WO2019031012A1

WO2019031012A1 - Action detection device and method therefor, and monitored person monitoring assist system

Info

Publication number: WO2019031012A1
Application number: PCT/JP2018/018636
Authority: WO
Inventors: 和馬新田; 保理江　大作
Original assignee: コニカミノルタ株式会社
Priority date: 2017-08-10
Filing date: 2018-05-15
Publication date: 2019-02-14
Also published as: JPWO2019031012A1; JP7137154B2

Abstract

The action detection device and method therefor, and monitored person monitoring assistance system according to the present invention measure a monitored person with each of first and second sensors, determine the sleeping state of the monitored person on the basis of a first measurement result from the first sensor, determine a prescribed action of the monitored person on the basis of a second measurement result from the second sensor, and control determination processing of the action according to the sleeping determination result.

Description

ACTION DETECTING APPARATUS, METHOD THEREOF, AND supervised person monitoring support system

The present invention relates to an action detection apparatus and an action detection method for detecting a predetermined action of a person to be monitored which is a monitoring target to be monitored. And this invention relates to the to-be-monitored person monitoring assistance system using this action detection apparatus.

Japan (Japan) has become an aging society, more specifically, a super aging society with an aging rate exceeding 26.7% (as of October 1, 2015, the Cabinet Office). In such an aging society, nurses who need nursing or nursing care due to illness, injury or old age, etc. (needed caregivers) need nursing care that occurs in a normal society that is not an aging society The number is expected to increase more than people who need care and those who need care. These caretakers generally enter facilities such as hospitals and welfare facilities for the elderly (in Japan, according to Japanese laws and regulations for the elderly, nursing homes and nursing homes for the elderly, etc.) receive. In such facilities, nurses and carers etc. (nursing carers) check their safety and security by regularly patrolling them.

However, the number of nursing carers has not kept pace with the number of carers who need nursing care, and the nursing industry and the care industry are chronically understaffed. Furthermore, since the number of carers and nurses decreases and the workload per person increases during the night shift and night shift hours as compared with the day shift hours, the reduction of the load is required. In order to reduce such labor shortages and the burden on nursing and carers, there is a need for a technology that complements nursing services and nursing services. For this reason, in recent years, there has been researched and developed a monitored person monitoring technology for monitoring (monitoring) a monitored person who is a monitoring target to be monitored of a care receiver required.

As one of such monitored person monitoring techniques, there is a state detecting device disclosed in Patent Document 1. The state detection device disclosed in this patent document 1 is detected by the image processing unit that detects the moving direction of the target person by analyzing an image obtained by imaging the target person on the bed, and the image processing unit A determination unit that determines the current state of the subject based on the moving direction and the past state of the target, and an output that outputs information indicating the current state of the subject obtained by the determination unit. And a unit. The past state and the current state are a landing state in which the subject is lying on the bed, a rising state in which the subject is raising the upper body on the bed, and the bed in which the subject is in the bed And the determination unit is configured to use the different criteria for each of the plurality of types of the past states, and the separated state including the bed leaving state at the end portion of the bed and the absent state in which the subject is separated from the bed. Determine the current state of. More specifically, the determination unit determines the state from the position of the image of the subject relative to the detection area in the past and the current position of the image of the subject relative to the detection area (see FIG. For example, paragraphs [0022] to [0031]).

On the other hand, in terms of safety confirmation, a single person living alone is also the same as the nurse who needs to be a person to be monitored and is a monitored person.

By the way, since the state detection device disclosed in the patent document 1 determines the above-mentioned state as described above, there is a possibility that erroneous determination may be made by the movement of the attendant near the bed, the turning over of the subject, etc. There is. In a system in which the discrimination result is reported (notified, notified) to a monitor such as a nurse or a carer, for example, useless notification to the monitor may be increased if a false alarm is generated due to misclassification, For example, by visiting the site, or confirming with images, the load of work due to a false alarm, for example, the work of confirming the safety of a monitored subject such as a nurse requiring a care or a care requiring person increases. In particular, the occurrence of false alarms due to misclassification is an important issue, particularly in the semi-night shift or night shift hours, when the number of observers decreases.

JP 2012-170483

The present invention is an invention made in view of the above-mentioned circumstances, and an object thereof is an action detection apparatus and an action detection method capable of further reducing misclassification (misjudgment, false detection), and the action detection apparatus It is an object of the present invention to provide a monitored person monitoring support system.

In order to realize the above-mentioned object, the behavior detection device and the behavior detection method reflecting the one aspect of the present invention, and the person-to-be-monitored support system measure the person to be monitored with the first and second sensors, respectively. The sleep state of the person to be monitored is determined based on the first measurement result of one sensor, the predetermined behavior of the person to be monitored is determined based on the second measurement result of the second sensor, and the sleep determination result is Control the action determination process.

The advantages and features provided by one or more embodiments of the invention will be better understood from the detailed description given below and the accompanying drawings. These detailed descriptions and the accompanying drawings are given by way of example only and are not intended as a definition of the limits of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows the structure of the to-be-monitored person monitoring assistance system in embodiment. It is a figure which shows the structure of the sensor apparatus in which the behavior detection apparatus of embodiment in the said person-to-be-monitored monitoring support system was integrated. It is a flowchart which shows operation | movement of the said sensor apparatus in a service mode. It is a flowchart which shows operation | movement of the said sensor apparatus in the action determination processing according to the sleep determination result shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the fall determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the fall determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the entering determination process shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the wake-up determination processing shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the bed leaving determination processing shown in FIG. It is a flowchart which shows operation | movement of the said sensor apparatus in the micro body movement abnormality determination processing shown in FIG. It is a figure which shows an example of the main screen displayed on the said terminal device. It is a figure which shows an example of the 1st setting screen displayed on the said terminal device. It is a figure which shows an example of the 2nd setting screen displayed on the said terminal device. It is a figure which shows an example of the monitoring information screen displayed on the said terminal device.

Hereinafter, an embodiment according to the present invention will be described based on the drawings. However, the scope of the invention is not limited to the disclosed embodiments. In addition, the structure which attached | subjected the same code | symbol in each figure shows that it is the same structure, and abbreviate | omits the description suitably. In the present specification, suffixes are generally indicated by reference numerals without suffixes, and individual configurations are indicated by subscripts.

The monitored person monitoring support system in the embodiment is provided corresponding to the monitored person Ob, and a sensor device for detecting a predetermined action in the monitored person Ob, and communicably connected to the sensor device from the sensor device A central processing unit that manages received detection results, and a terminal device communicably connected to the central processing unit and receiving and displaying the detection results via the central processing unit It is a system to support monitoring. This sensor device includes the behavior detection device in the present embodiment. The behavior detection apparatus in this embodiment determines the sleep state of the monitored person Ob based on the first and second sensors that measure the monitored person Ob and the first measurement result of the first sensor. Controlling the behavior determination unit according to a sleep determination result of the sleep state determination unit, and a behavior determination unit that determines a predetermined behavior of the monitored person Ob based on a second measurement result of the second sensor And a processing control unit. Since this behavior detection device controls the behavior determination unit according to the sleep determination result of the sleep state determination unit, it is possible to further reduce erroneous determinations. In the behavior detection device, in the present embodiment, the second sensor includes first and second sub-sensors that measure the monitored person Ob, and the behavior determination unit measures the first sub-sensor of the first sub-sensor. A first sub-action determining unit that executes a first sub-action determining process of determining a first action belonging to a first group among predetermined actions of the monitored person Ob based on a result; Second sub-action determination that executes a second sub-action determination process of determining a second action belonging to a second group different from the first group among predetermined actions of the monitored person Ob based on a two-sub measurement result And the processing control unit controls at least one of the first and second sub-action determining units according to the sleep determination result of the sleep state determining unit. According to this, it is possible to divide the predetermined action into the first action belonging to the first group which can not occur in the sleep state and the second action belonging to the second group which can occur in the sleep state. Such an action detection device can control the action determination unit more appropriately according to the sleep determination result of the sleep state determination unit, and can further reduce erroneous determinations. The following more specifically describes.

The terminal device may be one type of device, but in the present embodiment, the terminal device is two types of devices, a fixed terminal device and a portable terminal device. The main difference between the fixed terminal device and the mobile terminal device is that while the fixed terminal device is operated in a fixed manner, the mobile terminal device is operated by being carried by a supervisor (user) such as a nurse or a caregiver, for example. These fixed terminal devices and mobile terminal devices are substantially the same.

FIG. 1 is a diagram showing a configuration of a monitored person monitoring support system in the embodiment. FIG. 2 is a diagram showing a configuration of a sensor device in which the behavior detection device of the embodiment is incorporated in the monitored person monitoring support system.

More specifically, for example, as shown in FIG. 1, the monitored person monitoring support system MS includes one or more sensor devices SU (SU-1 to SU-4), a management server SV, and a fixed terminal. A device SP, one or more portable terminal devices TA (TA-1 and TA-2), and a private branch exchange (PBX) CX are provided in a wired or wireless manner and in a LAN (Local Area Network). Etc. communicably connected via a network (network, communication line) NW. The network NW may be provided with relays such as repeaters, bridges and routers for relaying communication signals. In the example shown in FIG. 1, the plurality of sensor devices SU-1 to SU-4, the management server SV, the fixed terminal SP, the plurality of portable terminals TA-1 and TA-2, and the private branch exchange CX are L2 switches. Are connected communicably to each other by a wired / wireless mixed LAN (for example, a LAN according to the IEEE 802.11 standard) NW including the line concentrators (hub, HUB) LS and the access point AP. More specifically, the plurality of sensor devices SU-1 to SU-4, the management server SV, the fixed terminal SP, and the private branch exchange CX are connected to the concentrator LS, and the plurality of mobile terminals TA-1 and TA-2 are connected. Are connected to the concentrator LS via the access point AP. Then, the network NW constructs a so-called intranet by using an internet protocol group such as a transmission control protocol (TCP) and an internet protocol (IP).

The private branch exchange (line switching unit) CX is connected to the network NW, controls extension telephones such as call origination, call reception, and call between the mobile terminal devices TA, and carries out extension telephone calls between the mobile terminal devices TA, For example, it is connected to an outside telephone TL such as a fixed telephone or a mobile telephone through a public telephone network PN such as a fixed telephone network or a mobile telephone network, for example, to make, receive, and make calls between the outside telephone TL and the mobile terminal device TA. , Etc. to control the outside line telephone to carry out the outside line telephone between the outside line telephone TL and the portable terminal device TA. The private branch exchange CX is, for example, a digital exchange, an IP-PBX (Internet Protocol Private Branch eXchange), or the like.

The monitored person monitoring support system MS is disposed at an appropriate place according to the monitored person Ob. The monitored person (watching target person) Ob is, for example, a person who needs nursing due to illness or injury, a person who needs care due to a decrease in physical ability or the like, or a single person living alone. In particular, from the viewpoint of enabling early detection and coping, the person to be monitored Ob is a person who needs the detection when a predetermined adverse event such as an abnormal condition occurs in the person. preferable. For this reason, the person-to-be-monitored monitoring support system MS is suitably disposed in buildings such as hospitals, welfare facilities for the elderly and dwelling units according to the type of the person to be monitored Ob. In the example illustrated in FIG. 1, the monitored person monitoring support system MS is disposed in a building of a care facility provided with a plurality of living rooms RM in which a plurality of monitored persons Ob reside, and a plurality of rooms such as a nurse station. .

The sensor device SU has a communication function and the like for communicating with other devices SV, SP, and TA via the network NW, detects a predetermined event related to the monitored person Ob, and detects the detected event as the management server device SV. To the terminal apparatus SP and TA, and generates an image including a moving image and distributes the moving image to the terminal apparatus SP and TA. The predetermined event (event) preferably includes an event that requires a response. In the present embodiment, the predetermined event includes a predetermined action set in the monitored person Ob and includes a nurse call. Such a sensor device SU includes, for example, as shown in FIG. 2, a sensor unit 11, a sensor side sound input / output unit (SU sound input / output unit) 12, a nurse call reception operation unit 13, and a sensor side control process. A unit (SU control processing unit) 14, a sensor side communication interface unit (SU communication IF unit) 15, and a sensor side storage unit (SU storage unit) 16 are provided.

The sensor unit 11 is connected to the SU control processing unit 14, and is a device that measures predetermined amounts set in advance in the monitored person Ob under the control of the SU control processing unit 14. In the present embodiment, the sensor unit 11 includes a first sensor to determine the sleep state of the monitored person Ob, and includes a second sensor to determine the predetermined action of the monitored person Ob.

In the present embodiment, since the first sensor determines the sleep state of the monitored person Ob based on the respiratory state, any kind of device capable of measuring the respiration of the monitored person Ob as one of the predetermined amounts. It is good. The first sensor may be, for example, a pulsimeter or the like attached to a wrist or the like to measure a pulse, but in the present embodiment, the Doppler sensor 112 can be It comprises and is constituted.

The second sensor includes a first sub-sensor to determine a first action belonging to a first group among the predetermined actions, and belongs to a second group different from the first group among the predetermined actions. A second sub-sensor is provided to determine a second action. The predetermined action is, for example, in the present embodiment, the entering of the monitored person Ob into the bedding BD, the rising of the monitored person Ob, the leaving of the monitored person Ob from the bedding BD, the monitored person The fall includes the fall of Ob from the bedding BD, the fall of the monitored person Ob falling outside the bedding BD, and a micromotion abnormality that is an abnormality of micromotion due to the respiration of the monitored person. And in this embodiment, these predetermined actions are divided into the 1st group which can not occur in a sleep state, and the 2nd group which can arise in a sleep state. The first behavior belonging to the first group which can not occur in this sleep state includes admission, wake up, bed leaving, fall and fall, and the second behavior belonging to the second group which can occur in said sleep condition is slightly different. Physical movement abnormality is included. The first sub-sensor may be any device capable of determining such a first action. The first sub-sensor may be, for example, a thermographic apparatus capable of extracting a human region from a temperature distribution, or a distance image sensor capable of extracting a human region from a distance distribution, but in the present embodiment, the first sub-sensor is based on an image. Since the action is determined, the camera 111 is configured to generate an image as one of the predetermined amounts. The second sub sensor may be any device capable of determining such a second action. In the present embodiment, since the second action is a micromotion abnormality which is a micromotion abnormality due to the respiration of the person being monitored, a device capable of measuring the respiration of the person being monitored Ob as one of the predetermined amounts. For example, the Doppler sensor 112 is comprised. That is, in the present embodiment, the Doppler sensor 112 is shared by the first sensor and the second sub sensor.

As described above, in the present embodiment, the sensor unit 11 includes the camera 111 and the Doppler sensor 112.

The camera 111 is a device that is connected to the SU control processing unit 14 and generates an image (image data) under the control of the SU control processing unit 14. The images include still images (still image data) and moving images (moving image data). The camera 111 is arranged to be able to monitor the space where the person to be monitored Ob is planning to be located (location space; room RM in the arrangement location in the example shown in FIG. 1) An image (image data) obtained by imaging and looking over the imaging target is generated, and an image (target image) of the imaging target is output to the SU control processing unit 14. Preferably, the imaging unit 111 is scheduled to locate the head of the subject Ob in the bedding (for example, a bed or the like) BD in which the subject Ob is lying, since it is highly probable that the entire subject Ob can be imaged. It arrange | positions so that an imaging target can be imaged from the just overhead of the head preset position (usually the arrangement | positioning position of a pillow) currently set. The sensor unit SU uses this camera 111 to obtain an image of the person to be monitored Ob, which is taken from above the person to be monitored Ob, preferably an image of the person to be monitored Ob, which is taken from directly above the planned head position.

Such a camera 111 may be a device that generates an image of visible light, but in the present embodiment, it is a digital infrared camera that generates an infrared image so as to be able to monitor the monitored person Ob even in a relatively dark state. is there. Such a digital infrared camera 111 is, for example, in the present embodiment, an imaging optical system for forming an infrared optical image of an imaging object on a predetermined imaging surface, and matching the light receiving surface with the imaging surface. And an image sensor that converts an infrared optical image of the imaging target into an electrical signal, and an image that is data representing an infrared image of the imaging target by performing image processing on an output of the image sensor An image processing unit that generates data is configured. In the present embodiment, the imaging optical system of the camera 111 is preferably a wide-angle optical system (a so-called wide-angle lens (including a fisheye lens)) having an angle of view capable of imaging the entire room RM provided.

The Doppler sensor 112 is connected to the SU control processing unit 14, and is a device that measures the movement of the body surface of the chest associated with breathing in the monitored person Ob according to the control of the SU control processing unit 14. The Doppler sensor 112 is a body movement sensor that transmits a transmission wave, receives a reflection wave of the transmission wave reflected by an object, and outputs a Doppler signal of a Doppler frequency component based on the transmission wave and the reflection wave. . When the object is moving, the frequency of the reflected wave is shifted in proportion to the moving velocity of the object by the so-called Doppler effect, so the difference between the frequency of the transmission wave and the frequency of the reflected wave (Doppler frequency component) It occurs. The Doppler sensor 112 generates a signal of this Doppler frequency component as a Doppler signal at a predetermined sampling rate, and outputs the signal to the SU control processing unit 14. When the SU control processing unit 14 receives a Doppler signal from the Doppler sensor 112, the SU control processing unit 14 stores the received Doppler signal in the SU storage unit 16 in time series. The transmission wave may be an ultrasonic wave, a microwave or the like, but in the present embodiment, it is a microwave. The microwave can be transmitted through the clothes and reflected by the body surface of the monitored person Ob, so that the movement of the body surface can be detected even if the monitored person Ob wears clothes, which is preferable.

The SU sound input / output unit 12 is a circuit connected to the SU control processing unit 14 for acquiring an external sound and inputting it to the sensor unit SU, and an electric signal representing the sound according to the control of the SU control processing unit 14 It is a circuit for generating and outputting a sound according to. The SU sound input / output unit 12 is configured to include, for example, a microphone that converts acoustic vibration of sound into an electrical signal, and a speaker that converts electrical signal of sound into acoustic vibration of sound. The SU sound input / output unit 12 outputs an electrical signal representing an external sound to the SU control processing unit 14, and converts the electrical signal input from the SU control processing unit 14 into acoustic vibration of sound and outputs the acoustic vibration.

The nurse call reception operation unit 13 is connected to the SU control processing unit 14 and is a switch circuit such as a push button type switch for inputting a nurse call to the sensor device SU. The nurse call reception operation unit 13 may be connected to the SU control processing unit 14 by wire, or may be connected to the SU control processing unit 14 by short distance wireless communication such as Bluetooth (registered trademark) standard, for example.

The SU communication IF unit 15 is a communication circuit that is connected to the SU control processing unit 14 and performs communication according to the control of the SU control processing unit 14. The SU communication IF unit 15 generates the communication signal containing the data to be transferred, which is input from the SU control processing unit 14, in accordance with the communication protocol used in the network NW of the person-to-be-monitored monitoring support system MS The communication signal is transmitted to the other devices SV, SP, TA via the network NW. The SU communication IF unit 15 receives communication signals from other devices SV, SP, and TA via the network NW, extracts data from the received communication signals, and the SU control processing unit 14 can process the extracted data. The data is converted into data of the following format and output to the SU control processing unit 14. The SU communication IF unit 15 includes, for example, a communication interface circuit conforming to the IEEE 802.11 standard or the like.

The SU storage unit 16 is a circuit which is connected to the SU control processing unit 14 and stores various predetermined programs and various predetermined data according to the control of the SU control processing unit 14. The various predetermined programs include, for example, an SU control program that controls each of the units 11 to 13, 15, and 16 of the sensor device SU according to the function of each unit, and a monitored person based on the output of the sensor unit 11. A sleep state determination program for determining the sleep state of Ob, an action determination program for determining a predetermined action of the monitored person Ob based on the output of the sensor unit 11 and notifying the management server apparatus SV; Processing control program for controlling the behavior determination program according to the result of sleep determination, and when the nurse call acceptance operation unit 13 receives a nurse call, the management server SV is notified of that and the SU sound input / output unit 12 Nurse call processing program to make voice call with the terminal device SP, TA by using The video, terminal SP requested the video, which contains control program such as a streaming processing program broadcast streaming to TA. In the various predetermined data, each program such as a sensor device identifier (sensor ID) which is an identifier for identifying and identifying the sensor device SU of its own device, and a communication address of the management server device SV is executed. It contains the necessary data etc. above. The SU storage unit 16 includes, for example, a ROM (Read Only Memory), which is a non-volatile memory element, and an Electrically Erasable Programmable Read Only Memory (EEPROM), which is a rewritable non-volatile memory element. The SU storage unit 16 includes, for example, a random access memory (RAM) serving as a working memory of a so-called SU control processing unit 14 that stores data and the like generated during execution of the predetermined program.

The SU control processing unit 14 controls each unit of the sensor unit SU according to the function of each unit, detects a predetermined event related to the monitored person Ob, and notifies the management server apparatus SV of the detected event. , And a circuit for performing voice communication with the terminal devices SP and TA, and generating an image including a moving image to distribute the moving image to the terminal devices SP and TA. The SU control processing unit 14 includes, for example, a central processing unit (CPU) and peripheral circuits thereof. The SU control processing unit 14 executes the control processing program, whereby the sensor side control unit (SU control unit) 141, the sleep state determination unit 142, the action determination unit 143, the processing control unit 144, and the nurse call processing unit 145 And a streaming processing unit 146 functionally.

The SU control unit 141 controls the respective units 11 to 13, 15, and 16 of the sensor unit SU according to the functions of the respective units, and controls the entire control of the sensor unit SU.

The sleep state determination unit 142 determines the sleep state of the monitored person Ob based on the output of the sensor unit 11, that is, the first measurement result of the first sensor. More specifically, based on the first measurement result of the first sensor, the sleep state determination unit 142 indicates a sleep degree indicating the degree of depth of sleep of the person to be monitored Ob, and reliability with respect to the sleep degree. Find the degree of confidence that represents the degree of In the present embodiment, the sleep state determination unit 142 determines the sleep state based on the Doppler signal of the Doppler sensor 112 which is an example of the first sensor. More specifically, the sleep state determination unit 142 performs, for example, fast Fourier transform (FFT) on the Doppler signal measured within a predetermined time (for example, one minute or two minutes) from the measurement time point to the past. From the obtained spectrum, an average value of amplitudes in a frequency band corresponding to a general respiratory frequency is determined, and the determined average value is compared with a threshold for determining the sleep level (sleep level classification threshold) to obtain sleep. Find the degree. Then, the sleep state determination unit 142 obtains the duration of the obtained sleep degree, compares the duration of the obtained sleep degree with a threshold (reliability category threshold) for determining the reliability, and determines the reliability. Ask. For example, the sleep level classification threshold is appropriately set to one or more using, for example, a plurality of samples. In the present embodiment, the behavior determination unit 143 is controlled as described later depending on whether it is an awake state or a sleep state, so that the sleep level classification threshold is one value for discriminating whether awake or sleep. In order to divide the sleep degree into three stages of low sleep degree, low sleep degree, medium sleep degree, and high sleep degree, the sleep may be deep. It may be a value. Also, for example, the reliability classification threshold is appropriately set to one or more using a plurality of samples, for example. In the present embodiment, the behavior determination unit 143 is controlled as described later depending on whether the reliability is relatively high or the reliability is relatively low. The reliability classification threshold may be a single value for discriminating between high reliability and low reliability, or the reliability may be a high reliability with a relatively high reliability, or a relatively medium reliability. In order to divide into three stages of medium reliability and low reliability with relatively low reliability, all two values may be used. The sleep state determination unit 142 outputs (notifies) the sleep degree and the reliability obtained as described above to the processing control unit 144 as a result of the sleep determination, in the present embodiment.

The action determination unit 143 determines a predetermined action set in the monitored person Ob based on the output of the sensor unit 11, that is, the second measurement result of the second sensor, and notifies the management server SV of the predetermined action. It is In the present embodiment, the predetermined behavior is, as described above, entering, getting up, leaving, falling, falling, and movement abnormality. These entering, getting up, leaving, falling and falling are the first actions belonging to the first group, and are determined based on the output of the camera 111 (target image), and micro movement abnormality is to the second group. This is the second action to be included, and is detected based on the output (Doppler signal) of the Doppler sensor 112. Therefore, the action determination unit 143 functionally determines, based on the first sub-measurement result of the first sub-sensor, the first action belonging to the first group among the predetermined actions in the monitored person Ob. A second group different from the first group among the predetermined behaviors of the person to be monitored Ob based on the first sub behavior determination unit 1431 that executes the sub behavior determination process and the second sub measurement result of the second sub sensor And a second sub-action determination unit 1432 that executes a second sub-action determination process of determining a second action belonging to. More specifically, in the present embodiment, the first sub-action determining unit 1431 determines the first action (entering, getting up, leaving, falling, falling) based on the target image of the camera 111, and manages the management server device. The SV is notified, and the second sub-action determining unit 1432 determines the second action (microbody movement abnormality) based on the Doppler signal of the Doppler sensor 112 and notifies the management server SV.

More specifically, entering, getting up, leaving, falling, falling and abnormal movement are determined as follows. In addition, the area in which the bedding BD is arranged in the target image (the area where the bedding BD is located) is stored in advance in the storage unit 16 as one of the various data, and various threshold values and continuation determination time in the description below. Is appropriately set from a plurality of samples and stored in advance in the storage unit 16 as one of the various data.

In the determination of admission, the first sub-action determining unit 1431 uses the background difference method, for example, from the target image acquired from the camera 111 when the previous state variable (variable storing the action determination result) is If the person area extracted by the above completely overlaps with the area where the bedding BD is located (if the person area is completely within the area where the bedding BD is located), it is provisionally determined as being in bed and the duration of the complete superposition state When it continues beyond the admission continuation determination time, it is finally determined that there is an admission, and the admission is detected. Then, the first sub behavior determination unit 1431 updates the state variable with “in bed”. The admission continuation determination time is a threshold value for ultimately determining that the bed, which is temporarily determined by completely overlapping the extracted person area and the location area of the bedding BD, is the bed.

In the wakeup determination, the first sub-action determination unit 1431 determines that the previous state variable is “bed entry”, and the person area extracted from the target image acquired from the camera 111 this time protrudes from the area of the bedding BD. If the overrun area is equal to or greater than the wakeup determination threshold and less than the departure judgment threshold, it is temporarily determined to be up, and the duration of the overrun area in a state above the wakeup determination threshold and less than the departure judgment threshold continues to be up If it exceeds the determination time, it is finally determined that there is wakeup, and the wakeup is detected. Then, the first sub behavior determination unit 1431 updates the state variable with “wake up”. The wakeup determination threshold is a threshold for determining whether or not to get up based on the size of the protrusion region, and the departure determination threshold is determined whether to leave the bed according to the size of the protrusion region The departure determination threshold is set to a value larger than the wake-up determination threshold. The wake-up continuation determination time is a threshold for determining that the wake-up temporarily determined by comparing the protrusion region and the wake-up determination threshold is finally a wake-up.

In the determination of leaving, the first sub-action determining unit 1431 determines that the previous state variable is any one of “arriving” and “rising”, and the person area extracted from the target image acquired from the camera 111 this time When the overrun area which is out of the area of the bedding BD is equal to or more than the bed leaving determination threshold, it is temporarily determined to be bed leaving and the continuation time of the over bump area in the state of being over the bed leaving decision threshold exceeds the bed continuation determination time When it is determined, it is finally determined that there is a bed, and the bed is detected. Then, the first sub behavior determination unit 1431 updates the state variable with “bedding off”. The bed leaving continuation determination time is a threshold value for finally determining that bed leaving which has been tentatively determined by comparing the protruding area with the bed leaving determination threshold is bed leaving.

In the fall determination, the first sub-action determination unit 1431 determines that the size of the head region of the human region extracted from the target image acquired from the camera 111 at this time is equal to or less than the lying posture determination threshold. When the change speed of the size is equal to or more than the fall judgment speed threshold and the person area is in the fall judgment area set around the area where the bedding BD is located, it is judged that there is a fall and the fall is determined. Detect The lying posture determination threshold is a threshold for determining whether or not the size of the head region in the lying posture is. The fall determination speed threshold is a threshold for determining whether or not a fall is caused by the change speed of the size of the head region.

In the fall determination, the first sub-action determination unit 1431 determines that the size of the head region of the person region extracted from the target image acquired from the camera 111 at this time is equal to or less than the lying posture determination threshold. When the change speed of the size is equal to or more than the fall determination speed threshold and the person area is in the area excluding the area where the bedding BD is located and the fall determination area, it is determined that there is a fall and the fall is detected. . The fall determination speed threshold value is a threshold value for determining whether or not it is a fall according to the change speed of the size of the head region.

In the micro movement abnormality, the second sub behavior determination unit 1432 determines the micro movement abnormality based on the Doppler signal of the Doppler sensor 112 which is an example of the second sub sensor. More specifically, as in the sleep state determination unit 141, the second sub-action determination unit 1432 performs, for example, fast Fourier transform (FFT) on the Doppler signal measured within a predetermined time from the measurement time point to the past. From the spectrum obtained by FFT, an average value of amplitudes in a frequency band corresponding to a general respiration frequency is determined, and the determined average value and a threshold for determining whether or not there is an abnormality in the body movement ( The body movement abnormality judgment threshold value is compared, and if the above-mentioned average value is equal to or less than the body movement abnormality judgment threshold value, the body movement abnormality judgment judgment is provisionally judged, and the above average value is the body movement abnormality judgment threshold value When the continuation time of the state which is the following continues beyond the time of the determination of the continuation of the microbe movement abnormality, it is finally determined that there is the microbe movement abnormality, and the microbeose movement abnormality is detected. Then, the second sub action determination unit 1432 updates the state variable with “microbody movement abnormality”. In order that the micro movement abnormality continuation determination time may finally determine that the micro movement abnormality temporarily determined by comparing the average value thus determined and the micro movement abnormality determination threshold is a micro movement abnormality. Is the threshold of

As described above, when the predetermined action is detected, the action determination unit 143 receives event information (event information) representing the contents of a predetermined event (event) related to the monitored person Ob and notifies the event. The SU communication IF unit 15 notifies the management server SV of the first event notification communication signal. More specifically, the action determination unit 143 is a communication that contains the target image used in the detection of the sensor ID of the own device, the event information indicating the content of the event, the entering, getting up, leaving, falling and falling. A signal (first event notification communication signal) is transmitted to the management server SV via the SU communication IF unit 15. In the present embodiment, the event information is one or more of entering, getting up, leaving, falling, falling, falling-body movement abnormality and nurse call (NC), and here, the action determination unit 143 detects The first event notification communication signal is stored as the event information, one or more of the entering, getting up, leaving, falling, falling, and movement abnormality. The image may be at least one of a still image and a moving image. In the present embodiment, as described later, the still image is first notified, and the moving image is distributed according to the user's request. First, a moving image may be distributed, or a still image and a moving image may be transmitted, and the still image and the moving image may be displayed on the terminal device SP, TA by screen division.

The process control unit 144 controls the action determination unit 143 according to the sleep determination result of the sleep state determination unit 142. In the present embodiment, the process control unit 144 controls at least one of the first and second sub

behavior determination units

1431 and 1432 according to the sleep determination result of the sleep state determination unit 142. More specifically, in the present embodiment, the process control unit 144 performs the first sub-action determination process in the first sub-action determination unit 1431 according to the sleep determination result of the sleep state determination unit 142. It controls whether or not to execute the second sub action determination process in the second sub action determination unit 1432. More specifically, for example, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 causes the first sub behavior determination unit 1431 to execute the process. The first sub behavior determination process is not executed, and the second sub behavior determination unit 1432 is caused to execute the second sub behavior determination process. When the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the sleep degree is greater than or equal to a predetermined sleep determination threshold set in advance, or In this case, the degree of reliability is equal to or more than a predetermined reliability determination threshold value set in advance. Further, for example, when the sleep determination result of the sleep state determination unit 142 indicates that both the sleep degree and the reliability are low, the process control unit 144 executes the first sub behavior determination process to the first sub behavior determination unit 1431. And the second sub-action determining unit 1432 does not execute the second sub-action determining process. When the sleep determination result of the sleep state determination unit 142 indicates that both the sleep degree and the reliability are low, the sleep degree is less than a predetermined sleep determination threshold set in advance, and the reliability is set in advance. In this case, it is less than the predetermined confidence determination threshold.

When the nurse call reception operation unit 13 receives a nurse call, the nurse call processing unit 145 notifies the management server apparatus SV of a first event notification communication signal that accommodates this as another example of the predetermined event. By using the SU sound input / output unit 12 or the like, voice communication is performed with the terminal devices SP and TA. More specifically, when the nurse call reception operation unit 13 is operated for input, the nurse call processing unit 145 performs SU communication of the first event notification communication signal containing the nurse call as the sensor ID of the own device and the event information. It transmits to the management server apparatus SV via the IF unit 15. Then, the nurse call processing unit 145 uses the SU sound input / output unit 12 or the like to make a voice call, for example, by using Voice over Internet Protocol (VoIP) with the terminal devices SP and TA.

When there is a request for distribution of a moving image from the fixed terminal apparatus SP or the portable terminal apparatus TA via the communication IF unit 3, the SU streaming processing unit 146 sends the requested fixed terminal apparatus SP or the portable terminal apparatus TA , And distributes a moving image (for example, a live moving image) generated by the camera 11 through the SU communication IF unit 15 by streaming reproduction.

Four first to fourth sensor devices SU-1 to SU-4 provided corresponding to the monitored person Ob are shown in FIG. 1 as an example, and the first sensor device SU-1 is shown. Is disposed in the room RM-1 (not shown) of Mr. A's Ob-1 who is one of the monitored persons Ob, and the second sensor device SU-2 is Mr. B's Ob- who is one of the monitored persons Ob. The third sensor device SU-3 is disposed in a living room RM-2 (not shown) of 2 and is disposed in a living room RM-3 (not shown) of Mr. C's Ob-3 who is one of the monitored persons Ob. The fourth sensor device SU-4 is disposed in a living room RM-4 (not shown) of Mr. D's Ob-4 who is one of the monitored persons Ob.

In the sensor device SU having such a configuration, the sensor unit 11, the sleep state determination unit 142, the behavior determination unit 143, and the process control unit 144 constitute an example of the behavior detection device.

The management server SV has a communication function of communicating with the other devices SU, TA, and SP via the network NW, and receives the notification of the predetermined event from the sensor device SU by the first event notification communication signal. Manages information (monitoring information) related to monitoring of the observer Ob, and notifies (predicts, notifies, transmits) the predetermined event to a predetermined terminal apparatus SP and TA with a second event notification communication signal, and executes a client (this implementation) In the embodiment, the data is provided to the client according to the request of the terminal device (SP, TA, etc.) to manage the entire monitored person monitoring support system MS. In the present embodiment, the monitoring information includes, for example, a sensor ID of the sensor device SU that is a transmission source of the first event notification communication signal, the predetermined event (a type of predetermined action detected by the sensor device SU, and a sensor device The image includes the nurse call accepted by SU, the image of the monitored person Ob, and the time (notification time) when the notification is received, and these are stored (recorded, managed) in association with one another. The monitoring information is accommodated in the second event notification communication signal. The second event notification communication signal may be transmitted, for example, by broadcast communication (broadcast or multicast), or, for example, one or more associated with the sensor device SU that is the transmission source of the first event notification communication signal. May be sent to the terminal device SP, TA. Such a management server SV can be configured, for example, by a computer with a communication function.

The fixed terminal device SP includes a communication function of communicating with other devices SU, SV, and TA via the network NW, a display function of displaying predetermined information, and an input function of inputting predetermined instructions and data. Monitored by, for example, inputting predetermined instructions and data given to the management server SV and the portable terminal TA, displaying the monitoring information obtained by the sensor SU by notification from the management server SV, etc. The device functions as a user interface (UI) of the person monitoring support system MS. Such fixed terminal apparatus SP can be configured, for example, by a computer with a communication function.

The portable terminal device TA has a communication function of communicating with other devices SV, SP, SU via the network NW, a display function of displaying predetermined information, an input function of inputting predetermined instructions and data, and a voice call. A call function to be performed is provided, and predetermined instructions and data given to the management server device SV and the sensor device SU are input, or the monitoring information obtained by the sensor device SU is displayed by notification from the management server device SV, It is a device for answering or calling a nurse call by voice communication with the sensor unit SU. Such a portable terminal device TA can be configured by, for example, a portable communication terminal device such as a so-called tablet computer, a smartphone, or a mobile phone.

Next, the operation of this embodiment will be described. FIG. 3 is a flow chart showing the operation of the sensor device in the service mode. FIG. 4 is a flowchart showing an operation of the sensor device in the action determination process according to the sleep determination result shown in FIG. FIG. 5 is a flowchart showing an operation of the sensor device in the fall determination process shown in FIG. FIG. 6 is a flowchart showing the operation of the sensor device in the fall determination process shown in FIG. FIG. 7 is a flow chart showing the operation of the sensor device in the entrance determination process shown in FIG. FIG. 8 is a flowchart showing an operation of the sensor device in the wakeup determination process shown in FIG. FIG. 9 is a flowchart showing the operation of the sensor device in the bed leaving determination process shown in FIG. 4. FIG. 10 is a flowchart showing the operation of the sensor device in the micro movement abnormality determination process shown in FIG. 4. FIG. 11 is a diagram showing an example of a main screen displayed on the terminal device. FIG. 12 is a diagram showing an example of a first setting screen displayed on the terminal device. FIG. 13 is a diagram showing an example of a second setting screen displayed on the terminal device. FIG. 14 is a diagram showing an example of a monitoring information screen displayed on the terminal device.

In the person-to-be-monitored person monitoring support system MS configured as described above, when the power is turned on, each of the devices SU, SV, SP, and TA performs initialization of necessary parts and starts its operation. In the sensor unit SU, the SU control processing unit 14 includes an SU control unit 141, a sleep state determination unit 142, an action determination unit 143, a process control unit 144, a nurse call processing unit 145, and a streaming process. The unit 146 is functionally configured, and in the behavior determination unit 143, the first sub behavior determination unit 1431 and the second sub behavior determination unit 1432 are functionally configured.

When the power is turned on and the operation is started, the terminal device SP, TA, for example, the fixed terminal device SP accepts a log-in operation by a supervisor (user) such as a nurse or a caregiver. In the login operation, an ID or the like of a user name or the like of the monitor (user) is input and stored in the storage unit. When the fixed terminal device SP logs in to the monitored person monitoring support system MS by the login operation, the fixed terminal device SP displays a main screen on the display unit.

The main screen is a screen for receiving the operation mode of the fixed terminal device SP. For example, as shown in FIG. 11, the main screen 21 includes a “service mode” button 211 and a “setting mode” button 212. The “service mode” button 211 is a button for requesting a service mode for monitoring the monitored person Ob as the operation mode of the fixed terminal device SP, and an instruction to operate the fixed terminal device SP in the service mode (instruction, command ) Is a button for inputting. The “setting mode” button 212 is a button for requesting a setting mode for setting a predetermined parameter defined in advance as an operation mode of the fixed terminal apparatus SP, and instructs the fixed terminal apparatus SP to operate in the setting mode. It is a button for inputting.

When displaying the main screen 21 as described above, when receiving an input operation from the input unit of the fixed terminal device SP, the fixed terminal device SP receives the input operation received by the control processing unit as “service mode It is determined whether it is an input operation of the “” button 211 or an input operation of the “setting mode” button 212.

As a result of the determination, when the received input operation is an input operation of the “service mode” button 211, the fixed terminal device SP starts operation in the service mode so as to monitor the monitored person Ob. The input operation is, for example, an operation in which the cursor is moved onto the “service mode” button 211 by the movement of the mouse and the mouse is left-clicked.

On the other hand, as a result of the determination, when the received input operation is an input operation of the “setting mode” button 212, the fixed terminal device SP starts operation in the setting mode so as to set the predetermined parameter. .

In the setting mode, as described above, when the input operation of the “setting mode” button 212 is received, the fixed terminal device SP displays a setting screen on the display unit. In the present embodiment, authentication is performed using an ID such as a user name, and only the authorized user (the setter) can enter the setting mode.

The setting screen is a screen for inputting and setting the predetermined parameter. In the present embodiment, the predetermined parameter is a setting value used to appropriately determine the predetermined event, and for example, an imaging condition for extracting a monitored person Ob from an image, and the determination Threshold (determination threshold) or the like. More specifically, in the present embodiment, the predetermined parameters are a frame rate, a brightness level, a ceiling height, and an area where the bedding BD is located. The setting screen comprises two first and second setting screens in the present embodiment. The first setting screen inputs (determines) a person to be monitored Ob (sensor device SU) to be a target of parameter setting, and mainly the numerical parameters (the frame rate in the present embodiment) among the predetermined parameters. , Brightness level and ceiling height) are input and set. The second setting screen is a screen for inputting and setting other parameters (in the present embodiment, the location area of the bedding BD) other than numerical parameters among the predetermined parameters.

More specifically, when the input operation of the “setting mode” button 212 is received from the input unit, the fixed terminal device SP causes the control processing unit to display the first setting screen on the display unit 4.

For example, as shown in FIG. 12, this first setting screen 22 is for inputting and setting a frame rate and a monitor person's name input setting area 221 for inputting and setting the name of the monitoree Ob. Frame rate input setting area 222, a brightness level input setting area 223 for inputting and setting a brightness level, a ceiling height input setting area 224 for inputting and setting a ceiling height, An area setting button 225 and a "return to main screen" button 226 are provided. Each of the input setting areas 221 to 224 includes an input field for parameter values, and an “update” button for storing and setting parameters based on the parameter values input to the input fields. The “area setting” button 225 is a button for requesting the second setting screen, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the second setting screen. The “return to main screen” button 226 is a button for requesting the main screen 21, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the main screen 21. The “return to main screen” button 226 is also a button for setting each parameter value stored as a parameter in the storage unit to the sensor unit SU via the management server unit SV.

In the example shown in FIG. 12, "Mr. A", "15 fps", "5" and "2.4 m" are input in the respective input fields in the respective input setting areas 221 to 224. When the "update" button in the monitored person name input setting area 221 is operated, the control processing unit of the fixed terminal device SP sets the target of parameter setting to "Mr. A", and the storage unit of the fixed terminal device SP Is stored in Note that the sensor device SU that monitors “person A” or its sensor ID may be input and set as a parameter setting target. When the “update” button in the frame rate input setting area 222 is input, the control processing unit of the fixed terminal device SP sets the frame rate to “15 fps” and is stored in the storage unit of the fixed terminal device SP. In the present embodiment, since the sensor unit SU performs the event detection operation every frame or every few frames, setting the frame rate defines the execution interval of the event detection operation. When the “update” button in the brightness level input setting area 223 is input, the control processing unit of the fixed terminal device SP sets the brightness level to “5”, and is stored in the storage unit of the fixed terminal device SP. Ru. If the target image captured by the sensor unit SU is too dark or too bright, it becomes difficult to extract the person area of the person to be monitored Ob from the target image, and it becomes difficult to identify a person. By setting the brightness level, a target image can be generated with a proper exposure, the person area can be extracted more appropriately, and the person can be more appropriately identified. When the “update” button in the ceiling height input setting area 224 is input, the control processing unit of the fixed terminal device SP sets the ceiling height to “2.4 m”, and the storage unit of the fixed terminal device SP is It is memorized. When the sensor unit SU is disposed on a ceiling with a standard ceiling height (for example, 2.4 m or the like), the recumbent posture determination threshold value or the like in the case where the sensor unit SU is disposed is stored in advance in the sensor unit SU as a default value. By setting the ceiling height, the recumbent posture determination threshold of the default value is corrected, and the corrected recumbent posture determination threshold is used for the detection of the predetermined action described above. By setting the ceiling height, the lying posture determination threshold can be adjusted in accordance with the situation of the sensor device SU actually installed.

When the input operation of the “area setting” button 225 is received, the fixed terminal device SP displays the second setting screen on its display unit.

The second setting screen 23 includes, for example, a target image display area 231 for displaying a target image, an “update” button 232, and a “return” button 233, as shown in FIG. In the target image display area 231, the camera 111 of the sensor device SU for monitoring the monitored person Ob having the name of the monitored person Ob inputted in the monitored person name input setting area 221 of the first setting screen 22. The generated target image is displayed. The “update” button 232 is a button for requesting setting of parameters in the area input from the input unit while referring to the target image displayed in the target image display area 231. The “return” button 233 is a button for requesting the first setting screen 22, and is a button for inputting an instruction to cause the fixed terminal apparatus SP to display the first setting screen 22.

In the second setting screen 23 as described above, when the second setting screen 23 is displayed, the fixed terminal device SP waits for the input of the location area of the bedding BD. When the user inputs four vertices of the location area of the bedding BD from the input unit and performs an input operation of the "update" button 232, the control processing unit of the fixed terminal SP determines The pixel position is input, stored in the storage unit, and the location area of the bedding BD is set. FIG. 13 illustrates how the user inputs the four vertices of the area where the bedding BD is located.

Then, when the “Return” button 233 is operated, the first setting screen 22 is displayed on the display unit 4. Furthermore, when the “Return to main screen” button 226 is operated, the main screen 21 is displayed. At this time, the fixed terminal device SP manages each parameter value stored as a parameter in its storage unit as a management server device The sensor unit SU transmits the parameter values to the sensor unit SU via the SV, and stores and sets the received parameter values in the SU storage unit 16 of the own unit SU. As a result, each value of the predetermined parameter is set in the sensor unit SU.

On the other hand, when the input operation of the “service mode” button 211 is received on the main screen 21 described above, the fixed terminal device SP operates in the service mode, and the monitored person monitoring support system MS operates as follows. Monitors the monitored person Ob.

In the monitoring of the monitored person Ob, the sensor device SU detects a predetermined operation in the monitored person Ob by operating as follows for each frame or every few frames, and a nurse call is performed. The presence or absence of acceptance of is determined.

In FIG. 3, first, the sensor unit SU causes the sleep state determination unit 142 of the SU control processing unit 14 to execute a sleep state determination process on the monitored person Ob based on the Doppler signal of the Doppler sensor 112 in the sensor unit 11 (S1 ). More specifically, the sleep state determination unit 142 acquires, from the SU storage unit 16, a Doppler signal measured within a predetermined time, for example, within one minute, from the present time to the past. Subsequently, the sleep state determination unit 142 performs, for example, a fast Fourier transform (FFT) on the acquired one-minute Doppler signal. Subsequently, the sleep state determination unit 142 obtains an average value of amplitudes in a frequency band corresponding to a general respiration frequency from the spectrum obtained by the FFT. Subsequently, the sleep state determination unit 142 compares the obtained average value with the sleep level division threshold to obtain the sleep degree, and stores the obtained sleep degree in the SU storage unit 16 in time series. Subsequently, the sleep state determination unit 142 obtains the duration of the obtained sleep degree by referring to the SU storage unit 16. Subsequently, the sleep state determination unit 142 compares the duration of the obtained sleep degree with the reliability class threshold to obtain the reliability. For example, in the present embodiment, the sleep level classification threshold is one value that discriminates between awakening and sleep, and the reliability classification threshold is one value that discriminates between high reliability and low reliability. . Then, the sleep state determination unit 142 outputs (notifies) the sleep degree and the reliability obtained as described above to the processing control unit 144 in the sleep determination result, in the present embodiment.

Next, the sensor device SU is based on the target image of the camera 111 in the sensor unit 11 according to the sleep determination result determined by the sleep state determination unit 142 in the process S1 by the action determination unit 143 of the SU control processing unit 14 An action determination process for the monitored person Ob is executed (S2). More specifically, in the present embodiment, the process control unit 144 performs the first sub-action determination process in the first sub-action determination unit 1431 of the action determination unit 143 according to the sleep determination result of the sleep state determination unit 142. It controls whether or not to execute the second sub-action determination process in the second sub-action determination unit 1432 of the action determination unit 143. More specifically, in the present embodiment, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 determines the first sub-action determination unit 1431. The second sub-action determination process in the second sub-action determination unit 1432 is not performed. That is, the processes S21 to S27 for determining the first action (in the present embodiment, entering, getting up, leaving, falling and falling in this embodiment) by the first sub-action determining unit 1431 are not executed, and the second sub Only the process S28 for determining the below-mentioned 2nd action (this embodiment micro body movement abnormality) by the action determination part 1432 is performed. On the other hand, when the sleep determination result of the sleep state determination unit 142 indicates that both the sleep degree and the reliability are low, the process control unit 144 executes the first sub behavior determination process in the first sub behavior determination unit 1431. And, the second sub action determination process in the second sub action determination unit 1432 is not executed. That is, the processes S21 to S27 for determining the first action described later by the first sub-action determining unit 1431 are executed, and the process S28 for determining the second action described below by the second sub-action determining unit 1432 Will not be executed.

That is, in the process S2, first, the process control unit 144 compares each of the sleep degree and the reliability degree determined by the sleep state determination unit 142 in the process S1 with each of the sleep determination threshold value and the reliability degree determination threshold value. As a result of the comparison, if the sleep degree is equal to or higher than the sleep determination threshold, or if the reliability is equal to or higher than the confidence determination threshold, the processing control unit 144 causes the first sub behavior determination unit 1431 to Only the process S28 for determining the second action is executed by the second sub-action determining unit 1432 without executing the processes S21 to S27 for determining the first action. On the other hand, if it is determined that the degree of sleep is less than the sleep determination threshold and the degree of reliability is less than the confidence determination threshold as a result of the comparison, the processing control unit 144 determines that the first sub behavior determination unit 1431 is performed. In addition, the process S21 to the process S27 for determining the first action are performed, and the second sub action determining unit 1432 is not performed only the process S28 for determining the second action.

Next, each process of processes S21 to S28 in which the process control unit 144 controls whether to execute or not according to the sleep determination result determined by the sleep state determination unit 142 in the process S1 as described above will be described.

In FIG. 4, in the processing S21, the sensor device SU causes the behavior determination unit 143 of the SU control processing unit 14 to acquire an image of one frame as a target image from the camera 111 of the sensor unit 11.

Subsequently, in process S22, the sensor device SU causes the first sub behavior determination unit 1431 of the behavior determination unit 143 to extract a human region from the target image acquired in process S21, for example, by the background subtraction method. Note that the first sub action determination unit 1431 may extract a moving subject region as a human region from the target image acquired in the processing S21, for example, by the frame difference method.

Subsequently, in the process S23, the sensor device SU causes the first sub-action determining unit 1431 to execute the fall determination process based on the extracted person area.

More specifically, in this fall determination process, in FIG. 5, first, the first sub behavior determination unit 1431 determines whether or not the fall determination condition is satisfied based on the person area extracted in the process S22 (see FIG. 5) S231). More specifically, the first sub-action determining unit 142 determines that the size of the head area of the human area extracted from the target image in step S22 is equal to or less than the lying posture determination threshold, and the size of the head area is If the change speed is equal to or higher than the fall judgment speed threshold and the person area is in the fall judgment area set around the area of the bedding BD, it is judged that there is a fall (Yes), and then The processing S232 is executed, and in the other cases, it is determined that there is no fall (No), and the present fall determination processing is ended. Here, the extraction of the head region is performed by, for example, circular or elliptical Hough transform from the person region, for example, pattern matching using a prepared head model (template), for example, head extraction It is extracted by the neural network learned for the purpose. In the process S232, the first sub-action determining unit 1431 determines fall occurrence and indicates fall presence information indicating presence of fall (for example, a fall flag indicating presence or absence of fall is changed from “0” to “1”) This is stored in the SU storage unit 16 and the present fall determination processing is ended.

Returning to FIG. 4, in the processing S24 following the above-described processing S23, the sensor device SU causes the first sub-action determining unit 1431 to execute the fall determination processing based on the extracted person area.

More specifically, in the fall determination process, in FIG. 6, first, the first sub-action determination unit 1431 determines whether or not the fall determination condition is satisfied based on the person area extracted in the process S22 (FIG. 6) S241). More specifically, the first sub-action determining unit 142 determines that the size of the head area of the human area extracted from the target image in step S22 is equal to or less than the lying posture determination threshold, and the size of the head area is If the change speed is equal to or higher than the fall determination speed threshold and the person area is in the area excluding the area where the bedding BD is located and the fall determination area, it is determined that there is a fall (Yes). Is determined, and in the case other than this, it is determined that there is no fall (No), and this fall determination processing is ended. In the process S242, the first sub-action determining unit 1431 determines the occurrence of a fall and indicates fall presence information (for example, the fall flag indicating the presence or absence of a fall is changed from "0" to "1") indicating the presence of a fall. It memorizes in SU memory section 16, ends this falling decision processing.

Returning to FIG. 4, in the processing S25 following the above-described processing S24, the sensor device SU causes the first sub-action determining unit 1431 to perform the entrance determination processing based on the extracted person area.

More specifically, in this entrance determination processing, first in FIG. 7, the first sub-action determination unit 1431 determines whether or not the state variable (previous state variable) is (S251). As a result of the determination, if the state variable is not “bedding off” (No), the first sub-action determining unit 1431 ends the main entrance determination process. On the other hand, as a result of the determination, if the state variable is “bedding off” (Yes), the first sub-action determining unit 1431 next executes processing S252. In the process S252, the first sub-action determining unit 1431 determines whether or not the determination condition of admission is satisfied based on the person area extracted in the process S22. More specifically, the first sub-action determining unit 1431 detects the case in which the person area extracted from the target image in step S22 completely overlaps the area where the bedding BD is located (the person area is completely located in the bedding BD) (If it becomes inside), provisionally determine that it is in the bed, and if the duration of the complete superposition state continues beyond the in-bed continuation determination time, finally determine that there is an in-bed (Yes), next Then, the process S253 is executed, and in the case other than this, it is determined that there is no bed entry (No), and the main entry and floor determination process is ended. In the process S253, the first sub-action determining unit 1431 determines the occurrence of the entrance and the presence information indicating the presence of the entrance (for example, the entrance flag indicating the presence or absence of the entrance changes from "0" to "1"). Is stored in the SU storage unit 16). Subsequently, the first sub-action determining unit 1431 updates the state variable with “in bed” (state variable 「“ in bed ”) (S254), and ends the main entrance determination process.

Returning to FIG. 4, in the processing S26 following the processing S25, the sensor device SU causes the first sub-action determining unit 1431 to execute wakeup determination processing based on the extracted person area.

More specifically, in the wake-up determination process, in FIG. 8, first, the first sub behavior determination unit 1431 determines whether the state variable (previous state variable) is (S261). As a result of this determination, when the state variable is not “bed entry” (No), the first sub behavior determination unit 1431 ends the wakeup determination process. On the other hand, as a result of the determination, if the state variable is “in bed” (Yes), the first sub behavior determination unit 1431 next executes a process S262. In the process S262, the first sub-action determining unit 1431 determines whether or not the wake-up determination condition is satisfied based on the person area extracted in the process S22. More specifically, the first sub-action determining unit 1431 detects that the person area extracted from the target image in the process S22 this time is larger than the wakeup determination threshold and is less than the bedfall determination threshold. In this case, it is provisionally determined that the vehicle has risen, and if the duration of the overhang region in the state which is equal to or higher than the wakeup determination threshold and less than the departure judgment threshold exceeds the wakeup continuation determination time, it is finally determined that wakeup is present. Then (Yes), next, the process S263 is executed, and in the other cases except this, it is determined that there is no wakeup (No), and this wakeup determination process is ended. In the process S263, the first sub-action determining unit 1431 determines wakeup occurrence and indicates wakeup presence information indicating wakeup presence (for example, the wakeup flag indicating presence or absence of wakeup is changed from "0" to "1"). It is stored in the SU storage unit 16. Subsequently, the first sub-action determining unit 1431 updates the state variable with “wake up” (state variable 「“ wake up ”) (S 264), and ends the overturn determination process.

Returning to FIG. 4, in the processing S27 following the above-described processing S26, the sensor device SU causes the first sub-action determining unit 1431 to execute bed departure determination processing based on the extracted person area.

More specifically, in the bed leaving determination process, in FIG. 9, the first sub-action determining unit 1431 first determines whether the state variable (previous state variable) is (S271). As a result of this determination, when the state variable is neither “bed entry” nor “wake up” (No), the first sub behavior determination unit 1431 ends the bed departure determination process. On the other hand, as a result of the determination, if the state variable is any one of “arriving” and “rising” (Yes), the first sub-action determining unit 1431 next executes processing S272. In the process S272, the first sub-action determining unit 1431 determines whether or not the determination condition for bed departure is satisfied based on the person area extracted in the process S22. More specifically, the first sub-action determining unit 1431 determines that the floor area is temporary when the overrun area in which the person area extracted from the target image in the process S22 is currently out of the area of the bedding BD If the duration of the overhang region in the state of being equal to or greater than the departure judgment threshold exceeds the stay continuation judgment time, it is finally determined that there is bed departure (Yes), and then processing S273 is executed, In the case other than this, it is determined that there is no bed leaving (No), and the bed leaving determination process is ended. In the process S273, the first sub-action determining unit 1431 determines the occurrence of bed leaving and has bed leaving presence information (for example, the bed leaving flag indicating presence or absence of bed leaving is changed from "0" to "1") indicating presence of bed leaving. It is stored in the SU storage unit 16. Subsequently, the first sub-action determining unit 1431 updates the state variable with “bedding off” (state variable 「“ being off ”) (S 274), and the present fall determining process is ended.

Returning to FIG. 4, in the processing S28 subsequent to the processing S27, the sensor device SU causes the micro movement abnormality based on the Doppler signal of the Doppler sensor 112 in the sensor unit 11 by the second sub-action determining unit 1432 of the action determining unit 143 Execute determination processing.

More specifically, in this micro movement abnormality determination process, in FIG. 10, first, the second sub behavior determination unit 1432 determines whether the micro movement abnormality determination condition is satisfied based on the Doppler signal of the Doppler sensor 112. It is determined (S281). More specifically, the second sub-action determination unit 142 first acquires a Doppler signal measured within a predetermined time period, for example, within one minute, from the current time to the past from the SU storage unit 16. Subsequently, the sleep state determination unit 142 performs, for example, a fast Fourier transform (FFT) on the acquired one-minute Doppler signal. Subsequently, the second sub-action determining unit 142 obtains an average value of amplitudes in a frequency band corresponding to a general respiration frequency from the spectrum obtained by the FFT. Subsequently, the second sub-action determining unit 142 compares the calculated average value with the micro movement abnormality determination threshold, and if the calculated average value is equal to or less than the micro movement abnormality determination threshold, the micro body If the continuance time of the state where the average value is less than or equal to the micro movement abnormality judgment threshold is tentatively determined as the movement abnormality and continues beyond the micro movement abnormality continuation judgment time, the micro movement abnormality presence and the final state Then, the process S 282 is executed, and in the other cases, it is determined that there is no micro movement abnormality (No), and the micro movement abnormality determination process is ended. In the process S282, the second sub-action determining unit 1432 determines the occurrence of micro movement abnormality and information on micro movement abnormality presence information indicating presence of micro movement abnormality (for example, micro movement abnormality indicating presence or absence of micro movement abnormality) The flag is changed from “0” to “1”) and stored in the SU storage unit 16, and the micro movement abnormality determination process is ended.

As described above, whether the process S21 to the process S28 is performed or not is the process control unit 144 according to the sleep determination result determined by the sleep state determination unit 142 in the process S1. It is controlled.

Returning to FIG. 3, next, the sensor unit SU determines, by the SU control processing unit 14, whether or not notification of a predetermined event is necessary (S3). More specifically, the sensor device SU causes the behavior determination unit 143 of the SU control processing unit 14 to determine, in the SU storage unit 16, a result of determining a predetermined behavior such as the fall presence information or the fall presence information. If it is determined whether or not stored, and the result of determining the predetermined action is stored in the SU storage unit 16, the action determination unit 143 determines that the notification is necessary (Yes), and then After the process S4 is performed, the current process is ended, and when the result of determining the predetermined action is not stored in the SU storage unit 16, the action determination unit 143 determines that the notification is unnecessary. It judges (No) and ends this processing this time.

In the process S4, the sensor device SU accommodates the predetermined action determined as the event information in order to notify the predetermined terminal device SP and TA of the determined predetermined action by the action determination unit 143. The first event notification communication signal according to the detection of the predetermined action is transmitted to the management server SV. In one specific example, when wakeup information is stored in the SU storage unit 16, the behavior determination unit 143 uses the sensor ID of the own machine, “wakeup” as event information, and the wakeup determination. The first event notification communication signal containing the selected target image is transmitted to the management server SV via the SU communication IF unit 15.

Then, while executing each of the processes S1 to S4 as described above, the sensor device SU determines whether the nurse call processing unit 145 of the SU control processing unit 14 receives a nurse call or not. When the nurse call is accepted, the sensor device SU accommodates the accepted nurse call as the event information in order to notify acceptance of the nurse call to predetermined terminal devices SP and TA. The first event notification communication signal is transmitted to the management server apparatus SV.

When the management server device SV receives the first event notification communication signal from the sensor device SU via the network NW, each sensor ID, event information, and other information contained in the first event notification communication signal is the sensor ID. Are stored (recorded) as monitoring information of the monitored person Ob monitored by the sensor device SU. That is, the management server device SV stores the sensor ID, the event information, and other information contained in the first event notification communication signal in association with each other. Then, the management server device SV transmits a second event notification communication signal to the terminal devices SP and TA of the notification destination corresponding to the sensor device SU of the transmission source (notification source) in the received first event notification communication signal.

When the fixed terminal apparatus SP and the portable terminal apparatus TA receive the second event notification communication signal from the management server apparatus SV via the network NW, the sensor ID, the event information, etc. contained in the second event notification communication signal Each piece of information is stored (recorded) as monitoring information of the monitored person Ob monitored by the sensor device SU having the sensor ID, and the monitoring information is displayed. For example, when the sensor device SU repeatedly executes the detection operation of a predetermined event but does not detect the predetermined event, the terminal device SP, TA, for example, the fixed terminal device SP is shown in FIG. 14A. When the monitoring information screen 31a is displayed, and the sensor device SU detects a predetermined event and the predetermined event detected by the second event notification communication signal is notified, the fixed terminal apparatus SP performs monitoring as shown in FIG. 14B. An information screen 31 b is displayed. The monitoring information screen 31a illustrated in FIG. 14A includes a monitoring image display area 311 that displays an image captured by the sensor device SU. The monitoring information screen 31b shown in FIG. 14B further includes an event display area 312 for displaying the type of the event detected by the sensor device SU. In the example shown to FIG. 14B, the event display area 312 which superimposed on the monitoring image display area 311 and displayed the message of "bed release detection" is shown in figure.

For example, if the person being monitored is in a sleep state, for example, an action such as bed entry, bed leaving and fall can not occur, and if the action determination unit 143 determines an action that can not occur in such a sleep state, It is highly probable that it is a false decision. Since the person-to-be-monitored monitoring support system MS in the present embodiment and the behavior detection device and the behavior detection method incorporated in the sensor device SU control the behavior determination unit 143 according to the sleep determination result of the sleep state determination unit 142 False positives can be reduced.

The above-mentioned person-to-be-monitored monitoring support system MS, the above-mentioned action detection device, and the above-mentioned action detection method are the first actions belonging to the first group which can not occur in the sleep state (in this embodiment, entering and getting up) , Bed break, fall and fall) and the second action belonging to the second group that can occur in the sleep state (microbody movement abnormality in this embodiment), the sleep determination of the sleep state determination unit 142 The action determination unit 143 can be more appropriately controlled according to the result, and erroneous determination can be further reduced.

The above-mentioned person-to-be-monitored monitoring support system MS, the above-mentioned action detection apparatus, and the above-mentioned action detection method may execute only the sub-action determination processing which determines the action which can not occur in the sleep state By controlling the action determination unit 143 according to the sleep determination result of the sleep state determination unit 142 so as to execute only the sub-action determination process that determines the action, it is possible to further reduce the erroneous determination.

In the above embodiment, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 causes the first sub behavior determination unit 1431 to The first sub behavior determination process is not executed, and the second sub behavior determination unit 1432 is executed to execute the second sub behavior determination process, and the sleep determination result of the sleep state determination unit 142 indicates that both the sleep degree and the reliability are When it is low, the first sub-action judging unit 1431 is caused to execute the first sub-action judging process, and then the second sub-action judging unit 1432 is caused to execute the second sub-action judging process. As described above, the process control unit 144 may control the behavior determination unit 143 according to the sleep determination result of the sleep state determination unit 142.

In the first modification, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep level and the reliability regardless of whether the first sub behavior determination process is performed in the first sub behavior determination unit 1431. When one of the degrees is high, only the second sub behavior determination unit 1432 is set as a control target, and the second sub behavior determination unit 1432 causes the second sub behavior determination process to be executed. Regardless of whether or not the first sub behavior determination process is performed in the first sub behavior determination unit 1431, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 indicates that both the sleep level and the reliability are low. The control target is only the second sub behavior determination unit 1432 and does not cause the second sub behavior determination unit 1432 to execute the second sub behavior determination process. In one example, the process control unit 144 determines whether or not to execute the process S28 without controlling whether or not each process of the process S21 to the process S27 described above with reference to FIG. 4 is performed. It controls according to the sleep determination result of the part 142. Thus, the behavior determination unit 143 is controlled to determine only the behavior that may occur in the sleep state, and the monitored person monitoring support system MS, the behavior detection apparatus, and the behavior detection method can further reduce erroneous determinations.

In the second modified embodiment, whether the processing control unit 144 outputs the first sub-action determination result in the first sub-action determining unit 1431 according to the sleep determination result of the sleep state determining unit 142, and It is controlled whether or not the output of the second sub-action determination result in the second sub-action determining unit 1432 is performed. In the second variation, although the first and second sub-action determination processes are respectively executed, by controlling the output of the result, an effect equivalent to the effect obtained by the control of the execution can be obtained. More specifically, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability degree is high, the process control unit 144 causes the first sub-action determination unit 1431 to execute the process. The first sub-action determination unit does not output the first sub-action determination result, and causes the second sub-action determination unit to output the second sub-action determination result. In one example, in each of the processes S21 to S27 described above with reference to FIG. 4, the process control unit 144 determines the first sub-action even if the first sub-action determining unit 1431 determines the predetermined action. For example, in the processing S28 described above with reference to FIG. 4, the determination unit 1431 does not store the result of the determination of the predetermined action, such as the fall presence information and the fall presence information, in the SU storage unit 16. If the second sub-action determining unit 1432 determines the predetermined action, the second sub-action determining unit 1432 determines, for example, the SU memory 16 as a result of determining the predetermined action of the information on fine motion abnormality Remember. When the sleep determination result of the sleep state determination unit 142 indicates that both the sleep level and the reliability are low, the process control unit 144 causes the first sub behavior determination unit 1431 to output the first sub behavior determination result. Then, the second sub behavior determination unit 1432 does not output the second sub behavior determination result. In one example, in each of the processes S21 to S27 described above with reference to FIG. 4, the process control unit 144 determines the first sub-action when the first sub-action determining unit 1431 determines the predetermined action. The unit 1431 causes the SU storage unit 16 to store the result of the determination of the predetermined action, such as the fall / fall information or the fall / presence information, for example, and the second sub in step S28 described above with reference to FIG. Even if the action determination unit 1432 determines the predetermined action, the second sub action determination unit 1432 does not store the result of the determination of the predetermined action of the micro movement abnormality presence information, for example, in the SU storage unit 16 .

Alternatively, in the second modified embodiment, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep level regardless of the presence or absence of the output of the first sub behavior determination result of the first sub behavior determination unit 1431. When one of the degrees of reliability is high, only the second sub behavior determination unit 1432 is set as a control target, and the second sub behavior determination unit 1432 causes the second sub behavior determination result to be output. When the sleep determination result of the sleep state determination unit 142 indicates that both the sleep level and the reliability are low, the process control unit 144 sets only the second sub behavior determination unit 1432 as a control target, and the second sub behavior determination unit 1432 Do not output the second sub-action determination result in In one example, the process control unit 144 does not control whether or not to output the first sub-action determination result in each process of the above-described processes S21 to S27 described with reference to FIG. It is controlled according to the sleep determination result of the sleep state determination unit 142 whether or not the sub behavior determination result is output.

According to this, the monitored person monitoring support system MS, the activity detection apparatus, and the activity detection method output, for example, only the sub-action determination result of the sub-action determination process that determines an action that can not occur in the sleep state. Or, conversely, the behavior determination unit 143 is output according to the sleep determination result of the sleep state determination unit 142 so as to output only the sub-action determination result of the sub-action determination process that determines the behavior that may occur in the sleep state. By controlling, it is possible to further reduce the erroneous determination.

In the third modification, the processing control unit 144 causes the first sub-action determination result in the first sub-action determining unit 1431 to be the second sub-action in the second sub-action determining unit 1432 according to the sleep determination result of the sleep state determining unit 142. Control whether or not to assist with the action determination result. More specifically, for example, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the processing control unit 144 causes the process control unit 144 in the first sub behavior determination unit 1431 to When the first sub-behavior determination result is assisted by the second sub-behavior determination result in the second sub-behavior determination unit 1432 and the sleep determination result of the sleep state determination unit 142 indicates that both the sleep degree and the reliability are low, The first sub behavior determination result in the first sub behavior determination unit 1431 is not assisted by the second sub behavior determination result in the second sub behavior determination unit 1432. More specifically, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the processing control unit 144 determines that the first sub-action in the first sub-action determination unit 1431 is performed. The determination result is rewritten to the second sub behavior determination result in the second sub behavior determination unit 1432. That is, regardless of the first sub-action determination result, only the second sub-action determination result is valid. Alternatively, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the processing control unit 144 determines the first sub behavior determination result of the first sub behavior determination unit 1431. The second sub behavior determination result in the second sub behavior determination unit 1432 is additionally written. That is, the second sub-action determination result is attached to the first sub-action determination result, and the first event notification communication signal accommodates the determined first action and second action as the event information.

According to this, the monitored person monitoring support system MS, the behavior detecting device, and the behavior detecting method are, for example, a sub-behavior of the sub-behavior determination processing that determines the behavior that can not occur in the sleeping state Since it is possible to assist the determination result with the sub-action determination result of the sub-action determination process of determining the action that may occur in the sleep state, erroneous determination can be further reduced.

In a fourth modification, the first sub-action determination process compares a first sub-measurement result of the first sub-sensor with a preset first action determination threshold associated with the first action. Thus, the process control unit 144 executes, as the control, the first sub-action determination unit 1431 according to the sleep determination result of the sleep state determination unit 142. The first behavior determination threshold value in the first sub behavior determination process is changed. More specifically, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high as the control, the process control unit 144 sets the sleep state determination unit 142 to The first behavior determination threshold is changed to a value that is less likely to be determined as the first behavior as compared with the case where the sleep determination result and the degree of sleep and the degree of reliability are both low. As the control, when the sleep determination result of the sleep state determination unit 142 is low in both the sleep degree and the reliability, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep degree and the reliability. The first action determination threshold is changed to a value that is more easily determined to be the first action than when any one of the degrees is high. In the above-described embodiment, the wakeup determination threshold, the bed departure determination threshold, the lying posture determination threshold, the fall determination speed threshold, and the fall determination speed threshold respectively correspond to an example of the first action determination threshold. One or more of the wakeup determination threshold, the bed departure determination threshold, the lying posture determination threshold, the fall determination speed threshold, and the fall determination speed threshold are the sleep determination results of the sleep state determination unit 142 by the process control unit 144 It changes according to.

According to this, the monitored person monitoring support system MS, the behavior detecting device, and the behavior detecting method, for example, determine the behavior of the sub behavior determining process that determines the behavior that can not occur in the sleeping state in the case of the sleeping state. Since it is possible to change the threshold value to a value that can not be substantially determined to be the action, it is possible to further reduce the erroneous determination.

In a fifth modification, the second sub-action determination process compares a second sub-measurement result of the second sub-sensor with a preset second action determination threshold associated with the second action. Thus, the process control unit 144 executes, as the control, the second sub-action determination unit 1432 according to the sleep determination result of the sleep state determination unit 142. The second behavior determination threshold value in the second sub behavior determination process is changed. More specifically, as the control, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is lower if both the sleep degree and the reliability are lower. The second behavior determination threshold is changed to a value that is less likely to be determined as the second behavior as compared to the case where either the sleep level or the reliability level is high. As the control, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep. The second behavior determination threshold is changed to a value that is more easily determined to be the second behavior than when both the degree and the reliability are low. In the above-described embodiment, the micro movement abnormality determination threshold corresponds to an example of the second behavior determination threshold, and the micro movement abnormality determination threshold corresponds to the sleep state of the sleep state determination unit 142 by the processing control unit 144. It is changed according to the judgment result.

According to this, the monitored person monitoring support system MS, the activity detection apparatus, and the activity detection method, for example, determine the activity determination threshold value of the sub activity determination process that determines the activity that can occur in the sleep state in the sleep state Can be changed to a value that is easily determined to be the action, etc., so that erroneous determination can be further reduced.

In a sixth modification, the first sub-action determination process is preset, which is associated with the first sub-measurement result of the first sub-sensor and the first action at predetermined time intervals set in advance. It is temporarily determined whether or not it is the first action by comparing it with the first action determination threshold value, and if the tentatively determined result that is temporarily determined is the first action, the preset first continuation determination The processing is finally determined to be the first action when continuing for a time, and the processing control unit 144 performs the first sub-operation according to the sleep determination result of the sleep state determination unit 142 as the control. The first continuation determination time in the first sub behavior determination process executed by the behavior determination unit 1431 is changed. As the control, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep. The first continuation determination time is changed to a value that is less likely to be determined as the first action than when both the degree and the reliability are low. As the control, when the sleep determination result of the sleep state determination unit 142 is low in both the sleep degree and the reliability, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep degree and the reliability. The first continuation determination time is changed to a value that is more easily determined to be the first action than when any one of the degrees is high. In the above-mentioned embodiment, the admission continuation determination time, the wakeup continuation determination time, and the bedup continuation determination time respectively correspond to an example of the first continuation determination time, and these admission continuation determination times, the wakeup The processing control unit 144 changes one or more of the continuation determination time and the bed-up continuation determination time according to the sleep determination result of the sleep state determination unit 142.

According to this, the monitored person monitoring support system MS, the activity detection apparatus, and the activity detection method, for example, continue determination of the sub activity determination process that determines an activity that can not occur in the sleep state in the sleep state. Since it is possible to change the time to a value that can not be substantially determined to be the action, it is possible to further reduce the erroneous determination.

In the seventh modified embodiment, the second sub action determination process is preset, which is associated with the second sub measurement result of the second sub sensor and the second action at predetermined time intervals set in advance. It is temporarily determined whether or not it is the second action by comparing it with the second action determination threshold value, and if the temporary determination result temporarily determined is the second action, a second continuation determination set in advance is made. This is a process of finally determining the second action when continuing for a period of time, and the process control unit 144 performs the second control according to the sleep determination result of the sleep state determination unit 142 as the control. The second continuation determination time in the second sub behavior determination process executed by the sub behavior determination unit is changed. As the control, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep. The second continuation determination time is changed to a value that is more easily determined to be the second action than when both the degree and the reliability are low. As the control, when the sleep determination result of the sleep state determination unit 142 is low in both the sleep degree and the reliability, the process control unit 144 determines that the sleep determination result of the sleep state determination unit 142 is the sleep degree and the reliability. The second continuation determination time is changed to a value that is less likely to be determined as the second action than when any one of the degrees is high. In the above embodiment, the micro movement abnormality continuation determination time corresponds to an example of the second continuation determination time, and the processing control unit 144 causes the sleep state determination unit 142 to determine the micro movement abnormality continuation determination time. It changes according to the sleep judgment result of.

According to this, the monitored person monitoring support system MS, the activity detection apparatus, and the activity detection method, for example, continue determination time of the sub activity determination process that determines an activity that may occur in the sleep state in the case of the sleep state. Can be changed to a value that is easily determined to be the action, etc., so that erroneous determination can be further reduced.

In the eighth modified embodiment, the process control unit 144 determines whether the first sub behavior determination unit 1431 uses the first sub measurement result of the first sub sensor according to the sleep determination result of the sleep state determination unit 142, And, it is controlled whether or not to make the second sub behavior determination unit 1432 use the second sub measurement result of the second sub sensor. In the above-described embodiment and the first modification, the execution of the behavior determination processing in the behavior determination unit 143 is controlled, and in the second modification, the output of the behavior determination result in the behavior determination unit 143 is controlled. In the modification, by controlling the input of the action determination unit 143, an effect equivalent to the effect obtained by the control of the execution and the control of the output can be obtained. More specifically, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability degree is high, the process control unit 144 causes the first sub-action determination unit 1431 to execute the process. The first sub measurement result of one sub sensor (the target image generated by the camera 111 of the sensor unit 11 in the above embodiment) is used, and the second sub behavior determination unit 1432 performs the second sub measurement of the second sub sensor The result (in the above embodiment, the Doppler signal generated by the Doppler sensor 112 of the sensor unit 11 and stored in the SU storage unit 16) is used. In one example, the process control unit 144 causes the first sub behavior determination unit 1431 to use the target image generated by the camera 111 in each of the processes S21 to S27 described above with reference to FIG. In the second sub behavior determination unit 1432, the Doppler signal generated by the Doppler sensor 112 and stored in the SU storage unit 16 is used. When the sleep determination result of the sleep state determination unit 142 indicates that both the sleep level and the reliability are low, the process control unit 144 causes the first sub behavior determination unit 1431 to perform the first sub measurement result of the first sub sensor (described above In the above, the target image is used, and the second sub behavior determination unit 1432 does not use the second sub measurement result of the second sub sensor (the Doppler signal in the above description). In one example, the process control unit 144 causes the first sub behavior determination unit 1431 to use the target image generated by the camera 111 in each of the processes S21 to S27 described above with reference to FIG. , The second sub behavior determination unit 1432 does not use the Doppler signal generated by the Doppler sensor 112 and stored in the SU storage unit 16. That is, the process S28 is not performed. When the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability is high, the process control unit 144 causes the first sub behavior determination unit 1431 to select the first sub sensor of the first sub sensor. The measurement result (the target image as described above) is not used, and the second sub behavior determination unit 1432 uses the second sub measurement result of the second sub sensor (the Doppler signal as described above). In one example, the process control unit 144 does not cause the first sub behavior determination unit 1431 to use the target image generated by the camera 111 in each of the processes S21 to S27 described above with reference to FIG. 4. In S28, the second sub behavior determination unit 1432 uses the Doppler signal generated by the Doppler sensor 112 and stored in the SU storage unit 16. That is, each process of process S21 to process S27 is not performed.

According to this, in the monitored person monitoring support system MS, the activity detection apparatus, and the activity detection method, for example, the sub activity determination unit that determines the activity that can not occur in the sleep state does not use the sub measurement result Conversely, control the action determination unit 143 according to the sleep determination result of the sleep state determination unit 142 so that the sub-action determination unit determines the action that may occur in the sleep state, or the like. False positives can be further reduced.

In a ninth modified embodiment, the first sub-action determination process determines whether or not it is the first action this time based on the first sub-measurement result of the first sub-sensor and the past first sub-action determination result. The processing control unit 144 forcibly changes the current first sub-action determination result to a preset specified value in accordance with the sleep determination result of the sleep state determination unit 142. In the above-mentioned embodiment, the state variable corresponds to an example of the past first sub-action determination result. For example, when the sleep determination result of the sleep state determination unit 142 indicates that either the sleep degree or the reliability degree is high, the process control unit 144 forcibly updates the state variable with “bed entry”. . Therefore, even if the wakeup is erroneously determined, the wakeup can be determined again, and the erroneous determination can be further reduced.

According to this, the above-mentioned person-to-be-monitored monitoring support system MS, the above-mentioned action detection device and the above-mentioned action detection method set the current first sub-action determination result in advance according to the sleep determination result of the sleep state determination unit 142 Since the value is forcibly changed to the prescribed value, the next first sub-action determination process can be processed more appropriately, and erroneous determinations can be further reduced.

In the tenth modified embodiment, as shown by the broken line in FIG. 2, the sensor unit SU functionally further includes a clock unit 147 for clocking the date and time in the SU control processing unit 14, and at least a sleep time zone The SU storage unit 16 is further provided with a schedule information storage unit 161 that stores schedule information representing the schedule of the included monitored person Ob in association with the monitored person Ob, and the processing control unit 144 The schedule of the monitored person Ob corresponding to the acquired current time is extracted from the schedule information storage unit 161, and the extracted schedule of the monitored person Ob and the sleep determination result of the sleep state determination unit 142 are extracted. The action determination unit 143 is controlled according to For example, if the schedule of the monitored person Ob corresponding to the current time is a sleep time zone, the processing control unit 144 may, for example, determine that the sleep determination result of the sleep state determination unit 142 has both the sleep level and the reliability level. The first action determination threshold is changed to a value that is less likely to be determined as the first action than when it is low, or, for example, the sleep determination result of the sleep state determination unit 142 indicates the sleep degree and the reliability The second action determination threshold is changed to a value that is more likely to be determined to be the second action than when both are low, or, for example, the sleep determination result of the sleep state determination unit 142 is the sleep degree and the reliability The first continuation determination time is changed to a value that is less likely to be determined as the first action than when both are low, or, for example, the sleep determination result of the sleep state determination unit 142 is the sleep degree and the confidence Every time The determined likely value and the a second behavior than in case both low, equally or change the second continuation determination time.

According to this, the monitored person monitoring support system MS, the activity detecting device and the activity detecting method control the activity determining unit 143 according to the schedule of the monitored person Ob and the sleep determination result of the sleep state determining unit 142. As a result, the schedule of the person to be monitored Ob can be taken into consideration, and false decisions can be further reduced.

Although the present specification discloses various aspects of the technology as described above, the main technologies are summarized below.

An activity detection apparatus according to an aspect includes first and second sensors for measuring a person to be monitored, and a sleep state determination unit that determines a sleep state of the person to be monitored based on a first measurement result of the first sensor. An action determination unit that determines a predetermined action of the person to be monitored based on a second measurement result of the second sensor, and a process control that controls the action determination unit according to a sleep determination result of the sleep state determination unit And a unit.

For example, if the person being monitored is in a sleep state, for example, no action such as admission, leaving or falling can not occur, and if the action determination unit determines an action that can not occur in such a sleep state, that is false. The probability of being a judgment is high. The behavior detection device controls the behavior determination unit according to the sleep determination result of the sleep state determination unit, so that erroneous determination can be further reduced.

In another aspect, in the above-described behavior detection device, the second sensor includes first and second sub-sensors that measure a person to be monitored, and the behavior determination unit determines a first sub-measurement result of the first sub-sensor. A first sub-action determining unit that executes a first sub-action determining process of determining a first action belonging to the first group among the predetermined actions of the person to be monitored based on the second sub-sensor; A second sub-action determining unit that executes a second sub-action determining process of determining a second action belonging to a second group different from the first group among the predetermined actions of the monitored person based on a measurement result; The process control unit controls at least one of the first and second sub-action determination units according to the sleep determination result of the sleep state determination unit. Preferably, in the above-described behavior detection apparatus, the first behavior is entering the bed when the monitored person enters the bedding, getting up when the monitored person wakes up, leaving the monitored person away from the bedding, and the monitored person bedding Includes falls that have fallen from it, and falls where the monitored person falls outside the bedding. Preferably, in the above-mentioned action detection device, the second action includes a movement abnormality that is an abnormality of movement due to breathing of a person being monitored. Preferably, in the above-described behavior detection device, the first sensor and the second sub-sensor are one dual-use Doppler sensor, and the sleep state determination unit is based on the Doppler signal of the Doppler sensor. A sleep state determination process of determining a sleep state, and the second sub-action determination unit is configured to select a second action different from the first group among the predetermined actions of the person to be monitored based on the Doppler signal of the Doppler sensor; A second sub-action determination process is performed to determine a second action belonging to a group.

Such an action detection device can divide the predetermined action into a first action belonging to a first group which can not occur in the sleep state and a second action belonging to a second group which can occur in the sleep state. Therefore, the behavior determination unit can be more appropriately controlled according to the sleep determination result of the sleep state determination unit, and erroneous determination can be further reduced.

In another one mode, in the above-mentioned action detection device, the processing control unit executes the first sub-action judging process in the first sub-action judging unit according to the sleep judgment result of the sleep state judging unit. It controls whether or not to execute the second sub action determination process in the second sub action determination unit. Preferably, in the above-described behavior detection device, the sleep state determination unit represents the degree of sleep representing the degree of depth of sleep of the person to be monitored based on the first measurement result of the first sensor, and confidence in the degree of sleep Find the degree of confidence that represents the degree of gender. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The unit does not execute the first sub action determination process, and causes the second sub action determination unit to execute the second sub action determination process. When the sleep determination result of the sleep state determination unit is one of the sleep degree and the reliability is high, the sleep degree is equal to or more than a predetermined sleep determination threshold set in advance, or In this case, the degree is equal to or more than a predetermined confidence determination threshold value set in advance. Preferably, in the above-described behavior detection device, the processing control unit causes the first sub-action determination unit to select the first sub-action determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. One sub-action determination processing is executed, and the second sub-action determination unit is not caused to execute the second sub-action determination processing. When the sleep determination result of the sleep state determination unit indicates that both the sleep degree and the reliability are low, the sleep degree is less than a predetermined sleep determination threshold set in advance, and the reliability is set in advance. In this case, it is less than the predetermined confidence determination threshold. Preferably, in the above-described behavior detection device, the processing control unit determines that the second sub-action determination is performed when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. Only the unit is to be controlled, and the second sub behavior determination unit is caused to execute the second sub behavior determination process. Preferably, in the above-described behavior detection device, the process control unit controls only the second sub-action determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The target is not to cause the second sub-action determination unit to execute the second sub-action determination process.

Such an activity detection apparatus executes, for example, only a sub-action determination process that determines an action that can not occur in the sleep state, or conversely performs only a sub-action determination process that determines an action that may occur in the sleep state. By controlling the behavior determination unit in accordance with the sleep determination result of the sleep state determination unit so as to reduce the false determination, false determination can be further reduced.

In another mode, in the above-mentioned action detection device, the processing control unit outputs the first sub-action determination result in the first sub-action determination unit according to the sleep determination result of the sleep state determination unit. It controls whether or not to output the second sub-action determination result in the second sub-action determining unit. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The unit does not output the first sub-action determination result, and causes the second sub-action determination unit to output the second sub-action determination result. Preferably, in the above-described behavior detection device, the processing control unit causes the first sub-action determination unit to select the first sub-action determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The first sub-action determination result is output, and the second sub-action determination unit does not output the second sub-action determination result. Preferably, in the above-described behavior detection device, the processing control unit determines that the second sub-action determination is performed when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. Only the unit is to be controlled, and the second sub-action judging unit outputs the second sub-action judgment result. Preferably, in the above-described behavior detection device, the process control unit controls only the second sub-action determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. It is an object, and the second sub behavior determination unit does not output the second sub behavior determination result.

Such a behavior detection apparatus outputs, for example, only the sub-action determination result of the sub-action determination process that determines an action that can not occur in the sleep state, or conversely determines the action that can occur in the sleep state. By controlling the behavior determination unit according to the sleep determination result of the sleep state determination unit so as to output only the sub behavior determination result of processing or the like, erroneous determination can be further reduced.

In another aspect, in the above-described behavior detection device, the processing control unit determines a first sub-action determination result in the first sub-action determination unit according to the sleep determination result of the sleep state determination unit as the second sub-action It is controlled whether or not the second sub-action determination result in the action determination unit is to be assisted. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. When the first sub-behavior determination result in the section is assisted by the second sub-behavior determination result in the second sub-behavior determination unit, and the sleep determination result of the sleep state determination unit indicates that both the sleep degree and the reliability are low The first sub behavior determination result in the first sub behavior determination unit is not assisted by the second sub behavior determination result in the second sub behavior determination unit. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The first sub-action determination result in the unit is rewritten to the second sub-action determination result in the second sub-action determination unit. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The second sub-action determination result in the second sub-action determination unit is added to the first sub-action determination result in the unit.

Such a behavior detection apparatus determines, for example, a sub-action determination result of a sub-action determination process that determines an action that can not occur in the sleep state in the sleep state, and determines an action that can occur in the sleep state Since it becomes possible to assist with the sub-action determination result of the above, erroneous determination can be further reduced.

In another aspect, in the above-described behavior detection device, the first sub-action determination process includes a first preset measurement result associated with the first sub-measurement result of the first sub-sensor and the first action. It is a process which determines whether it is the said 1st action by comparing with an action determination threshold value, and the said process control part is said 1st according to the sleep determination result of the said sleep state determination part as said control. The first action determination threshold value in the first sub action determination process executed by the sub action determination unit is changed. Preferably, in the above-described behavior detection device, the process control unit performs the control when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The first behavior determination threshold is changed to a value that is less likely to be determined as the first behavior than when the sleep determination result of the state determination unit is low in both the sleep level and the reliability. Preferably, in the above-described behavior detection device, the processing control unit may perform, as the control, the sleep state determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The first behavior determination threshold is changed to a value that is more likely to be determined as the first behavior as compared with the case where the sleep determination result indicates that either the sleep degree or the reliability is high.

Such a behavior detection apparatus, for example, changes the behavior determination threshold value of the sub behavior determination process that determines the behavior that can not occur in the sleep state to a value that can not be substantially determined as the behavior in the sleep state. Since it becomes possible to do so, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described behavior detecting device, the second sub-action determining process is performed by setting a second sub-measurement result of the second sub-sensor and a preset second associated with the second action. It is a process which determines whether it is the said 2nd action by comparing with an action determination threshold value, and the said process control part is said 2nd according to the sleep determination result of the said sleep state determination part as said control. The second action determination threshold value in the second sub action determination process performed by the sub action determination unit is changed. Preferably, in the above-described behavior detection device, the processing control unit may perform, as the control, the sleep state determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The second behavior determination threshold value is changed to a value that is less likely to be determined as the second behavior as compared with the case where the sleep determination result indicates that either the sleep degree or the reliability degree is high. Preferably, in the above-described behavior detection device, the process control unit performs the control when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The second behavior determination threshold is changed to a value that is more likely to be determined as the second behavior than when the sleep determination result of the state determination unit is low in both the sleep degree and the reliability.

Such a behavior detection apparatus, for example, changes the behavior determination threshold value of the sub behavior determination process that determines the behavior that may occur in the sleep state to a value that is easily determined to be the behavior in the case of the sleep state. Since this becomes possible, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described behavior detection device, the first sub-action determination process corresponds to a first sub-measurement result of the first sub-sensor and the first action at predetermined time intervals set in advance. It is temporarily determined whether or not it is the first action by comparing it with a preset first action determination threshold value, and if the provisionally determined temporary determination result is the first action, it is determined in advance. It is a process which finally determines that it is the said 1st action, when continuing for the set 1st continuation determination time, and the said process control part is a sleep determination of the said sleep state determination part as said control. The first continuation determination time in the first sub behavior determination process performed by the first sub behavior determination unit is changed according to the result. Preferably, in the above-described behavior detection device, the process control unit performs the control when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The first continuation determination time is changed to a value that is less likely to be determined as the first action than when the sleep determination result of the state determination unit is low in both the sleep degree and the reliability. Preferably, in the above-described behavior detection device, the processing control unit may perform, as the control, the sleep state determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The first continuation determination time is changed to a value that is more likely to be determined to be the first action than when the sleep determination result is high in either the sleep degree or the reliability.

Such a behavior detection apparatus, for example, changes the continuation determination time of the sub behavior determination process that determines the behavior that can not occur in the sleep state to a value that can not be substantially determined as the behavior in the sleep state. Since it becomes possible to do so, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described behavior detection device, the second sub-action determination process corresponds to a second sub-measurement result of the second sub-sensor and the second action at predetermined time intervals set in advance. It is temporarily determined whether or not it is the second action by comparing it with a preset second action determination threshold value, and if the provisionally determined temporary determination result is the second action, it is determined in advance. The processing is finally determined to be the second action when continuing for the set second continuation determination time, and the processing control unit determines the sleep determination of the sleep state determination unit as the control. According to the result, the second continuation determination time in the second sub-action determination process performed by the second sub-action determination unit is changed. Preferably, in the above-described behavior detection device, the process control unit performs the control when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The second continuation determination time is changed to a value that is more likely to be determined as the second action than when the sleep determination result of the state determination unit is low in both the sleep degree and the reliability. Preferably, in the above-described behavior detection device, the processing control unit may perform, as the control, the sleep state determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The second continuation determination time is changed to a value that is less likely to be determined as the second action as compared with the case where the sleep determination result indicates that either the sleep degree or the reliability is high.

Such a behavior detection apparatus, for example, changes the continuation determination time of the sub behavior determination process that determines the behavior that may occur in the sleep state to a value that is easily determined to be the behavior in the case of the sleep state. Since this becomes possible, it is possible to further reduce the erroneous determination.

In another aspect, in the above-described behavior detection device, the processing control unit causes the first sub-action determination unit to generate a first sub-measurement result of the first sub-sensor according to a sleep determination result of the sleep state determination unit. And whether or not to cause the second sub-operation determination unit to use the second sub-measurement result of the second sub-sensor. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The control unit causes the unit to use the first sub measurement result of the first sub sensor, and causes the second sub behavior determination unit to use the second sub measurement result of the second sub sensor. Preferably, in the above-described behavior detection device, the processing control unit causes the first sub-action determination unit to select the first sub-action determination unit when the sleep determination result of the sleep state determination unit is low in both the sleep degree and the reliability. The first sub measurement result of one sub sensor is used, and the second sub behavior determination unit does not use the second sub measurement result of the second sub sensor. Preferably, in the above-described behavior detection device, the processing control unit determines the first sub-action determination when the sleep determination result of the sleep state determination unit indicates that either the sleep degree or the reliability is high. The control unit does not use the first sub measurement result of the first sub sensor, and causes the second sub behavior determination unit to use the second sub measurement result of the second sub sensor.

Such a behavior detection apparatus does not use the sub-measurement result in, for example, the sub behavior determination unit that determines the behavior that can not occur in the sleep state, or conversely determines the behavior that can occur in the sleep state. By controlling the behavior determination unit according to the sleep determination result of the sleep state determination unit so as to use the sub-measurement result, etc., false determination can be further reduced.

In another aspect, in the above-described action detection device, the first sub-action determination process is a first action this time based on a first sub-measurement result of the first sub-sensor and a first sub-action determination result in the past. And the processing control unit forcibly changes the current first sub-action determination result to a preset predetermined value according to the sleep determination result of the sleep state determination unit. Do.

Since such an action detection device forcibly changes the current first sub-action determination result to a preset prescribed value according to the sleep determination result of the sleep state determination unit, the next first sub-action determination is performed. Processing can be more appropriately processed, and false determinations can be further reduced.

In another aspect, in the above-described behavior detection device, the watch person is provided with schedule information representing a watch of the date and time and a schedule of the person to be monitored including at least a sleep time zone. And the process control unit acquires the current time from the clock unit, and the schedule information storage unit corresponds to the schedule of the person to be monitored corresponding to the acquired current time. And the behavior determination unit is controlled according to the extracted schedule of the monitored person and the sleep determination result of the sleep state determination unit.

Such a behavior detection device controls the behavior determination unit according to the schedule of the monitored person and the sleep determination result of the sleep state determination unit, so that the schedule of the monitored person can be taken into consideration, thereby reducing erroneous determinations. it can.

In the behavior detecting method according to another aspect, the sleep state of the person to be monitored is determined based on the measurement step of measuring the person to be monitored by the first and second sensors, and the first measurement result of the first sensor. The action determination step according to the sleep determination result of the sleep state determination step, the action determination step of determining the predetermined action of the monitored person based on the second measurement result of the second sensor, and the sleep state determination step And a process control process for controlling the process.

Such a behavior detection method controls the behavior determination process according to the sleep determination result of the sleep state determination process, so that erroneous determination can be further reduced.

A monitored person monitoring support system according to another aspect is provided corresponding to the monitored person, the sensor device detecting a predetermined behavior of the monitored person, and the sensor device communicably connected to the sensor device Central processing unit for managing detection results received from the server, and a terminal device communicably connected to the central processing unit and receiving and displaying the detection results via the central processing unit, It is a to-be-monitored person monitoring assistance system for supporting monitoring, and the said sensor apparatus contains one of these above-mentioned action detection apparatuses.

According to this, it is possible to provide a person-to-be-monitored support system using any of the above-described behavior detection devices. Such a person-to-be-monitored support system uses any one of the above-described action detection devices, so that it is possible to further reduce erroneous determinations.

This application is based on Japanese Patent Application No. 2017-155073 filed on Aug. 10, 2017, the contents of which are incorporated in the present application.

Although embodiments of the present invention have been illustrated and described in detail, it is merely illustrative and not restrictive. The scope of the present invention should be interpreted by the terms of the appended claims.

While the present invention has been properly and sufficiently described above through the embodiments with reference to the drawings in order to express the present invention, those skilled in the art can easily change and / or improve the above embodiments. It should be recognized that it is possible. Therefore, unless a change or improvement implemented by a person skilled in the art is at a level that deviates from the scope of the claims set forth in the claims, the change or the improvement is the scope of the rights of the claim It is interpreted as being included in

According to the present invention, it is possible to provide an activity detection apparatus and an activity detection method for detecting a predetermined activity of a monitored person to be monitored, and a monitored person monitoring support system using the activity detection apparatus.

Claims

First and second sensors for measuring the monitored person;
A sleep state determination unit that determines a sleep state of the person to be monitored based on a first measurement result of the first sensor;
An action determining unit that determines a predetermined action of the person to be monitored based on a second measurement result of the second sensor;
And a processing control unit that controls the behavior determination unit according to the sleep determination result of the sleep state determination unit.
Behavior detection device.
The second sensor includes first and second sub-sensors that measure the monitored person,
The said action determination part performs the 1st sub action determination processing which determines the 1st action which belongs to the 1st group among predetermined actions in the said person to be monitored based on the 1st sub measurement result of the 1st sub sensor The second sub-operation belonging to the second group different from the first group among the predetermined activities of the person to be monitored based on the first sub-operation judging unit and the second sub-measurement result of the second sub-sensor And 2) a second sub-action determining unit that executes the second sub-action determining process,
The process control unit controls at least one of the first and second sub-action determination units according to the sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 1.
The process control unit determines whether or not the first sub behavior determination process in the first sub behavior determination unit is to be performed according to the sleep determination result of the sleep state determination unit, and the second sub behavior determination unit Control whether or not to execute the second sub-action determination process in
The behavior detection device according to claim 2.
Whether the processing control unit outputs the first sub-action determination result in the first sub-action determining unit according to the sleep determination result of the sleep state determining unit, and the second sub-action determining unit Control whether or not to output the second sub-action determination result in
The behavior detection device according to claim 2.
The processing control unit assists the first sub-behavior determination result in the first sub-behavior determination unit according to the second sub-behavior determination result in the second sub-behavior determination unit according to the sleep determination result of the sleep state determination unit. Control whether or not
The behavior detection device according to claim 2.
The first sub-action determination process compares the first sub-measurement result of the first sub-sensor with a preset first action determination threshold value associated with the first action, and the first action is determined. It is processing to determine whether or not
The process control unit changes, as the control, a first behavior determination threshold value in a first sub behavior determination process performed by the first sub behavior determination unit according to a sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 2.
The second sub-action determination process compares the second sub-measurement result of the second sub-sensor with a preset second action determination threshold value associated with the second action and the second action. It is processing to determine whether or not
The process control unit changes, as the control, a second behavior determination threshold in a second behavior determination process executed by the second behavior determination unit according to a sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 2.
The first sub-action determination process is performed by setting a first sub-measurement result of the first sub-sensor and a first action determination threshold set in advance, which is associated with the first action, at predetermined time intervals set in advance. It is temporarily determined whether or not it is the first action by comparing with the above, and the temporary determination result temporarily determined as above is continuing the first continuation determination time set in advance, if it is the first action. In this case, the process is finally determined to be the first action,
The processing control unit changes, as the control, a first continuation determination time in a first sub behavior determination process performed by the first sub behavior determination unit according to a sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 2.
The second sub-action determination process sets a second action determination threshold set in advance, which is associated with the second sub-measurement result of the second sub-sensor and the second action at predetermined time intervals set in advance. It is temporarily determined whether or not it is the second action by comparing with the above, and the temporary determination result temporarily determined is continuing the second continuation determination time set in advance if the second action is the result. In this case, the process is finally determined to be the second action,
The process control unit changes, as the control, a second continuation determination time in a second sub behavior determination process performed by the second sub behavior determination unit according to the sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 1.
The processing control unit determines whether or not the first sub behavior determination unit uses the first sub measurement result of the first sub sensor according to the sleep determination result of the sleep state determination unit, and the second sub Controlling whether the action determination unit is to use the second sub measurement result of the second sub sensor;
The behavior detection device according to claim 2.
The first sub-action determination process is a process of determining whether or not it is the first action this time based on the first sub-measurement result of the first sub-sensor and the past first sub-action determination result.
The process control unit forcibly changes the current first sub-action determination result to a preset specified value according to the sleep determination result of the sleep state determination unit.
The behavior detection device according to claim 2.
Clock part which measures date and time, and
A schedule information storage unit which stores schedule information representing at least the time zone of sleep including the schedule of the person to be monitored in association with the person to be monitored;
The process control unit acquires the current time from the clock unit, extracts the schedule of the monitored person corresponding to the acquired current time from the schedule information storage unit, and extracts the extracted monitored person Controlling the behavior determination unit according to the schedule and the sleep determination result of the sleep state determination unit;
The behavior detection apparatus according to any one of claims 1 to 11.
A measuring step of measuring a person to be monitored by each of the first and second sensors;
A sleep state determining step of determining a sleep state of the person to be monitored based on a first measurement result of the first sensor;
An action determining step of determining a predetermined action of the person to be monitored based on a second measurement result of the second sensor;
Processing control step of controlling the behavior determination step according to the sleep determination result of the sleep state determination step;
Behavior detection method.
A sensor device provided corresponding to the person to be monitored, which detects a predetermined behavior of the person to be monitored, a central processing unit communicably connected to the sensor device, and managing a detection result received from the sensor device; The monitored person monitoring support system includes a terminal device communicably connected to the central processing unit and receiving and displaying the detection result via the central processing unit, and supporting monitoring of the monitored person. ,
The sensor device includes the behavior detection device according to any one of claims 1 to 12.
Monitored person monitoring support system.