[go: up one dir, main page]

WO2019030881A1 - Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci - Google Patents

Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci Download PDF

Info

Publication number
WO2019030881A1
WO2019030881A1 PCT/JP2017/029020 JP2017029020W WO2019030881A1 WO 2019030881 A1 WO2019030881 A1 WO 2019030881A1 JP 2017029020 W JP2017029020 W JP 2017029020W WO 2019030881 A1 WO2019030881 A1 WO 2019030881A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
monitoring
movement
person
unit
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2017/029020
Other languages
English (en)
Japanese (ja)
Inventor
安川　徹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
AI Viewlife Co Ltd
Original Assignee
AI Viewlife Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by AI Viewlife Co Ltd filed Critical AI Viewlife Co Ltd
Priority to PCT/JP2017/029020 priority Critical patent/WO2019030881A1/fr
Publication of WO2019030881A1 publication Critical patent/WO2019030881A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/02—Alarms for ensuring the safety of persons
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/04—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using a single signalling line, e.g. in a closed loop

Definitions

  • the present invention relates to a monitoring system, a monitoring method, a monitoring program, and a recording medium therefor.
  • Patent Document 1 a camera takes a picture of a bed and the vicinity of the bed, and according to the positional relationship between an object such as a bed and a moving object region where movement occurs
  • An information processing apparatus includes an action estimation unit that estimates an action related to a target of a watching target person. Then, it is described that when the action estimated for the watching target is an action showing a sign that the watching target is approaching danger, a notification for notifying the sign to the watching over the guard target is given.
  • Patent Document 2 a moving image of the behavior of the person being watched over in and around the bed is photographed, and a moving object is detected and detected based on the optical flow in the moving image.
  • An information processing apparatus includes an action estimation unit that estimates an action of a watching target person on or in the vicinity of a bed based on the position and moving direction of a moving object.
  • Patent Document 3 JP-A-2014-182409 (Patent Document 3) describes an environment in which a person to be monitored is photographed according to the installation position of the imaging unit in order to analyze an image according to the installation position of the imaging unit.
  • the monitoring apparatus which stored the monitoring environment data which defined previously was described.
  • JP-A-2014-236896 Patent Document 4
  • the depth is acquired for each pixel of a photographed image obtained by photographing a person to be watched and an object such as a bed serving as a standard of the person to be watched
  • An information processing apparatus is described which estimates the positional relationship in real space of a subject including a watching target person and a subject using the above, and estimates an action of the watching target person.
  • JP, 2014-166197, A (patent documents 1)
  • a person who watches over a specific target object such as a bed, for example, can presume an action of a target person.
  • the watching target rests on the bed. If this is the case, it may not be possible to check whether the watching target is present on the bed and whether the watching target is breathing normally on the bed.
  • Patent Document 2 how is it based on the position and moving direction of the moving body to be detected in one limited range such as on the bed or near the bed? Since the watching target person's behavior is uniformly estimated for the watching target person, if the watching target person is resting on the bed, whether the watching target person is present on the bed, In addition, it may not be possible to confirm whether the watching target breathes normally on the bed.
  • the environment stored in the monitoring environment data is a bed to be monitored as a reference It can only monitor the activity of the monitored person at a specific location. In addition, even if it can be confirmed that the person being monitored is on the bed, but there is little movement of the person being monitored, it may not be possible to confirm whether the person being monitored is resting or breathing normally. is there.
  • Patent Document 4 the action of the watching target person in real space is estimated not in two dimensions based on the two-dimensional photographed image, but the target to be photographed is There is a specific place like a bed.
  • this information processing apparatus even if it is confirmed that the person to be monitored is on the bed, if the person to be monitored hardly operates, whether the person to be monitored is resting normally breaths normally. May not be confirmed.
  • a monitoring system configured to notify a person who watches over a watching target of a warning sign when the action estimated about the watching target is an action showing a warning sign of danger approaching the watching target person, the action of the watching target person is If it is correctly detected and estimated correctly, the potential dangers of the watchers can not be correctly predicted.
  • an object of the present invention is to provide a monitoring system, a monitoring method, a monitoring program, and a recording medium for the same, which can improve the accuracy of the prediction of the danger to the person to be monitored.
  • a monitoring system comprises a first measuring unit for measuring the movement in a first area in which a monitoring target is present, and a second area in which the monitoring target is different from the first area.
  • the present inventors take advantage of minute movements of the human body in a certain pattern when breathing normally, so that minute movement patterns can be obtained without detecting absolute values of minute movements. It has been found that the presence or absence of breathing can be detected by detecting and comparing the pattern with the pattern of movement of the human body during normal breathing.
  • the body When a person is breathing normally at rest, the body tremors at the same cycle as the breathing cycle. Therefore, the displacement of a specific position (first area) of the person to be monitored is measured. At the same time, at the same measurement interval, the displacement of the position (second region) of the place where the monitoring subject is not present is also measured. The displacement of the second region is noise. There is almost no displacement in the second region. Then, by comparing the time change of the displacement of the first area with the time change of the displacement of the second area, or the time change of the difference between the displacement of the first area and the displacement of the second area It is possible to know whether or not the tremor due to the breathing of the person being monitored is detected, without having to measure the absolute value of or eliminate the noise.
  • the temporal change of the movement is compared with the temporal change of the movement in the first area in which the monitoring target exists and the temporal change of the movement in the second area on the bed where the monitoring target does not exist.
  • the movement in the first region and the movement in the second region are configured to be measured at a time interval of three quarters of the mean breathing cycle. preferable.
  • the body When a person is breathing normally at rest, the body tremors at the same cycle as the breathing cycle. Although a general breathing cycle is about 4 seconds, the breathing cycle varies depending on the individual, physical condition, and the like. Therefore, for example, first, the average of the breathing cycle of the monitoring subject (average breathing cycle) is measured, and then, at a time interval of three quarters of the average breathing cycle, the specific position of the monitoring subject (first Measure the displacement of the By measuring at time intervals of three quarters of the average breathing cycle, relatively large body displacements can be measured.
  • the first measurement unit and the second measurement unit are configured to measure the fine movement in a non-contact state using an infrared laser.
  • the surveillance system comprises a notification unit for notifying the user when the difference in movement is less than or equal to a predetermined value for a predetermined time.
  • the first area is preferably an area on the bed.
  • the information processing apparatus measures the movement in the first area in which the monitoring target is present, and the second area in which the monitoring target is different from the first area.
  • the information processing apparatus measures the movement in the area
  • the information processing apparatus acquires the time change of the difference between the movement in the first area and the movement in the second area, and the time change of the movement difference
  • And B determining whether the information processing apparatus has a predetermined pattern or change amount.
  • the monitoring program comprises the steps of measuring the movement in a first area in which the monitoring subject is present, and the movement in a second area in which there is no monitoring subject different from the first area. Whether the step of measuring, the step of obtaining the temporal change of the difference between the motion in the first region and the motion in the second region, and the temporal change of the motion difference are a predetermined pattern or change amount It is a monitoring program for making an information processor perform the step of judging whether or not it is not.
  • a recording medium according to the present invention is a recording medium recording the above program.
  • FIG. 1 It is a block diagram which shows the control related structure of the apparatus connected to the monitoring apparatus of this invention, and a monitoring apparatus. It is a figure which shows typically an example of the map of the room in which the monitoring apparatus of this invention is installed.
  • the figure (A) which shows the time change of displacement of the 1st field typically when the person to be monitored rests in a bed area as an example of a predetermined pattern, and the time of displacement of the 2nd field
  • FIG.B which shows change typically. It is a figure which shows an example of the matrix which linked a status, an area, and a living body detection result with an event.
  • the monitoring system 1 mainly includes a monitoring apparatus 100, a server 200, and a supervisor terminal 300.
  • the monitoring apparatus 100 is attached, for example, in the room of the person to be monitored.
  • the monitoring system 1 may include a plurality of monitoring devices 100, for example, the number of rooms to be monitored.
  • the monitoring apparatus 100 is, for example, an information processing apparatus including an external connection unit 110 connecting the server 200 and the monitoring apparatus 100, a control unit 120, a storage unit 130, and an infrared sensor 140.
  • the control unit 120 of the monitoring apparatus 100 is configured of a CPU, a RAM, a ROM, and the like.
  • the monitoring device 100 may include multiple processors.
  • the storage unit 130 stores a program 131, a matrix 132, a map 133, and a pattern 134 in this embodiment.
  • the program 131 is a monitoring program 131 for causing the monitoring apparatus 100 to execute the monitoring method.
  • the matrix 132 is a combination in which a status, an area, a living body detection result, and a time, which will be described in detail later, are associated with an event of the person to be monitored.
  • a bed, a living room, a toilet, and an entrance / exit area are designated as areas in an image photographing target area of a monitoring target person's room.
  • a pattern 134 is a time change of the body tremor of the person being monitored at rest. Since the matrix 132, the map 133, and the pattern 134 are updated, the storage unit 130 may be configured to store only the latest matrix 132, the map 133, and the pattern 134.
  • the control unit 120 executes the program 131 stored in the storage unit 130 to control each component.
  • the monitoring apparatus 100 includes a human body detection unit 121 including an area detection unit 121a and a status detection unit 121b, a first measurement unit 122a, and a second measurement unit 122b.
  • the human body detection unit 121, the living body detection unit 122, and the clock 123 of the control unit 120 are simply referred to as a detection unit.
  • the server 200 includes, for example, an external connection unit 210, a clock 220, a drive 230, and a storage unit 240.
  • the external connection unit 210 is for connecting the server 200 and the monitoring device 100, and the server 200 and the supervisor terminal 300.
  • the clock 220 of the server 200 is configured to be able to obtain accurate time information.
  • the drive 230 is for reading the recording medium on which the program 131 of the monitoring method is recorded, when the program 131 of the monitoring method is not stored in the storage unit 130 of the monitoring device 100. Therefore, the program 131 may be recorded not on the storage unit 130 of the monitoring apparatus 100 but on the recording medium read by the drive 230.
  • a recording medium for recording the program 131 a known medium such as a CD, a DVD, a semiconductor memory or the like is used.
  • a known medium such as a CD, a DVD, a semiconductor memory or the like is used.
  • the latest program 131, the matrix 132, the map 133, and the pattern 134, but also the update history of the matrix 132, the map 133, and the pattern 134 may be stored in the storage unit 240 of the server 200.
  • the supervisor terminal 300 is a terminal for the supervisor to operate at hand.
  • the monitoring system 1 may have a plurality of supervisor terminals 300, for example, the number of supervisors.
  • the supervisor terminal 300 includes, for example, an external connection unit 310, a clock 320, an input unit 300, a notification unit 340, and a display unit 350.
  • the external connection unit 310 is for connecting the supervisor terminal 300 and the server 200.
  • the input unit 330 is used by a supervisor to input information to the control unit 120 of the monitoring apparatus 100, and is configured as an input device such as a mouse, a keyboard, or a touch panel, for example.
  • the notification unit 340 is for notifying an observer, and may be configured as, for example, a display for displaying characters and images, and is configured to notify a specific event by turning on or off light. It may be configured to notify a specific event by generation or stop of sound, or may be configured otherwise. Further, the notification unit 340 may be configured to notify only when the event is a sign of danger. The notification unit 340 may be configured to notify the monitoring target person as well as the monitoring person of the event.
  • each of the monitoring device 100, the server 200, and the supervisor terminal 300 of the monitoring system 1 may be configured by a plurality of device groups.
  • the monitoring system 1 mainly performs operations of map setting, moving object detection, living body detection, status transition determination, event determination, and determination update.
  • the processing procedures of the operation described below may be replaced, omitted, replaced, or added as appropriate. Also, multiple processing procedures may be performed simultaneously.
  • ⁇ Map setting> As shown in FIG. 2, the room 400 of the monitoring target person 9 is photographed by the infrared sensor 140 of the monitoring device 100, processed as an image, and stored as the map 133 in the storage unit 130 of the monitoring device 100.
  • the infrared sensor 140 measures the distance from the infrared sensor 140 to the object, and transmits data to the control unit 120.
  • the infrared sensor 140 is a sensor using a wide-angle infrared laser in this embodiment, but instead of the infrared sensor 140, a known means capable of measuring the distance to an object may be used.
  • the control unit 120 receives the distance data detected by the infrared sensor 140, performs image processing, and displays the processed image via the server 200 through the external connection units 110, 210, and 310. Display on 350.
  • the observer confirms the image displayed on the display unit 350, and operates the input unit 330 to designate each of the bed area 401, the room area 402, the toilet area 403, and the entrance area 404 in the displayed image. And set the map 133.
  • the guard sets, for example, a bed surface and a range of 100 cm above the bed surface as a bed area 401. Further, the positional accuracy of the bed area 401 can be ⁇ 3 cm.
  • a specific area in the bed area 401 is further designated as a first area 411 (biological detection area).
  • the vicinity of the entrance of the toilet can be designated as the toilet area 403, and the vicinity of the entrance of the room 400 as the entrance area 404.
  • the living room area 402 may be designated as the total target area detected by the infrared sensor 140 excluding the bed area 401, the toilet area 403, and the entrance / exit area 404.
  • the outdoor area is not designated on the map, and the area outside the map is set as the outdoor area.
  • the set map 133 is transmitted from the supervisor terminal 300 to the monitoring apparatus 100 via the server 200 through the external connection units 110, 210, and 310, and stored in the storage unit 130 of the monitoring apparatus 100 and the storage unit 240 of the server 200. Be done.
  • the map is set as described above.
  • the monitoring apparatus 100 performs moving object detection.
  • the motion detection detects the area and status of the person being monitored.
  • the human body detection unit 121 of the monitoring apparatus 100 captures a moving object based on an image captured by the infrared sensor 140 and processed by the control unit 120.
  • the human body detection unit 121 further assumes that the center of the captured moving object is a torso, and assumes the highest point of the moving object to be a head or a shoulder, and extracts feature points of the head and the torso.
  • the feature points of the head are height, curved surface and volume, and are determined by 360 ° measurement.
  • the feature points of the torso are height and shoulder, chest, arms and volume, and are determined by 360 ° measurement. Note that not all feature points may be extracted. If there is an extracted feature point, tracking is performed on the moving body, and the movement direction (vector) is estimated using the optical flow.
  • the human body detection unit 121 stands by while maintaining the information detected immediately before the stop, and resumes the tracking and the optical flow when the movement is resumed.
  • the area detection unit 121a of the human body detection unit 121 detects an area in which the moving object exists based on the feature points and the vectors of the moving object.
  • the area detecting unit 121a causes the moving object to move to the outdoor room area outside the map 133. It shall be detected.
  • the status detection unit 121b of the human body detection unit 121 detects the status of the moving object based on the feature points and the vectors of the moving object.
  • the status of the mobile means the specific state of the mobile, and in this embodiment, the status detected by the status detection unit 121b is recumbent, standing, rising, boundary, falling, crouching, lying down , Entering the room 400, leaving the room 400, entering (toilet), leaving (toilet).
  • the type of status and the content of each status are not limited to the following, and may be freely defined.
  • the highest point of the moving body is within the range of less than 30 cm in height in the bed area 401, the status of "recumbent" is detected.
  • the status of “wake up” is detected.
  • the status of “rising up” is not detected.
  • the boundary position includes three actions: end sitting, crossing the fence, and falling off.
  • the end sitting position is a state in which the lower body is exposed to the bedside in the sitting state, and as described above, the lower body of the moving body is outside the bed area 401, and 30% to 100% of the moving body volume.
  • the status of "end sitting" is detected.
  • the upper fence is the sitting upper position of the upper body in the bedside, the upper body of the moving body is outside the bed area 401, and 30% or more and less than 100% of the moving body volume is the bed area If it is detected that it is out of 401, the status of "over fence" is detected.
  • the falling down was in the state where the upper body or lower body was exposed to the bedside in the lying position, and it was detected that the volume of 30% or more and less than 100% of the moving body exceeded the bed frame In the case, the "slip down" status is detected.
  • the "slip down" status is detected also in such a case.
  • the status detection unit 121 b stores the latest status in the storage unit 130 of the monitoring apparatus 100 and the storage unit 240 of the server 200 when the detected status of the person to be monitored changes. If the status of the person to be monitored does not change, the status detection unit 121b may not update the status stored in the storage unit 240. With regard to the specific status, the status detection unit 121b may cause the storage units 130 and 240 to store the latest status again even if the detected status of the person to be monitored does not change for a certain period.
  • the status detection unit 121 b may cause the display unit 350 of the supervisor terminal 300 to display the latest status via the external connection units 110, 210, and 310. If the status is displayed on the display unit 350, the supervisor can also correct the status. For example, when the area detection unit 121a detects that the monitoring target person is in the toilet area 403, and the status detection unit 121b detects the on (toilet) status, the display unit 350 has a “on (toilet)” status Is displayed. However, if the status is the result of false detection and the surveillance target person has actually returned from the toilet area 403 into the living area 402, the supervisor operates the input unit 330, and the external connection units 110 and 210 are operated. , 310 can input the actual status to the control unit 120.
  • the storage units 130 and 240 store the latest status reflecting the status corrected by the supervisor.
  • the monitoring device 1 does not detect a change larger than a predetermined size in the first area 411 for a predetermined period.
  • the motion detection is ended, and the living body detection for detecting a more minute movement is started.
  • the living body detection is performed by the living body detection unit 122 of the monitoring device 100.
  • the watched person When the watched person is resting on the bed, the watched person has only a slight movement. Therefore, in the method of tracking the relatively large movement of the moving object and detecting the area and the status, as in the area detection unit 121a and the status detection unit 121b, when the observer is resting on the bed, the observer It may not be possible to detect if it is present on the bed. On the other hand, in the detection method capable of detecting a minute movement on the bed, noise is also picked up, so removal of the noise becomes a problem.
  • the present inventor utilizes minute movement of the human body in a certain pattern during normal breathing, and does not detect the absolute value of minute movement, so that the minute movement It has been found that the presence or absence of breathing can be detected by detecting the pattern and comparing the pattern to the pattern of movement of the human body during normal breathing.
  • the displacement of the position (second region) of the place where the monitoring subject is not present is also measured.
  • the displacement of the second region is noise.
  • FIG. 3B there is almost no displacement in the second region.
  • living body detection is performed as follows.
  • the living body detection unit 122 When it is detected by the area detection unit 121a that a mobile object exists in the bed area 401, the living body detection unit 122 has less displacement in the bed area, and an infrared sensor than the first area 411 set in advance.
  • the area 412 near the position 140 is stored in the storage unit 130 as a second area.
  • the first measurement unit 122a of the living body detection unit 122 detects a displacement in the first area 411 determined in advance, and starts the living body detection when the displacement amount becomes smaller than a predetermined size.
  • the first area 411 and the second area 412 are set in the bed area 401, but the first area 411 and the second area 412 are other areas such as the living room area 402. May be
  • the average period of the breathing of the monitoring subject is measured.
  • the first measurement unit 122a calculates the average period of the breathing of the monitoring subject from the interval between the time when the height of the first area 411 is the highest and the time when the height of the first area 411 is the lowest. Ask.
  • the first measurement unit 122a measures the height of the first region 411 at a time interval of three quarters of the calculated average period of respiration, and the second measurement unit 122b determines the height.
  • the height of the second region 412 is measured at a time interval of three quarters of the mean period of respiration.
  • the first measuring unit 122a and the second measuring unit 122b may measure every 3 seconds.
  • the determination unit 124 changes temporally the difference between the height in the first region 411 measured by the first measurement unit 122a and the height in the second region 412 measured by the second measurement unit 122b. It is configured to get.
  • the determination unit 124 is further configured to determine whether the temporal change of the height difference is a predetermined pattern 134 or a change amount. If the time change of the height difference is a predetermined pattern 134 or change amount, the determination unit 124 determines that respiration is detected in the first area 411, that is, a living body is detected. Do. If the temporal change in height difference is not a predetermined pattern 134 or change amount, the determination unit 124 determines that respiration is abnormal in the first area 411.
  • the determination unit 124 determines that the respiration is not detected, that is, the living body is not detected. If respiration is abnormal or respiration is not detected, it is determined to be a biological abnormality.
  • the temporal change of the movement in the first area 411 on the bed in which the monitoring target is present is compared with the temporal change of the movement in the second area 412 on the bed in which the monitoring target does not exist. More accurately detect whether there is a person being monitored on the bed, without removing noise, by observing whether the difference between time changes of movement changes with a specific cycle Can.
  • the motion in the first region 411 and the motion in the second region 412 are measured at intervals of three quarters of the average respiratory cycle. By doing this, it is possible to capture the presence or absence of breathing with a small number of measurements.
  • the living body detection is stopped and the moving body detection is started.
  • the determination unit 124 compares the area detected at a certain detection time, the status, the result of living body detection (whether the body is abnormal or not), and the next detected status with the matrix 132, and detects an event of the monitoring target person. , It is determined whether the event is a sign of danger.
  • the rising reception status is displayed. Let it be the first status.
  • the status detection unit 121 b detects another status, the new status is set as a second status.
  • the status detection unit 121b detects the boundary position status next to the wakeup status, the boundary position status is set as the second status.
  • the status after the predetermined time may be set as the second status. For example, if the first status is rising and the status of the person being monitored remains rising after a predetermined time has elapsed, the second status may be rising.
  • the first method is a method of judging that a specific event always occurs if it is a combination of a specific area, first and second status, time, and a living body detection result.
  • an area detected at a certain detection time is a bed between 8:00 and 9:00 AM
  • the living body detection unit 122 detects a living body
  • the first status is “ If the second status is "beading”, the determination unit 124 always determines that "beading" occurs as an event, and determines that this event is a sign of danger.
  • the second method is whether a specific event occurs based on the specific area, the first and second status, the combination of time, respiration and / or movement and the probability of occurrence of past events It is a method to judge whether or not.
  • an area detected at a certain detection time is from 9:00 to 10:00 am as a bed, and the living body detection unit 122 detects a living body, and the first status is “ If the second status is “displacement”, the determination unit 124 determines that the “toilet” event is subsequently performed based on the history of the past events stored in the storage unit 240 of the server 200. Calculate the probability of occurrence. If the probability is, for example, 60% or more, the determination unit 124 determines that the “toilet” event occurs, and determines that this event is a sign of danger. On the other hand, based on the history of past events, if the probability that the “toilet” event will occur thereafter is less than 60%, for example, the determination unit 124 does not determine that the “toilet” event will occur.
  • an area detected at a certain detection time is a bed between 10:00 am and 11:00 am, and the living body detection unit 122 detects a living body and the detection is performed If the first status is “wake up” and the second status is “disengagement”, the determination unit 124 subsequently determines, based on the history of past events stored in the storage unit 240 of the server 200. Calculate the probability that the event of "vacuum” will occur. If the probability is, for example, 60% or more, the determination unit 124 determines that an event of “exit” occurs, and determines that this event is a sign of danger. On the other hand, based on the history of past events, if the probability of the occurrence of the event of “exit” after this is less than, for example, 60%, the determination unit 124 does not determine that the event of “exit” occurs.
  • Which event is to be determined by the first method and which event is to be determined by the second method is arbitrary.
  • the living body detection unit 122 detects that there is a breath, and the bed area 401 detects a “rest” position as the first status.
  • the determination unit 124 determines that the “caregiver or family entry / exit” event has occurred. In this case, it is not judged to be a sign of danger. In addition, the latest status of the watcher is returned to the "place".
  • control unit 120 controls the notification unit 340 so that the notification unit 340 notifies the observer.
  • the determination unit 124 may notify the monitor of the event by an electronic mail or a short message through a communication unit that performs network communication with the outside.
  • ⁇ Decision update> The observer notified by the notification unit 340 visually recognizes the person to be monitored through the display unit 350 or directly to confirm the correctness of the event. If it is correct that the notified event occurs, the observer will handle the event. On the other hand, if the notified event does not actually occur, the observer inputs to the input unit 330 that the notified event is erroneous.
  • the determination unit 124 causes the storage unit 240 of the server 200 to store the area, the status, the living body detection result, and the log of the correctness of the event determined based on the time, and the probability of occurrence of the event is updated. In this way, since the monitor can give feedback to the judgment by the judgment unit 124, estimation of the action of the monitor subject according to the characteristics of the watch target person, the characteristics of the watch target person, and changes in the environment And the accuracy of the prediction of the danger to the person being monitored.
  • the monitor operates the input unit 330 to give an instruction to the control unit 120 so that notification is not given in a specific time zone, for example, even when an event of “career or family entry / exit” occurs. It is also good.
  • the monitoring apparatus 100 periodically repeat the above-described process.
  • the time interval of repetition is set appropriately.
  • the monitoring apparatus 100 may be configured to start the monitoring process by the input of the monitoring person when the above-described process is not periodically repeated.
  • the monitor gives feedback to the determination by the determination unit 124, and thereby the monitor target person according to the characteristics of the monitor target 9, or the characteristics of the monitor target 9 or changes in the environment.
  • This is a monitoring system capable of improving the accuracy of the estimation of the behavior of 9 and the prediction of the danger to the person to be monitored 9.
  • the monitoring system 1 detects the monitoring target person based on the detection unit that detects at least one element of the plurality of elements for specifying the event of the monitoring target person 9, and the element of the event detected by the detection unit.
  • a judgment unit 124 which judges the 9 events, a notification unit 340 which notifies the monitor of the event judged by the judgment unit 124, and a corrector of the event notified by the notification unit 340 are inputted to the judgment unit 124 by the monitor
  • the determination of the event of the person 9 to be monitored by the determination unit 124 is configured to be updated based on the correctness / incorrectness input by the input unit 330.
  • the area detection unit 121a and the status detection unit 121b of the detection unit detect an area in which the monitoring target person 9 is present and a status of the monitoring target person 9 as elements for specifying an event
  • the storage unit 130 or 240 stores a combination in which at least the area in which the monitoring target person 9 is present and the change in status is associated with the event of the monitoring target person 9, and the determination unit 124 includes at least the area detection unit 121a of the detection unit.
  • the area detected by the status detection unit 121 b and the change in status are compared with the combination stored in the storage units 130 and 240 to determine the event of the person 9 to be monitored.
  • the detection unit is configured to further detect the presence or absence of breathing of the monitoring target person 9 by the living body detection unit 122, and the combination stored in the storage units 130 and 240 corresponds to the respiration of the monitoring target person 9. Furthermore, the determination unit 124 is configured to determine the event of the person to be monitored 9 by further collating with the combination associated with the presence or absence of breathing detected by the detection unit.
  • the detection unit is configured to further detect the time by the clock 123, the combination stored in the storage units 130 and 240 is further associated with the time, and the determination unit 124 further detects The time detected by the clock 123 is collated with the combination to determine the event of the person 9 to be monitored.
  • the area detected by the area detection unit 121a of the detection unit includes a bed area 401, a living room area 402, a toilet area 403, an entrance area 404, and an outdoor room.
  • the status of the person to be monitored 9 includes lying, standing, rising, boundary, leaving, entering and leaving the room, falling, crouching and lying down.
  • the monitoring apparatus 100 detects at least one element of a plurality of elements for identifying an event of the person 9 to be monitored.
  • the monitoring program executed in the monitoring system 1 detects at least one element of the plurality of elements for identifying the event of the person 9 to be monitored, and the element of the detected event. Step of judging the event of the person 9 to be monitored, notifying the observer of the determined event, and whether or not the person of the person 9 is monitored based on the correctness of the event notified to the observer inputted by the observer. It is a monitoring program for causing the monitoring apparatus 100 to execute the step of updating the determination of the event.
  • the recording medium of the present embodiment is a recording medium recording the above-described program.
  • the monitoring system 1 improves the accuracy of the prediction of the danger to the monitoring subject 9 by judging the event of the monitoring subject 9 not only on the status of the monitoring subject 9 but also on the status and the area. Is a possible surveillance system.
  • the monitoring system 1 detects the area where the monitoring subject 9 is present and the status of the monitoring subject 9 as an element for identifying the event of the monitoring subject 9, and the status detection section 121b. And a determination unit 124 that determines the event of the person 9 to be monitored based on the elements of the event detected by the detection unit, the area where the person 9 to be monitored is present, and the status The determination unit 124 collates at least the area detected by the detection unit and the change in status with the combination stored in the storage units 130 and 240. , And is configured to determine an event of the monitoring target person 9.
  • the detection unit is configured to further detect the presence or absence of breathing of the monitoring target person 9 by the living body detection unit 122, and the combination stored in the storage units 130 and 240 is the same as that of the monitoring target person 9. Further associated with the presence or absence of breathing, the determination unit 124 is further configured to determine the event of the person to be monitored 9 by collating with the combination associated with the presence or absence of breathing detected by the detection unit.
  • the detection unit is configured to further detect time by the clock 123, the combination stored in the storage units 130 and 240 is further associated with the time, and the determination unit 124 further detects The detected time is collated with the combination to determine the event of the person 9 to be monitored.
  • the area detected by the detection unit includes a bed area 401, a living area 402, a toilet area 403, an entrance area 404, and an outdoor room.
  • the status of the person to be monitored 9 includes lying, standing, rising, boundary, leaving, entering and leaving the room, falling, crouching and lying down.
  • the monitoring system 1 further includes a notification unit 340 that notifies the supervisor of the event determined by the determination unit 124.
  • the monitoring system 1 includes an input unit 330 in which the observer inputs correctness / incorrectness of the event notified by the notification unit 340 to the determination unit 124. Judgment of the event of the person 9 to be monitored by the determination unit 124 is input by the input unit 330. It is configured to be updated based on correctness.
  • the monitoring method executed in the monitoring system 1 of the present embodiment includes the area in which the monitoring subject 9 is present and the status of the monitoring subject 9 as elements for the monitoring apparatus 100 to identify the event of the monitoring subject 9. Detecting the event of the person 9 to be monitored based on the detected elements of the event, and at least the area where the person 9 to be monitored is present and the status are associated with the event of the person 9 to be monitored Storing the combination, and checking at least the detected area and status against the stored combination to determine an event of the person 9 to be monitored.
  • the monitoring program executed in the monitoring system 1 of the present embodiment detects an area in which the monitoring subject 9 is present and the status of the monitoring subject 9 as elements for specifying an event of the monitoring subject 9 And determining the event of the person to be monitored 9 based on the element of the detected event, and storing a combination in which at least the area where the person to be monitored 9 is present and the status are associated with the event of the person to be monitored 9 And a monitoring program for causing the monitoring apparatus 100 to execute the step of judging the event of the person 9 to be monitored by collating at least the detected area and the status with the stored combination.
  • the recording medium of the present embodiment is a recording medium recording the above-described program.
  • the monitoring system 1 can detect the presence or absence of breathing without detecting the absolute value of a minute movement when there is almost no movement, such as when the person to be monitored 9 is in a resting state. It is a system.
  • the monitoring system 1 is different from the first measurement unit 122a that measures the movement in the first area 411 in which the monitoring subject 9 exists, and the first area 411, in which the monitoring subject 9 does not exist.
  • Control unit 120 configured to obtain a temporal change in the difference with the movement in region 412, and control unit 120 further determines whether the temporal change in the movement difference is a predetermined pattern or change amount It is comprised so that it may judge whether or not.
  • the movement in the first area 411 and the movement in the second area 412 are configured to be measured at a time interval of three quarters of the average breathing cycle.
  • the first measurement unit 122a and the second measurement unit 122b are configured to measure a slight movement in a non-contact state using an infrared laser.
  • the monitoring system 1 is provided with the notification part 340 which notifies a monitoring person, when the difference of movement is below a predetermined value during predetermined time.
  • the first area 411 is an area on the bed area 401.
  • the monitoring method performed in the monitoring system 1 according to the present embodiment is different from the first area 411 in which the monitoring apparatus 100 measures the movement in the first area 411 where the monitoring target person 9 is present.
  • the monitoring apparatus 100 measures the movement in the second area 412 where the monitoring target person 9 does not exist, and the temporal change of the difference between the movement in the first area 411 and the movement in the second area 412.
  • the method includes the steps of: acquiring by the monitoring device 100; and determining whether the time change of the movement difference is a predetermined pattern or change amount.
  • the monitoring program executed in the monitoring system 1 of the present embodiment is a monitoring target person different from the step of measuring the movement in the first region 411 where the monitoring target person 9 exists, and the first region 411. 9: measuring the movement in the second area 412 where there is no 9; obtaining a temporal change in the difference between the movement in the first area 411 and the movement in the second area 412; It is a monitoring program for making the monitoring apparatus 100 execute the step of determining whether or not the time change of is a predetermined pattern or change amount.
  • the recording medium of the present embodiment is a recording medium on which the above-described program is recorded.
  • monitoring system 100: monitoring device, 120: control unit, 121: human body detection unit, 121a: area detection unit, 121b: status detection unit, 122: living body detection unit, 122a: first measurement unit, 122b: first 2 measurement unit 123: clock 124: determination unit 130: storage unit 131: program 132: matrix 134: pattern 140: infrared sensor 240: storage unit 330: input unit 340: notification unit , 350: display unit, 401: bed area, 402: living room area, 403: toilet area, 404: entrance area, 411: first area, 412: second area.

Landscapes

  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Emergency Alarm Devices (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Alarm Systems (AREA)

Abstract

L'invention concerne un système de surveillance, un procédé de surveillance, un programme de surveillance et un support d'enregistrement pour celui-ci, avec lesquels il est possible d'améliorer la précision de prédiction du danger pour un sujet de surveillance. Un système de surveillance 1 comprend : une première unité de mesure 122a pour mesurer un mouvement dans une première région 411 dans laquelle un sujet de surveillance 9 est présent ; une seconde unité de mesure 122b pour mesurer le mouvement dans une seconde région 412 dans laquelle le sujet de surveillance 9 n'est pas présent, la seconde région 412 étant différente de la première région 411 ; et une unité de commande 120 configurée pour acquérir le changement dans le temps de la différence entre le mouvement dans la première région 411 mesurée par la première unité de mesure 122a et le mouvement dans la seconde région 412 mesurée par la seconde unité de mesure 122b. L'unité de commande 120 est en outre configurée pour déterminer si le changement dans le temps de la différence de mouvement suit un motif prédéfini ou une quantité de changement.
PCT/JP2017/029020 2017-08-09 2017-08-09 Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci Ceased WO2019030881A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/029020 WO2019030881A1 (fr) 2017-08-09 2017-08-09 Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/029020 WO2019030881A1 (fr) 2017-08-09 2017-08-09 Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci

Publications (1)

Publication Number Publication Date
WO2019030881A1 true WO2019030881A1 (fr) 2019-02-14

Family

ID=65272037

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/029020 Ceased WO2019030881A1 (fr) 2017-08-09 2017-08-09 Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci

Country Status (1)

Country Link
WO (1) WO2019030881A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000189389A (ja) * 1998-12-25 2000-07-11 Matsushita Electric Works Ltd 睡眠状態監視装置
JP2002175582A (ja) * 2000-12-07 2002-06-21 Keio Gijuku 監視装置
JP2008110215A (ja) * 2007-11-15 2008-05-15 Sumitomo Osaka Cement Co Ltd 監視装置
JP3185531U (ja) * 2013-05-29 2013-08-22 株式会社ソキエ 障害者施設のサポートシステム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000189389A (ja) * 1998-12-25 2000-07-11 Matsushita Electric Works Ltd 睡眠状態監視装置
JP2002175582A (ja) * 2000-12-07 2002-06-21 Keio Gijuku 監視装置
JP2008110215A (ja) * 2007-11-15 2008-05-15 Sumitomo Osaka Cement Co Ltd 監視装置
JP3185531U (ja) * 2013-05-29 2013-08-22 株式会社ソキエ 障害者施設のサポートシステム

Similar Documents

Publication Publication Date Title
US11688265B1 (en) System and methods for safety, security, and well-being of individuals
CN115116133B (zh) 一种用于独居老人监护的异常行为检测系统及方法
US10080513B2 (en) Activity analysis, fall detection and risk assessment systems and methods
US8508372B2 (en) Method and system for fall detection
WO2019239813A1 (fr) Procédé de traitement d'informations, programme de traitement d'informations et système de traitement d'informations
US20020044682A1 (en) Method and apparatus for subject physical position and security determination
JP2019534495A (ja) ベッド転落を予測及び防止する患者監視のためのデバイス、システム、及び方法
JP2019535052A (ja) ベッド転落を予測及び防止する患者監視のためのデバイス、システム、及び方法
Bauer et al. Modeling bed exit likelihood in a camera-based automated video monitoring application
WO2019176222A1 (fr) Système, procédé et programme de détection d'anomalie
WO2019030880A1 (fr) Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement associé
JP2018149236A (ja) 健康管理システム、装置、および方法
KR20240159456A (ko) 사용자의 이상상태를 탐지하는 방법 및 장치
JP2021140422A (ja) 監視システム、監視装置及び監視方法
JP2019152914A (ja) 保育施設児童見守りシステム及び情報処理方法
JP4901674B2 (ja) 滞在状況監視システム、滞在状況監視サーバ及び滞在状況監視方法
WO2019030881A1 (fr) Système de surveillance, procédé de surveillance, programme de surveillance et support d'enregistrement pour celui-ci
JP2014048947A (ja) 画像監視装置
WO2019030879A1 (fr) Système, procédé et programme de surveillance, et support d'enregistrement dudit programme
WO2024146790A1 (fr) Procédé et dispositif informatique pour aider une évaluation d'un traumatisme crânien d'un sujet provoquée par un événement de chute
AU2015299180B2 (en) A system for identifying a change in walking speed of a person.
CN115457731A (zh) 跌倒侦测系统及其侦测方法
JP2023070277A (ja) 介護施設向け危険予知システム、プログラムおよび介護施設向け危険予知方法
JP7711956B2 (ja) 見守りシステム並びに見守り方法及び見守りプログラム
WO2021033453A1 (fr) Système de traitement d'image, programme de traitement d'image et procédé de traitement d'image

Legal Events

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

Ref document number: 17921280

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17921280

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP