JP2011030919A - Subject detecting system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To accurately detect abnormality of a subject's body. <P>SOLUTION: The subject detecting system (S) includes an imaging member (CA) imaging subject images; a deactivation discriminating means (C12C) discriminating whether the subject is in a deactivated state based on the difference between a first subject image and a second subject image; an abnormality discriminating means (C12) discriminating the occurrence of abnormality to the subject's body when the subject is discriminated to be in the deactivated state; and an abnormality notifying means (C104) notifying the effect that the occurrence of abnormality to the subject's body is discriminated. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a subject detection system that detects an abnormality or the like of a subject's body.

In recent years, in Japan, due to the increase in the elderly population, the occurrence of solitary death of elderly people living alone in housing complexes such as housing estates has become a social problem. However, there is a limit to the manpower of relatives, home helpers, nursing volunteers, nursing care workers, etc. for nursing care support for elderly people living alone, etc. Supporting nursing care support systems that make full use of IT (Information Technology) technology There is an urgent need to establish a system.
Here, as an example of a care support system, in a care facility or hospital, when the health status of a care recipient (resident, inpatient, etc.) is monitored remotely and a physical abnormality is detected, a relative or doctor For example, the techniques described in Patent Documents 1 to 4 below are known for abnormality reporting systems for reporting to nurses and the like.

  JP-A-2005-278765 as Patent Document 1 continuously monitors the subject's physical condition for 24 hours using a physical condition monitoring device (1) attached to a subject such as an elderly person living alone. If the determination is made, the mobile phone with GPS function carried by the subject (2), the Internet (3), and the computer device (4) managed by the operator are notified to the family, care center, etc. (5) The technology about the safe life support system is described. In Patent Document 1, the body condition monitoring device (1) is constituted by a microcomputer (9), an acceleration sensor (6), and the like, and the microcomputer (9) is input from the acceleration sensor (6). Based on the acceleration, the movement, breathing, heartbeat, posture, and fall of the human body are calculated to determine whether these are normal or abnormal.

  Japanese Patent Application Laid-Open No. 2005-46320 as Patent Document 2 describes measurement value information (S) based on biological information from an individual sensor (7) attached to a care recipient (M) as reference value information (R). ), A technique for notifying the nurse (P) that an abnormal situation has occurred in the care recipient (M) is described. Note that Patent Document 2 describes measuring the body temperature, heart rate, arrhythmia, respiratory rate, blood pressure, and the like as the biological information. Further, in Patent Document 2, when an abnormal situation occurs, video information (K) from the monitoring camera (6) is also transmitted together with the measurement value information (S), and the actual information of the care recipient (M) is transmitted. A technique for confirming the state is described.

  Japanese Patent Application Laid-Open No. 2008-40761 as Patent Document 3 attaches a sensor (14) for detecting a normal state / abnormal state of biometric data to a service user (9), and from the sensor (14). Is described in 24 hours in real time via the IP network (21). Patent Document 3 discloses that the information processing center (22) that has acquired the biological data via the IP network (21) creates and stores biological information, or the disease sign management center that has acquired the biological information. (23) describes a technique in which an electronic medical record is created or a nursing / emergency center (24) that has acquired the electronic medical record performs a nursing / emergency treatment. Patent Document 3 describes measuring the body temperature, heart rate, blood pressure, heart sound, falls, body weight, blood sugar level, urine sugar level, etc. as the biological data. In Patent Document 3, a specialist at a care / emergency center (24) has a video dialogue via a monitor of a user terminal (6), a camera (7), etc. installed in a home / care facility (1). The technology to check the situation (interview, safety confirmation, etc.) is described.

Furthermore, Japanese Patent Application Laid-Open No. 2008-4084 as Patent Document 4 includes a signal from a heartbeat / respiration beat sensor (2a) that detects a heartbeat / respiration beat in a state where an assistant (12) is lying on a bed (11). There is described a technique regarding an emergency call system that issues a warning signal to a support organization (6) from a control device (3) that constantly receives the signal when the signal is interrupted for a certain time. In Patent Document 4, a thin-film pressure sensor is used as the heartbeat / respiration pulse sensor (2a), and specifically, an ultra-sensitive pressure-sensitive film sensor manufactured by Finland EMFiT is used. Is described.
Further, in Patent Document 4, a load when a person who needs assistance (12) gets off the bed (11) is detected by a mat sensor (7) arranged on the side of the bed (11), whereby a heart rate / Whether the person requiring assistance (12) has left the bed (11) or the heartbeat / respiration beat of the person requiring assistance has stopped when the signal from the respiratory sensor (2a) is interrupted Techniques for discriminating between are described.

Japanese Patent Laying-Open No. 2005-278765 (Abstract, “0013” to “0021”, FIGS. 1 to 5) Japanese Patent Laying-Open No. 2005-46320 (abstract, “0010” to “0034”, FIGS. 1 to 4) JP 2008-40761 A (Abstract, “0024” to “0026”, “0071” to “0081”, FIGS. 1 to 5) JP 2008-4084 A (abstract, “0016” to “0021”, “0032” to “0034”, FIGS. 1 to 5)

"Finland EMFIT High Sensitive Pressure Sensor", "online", 2007, Euro Protech Co., Ltd., "Search July 22, 2009", Internet <URL: http://www.europrotech.com/Euro /trade/t_emfit2.html> Naohiro Wakamura and three others, “Construction of Intelligence Room-Operation of Home Appliances Using Intuitive Gestures”, “online”, July 2005, “July 22, 2009 Search”, Internet <URL: http://www.mech.chuo-u.ac.jp/umedalab/publications/pdf/2005/suzuki_2005_miru.pdf>

(Problems of conventional technology)
In the techniques described in Patent Literatures 1 to 4, since biological information of a care recipient is measured by a sensor, measurement errors such as noise may occur. In this case, depending on the determination condition as to whether or not it is an abnormal state, there is a possibility that the abnormal state is erroneously detected, or the abnormal state is failed to be detected, that is, cannot be detected. In addition, there is no method for reconfirming whether it is a false detection or the like, and even if a caregiver or the like lacking manpower rushes, it may be useless.
In addition, in the techniques described in Patent Documents 1 and 4, since only biological information such as heartbeat and respiration is remotely monitored, the state of the care recipient at the time of abnormality is visually confirmed after reporting the abnormal state. There was a problem that could not.

In addition, in the techniques described in Patent Documents 1 to 3, in order to constantly detect abnormalities in the body of a care recipient, it is necessary to always wear a contact sensor that measures biological information. Could be annoying. In the technique described in Patent Document 4, it is not necessary to wear a contact-type sensor, but there is a problem that the body state can be measured only in a narrow range such as a bed.
Furthermore, in the techniques described in Patent Documents 2 and 3, since the video information of the camera that captured the care recipient is transmitted as it is via the network, the privacy of the care recipient may be infringed. .

In view of the above circumstances, the present invention has the following contents (O01) to (O02) as technical problems.
(O01) To accurately detect abnormality of the subject's body.
(O02) Ensure the privacy of the subject.

In order to solve the technical problem, the subject detection system according to claim 1 comprises:
An imaging member for imaging a subject image as a subject image;
When the subject image continuously captured at a preset time interval by the imaging member is a first subject image and a second subject image, the difference between the first subject image and the second subject image Based on non-operation determination means for determining whether or not the subject is in an inoperative state;
An abnormality determining means for determining that an abnormality has occurred in the subject's body when the non-operation determining means determines that the subject is in an inoperative state;
An abnormality reporting means for reporting that the abnormality determining means has determined that an abnormality has occurred in the subject's body;
It is provided with.

The invention according to claim 2 is the subject detection system according to claim 1,
Contour extracting means for extracting a contour image that is an image of the subject's contour from the subject image;
When the image obtained by extracting the contour of the subject from the first subject image and the second subject image by the contour extracting means is used as the first contour image and the second contour image, the first contour image and the second contour The non-operation determination means for determining whether or not the subject is in an inoperative state based on a difference from an image;
Image display means for displaying the contour image at each time interval;
It is provided with.

The invention according to claim 3 is the subject detection system according to claim 2,
The image display means for switching the contour image to the subject image when the abnormality notification means reports that an abnormality has occurred in the subject's body;
It is provided with.

The invention according to claim 4 is the subject detection system according to claim 3,
When it is reported by the abnormality reporting means that an abnormality has occurred in the body of the subject, and when an input for switching the contour image to the subject image is made, it is determined that the contour image is switched to the subject image. Switching discriminating means to perform,
The image display means for switching and displaying the contour image to the subject image when it is determined by the switching determination means to switch the contour image to the subject image;
It is provided with.

Invention of Claim 5 is a test subject detection system in any one of Claims 1 thru | or 4,
The imaging member arranged so as to be capable of imaging the preset action range of the subject,
It is provided with.

The invention described in claim 6 is the subject detection system according to any one of claims 1 to 5,
Determining that an abnormality has occurred in the body of the subject when the number of times that the subject is continuously determined to be in an inoperative state by the non-operation determining unit exceeds a preset threshold for inactivity; Anomaly discrimination means,
It is provided with.

The invention described in claim 7 is the subject detection system according to any one of claims 1 to 6,
A biological information measuring member for measuring the biological information of the subject;
When the measured value of the biological information measured by the biological information measuring member is outside the normal range for the living body from a preset minimum value to a maximum value, and the non-operation determining means indicates that the subject is inactive The abnormality determining means for determining that an abnormality has occurred in the body of the subject when determined to be in a state;
It is provided with.

The invention according to claim 8 is the subject detection system according to claim 7,
The biological information measuring member configured by a thin film pressure sensor that detects a waveform of pressure according to the heartbeat, breathing, and body movement of the subject,
When the heart rate per unit time of the subject based on the detection signal from the pressure sensor is outside the normal heart rate range from the preset minimum heart rate to the maximum heart rate, or based on the detection signal When the respiration rate per unit time of the subject is outside the normal range for breathing from the preset minimum respiration rate to the maximum respiration rate, or the number of body movements per unit time of the subject based on the detection signal is The abnormality determining means for determining that the measured value of the biological information is outside the normal range for the living body when the normal number for the body movement from the set minimum body movement number to the maximum body movement number is outside the normal range for body movement;
It is provided with.

The invention according to claim 9 is the subject detection system according to claim 8,
The pressure-sensitive sensor arranged in a predetermined range of action of the subject,
It is provided with.

