A care support system including a management server that receives and manages information transmitted from the moving object detection unit.
PCT/JP2017/023637 2016-08-09 2017-06-27 Moving body detection unit and care support system WO2018030017A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2018532866A JP6984601B2 (en) 2016-08-09 2017-06-27 Motion detection unit and care support system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2016-156325 2016-08-09
JP2016156325 2016-08-09

Publications (1)

Publication Number Publication Date
WO2018030017A1 true WO2018030017A1 (en) 2018-02-15

Family

ID=61162068

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/023637 WO2018030017A1 (en) 2016-08-09 2017-06-27 Moving body detection unit and care support system

Country Status (2)

Country Link
JP (1) JP6984601B2 (en)
WO (1) WO2018030017A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014159773A1 (en) * 2013-03-13 2014-10-02 Kirill Mostov An apparatus for remote contactless monitoring of sleep apnea
WO2015037269A1 (en) * 2013-09-13 2015-03-19 コニカミノルタ株式会社 Monitor subject monitoring device and method, and monitor subject monitoring system
JP2015228159A (en) * 2014-06-02 2015-12-17 株式会社東京精密 Non-contact monitored living body sensing device
JP3202674U (en) * 2015-11-24 2016-02-18 株式会社メイク Non-contact type bed management system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102009057191A1 (en) * 2009-12-05 2011-06-09 Valeo Schalter Und Sensoren Gmbh Method for uniquely determining a distance and / or a relative speed of an object, driver assistance device and motor vehicle
JP5558440B2 (en) * 2011-09-08 2014-07-23 三菱電機株式会社 Object detection device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014159773A1 (en) * 2013-03-13 2014-10-02 Kirill Mostov An apparatus for remote contactless monitoring of sleep apnea
WO2015037269A1 (en) * 2013-09-13 2015-03-19 コニカミノルタ株式会社 Monitor subject monitoring device and method, and monitor subject monitoring system
JP2015228159A (en) * 2014-06-02 2015-12-17 株式会社東京精密 Non-contact monitored living body sensing device
JP3202674U (en) * 2015-11-24 2016-02-18 株式会社メイク Non-contact type bed management system

Also Published As

Publication number Publication date
JPWO2018030017A1 (en) 2019-06-06
JP6984601B2 (en) 2021-12-22

Similar Documents

Publication Publication Date Title
JP6150207B2 (en) Monitoring system
TWI425431B (en) Surveillance system and program
JPWO2016143641A1 (en) Attitude detection device and attitude detection method
JP6852733B2 (en) Living body monitoring device and living body monitoring method
WO2018216363A1 (en) Care support system and radio wave control method
WO2018034064A1 (en) Care support system
WO2019049530A1 (en) Data processing device, care support system and data processing method
WO2020071374A1 (en) Condition monitoring device and condition monitoring method
WO2018030017A1 (en) Moving body detection unit and care support system
WO2020071375A1 (en) Condition monitoring device
JP7090327B2 (en) Information processing equipment, information processing method, program
CN116243306A (en) Method and system for monitoring object
JP6766585B2 (en) Observed person monitoring device and method
JP2023548886A (en) Apparatus and method for controlling a camera
JP2017174706A (en) Image recognition system, moving body detection unit, and care support system
WO2019216064A1 (en) Care support system and information provision method
WO2017217285A1 (en) Care support system
JP6733668B2 (en) Watching system
JP7380551B2 (en) Care support system and information processing method
JP7163923B2 (en) Care support system and communication control method
JP2018117331A (en) Bed watching device
JP6823327B2 (en) Autonomous mobile robot and vital sign monitoring method
JP7205540B2 (en) Computer Executed Programs, Information Processing Devices, and Computer Executed Methods
JP7215481B2 (en) Computer Executed Programs, Information Processing Devices, and Computer Executed Methods
WO2020021897A1 (en) Information processing device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17839091

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018532866

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17839091

Country of ref document: EP

Kind code of ref document: A1