JP6874679B2 - Monitoring device - Google Patents

Description

The present invention relates to a monitoring device for finding abnormalities in the health condition of a resident spending time in a nursing care facility or the like.

In recent years, a monitoring device for detecting abnormalities in the health condition of residents spending time in nursing care facilities, hospitals, etc. has been proposed. Residents who spend time in nursing care facilities or hospitals may be prone to falls indoors, falls from beds, and have abnormalities such as breathing and heartbeat. The facility is staffed by caregivers and nurses who support their lives, but the number is relatively small and they cannot be accompanied at all times. A monitoring device has been proposed to solve such a problem, and examples of the prior art relating thereto are disclosed in Patent Documents 1 and 2.

The image processing apparatus described in Patent Document 1 includes an image pickup camera for photographing a room and an image processing unit for an image taken by the image pickup camera. This image processing device presets the floor area and the bed area in the indoor image taken by the imaging camera, detects the movement of the human body between the floor area and the bed area, and enters the subject into the bed. Judge the floor and getting out of bed. As a result, it is possible to accurately determine whether the subject enters or leaves the bed.

The safety monitoring device described in Patent Document 2 acquires biological information related to the body movement and respiration of the subject from the reflected wave of the radio wave radiated toward the subject, and the safety of the subject is obtained from the biological information. Is being monitored. This safety monitoring device uses a Doppler sensor that detects and outputs the deviation between the radiated wave using microwaves and the reflected wave to acquire the biological information of the subject. This makes it possible to correctly detect the body movement and respiration of the subject.

Japanese Unexamined Patent Publication No. 2002-230533 Japanese Unexamined Patent Publication No. 2012-75861

However, in the prior art described in Patent Document 1, the device may react to disturbances such as a curtain swaying around the bed and a shadow generated by light shining through a window. As a result, there is a problem that an erroneous judgment may occur when the subject enters or leaves the bed. Further, in the prior art described in Patent Document 2, consideration is not given to the subject entering and leaving the bed. As a result, there is a problem that if the subject cannot obtain the biological information when he / she is out of bed, he / she may falsely report that the subject has an abnormality.

The present invention has been made in view of the above points, and it is possible to accurately grasp the existence and biological information of the subject, and to suitably find abnormalities in the health condition of the subject. The purpose is to provide the device.

In order to solve the above problems, the monitoring device of the present invention includes a moving object detection unit for detecting the movement of the subject, a biological signal detecting unit for detecting the biological signal of the subject, and the moving object detection unit. A behavior discrimination unit that determines the presence or absence of a subject in a predetermined area based on the information obtained from the unit, and a biological signal that determines the presence or absence of a biological signal of the subject based on the information obtained from the biological signal detection unit. It is characterized in that it includes a discrimination unit, and determines the presence or absence of a subject in the predetermined region based on the information of both the discrimination by the behavior discrimination unit and the discrimination by the biological signal discrimination unit.

According to this configuration, for example, whether or not the subject is present on the bed in the living room of the facility is determined based on both the information of the subject's body movement and the biological signal. The accuracy is improved as compared with the case where the presence or absence of the subject is determined based on the information of either the body movement of the subject or the biological signal.

According to the present invention, it is determined whether or not the subject is present on the bed in the living room of the facility based on the information of both the body movement of the subject and the biological signal, so that the subject sways around the bed. It is possible to suppress the influence of disturbances such as curtains. Furthermore, it is possible to clearly grasp whether the subject enters or leaves the bed. Then, it becomes possible to suitably find abnormalities in the health condition of the subject.

It is a block diagram which shows the application example of the monitoring apparatus which concerns on 1st Embodiment of this invention. It is a block diagram of the monitoring apparatus which concerns on 1st Embodiment of this invention. It is explanatory drawing which shows the image of the moving body detection part of the monitoring apparatus which concerns on 1st Embodiment of this invention, and the state transition of a subject. It is a graph which shows the output (AD output value) of the biological signal by the biological signal detection unit of the monitoring device which concerns on 1st Embodiment of this invention. It is a graph which shows the output (power spectrum) of the biological signal by the biological signal detection unit of the monitoring device which concerns on 1st Embodiment of this invention. It is a graph which shows the output (AD output value) of a noise signal by the biological signal detection part of the monitoring device which concerns on 1st Embodiment of this invention. It is a graph which shows the output (power spectrum) of the noise signal by the biological signal detection part of the monitoring apparatus which concerns on 1st Embodiment of this invention. It is a state transition diagram of a subject used in the monitoring apparatus which concerns on 1st Embodiment of this invention. It is an image of a moving object detection unit of the monitoring device according to the first embodiment of the present invention, and shows a state transition in which a subject enters a bed. It is the result image of the moving body detection of the monitoring device corresponding to the state transition of FIG. 9, and the output of the biological signal detection unit. It is an image of a moving object detection unit of the monitoring device according to the first embodiment of the present invention, and shows a state in which a subject leaves the bed and the curtain near the bed moves. It is the result image of the moving body detection of the monitoring device corresponding to the state transition of FIG. 11 and the output of the biological signal detection unit. It is an image of a moving object detection unit of the monitoring device according to the first embodiment of the present invention, and shows a state in which a subject enters the bed and the curtain near the bed moves. It is the result image of the moving body detection of the monitoring device corresponding to the state transition of FIG. 13 and the output of the biological signal detection unit. It is explanatory drawing which shows the discriminating method of the biological signal of the subject who is in the bed state by the monitoring device which concerns on 1st Embodiment of this invention. It is explanatory drawing which shows the discriminating method of the biological signal of the subject who shifts to the bed-filled state by the monitoring device which concerns on 1st Embodiment of this invention. It is a block diagram of the monitoring apparatus which concerns on 2nd Embodiment of this invention. It is explanatory drawing which shows the discrimination method of the biological signal and the body movement of the subject by the monitoring device which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the application example of the monitoring apparatus which concerns on 4th Embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<First Embodiment>
First, the schematic configuration of the monitoring device according to the first embodiment of the present invention will be described with reference to FIG. FIG. 1 is a configuration diagram showing an application example of the monitoring device.

The monitoring device 1 is installed in a nursing care facility as shown in FIG. 1, for example. The long-term care facility includes, for example, a staff station 100, a living room 110, and a wired LAN (Local Area Network) 300. The number of living rooms 110 shown in FIG. 1 is two, but more living rooms may be provided.

The staff station 100 is a so-called stuffing place for caregivers who support the lives of the care recipients who spend their time in the care facility.

A bed 111 used by the care recipient is installed in the living room 110. One bed 111 is installed in each of the living rooms 110 shown in FIG. 1, but when two or more care recipients move into the living room 110, a plurality of beds 111 corresponding to each of the care recipients are installed. Will be done.

The wired LAN 300 is installed for communication between the staff station 100 and the living room 110. A wireless LAN may be installed instead of the wired LAN 300.

A server device 101 communicatively connected to the wired LAN 300 is installed in the staff station 100. The server device 101 receives various signals from the monitoring device 1 and processes the signals to notify the caregiver and the nurse of the facility of the health condition of the care recipient and the like. The server device 101 includes a display unit 102 as an example of the notification unit.

The display unit 102 includes a display device used in a computer such as a display. The display unit 102 displays an indoor image of the living room 110 received from the monitoring device 1, biological information of the care recipient, and the like. The display unit 102 may be a display device such as a mobile terminal owned by the caregiver and linked to the server device 101.

The monitoring device 1 is installed on the ceiling 110a of each living room 110 in association with the bed 111 of each living room 110, and is communicably connected to the wired LAN 300. When two or more care recipients (subject P) move into the living room 110 and a plurality of beds 111 corresponding to each move in, the care recipient (subject P) is individually dealt with. A plurality of monitoring devices 1 are installed.

Subsequently, the detailed configuration of the monitoring device 1 will be described with reference to FIGS. 2 to 7. FIG. 2 is a block diagram of the monitoring device 1. FIG. 3 is an image of the motion detection unit of the monitoring device 1 and an explanatory diagram showing the state transition of the subject. 4 and 5 are graphs showing the output (AD output value and power spectrum) of the biological signal by the biological signal detection unit of the monitoring device 1. 6 and 7 are graphs showing the output (AD output value and power spectrum) of the noise signal by the biological signal detection unit of the monitoring device 1.

As shown in FIG. 2, the monitoring device 1 includes a moving object detection unit 11, a video signal processing unit 12, a biological signal detection unit 21, a sensor signal processing unit 22, a comprehensive judgment unit 31, a control unit 32, and timekeeping for measuring various times. A unit 33 is provided.

The motion detection unit 11 includes a camera for detecting the movement and state of the subject by video. The motion detection unit 11 is installed toward the bed 111 of each living room 110, and captures a state of the subject entering, leaving the bed, falling, etc. as an image. The moving object detection unit 11 is provided with a near-infrared light projecting unit (not shown) in which the IR cut filter is removed so that the state of the subject can be imaged even in a pitch-black environment. Further, the camera of the moving object detection unit 11 can take an image of the entire living room by providing a wide-angle lens.

The video signal processing unit 12 processes the video signal received from the moving object detection unit 11 and detects a state such as entering or leaving the subject from the video. The video signal processing unit 12 includes an image processing unit 13 and an action determination unit 14.

The image processing unit 13 executes image processing for detecting a region in which movement can be seen from the image captured by the moving object detection unit 11. As a method for detecting moving objects by image processing, methods such as background subtraction method, time difference method, template matching method, and optical flow method can be applied.

The action discriminating unit 14 discriminates the movement of the moving object detected by performing image processing by the image processing unit 13. FIG. 3 shows the entire image region 11a captured by the moving object detection unit 11, and the bed area 15a as a predetermined region, the boundary area 15b and the out-of-bed area 15c, which are other regions, are predetermined. The bed area 15a as a predetermined area is set by using the image of the living room 110 taken when no one is present. For the subject P who moves with respect to the bed area 15a, the boundary area 15b, and the out-of-bed area 15c, for example, as shown by an arrow in FIG. 3, the behavior determination unit 14 is obtained from the moving object detection unit 11 via the image processing unit 13. Based on the above information, the presence or absence of the subject P in the bed area 15a is determined. The boundary area 15b between the bed area 15a and the out-of-bed area 15c does not have to be an area having a large area, and may be a line.

The biological signal detection unit 21 comprises a microwave Doppler sensor for radiating and receiving radio waves to individually detect the biological signal of the subject. The biological signal detection unit 21 includes a radiation unit and a reception unit (not shown), for example, radiates microwaves in the 24 GHz band toward the bed 111 of each living room 110, and receives the Doppler-shifted reflected wave reflected by the subject. .. The biological signal detection unit 21 detects the respiratory state and heart rate of the subject from the reflected wave.

4 and 5 show an example of the biological signal detected by the biological signal detection unit 21. On the other hand, FIGS. 6 and 7 show an example of a noise signal detected by the biological signal detection unit 21. 4 and 6 show the output signal waveform of the biological signal detection unit 21 when the horizontal axis is time and the vertical axis is the AD output value. 5 and 7 show the output signal waveform of the biological signal detection unit 21 when the horizontal axis is the Doppler frequency and the vertical axis is the power spectrum after Fourier transform.

A biological signal is a signal detected by a Doppler sensor in response to a movement of the body surface synchronized with respiration. A normal person breathes generally at about 15 to 25 times / minute, and when the sensor output is frequency-analyzed, a strong peak appears at about 0.3 Hz. On the other hand, the noise signal of the Doppler sensor has a weak power and little change, so a clear peak does not appear. Comparing these waveforms reveals clearly different characteristics, so that the biological signal of the subject can be detected by using the biological signal detection unit 21.

The sensor signal processing unit 22 processes the sensor signal received from the biological signal detection unit 21 and detects a state such as the presence or abnormality of the subject from the signal data. The sensor signal processing unit 22 includes a signal cutting unit 23, a frequency analysis unit 24, and a biological signal discrimination unit 25.

The signal cutting unit 23 cuts out digital data continuously received from the biological signal detecting unit 21 in time series for a predetermined relatively short time. As a data cutting method, for example, an SFTT (Short Time Fourier Transform) method can be used. When observing the presence or absence of respiration of about 0.3 Hz, it is desirable to set the cutout cycle between 10 seconds and 1 minute from the viewpoint of achieving both frequency resolution and time resolution. Frequency analysis assumes an infinite length repetitive signal, and for that purpose, it is common to perform processing to smooth the end of the data section with a window function. Further, it is possible to improve the time resolution by overlapping the cutout data sections. The overlap is preferably between 1/2 and 1/4 of the data interval. The cutting interval is generally constant, but it may be changed each time the cutting is performed.

The frequency analysis unit 24 performs an operation related to frequency analysis on the signal data cut out by the signal cutting unit 23. The FFT (Fast Fourier Transform) method can be used for the calculation of the frequency analysis unit 24. Further, a DFT (Discrete Fourier Transform) method, a DCT (Discrete Cosine Transform) method, or a wavelet transform may be used.

The biological signal discrimination unit 25 discriminates the presence or absence of a biological signal from the signal data subjected to the frequency analysis process by the frequency analysis unit 24 based on the peak value. The biological signal discriminating unit 25 finds the peak value having the strongest power within 0.2 to 0.5 Hz, which is the normal range of the respiratory frequency, in the power spectrum after FFT, and sets a preset threshold value (the position of the broken line in FIG. 5). Compare if it is greater than (value of). When the peak value is larger than the threshold value, the biological signal discriminating unit 25 determines that there is a biological signal. In other cases, the biological signal discrimination unit 25 determines that there is no biological signal. For example, if there is nothing moving, it is determined that there is no breathing because the power is below the threshold value. In addition, the power spectrum is distributed at a higher frequency when movements other than humans, for example, only a fan continues to rotate. As a result, the peak value is no longer in the normal range of the respiratory frequency, so that the peak above the threshold value does not appear in the normal range of 0.2 to 0.5 Hz of the respiration, and it is determined that there is no biological signal. In this way, the biological signal discriminating unit 25 determines the presence or absence of the biological signal depending on whether or not the peak value having the strongest power within the normal range of 0.2 to 0.5 Hz is larger than the preset threshold value. ..

The comprehensive determination unit 31 receives each determination result from the video signal processing unit 12 and the sensor signal processing unit 22, makes a comprehensive judgment to determine the state of the subject, and holds the state of the subject. .. Further, the comprehensive determination unit 31 generates various signals to be transmitted to the server device 101 regarding the state of the subject.

The control unit 32 is composed of a calculation unit, a storage unit, and other electronic components (not shown), and receives information from the moving object detection unit 11 and the biological signal detection unit 21 based on the programs and data stored and input in advance in the storage unit and the like. At the same time, the operation of the components including the video signal processing unit 12, the sensor signal processing unit 22, and the comprehensive determination unit 31 is controlled to realize image processing and signal processing related to the detection of the state of the subject. Further, the control unit 32 exchanges information with the server device 101.

Subsequently, a method for determining the state of the presence or absence of the subject by the monitoring device 1 will be described with reference to FIGS. 8 to 14. FIG. 8 is a state transition diagram of the subject used in the monitoring device 1. 9 and 10 are an image of the moving body detection unit 11 showing a state transition in which the subject enters the bed, a result image of the moving body detection, and an output of the biological signal detection unit 21. 11 and 12 are an image of the moving object detection unit 11 showing a state in which the subject has left the bed and the curtain near the bed has moved, a result image of the moving object detection, and an output of the biological signal detection unit 21. 13 and 14 are an image of the moving object detection unit 11 showing a state in which the subject enters the bed and the curtain near the bed moves, an image of the result of the moving object detection, and an output of the biological signal detection unit 21.

Regarding the state transition of the subject shown in FIG. 8, when the subject P who is out of bed enters the boundary area 15b (see FIG. 3) (see the upper side of FIG. 9), the behavior determination unit 14 is examined as the moving body M. The movement of the person P and the movement of the futon 112 are discriminated (see the upper left side of FIG. 10). After that, when the subject P enters the bed 111, the behavior determination unit 14 determines the entry of the moving object M into the bed area 15a, and the comprehensive determination unit 31 determines that the moving object M is in the “on the way to bed” state. Determine. The “state on the way to bed” means an intermediate state in which the subject enters the bed area 15a from the boundary area 15b.

When the subject P, whose behavior determination unit 14 is determined to be in the “on-the-floor state”, goes to bed (see the lower side of FIG. 9), the movement is reduced and the behavior determination unit 14 does not detect it as a moving object M (FIG. 10). See lower left).

Here, regarding the discrimination of the biological signal discriminating unit 25, during the movement of the subject P to the bed area 15a, changes occur in response to various movements of each part of the body of the subject P. A random signal with a large amplitude is detected (see the upper right side of FIG. 10). In this case, since a specific peak does not appear in a predetermined frequency band (for example, 0.2 to 0.5 Hz), the biological signal discrimination unit 25 determines that there is no biological signal.

When the subject P enters the bed 111 and goes to bed, the biological signal discriminating unit 25 determines that there is a biological signal in response to a relatively stable periodic body movement due to resting breathing. The determination result of the presence or absence of the biological signal is received from the sensor signal processing unit 22, and the comprehensive determination unit 31 changes the state of the subject P (moving object M) from the "in-floor state" to the "bed-in state". The "bed-in state" means that the subject P is sleeping at rest.

When the biological signal determination unit 25 determines the disappearance of the biological signal in the "bed-in state", the comprehensive determination unit 31 determines that the subject P is in an abnormal state, and notifies the server device 101 that it should be transmitted. Generate a signal. This notification signal is transmitted to the server device 101, and an abnormality is notified using the display unit 102 or the like.

11 and 12 show a state in which the curtain C near the bed is moving when the subject P is out of bed 111, and it is erroneously recognized that the subject P has entered the bed by discriminating only the image. An example that is easy to do is shown. When the curtain C near the bed moves and enters the bed area 15a (see the lower side of FIG. 11), the action determination unit 14 determines the movement of the curtain C as the moving body M (see the lower left side of FIG. 12), and the overall result is The determination unit 31 determines that the moving body M is in the “on the way to bed” state.

However, since the sensor signal processing unit 22 does not detect the biological signal (see the lower right side of FIG. 12), the "in-floor state" is maintained and does not transition to the "bed-in state". After that, when the biological signal cannot be detected after the elapse of a predetermined time predetermined in the "state in the middle of getting into bed", the comprehensive determination unit 31 shifts the state related to the moving body M to the "state of getting out of bed".

If the biological signal is not discriminated and is discriminated only by the image, there is a risk that if the curtain C near the bed moves and enters the bed area 15a, it may be determined that the patient is in the bed-accessible state, and there is no biological signal thereafter. There is a high possibility of detecting this and falsely reporting that the subject P is in an abnormal state. However, in the present embodiment, it is possible to prevent the occurrence of false alarms by the above processing.

13 and 14 show a state in which the curtain C near the bed is moving when the subject P is in bed 111, and the subject P is in the process of getting out of bed by determining only the image. It shows an example that is easy to misreport. When the subject P moves to the bed area 15a while the subject P is sleeping at rest (see the lower side of FIG. 13), the behavior determination unit 14 determines the movement of the curtain C as the moving body M. (See the lower left side of FIG. 14), the comprehensive determination unit 31 determines that the moving body M is in the “halfway state of getting out of bed”. The “state in the middle of getting out of bed” means an intermediate state in which the subject leaves from the bed area 15a to the boundary area 15b.

However, since the sensor signal processing unit 22 continues to detect the biological signal (see the lower right side of FIG. 14), it is assumed that the movement does not continue to get out of bed, and the comprehensive judgment unit 31 enters from the "state in the middle of getting out of bed". Return to "floor condition".

If the biological signal is not discriminated and is discriminated only by the image, if the curtain C near the bed moves and enters the bed area 15a, it may be determined that the subject P is in the process of getting out of bed. There is a high possibility of false alarms after that. However, in the present embodiment, it is possible to prevent the occurrence of false alarms by the above processing. The same process is performed when only the limbs of the subject P enter the boundary area 15b while sleeping.

In this way, it is determined whether or not the subject P is present in the bed 111 based on the information of both the body movement of the subject P and the biological signal. The accuracy is improved as compared with the case where the presence or absence of the subject P is determined based on the information of either the body movement of the subject P or the biological signal. Therefore, the existence and biological information of the subject P can be accurately grasped, and abnormalities in the health condition of the subject P can be suitably found.

Subsequently, the details of the method for discriminating the biological signal of the subject by the monitoring device 1 will be described with reference to FIGS. 15 and 16. FIG. 15 is an explanatory diagram showing a method for discriminating the biological signal of the subject who is in the bed state by the monitoring device 1, and FIG. 16 is a method for discriminating the biological signal of the subject who shifts to the bed state by the monitoring device 1. It is explanatory drawing which shows.

The abnormality in which the biological signal disappears means, for example, when the subject stops breathing while sleeping and cannot see any movement of the body. If it is decided to detect the state in which the subject is not moving within a predetermined determination period (for example, 10 minutes), it is necessary to comprehensively determine the determination result of the presence or absence of a biological signal in the past 10 minutes. There is.

There will be a time lag before the determination result is finalized. Due to this time lag, there is a possibility that a problem may occur when the determination result of the presence or absence of the biological signal is directly linked with the bed entry determination using the image by the behavior determination unit 14. Therefore, in the present embodiment, this problem is addressed by the following method for discriminating the biological signal of the subject.

In order for the biological signal processing unit 22 to determine the presence or absence of the biological signal in the biological signal processing unit 22, the sensor signal received from the biological signal detection unit 21 is cut out by the signal cutting unit 23 and the frequency is cut out by the frequency analysis unit 24 as described above. Perform the analysis. The sensor signal processing unit 22 executes this series of processes by sequentially overlapping them by 1/4.

FIG. 15 shows a state in which the movement of the body of the subject who is in the bed state is stopped. For example, as shown in FIG. 15, the sensor signal processing unit 22 cuts out a signal for 16 seconds from the sensor signal, executes frequency analysis every 4 seconds, and obtains a biological signal. Then, the sensor signal processing unit 22 calculates the ratio of the period with the biological signal to the biological signal obtained every 4 seconds in a predetermined determination period (for example, 10 minutes). As a result, it is possible to make it less susceptible to discrimination errors in a short period of time. When the ratio of the period with the biological signal decreases and reaches, for example, 50%, the biological signal discrimination unit 25 determines the disappearance of the biological signal, and the comprehensive judgment unit 31 determines that the subject P is in an abnormal state. To generate a notification signal.

FIG. 16 shows the state before and after the subject P enters the bed. According to FIG. 16, in the state where there is no biological signal before entering the bed (for example, the discrimination period set to 10 minutes), the generation of the notification signal related to the abnormality is turned on, but the generation of the notification permission signal is turned off. You can see that it is. That is, at this stage, the notification signal is not transmitted to the server device 101. In such a state where there is no biological signal, the notification signal is turned on to maintain a state in which the notification signal related to the abnormality can be transmitted at any time. However, since it is not possible to determine whether the notification signal is due to the subject P getting out of bed or due to the abnormal state of the subject P in the absence of the biological signal, the transmission of the notification signal is permitted. It is controlled by the presence or absence of a signal.

The bedtime is counted from the timing when the subject P enters the bed (the timing when the ratio of the period with the biological signal starts to increase from around 0%). As described above, the ratio of the period with the biological signal in the predetermined determination period is calculated, and the sensor signal processing unit 22 executes this series of processing by sequentially overlapping by 1/4. Therefore, it is 0% at the timing of entering the bed, but the proportion of the period with the biological signal gradually increases as the bed time elapses. Then, when the ratio of the period with the biological signal reaches, for example, 50%, the generation of the notification signal is turned off. Further, when the bedtime exceeds a predetermined threshold value corresponding to the time when the ratio of the period with the biological signal becomes 100%, the generation of the notification permission signal is turned on. In this way, the threshold value of the bedtime is set to a value at which neither the notification signal nor the notification permission signal is turned on. In other words, it is controlled in association with the threshold value of the bedtime so that the notification permission signal is turned on after the notification signal is turned off. By controlling in this way, it is possible to suppress the occurrence of a false alarm in which the subject P is determined to have no biological signal immediately after entering the bed due to the time lag until the determination result is confirmed. .. As shown in FIG. 15, when the ratio of the period with the biological signal becomes 100% and then falls below 50%, the notification signal is transmitted to the server device 101 assuming that the subject P is in an abnormal state. ..

<Second Embodiment>
Next, the monitoring device according to the second embodiment of the present invention will be described with reference to FIGS. 17 and 18. FIG. 17 is a block diagram of the monitoring device, and FIG. 18 is an explanatory diagram showing a method of discriminating the biological signal and body movement of the subject by the monitoring device. Since the basic configuration of this embodiment is the same as that of the first embodiment described above, the components common to the first embodiment are designated by the same reference numerals as before, and the description thereof will be omitted. And.

The monitoring device 1 of the second embodiment includes the sensor signal processing unit 42 shown in FIG. The sensor signal processing unit 42 includes a first signal cutting unit 43, a frequency analysis unit 24, a biological signal discriminating unit 25, a second signal cutting unit 44, a power analysis unit 45, and a body motion discriminating unit 46. Since the first signal cutting unit 43, the frequency analysis unit 24, and the biological signal discrimination unit 25 perform the same signal processing as in the first embodiment, the description thereof will be omitted here.

The second signal cutting unit 44 cuts out a signal at a time interval different from that of the first signal cutting unit 43 for detecting a biological signal. The power analysis unit 45 calculates the sum of squares of the amplitudes of the signals cut out by the second signal cutting unit 44. The body movement determination unit 46 determines that there is body movement when the output from the power analysis unit 45 exceeds a predetermined threshold value.

In the monitoring device 1 of the second embodiment, when the subject P enters the bed 111 with respect to the state transition of the subject shown in FIG. 8, the sensor signal processing unit 42 moves to the bed area 15a based on the sensor signal. The approach of M is determined, and the comprehensive determination unit 31 determines that the moving body M is in the “on-the-bed state”. Further, the video signal processing unit 12 determines the entry of the moving object M into the bed area 15a based on the image of the camera, and the comprehensive determination unit 31 changes the state of the subject P (moving object M) from the “on-the-floor state”. Change to "bed-in state".

As shown in FIG. 18, when the subject P enters the bed, a large body movement is involved, so that the sensor signal suddenly changes from a state in which nothing can be detected to a random waveform having a large power. The second signal cutting unit 44, the power analysis unit 45, and the body movement determination unit 46 detect the change accompanying the large body movement, and the sensor signal processing unit 42 determines the entry of the subject P into the bed area 15a. The same process can be realized when the subject leaves the bed.

Since body movement is an event that is shorter in time than a biological signal such as breathing, the time interval for cutting out the signal by the second signal cutting unit 44 is set to the time interval of cutting out the signal by the first signal cutting unit 43 in the case of a biological signal. It is desirable to set it shorter than the time interval to improve the time responsiveness (see FIG. 18). In particular, since the determination of getting out of bed is a highly urgent event, it is even more effective to improve the time responsiveness.

<Third Embodiment>
Next, the monitoring device according to the third embodiment of the present invention will be described. Since the basic configuration of this embodiment is the same as that of the first and second embodiments described above, the components common to those embodiments are designated by the same reference numerals as before and the description thereof is omitted. It shall be.

The monitoring device 1 of the third embodiment does not provide an order for discrimination by the video signal processing unit 12 and the sensor signal processing unit 22 described in the first and second embodiments. In addition, it is possible to combine the discrimination based on the image and the discrimination based on the biological signal as the transition conditions for entering / leaving the bed without explicitly defining the intermediate states such as "the state in the middle of entering the bed" and "the state in the middle of leaving the bed". ..

<Fourth Embodiment>
Next, the monitoring device according to the fourth embodiment of the present invention will be described with reference to FIG. FIG. 19 is a configuration diagram showing an application example of the monitoring device. Since the basic configuration of this embodiment is the same as that of the first and second embodiments described above, the components common to those embodiments are designated by the same reference numerals as before and the description thereof is omitted. It shall be.

In the monitoring device 1 of the fourth embodiment, as shown in FIG. 19, the biological signal detection unit 21 is installed in the vicinity of the bed 111 independently of the main body of the monitoring device 1. For example, wireless communication is used for communication between the main body of the monitoring device 1 and the biological signal detection unit 21.

Instead of the Doppler sensor, the biological signal detection unit 21 can use a sensor capable of capturing minute movements such as heartbeat and respiration. In particular, when the biological signal detection unit 21 is fixed to the bed 111 and used, various vibration sensors can also be used.

According to this configuration, since the biological signal detection unit 21 is installed in the vicinity of the bed 111, the biological signal of the subject P can be detected by specializing in an event around the bed 111 (for example, the movement of the subject P or the futon). It is possible to detect it, and it is possible to improve the accuracy of determining the presence or absence of the biological signal of the subject P.

As in the first to fourth embodiments, the monitoring device 1 includes a moving object detecting unit 11 for detecting the movement of the subject P and a biological signal detecting unit for detecting the biological signal of the subject P. The behavior determination unit 14 that determines the presence or absence of the subject P in the bed area 15a determined in advance based on the information obtained from the moving object detection unit 11 and the subject P based on the information obtained from the biological signal detection unit 21. The biological signal discriminating unit 25 for discriminating the presence or absence of the biological signal of the above is provided. Then, the monitoring device 1 determines the presence or absence of the subject P in the bed area 15a based on the information of both the discrimination by the behavior discrimination unit 14 and the discrimination by the biological signal discrimination unit 25.

According to this configuration, whether or not the subject P is present in the bed 111 of the living room 110 is determined based on both the information of the body movement of the subject P and the biological signal. The accuracy of the determination can be improved as compared with the case where the presence or absence of the subject P is determined based on the information of either the body movement of the subject P or the biological signal. Therefore, it becomes possible to accurately grasp the existence of the subject P.

Further, the monitoring device 1 is provided with a time measuring unit 33 for measuring the time, and after confirming the existence of the subject P in the bed area 15a, the subject P is after a predetermined determination period (for example, 10 minutes) has elapsed. If the biological signal of the subject cannot be detected, it is determined that the subject P has an abnormality and a notification signal is output.

According to this configuration, it becomes possible to suitably find abnormalities in the health condition of the subject P.

Then, as in the first embodiment, the behavior determination unit 14 is in the "intermediate state" in which the subject P enters from the outside of the bed area 15a to the inside, or from the inside to the outside of the bed area 15a. The monitoring device 1 discriminates the "intermediate state of getting out of bed", which is the intermediate state in which the subject P leaves, the behavior discriminating unit 14 discriminates between those intermediate states, and the biological signal discriminating unit 25 determines the biological signal of the subject P. The presence or absence of the subject P in the bed area 15a is determined based on the determination of the presence or absence.

Further, as in the second embodiment, the biological signal discrimination unit 25 is in an intermediate state in which the subject P enters from the outside of the bed area 15a to the inside, or is in the middle of entering the bed, or from the inside to the outside of the bed area 15a. The "state in the middle of getting out of bed", which is an intermediate state in which the subject P leaves the bed, is determined, and the monitoring device 1 determines the intermediate states by the biological signal discrimination unit 25, and the behavior determination unit 14 determines the subject in the bed area 15a. The presence or absence of the subject P in the bed area 15a is determined based on the determination of the presence or absence of P.

According to these configurations, it is possible to distinguish between the transition state of entering and leaving the bed by the subject P and the state in which only the curtain C near the bed and the limbs of the subject P move. Therefore, the existence of the subject P can be grasped more accurately, and a false alarm that the subject P is in an abnormal state can be suppressed.

Further, the bed area 15a is an arrangement area of the bed 111 of the subject P.

According to this configuration, it is possible to accurately grasp the entry / exit of the subject P with respect to the bed 111.

Further, the moving object detection unit 11 is composed of a camera capable of capturing an image of the bed area 15a.

According to this configuration, it is possible to accurately detect the movement and state of the subject P with respect to the bed area 15a by the image.

Further, the biological signal detection unit 21 includes a Doppler sensor that radiates and receives microwaves.

According to this configuration, the biological signal of the subject P can be accurately detected from a distant place by using the microwave.

Although the embodiments of the present invention have been described above, the scope of the present invention is not limited to this, and various modifications can be made without departing from the gist of the invention.

For example, as the camera constituting the moving object detecting unit 11 shown in the above embodiment, any method can be adopted as long as the movement of the subject's body can be captured. For example, an optical image sensor, infrared rays, etc. A two-dimensional image sensor, a three-dimensional image sensor, or the like can be selected.

The present invention can be used in a monitoring device for detecting abnormalities in the health condition of a person who spends time in a nursing care facility or the like.

1 Monitoring device 11 Moving object detection unit 12 Video signal processing unit 13 Image processing unit 14 Behavior discrimination unit 21 Biometric signal detection unit 22, 42 Sensor signal processing unit 23 Signal cutting unit 24 Frequency analysis unit 25 Biometric signal discrimination unit 31 Comprehensive judgment unit 32 Control unit 33 Timing unit 43 1st signal cutout unit 44 2nd signal cutout unit 45 Power analysis unit 46 Body movement discrimination unit

Claims (6)

A motion detector for detecting the movement of the subject in the living room,
A biological signal detection unit for detecting the biological signal of the subject,
A behavior determination unit that determines the presence or absence of a subject in the bedding arrangement area of the subject in the living room based on the information obtained from the motion detection unit.
A biological signal discrimination unit that determines the presence or absence of a biological signal of a subject based on information obtained from the biological signal detection unit, and a biological signal discrimination unit.
With
The behavior determination unit includes the bedding arrangement area, the bedding outer area, the bedding arrangement area, and the bedding outer area preset with respect to the image area in the living room imaged by the moving object detection unit. Determine the presence or absence of the subject in the boundary area between
Based on the behavior determination unit determining the entry of the subject from the boundary area to the bedding arrangement area, it is determined that the subject is in the middle of bed, and the subject is in the middle of bed. Based on the determination by the biological signal discriminating unit that the examiner has the biological signal, it is determined that the subject is in the bed-accessible state.
Based on the behavior determination unit determining the exit of the subject from the bedding arrangement area to the boundary area, it is determined that the subject is in the state of getting out of bed, and the subject is in the state of getting out of bed. A monitoring device characterized in that it is determined that the subject is in a state of getting out of bed based on the determination by the biological signal discriminating unit that the biological signal is absent. It is equipped with a timekeeping unit that measures time, and after determining the presence of the subject in the bedding placement area, the subject is notified when the biological signal of the subject cannot be detected after the elapse of a predetermined determination period. The monitoring device according to claim 1, wherein an abnormality is determined and a notification signal is output. Determine the intermediate state in which the biological signal discrimination unit is the subject leaves the inside to the outside of the intermediate state subject enters the inside from the outside of the arrangement region of the bedding or arrangement region of the bedding, the biological It is characterized in that the presence or absence of a subject in the bedding arrangement area is determined based on the determination of the intermediate state by the signal discrimination unit and the determination of the presence or absence of the subject in the bedding arrangement area by the behavior determination unit. The monitoring device according to claim 1 or 2. The monitoring device according to any one of claims 1 to 3, wherein the moving object detecting unit comprises a camera capable of capturing an image of the bedding arrangement area. The monitoring device according to any one of claims 1 to 4, wherein the biological signal detection unit includes a Doppler sensor that radiates and receives radio waves. The monitoring according to any one of claims 1 to 5 , further comprising a main body portion and the biological signal detection unit installed in the vicinity of the bedding arrangement area independently of the main body portion. apparatus.

Images