The invention according to claim 10 is the subject detection system according to any one of claims 7 to 9,
While prompting the subject to speak, a voice extraction member that extracts the voice accompanying the subject's utterance;
When the voice extracted by the voice extraction member is outside the preset normal range for voice, and the measurement value of the biological information measured by the biological information measurement member is outside the normal range for biological And when the non-operation determination unit determines that the subject is in an inoperative state, the abnormality determination unit determines that an abnormality has occurred in the subject's body;
It is provided with.

The invention according to claim 11 is the subject detection system according to any one of claims 1 to 10,
An imaging discriminating means for discriminating whether or not the subject image has been imaged;
Absence determining means for determining that the subject is absent when the imaging determining means determines that the subject image is not captured;
Absence notification means for reporting that the subject is determined to be absent by the absence determination means;
It is provided with.

According to the first aspect of the present invention, the abnormality of the subject's body can be automatically detected by image analysis of the subject image, and the subject image is visually confirmed after the abnormality of the subject's body is automatically detected. You can also As a result, false detection and inability to detect can be reduced, and abnormality of the subject's body can be detected with high accuracy. According to the first aspect of the present invention, when the subject image is not displayed when the abnormality of the subject's body is automatically detected, infringement of the subject's privacy is reduced as compared with the case where the subject image is displayed. be able to.
According to the second aspect of the present invention, since the subject's malfunction is automatically detected by image analysis of the subject's contour image, it is based on the error of the image other than the contour as compared with the case without the configuration of the present invention. False detection and inability to detect can be reduced, and abnormalities in the subject's body can be accurately detected. In addition, according to the second aspect of the present invention, the contour image can be displayed and visually confirmed, and the invasion of the subject's privacy can be reduced as compared with the case where the subject image is displayed as it is.

According to the third aspect of the present invention, it is possible to prevent the contour image from being switched and displayed on the subject image until it is reported that an abnormality has occurred in the subject's body. Infringement can be reduced, and it is possible to easily confirm the condition of the subject after reporting the abnormality.
According to the fourth aspect of the present invention, it is possible to prevent the contour image from being switched and displayed on the subject image until the switching input is made after it is reported that an abnormality has occurred in the subject's body. Compared with the case where the subject image is displayed before being performed, the invasion of the subject's privacy can be reduced.
According to the fifth aspect of the present invention, it is possible to always capture a subject image in the subject's action range, and detect abnormality of the subject's body over a wide range even if the contact sensor is not always worn. be able to.

According to the sixth aspect of the present invention, it is possible to accurately detect that an abnormality has occurred in the subject's body, compared to the case where the subject's malfunction is determined at a time.
According to the seventh aspect of the present invention, so-called double check can be performed to detect abnormality of the subject's body from two types of detection results of abnormality and inactivity of the subject's biological information, and double check is not performed. Compared to the case, the abnormality of the subject's body can be detected with high accuracy.
According to the invention described in claim 8, three types of heartbeat, respiration, and body movement can be measured as the biological information of the subject.
According to the invention of claim 9, it is possible to always measure the heart rate, the respiratory rate and the number of body movements per unit time in the behavior range of the subject, and even if the contact type sensor is not always worn, Abnormalities of the subject's body can be detected in a wide range.

According to the invention described in claim 10, so-called triple check can be performed, in which abnormality of the subject's body is detected from the three types of detection results of abnormality of the subject's voice, abnormality of the biological information, and inactivity. Compared with the case where the check is not executed, the abnormality of the subject's body can be detected with high accuracy.
According to the eleventh aspect of the present invention, the absence of the subject can be automatically detected and reported when the subject image is not captured.

FIG. 1 is an overall explanatory diagram of a subject detection system according to the first embodiment. FIG. 2 is an explanatory diagram showing the function of each device constituting the subject detection system of the first embodiment in a block diagram (functional block diagram). FIG. 3 is a block diagram continued from FIG. 4 is an explanatory diagram of an example of the contour image of the first embodiment, FIG. 4A is an explanatory diagram of a room image including a subject image captured by the camera, and FIG. 4B is a contour image extracted from the room image of FIG. 4A. It is explanatory drawing of. FIG. 5 is an explanatory diagram of a heartbeat / respiration / body motion waveform of the subject of Example 1, FIG. 5A is an explanatory diagram of an example of a heartbeat waveform, FIG. 5B is an explanatory diagram of an example of a respiratory waveform, and FIG. It is explanatory drawing of an example of the waveform of a body movement. 6 is an explanatory diagram of an example of the voice of the subject of Example 1, FIG. 6A is an explanatory diagram of an example of the normal voice of the subject, and FIG. 6B is an explanatory diagram of an example of the abnormal voice of the subject. FIG. 7 is an explanatory diagram of a subject detection image according to the first embodiment. FIG. 8 is a flowchart of the main process of the subject detection server according to the first embodiment. FIG. 9 is a flowchart of the absence detection process of the subject detection server according to the first embodiment. FIG. 10 is a flowchart of the audio abnormality detection process of the subject detection server according to the first embodiment. FIG. 11 is a flowchart of the biological abnormality detection process of the subject detection server according to the first embodiment. FIG. 12 is a flowchart of the non-operation detection process of the subject detection server according to the first embodiment. FIG. 13 is a flowchart of detection result reporting processing of the client personal computer and the mobile phone according to the first embodiment. FIG. 13 is a flowchart of image display processing of the client personal computer and the mobile phone according to the first embodiment.

Next, specific examples of embodiments of the present invention (hereinafter referred to as examples) will be described with reference to the drawings, but the present invention is not limited to the following examples.
In the following description using the drawings, illustrations other than members necessary for the description are omitted as appropriate for easy understanding.

FIG. 1 is an overall explanatory diagram of a subject detection system according to the first embodiment.
In FIG. 1, a subject detection system S according to the first embodiment of the present invention includes a subject detection server (subject detection device, home server, home controller) SV as a subject detection system S body. The subject detection server SV according to the first embodiment is configured by a so-called computer device.
The subject detection system S includes a camera (imaging member) CA that captures an indoor image including a subject image as an image of an indoor subject (subject, human). The camera CA according to the first exemplary embodiment is arranged so as to be able to capture an image of the entire room as a predetermined action range of the subject.

The subject detection system S is a film-like pressure sensor (sheet sensor, film) that detects pressure according to heartbeat, respiration (respiration beat), and body movement (motion) as an example of the biological information of the subject. State sensor, biological information measuring member) SN1. The pressure-sensitive sensor SN1 of Example 1 is laid between a mattress support (bed body) 1a of a bed (bed) 1 disposed in a room and a mattress 1b supported by the mattress support 1a. The bed pressure sensor SN1a and the floor surface pressure sensor SN1b laid between the indoor floor surface (entire floor surface, action range) 2 and the carpet 3 are provided.
Here, in Example 1, a high-sensitivity pressure sensor manufactured by EMFIT of Non-Patent Document 1 can be used as the pressure sensor SN1. For this reason, for example, when the subject lies on the bed 1, the subject's whole body presses the mattress 1b, a futon (not shown) or the like, or when the subject moves in the room, the subject's feet are placed on the carpet 3. Heartbeat, respiration, and body movement can be measured from the pressure of pressing. In addition, about the technique regarding the said high sensitivity pressure sensor, since it describes in the patent document 4, the nonpatent literature 1, etc., for example, since it is conventionally well-known, detailed description is abbreviate | omitted.

In addition, the subject detection system S has an utterance request (for example, “Good morning. Then, say“ Ah ”) to urge the subject to utter at a preset voice extraction time (for example, 7:00 am). For 3 seconds ") and a microphone MC for extracting the sound accompanying the utterance of the subject in response to the utterance request (e.g., the sound" a "for 3 seconds). Have.
The speaker SP and the microphone MC constitute an audio extraction member (SP + MC) of Example 1.
In addition, the camera CA, the pressure sensor SN1, and the sound extraction member (SP + MC) of the first embodiment are connected to the subject detection server SV via a connection cable CB.

  The subject detection server SV is a client personal computer PC (receiving terminal, personal computer) that can receive and store information from the subject detection server SV via the Internet Ni as an example of a first information communication line. Computer, monitoring center, subject information management center). The client personal computer PC according to the first embodiment includes a so-called computer device, and includes a computer main body H1, a display H2, input devices such as a keyboard H3 and a mouse H4, an HD drive (hard disk drive) (not shown), and the like. Has been. Further, the subject detection server SV is an example of a mobile body that can receive information from the subject detection server SV via the mobile communication network Np as an example of the second information communication line or the Internet Ni. Mobile phone (receiving terminal, mobile terminal) MP.

(Description of the control part of Example 1)
FIG. 2 is an explanatory diagram showing the function of each device constituting the subject detection system of the first embodiment in a block diagram (functional block diagram).
FIG. 3 is a block diagram continued from FIG.
2 and 3, the subject detection server SV, the computer main body H1 of the client personal computer PC, and the respective control units (controllers) of the mobile phone MP are used for input / output of signals to / from the outside, adjustment of input / output signal levels, etc. I / O (input / output interface), ROM (read-only memory, recording medium) in which programs and data for performing necessary startup processing are stored, and necessary data and programs for temporary storage It has RAM (Random Access Memory, recording medium), CPU (Central Processing Unit) that performs processing according to the startup program stored in ROM, etc., and clock oscillator etc., and is stored in ROM, RAM, etc. Various functions can be realized by executing the program.
The subject detection server SV, the client personal computer PC, and the mobile phone MP configured as described above can realize various functions by executing programs stored in the hard disk, ROM, or the like.

(Signal input element connected to the control unit of the subject detection server SV)
Output signals such as the following signal output elements CA, SN1, (SP + MC) are input to the control unit of the subject detection server SV.
CA: Camera The camera CA inputs the captured indoor image as an output signal to the control unit.
SN1: Pressure sensor The pressure sensor SN1 inputs, as an output signal, a detection signal based on the pressure of the subject pressing the bed pressure sensor SN1a or the floor pressure sensor SN1b as an output signal.
(SP + MC): Voice extraction member The voice extraction member (SP + MC) extracts the voice of the subject corresponding to the utterance request output from the speaker SP with the microphone MC, and inputs the voice as an output signal to the control unit.

(Description of the control unit of the subject detection server SV)
The hard disk drive of the subject detection server SV stores a basic software (operating system) OS that controls basic operations of the subject detection server SV, a subject detection program AP1 as an application program, and other software (not shown). .

(Subject detection program AP1)
The subject detection program AP1 includes the following functional means (program module).
FL0: Absence flag The absence flag FL0 has an initial value of “0”, “0” when the subject is in the room, and “1” when the subject is absent.
FL1: Voice flag The voice flag FL1 has an initial value of “0”, “0” when the voice uttered by the subject is normal, and “1” when the voice uttered by the subject is abnormal.
FL2: biometric flag The biometric flag FL2 is “0” when the initial value is “0”, and the subject's heartbeat / respiration / body movement is normal, and any one of the subject's heartbeat / respiration / body movement is present. It becomes “1” when abnormal.
FL3: Operation flag The operation flag FL3 is “0” when the initial value is “0” and the subject's motion can be confirmed, and “1” when the subject's motion cannot be confirmed.

C1: Image Imaging Unit The image imaging unit C1 as an example of the subject image imaging unit includes an imaging timing determination unit C1A that determines whether or not an imaging timing at which a preset time interval has elapsed has been reached. An indoor image including a subject image (a camera image of the entire room) is captured. The image capturing unit C1 according to the first exemplary embodiment captures the room image at the capturing time for each time interval. In the image capturing means C1, it is possible to set 1/30 [second] as the time interval, for example, in the same manner as in normal video shooting.
C2: Image storage unit The image storage unit C2 stores the indoor image captured by the image capturing unit C1.
C3: Imaging determination unit The imaging determination unit C3 determines whether or not the subject image has been captured. The imaging determination unit C3 according to the first embodiment determines whether or not the subject image has been captured by determining whether or not the subject image is included in the room image stored in the image storage unit C2. Determine.

C4: Absence determination means The absence determination means C4 determines that the subject is absent when the imaging determination means C3 determines that the subject image is not captured, and sets the absence flag FL0 to “1”. To do.
C5: Absence detection information transmission means The absence detection information transmission means C5 is absent from the absence detection information reception means C101 described later when the absence determination means C4 determines that the subject is absent. Absence detection information indicating that is transmitted.

4 is an explanatory diagram of an example of the contour image of the first embodiment, FIG. 4A is an explanatory diagram of a room image including a subject image captured by the camera, and FIG. 4B is a contour image extracted from the room image of FIG. 4A. It is explanatory drawing of.
C6: Contour Extracting Unit The contour extracting unit C6 extracts a contour image that is a contour image of a subject from the subject image, as shown in FIG. The contour extracting unit C6 according to the first embodiment converts the indoor image (see FIG. 4A) as a full-color image into a contour image (see FIG. 4B) as a monochrome image in which the contour of the imaged object is white and other than the contour is black. By converting, the contour image of the subject image is extracted.

C7: Contour Storage Unit The contour storage unit C7 temporarily stores the first contour image and the second contour image that are the respective contour images of the first subject image and the second subject image that are continuously captured at time intervals. It has first contour image storage means C7A and second contour image storage means C7B for storing, and stores the contour image extracted by the contour extraction means C6.
In Example 1, every time a contour image is extracted by the contour extraction means C6, the extracted contour image is stored, and the latest contour image is temporarily stored in the second contour image storage means C7B as the second contour image. The stored contour image immediately before the latest contour image, that is, the original second contour image, is temporarily stored in the first contour image storage means C7A as the first contour image.

C8: Voice extraction means The voice extraction means C8 is an extraction time determination means C8A for determining whether or not a voice extraction time has come, an utterance request output means C8B for outputting an utterance request by the speaker SP, and an audio of the subject by the microphone MC Extraction discriminating means C8C for discriminating whether or not the sound has been extracted, frequency decomposing means C8D for decomposing the sound into preset frequency components (basic frequency, modulation frequency, etc.), and calculating the amplitude of each frequency component And a voice extraction member (SP + MC) for extracting the voice uttered by the subject (see FIG. 6 described later). The technique for decomposing each frequency component from the audio signal is described in, for example, Japanese Unexamined Patent Application Publication No. 2009-003162 and Japanese Unexamined Patent Application Publication No. 2005-241997. To do.
C9: Voice information storage means The voice information storage means C9 stores voice information about the voice extracted by the voice extraction means C8. In the voice information storage unit C9 according to the first embodiment, the voice information, the waveform of the voice frequency component, and the amplitude information are stored as the voice information.

FIG. 5 is an explanatory diagram of a heartbeat / respiration / body motion waveform of the subject of Example 1, FIG. 5A is an explanatory diagram of an example of a heartbeat waveform, FIG. 5B is an explanatory diagram of an example of a respiratory waveform, and FIG. It is explanatory drawing of an example of the waveform of a body movement.
C10: Biological information measuring means The biological information measuring means C10 includes a frequency resolving means C10A for decomposing the detection signal of the pressure-sensitive sensor SN1 into each frequency of heartbeat, respiration, and body movement, and a unit of time of the subject from the heartbeat frequency A heart rate calculating means C10B for calculating a heart rate [bpm: beats per minute, times / minute], a respiration rate calculating means C10C for calculating a respiration rate [bpm] per unit time of the subject from a respiration frequency, and a body Body motion number calculating means C10D for calculating the number of body motion per unit time [bpm] of the subject from the frequency of motion, and measuring heartbeat / respiration / body motion as an example of biological information of the subject (FIG. 5).

In the biological information measuring means C10 of Example 1, the heartbeat frequency is f _h [Hz], the respiration frequency is f _r [Hz], and the body motion frequency is f _m [Hz]. When the heart rate is h [bpm], the respiration rate is r [bpm], and the body motion number is m [bpm], the heart rate h [bpm], the respiration rate r [bpm], and the body The dynamic number m [bpm] is calculated by the following equations (1-1) to (1-3).
h = f _h × 60 Formula (1-1)
r = f _r × 60 Formula (1-2)
m = f _m × 60 Formula (1-3)
C11: Biological Information Storage Unit The biological information storage unit C11 stores biological information about heartbeat / respiration / body movement measured by the biological information measurement unit C10. In the biological information storage unit C11 of Example 1, as the biological information, detection signals, heartbeat / respiration / body motion waveforms, heart rate h [bpm] / respiration rate r [bpm] / body motion m [bpm]. ] Is stored.
C12: Abnormality determination unit The abnormality determination unit C12 includes a voice abnormality determination unit C12A, a biological abnormality determination unit C12B, and a non-operation determination unit C12C, and determines whether an abnormality has occurred in the body of the subject. The abnormality determination unit C12 of the first embodiment includes the voice flag FL1 updated by the voice abnormality determination unit C12A, the biological abnormality determination unit C12B, and the non-operation determination unit C12C, the biological flag FL2, When all the operation flags FL3 are “1”, it is determined that an abnormality has occurred in the subject's body.

6 is an explanatory diagram of an example of the voice of the subject of Example 1, FIG. 6A is an explanatory diagram of an example of the normal voice of the subject, and FIG. 6B is an explanatory diagram of an example of the abnormal voice of the subject.
C12A: Voice abnormality determination means The voice abnormality determination means C12A determines whether the subject's voice extracted by the voice extraction member (SP + MC) is outside a preset normal range for voice. It is determined that an abnormality has occurred.
Here, for example, motor disorder dysarthria caused by Parkinson's disease, ALS (amyotrophic lateral sclerosis), pseudobulbar paralysis (sequelae of stroke, etc.), laryngeal cancer, vocal cord cancer, vocal cord nodules, polyps It is known that so-called speech disorders such as speech language disorders caused by vocal cord lesions such as vocal cords and vocal cord polyps are accompanied by hoarseness. In addition, "screaming" is read as "Seisei" and is used for voices such as voices, hoarse voices, faint voices, junk voices, muddy voices, unnatural voices that are strong, weak voices, etc. This is a state in which the vibration of the vocal cords is disturbed. Therefore, if a sign or a sign that the subject becomes hoarse, that is, an abnormal voice of the subject (see FIG. 6B) is determined, a simple and preliminary diagnosis of the abnormality of the subject's body can be made.

For this reason, the voice abnormality determination means C12A of the first embodiment calculates the amplitude of each frequency component of the subject's voice stored in the voice information storage means C9, and the amplitude such as the fundamental frequency and the modulation frequency is measured in advance. When the subject's voice is out of the normal range for voice from the minimum amplitude to the maximum amplitude set based on the amplitude of each frequency component of the normal voice of the subject (see FIG. 6A) The sound flag FL1 is set to “1”. Therefore, as shown in FIG. 6B, when the waveform of each frequency component of the subject's voice is interrupted, the amplitude is zero, and it is determined that the voice is outside the normal range, so that the subject's voice is abnormal. Can be detected.
C12B: Biological abnormality determination means The biological abnormality determination means C12B has a heartbeat abnormality determination means C12B1, a respiratory abnormality determination means C12B2, and a body movement abnormality determination means C12B3, and the biological information measured by the pressure sensor SN1. When the measured heart rate h [bpm], the respiratory rate r [bpm], and the body motion number m [bpm] are outside the normal range for the living body from the preset minimum value to the maximum value,・ Determine that an abnormality has occurred in breathing or body movement.

C12B1: Heart rate abnormality determination unit The heart rate abnormality determination unit C12B1 is outside the normal range for heart rate from the preset minimum heart rate to the maximum heart rate, with the heart rate h [bpm] stored in the biological information storage unit C11. In this case, it is determined that the heartbeat of the subject is in an abnormal state, and the biological flag FL2 is set to “1”. In Example 1, the minimum heart rate of the normal heart rate range is preset to 40 [bpm], the maximum heart rate is set to 100 [bpm], and the normal heart rate range is 40 to 100 [bpm]. bpm]. That is, when the heart rate h [bpm] is smaller than 40 [bpm], so-called “bradycardia”, or larger than 100 [bpm], so-called “tachycardia”, the heart rate of the subject. Is determined to be in an abnormal state.

C12B2: Respiratory abnormality determining means Respiratory abnormality determining means C12B2 is out of the normal range for respiration from the preset minimum respiratory rate to the maximum respiratory rate for the respiratory rate r [bpm] stored in the biological information storage unit C11. In this case, it is determined that the subject's breathing is in an abnormal state, and the biological flag FL2 is set to “1”. In Example 1, the minimum respiration rate of the normal breathing range is preset to 10 [bpm], the maximum heart rate is set to 25 [bpm], and the normal breathing range is 10 to 25 [bpm]. bpm]. That is, when the respiration rate r [bpm] is less than 10 [bpm], so-called “slow breathing”, or greater than 25 [bpm], so-called “tachypnea”, the subject's breathing Is determined to be in an abnormal state.

C12B3: Body movement abnormality determination means The body movement abnormality determination means C12B3 is for body movement from the minimum body movement number to the maximum body movement number in which the body movement number m [bpm] stored in the biological information storage unit C11 is preset. If it is outside the normal range, it is determined that the body movement of the subject is abnormal, and the biological flag FL2 is set to “1”. In Example 1, for example, the minimum body motion number in the normal range for body motion can be preset to 10 [bpm] as the minimum respiratory rate, and the maximum body motion number can be set to 100 [bpm] as the maximum heart rate. . That is, the normal range for body movement can be set as 10 to 100 [bpm].
C12C: Non-operation determination unit The non-operation determination unit C12C includes a contour image coincidence determination unit C12C1 and a coincidence number counting unit C12C2, and based on the difference between the first subject image and the second subject image, It is determined whether or not is in a non-operational state. The non-operation determination unit C12C according to the first exemplary embodiment is configured such that the first contour image and the second contour image are continuously matched by the contour image match determination unit C12C1 and the match number counting unit C12C2. Is determined to have exceeded a preset non-operation threshold value _Nmax , it is determined that the subject is in an inoperative state.

C12C1: Contour image coincidence determining unit The contour image coincidence determining unit C12C1 includes the first contour image temporarily stored in the first contour image storage unit C7A and the first contour image temporarily stored in the second contour image storage unit C7B. It is determined whether or not the two contour images match.
C12C2: Number-of-matching counting means The number-of-matching counting means C12C2 counts the number n of times that the first contour image and the second contour image are matched by the contour image matching determination means C12C1. That is, the value of the counter n for counting the number of coincidences is counted.
C13: Abnormality detection information transmission means When the abnormality determination means C12 determines that an abnormality has occurred in the subject's body, the abnormality detection information transmission means C13 sends an abnormality detection information reception means C103 described later to the subject. Abnormality detection information indicating that an abnormality has been detected is transmitted.

C14: Subject information transmission means The subject information transmission means C14, with respect to the subject information reception means C105 described later, the indoor image stored in the image storage means C2, and the contour image stored in the contour storage means C7 The voice information stored in the voice information storage means C9 and the biological information stored in the biological information storage means C11 are transmitted as subject information. The subject information transmission means C14 of the first embodiment, when neither the absence nor the abnormality of the subject is detected by the absence determination means C4 and the abnormality determination means C12, the contour image, the voice information, and the biological information Is transmitted as subject information. When the absence determination means C4 detects the absence of the subject, only the indoor image not including the subject image is transmitted as the subject information, and the abnormality determination means C12 detects the abnormality of the subject's body. All the information, that is, the indoor image including the subject image, the contour image, the voice information, and the biological information are transmitted as subject information.

(Description of each control unit of the computer main body H1 of the client personal computer PC and the mobile phone MP)
Also for the hard disk drive of the client personal computer PC and the mobile phone MP, a basic software (operating system) OS for controlling basic operations, a detection result reporting program AP2 as an application program, an image display program AP3, and other software (not shown) Is remembered.

(Detection result report program AP2)
The detection result notification program AP2 has the following functional means (program module).
C101: Absence detection information receiving means The absence detection information receiving means C101 receives the absence detection information transmitted by the absence detection information transmitting means C5.
C102: Absence reporting means The absence reporting means C102 reports that the subject is absent when the absence detection information is received by the absence detection information receiving means C101. The absence notification means C102 of Example 1 notifies that the subject is absent by sounding an absence notification sound every time the absence detection information is received.

C103: Abnormality detection information receiving means The abnormality detection information receiving means C103 receives the abnormality detection information transmitted by the abnormality detection information transmitting means C13.
C104: Abnormality reporting means The abnormality reporting means C104 reports that an abnormality has occurred in the subject's body when the abnormality detection information is received by the abnormality detection information receiving means C103. In the abnormality notification means C104 of the first embodiment, when the abnormality detection information is received even once, abnormality is generated in the body of the subject by continuously sounding the abnormality notification sound until the end signal from the user is input. Report that you did.

C105: Subject information receiving means The subject information receiving means C105 receives the subject information transmitted by the subject information transmitting means C14.
C106: Subject information storage means The subject information storage means C106 stores the subject information received by the subject information receiving means C105.

(Image display program AP3)
The image display program AP3 has the following functional means (program modules).

7 is an explanatory diagram of the subject detection image of Example 1, FIG. 7A is an explanatory diagram of the subject detection image at normal time, FIG. 7B is an explanatory diagram of the subject detection image at the time of absence detection, and FIG. It is explanatory drawing of the test subject detection image of the state in which is selected.
C107: Image Display Unit The image display unit C107 includes a switching determination unit C107A and an image switching unit C107B. The subject detection image 101 shown in FIG. 7 is displayed on a display H2 of the client personal computer PC or a display unit (not shown) of the mobile phone MP. To display. In FIG. 7, the subject detection image 101 according to the first embodiment includes a notification display unit 101a that displays absence detection information or abnormality detection information, an image display unit 101b that displays an indoor image or a contour image, and a heartbeat / biological information. A living body display unit 101c for displaying each waveform of respiration and body motion, heart rate h [bpm], respiration rate h [bpm], body motion number m [bpm], and the like. An audio display unit 101d that displays a waveform and the like, and a switching button (switching check box) 101e for switching the image of the image display unit 101b between the indoor image and the contour image are provided.

  The image display unit C107 according to the first embodiment displays each of the contour image, the biological information, and the audio information received as the subject information by the subject information reception unit C105 when no absence or abnormality is detected. It displays on the part 101b-101d (refer FIG. 7A). Further, when the absence detection information is received by the absence detection information receiving means C101, that is, when absent, the image display means C107 displays the absence detection information on the notification display unit 101a and as the subject information. Only the received indoor image (the indoor image not including the subject image) is displayed on the image display unit 101b (see FIG. 7B). Further, the image display unit C107 displays the abnormality detection information on the notification display unit 101a when the abnormality detection information is received by the abnormality detection information reception unit C103, that is, when there is an abnormality, and as the subject information. The received contour image, the biological information, and the voice information are displayed on the display units 101b to 101d (see FIG. 7C). Note that the image display unit C107 switches the contour image displayed on the image display unit 101b to an indoor image (an indoor image including a subject image) when the switching button 101e is selected at the time of abnormality.

C107A: switching determination means C107A, when receiving the abnormality detection information by the abnormality detection information receiving means C103 (at the time of abnormality), the user (viewing neighbors, home helpers, care volunteers, care workers, etc.) It is determined whether or not the switching button 101e is selected by the input of a viewer, a monitor, a relative, an acquaintance, a doctor, a nurse, or the like.
C107B: Image switching unit The image switching unit C107B switches the contour image displayed on the image display unit 101b to an indoor image when the switching determination unit C107A determines that the switching button 101e is selected.

(Description of Flowchart of Example 1)
Next, the flow of processing of the subject detection server SV, the computer main body H1 of the client personal computer PC, and the programs AP1 to AP3 of the mobile phone MP according to the first embodiment will be described with reference to flowcharts.
(Description of flowchart of main process of subject detection server SV of embodiment 1)
FIG. 8 is a flowchart of the main process of the subject detection server according to the first embodiment.
The process of each ST (step) in the flowchart of FIG. 8 is performed according to a program stored in the ROM or the like of the control unit. This process is executed in a multitasking manner in parallel with other various processes of the control unit.

The flowchart shown in FIG. 8 is started when the subject detection server SV is activated and the subject detection program AP1 is forcibly activated.
In ST1 of FIG. 8, it is determined whether or not the subject is absent by determining whether or not the absence flag FL0 is “1”. If yes (Y), the process proceeds to ST2, and if no (N), the process proceeds to ST4.
In ST2, the absence detection information is transmitted to the client personal computer PC and the mobile phone MP. Then, the process proceeds to ST3.
In ST3, an indoor image (see FIG. 7B) that does not include the subject image is transmitted to the client personal computer PC and the mobile phone MP. Then, the process returns to ST1.
In ST4, it is determined whether or not an abnormality has occurred in the subject's body by determining whether or not the voice flag FL1, the biological flag FL2, and the action flag FL3 are all “1”. If no (N), the process moves to ST5, and if yes (Y), the process moves to ST6.

In ST5, the subject information including voice information, biological information, and contour image is transmitted to the client personal computer PC and the mobile phone MP. Then, the process returns to ST1.
In ST6, the abnormality detection information is transmitted to the client personal computer PC and the mobile phone MP. Then, the process proceeds to ST7.
In ST7, the subject information including voice information, biological information, contour image, and room image is transmitted to the client personal computer PC and the mobile phone MP. Then, the process proceeds to ST8.
In ST8, it is determined whether or not the user has received an end signal indicating that diagnosis / treatment has been completed. If no (N), the process moves to ST6, and if yes (Y), the process returns to ST1.

(Explanation of Flowchart of Absence Detection Processing of Subject Detection Server SV of Example 1)
FIG. 9 is a flowchart of the absence detection process of the subject detection server according to the first embodiment.
The processing of each ST (step) in the flowchart of FIG. 9 is performed according to a program stored in the ROM or the like of the control unit. This process is executed in a multitasking manner in parallel with other various processes of the control unit.

The flowchart shown in FIG. 9 is started when the subject detection server SV is activated and the subject detection program AP1 is forcibly activated.
In ST11 of FIG. 9, the absence flag FL0 is set to “0”. Then, the process proceeds to ST12.
In ST12, it is determined whether or not it is the imaging time for each preset time interval (for example, 1/30 [second]). If yes (Y), the process proceeds to ST13, and, if no (N), ST12 is repeated.
In ST13, an indoor image (see FIG. 4A) is captured and stored by the camera CA (see FIG. 1). Then, the process proceeds to ST14.
In ST14, it is determined whether or not the subject image is captured by determining whether or not the subject image is included in the indoor image. If no (N), the process moves to ST15, and if yes (Y), the process moves to ST16.
In ST15, the absence flag FL0 is set to “1”. Then, the process returns to ST12.
In ST16, a contour image (see FIG. 4B) is extracted from the captured indoor image and stored. Then, the process returns to ST11.

(Explanation of Flowchart of Audio Abnormality Detection Processing of Subject Detection Server SV of Example 1)
FIG. 10 is a flowchart of the audio abnormality detection process of the subject detection server according to the first embodiment.
The processing of each ST (step) in the flowchart of FIG. 10 is performed according to a program stored in the ROM or the like of the control unit. This process is executed in a multitasking manner in parallel with other various processes of the control unit.

The flowchart shown in FIG. 10 is started when the subject detection server SV is activated and the subject detection program AP1 is forcibly activated.
In ST21 of FIG. 10, the voice flag FL1 is set to “0”. Then, the process proceeds to ST22.
In ST22, it is determined whether or not a preset voice extraction time (for example, 7 am) has come. If yes (Y), the process transfers to ST23, and, if no (N), ST22 is repeated.
In ST23, an utterance request is output from speaker SP (see FIG. 1). Then, the process proceeds to ST24.
In ST24, it is determined whether or not the subject's voice is extracted from the microphone MC (see FIG. 1). If yes (Y), the process proceeds to ST25, and, if no (N), the process proceeds to ST29.

In ST25, the extracted voice is stored as voice information. Then, the process proceeds to ST26.
In ST26, the extracted voice is decomposed into preset frequency components (see FIG. 6). Then, the process proceeds to ST27.
In ST27, the amplitude of each decomposed frequency component is calculated. Then, the process proceeds to ST28.
In ST28, it is determined whether or not the calculated amplitude of each frequency component is outside the normal range for speech from the preset minimum amplitude to the maximum amplitude. That is, it is determined whether or not an abnormality has occurred in the subject's voice. If yes (Y), the process proceeds to ST29, and, if no (N), the process returns to ST21.
In ST29, the voice flag FL1 is set to “1”. Then, the process returns to ST22.

(Explanation of Flowchart of Biological Abnormality Detection Processing of Subject Detection Server SV of Example 1)
FIG. 11 is a flowchart of the biological abnormality detection process of the subject detection server according to the first embodiment.
The processing of each ST (step) in the flowchart of FIG. 11 is performed according to a program stored in the ROM or the like of the control unit. This process is executed in a multitasking manner in parallel with other various processes of the control unit.

The flowchart shown in FIG. 11 is started when the subject detection server SV is activated and the subject detection program AP1 is forcibly activated.
In ST31 of FIG. 11, the biological flag FL1 is set to “0”. Then, the process proceeds to ST32.
In ST32, the detection signal from the pressure sensor SN1 is stored. Then, the process proceeds to ST33.

In ST33, the waveform of the detection signal is frequency-resolved into each waveform of heartbeat / respiration / body motion and stored (see FIG. 5). Then, the process proceeds to ST34.
In ST34, from the frequencies f _h , f _r , and f _m of the heartbeat / respiration / body movement waveforms, the heart rate h [bpm] / respiration rate per unit time according to the equations (1-1) to (1-3). r [bpm] · body motion number m [bpm] is calculated and stored. Then, the process proceeds to ST35.
In ST35, it is determined whether or not the calculated heart rate h [bpm] is outside the normal heart rate range from the minimum heart rate (40 [bpm]) to the maximum heart rate (100 [bpm]). That is, it is determined whether or not an abnormality has occurred in the heartbeat of the subject. If no (N), the process moves to ST36, and if yes (Y), the process moves to ST38.

In ST36, it is determined whether or not the calculated respiration rate r [bpm] is outside the normal breathing range from the minimum respiration rate (10 [bpm]) to the maximum respiration rate (25 [bpm]). That is, it is determined whether an abnormality has occurred in the subject's breathing. If no (N), the process proceeds to ST37, and if yes (Y), the process proceeds to ST38.
In ST37, is the calculated body motion number m [bpm] outside the normal body motion range from the minimum body motion number (for example, 10 [bpm]) to the maximum body motion number (for example, 100 [bpm])? Determine whether or not. That is, it is determined whether an abnormality has occurred in the body movement of the subject. If yes (Y), the process proceeds to ST38, and, if no (N), the process returns to ST31.
In ST38, the biological flag FL1 is set to “1”. Then, the process returns to ST32.

(Explanation of Flowchart of Non-operation Detection Process of Subject Detection Server SV of Example 1)
FIG. 12 is a flowchart of the non-operation detection process of the subject detection server according to the first embodiment.
The processing of each ST (step) in the flowchart of FIG. 12 is performed according to a program stored in the ROM or the like of the control unit. This process is executed in a multitasking manner in parallel with other various processes of the control unit.

The flowchart shown in FIG. 12 is started when the subject detection server SV is activated and the subject detection program AP1 is forcibly activated.
In ST41 of FIG. 12, the following processes (1) and (2) are executed, and the process proceeds to ST42.
(1) The operation flag FL3 is set to “0”.
(2) 0 is set to the counter n for counting the number of coincidences (n = 0).

In ST42, the first contour image and the second contour image are temporarily stored. That is, the second contour image is temporarily stored as the latest contour image, and the first contour image is temporarily stored as the contour image immediately before the latest contour image (original second contour image). Then, the process proceeds to ST43.
In ST43, it is determined whether or not the temporarily stored first contour image matches the second contour image. If yes (Y), the process transfers to ST44, and, if no (N), the process returns to ST41.
In ST44, +1 is added to the counter n (n = n + 1). Then, the process proceeds to ST45.
In ST45, it is determined whether or not the value of the counter n has exceeded a preset non-operation threshold N _max (n> N _max ). That is, it is determined whether or not the subject is in an inoperative state. If yes (Y), the process proceeds to ST46, and, if no (N), the process returns to ST42.
In ST46, the operation flag FL3 is set to “1”. Then, the process returns to ST42.

(Explanation of Flowchart of Detection Result Reporting Process of Client PC PC and Mobile Phone MP in Embodiment 1)
FIG. 13 is a flowchart of detection result reporting processing of the client personal computer and the mobile phone according to the first embodiment.
The processing of each ST (step) in the flowchart of FIG. 13 is performed according to a program stored in the ROM or the like of each control unit. Further, this process is executed in a multitasking manner in parallel with the other various processes of each control unit.

The flowchart shown in FIG. 13 is started when the client personal computer PC and the mobile phone are activated and the detection result notification program AP2 is forcibly activated.
In ST101 of FIG. 13, the subject information from the subject detection server SV is received and stored. Then, the process proceeds to ST102.
In ST102, it is determined whether or not absence detection information is received from the subject detection server SV. If yes (Y), the process proceeds to ST103, and, if no (N), the process proceeds to ST104.
In ST103, the absence notification sound is played to notify the user that the subject is absent. Then, the process returns to ST101.
In ST104, it is determined whether or not the abnormality detection information from the subject detection server SV has been received. If yes (Y), the process transfers to ST105, and, if no (N), the process returns to ST101.
In ST105, an abnormality notification sound is sounded to notify the user that an abnormality has occurred in the subject's body. Then, the process proceeds to ST106.
In ST106, it is determined whether or not the user has received an end signal indicating that diagnosis / treatment has been ended. If no (N), the process returns to ST105, and if yes (Y), the process returns to ST101.

(Explanation of Flowchart of Image Display Processing of Client Personal Computer PC and Mobile Phone MP in Embodiment 1)
FIG. 14 is a flowchart of image display processing of the client personal computer and the mobile phone according to the first embodiment.
Processing of each ST (step) in the flowchart of FIG. 14 is performed according to a program stored in the ROM or the like of each control unit. Further, this process is executed in a multitasking manner in parallel with the other various processes of each control unit.

The flowchart shown in FIG. 14 is started when the image display program AP3 is activated by user input after the client personal computer PC and the mobile phone are activated.
In ST201 of FIG. 14, the subject detection image 101 (see FIG. 7) is displayed. Then, the process proceeds to ST202.
In ST202, it is determined whether or not absence detection information is received from the subject detection server SV. If yes (Y), the process proceeds to ST203, and, if no (N), the process proceeds to ST204.
In ST203, the following processes (1) and (2) are executed, and the process moves to ST209.
(1) The absence detection information is displayed on the notification display unit 101a (see FIG. 7B).
(2) An indoor image not including the subject image is displayed on the image display unit 101b (see FIG. 7B).

In ST204, it is determined whether or not the abnormality detection information from the subject detection server SV has been received. If yes (Y), the process proceeds to ST205, and, if no (N), the process proceeds to ST208.
In ST205, the abnormality detection information is displayed on the notification display unit 101a (see FIG. 7C). Then, the process proceeds to ST206.
In ST206, it is determined whether or not the switching button 101 is selected (see FIG. 7C). If yes (Y), the process proceeds to ST207, and, if no (N), the process proceeds to ST208.
In ST207, room images, biological information, and audio information including the subject image are displayed on the respective display units 101b to 101d (see FIG. 7C). Then, the process proceeds to ST209.
In ST208, contour images, biological information, and audio information are displayed on the respective display units 101b to 101d (see FIG. 7A). Then, the process proceeds to ST209.
In ST209, it is determined whether or not an end signal indicating that the confirmation by the image from the user is to be ended is received. If yes (Y), the process proceeds to ST210, and, if no (N), the process returns to ST202.
In ST210, the subject detection image 101 is hidden. Then, the image display process ends.

(Operation of Example 1)
In the subject detection system S according to the first embodiment having the above-described configuration, the voice extraction member (SP + MC) is not extracted or extracted in the voice abnormality detection process (see ST21 to ST29 in FIG. 10). When the amplitude of each frequency component of the voice is outside the normal range, an abnormality in the voice of the subject is detected. Further, in the biological abnormality detection processing (see ST31 to ST38 in FIG. 11), the subject's heart rate h [bpm], respiration rate r [bpm], and body motion number m [bpm] based on the detection signal of the pressure sensor SN1. If any of these is out of the normal range, an abnormality in the biological information of the subject is detected. Further, in the non-operation detection process (see ST41 to ST46 in FIG. 12), the contour image (see FIG. 4B) of the indoor image (see FIG. 4A) including the subject image captured by the camera CA does not change for a certain period. In addition, the malfunction of the subject is detected.

Then, when an abnormality in the subject's voice is detected, an abnormality in the biological information of the subject is detected, and a malfunction of the subject is detected, it is detected that an abnormality has occurred in the subject's body (see FIG. 8), the abnormality of the subject's body is reported to each user of the client personal computer PC and the mobile phone MP (see ST6 in FIG. 8, ST104 to ST106 in FIG. 13, and ST204 to ST209 in FIG. 14).
That is, in the subject detection system S of the first embodiment, when a subject's abnormality is detected by three types of sensors (SP + MC), SN1, and CA, a so-called triple check is performed to detect the subject's abnormal state. . For this reason, the subject detection system S according to the first embodiment can reduce the erroneous detection and the inability to detect the abnormal state and can detect the abnormal state with high accuracy compared to the case where the abnormal state is detected by one type of sensor. .

  In particular, in the non-operation detection process of the first embodiment, the abnormality of the subject is detected based on the measured values of the detection signals of the sensors (SP + MC) and SN1, since the abnormality of the subject is detected by the fact that there is no change in the image of the camera CA. Compared with the voice abnormality detection process, the biological abnormality detection process, and the like that detect noise, it is possible to reduce the occurrence of errors such as noise, and to reduce false detections and inability to detect. Therefore, the subject detection system S according to the first embodiment can detect an abnormal state with higher accuracy than when the non-operation detection process is not performed. In addition, since the function of detecting the malfunction of the subject from the change in the image of the camera CA is the same function as watching by a caregiver or the like, the burden of watching by the caregiver or the like can be reduced. .

In the subject detection system S of the first embodiment, the subject detection server SV transmits the contour image and the room image to the client personal computer PC and the mobile phone MP in real time (see ST4, ST5, and ST7 in FIG. 8). Then, in the client personal computer PC and the mobile phone MP, the received image is displayed on the image display unit 101b of the subject detection image 101 by executing the image display process (ST201 to ST210 in FIG. 14) according to the user's input. (See FIGS. 7A, 7C, ST101 in FIG. 13, and ST204 to ST208 in FIG. 14).
Therefore, in the subject detection system S according to the first embodiment, the state of the subject before and after the occurrence of an abnormality can be actually visually recognized from the images.

The received subject information including each image is stored in the subject detection server SV, the client personal computer PC, and the mobile phone MP. Therefore, in the subject detection system S of the first embodiment, the subject information stored after the occurrence of abnormality can be reconfirmed (ST12 and ST16 in FIG. 9, ST24 to ST27 in FIG. 10, ST32 to ST34 in FIG. 11). , See ST101 in FIG. 13).
In the subject detection system S according to the first embodiment, the stored subject information (each image / biological information / speech information) is used to reset the normal range for the subject's living body and the normal range for speech, or remotely by a doctor or the like. Used for preventive diagnosis of subjects from the ground, preparation of medical records (medical information, medical information, medical records) for subjects, certification of care levels for subjects by national and local governments, creation of statistical data for multiple subjects, etc. it can.

  Further, in the subject detection system S of the first embodiment, the entire area of the room as the subject's action range is captured as an indoor image by the camera CA, and the bed pressure sensor SN1a and the floor are included in the subject's action range. Surface pressure sensor SN1b is laid down. For this reason, the subject detection system S according to the first embodiment can always detect an abnormal state in the subject's action range even when the contact sensor is not always worn. As a result, the abnormal state can be detected in a wide range by the camera CA as the non-contact type sensor, and the troublesomeness of the subject wearing the contact type sensor can be eliminated.

Further, in the subject detection system S of the first embodiment, the indoor image as a full-color image captured by the camera CA is converted into a contour image as a monochrome image in which the contour of the captured object is white and other than the contour is black. (See ST12, ST13, and ST16 in FIGS. 4 and 9) When the contour image does not change for a certain period of time, the malfunction of the subject is detected (see ST41 to ST46 in FIG. 12).
Here, when detecting the malfunction of the subject by the change of the indoor image of the full-color image, for example, the change of the indoor brightness accompanying the change of sunlight inserted from the window is detected as the change of the indoor image, and the subject May not be detected (see FIG. 4A).
However, in Example 1, a subject's non-operation is detected only by the difference of the white outline in the said outline image (refer FIG. 4B). For this reason, the subject detection system S according to the first embodiment reduces false detection and inability to detect based on an error in an image other than the contour, as compared to a case where a subject's malfunction is detected by a change in a color image such as the indoor image. It is possible to detect the malfunction of the subject with high accuracy.
Further, in the subject detection system S of the first embodiment, the subject detection server SV automatically detects the subject's inactivity without displaying the indoor image or the contour image. Compared with the case of detecting by visual recognition, the invasion of the privacy of the subject can be reduced.

In the subject detection system S according to the first embodiment, the contour image is transmitted by the subject detection server SV in a normal state (see ST5 in FIG. 8), and an indoor image including the subject image together with the contour image is displayed only in an abnormal state. It is transmitted (see ST7 in FIG. 8). In the client personal computer PC and the mobile phone MP of the first embodiment, when the image display process is executed, the received contour image is displayed in a normal state (see FIG. 7A), and the indoor image is displayed only in an abnormal state. Switching display is possible (see FIG. 7C).
That is, in the subject detection system S according to the first embodiment, the opportunity for the video of the camera CA that captured the subject to be transmitted and displayed as it is via the networks Ni and Np is limited to only when an abnormality occurs. Therefore, the subject detection system S according to the first embodiment can reduce the invasion of the subject's privacy as compared to the case where the video of the camera that captured the subject is always transmitted as it is.

  Further, in the subject detection system S of Example 1, the contour image displayed on the image display unit 101b includes a subject image only when the switching button 101e of the subject detection image 101 is selected at the time of abnormality. Switch to image. For this reason, the subject detection system S according to the first embodiment can further limit the opportunity to display the image of the camera CA that has captured the subject as it is when the switching button 101e is selected, and automatically switches from the contour image to the room image when there is an abnormality. Compared to the case, the invasion of the privacy of the subject can be further reduced.

Further, in the subject detection system S of the first embodiment having the above-described configuration, in the absence detection process (see ST11 to ST16 in FIG. 9), the subject is absent when the subject image is not included in the indoor image. (See ST1 in FIG. 8, ST14 and ST15 in FIG. 9), and the absence of the subject is reported to each user of the client personal computer PC and the mobile phone MP (ST2 in FIG. 8, ST102 in FIG. 13, (See ST103, ST202 and ST203 in FIG. 14).
Therefore, in the subject detection system S of the first embodiment, the absence of the subject can be automatically detected based on the image of the camera CA. In addition, the function of automatically detecting the absence of the subject from the change in the image of the camera CA is the same function as the watch by the caregiver or the like, as the function of automatically detecting the non-operation of the subject. It is possible to reduce the burden of watching by visual recognition.

  In the subject detection system S according to the first embodiment having the above-described configuration, the mobile phone MP receives information (subject information) transmitted from the subject detection server SV via the Internet Ni or the mobile communication network Np. , Absence detection information, abnormality detection information). That is, in the mobile phone MP of the first embodiment, the information communication line for receiving the information is duplicated. Therefore, in the subject detection system S according to the first embodiment, the reliability of notifying the user of the cellular phone MP of the abnormality of the subject or the absence of the subject is compared with the case where the information communication line is not duplexed. (Transmission reliability) can be improved.

(Example of change)
As mentioned above, although the Example of this invention was explained in full detail, this invention is not limited to the said Example, A various change is performed within the range of the summary of this invention described in the claim. It is possible. Modification examples (H01) to (H024) of the present invention are exemplified below.
(H01) In the above embodiment, the camera CA (see FIG. 1) is a normal video camera (surveillance camera) such as a CCD (Charge Coupled Device) camera or a CMOS (Complementary Metal Oxide Semiconductor) camera. For example, a special camera such as an infrared camera (a night vision device) or a thermography (a thermography device or a thermal imaging device) can be used. When an infrared camera is used, for example, it is possible to image the subject's body through a thin cloth, etc., or even when the room is dark. It is possible to improve the accuracy. When thermography is used, for example, the body temperature of the subject can be measured simultaneously with the detection of the subject's inactivity. The camera CA is not limited to a so-called unidirectional fixed surveillance camera or the like, and can freely operate pan (horizontal swing), tilt (vertical swing) and zoom, for example. It is also possible to use an omnidirectional surveillance camera such as a so-called pan tilt zoom camera (PTZ camera). When a pan / tilt / zoom camera is used, for example, a subject image in a room image can be recognized and a subject in the room can be tracked and imaged. Further, the camera CA is not limited to a case where it is fixedly supported on a ceiling or the like in the room, and can be supported so as to be slidable by a slider or the like disposed on the ceiling, for example. In this case, for example, the subject in the indoor image, the image can be recognized, and the indoor subject can be tracked (tracked) and imaged, and the same effect as when using a pan / tilt / zoom camera can be expected.

(H02) In the above embodiment, one camera CA is arranged and the entire room within the preset action range of the subject is imaged (see FIG. 1), but the present invention is not limited to this. It is also possible to arrange two or more. For example, in the case where a plurality of rooms such as a toilet, a bathroom, a living room, a kitchen, a veranda, and a corridor are within the subject's range of action in addition to the bedroom in which the bed 1 is disposed, a camera CA is provided for each room. It is also possible to detect the malfunction of the subject in the room where the table is placed and the subject image is captured. In addition, for example, two or more cameras CA are arranged in one room to detect the inactivity of the subject from different angles, or the whole room is viewed in stereo, and the subject 3 is detected simultaneously with the detection of the inactivity of the subject. It is also possible to identify the dimension position. A technique for identifying a user's three-dimensional position by viewing the room in stereo with a plurality of cameras is described in, for example, Non-Patent Document 2 and is well known.

(H03) A contour image (see FIG. 4B) of the indoor image (see FIG. 4A) including the subject image captured by the camera CA, as in the non-operation detection process (see ST41 to ST46 in FIG. 12) of the first embodiment. It is preferable that the subject's inactivity is detected when the reference) does not change for a certain period of time, but the present invention is not limited to this, and it is also possible to detect the subject's inactivity based on the difference between the indoor images themselves. For example, when the subject image in the room image does not change for a certain period, it is possible to detect the malfunction of the subject.
(H04) In the embodiment, when the value of the counter n for counting the number of matches exceeds a preset non-operation threshold N _max in the non-operation detection process, it is determined that the subject is in an inactive state. However, the present invention is not limited to this. For example, the time interval for capturing an indoor image is set to a relatively long time of 10 [seconds], and the first contour image and the second image are set even once. When the contour image matches, it is possible to omit the count processing of the number of matches by the counter n by determining that the subject is in an inoperative state.

(H05) In the embodiment, in the non-operation detection process, when the first contour image and the second contour image completely coincide with each other for a certain period, it is determined that the subject is non-operation (FIG. 12). However, the present invention is not limited to this. For example, when the first contour image and the second contour image match 98% or more for a certain period, it is possible to determine that the subject is inoperative. is there. That is, the present invention is not limited to the case where there is no difference between the first contour image and the second contour image, and the subject can be regarded as inoperative even when there is a slight difference. On the other hand, for example, when the first contour image and the second contour image coincide with each other for a certain period of 2 [%] or less, it is possible to determine that an abnormality has occurred in the body of the subject. That is, when the difference between the first contour image and the second contour image is large, it is determined that there is a possibility that the subject is painful and violent or that the subject is attacked by a robber. It is also possible to determine that it has occurred.

(H06) As in the above embodiment, the subject detection server SV transmits the indoor image including the subject image together with the contour image only when there is an abnormality (see ST7 in FIG. 8), and the indoor image is transmitted as much as possible. However, the present invention is not limited to this. For example, the room image is transmitted together with the contour image even in a normal state, and the control is performed by the client personal computer PC or the mobile phone MP. Only the outline image and the indoor image can be switched and displayed. Also, for example, the contour image and the room image can be transmitted even in a normal state, and the contour image and the room image can be switched and displayed even in a normal state by control of the client personal computer PC or the mobile phone MP. Is possible.
(H07) As in the above-described embodiment, the outline image displayed on the image display unit 101b is displayed only when the switching button 101e is selected at the time of abnormality by the input of the user of the client personal computer PC or the mobile phone MP. Although it is preferable to switch to the indoor image (see ST204 to ST208 in FIGS. 7A, 7C, and 14), the present invention is not limited to this. A configuration that automatically switches to an image is also possible.

(H08) In the above-described embodiment, the bed pressure sensor SN1a and the floor pressure sensor SN1b are spread over the bed 1 and the floor 2 in the whole room that are within the preset action range of the subject (see FIG. 1), the place where the pressure-sensitive sensor SN1 is arranged is not limited to this. For example, the pressure-sensitive sensor SN1 can be arranged on a wheelchair seat. Further, for example, in the case where a plurality of rooms such as a toilet, a bathroom, a living room, a kitchen, a veranda, and a corridor other than the bedroom in which the bed 1 is arranged as in the first embodiment are within the action range of the subject. It is also possible to detect the heartbeat / respiration / body movement within the action range of the subject by arranging the pressure-sensitive sensor SN1 in the entire room of each room. The pressure sensor SN1 has been confirmed by experiments and the like to have a heat resistance of about 60 [° C.], and can detect the heartbeat / respiration / body movement of the subject even in a bathroom. is there.

(H09) In the above embodiment, only the heartbeat / respiration / body movement of the subject was measured by the bed pressure sensor SN1a and the floor pressure sensor SN1b (see FIGS. 1 and 5). For example, when the bed pressure sensor SN1a outputs a detection signal of the subject, it is determined that the subject is lying on the bed 1, or the floor pressure sensor SN1b detects the subject. It is also possible to determine that the subject is moving on the floor 2 when outputting a signal. That is, when a plurality of pressure sensors SN1 are arranged in one room, it is possible to determine the position and behavior of the subject by determining which pressure sensor SN1 outputs the detection signal of the subject. it can. Further, for example, when a plurality of pressure sensors SN1 are arranged for each of a plurality of rooms such as a bedroom, a toilet, a bathroom, a living room, and a kitchen, in which room the pressure sensor SN1 outputs a detection signal of the subject. It is possible to determine in which room the subject is located. That is, when a plurality of pressure-sensitive sensors SN1 are arranged in blocks (divided), it is determined which block (section) the subject is in, and what the subject is doing in the block is inferred. It is possible to

(H010) In the above embodiment, any one of the heart rate h [bpm], the respiratory rate r [bpm], and the body motion number m [bpm] per unit time of the subject measured from the detection signal of the pressure sensor SN1 is selected. Although the abnormality of the biological information of the subject was detected when it was out of each normal range, the present invention is not limited to this. For example, the heart rate h [bpm], the respiratory rate r [bpm], and the body motion number m [ It is also possible to detect an abnormality in the biological information of the subject when any two or more of [bpm] are out of the normal range, or when all three are out of the normal range. Further, for example, only the heart rate h [bpm] is measured from the detection signal of the pressure sensor SN1, and an abnormality in the biological information of the subject is detected when it is outside the normal range for heart rate (40 to 100 [bpm]). It is also possible.

(H011) In the above embodiment, the heart rate h [bpm], the respiration rate r [bpm], and the body motion number m [bpm] per unit time of the subject were measured by the pressure sensor SN1, but the heart rate, respiration, etc. The biological information detection member for detecting the biological information is not limited to this, and for example, a contact type sensor similar to Patent Documents 1 to 3 can be used as the biological information detection member. In this case, for example, a contact-type sensor is constituted by a thermometer or a sphygmomanometer, and it is determined whether or not the body temperature [° C.] or blood pressure [mmHg] of the subject measured by the thermometer or sphygmomanometer is outside the normal range. It is also possible to do. Further, for example, it is possible to arrange a load sensor on the bed 1 and determine whether or not the weight [kg] of the subject measured by the load sensor is out of the normal range as the biological information. Biological information other than heart rate h [bpm], respiration rate r [bpm], and body motion number m [bpm] by using a pressure-sensitive sensor in combination with other sensors (contact type sensor, load sensor, etc.) It is also possible to determine whether or not (body temperature [° C.], blood pressure [mmHg], body weight [kg], etc.) is also outside the normal range.

(H012) In the above embodiment, in order to easily detect the abnormality of the subject's voice, it is determined whether or not the amplitude of each frequency component of the subject's voice is outside the normal range. However, for example, by voiceprint analysis, the voice generated by the subject and the normal voice of the subject measured in advance are strictly collated, and the subject's voice abnormalities (such as hoarseness) are accurately detected. It is possible to detect well. The technique for voiceprint analysis is described in, for example, Japanese Patent Application Laid-Open No. 2008-252849 and Japanese Patent Application Laid-Open No. 2003-219038, and is well known.
(H013) Normal range for voice of the above embodiment, normal range for heartbeat (40-100 [bpm]), normal range for breathing (10-25 [bpm]), normal range for body movement (normal range for living body) Each set value such as 10 to 100 [bpm]) can be changed to any value according to the voice of the subject and the heartbeat, respiration, and body movement as biological information. Further, the non-operation threshold value N _max can be arbitrarily set according to the time interval at which the camera CA captures an indoor image.

(H014) As in the above embodiment, in order to accurately detect the abnormality of the subject's body, the abnormality of the subject's body is detected from the three types of detection results of the subject's voice abnormality, biological information abnormality, and malfunction. It is preferable to execute a triple check to be detected, but the present invention is not limited to this. For example, two types of detection, that is, abnormality and non-operation of the subject's voice, or two types of detection, that is, abnormality and non-operation of the biological information of the subject It is also possible to execute a so-called double check that detects an abnormality of the subject's body from the result. In addition, for example, it is possible to execute only the non-operation detection process capable of accurately detecting the abnormality of the subject's body and detect the abnormality of the subject's body only from the detection result of the non-operation of the subject.

(H015) In the above-described embodiment, the abnormality detection information and the absence detection information are transmitted from the subject detection server SV to the client personal computer PC and the mobile phone MP via the networks Ni and Np, and a notification sound is generated (see FIG. 13 (see ST103 and ST105 in FIG. 13), the information is displayed on the notification display unit 101a of the subject detection image 101 (see ST203 and ST205 in FIG. 14) and notified to each user of the client personal computer PC and the mobile phone MP. The method of reporting the results is not limited to this. For example, when an abnormality of a subject is detected, a security company is notified via a security sensor, a security bell is sounded, a fire alarm (fire alarm) , Automatic fire alarms, fire alarms for homes, etc.), fire alarm bells, police and hospitals It is also possible to or automatic report, and outputs an alarm sound or alarm message from the other speaker disposed in the room of the speaker SP and outdoors.
(H016) In the above-described embodiment, the mobile phone MP (see FIG. 1) is used as an example of a mobile body that the user can carry and move. However, the mobile body is not limited to the mobile phone MP. It is also possible to use other portable computers such as personal computers and PDAs (Personal Digital Assistants).

(H017) In the above embodiment, the Internet Ni and the mobile communication network (mobile phone network via a base station) Np are used as the information communication line (see FIG. 1). By other wired / wireless communication technologies such as wired LAN (Local Area Network), wireless LAN, Bluetooth (registered trademark), ad hoc network (autonomous distributed wireless network, autonomous distributed wireless network, autonomous distributed wireless network) It is also possible to configure. Here, an ad hoc network is a network that is autonomously formed between mobile objects without using an existing communication infrastructure such as a router in the Internet or a base station in a mobile phone. Network that is distributed and temporarily formed, and is used for services such as rescue activities in the event of an emergency disaster, inter-vehicle communication that is communication between vehicles, and a network (sensor network) between sensors of home appliances Is expected. Therefore, when an ad hoc network is used in the present invention, for example, all mobiles connected to the subject detection server SV via the ad hoc network (for example, cellular phones MP of people who have passed nearby) It is also possible to send detection information all at once and ask the user of each mobile unit for help.

(H018) In the mobile phone MP of the above embodiment, the information communication line is duplexed by the Internet Ni and the mobile communication network Np in order to improve the transmission reliability (see FIG. 1), but this is not limitative. For example, information communication by the Internet Ni can be omitted. In addition, for example, by using the Internet Ni, the mobile communication network Np, and other information communication lines (for example, Bluetooth, ad hoc network, etc.), the information communication line can be tripled or more to further improve the transmission reliability. is there.
(H019) In the embodiment, the speaker SP is used only for outputting a utterance request (see ST23 in FIG. 10), but the method of using the speaker SP is not limited to this. It is also possible to use it for a so-called “notification function” that periodically outputs a request for eating and drinking, a request for taking medicine, a sleep request for taking nap and sleep, and the like.

(H020) In the embodiment, in the absence detection process (see ST11 to ST16 in FIG. 9), when the subject image is not included in the indoor image captured by the camera CA, the subject may be absent. Although detected (see ST1 in FIG. 8, ST14 and ST15 in FIG. 9), the absence detection method of the subject is not limited to this. For example, biological information (heartbeat / respiration / body movement) is detected by the pressure sensor SN1. It is also possible to detect the absence of the subject when the subject is not measured or when the subject's voice is not extracted by the voice extraction member (SP + MC). In addition, for example, a double check or a triple check by each sensor CA, SN1, (SP + MC) can be executed in the same manner as the process of detecting the abnormality of the subject.

(H021) In the above embodiment, when the absence of the subject is detected (see ST1 in FIG. 8, ST14 and ST15 in FIG. 9), the absence of the subject is reported to each user of the client personal computer PC and the mobile phone MP. 8 (see ST2 in FIG. 8, ST102 and ST103 in FIG. 13, ST202 and ST203 in FIG. 14), however, the method of detecting the absence of the subject is not limited to the absence notification. For example, when the absence of the subject is detected It is also possible to forcibly cut off the power supply of home appliances such as air conditioners, televisions, lighting, etc. via the subject detection server SV, or to allow remote subjects to remotely control home appliances with a mobile phone It is. That is, detection of the absence of the subject can be used to prevent forgetting to turn off the home appliance, and it can contribute to labor saving of power use of the home appliance, that is, so-called energy saving. Further, for example, when the absence of a subject is detected, a visitor (visitor who locks an electronic lock (electronic lock, digital lock) or presses a call button on an interphone or door phone) via the subject detection server SV It is also possible to enable conversation between a person who is out of the office, a courier, a sales person, a suspicious person, etc.) and a subject on the go using a mobile phone or a videophone call. That is, the absence detection of the subject can be used for crime prevention measures when going out. In addition, about the technique which turns off the power supply of a household appliance in absence, it describes in Unexamined-Japanese-Patent No. 2003-106624, Unexamined-Japanese-Patent No. 2009-117129, etc., for example, about the technique which locks an electronic lock in absence. Is described in, for example, Japanese Patent Application Laid-Open No. 2002-266536, and the technology for making a call between an interphone and a mobile phone when absent is disclosed in, for example, Japanese Patent Application Laid-Open No. 2002-374359 and Japanese Patent Application Laid-Open No. 2002-300305. And is publicly known.

(H022) In the above-described embodiment, the client personal computer PC and the mobile phone MP are used for confirmation by visual recognition using subject information storage (accumulation of subject information history), abnormality notification, absence notification, subject detection image, It is also possible to connect the subject detection server SV and an interphone (door phone) so that when a call button of the interphone is pressed by a visitor, a call or videophone can be made by each receiving terminal PC, MP and the interphone. It is. In this case, users of each receiving terminal PC, MP (viewers such as neighbors, home helpers, care volunteers, care workers, etc., monitors, relatives, etc.) act as suspicious persons, sales, etc. on behalf of the subjects. It is also possible to respond to visitors, and it can be used to prevent crimes such as being invaded by a thief who has been determined to be away, or a subject such as an elderly person being unfairly priced and selling a high-priced product.

(H023) In the above embodiment, the abnormality of the subject is detected or the absence of the subject is detected by the output signal from each sensor CA, SN1, (SP + MC). For example, each sensor CA, SN1, ( It is also possible to detect a person or a pet other than the subject in the room by an output signal from (SP + MC). In this case, for example, the room temperature of the air conditioner can be automatically set according to the number of people in the room and the number of pets. In addition, for example, when a person other than the subject is detected when the subject is absent, it is determined that the person is a suspicious person or illegal intruder, and a security company is notified via a security sensor or a security bell is sounded. It is also possible to automatically report to the police or hospital.

(H024) In the above embodiment, the abnormality detection or absence detection by each sensor CA, SN1, (SP + MC) is performed for one subject in the room, but the number of subjects is not limited to one. It is also possible to perform abnormality detection and absence detection by each sensor CA, SN1, (SP + MC) for a plurality of subjects (for example, four inpatients in a four-person room of a hospital). In this case, for each sensor CA, SN1, (SP + MC), each sensor CA, SN1, (SP + MC) is arranged one by one in a large room without arranging the number according to the number of subjects. It is also possible to detect abnormality detection / absence detection of each subject separately. That is, the subject image / contour image of each subject is identified separately from the indoor image of the camera CA, the biological information of each subject is measured from the detection signal of the pressure sensor, or the voice extracted by the voice extraction member It is also possible to detect the abnormality detection / absence detection of each subject separately by separating and extracting the voice information of each subject from.

  The subject detection system S of the present invention, for example, can easily carry out safety confirmation, home nursing, remote diagnosis, medical chart creation, care level authorization, statistical data creation, etc. of subjects living alone such as elderly people living in housing complexes such as housing estates. When an abnormality of the subject's body is detected, a report is sent to a local government, a regional general support center, or a management center (client PC PC) such as a general hospital, and a doctor or nurse (receiving terminal PC or MP user) For relatives (separate relatives), neighbors, caregivers, meter readers of electric / gas meters, newspaper delivery staff, etc. (receiving terminal PC and MP users) who can carry out quick lifesaving procedures or run faster than ambulances This is useful when you want to report and take emergency measures. Also, for example, by providing with the neighboring university of the apartment house, providing a vacant room as a student dormitory at a low rent, and watching the student as a factor or nursing volunteer (reception terminal PC, MP user) Reduction of financial burden, reduction of manpower such as caregivers, revitalization of local communities, for example, creation of purpose of life for the elderly through contact with young people, inheritance of culture from the elderly to young people, It can also be expected to contribute to the prevention of marginal settlements.

C3 ... Imaging discrimination means,
C4 ... Absence determination means,
C10: contour extraction means,
C12 ... abnormality determination means,
C12C: Non-operation determination means,
C102 ... Absence reporting means,
C104 ... abnormality reporting means,
C107 ... image display means,
C107A ... switching discrimination means,
CA: imaging member,
h ... Heart rate of the subject per unit time,
m ... Number of body movements per unit time of the subject,
n: Number of times the subject was continuously determined to be inactive,
N _max ... threshold for non-operation,
r ... the subject's breathing rate per unit time,
S: Subject detection system,
SN1 ... biological information measuring member, pressure sensor,
(SP + MC) ... voice extraction member.

Claims (11)

An imaging member for imaging a subject image as a subject image;
When the subject image continuously captured at a preset time interval by the imaging member is a first subject image and a second subject image, the difference between the first subject image and the second subject image Based on non-operation determination means for determining whether or not the subject is in an inoperative state;
An abnormality determining means for determining that an abnormality has occurred in the subject's body when the non-operation determining means determines that the subject is in an inoperative state;
An abnormality reporting means for reporting that the abnormality determining means has determined that an abnormality has occurred in the subject's body;
A subject detection system comprising: Contour extracting means for extracting a contour image that is an image of the subject's contour from the subject image;
When the image obtained by extracting the contour of the subject from the first subject image and the second subject image by the contour extracting means is used as the first contour image and the second contour image, the first contour image and the second contour The non-operation determination means for determining whether or not the subject is in an inoperative state based on a difference from an image;
Image display means for displaying the contour image at each time interval;
The subject detection system according to claim 1, further comprising: The image display means for switching the contour image to the subject image when the abnormality notification means reports that an abnormality has occurred in the subject's body;
The subject detection system according to claim 2, further comprising: When it is reported by the abnormality reporting means that an abnormality has occurred in the body of the subject, and when an input for switching the contour image to the subject image is made, it is determined that the contour image is switched to the subject image. Switching discriminating means to perform,
The image display means for switching and displaying the contour image to the subject image when it is determined by the switching determination means to switch the contour image to the subject image;
The subject detection system according to claim 3, further comprising: The imaging member arranged so as to be capable of imaging the preset action range of the subject,
The subject detection system according to any one of claims 1 to 4, further comprising: Determining that an abnormality has occurred in the body of the subject when the number of times that the subject is continuously determined to be in an inoperative state by the non-operation determining unit exceeds a preset threshold for inactivity; Anomaly discrimination means,
The subject detection system according to claim 1, further comprising: A biological information measuring member for measuring the biological information of the subject;
When the measured value of the biological information measured by the biological information measuring member is outside the normal range for the living body from a preset minimum value to a maximum value, and the non-operation determining means indicates that the subject is inactive The abnormality determining means for determining that an abnormality has occurred in the body of the subject when determined to be in a state;
The subject detection system according to any one of claims 1 to 6, further comprising: The biological information measuring member configured by a thin film pressure sensor that detects a waveform of pressure according to the heartbeat, breathing, and body movement of the subject;
When the heart rate per unit time of the subject based on the detection signal from the pressure sensor is outside the normal heart rate range from the preset minimum heart rate to the maximum heart rate, or based on the detection signal When the respiration rate per unit time of the subject is outside the normal range for breathing from the preset minimum respiration rate to the maximum respiration rate, or the number of body movements per unit time of the subject based on the detection signal is The abnormality determining means for determining that the measured value of the biological information is outside the normal range for the living body when the normal number for the body movement from the set minimum body movement number to the maximum body movement number is outside the normal range for the body movement;
The subject detection system according to claim 7, further comprising: The pressure-sensitive sensor arranged in a predetermined range of action of the subject,
The subject detection system according to claim 8, further comprising: While prompting the subject to speak, a voice extraction member that extracts the voice accompanying the subject's utterance;
When the voice extracted by the voice extraction member is outside the preset normal range for voice, and the measurement value of the biological information measured by the biological information measurement member is outside the normal range for biological And when the non-operation determination unit determines that the subject is in an inoperative state, the abnormality determination unit determines that an abnormality has occurred in the subject's body;
The subject detection system according to claim 7, further comprising: An imaging discriminating means for discriminating whether or not the subject image has been captured;
Absence determining means for determining that the subject is absent when it is determined that the subject image is not captured by the imaging determining means;
Absence notification means for reporting that the subject is determined to be absent by the absence determination means;
The subject detection system according to claim 1, further comprising: