WO2019176222A1 - Système, procédé et programme de détection d'anomalie - Google Patents

Système, procédé et programme de détection d'anomalie Download PDF

Info

Publication number
WO2019176222A1
WO2019176222A1 PCT/JP2018/047303 JP2018047303W WO2019176222A1 WO 2019176222 A1 WO2019176222 A1 WO 2019176222A1 JP 2018047303 W JP2018047303 W JP 2018047303W WO 2019176222 A1 WO2019176222 A1 WO 2019176222A1
Authority
WO
WIPO (PCT)
Prior art keywords
abnormality
unit
occurrence
determination
information
Prior art date
Application number
PCT/JP2018/047303
Other languages
English (en)
Japanese (ja)
Inventor
保理江　大作
Original Assignee
コニカミノルタ株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by コニカミノルタ株式会社 filed Critical コニカミノルタ株式会社
Priority to JP2020505601A priority Critical patent/JP7147837B2/ja
Publication of WO2019176222A1 publication Critical patent/WO2019176222A1/fr

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
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • the present invention relates to an anomaly detection system, an anomaly detection method, and an anomaly detection program for detecting an anomaly in a detection target area.
  • notifications may concentrate on a small number of staff from each room.
  • misinformation erroneous notifications
  • the cared person may fall down violently, or the visceral pain may slowly crumble (stagnate) on the spot.
  • the video from the ceiling accurately captures the change in the behavior of the cared person in a direction perpendicular to the ceiling. Is difficult. For this reason, it is difficult to determine in a short time whether the cared person falls or squats down based on the video.
  • the cared person sometimes crouches temporarily in order to pick up something. Therefore, if notification is made in a short time after the fall is determined, there is a risk of causing false information.
  • notification is performed after a predetermined time has elapsed after the fall determination, and therefore, it is considered to be very effective in preventing the occurrence of misreporting.
  • JP 2010-40017 A (refer to claim 4, paragraphs [0025], [0064] to [0076], FIG. 13 to FIG. 16 and the like)
  • the video when there is a suspicion of occurrence of an abnormality (for example, a fall) is recorded in the recording without omission, and the above video can be easily searched later (reusability of recorded video) It is desirable to construct a system capable of improving However, such a system has not yet been proposed.
  • the present invention has been made to solve the above-described problems.
  • the object of the present invention is to avoid loss of video at the time when there is a suspicion of occurrence of abnormality while suppressing frequent occurrence of false alarms, and to replay recorded video.
  • An object of the present invention is to provide an anomaly detection system, an anomaly detection method, and an anomaly detection program that can improve usability.
  • An abnormality detection system includes an imaging unit that captures a detection target area and acquires a video, an information acquisition unit that acquires in-area information indicating a state in the detection target area, and the area Based on the internal information, after determining that there is a suspicion of the occurrence of abnormality by the abnormality suspicion determination unit that determines whether there is a suspicion of occurrence of abnormality in the detection target area, the area An abnormality confirmation determination unit that determines the presence or absence of the occurrence of the abnormality based on internal information, and an output unit that notifies the occurrence of the abnormality to the outside when the occurrence of the abnormality is confirmed by the abnormality confirmation determination unit And when the suspected abnormality determining unit determines that there is a suspicion of occurrence of the abnormality, the movie acquired by photographing with the imaging unit, which temporally includes the suspected determination timing.
  • the temporary holding unit holds the A video recording unit that acquires the video and the timing information, and records the acquired video and the timing information in association with a confirmed result by the abnormality confirmation determining unit.
  • An abnormality detection method is an information acquisition for acquiring in-area information indicating a state in the detection target area by an information acquisition unit including an imaging unit that captures a detection target area and acquires a video.
  • a suspected abnormality determination step of determining whether or not there is a suspicion of occurrence of an abnormality in the detection target area based on the process and the information in the area; and
  • a temporary holding step of temporarily holding the video acquired by shooting with the imaging unit, which temporarily includes a determination timing, in association with timing information indicating the determination timing in a temporary holding unit;
  • an abnormality determination step for determining the presence / absence of the abnormality, and when the occurrence of the abnormality is determined
  • a recording step of acquiring the video and the timing information held in the temporary holding unit, and recording the video and the timing information in the video recording unit in association with a confirmed result of occurrence of the abnormality.
  • an output step of notifying the occurrence
  • An abnormality detection program is a program that causes a computer to execute the above-described abnormality detection method.
  • FIG. 1 is a block diagram showing a schematic configuration of a care support system which is an example of an abnormality detection system according to an embodiment of the present invention. It is a block diagram which shows the specific structure of the room terminal which the said care support system has. It is explanatory drawing which shows typically the state which looked at the subject who stood up in the living room from the front. It is explanatory drawing which shows typically the state which looked at the subject of FIG. 3A from the ceiling side of the living room. It is explanatory drawing which shows typically the state which looked at the subject who fell in the living room from the front. It is explanatory drawing which shows typically the state which looked at the subject of FIG. 4A from the ceiling side of the room.
  • video refers to an image that can be visually recognized in a narrow sense, but here, in a broad sense that includes data (pixel values) of each pixel constituting the image in addition to the image that is visible. Let it be a concept.
  • the present invention is not limited to the following contents.
  • FIG. 1 is a block diagram illustrating a schematic configuration of a care support system 1 which is an example of the abnormality detection system of the present embodiment.
  • the care support system 1 is a system for supporting the daily life of a cared person living in a care facility or a general house, or a patient admitted to a hospital (nurse), and is also referred to as a monitoring system. .
  • the cared person and the cared person are the target persons to be supported by the care support system 1 for living activities.
  • the care support system 1 is constructed in a care facility will be described.
  • the care support system 1 is configured by connecting a room terminal 10, a management server 20, and a notification terminal 30 so that they can communicate with each other via a communication line 40.
  • the communication line 40 includes a wired LAN (Local Area Network), a wireless LAN, an Internet line, a communication line for mobile phones, and the like.
  • the room terminal 10 and the management server 20 and the management server 20 and the notification terminal 30 can communicate with each other, but the room terminal 10 and the notification terminal 30 may directly communicate with each other.
  • the room terminal 10 is installed on the ceiling of the living room R of the target person T in the care facility. When there are a plurality of rooms R in the care facility, the room terminal 10 is installed for each room R.
  • the living room R is an area (detection target area) that is a target of abnormality detection by the care support system 1.
  • the management server 20 collectively manages information output from each room terminal 10.
  • the notification terminal 30 includes a mobile terminal such as a smartphone, a tablet terminal, and a notebook personal computer.
  • the staff S who monitors the abnormality of the behavior of the target person T can carry the notification terminal 30, and based on the information notified from the management server 20 to the notification terminal 30 and output from the notification terminal 30, It is possible to grasp the state of the target person T of R.
  • FIG. 2 is a block diagram showing a specific configuration of the room terminal 10.
  • the room terminal 10 includes an information acquisition unit 11, an action recognition unit 12, a temporary holding unit 13, a notification management unit 14, and a control unit 15.
  • the control part 15 is comprised by the central processing unit (CPU; Central Processing Unit) which controls operation
  • CPU Central Processing Unit
  • the information acquisition unit 11 is a block that acquires in-area information indicating the state in the living room R (particularly the state of the subject T), and includes an imaging unit 11a and a sensor unit 11b.
  • the imaging unit 11a is configured by a camera that captures an image of the room R from the ceiling toward the floor and obtains an image (for example, an infrared image) of a viewpoint directly above the viewing direction.
  • the imaging unit 11a basically acquires moving images by continuous shooting as the video, but may be configured to intermittently acquire still images by intermittent shooting.
  • the video acquired by the imaging unit 11a constitutes the in-area information.
  • the sensor unit 11b is a sensor that detects a state in the living room R.
  • a pyroelectric sensor that detects thermal energy (infrared rays)
  • a vibration sensor that detects vibration
  • a sound sensor that detects an impact sound
  • a pressure sensor for detecting sitting on a chair (including a wheelchair), a distance measuring sensor for measuring a distance from the subject T, and the like are appropriately selected and configured.
  • infrared rays are detected by a lower position pyroelectric sensor, and infrared rays are not detected by a higher position pyroelectric sensor.
  • the fall of the subject T can be detected by installing a vibration sensor on the floor surface of the living room R and detecting the vibration with the vibration sensor.
  • the fall of the subject T can be detected by detecting the impact sound at the time of the fall with a sound sensor.
  • the distance measuring sensor As the distance measuring sensor, a high-precision distance measuring sensor that can accurately detect whether the subject T lying on the floor is in a fallen state or in a squatting state may be used. Such a high-precision distance measuring sensor is expensive. For this reason, when using a distance measuring sensor, the distance measuring sensor may be selected in consideration of the required accuracy and cost. In the present embodiment, as will be described later, the tumbling is suspected and confirmed based on the video acquired by the imaging unit 11a, so that the tumbling can be performed without using a high-precision distance measuring sensor. Can be accurately detected.
  • the behavior recognition unit 12 recognizes the presence or absence of behavioral abnormalities of the target person T in the living room R and the type of behavior based on the in-area information acquired by the information acquisition unit 11.
  • Such an action recognition unit 12 is configured by, for example, a GPU (Graphics Processing Unit) that is an arithmetic device specialized for real-time image processing, but may be configured by the same or separate CPU as the control unit 15. .
  • the recognition of the behavior of the subject T by the behavior recognition unit 12 is performed as follows, for example.
  • FIG. 3A schematically shows a state in which the subject T standing up in the room R is viewed from the front
  • FIG. 3B schematically shows a state in which the subject T in FIG. 3A is viewed from the ceiling side of the room R.
  • 4A schematically shows a state in which the subject T who has fallen in the living room R is viewed from the front
  • FIG. 4B schematically shows a state in which the subject T in FIG. 4A is viewed from the ceiling side of the living room R. It shows.
  • the action recognition unit 12 extracts the head region of the subject T from the video acquired by the imaging unit 11a, obtains the diameter value Lm (mm), and obtains the obtained diameter value Lm and a preset threshold value Thb (mm ) And the presence or absence of the subject T is determined based on the magnitude relationship.
  • the head region can be extracted from the video using, for example, a machine-learned neural network or by pattern matching with a preset shape.
  • the action recognition unit 12 When the diameter value Lm of the extracted head region is equal to or greater than the threshold value Thb, the action recognition unit 12 does not fall within the living room R (see FIGS. 3A and 3B), and the diameter value Lm is the threshold value. When it is less than Thb, it is determined that the subject T has fallen in the room R (see FIGS. 4A and 4B). Such a determination can be made on the video acquired by the imaging unit 11a because the distance between the ceiling-mounted room terminal 10 and the head of the subject T is close if the subject T is standing. If the size of the head of the subject person T increases and the subject person T is in a fallen state, the distance between the ceiling-mounted room terminal 10 and the head of the subject person T is increased, and is acquired by the imaging unit 11a. This is based on the fact that the head size of the subject T is reduced on the video.
  • the action recognition unit 12 determines that the subject T has fallen, the action recognition unit 12 once determines that the state is “suspected abnormality”, and from this determination time point, the head diameter value equal to or greater than a preset threshold Thb. It is determined that “abnormality has occurred” is determined when a state in which Lm is not detected continues for a predetermined time. On the other hand, when the head diameter value Lm greater than or equal to the preset threshold Thb is detected from the determination of the “suspected abnormality” state, the action recognition unit 12 cancels the “suspected abnormality” state, Make a determination of “None”.
  • the action recognition unit 12 may determine whether there is a suspicion of occurrence of an abnormality (falling) and / or determination of whether or not an abnormality has occurred based on other falling detections and state detections. For example, the action recognition unit 12 determines that there is a suspicion of occurrence of an abnormality (falling) and / or if the moving speed of the target person T is not detected above a predetermined threshold on the video acquired by the imaging unit 11a. A determination of whether an abnormality has occurred may be made. Further, the behavior recognition unit 12 cancels the suspicion of occurrence of abnormality and / or causes no abnormality when it is detected that the target person T is on the bed on the video acquired by the imaging unit 11a. A definite determination may be performed.
  • the action recognition unit 12 determines whether there is an abnormality occurrence and / or whether there is an abnormality occurrence based on the information detected by the sensor unit 11b in addition to the image acquired by the imaging unit 11a. You may go. For example, when the movement of the target person T is not detected by the pyroelectric sensor (for example, when infrared rays are detected for a predetermined time or more by the low-position pyroelectric sensor), the behavior recognition unit 12 determines that there is a suspicion of occurrence of an abnormality. And / or determination of occurrence of abnormality may be performed.
  • the behavior recognition unit 12 Based on the above, the behavior recognition unit 12 generates an abnormality in the detection target area based on the information in the area acquired by the information acquisition unit 11 (information acquired by the imaging unit 11a or the sensor unit 11b).
  • the action recognition unit 12 performs each determination of whether or not there is a suspicion of occurrence of abnormality and determination of whether or not the abnormality has occurred, and also acquires timing information indicating the timing of each determination.
  • the time information which shows the time of the action recognition part 12 making each determination can be considered, for example. Therefore, the action recognition unit 12 also functions as a time measuring unit that measures time, and can acquire the time information.
  • the time information includes not only the time of the day but also the date of the calendar (year / month / day), but here, for convenience, only the time will be described. .
  • the timing information may be a mere tag indicating the point in time when the action recognition unit 12 has made a suspicious determination.
  • the temporary holding unit 13 is acquired by photographing with the imaging unit 11a including temporally the determination timing of suspected when the behavior recognition unit 12 (suspected abnormality determining unit 12a) determines that there is a suspected abnormality.
  • the recorded video is temporarily stored in association with the timing information indicating the determination timing.
  • a temporary storage unit 13 includes a volatile memory such as a DRAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory).
  • the temporary holding unit 13 is configured by a ring buffer that can hold (store) a new video by overwriting the old video in time when the remaining data capacity becomes smaller than a predetermined value.
  • the notification management unit 14 is an interface for communicating with the outside (the management server 20, the notification terminal 30), and includes an input / output port for communication. For example, information acquired by the room terminal 10 (for example, video stored in the temporary storage unit 13 or real-time video acquired by the imaging unit 11a) is output to the outside via the notification management unit 14 and the communication line 40.
  • the notification management unit 14 may be configured to include an antenna, a transmission / reception circuit, a modulation circuit, a demodulation circuit, and the like so as to support wireless communication with the outside.
  • FIG. 5 is a block diagram showing a specific configuration of the management server 20.
  • the management server 20 once aggregates the notification results from the room terminals 10 of each room R and notifies the notification terminal 30 of them.
  • Such a management server 20 includes a video recording unit 21, an application management unit 22, and a control unit 23.
  • the control unit 23 is composed of a CPU that controls the operation of each unit of the management server 20, and operates according to an operation program stored in a storage unit (not shown).
  • the video recording unit 21 acquires the video and timing information held in the temporary holding unit 13 of the room terminal 10 when the behavior recognition unit 12 (abnormality determination determination unit 12b) determines that an abnormality has occurred, The acquired video and timing information are recorded in association with the result of determination by the abnormality determination determination unit 12b (for example, the determination result with occurrence of abnormality).
  • a video recording unit 21 is composed of, for example, a hard disk, but may be composed of another nonvolatile memory such as a flash memory.
  • the application management unit 22 is an interface for communicating with the outside (room terminal 10, notification terminal 30), and includes an input / output port for communication.
  • information acquired by the management server 20 for example, information recorded by the video recording unit 21
  • the application management unit 22 may include an antenna, a transmission / reception circuit, a modulation circuit, a demodulation circuit, and the like so as to support wireless communication with the outside.
  • the management server 20 may be configured to further include a display unit such as a liquid crystal display and an instruction input unit such as a mouse and a keyboard.
  • the management server 20 can be easily configured using a terminal device such as a personal computer.
  • the management server 20 usually includes application functions such as ON / OFF setting of a notification function, initial setting for action recognition in the room terminal 10, setting of selection of a notification terminal 30 as a notification destination, history management of determination and notification, etc.
  • application functions such as ON / OFF setting of a notification function, initial setting for action recognition in the room terminal 10, setting of selection of a notification terminal 30 as a notification destination, history management of determination and notification, etc.
  • these settings and management are not directly related to the present embodiment, description thereof will be omitted.
  • FIG. 6 is a block diagram showing a specific configuration of the notification terminal 30.
  • the notification terminal 30 is configured by a mobile terminal such as a smartphone, and includes an output unit 31, a communication unit 32, and a control unit 33.
  • the control unit 33 includes a CPU that controls the operation of each unit of the notification terminal 30 and operates according to an operation program stored in a storage unit (not shown).
  • the output unit 31 outputs the result notified from the management server 20 via the communication line 40.
  • the output unit 31 receives a notification from the management server 20 and notifies the occurrence of an abnormality to the outside when the abnormality determination unit 12b of the room terminal 10 determines that an abnormality has occurred.
  • Such an output unit 31 includes a display unit such as a liquid crystal display, an audio output unit (speaker), and the like.
  • the display unit may be a touch panel display that also serves as an input unit.
  • notification methods such as a screen display in the notification terminal 30, a notification sound, are not specifically limited, Arbitrary methods can be used.
  • the communication unit 32 is an interface for communicating with the outside (room terminal 10, management server 20), and includes an antenna, a transmission / reception circuit, a modulation circuit, a demodulation circuit, and the like. Therefore, the notification terminal 30 acquires, for example, information output from the management server 20 (for example, information recorded by the video recording unit 21) via the application management unit 22, the communication line 40, and the communication unit 32, and outputs the information. It is possible to output at the unit 31.
  • an abnormality occurrence notification method (including an abnormality detection method) in the care support system 1 configured as described above will be described.
  • the detection target area is the living room R in which the target person T performs daily activities
  • the abnormality in the detection target area to be recognized is an abnormality in the behavior of the target person T in the living room R.
  • the case where the behavior abnormality is a fall of the subject T to the floor of the living room R will be described as an example.
  • FIG. 7 is a flowchart showing an example of an operation flow in the care support system 1 of the present embodiment.
  • a video in-area information indicating the state of the room R
  • the video is temporarily held in the temporary holding unit 13 under the control of the control unit 15 (S2).
  • in-area information indicating the state of the living room R may be acquired by the sensor unit 11b instead of the imaging unit 11a.
  • the in-area information acquired by the sensor unit 11 b is temporarily stored in the temporary storage unit 13. Note that when ex-post analysis is performed, if an image temporally prior to the determination time of the suspicion of occurrence of abnormality is unnecessary (when only an image after the suspicion determination time is required), S2 is omitted. It is also possible to do.
  • the suspected abnormality determination unit 12a of the behavior recognition unit 12 recognizes the occurrence of an abnormality in the living room R (whether the subject T has fallen) based on the video acquired in S1, and the occurrence of the abnormality is detected. Suspicion is determined (S3; abnormal suspect determination step).
  • the abnormality suspect determination unit 12a is based on the magnitude relationship between the diameter value Lm of the head region of the subject T extracted from the video acquired by the imaging unit 11a and the preset threshold value Thb.
  • the presence or absence of the subject T can be recognized, and thereby the presence or absence of the fall can be determined (see FIG. 3B, FIG. 4B, etc.).
  • the temporary holding unit 13 is acquired by photographing with the imaging unit 11a including temporally the determination timing of the fall (suspected of occurrence of abnormality) by the control of the control unit 15.
  • the video is temporarily held in association with the timing information indicating the determination timing (S4; temporary holding step).
  • FIG. 8 shows an example of information held in the temporary holding unit 13.
  • the time stored in the temporary storage unit 13 is “8:15:29” in S2, that is, before the suspicion that there is a fall in S3.
  • the suspected fall determination time at S3 is “8:17:15”, and the final fall decision determination time at S5 described later is “8:20:07”.
  • the former time can be substantially substituted with the latter time.
  • the abnormality confirmation determination unit 12b of the behavior recognition unit 12 recognizes the occurrence of an abnormality in the living room R (whether or not the subject person T falls) based on the video acquired in S1, and the occurrence of the abnormality is detected. Determination to determine the presence or absence is performed (S5: abnormality determination step). Specifically, the abnormality confirmation determination unit 12b determines whether or not the suspicion of falling determined based on the video has continued for a predetermined time. If it does not continue for a predetermined time, a determination of no fall is made. Note that the predetermined time may be set in advance to a sufficiently long time (fixed determination time), or even if it is not a sufficiently long time, in order to determine that notification should actually be made based on a suspicion of a fall. It may be set to a time until the reliability of is sufficiently increased.
  • S5 if it is a definite determination without a fall, the process returns to S3, and a suspected abnormality occurrence (whether or not the subject T has fallen) is determined based on the video acquired in S1.
  • the decision determination time (8:20:07 seconds) is further associated and held in the temporary holding unit 13 (S6).
  • the information held in the temporary holding unit 13 is transmitted to the management server 20 via the notification management unit 14 and the communication line 40 (S7) and recorded in the video recording unit 21 of the management server 20 (S8). Recording process).
  • the application management unit 22 notifies the notification terminal 30 that an abnormality has occurred, that is, the subject T has fallen in the room R (S9).
  • the notification terminal 30 the notification content in S9 is output (for example, displayed) by the output unit 31 (S10; output process).
  • the staff S who is the owner of the notification terminal 30 can take necessary measures such as seeing the output contents, grasping the fall of the target person T, and rushing to the living room R immediately.
  • the output unit 31 of the notification terminal 30 notifies the occurrence of abnormality to the outside (S10). Therefore, even if there is a suspicion of the occurrence of an abnormality, if it is confirmed that no abnormality has occurred after that (for example, if the occurrence of the abnormality has been resolved in a short time), do not notify the outside. Can be. Thereby, it is possible to suppress the occurrence of unnecessary notifications to the outside, that is, erroneous reports. As a result, the monitoring frequency of the staff S can be reduced by reducing the frequency of rushing to the detection target area (room R) of the monitoring person (for example, the staff S) of the notification destination.
  • the video acquired by the imaging unit 11 a including the timing of the suspected determination is temporally held in the temporary holding unit 13, and the video is acquired from the temporary holding unit 13 in the video recording unit 21. Is recorded (S8). Thereby, the video at the suspected time can be left in the video recording unit 21 without omission, and the above-mentioned video loss can be avoided.
  • the timing information indicating the determination timing is the video acquired by the imaging unit 11a including the determination timing of suspected in time. Corresponding to (for example, time information) and temporarily stored in the temporary storage unit 13 (S4).
  • the abnormality determination determination unit 12b determines that an abnormality has occurred (S5)
  • the video and timing information stored in the temporary storage unit 13 are associated with the determination result of the abnormality determination determination unit 12b and recorded as a video. Recorded in the part 21 (S8).
  • the timing information is used as a clue and the video at the time of the suspected occurrence of the abnormality recorded in the video recording unit 21 is represented by the number of recorded videos (for example, 1 second). Even if the number of frames per frame) is large, it will be possible to quickly find it later. As a result, the situation at the time when there is a suspicion of occurrence of an abnormality can be immediately analyzed based on the above video, and the reusability of the recorded video can be improved.
  • the management server 20 monitors a plurality of locations at the same time, that is, when the management server 20 collectively manages information output from the room terminals 10 of the plurality of living rooms R, the information is output from one room terminal 10.
  • the number of recorded videos in the video recording unit 21 is remarkably increased as compared with the case where only the information is managed. Therefore, the configuration of the present embodiment that can improve the reusability of the recorded video as described above is very effective particularly when the management server 20 monitors a plurality of locations simultaneously.
  • the abnormality suspect determination unit 12a recognizes the occurrence of an abnormality based on the video acquired by the imaging unit 11a, and determines the presence or absence of the occurrence of the abnormality (S1, S3). Accordingly, the video can be used not only for monitoring the detection target area but also for determining a suspicion of occurrence of an abnormality, and the video can be effectively used.
  • the abnormality confirmation determination unit 12b recognizes the occurrence of the abnormality based on the video acquired by the imaging unit 11a, and determines whether or not the abnormality has occurred (S1, S5). As a result, the video can be used not only for monitoring the detection target area but also for determining whether or not an abnormality has occurred, and the video can be used effectively.
  • the timing information described above is time information at a timing at which it is determined that there is a suspicion of occurrence of an abnormality
  • the determination timing at which there is a suspicion of occurrence of an abnormality is clearly identified.
  • the detection target area is the living room R of the target person T who is a target for supporting daily activities
  • the abnormality suspect determination unit 12a determines the target person T in the living room R based on the information in the area (for example, video). Whether or not there is a suspicion of occurrence of an abnormality related to the behavior of the person is determined, and the abnormality determination determination unit 12b determines whether or not an abnormality related to the action of the target person T in the room R occurs based on the information in the area.
  • the care support system 1 that performs the presence / absence of the occurrence of abnormality and the determination of the determination, and notifies the occurrence of the abnormality to the outside when the determination is confirmed. That is, in the care support system 1 constructed for the purpose of supporting the living activities of the target person T, the effects of the present embodiment described above can be obtained.
  • the care support system 1 of the present embodiment is connected to each other so as to be communicable with each other, the room terminal 10 installed in the living room R, the management server 20 that manages information acquired by the room terminal 10, and the above information. It further includes a notification terminal 30 for notifying the staff S.
  • the room terminal 10 includes an information acquisition unit 11, an abnormality suspect determination unit 12a, an abnormality confirmation determination unit 12b, and a temporary holding unit 13.
  • the management server 20 includes a video recording unit 21, and the notification terminal 30 includes an output unit 31.
  • the care support system 1 configured to include the room terminal 10, the management server 20, and the notification terminal 30, the effects of the above-described embodiment can be obtained.
  • the abnormality related to the behavior of the subject T includes the fall of the subject T.
  • the effect of the above-described embodiment can be obtained.
  • FIG. 9 is a flowchart illustrating another example of the operation flow in the care support system 1 of the present embodiment.
  • the flowchart of FIG. 9 is the same as FIG. 7 except that S9 and S10 shown in FIG. 7 are replaced with S9 ′ and S10 ′.
  • S9 ′ and S10 ′ are replaced with S9 ′ and S10 ′.
  • the temporary holding unit 13 includes a video that is temporally later than the time point before the suspicion determination in S3, and this includes the timing of the determination of the determination of having a fall in S5.
  • Video acquired at (determination determination time) is also included. Therefore, the information held in the temporary holding unit 13 is transmitted to the management server 20 via the notification management unit 14 and the communication line 40 in S7, and is recorded in the video recording unit 21 of the management server 20 in S8.
  • the video recorded in the video recording unit 21 also includes a video (hereinafter also referred to as a finalized video) acquired by the imaging unit 11a at the timing when the occurrence of abnormality is determined by the abnormality determination determination unit 12b. It can be said that.
  • the management server 20 notifies the occurrence of an abnormality (the target person T has fallen) from the application management unit 22 to the notification terminal 30 under the control of the control unit 23, and the timing information of the determination determination Based on this, the confirmed video recorded in the video recording unit 21 is transmitted (S9 ′).
  • the management server 20 may acquire the real-time video being shot by the imaging unit 11a from the room terminal 10 and transmit it to the notification terminal 30 together with the final video or instead of the final video. Good.
  • the output unit 31 of the notification terminal 30 notifies the occurrence of abnormality to the outside (for example, the staff S) by display or the like, and outputs at least one of the finalized video and the real-time video (S10 ').
  • the staff S who is the owner of the notification terminal 30 looks at the notification of the occurrence of the abnormality, grasps that the abnormality has occurred in the target person T, and outputs the final-time video and the real-time video that are output. It is possible to rush to the room R while confirming the situation (for example, whether the abnormal state continues at present) at the time of confirmation or the current detection target area (room R).
  • the video (including the video at the time of suspicion) that was shot including the determination timing of the suspected abnormality occurrence at S3 includes the video at the moment of the fall, and as described above, the situation before and after the actual fall This is a video that is necessary to search for and confirm later.
  • the video (the video at the time of determination) acquired at the determination timing of the occurrence of the abnormality in S5 is a video necessary for notifying the staff S in real time of the situation at the time of falling confirmed and rushing In this respect, the purpose of use is different from that of a video when in doubt.
  • the temporary holding unit 13 of the room terminal 10 described above may be provided in the management server 20, and the video recording unit 21 of the management server 20 may be provided in the room terminal 10. Further, the room terminal 10 may include each configuration of the management server 20.
  • an example of detecting the fall of the target person T as an abnormality of the action of the target person T has been described.
  • an abnormality of an action other than a fall such as leaving the subject person T from the bed or leaving the room is detected. Even when notifying outside, the abnormality detection system and abnormality detection method of the present embodiment can be applied.
  • the detection target area was demonstrated. Is not limited to room R.
  • room R in a plant such as a factory, an area where gas piping is laid may be set as the detection target area.
  • the abnormality detection system and abnormality detection method of this embodiment it is possible to apply the abnormality detection system and abnormality detection method of this embodiment. That is, the abnormality detection system and abnormality detection method of the present embodiment can be applied to cases other than abnormality in human behavior and posture.
  • the information acquisition unit 11 acquires an image (infrared image) acquired by the imaging unit 11a as a thermography (temperature distribution), thereby detecting an abnormality as to whether or not a fire has occurred in the living room R. You can also. Furthermore, the impact sound (for example, the breaking sound of the window glass) in the living room R can be detected by the sound sensor as the sensor unit 11b. As described above, since the information acquisition unit 11 includes the imaging unit 11a and the sensor unit 11b, an abnormality other than the behavior of the target person T in the living room R (an abnormality other than a person) is detected and notified to the outside. Even in this case, the notification method described in this embodiment can be applied.
  • the abnormality suspect determination unit 12a basically determines the occurrence of abnormality by detecting “change”, and the abnormality confirmation determination unit 12b determines the occurrence of abnormality by detecting “state”. Although it is possible to make a judgment, for example, it is possible to detect the occurrence of an abnormality by detecting an impact sound and determining the occurrence of an abnormality, and by confirming the occurrence of an abnormality by detecting the weight distribution using a pressure sensor. It is also possible to perform the determination of using a different sensor.
  • the room terminal 10, the management server 20, and the notification terminal 30 (particularly the output unit 31) described in the present embodiment may be configured integrally (stand-alone type) and arranged separately in the same room R. May be. Therefore, the notification terminal 30 may be a terminal device provided in the living room R.
  • the management server 20 may be a client server or a cloud server.
  • the effects described in the present embodiment are not limited by the form and configuration of the system (standalone, client server, cloud server, etc.).
  • the output destination of the notification result may be the management server 20 (including an external server) instead of the portable individual terminal (notification terminal 30) owned by the staff S.
  • the notification terminal 30 may be notified directly from the room terminal 10 without going through the management server 20.
  • the management server 20 can have the function of the action recognition unit 12 of the room terminal 10.
  • the notification terminal 30 is not owned by the staff S, and may be a terminal installed in an external building or company (for example, a security company or an insurance company).
  • the care support system 1 described in the present embodiment can be configured by a computer (PC) in which an abnormality detection program (application software) is installed (for example, a stand-alone type).
  • an abnormality detection program application software
  • each unit of the care support system 1 can be operated to execute each process (each process) described above.
  • a program is acquired, for example, by downloading from the outside via a network and stored in a storage unit (not shown).
  • the program is recorded on a computer-readable recording medium such as a CD-ROM (Compact Disk-Read Only Memory), and the computer reads the program from the recording medium and stores it in a storage unit. Also good.
  • the abnormality detection system, abnormality detection method, and abnormality detection program of the present embodiment described above can also be expressed as follows.
  • An information acquisition unit that includes an imaging unit that captures a detection target area and acquires a video, and that acquires information in the area indicating a state in the detection target area; Based on the information in the area, a suspected abnormality determination unit that determines the presence or absence of a suspected abnormality in the detection target area; After determining that there is a suspicion of occurrence of the abnormality by the abnormality suspect determination unit, based on the information in the area, an abnormality confirmation determination unit that determines whether or not the abnormality has occurred, An output unit that notifies the occurrence of the abnormality to the outside when the occurrence of the abnormality is confirmed by the abnormality confirmation determination unit; When it is determined that the abnormality is suspected by the abnormality suspect determination unit, the video acquired by photographing with the image capturing unit including the suspected determination timing in terms of time is used as the determination timing.
  • a temporary holding unit that temporarily holds the information in association with the timing information shown;
  • the video and the timing information held in the temporary holding unit are acquired, and the abnormality determination is added to the acquired video and the timing information.
  • An abnormality detection system comprising: a video recording unit that records the determination result of the determination unit in association with each other.
  • the abnormality suspect determination unit recognizes the occurrence of the abnormality based on the video acquired by the imaging unit as the in-area information, and determines whether there is a suspicion of the occurrence of the abnormality. 2.
  • the abnormality detection system according to 1 above.
  • the abnormality confirmation determining unit recognizes the occurrence of the abnormality based on the video acquired by the imaging unit as the in-area information, and determines the presence or absence of the abnormality. Or the abnormality detection system of 2.
  • the video recorded in the video recording unit further includes a finalized video acquired by the imaging unit at a timing when the occurrence of the abnormality is determined by the abnormality determination determination unit,
  • the output unit notifies the occurrence of the abnormality to the outside, and outputs at least one of the finalized video and a real-time video being captured by the imaging unit.
  • timing information is time information at a timing at which it is determined that the abnormality has occurred.
  • the detection target area is a living room of a target person who is a target of support for daily activities
  • the abnormality suspect determination unit determines whether or not there is a suspicion of occurrence of an abnormality related to the behavior of the subject in the living room based on the information in the area
  • the abnormality determination unit according to any one of 1 to 5, wherein the abnormality determination determination unit determines whether or not an abnormality related to the behavior of the target person in the living room has occurred based on the information in the area.
  • a room terminal installed in the room, communicably connected to each other, a management server for managing information acquired by the room terminal, and a notification terminal for notifying staff of the information;
  • the room terminal includes the information acquisition unit, the abnormality suspect determination unit, the abnormality confirmation determination unit, and the temporary holding unit.
  • the management server includes the video recording unit, 7.
  • a temporary holding step for temporarily holding in the temporary holding unit After it is determined that there is a suspicion of occurrence of the abnormality, an abnormality confirmation determination step for determining the presence or absence of the abnormality based on the information in the area; When the occurrence of the abnormality is determined, the video and the timing information held in the temporary holding unit are acquired, and the determination result of the occurrence of the abnormality is associated with the acquired video and the timing information. Recording process for recording in the video recording unit, And an output step of notifying the outside of the occurrence of the abnormality when the occurrence of the abnormality is determined.
  • the occurrence of the abnormality is recognized based on the image acquired by the imaging unit as the in-area information, and the presence or absence of the suspected abnormality occurrence is determined. 10.
  • the occurrence of the abnormality is recognized based on the image acquired by the imaging unit as the in-area information, and the presence or absence of the abnormality is confirmed. Or the abnormality detection method of 10.
  • the video recorded in the video recording unit further includes a finalized video acquired by the imaging unit at a timing when the occurrence of the abnormality is determined in the abnormality determination step, In the output step, the occurrence of the abnormality is notified to the outside, and at least one of the finalized video and a real-time video being captured by the imaging unit is output.
  • timing information is time information at a timing at which the occurrence of the abnormality is suspected.
  • the detection target area is a living room of a target person who is a target of support for daily activities
  • determine whether or not there is a suspicion of occurrence of an abnormality related to the behavior of the subject in the living room 14.
  • the abnormality according to any one of 9 to 13, wherein, in the abnormality confirmation determination step, presence / absence of occurrence of abnormality relating to the behavior of the target person in the living room is determined based on the in-area information. Detection method.
  • An abnormality detection program for causing a computer to execute the abnormality detection method according to any one of 9 to 15.
  • a computer-readable recording medium on which the abnormality detection program according to 16 is recorded.
  • the present invention can be used for an abnormality detection system, an abnormality detection method, and an abnormality detection program for detecting an abnormality in a detection target area.

Landscapes

  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Alarm Systems (AREA)
  • Emergency Alarm Devices (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

L'invention concerne un système de détection d'anomalie (système d'aide aux soins (1)) comprenant : une unité d'acquisition d'informations (11) comprenant une unité d'imagerie (11a) ; une unité de détermination de suspicion d'anomalie (12a) qui, sur la base d'informations internes à une zone indiquant l'état dans une zone de détection, détermine la présence éventuelle d'une occurrence suspectée d'une anomalie ; une unité de détermination de confirmation d'anomalie (12b) qui, sur la base des informations internes à la zone, confirme si une anomalie s'est produite ou non, ladite confirmation se produisant après la détermination d'une occurrence suspectée d'une anomalie ; une unité de sortie qui, s'il est confirmé qu'une anomalie s'est produite, communique l'occurrence d'une anomalie à l'extérieur ; une unité de maintien temporaire (13) qui, si la présence d'une occurrence suspectée d'une anomalie est déterminée, maintient temporairement une image comprenant l'instant auquel a été déterminée une occurrence suspectée d'une anomalie, l'image étant maintenue en association avec des informations d'instant ; et une unité d'enregistrement d'image qui, lorsqu'il est confirmé qu'une anomalie s'est produite, enregistre le résultat de confirmation en association avec l'image et avec les informations d'instant.
PCT/JP2018/047303 2018-03-13 2018-12-21 Système, procédé et programme de détection d'anomalie WO2019176222A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2020505601A JP7147837B2 (ja) 2018-03-13 2018-12-21 異常検知システム、異常検知方法および異常検知プログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2018045768 2018-03-13
JP2018-045768 2018-03-13

Publications (1)

Publication Number Publication Date
WO2019176222A1 true WO2019176222A1 (fr) 2019-09-19

Family

ID=67907750

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/047303 WO2019176222A1 (fr) 2018-03-13 2018-12-21 Système, procédé et programme de détection d'anomalie

Country Status (2)

Country Link
JP (1) JP7147837B2 (fr)
WO (1) WO2019176222A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712876A (zh) * 2019-10-24 2021-04-27 西科姆医疗系统株式会社 影像记录系统、影像记录方法及影像记录程序
CN113470311A (zh) * 2021-06-30 2021-10-01 华北理工大学 一种基于老人健康管理的红外线防摔监控装置及方法
CN114999222A (zh) * 2021-03-02 2022-09-02 丰田自动车株式会社 异常举动通知装置、通知系统、通知方法以及记录介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08249051A (ja) * 1995-03-15 1996-09-27 Toshiba Corp 監視装置
JP2008282219A (ja) * 2007-05-10 2008-11-20 Chudenko Corp 離床検知システム及び方法
JP2017200132A (ja) * 2016-04-28 2017-11-02 キヤノン株式会社 監視システム

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4651999B2 (ja) * 2004-09-02 2011-03-16 綜合警備保障株式会社 監視システム、監視方法
JP5204707B2 (ja) * 2009-03-30 2013-06-05 セコム株式会社 画像監視装置

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08249051A (ja) * 1995-03-15 1996-09-27 Toshiba Corp 監視装置
JP2008282219A (ja) * 2007-05-10 2008-11-20 Chudenko Corp 離床検知システム及び方法
JP2017200132A (ja) * 2016-04-28 2017-11-02 キヤノン株式会社 監視システム

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712876A (zh) * 2019-10-24 2021-04-27 西科姆医疗系统株式会社 影像记录系统、影像记录方法及影像记录程序
CN114999222A (zh) * 2021-03-02 2022-09-02 丰田自动车株式会社 异常举动通知装置、通知系统、通知方法以及记录介质
CN114999222B (zh) * 2021-03-02 2023-11-10 丰田自动车株式会社 异常举动通知装置、通知系统、通知方法以及记录介质
CN113470311A (zh) * 2021-06-30 2021-10-01 华北理工大学 一种基于老人健康管理的红外线防摔监控装置及方法

Also Published As

Publication number Publication date
JPWO2019176222A1 (ja) 2021-03-18
JP7147837B2 (ja) 2022-10-05

Similar Documents

Publication Publication Date Title
KR102021999B1 (ko) 인체 감시 발열 경보 장치
WO2019176222A1 (fr) Système, procédé et programme de détection d'anomalie
JP6689566B2 (ja) 警備システム及び警備方法
WO2016186160A1 (fr) Système de traitement d'image, dispositif de traitement d'image, procédé de traitement d'image et programme de traitement d'image
JP6527701B2 (ja) 異常通知装置、システム、プログラム及び方法
JP6519166B2 (ja) 監視制御プログラム、監視制御装置、および監視制御方法
JP2021103850A (ja) 監視端末及び監視方法
US20200135002A1 (en) Information providing apparatus, information providing method and information providing system
JP6026115B2 (ja) 救助活動支援システム
JP2019030628A (ja) 情報提供装置、情報提供システム、情報提供方法、及びプログラム
JP2019176380A (ja) 制御装置及び監視システム
JP7172376B2 (ja) 情報提供装置、情報提供システム、情報提供方法、及びプログラム
US20180322334A1 (en) Person Monitoring Device And Method, And Person Monitoring System
JP7090327B2 (ja) 情報処理装置、情報処理方法、プログラム
KR20200076240A (ko) 고독사 관리 시스템
US20140146154A1 (en) Patient monitoring system with image capture functionality
WO2021033453A1 (fr) Système de traitement d'image, programme de traitement d'image et procédé de traitement d'image
WO2019216045A1 (fr) Système et procédé de commande de système
JP2021099818A (ja) 情報処理装置、情報処理方法、及びプログラム
JP2020190889A (ja) 要介護者見守りシステム
KR101609533B1 (ko) 라이프 케어시스템
JP7327396B2 (ja) 制御プログラム、レポート出力方法、およびレポート出力装置
JP7209315B1 (ja) 建物に関連するサービスを提供するためのコンピュータシステム、および、そのコンピュータシステムにおいて実行される方法およびプログラム
US11557189B2 (en) Information processing apparatus, information processing method, and system
US20200027335A1 (en) Emergency Monitoring and Information System

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: 18910194

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2020505601

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18910194

Country of ref document: EP

Kind code of ref document: A1