WO2022118397A1 - Risk value calculation device, system, method, and non-transitory computer-readable medium storing program - Google Patents

Risk value calculation device, system, method, and non-transitory computer-readable medium storing program Download PDF

Info

Publication number
WO2022118397A1
WO2022118397A1 PCT/JP2020/044863 JP2020044863W WO2022118397A1 WO 2022118397 A1 WO2022118397 A1 WO 2022118397A1 JP 2020044863 W JP2020044863 W JP 2020044863W WO 2022118397 A1 WO2022118397 A1 WO 2022118397A1
Authority
WO
WIPO (PCT)
Prior art keywords
risk value
person
image data
symptom
visible light
Prior art date
Application number
PCT/JP2020/044863
Other languages
French (fr)
Japanese (ja)
Inventor
俊明 田中
Original Assignee
日本電気株式会社
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 日本電気株式会社 filed Critical 日本電気株式会社
Priority to JP2022566547A priority Critical patent/JPWO2022118397A5/en
Priority to PCT/JP2020/044863 priority patent/WO2022118397A1/en
Publication of WO2022118397A1 publication Critical patent/WO2022118397A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Definitions

  • the present invention relates to a risk value calculation device, a system, a method and a program.
  • the technique of detecting or measuring the risk of infection for an infectious disease of a person existing in a predetermined space is known.
  • the infection risk identification system described in Patent Document 1 identifies the infection level of a person staying in a space, detects the position of a person in the space, and positions the person in the space based on the infection level and the position of the person. Generates information indicating the risk of infection with infectious substances for each.
  • Patent Document 2 a person is identified from an image taken by a video camera at a point where a lot of people come and go, the body temperature of the person is measured by a thermal image camera, and a person having a body temperature exceeding a predetermined threshold is selected. The technique of presuming a fever is described.
  • the present disclosure has been made in view of such problems, and an object of the present disclosure is to provide a risk value calculation device or the like that can suitably determine an infection risk.
  • the risk value calculation device includes an image data acquisition means, a temperature measurement means, a symptom detection means, a risk value calculation means, and an output means.
  • the image data acquisition means acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data.
  • the temperature measuring means identifies a person included in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person.
  • the symptom detecting means detects the symptom of a person's infectious disease based on the visible light image data.
  • the risk value calculation means calculates the infection risk value of a person based on the body surface temperature and the symptom.
  • the output means outputs the infection risk value.
  • the computer executes the following method.
  • the computer acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data.
  • the computer identifies the person contained in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person.
  • the computer detects the symptoms of an infectious disease in a person based on visible light image data.
  • the computer calculates the infection risk value of a person based on the body surface temperature and the symptom.
  • the computer outputs the infection risk value.
  • the program causes a computer to perform the following steps.
  • the computer acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data.
  • the computer identifies the person contained in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person.
  • the computer detects the symptoms of an infectious disease in a person based on visible light image data.
  • the computer calculates the infection risk value of a person based on the body surface temperature and the symptom.
  • the computer outputs the infection risk value.
  • FIG. It is a block diagram which shows the structure of the risk calculation apparatus which concerns on Embodiment 1.
  • FIG. It is a flowchart which shows the risk calculation method concerning Embodiment 1.
  • FIG. It is a flowchart which shows the risk calculation method concerning Embodiment 2.
  • FIG. It is a flowchart which shows the risk calculation method concerning Embodiment 3.
  • FIG. 1 is a block diagram showing a configuration of a risk value calculation device 11 according to the first embodiment.
  • the risk value calculation device 11 is used, for example, to grasp the possibility that a person existing in a predetermined facility is infected with a predetermined infection or the possibility of being infected.
  • the risk value calculation device 11 mainly includes an image data acquisition unit 110, a temperature measurement unit 111, a symptom detection unit 112, a risk value calculation unit 113, and an output unit 114. It should be noted that these configurations of the risk value calculation device 11 are connected so as to be communicable as appropriate.
  • the image data acquisition unit 110 acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data.
  • the image data acquisition unit 110 may supply the acquired visible light image data and thermal image data to the temperature measurement unit 111 and the symptom detection unit 112, respectively.
  • Visible light cameras and infrared cameras are installed in a predetermined facility, in the vicinity of the facility, or in a predetermined place outdoors.
  • the visible light camera captures a landscape including a person, generates visible light image data related to the captured landscape image, and supplies the generated visible light image data to the risk value calculation device 11.
  • the infrared camera captures a landscape including a person, generates thermal image data related to the captured landscape image, and supplies the generated thermal image to the risk value calculation device 11.
  • the visible light camera and the infrared camera overlap at least a part of the shooting range.
  • the infrared camera has a shooting range corresponding to at least a part of the visible light image taken by the visible light camera.
  • the visible light camera and the infrared camera are fixed so that their positional relationship does not change.
  • the photographing apparatus can associate an object included in the visible light image data generated by the visible light camera with an object included in the thermal image data generated by the infrared camera.
  • the visible light camera and the infrared camera may be one or more.
  • the visible light camera or the infrared camera may be movable so that the positional relationship with each other changes. In this case, the visible light camera or the infrared camera may temporarily pan, tilt, or zoom by the user's operation, for example, and even if the angle of view is changed, it may automatically return to the predetermined position. preferable.
  • the temperature measuring unit 111 identifies a person included in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. When the temperature measuring unit 111 measures the body surface temperature of a person, the temperature measuring unit 111 supplies the measured data on the body surface temperature to the risk value calculating unit 113.
  • the temperature measuring unit 111 first extracts an image of a person from visible light image data. At this time, the temperature measuring unit 111 may extract only a specific part such as a face image in the body of the person. When the visible light camera captures a plurality of persons at the same time, the temperature measuring unit 111 extracts and identifies each of the plurality of persons from the visible light image data.
  • the temperature measuring unit 111 extracts the thermal image data corresponding to the image of the specified person. Further, the temperature measuring unit 111 measures the body surface temperature of the person specified from the extracted thermal image data. The temperature measuring unit 111 may measure the body surface temperature from the portion showing the highest temperature in the extracted thermal image data. Further, the temperature measuring unit 111 may calculate a statistical value of the temperature of the extracted thermal image data, and the calculated statistical value may be used as the body surface temperature of the person.
  • the symptom detection unit 112 When the symptom detection unit 112 receives the visible light image data, the symptom detection unit 112 detects the symptom of the infectious disease of the person from the image data of the person included in the received visible light image data. When the symptom detection unit 112 detects a symptom from the image data of a person, the symptom detection unit 112 supplies data indicating that the symptom has been detected to the risk value calculation unit 113.
  • the symptom detection unit 112 identifies the image data of a person included in the visible light image data. Next, the symptom detection unit 112 analyzes the image data of the specified person and estimates the posture of this person. Further, the symptom detection unit 112 determines whether or not the estimated posture matches the symptom shown when suffering from a preset disease. Then, when the symptom detection unit 112 determines that the posture of the person matches the symptom, the symptom detection unit 112 detects the symptom from the specified person.
  • the preset disease is, for example, pneumonia, and more specifically, infectious pneumonia.
  • Infectious pneumonia includes viral pneumonia, bacterial pneumonia and mycoplasma pneumonia.
  • the preset disease may be another disease in which a peculiar symptom appears.
  • the risk value calculation unit 113 calculates the infection risk value of the specified person from the body surface temperature and the symptom of the person. When the risk value calculation unit 113 calculates the infection risk value of a person, the calculated infection risk value is supplied to the output unit 114.
  • the symptom detection unit 112 may detect the symptom by using the thermal image acquired from the thermal camera 92 in addition to the visible light image data acquired from the visible light camera.
  • the risk value calculation unit 113 receives data on the body surface temperature of a person from the temperature measurement unit 111. Further, the risk value calculation unit 113 receives data on a person's symptom from the symptom detection unit 112. Then, the risk value calculation unit 113 calculates the infection risk value of the person using these received data.
  • the infection risk value is an index for estimating that the patient is infected with a preset disease, and is indicated by a preset numerical value.
  • the infection risk value is defined by a numerical value from 0 to 1. In this case, for example, 0 means the lowest risk of infection and 1 means the highest risk of infection. The higher the "infection risk", the higher the possibility of infection.
  • the body surface temperature of a person is classified into a plurality of levels, and each classification is set to a preset value in the range of 0 to 1.
  • the symptom of the person is set to a preset value in the range of 0 to 1, for example, for each corresponding symptom.
  • the infection risk value is calculated by taking the average value of each value set in this way.
  • the infection risk value is calculated higher when the body surface temperature of a person exceeds a predetermined threshold value than when the threshold value is not exceeded.
  • the infection risk value is calculated to be higher when the person shows symptoms of an infectious disease than when the person does not show the symptoms.
  • the above-mentioned method for calculating the infection risk value is an example, and the method for calculating the infection risk value is not limited to the above-mentioned method.
  • the output unit 114 When the output unit 114 receives the infection risk value calculated by the risk value calculation unit 113, the output unit 114 outputs the received infection risk value to a predetermined display device.
  • the predetermined display device may be included in the risk value calculation device 11.
  • the predetermined display device may be included in a predetermined terminal device that is communicably connected to the risk value calculation device 11.
  • FIG. 2 is a flowchart showing a risk calculation method according to the first embodiment.
  • the flowchart shown in FIG. 2 is started by, for example, activating the risk value calculation device 11.
  • the image data acquisition unit 110 acquires the visible light image data from the visible light camera and the thermal image data from the infrared camera (step S11).
  • the image data acquisition unit 110 may acquire the visible light image data and the thermal image data in parallel, or may sequentially acquire the visible light image data and the thermal image data according to a preset protocol.
  • the temperature measuring unit 111 identifies a person included in the visible light image data and the thermal image data (step S12), and measures the body surface temperature of the specified person (step S13).
  • the temperature measuring unit 111 generates the body surface temperature data in such a manner that the risk value calculation unit 113 can identify each identified person.
  • the symptom detection unit 112 detects the symptom of a person's infectious disease based on the visible light image data (step S14).
  • the symptom detection unit 112 detects the symptom of a plurality of persons
  • the symptom detection unit 112 generates data related to the symptom in such a manner that the risk value calculation unit 113 can identify each identified person.
  • the risk value calculation unit 113 calculates the infection risk value of the specified person from the data on the body surface temperature received from the temperature measurement unit 111 and the data on the symptom received from the symptom detection unit 112 (step S15). ).
  • the output unit 114 receives the infection risk value calculated by the risk value calculation unit 113, and outputs the received infection risk value (step S16).
  • step S13 and step S14 may be executed in parallel, or step S12 may be executed after step S13.
  • the risk value calculation device 11 uses the visible light image data acquired from the visible light camera and the thermal image data acquired from the thermal camera.
  • the risk value calculation device 11 calculates the infection risk value by combining the body surface temperature of the person measured from the thermal image data and the symptom of the person detected from the visible light image data. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program capable of suitably determining an infection risk.
  • the risk value calculation device 11 has a processor and a storage device as a configuration (not shown).
  • the storage device included in the risk value calculation device 11 includes a storage device including a flash memory and a non-volatile memory such as an SSD (Solid State Drive).
  • the storage device of the risk value calculation device 11 stores a computer program (hereinafter, also simply referred to as a program) for executing the risk value calculation method according to the present embodiment.
  • the processor also reads a computer program from the storage device into the memory and executes the program.
  • Each configuration of the risk value calculation device 11 may be realized by dedicated hardware. Further, a part or all of each component may be realized by a general-purpose or dedicated circuitry, a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. A part or all of each component of each device may be realized by the combination of the circuit or the like and the program described above. Further, as a processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), or the like can be used.
  • a CPU Central Processing Unit
  • GPU Graphics Processing Unit
  • FPGA field-programmable gate array
  • each component of the risk value calculation device 11 when a part or all of each component of the risk value calculation device 11 is realized by a plurality of arithmetic units, circuits, etc., the plurality of arithmetic units, circuits, etc. may be centrally arranged or distributed. It may be arranged.
  • the arithmetic unit, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client-server system and a cloud computing system.
  • the function of the risk value calculation device 11 may be provided in the SAAS (Software as a Service) format.
  • SAAS Software as a Service
  • FIG. 3 is a block diagram showing a configuration of the risk value calculation device according to the second embodiment.
  • the risk value calculation device 12 shown in FIG. 3 is communicably connected to the user terminal 21, the visible light camera 91, and the thermal camera 92 via the network 500.
  • the network 500 is a communication network such as a wide area network such as the Internet or a local area network such as a line in a predetermined facility.
  • the visible light camera 91 and the thermal camera 92 are installed in a predetermined facility 90 and are communicably connected to the risk value calculation device 12 via the network 500. There is a person in the facility 90.
  • the visible light camera 91 and the thermal camera 92 each photograph an internal landscape including a person in the facility 90, and transmit the image data (visible light image data and thermal image data) generated by the images to the risk value calculation device 12, respectively. do.
  • the user terminal 21 is an information processing terminal such as a personal computer, a smartphone or a tablet terminal.
  • the user terminal 21 is communicably connected to the risk value calculation device 12 via the network 500, and receives the infection risk value from the risk value calculation device 12.
  • the user terminal 21 displays the infection risk value received from the risk value calculation device 12, and notifies the user who operates the user terminal 21 of the infection risk value.
  • the user can grasp the infection risk value of the person existing in the facility 90 via the user terminal 21. As a result, for example, the user can perform an activity to reduce the risk of infection to a person existing in the facility 90.
  • the risk value calculation device 12 according to the present embodiment is different from the risk value calculation device 11 according to the first embodiment in that the storage unit 120 is included.
  • the storage unit 120 is a storage device including a non-volatile memory such as an EPROM (ErasableProgrammableReadOnlyMemory) or a flash memory.
  • the storage unit 120 stores the symptom DB 121.
  • the symptom DB 121 contains information about a preset symptom of the disease. More specifically, the symptom DB 121 includes preset symptoms of the disease that are related to the posture of the affected person. Further, the symptom DB 121 includes information on a mode that can be collated with the posture of the person extracted by the symptom detection unit 112. The mode that can be collated with the extracted posture of the person is, for example, image data showing the posture pattern of the person or feature amount data obtained by extracting the feature amount of the posture pattern of the person.
  • the symptom DB 121 may include symptom attribute information associated with the memorized posture pattern. The symptom attribute information is information indicating the possibility of infection and the severity of the symptom corresponding to each symptom posture pattern.
  • the storage unit 120 supplies the symptom DB 121 to the symptom detection unit 112.
  • the symptom detection unit 112 reads the symptom DB 121 from the storage unit 120, and collates the read symptom DB 121 with the extracted posture of the person. As a result of the collation, the symptom detection unit 112 determines whether or not the posture of the extracted person matches the posture pattern indicating the symptom included in the symptom DB 121. When the symptom detection unit 112 determines that the extracted posture of the person is included in the symptom DB 121, the symptom detection unit 112 detects the symptom from the posture of this person.
  • the symptom detection unit 112 detects a symptom, for example, when the posture of the person and the posture pattern included in the symptom DB 121 match at a predetermined ratio or more within a predetermined period. Specifically, for example, the symptom detection unit 112 detects a symptom when it matches a posture pattern showing the symptom in 10 seconds out of 60 seconds.
  • the symptom detection unit 112 may supply the symptom attribute information to the risk value calculation unit 113 together with the detected symptom.
  • the risk value calculation device 12 can improve the accuracy of the calculated infection risk value.
  • FIG. 4 is a flowchart of the risk calculation method according to the second embodiment.
  • the flowchart shown in FIG. 4 is different from the flowchart according to the first embodiment shown in FIG. 2 in that the processing between steps S13 and S15 is step S21 and step S22 instead of step S14.
  • Steps S11 to S13 are the same as the flowchart shown in FIG.
  • the symptom detection unit 112 extracts the posture of the specified person from the visible light image data received from the image data acquisition unit 110 (step S21).
  • the symptom detection unit 112 reads the symptom DB 121 from the storage unit 120, collates the extracted posture of the person with the symptom DB 121, and detects the symptom (step S22). As a result of collation between the posture of the extracted person and the symptom DB 121, if it is determined that they match, the symptom detection unit 112 detects the symptom from the posture of the extracted person. As a result of collation between the posture of the extracted person and the symptom DB 121, if it is not determined that they match, the symptom detection unit 112 does not detect the symptom from the posture of the extracted person.
  • the symptom detection unit 112 supplies data related to the detected symptom to the risk value calculation unit 113.
  • the risk value calculation device 12 proceeds to step S15.
  • the processing after step S15 is the same as the flowchart shown in FIG.
  • the risk value calculation device 12 is not limited to the above configuration.
  • a visible light camera 91 and a thermal camera 92 are shown one by one.
  • the risk value calculation device 12 may acquire image data from a plurality of visible light cameras 91 and a thermal camera 92, respectively.
  • the visible light camera 91 and the thermal camera 92 may be configured in different numbers.
  • the risk value calculation device 12 collates the extracted posture of the person with the information of the symptom DB 121. As a result, the risk value calculation device 12 can accurately calculate the infection risk value.
  • the symptom DB 121 may be configured to be updatable. As a result, the risk value calculation device 12 can collate the symptoms according to the type of the prevalent disease. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can appropriately and flexibly determine the infection risk.
  • FIG. 5 is a block diagram showing a configuration of the risk value calculation device according to the third embodiment.
  • the risk value calculation device 13 shown in FIG. 5 is different from the risk value calculation device 11 and the risk value calculation device 12 described above in that the congestion degree calculation unit 115 is included.
  • the image data acquisition unit 110 according to the present embodiment also supplies the acquired visible light image data to the congestion degree calculation unit 115.
  • the congestion degree calculation unit 115 receives visible light image data from the image data acquisition unit 110, and calculates the degree of congestion in the space from the received visible light image data.
  • the degree of congestion in a space is calculated by the number of people existing in a predetermined space. When the degree of congestion is high, the number of people present in the space is larger than when the degree of congestion is low. That is, the congestion degree calculation unit 115 can calculate the congestion degree by counting the number of people in the predetermined space. For example, the congestion degree calculation unit 115 may set the entire visible light image data as a predetermined space, or may set a part of the image included in the visible light image data as a predetermined space. Further, the congestion degree calculation unit 115 may divide the space included in the visible light image data into a plurality of spaces and calculate the congestion degree for each divided space. The congestion degree calculation unit 115 supplies the calculated congestion degree to the risk value calculation unit 113.
  • the congestion degree calculation unit 115 may treat a person included in a predetermined space as a crowd and calculate the congestion degree from the state of the crowd.
  • a crowd refers to a state in which a plurality of people appear to overlap in a predetermined space.
  • the congestion degree calculation unit 115 detects the crowd and identifies the crowded state of the detected crowd.
  • the congestion degree calculation unit 115 calculates the congestion degree. More specifically, for example, the congestion degree calculation unit 115 extracts a predetermined local image smaller than the image size of the visible light image data, and determines the congestion state of the crowd in the extracted local image. In determining the congestion state, the congestion degree calculation unit 115 may use, for example, a classifier generated by machine learning. By adopting such a means, the congestion degree calculation unit 115 can calculate the congestion degree without counting the exact number of people in the image.
  • the congestion degree calculation unit 115 used the visible light image data when calculating the congestion degree.
  • the data used in the calculation of the degree of congestion performed by the degree of congestion calculation unit 115 is not limited to the visible light image data. That is, the congestion degree calculation unit 115 may calculate the congestion degree by using the thermal image data.
  • the risk value calculation unit 113 calculates the infection risk value by further considering the degree of congestion in the predetermined space including the person in the visible light image data in addition to the body surface temperature and the symptom of the specified person. That is, the risk value calculation unit 113 calculates the infection risk value of a person existing in a space having a relatively high degree of congestion higher than the infection risk value of a person existing in a space having a relatively low degree of congestion. By calculating the infection risk value in consideration of the degree of congestion in this way, the risk value calculation device 13 can improve the accuracy of the infection risk value.
  • the risk value calculation unit 113 may calculate the infection risk value in consideration of the situation of surrounding persons as follows.
  • the risk value calculation unit 113 may calculate the infection risk value of a person by further considering the body surface temperature and the symptom of the surrounding person existing around the person. More specifically, for example, when there is a peripheral person in the vicinity of the person who calculates the infection risk value, the body surface temperature of the peripheral person exceeds normal temperature, or the posture of the peripheral person is a symptom. If it matches the posture pattern of, the risk value calculation unit 113 takes this into consideration and calculates a relatively high infection risk value.
  • the risk value calculation unit 113 calculates the infection risk value in consideration of the infection risk value of the peripheral person. For example, when the infection risk value of a peripheral person is the first risk value (for example, 0.7), the risk value calculation unit 113 is higher than the case where the infection risk value of the peripheral person is the second risk value (for example, 0.3). Calculate the infection risk value relatively high.
  • the risk value calculation unit 113 may calculate the infection risk value of the person by further considering the distance to the surrounding person existing in the vicinity of the person. More specifically, for example, when the distance to the surrounding person is the first distance (for example, 1 meter), the risk value calculation unit 113 has the second distance (for example, 3) in which the infection risk value of the peripheral person is farther than the first distance. Calculated relatively higher than the infection risk value calculated in the case of (meter). Based on the above contents, for example, the infection risk value can be calculated as follows. First, each element for calculating the infection risk value is set to a value between 0 and 1 as follows.
  • the body surface temperature of a person is classified into a plurality of levels, and each classification is set to a preset value in the range of 0 to 1.
  • the symptom of the person is set to a preset value in the range of 0 to 1, for example, for each corresponding symptom.
  • the degree of congestion is normalized so that the more crowded it is, the closer it is to 1, and the less crowded it is, the closer it is to 0.
  • the infection risk value is calculated by taking the average value of each value set in this way.
  • the body surface temperature of the surrounding person and the symptom of the surrounding person are set to a value between 0 and 1. Then, the risk value calculation unit 113 calculates the average value of these elements as the infection risk value.
  • the risk value calculation unit 113 may perform weighting so that the influence of a specific element is reflected relatively large when calculating the average value.
  • the above-mentioned infection risk value indicates the risk that the infection spreads to the surrounding persons existing around the predetermined person.
  • the risk value calculation unit 113 may calculate the risk of spreading the infection from a peripheral person to a predetermined person, or may calculate the risk of spreading the infection in a predetermined crowd.
  • the above-mentioned method for calculating the infection risk value is an example, and the method for calculating the infection risk value is not limited to the above-mentioned method.
  • FIG. 6 is a flowchart of the risk calculation method according to the third embodiment.
  • the flowchart shown in FIG. 6 is different from the flowchart according to the second embodiment shown in FIG. 4 in that it has steps S31 and S32 instead of step S15.
  • step S31 the congestion degree calculation unit 115 calculates the congestion degree from the visible light image data (step S31).
  • the risk value calculation unit 113 specifies from the data on the body surface temperature received from the temperature measurement unit 111, the data on the symptom received from the symptom detection unit 112, and the congestion degree received from the congestion degree calculation unit 115.
  • the infection risk value of the person who has been infected is calculated (step S32).
  • the output unit 114 outputs the infection risk value received from the risk value calculation unit 113 (step S16).
  • step S31 may be executed between steps S11 and S32 at a timing different from the order shown in FIG.
  • the order of the processes of measuring the body surface temperature (step S13), detecting the symptoms of a person (steps S21 and S22), and calculating the degree of congestion (step S31) does not matter. Further, these processes may be executed in parallel.
  • the embodiment 3 has been described above.
  • the risk value calculation device 13 according to the third embodiment calculates the degree of congestion, and calculates the risk value by adding the calculated degree of congestion.
  • the risk value calculation device 12 can accurately calculate the infection risk value.
  • the risk value calculation unit 113 can calculate the infection risk value more accurately by further considering the situation of the people around the person who calculates the infection risk value. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can determine the infection risk in a suitable and accurate manner.
  • the fourth embodiment is a system including at least a risk value calculation device and an authentication device.
  • FIG. 7 is a block diagram showing a configuration of the risk calculation system according to the fourth embodiment.
  • FIG. 7 shows the risk value calculation system 700.
  • the risk value calculation system 700 includes a risk value calculation device 14, an authentication device 200, a user terminal 21, a visible light camera 91, and a thermal camera 92.
  • the risk value calculation device 14 is communicably connected to the authentication device 200 via the network 500.
  • the risk value calculation device 14 also authenticates a person in cooperation with the authentication device 200 when identifying the person.
  • the risk value calculation device 11 can use the attribute information associated with the specified person.
  • the risk value calculation device 11 can store the history of the infection risk value in the specified person and directly notify the individual of the calculated infection risk value.
  • the storage unit 120 included in the risk value calculation device 14 stores the attribute information 122.
  • the attribute information includes the attribute information associated with the person involved in the authentication.
  • the attribute information 122 includes personal information such as a person's name and contact information, for example. Further, the attribute information 122 may include information on the medical history and chronic illness of the person involved in the authentication.
  • the risk value calculation device 14 may use the attribute information when calculating the infection risk value. For example, the risk value calculation unit 113 may calculate the infection risk value relatively high for a person having a chronic disease of the immune system.
  • the authentication device 200 is communicably connected to the risk value calculation device 14 via the network 500.
  • the authentication device 200 cooperates with the risk value calculation device 14 to authenticate a person from the face image data of the person. More specifically, the authentication device 200 receives the visible light image data from the risk value calculation device 14, and authenticates the face image included in the received visible light image data. Further, the authentication device 200 supplies the authentication result to the risk value calculation device 14.
  • FIG. 8 is a block diagram showing the configuration of the authentication device 200.
  • the authentication device 200 includes a face feature DB 210, a face detection unit 220, a feature point extraction unit 230, a registration unit 240, and an authentication unit 250.
  • the face feature DB 210 is a face feature database that stores a user ID of a person in association with the face feature information of the person.
  • the face detection unit 220 detects the face region included in the captured image and outputs it to the feature point extraction unit 230.
  • the feature point extraction unit 230 extracts feature points from the face region detected by the face detection unit 220, and outputs face feature information to the registration unit 240. Face feature information is a set of extracted feature points.
  • the registration unit 240 newly issues a user ID when registering facial feature information.
  • the registration unit 240 registers the issued user ID and the face feature information extracted from the registered image in the face feature DB 210 in association with each other.
  • the authentication unit 250 collates the face feature information extracted from the face image with the face feature information in the face feature DB 210. If the face feature information matches, the authentication unit 250 determines that the face recognition was successful, and if the face feature information does not match, determines that the face recognition has failed.
  • the authentication unit 250 returns the success or failure of face authentication to the risk value calculation device 14.
  • the presence or absence of matching of facial feature information corresponds to the success or failure of authentication.
  • the authentication unit 250 identifies the user ID associated with the successful face feature information, and sets the authentication result including the specified user ID and the fact that the authentication is successful as a risk value. Reply to the calculation device 14.
  • the risk value calculation system 700 may be a combination of the risk value calculation device 14 and the authentication device 200.
  • the user terminal 21 may be a terminal of a person to be authenticated. In that case, the user terminal 21 is possessed by each of the plurality of persons involved in the authentication. Therefore, the risk value calculation system 700 may have a plurality of user terminals 21 corresponding to a plurality of persons involved in authentication.
  • the embodiment 4 has been described above.
  • the risk value calculation system 700 according to the fourth embodiment can authenticate a person and calculate an infection risk value for the person to be authenticated. Therefore, the risk value calculation system 700 can calculate the infection risk value in consideration of personal information. Alternatively, the risk value calculation system 700 can notify the individual of the calculated infection risk value. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can suitably determine an infection risk in consideration of personal information.
  • Non-temporary computer-readable media include various types of tangible recording media.
  • Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), optomagnetic recording media (eg, optomagnetic disks), CD-ROM (Read Only Memory) CD-R, CDs. -R / W, including semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (RandomAccessMemory)).
  • the program may also be supplied to the computer by various types of temporary computer-readable media. Examples of temporary computer readable media include electrical, optical, and electromagnetic waves.
  • the temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.
  • An image data acquisition means for acquiring visible light image data generated by a visible light camera and thermal image data generated by an infrared camera having a shooting range corresponding to at least a part of the visible light image data.
  • a temperature measuring means for identifying a person included in the visible light image data and the thermal image data and measuring the body surface temperature of the specified person.
  • a symptom detecting means for detecting a symptom of an infectious disease of the person based on the visible light image data, and a symptom detecting means.
  • a risk value calculating means for calculating an infection risk value of the person based on the body surface temperature and the symptom, and a risk value calculating means.
  • a risk value calculation device including an output means for outputting the infection risk value.
  • the symptom detecting means detects the symptom from the posture of the person.
  • the risk value calculation device according to Appendix 1. (Appendix 3) Further equipped with a storage unit for storing postural patterns associated with the symptoms of the infectious disease.
  • the symptom detecting means detects the symptom by collating the posture of the person with the posture pattern.
  • the risk value calculation device described in Appendix 2. (Appendix 4)
  • the symptom detecting means detects the symptom when the posture of the person and the posture pattern match at a predetermined ratio or more within a predetermined period.
  • the risk value calculation device described in Appendix 3. (Appendix 5)
  • the storage unit stores the posture pattern associated with a predetermined pneumonia symptom.
  • the risk value calculation device according to Appendix 3 or 4.
  • Appendix 6 Further provided with a congestion degree calculation means for calculating the congestion degree of the space from the visible light image data is provided.
  • the risk value calculating means calculates the infection risk value by further adding the degree of congestion of the predetermined space including the person in the visible light image data.
  • the risk value calculation device according to any one of Supplementary note 1 to 5.
  • the congestion degree calculation means calculates the congestion degree based on the number of people in a predetermined space.
  • the risk value calculation device according to Appendix 6.
  • the risk value calculating means calculates the infection risk value of the person by further considering the body surface temperature of the surrounding person existing around the person and the symptom.
  • the risk value calculation device according to Appendix 6 or 7.
  • the risk value calculating means calculates when the infection risk value of the peripheral person is the first risk value, the infection risk value of the person is such that the infection risk value of the peripheral person is lower than the first risk value. 2 Calculated relatively higher than the infection risk value calculated in the case of risk value, The risk value calculation device according to Appendix 8. (Appendix 10) The risk value calculating means calculates the infection risk value of the person by further adding the distance to the surrounding person existing in the vicinity of the person. The risk value calculation device according to any one of Supplementary note 6 to 9. (Appendix 11) The risk value calculating means calculates the infection risk value of the person when the distance of the peripheral person is the first distance, when the infection risk value of the peripheral person is the second distance farther than the first distance.
  • the risk value calculation device calculates relatively higher than the calculated infection risk value, The risk value calculation device according to Appendix 10.
  • Appendix 12 An authentication device that authenticates a person from the visible light image data, A risk value calculation system including the risk value calculation device according to any one of Supplementary note 1 to 11, which calculates and outputs an infection risk value of the person to be authenticated.
  • Appendix 13 The computer The visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data are acquired, respectively. Identify the person included in the visible light image data and the thermal image data, The body surface temperature of the identified person was measured and Based on the visible light image data, the symptom of the infectious disease of the person is detected.
  • the infection risk value of the person is calculated.
  • Output the infection risk value, Risk value calculation method. (Appendix 14) The process of acquiring the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data, respectively.
  • a process for identifying a person included in the visible light image data and the thermal image data The process of measuring the body surface temperature of the identified person and The process of detecting the symptom of the infectious disease of the person based on the visible light image data, The process of calculating the infection risk value of the person based on the body surface temperature and the symptom, and The process of outputting the infection risk value and A non-temporary computer-readable medium containing a risk value calculation program that causes a computer to execute.
  • Risk value calculation device 11 Risk value calculation device 12 Risk value calculation device 13 Risk value calculation device 14 Risk value calculation device 21 User terminal 90 Facility 91 Visible light camera 92 Thermal camera 110 Image data acquisition unit 111 Temperature measurement unit 112 Symptom detection unit 113 Risk value calculation unit 114 Output unit 115 Congestion degree calculation unit 120 Storage unit 121 Symptom DB 122 Attribute information 200 Authentication device 210 Face feature DB 220 Face detection unit 230 Feature point extraction unit 240 Registration unit 250 Authentication unit 500 Network 700 Risk value calculation system

Landscapes

  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

This risk value calculation device (11) comprises: an image data acquisition unit (110), a temperature measurement unit (111), a symptom detection unit (112), a risk value calculation unit (113), and an output unit (114). The image data acquisition unit (110) acquires visible light image data generated by a visible light camera, and thermal image data generated by an infrared camera having a shooting range corresponding to at least a part of the visible light image data. The temperature measurement unit (111) specifies a person included in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. The symptom detection unit (112) detects the symptom of the person's infectious disease, on the basis of the visible light image data. The risk value calculation unit (113) calculates an infection risk value of the person, on the basis of the body surface temperature and the symptom. The output unit (114) outputs the infection risk value.

Description

リスク値算出装置、システム、方法及びプログラムが格納された非一時的なコンピュータ可読媒体Non-temporary computer-readable media containing risk value calculators, systems, methods and programs
　本発明はリスク値算出装置、システム、方法及びプログラムに関する。 The present invention relates to a risk value calculation device, a system, a method and a program.
　所定の空間に存在する人の感染症に対する感染リスクを検出ないし測定する技術が知られている。 The technique of detecting or measuring the risk of infection for an infectious disease of a person existing in a predetermined space is known.
　例えば、特許文献１に記載の感染リスク特定システムは、空間に滞在する人の感染レベルを特定し、空間における人の位置を検出し、上記感染レベルと上記人の位置に基づいて空間内の位置ごとに感染性物質への感染リスクを示す情報を生成する。 For example, the infection risk identification system described in Patent Document 1 identifies the infection level of a person staying in a space, detects the position of a person in the space, and positions the person in the space based on the infection level and the position of the person. Generates information indicating the risk of infection with infectious substances for each.
　また、特許文献２には、人の往来の多い地点において、ビデオカメラによる映像から人物を特定すると共に、熱画像カメラで当該人物の体温を測定し、所定閾値を超える体温の人物を選別して発熱者と推定する技術が記載されている。 Further, in Patent Document 2, a person is identified from an image taken by a video camera at a point where a lot of people come and go, the body temperature of the person is measured by a thermal image camera, and a person having a body temperature exceeding a predetermined threshold is selected. The technique of presuming a fever is described.
特開２０２０－０６７９３９号公報Japanese Unexamined Patent Publication No. 2020-07939 特開２０１２－２３５４１５号公報Japanese Unexamined Patent Publication No. 2012-235415
　上記の技術の内、例えばサーマルカメラにより人物の体表温度を測定する場合には、次のような課題がある。第１に、感染症の感染者が必ず発熱しているというわけではない。第２に、サーマルカメラが測定する人物の身体の部位が露出されていない場合や、外気温の影響を大きく受ける場合には体表温度を好適に測定できない場合がある。また所定のゲートを通過する人物の呼吸や心拍数を測定し、測定した呼吸や心拍数とその人物の発熱状況とを併せて分析する試みがある。しかしそのような技術を採用する場合、呼吸や心拍数などは広い空間における複数人に対して測定することができない。 Among the above techniques, for example, when measuring the body surface temperature of a person with a thermal camera, there are the following problems. First, people infected with infectious diseases do not always have a fever. Secondly, the body surface temperature may not be satisfactorily measured when the part of the body of the person measured by the thermal camera is not exposed or when it is greatly affected by the outside air temperature. There is also an attempt to measure the respiration and heart rate of a person passing through a predetermined gate and analyze the measured respiration and heart rate together with the fever status of the person. However, when such a technique is adopted, respiration, heart rate, etc. cannot be measured for multiple people in a wide space.
　本開示はこのような課題を鑑みてなされたものであり、好適に感染リスクを判定できるリスク値算出装置等を提供することを目的とする。 The present disclosure has been made in view of such problems, and an object of the present disclosure is to provide a risk value calculation device or the like that can suitably determine an infection risk.
　本開示の１実施形態にかかるリスク値算出装置は、画像データ取得手段、温度測定手段、症状検出手段、リスク値算出手段および出力手段を有する。画像データ取得手段は、可視光カメラが生成した可視光画像データと可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する。温度測定手段は、可視光画像データおよび熱画像データに含まれる人物を特定し、特定した人物の体表温度を測定する。症状検出手段は、可視光画像データに基づいて人物の感染症の症状を検出する。リスク値算出手段は、体表温度と症状とに基づいて、人物の感染リスク値を算出する。出力手段は、感染リスク値を出力する。 The risk value calculation device according to one embodiment of the present disclosure includes an image data acquisition means, a temperature measurement means, a symptom detection means, a risk value calculation means, and an output means. The image data acquisition means acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data. The temperature measuring means identifies a person included in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. The symptom detecting means detects the symptom of a person's infectious disease based on the visible light image data. The risk value calculation means calculates the infection risk value of a person based on the body surface temperature and the symptom. The output means outputs the infection risk value.
　本開示の１実施形態にかかる判定方法は、以下の方法をコンピュータが実行する。コンピュータは、可視光カメラが生成した可視光画像データと可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する。コンピュータは、可視光画像データおよび熱画像データに含まれる人物を特定し、特定した人物の体表温度を測定する。コンピュータは、可視光画像データに基づいて人物の感染症の症状を検出する。コンピュータは、体表温度と症状とに基づいて、人物の感染リスク値を算出する。コンピュータは、感染リスク値を出力する。 As the determination method according to the embodiment of the present disclosure, the computer executes the following method. The computer acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data. The computer identifies the person contained in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. The computer detects the symptoms of an infectious disease in a person based on visible light image data. The computer calculates the infection risk value of a person based on the body surface temperature and the symptom. The computer outputs the infection risk value.
　本開示の１実施形態にかかるプログラムは、コンピュータに、以下のステップを実行させるものである。コンピュータは、可視光カメラが生成した可視光画像データと可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する。コンピュータは、可視光画像データおよび熱画像データに含まれる人物を特定し、特定した人物の体表温度を測定する。コンピュータは、可視光画像データに基づいて人物の感染症の症状を検出する。コンピュータは、体表温度と症状とに基づいて、人物の感染リスク値を算出する。コンピュータは、感染リスク値を出力する。 The program according to one embodiment of the present disclosure causes a computer to perform the following steps. The computer acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data. The computer identifies the person contained in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. The computer detects the symptoms of an infectious disease in a person based on visible light image data. The computer calculates the infection risk value of a person based on the body surface temperature and the symptom. The computer outputs the infection risk value.
　本開示によれば、好適に感染リスクを判定できるリスク値算出装置等を提供することができる。 According to the present disclosure, it is possible to provide a risk value calculation device or the like that can suitably determine the infection risk.
実施形態１にかかるリスク算出装置の構成を示すブロック図である。It is a block diagram which shows the structure of the risk calculation apparatus which concerns on Embodiment 1. FIG. 実施形態１にかかるリスク算出方法を示すフローチャートである。It is a flowchart which shows the risk calculation method concerning Embodiment 1. 実施形態２にかかるリスク算出装置の構成を示すブロック図である。It is a block diagram which shows the structure of the risk calculation apparatus which concerns on Embodiment 2. FIG. 実施形態２にかかるリスク算出方法を示すフローチャートである。It is a flowchart which shows the risk calculation method concerning Embodiment 2. 実施形態３にかかるリスク算出装置の構成を示すブロック図である。It is a block diagram which shows the structure of the risk calculation apparatus which concerns on Embodiment 3. FIG. 実施形態３にかかるリスク算出方法を示すフローチャートである。It is a flowchart which shows the risk calculation method concerning Embodiment 3. 実施形態４にかかるリスク算出システムの構成を示すブロック図である。It is a block diagram which shows the structure of the risk calculation system which concerns on Embodiment 4. 実施形態４にかかる認証装置の構成を示すブロック図である。It is a block diagram which shows the structure of the authentication apparatus which concerns on Embodiment 4. FIG.
　以下では、本開示の実施形態について、図面を参照しながら詳細に説明する。各図面において、同一又は対応する要素には同一の符号が付されており、説明の明確化のため、必要に応じて重複説明は省略される。 Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and duplicate explanations are omitted as necessary for the sake of clarity of explanation.
　＜実施形態１＞
　図１を参照して実施形態１について説明する。図１は、実施形態１にかかるリスク値算出装置１１の構成を示すブロック図である。リスク値算出装置１１は、例えば所定の施設に存在する人が所定の感染に感染している可能性や感染する可能性を把握するために利用される。リスク値算出装置１１は主な構成として、画像データ取得部１１０、温度測定部１１１、症状検出部１１２、リスク値算出部１１３および出力部１１４を有する。なお、リスク値算出装置１１が有するこれらの構成は、適宜通信可能に接続されている。 <Embodiment 1>
The first embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration of a risk value calculation device 11 according to the first embodiment. The risk value calculation device 11 is used, for example, to grasp the possibility that a person existing in a predetermined facility is infected with a predetermined infection or the possibility of being infected. The risk value calculation device 11 mainly includes an image data acquisition unit 110, a temperature measurement unit 111, a symptom detection unit 112, a risk value calculation unit 113, and an output unit 114. It should be noted that these configurations of the risk value calculation device 11 are connected so as to be communicable as appropriate.
　画像データ取得部１１０は、可視光カメラが生成した可視光画像データと可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する。画像データ取得部１１０は、取得した可視光画像データおよび熱画像データを、温度測定部１１１および症状検出部１１２にそれぞれ供給し得る。 The image data acquisition unit 110 acquires the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data. The image data acquisition unit 110 may supply the acquired visible light image data and thermal image data to the temperature measurement unit 111 and the symptom detection unit 112, respectively.
　可視光カメラおよび赤外線カメラは、所定の施設内や施設の周辺または屋外における所定の場所等に設置されている。可視光カメラは、人物を含む風景を撮影し、撮影した風景の画像にかかる可視光画像データ生成し、生成した可視光画像データをリスク値算出装置１１に供給する。赤外線カメラは、人物を含む風景を撮影し、撮影した風景の画像にかかる熱画像データ生成し、生成した熱画像をリスク値算出装置１１に供給する。 Visible light cameras and infrared cameras are installed in a predetermined facility, in the vicinity of the facility, or in a predetermined place outdoors. The visible light camera captures a landscape including a person, generates visible light image data related to the captured landscape image, and supplies the generated visible light image data to the risk value calculation device 11. The infrared camera captures a landscape including a person, generates thermal image data related to the captured landscape image, and supplies the generated thermal image to the risk value calculation device 11.
　可視光カメラと赤外線カメラとは、少なくとも撮影範囲の一部が互いに重複している。換言すると、赤外線カメラは、可視光カメラが撮影する可視光画像の少なくとも一部に対応した撮影範囲を持つ。また可視光カメラと赤外線カメラとは、互いの位置関係が変化しないように固定されていることが好ましい。このような構成により、撮影装置は、可視光カメラが生成した可視光画像データに含まれる物体と赤外線カメラが生成した熱画像データに含まれる物体とを対応づけることができる。なお、可視光カメラおよび赤外線カメラは、それぞれ１台であってもよいし、複数であってもよい。また例えば可視光カメラまたは赤外線カメラは、互いの位置関係が変化する可動式であってもよい。この場合、可視光カメラまたは赤外線カメラは、例えばユーザの操作等により一時的にパン、チルトまたはズームを行って、画角が変更されたとしても、その後自動的に所定の位置に復帰することが好ましい。 The visible light camera and the infrared camera overlap at least a part of the shooting range. In other words, the infrared camera has a shooting range corresponding to at least a part of the visible light image taken by the visible light camera. Further, it is preferable that the visible light camera and the infrared camera are fixed so that their positional relationship does not change. With such a configuration, the photographing apparatus can associate an object included in the visible light image data generated by the visible light camera with an object included in the thermal image data generated by the infrared camera. The visible light camera and the infrared camera may be one or more. Further, for example, the visible light camera or the infrared camera may be movable so that the positional relationship with each other changes. In this case, the visible light camera or the infrared camera may temporarily pan, tilt, or zoom by the user's operation, for example, and even if the angle of view is changed, it may automatically return to the predetermined position. preferable.
　温度測定部１１１は、可視光画像データおよび熱画像データに含まれる人物を特定し、特定した人物の体表温度を測定する。温度測定部１１１は、人物の体表温度を測定すると、測定した体表温度に関するデータをリスク値算出部１１３に供給する。 The temperature measuring unit 111 identifies a person included in the visible light image data and the thermal image data, and measures the body surface temperature of the specified person. When the temperature measuring unit 111 measures the body surface temperature of a person, the temperature measuring unit 111 supplies the measured data on the body surface temperature to the risk value calculating unit 113.
　より具体的には、例えば温度測定部１１１はまず、可視光画像データから人物の画像を抽出する。このとき温度測定部１１１は、人物の身体の内、顔画像など特定の部位のみを抽出してもよい。可視光カメラが同時に複数の人物を撮影した場合には、温度測定部１１１は、可視光画像データから複数の人物をそれぞれ抽出してそれぞれ特定する。 More specifically, for example, the temperature measuring unit 111 first extracts an image of a person from visible light image data. At this time, the temperature measuring unit 111 may extract only a specific part such as a face image in the body of the person. When the visible light camera captures a plurality of persons at the same time, the temperature measuring unit 111 extracts and identifies each of the plurality of persons from the visible light image data.
　次に温度測定部１１１は、特定した人物の画像に対応する熱画像データを抽出する。さらに温度測定部１１１は、抽出した熱画像データから特定した人物の体表温度を測定する。温度測定部１１１は、抽出された熱画像データのうち最も高い温度を示す部分から体表温度を測定してもよい。また温度測定部１１１は、抽出された熱画像データの温度の統計値を算出し、算出した統計値を人物の体表温度としてもよい。 Next, the temperature measuring unit 111 extracts the thermal image data corresponding to the image of the specified person. Further, the temperature measuring unit 111 measures the body surface temperature of the person specified from the extracted thermal image data. The temperature measuring unit 111 may measure the body surface temperature from the portion showing the highest temperature in the extracted thermal image data. Further, the temperature measuring unit 111 may calculate a statistical value of the temperature of the extracted thermal image data, and the calculated statistical value may be used as the body surface temperature of the person.
　症状検出部１１２は、可視光画像データを受け取ると、受け取った可視光画像データに含まれる人物の画像データからその人物の感染症の症状を検出する。症状検出部１１２は人物の画像データから症状を検出すると、症状を検出したことを示すデータをリスク値算出部１１３に供給する。 When the symptom detection unit 112 receives the visible light image data, the symptom detection unit 112 detects the symptom of the infectious disease of the person from the image data of the person included in the received visible light image data. When the symptom detection unit 112 detects a symptom from the image data of a person, the symptom detection unit 112 supplies data indicating that the symptom has been detected to the risk value calculation unit 113.
　より具体的には、症状検出部１１２は、可視光画像データに含まれる人物の画像データを特定する。次に症状検出部１１２は、特定した人物の画像データを解析してこの人物の姿勢を推定する。さらに症状検出部１１２は、推定した姿勢が予め設定された疾病を罹患した場合に示される症状に一致するか否かを判定する。そして症状検出部１１２は人物の姿勢が症状に一致すると判定した場合には、特定した人物から症状を検出する。 More specifically, the symptom detection unit 112 identifies the image data of a person included in the visible light image data. Next, the symptom detection unit 112 analyzes the image data of the specified person and estimates the posture of this person. Further, the symptom detection unit 112 determines whether or not the estimated posture matches the symptom shown when suffering from a preset disease. Then, when the symptom detection unit 112 determines that the posture of the person matches the symptom, the symptom detection unit 112 detects the symptom from the specified person.
　予め設定された疾病とは、例えば肺炎であり、より具体的には、感染性の肺炎である。感染性の肺炎とは、ウイルス性肺炎、細菌性肺炎およびマイコプラズマ肺炎を含む。このような肺炎に感染した者が肺炎を発症した場合、感染者は例えば悪寒により両肘を抱えたり、前かがみの姿勢になったり、あるいは喉や胸に痛みを感じるために喉や胸に手を当てたりする。なお予め設定された疾病とは、特有の症状が現れる他の疾病であってもよい。 The preset disease is, for example, pneumonia, and more specifically, infectious pneumonia. Infectious pneumonia includes viral pneumonia, bacterial pneumonia and mycoplasma pneumonia. When a person infected with such pneumonia develops pneumonia, the infected person may hold both elbows due to chills, lean forward, or have a hand in the throat or chest due to pain in the throat or chest. I guess. The preset disease may be another disease in which a peculiar symptom appears.
　リスク値算出部１１３は、特定した人物の体表温度および症状から、その人物の感染リスク値を算出する。リスク値算出部１１３は人物の感染リスク値を算出すると、算出した感染リスク値を出力部１１４に供給する。なお、症状検出部１１２は、可視光カメラから取得した可視光画像データに加えて、サーマルカメラ９２から取得した熱画像を利用して症状を検出してもよい。 The risk value calculation unit 113 calculates the infection risk value of the specified person from the body surface temperature and the symptom of the person. When the risk value calculation unit 113 calculates the infection risk value of a person, the calculated infection risk value is supplied to the output unit 114. The symptom detection unit 112 may detect the symptom by using the thermal image acquired from the thermal camera 92 in addition to the visible light image data acquired from the visible light camera.
　より具体的には、リスク値算出部１１３は、温度測定部１１１から人物の体表温度に関するデータを受け取る。またリスク値算出部１１３は、症状検出部１１２から人物の症状に関するデータを受け取る。そしてリスク値算出部１１３は、受け取ったこれらのデータを使って人物の感染リスク値を算出する。感染リスク値は、予め設定された疾病に感染していることを推定する指標であり、予め設定された数値により示される。例えば感染リスク値は０から１までの数値により定義される。この場合、例えば０が最も感染リスクが低く、1が最も感染リスクが高いことを意味する。なお「感染リスク」は、高いほど感染している可能性が高いことを示す。より具体的には、例えば、人物の体表温度は、複数のレベルに分類され、それぞれの区分が、０から１の範囲のうち予め設定された値に設定される。また人物の症状は、例えば該当する症状ごとに０から１の範囲のうち予め設定された値に設定される。感染リスク値は、このように設定されたそれぞれの値の平均値を取ることにより算出される。感染リスク値は、人物の体表温度が所定の閾値を超える場合には、当該閾値を超えない場合よりも高く算出される。また感染リスク値は、当該人物が感染症の症状を示す場合には、当該症状を示さない場合よりも高く算出される。なお、上述の感染リスク値の算出方法は一例であって、感染リスク値の算出方法は上述のものに限定されない。 More specifically, the risk value calculation unit 113 receives data on the body surface temperature of a person from the temperature measurement unit 111. Further, the risk value calculation unit 113 receives data on a person's symptom from the symptom detection unit 112. Then, the risk value calculation unit 113 calculates the infection risk value of the person using these received data. The infection risk value is an index for estimating that the patient is infected with a preset disease, and is indicated by a preset numerical value. For example, the infection risk value is defined by a numerical value from 0 to 1. In this case, for example, 0 means the lowest risk of infection and 1 means the highest risk of infection. The higher the "infection risk", the higher the possibility of infection. More specifically, for example, the body surface temperature of a person is classified into a plurality of levels, and each classification is set to a preset value in the range of 0 to 1. Further, the symptom of the person is set to a preset value in the range of 0 to 1, for example, for each corresponding symptom. The infection risk value is calculated by taking the average value of each value set in this way. The infection risk value is calculated higher when the body surface temperature of a person exceeds a predetermined threshold value than when the threshold value is not exceeded. In addition, the infection risk value is calculated to be higher when the person shows symptoms of an infectious disease than when the person does not show the symptoms. The above-mentioned method for calculating the infection risk value is an example, and the method for calculating the infection risk value is not limited to the above-mentioned method.
　出力部１１４は、リスク値算出部１１３が算出した感染リスク値を受け取ると、受け取った感染リスク値を所定の表示装置へ出力する。所定の表示装置は、リスク値算出装置１１に含まれてもよい。所定の表示装置は、リスク値算出装置１１と通信可能に接続する所定の端末装置に含まれるものであってもよい。 When the output unit 114 receives the infection risk value calculated by the risk value calculation unit 113, the output unit 114 outputs the received infection risk value to a predetermined display device. The predetermined display device may be included in the risk value calculation device 11. The predetermined display device may be included in a predetermined terminal device that is communicably connected to the risk value calculation device 11.
　次に、図２を参照して、実施形態１にかかるリスク値算出装置１１が実行する処理について説明する。図２は、実施形態１にかかるリスク算出方法を示すフローチャートである。図２に示すフローチャートは、例えばリスク値算出装置１１を起動させることにより開始する。 Next, with reference to FIG. 2, the process executed by the risk value calculation device 11 according to the first embodiment will be described. FIG. 2 is a flowchart showing a risk calculation method according to the first embodiment. The flowchart shown in FIG. 2 is started by, for example, activating the risk value calculation device 11.
　まず、画像データ取得部１１０は、可視光カメラから可視光画像データを取得するとともに、赤外線カメラから熱画像データを取得する（ステップＳ１１）。画像データ取得部１１０は、可視光画像データと熱画像データとを平行して取得してもよいし、予め設定されたプロトコルにしたがって、順次取得してもよい。 First, the image data acquisition unit 110 acquires the visible light image data from the visible light camera and the thermal image data from the infrared camera (step S11). The image data acquisition unit 110 may acquire the visible light image data and the thermal image data in parallel, or may sequentially acquire the visible light image data and the thermal image data according to a preset protocol.
　次に、温度測定部１１１は、可視光画像データおよび熱画像データに含まれる人物を特定し（ステップＳ１２）、特定した人物の体表温度を測定する（ステップＳ１３）。なお、温度測定部１１１は、複数の人物の体表温度を測定した場合には、それぞれ特定した人物をリスク値算出部１１３が識別できる態様により体表温度のデータを生成する。 Next, the temperature measuring unit 111 identifies a person included in the visible light image data and the thermal image data (step S12), and measures the body surface temperature of the specified person (step S13). When the body surface temperature of a plurality of persons is measured, the temperature measuring unit 111 generates the body surface temperature data in such a manner that the risk value calculation unit 113 can identify each identified person.
　次に、症状検出部１１２は、可視光画像データに基づいて人物の感染症の症状を検出する（ステップＳ１４）。なお、症状検出部１１２は、複数の人物の症状を検出した場合には、それぞれ特定した人物をリスク値算出部１１３が識別できる態様により、症状に関するデータを生成する。 Next, the symptom detection unit 112 detects the symptom of a person's infectious disease based on the visible light image data (step S14). When the symptom detection unit 112 detects the symptom of a plurality of persons, the symptom detection unit 112 generates data related to the symptom in such a manner that the risk value calculation unit 113 can identify each identified person.
　次に、リスク値算出部１１３は、温度測定部１１１から受け取った体表温度に関するデータと、症状検出部１１２から受け取った症状に関するデータとから、特定した人物の感染リスク値を算出する（ステップＳ１５）。 Next, the risk value calculation unit 113 calculates the infection risk value of the specified person from the data on the body surface temperature received from the temperature measurement unit 111 and the data on the symptom received from the symptom detection unit 112 (step S15). ).
　次に、出力部１１４は、リスク値算出部１１３が算出した感染リスク値を受け取り、受け取った感染リスク値を出力する（ステップＳ１６）。 Next, the output unit 114 receives the infection risk value calculated by the risk value calculation unit 113, and outputs the received infection risk value (step S16).
　以上、リスク値算出装置１１が実行する処理について説明した。なお、本実施形態にかかるリスク値算出方法は上述のフローチャートに限られない。例えば、ステップＳ１３とステップＳ１４とは並行して実行されてもよいし、ステップＳ１３の後にステップＳ１２が実行されてもよい。 The process executed by the risk value calculation device 11 has been described above. The risk value calculation method according to this embodiment is not limited to the above flowchart. For example, step S13 and step S14 may be executed in parallel, or step S12 may be executed after step S13.
　以上、実施形態１について説明した。上述のとおり、実施形態１にかかるリスク値算出装置１１は、可視光カメラから取得した可視光画像データとサーマルカメラから取得した熱画像データとを利用する。リスク値算出装置１１は、熱画像データから測定した人物の体表温度と、可視光画像データから検出した、かかる人物の症状と、を併せて感染リスク値を算出する。よって、本実施形態によれば、好適に感染リスクを判定できるリスク値算出装置、リスク値算出方法およびプログラムを提供することができる。 The embodiment 1 has been described above. As described above, the risk value calculation device 11 according to the first embodiment uses the visible light image data acquired from the visible light camera and the thermal image data acquired from the thermal camera. The risk value calculation device 11 calculates the infection risk value by combining the body surface temperature of the person measured from the thermal image data and the symptom of the person detected from the visible light image data. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program capable of suitably determining an infection risk.
　尚、リスク値算出装置１１は、図示しない構成としてプロセッサ及び記憶装置を有するものである。リスク値算出装置１１が有する記憶装置は、フラッシュメモリやＳＳＤ（Solid State Drive）などの不揮発性メモリを含む記憶装置を含む。 The risk value calculation device 11 has a processor and a storage device as a configuration (not shown). The storage device included in the risk value calculation device 11 includes a storage device including a flash memory and a non-volatile memory such as an SSD (Solid State Drive).
　リスク値算出装置１１が有する記憶装置には、本実施形態に係るリスク値算出方法を実行するためのコンピュータプログラム（以降、単にプログラムとも称する）が記憶されている。またプロセッサは、記憶装置からコンピュータプログラムをメモリへ読み込ませ、当該プログラムを実行する。 The storage device of the risk value calculation device 11 stores a computer program (hereinafter, also simply referred to as a program) for executing the risk value calculation method according to the present embodiment. The processor also reads a computer program from the storage device into the memory and executes the program.
　リスク値算出装置１１が有する各構成は、それぞれが専用のハードウェアで実現されていてもよい。また、各構成要素の一部又は全部は、汎用または専用の回路（circuitry）、プロセッサ等やこれらの組合せによって実現されてもよい。これらは、単一のチップによって構成されてもよいし、バスを介して接続される複数のチップによって構成されてもよい。各装置の各構成要素の一部又は全部は、上述した回路等とプログラムとの組合せによって実現されてもよい。また、プロセッサとして、ＣＰＵ（Central Processing Unit）、ＧＰＵ（Graphics Processing Unit）、ＦＰＧＡ（field-programmable gate array）等を用いることができる。 Each configuration of the risk value calculation device 11 may be realized by dedicated hardware. Further, a part or all of each component may be realized by a general-purpose or dedicated circuitry, a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. A part or all of each component of each device may be realized by the combination of the circuit or the like and the program described above. Further, as a processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (field-programmable gate array), or the like can be used.
　また、リスク値算出装置１１の各構成要素の一部又は全部が複数の演算装置や回路等により実現される場合には、複数の演算装置や回路等は、集中配置されてもよいし、分散配置されてもよい。例えば、演算装置や回路等は、クライアントサーバシステム、クラウドコンピューティングシステム等、各々が通信ネットワークを介して接続される形態として実現されてもよい。また、リスク値算出装置１１の機能がＳａａＳ（Software as a Service）形式で提供されてもよい。 Further, when a part or all of each component of the risk value calculation device 11 is realized by a plurality of arithmetic units, circuits, etc., the plurality of arithmetic units, circuits, etc. may be centrally arranged or distributed. It may be arranged. For example, the arithmetic unit, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client-server system and a cloud computing system. Further, the function of the risk value calculation device 11 may be provided in the SAAS (Software as a Service) format.
　＜実施形態２＞
　次に、実施形態２について説明する。図３は、実施形態２にかかるリスク値算出装置の構成を示すブロック図である。図３に示すリスク値算出装置１２は、ネットワーク５００を介して、ユーザ端末２１、可視光カメラ９１およびサーマルカメラ９２に互いに通信可能に接続している。ネットワーク５００は、例えばインターネットのようなワイドエリアネットワークまたは所定の施設内の回線のようなローカルエリアネットワークなどの通信網である。 <Embodiment 2>
Next, the second embodiment will be described. FIG. 3 is a block diagram showing a configuration of the risk value calculation device according to the second embodiment. The risk value calculation device 12 shown in FIG. 3 is communicably connected to the user terminal 21, the visible light camera 91, and the thermal camera 92 via the network 500. The network 500 is a communication network such as a wide area network such as the Internet or a local area network such as a line in a predetermined facility.
　可視光カメラ９１およびサーマルカメラ９２は、所定の施設９０内に設置され、ネットワーク５００を介してリスク値算出装置１２と通信可能に接続している。施設９０には人物が存在する。可視光カメラ９１およびサーマルカメラ９２は、施設９０における人物を含む内部の風景をそれぞれ撮影し、撮影して生成した画像データ（可視光画像データおよび熱画像データ）をそれぞれリスク値算出装置１２に送信する。 The visible light camera 91 and the thermal camera 92 are installed in a predetermined facility 90 and are communicably connected to the risk value calculation device 12 via the network 500. There is a person in the facility 90. The visible light camera 91 and the thermal camera 92 each photograph an internal landscape including a person in the facility 90, and transmit the image data (visible light image data and thermal image data) generated by the images to the risk value calculation device 12, respectively. do.
　ユーザ端末２１は、例えばパーソナルコンピューター、スマートフォンまたはタブレット端末等の情報処理端末である。ユーザ端末２１は、ネットワーク５００を介してリスク値算出装置１２と通信可能に接続しており、リスク値算出装置１２から感染リスク値を受け取る。ユーザ端末２１はリスク値算出装置１２から受け取った感染リスク値を表示して、ユーザ端末２１を操作するユーザに感染リスク値を通知する。ユーザは、ユーザ端末２１を介して施設９０に存在する人物の感染リスク値を把握できる。これにより例えばユーザは、施設９０に存在する人物に対する感染リスクを低減する活動を行うことができる。 The user terminal 21 is an information processing terminal such as a personal computer, a smartphone or a tablet terminal. The user terminal 21 is communicably connected to the risk value calculation device 12 via the network 500, and receives the infection risk value from the risk value calculation device 12. The user terminal 21 displays the infection risk value received from the risk value calculation device 12, and notifies the user who operates the user terminal 21 of the infection risk value. The user can grasp the infection risk value of the person existing in the facility 90 via the user terminal 21. As a result, for example, the user can perform an activity to reduce the risk of infection to a person existing in the facility 90.
　本実施形態にかかるリスク値算出装置１２は、記憶部１２０を含む点が、実施形態１にかかるリスク値算出装置１１と異なる。記憶部１２０は、ＥＰＲＯＭ（Erasable Programmable Read Only Memory）またはフラッシュメモリ等の不揮発メモリを含む記憶装置である。 The risk value calculation device 12 according to the present embodiment is different from the risk value calculation device 11 according to the first embodiment in that the storage unit 120 is included. The storage unit 120 is a storage device including a non-volatile memory such as an EPROM (ErasableProgrammableReadOnlyMemory) or a flash memory.
　記憶部１２０は、症状ＤＢ１２１を記憶する。症状ＤＢ１２１は、予め設定された疾病の症状に関する情報を含む。より具体的には、症状ＤＢ１２１は、予め設定された疾病の症状のうち、罹患者の姿勢に関連するものを含む。また症状ＤＢ１２１は、症状検出部１１２が抽出した人物の姿勢と照合できる態様の情報を含む。抽出した人物の姿勢と照合できる態様とは、例えば人物の姿勢パターンを示す画像データや、人物の姿勢パターンの特徴量を抽出した特徴量データである。症状ＤＢ１２１は、記憶する姿勢パターンに付随する症状属性情報が含まれていてもよい。症状属性情報は、症状の姿勢パターンそれぞれに対応する感染の可能性や症状の重篤度合いを示す情報である。記憶部１２０は、症状検出部１１２に対して症状ＤＢ１２１を供給する。 The storage unit 120 stores the symptom DB 121. The symptom DB 121 contains information about a preset symptom of the disease. More specifically, the symptom DB 121 includes preset symptoms of the disease that are related to the posture of the affected person. Further, the symptom DB 121 includes information on a mode that can be collated with the posture of the person extracted by the symptom detection unit 112. The mode that can be collated with the extracted posture of the person is, for example, image data showing the posture pattern of the person or feature amount data obtained by extracting the feature amount of the posture pattern of the person. The symptom DB 121 may include symptom attribute information associated with the memorized posture pattern. The symptom attribute information is information indicating the possibility of infection and the severity of the symptom corresponding to each symptom posture pattern. The storage unit 120 supplies the symptom DB 121 to the symptom detection unit 112.
　本実施形態にかかる症状検出部１１２は、記憶部１２０から症状ＤＢ１２１を読み取り、読み取った症状ＤＢ１２１と、抽出した人物の姿勢とを照合する。症状検出部１１２は、照合の結果、抽出した人物の姿勢が症状ＤＢ１２１に含まれる症状を示す姿勢パターンと一致するか否かを判定する。症状検出部１１２は、抽出した人物の姿勢が症状ＤＢ１２１に含まれると判定した場合、この人物の姿勢から症状を検出する。症状検出部１１２は、例えば、人物の姿勢と症状ＤＢ１２１に含まれる姿勢パターンとが所定期間内に所定の割合以上に一致した場合に、症状を検出する。具体的には、例えば症状検出部１１２は、６０秒間の内の１０秒間に症状を示す姿勢パターンに一致した場合に、症状を検出する。 The symptom detection unit 112 according to the present embodiment reads the symptom DB 121 from the storage unit 120, and collates the read symptom DB 121 with the extracted posture of the person. As a result of the collation, the symptom detection unit 112 determines whether or not the posture of the extracted person matches the posture pattern indicating the symptom included in the symptom DB 121. When the symptom detection unit 112 determines that the extracted posture of the person is included in the symptom DB 121, the symptom detection unit 112 detects the symptom from the posture of this person. The symptom detection unit 112 detects a symptom, for example, when the posture of the person and the posture pattern included in the symptom DB 121 match at a predetermined ratio or more within a predetermined period. Specifically, for example, the symptom detection unit 112 detects a symptom when it matches a posture pattern showing the symptom in 10 seconds out of 60 seconds.
　症状ＤＢ１２１が症状属性情報を含む場合、症状検出部１１２は、検出した症状に併せて、症状属性情報をリスク値算出部１１３に供給してもよい。これにより、リスク値算出装置１２は、算出する感染リスク値の精度を向上させることができる。 When the symptom DB 121 includes the symptom attribute information, the symptom detection unit 112 may supply the symptom attribute information to the risk value calculation unit 113 together with the detected symptom. As a result, the risk value calculation device 12 can improve the accuracy of the calculated infection risk value.
　次に、図４を参照して実施形態２にかかるリスク値算出装置１２の処理について説明する。図４は、実施形態２にかかるリスク算出方法のフローチャートである。図４に示すフローチャートは、ステップＳ１３とステップＳ１５の間の処理が、ステップＳ１４に代えてステップＳ２１およびステップＳ２２となっている点が、図２に示す実施形態１にかかるフローチャートと異なる。 Next, the process of the risk value calculation device 12 according to the second embodiment will be described with reference to FIG. FIG. 4 is a flowchart of the risk calculation method according to the second embodiment. The flowchart shown in FIG. 4 is different from the flowchart according to the first embodiment shown in FIG. 2 in that the processing between steps S13 and S15 is step S21 and step S22 instead of step S14.
　ステップＳ１１からステップＳ１３は、図２に示したフローチャートと同様である。ステップＳ２１において、症状検出部１１２は、画像データ取得部１１０から受け取った可視光画像データから、特定した人物の姿勢を抽出する（ステップＳ２１）。 Steps S11 to S13 are the same as the flowchart shown in FIG. In step S21, the symptom detection unit 112 extracts the posture of the specified person from the visible light image data received from the image data acquisition unit 110 (step S21).
　次に、症状検出部１１２は、記憶部１２０から症状ＤＢ１２１を読み取り、抽出した人物の姿勢と症状ＤＢ１２１を照合し、症状を検出する（ステップＳ２２）。抽出した人物の姿勢と症状ＤＢ１２１との照合の結果、一致すると判定した場合、症状検出部１１２は抽出した人物の姿勢から症状を検出する。抽出した人物の姿勢と症状ＤＢ１２１との照合の結果、一致すると判定しない場合、症状検出部１１２は抽出した人物の姿勢から症状を検出しない。症状検出部１１２は、検出した症状に関するデータをリスク値算出部１１３に供給する。次にリスク値算出装置１２は、ステップＳ１５に進む。ステップＳ１５以降の処理は、図２に示したフローチャートと同様である。 Next, the symptom detection unit 112 reads the symptom DB 121 from the storage unit 120, collates the extracted posture of the person with the symptom DB 121, and detects the symptom (step S22). As a result of collation between the posture of the extracted person and the symptom DB 121, if it is determined that they match, the symptom detection unit 112 detects the symptom from the posture of the extracted person. As a result of collation between the posture of the extracted person and the symptom DB 121, if it is not determined that they match, the symptom detection unit 112 does not detect the symptom from the posture of the extracted person. The symptom detection unit 112 supplies data related to the detected symptom to the risk value calculation unit 113. Next, the risk value calculation device 12 proceeds to step S15. The processing after step S15 is the same as the flowchart shown in FIG.
　以上、実施形態2について説明したが、リスク値算出装置１２は上述の構成に限られない。図３において可視光カメラ９１とサーマルカメラ９２を１つずつ示した。しかし、リスク値算出装置１２は、それぞれ複数の可視光カメラ９１およびサーマルカメラ９２から画像データを取得するものであってもよい。またこの場合、可視光カメラ９１とサーマルカメラ９２とは構成される数が異なっていてもよい。 Although the second embodiment has been described above, the risk value calculation device 12 is not limited to the above configuration. In FIG. 3, a visible light camera 91 and a thermal camera 92 are shown one by one. However, the risk value calculation device 12 may acquire image data from a plurality of visible light cameras 91 and a thermal camera 92, respectively. Further, in this case, the visible light camera 91 and the thermal camera 92 may be configured in different numbers.
　以上、実施形態2について説明した。上述のとおり、実施形態２にかかるリスク値算出装置１２は、抽出した人物の姿勢と症状ＤＢ１２１の情報とを照合する。これにより、リスク値算出装置１２は、精度よく感染リスク値を算出できる。なお、症状ＤＢ１２１は更新可能に構成されていてもよい。これにより、リスク値算出装置１２は、流行している疾病の種類に応じた症状を照合できる。よって、本実施形態によれば、好適かつ柔軟に感染リスクを判定できるリスク値算出装置、リスク値算出方法およびプログラムを提供することができる。 The embodiment 2 has been described above. As described above, the risk value calculation device 12 according to the second embodiment collates the extracted posture of the person with the information of the symptom DB 121. As a result, the risk value calculation device 12 can accurately calculate the infection risk value. The symptom DB 121 may be configured to be updatable. As a result, the risk value calculation device 12 can collate the symptoms according to the type of the prevalent disease. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can appropriately and flexibly determine the infection risk.
　＜実施形態３＞
　次に、実施形態３について説明する。図５は、実施形態３にかかるリスク値算出装置の構成を示すブロック図である。図５に示すリスク値算出装置１３は、混雑度算出部１１５を含む点が、上述のリスク値算出装置１１およびリスク値算出装置１２と異なる。本実施形態にかかる画像データ取得部１１０は、取得した可視光画像データを混雑度算出部１１５にも供給する。 <Embodiment 3>
Next, the third embodiment will be described. FIG. 5 is a block diagram showing a configuration of the risk value calculation device according to the third embodiment. The risk value calculation device 13 shown in FIG. 5 is different from the risk value calculation device 11 and the risk value calculation device 12 described above in that the congestion degree calculation unit 115 is included. The image data acquisition unit 110 according to the present embodiment also supplies the acquired visible light image data to the congestion degree calculation unit 115.
　混雑度算出部１１５は、画像データ取得部１１０から可視光画像データを受け取り、受け取った可視光画像データから空間の混雑度を算出する。空間の混雑度は、所定空間に存在する人数により算出される。混雑度が高い場合は、混雑度が低い場合に比較して、その空間に存在する人数が多い。すなわち、混雑度算出部１１５は、所定空間の人数を数えることにより混雑度を算出しうる。混雑度算出部１１５は、例えば可視光画像データ全体を所定空間として設定してもよいし、可視光画像データに含まれる画像の一部分を所定空間として設定してもよい。また混雑度算出部１１５は可視光画像データに含まれる空間を複数に分割し、分割した空間ごとの混雑度を算出してもよい。混雑度算出部１１５は、算出した混雑度を、リスク値算出部１１３に供給する。 The congestion degree calculation unit 115 receives visible light image data from the image data acquisition unit 110, and calculates the degree of congestion in the space from the received visible light image data. The degree of congestion in a space is calculated by the number of people existing in a predetermined space. When the degree of congestion is high, the number of people present in the space is larger than when the degree of congestion is low. That is, the congestion degree calculation unit 115 can calculate the congestion degree by counting the number of people in the predetermined space. For example, the congestion degree calculation unit 115 may set the entire visible light image data as a predetermined space, or may set a part of the image included in the visible light image data as a predetermined space. Further, the congestion degree calculation unit 115 may divide the space included in the visible light image data into a plurality of spaces and calculate the congestion degree for each divided space. The congestion degree calculation unit 115 supplies the calculated congestion degree to the risk value calculation unit 113.
　また混雑度算出部１１５は、上述の方法に代えて、所定の空間に含まれる人物を群衆として扱い、群衆の状態から混雑度を算出してもよい。群衆とは、所定の空間において複数の人物が重なり合って見える状態を示す。この場合、混雑度算出部１１５は、群衆を検知し、検知した群衆の混雑状態を識別する。これにより、混雑度算出部１１５は混雑度を算出する。より具体的には、例えば混雑度算出部１１５は、可視光画像データの画像サイズより小さい所定の局所画像を抽出し、抽出した局所画像における群衆の混雑状態を判定する。かかる混雑状態の判定に際して、混雑度算出部１１５は例えば機械学習により生成された識別器を利用し得る。このような手段を採用することにより、混雑度算出部１１５は、画像内の正確な人数を数えることなく、混雑度を算出できる。 Further, instead of the above method, the congestion degree calculation unit 115 may treat a person included in a predetermined space as a crowd and calculate the congestion degree from the state of the crowd. A crowd refers to a state in which a plurality of people appear to overlap in a predetermined space. In this case, the congestion degree calculation unit 115 detects the crowd and identifies the crowded state of the detected crowd. As a result, the congestion degree calculation unit 115 calculates the congestion degree. More specifically, for example, the congestion degree calculation unit 115 extracts a predetermined local image smaller than the image size of the visible light image data, and determines the congestion state of the crowd in the extracted local image. In determining the congestion state, the congestion degree calculation unit 115 may use, for example, a classifier generated by machine learning. By adopting such a means, the congestion degree calculation unit 115 can calculate the congestion degree without counting the exact number of people in the image.
　なお、上述した例において、混雑度算出部１１５は、混雑度の算出に際して可視光画像データを利用した。しかし、混雑度算出部１１５が行う混雑度の算出において利用されるデータは可視光画像データに限られない。すなわち混雑度算出部１１５は熱画像データを利用して混雑度の算出を行ってもよい。 In the above example, the congestion degree calculation unit 115 used the visible light image data when calculating the congestion degree. However, the data used in the calculation of the degree of congestion performed by the degree of congestion calculation unit 115 is not limited to the visible light image data. That is, the congestion degree calculation unit 115 may calculate the congestion degree by using the thermal image data.
　リスク値算出部１１３は、特定した人物の体表温度および症状に加え、可視光画像データにおいて人物が含まれる所定空間の混雑度をさらに加味して感染リスク値を算出する。すなわち、リスク値算出部１１３は、混雑度が比較的に高い空間に存在する人物の感染リスク値を、混雑度が比較的に低い空間に存在する人物の感染リスク値より高く算出する。このように混雑度を加味して感染リスク値を算出することにより、リスク値算出装置１３は、感染リスク値の精度を向上させることができる。 The risk value calculation unit 113 calculates the infection risk value by further considering the degree of congestion in the predetermined space including the person in the visible light image data in addition to the body surface temperature and the symptom of the specified person. That is, the risk value calculation unit 113 calculates the infection risk value of a person existing in a space having a relatively high degree of congestion higher than the infection risk value of a person existing in a space having a relatively low degree of congestion. By calculating the infection risk value in consideration of the degree of congestion in this way, the risk value calculation device 13 can improve the accuracy of the infection risk value.
　リスク値算出部１１３は、以下のように周辺の人物の状況をさらに加味して感染リスク値を算出してもよい。リスク値算出部１１３は、人物の周辺に存在する周辺人物の体表温度と症状とをさらに加味して人物の感染リスク値を算出してもよい。より具体的には、例えば、感染リスク値を算出する人物の近傍に、周辺人物が存在している場合において、周辺人物の体表温度が平熱を超えている場合や、周辺人物の姿勢が症状の姿勢パターンと一致している場合には、リスク値算出部１１３はこれを加味し、比較的に高い感染リスク値を算出する。 The risk value calculation unit 113 may calculate the infection risk value in consideration of the situation of surrounding persons as follows. The risk value calculation unit 113 may calculate the infection risk value of a person by further considering the body surface temperature and the symptom of the surrounding person existing around the person. More specifically, for example, when there is a peripheral person in the vicinity of the person who calculates the infection risk value, the body surface temperature of the peripheral person exceeds normal temperature, or the posture of the peripheral person is a symptom. If it matches the posture pattern of, the risk value calculation unit 113 takes this into consideration and calculates a relatively high infection risk value.
　また、周辺人物の感染リスク値が既に算出されている場合、リスク値算出部１１３は、周辺人物の感染リスク値を加味して感染リスク値を算出する。例えば、周辺人物の感染リスク値が第１リスク値（例えば０．７）の場合、リスク値算出部１１３は、周辺人物の感染リスク値が第２リスク値（例えば０．３）の場合よりも比較的に高く感染リスク値を算出する。 If the infection risk value of a peripheral person has already been calculated, the risk value calculation unit 113 calculates the infection risk value in consideration of the infection risk value of the peripheral person. For example, when the infection risk value of a peripheral person is the first risk value (for example, 0.7), the risk value calculation unit 113 is higher than the case where the infection risk value of the peripheral person is the second risk value (for example, 0.3). Calculate the infection risk value relatively high.
　またリスク値算出部１１３は、人物の周辺に存在する周辺人物との距離をさらに加味して人物の感染リスク値を算出してもよい。より具体的には、例えば、周辺人物との距離が第１距離（例えば１メートル）の場合、リスク値算出部１１３は、周辺人物の感染リスク値が第１距離より遠い第２距離（例えば３メートル）の場合に算出する感染リスク値よりも比較的に高く算出する。上述の内容を踏まえ、例えば感染リスク値は次のように算出されうる。まず感染リスク値を算出するための各要素は、次のように０から１の間の値に設定される。例えば、人物の体表温度は、複数のレベルに分類され、それぞれの区分が、０から１の範囲のうち予め設定された値に設定される。また人物の症状は、例えば該当する症状ごとに０から１の範囲のうち予め設定された値に設定される。また混雑度は、混雑しているほど１に近く、混雑していないほど０に近い値になるように正規化される。感染リスク値は、このように設定されたそれぞれの値の平均値を取ることにより算出される。周辺人物の体表温度および周辺人物の症状についても同様に０から１の間の値に設定される。そしてリスク値算出部１１３は、感染リスク値としてこれらの要素の平均値を算出する。なお、リスク値算出部１１３は平均値を算出する際に、特定の要素の影響が比較的に大きく反映されるように重み付けを行ってもよい。なお、上述の感染リスク値は、所定の人物の周囲に存在する周辺人物へ感染が拡がるリスクを示した。しかしリスク値算出部１１３は、周辺人物から所定の人物へ感染が拡がるリスクを算出してもよいし、所定の群衆において感染が拡がるリスクを算出してもよい。上述の感染リスク値の算出方法は一例であって、感染リスク値の算出方法は上述のものに限定されない。 Further, the risk value calculation unit 113 may calculate the infection risk value of the person by further considering the distance to the surrounding person existing in the vicinity of the person. More specifically, for example, when the distance to the surrounding person is the first distance (for example, 1 meter), the risk value calculation unit 113 has the second distance (for example, 3) in which the infection risk value of the peripheral person is farther than the first distance. Calculated relatively higher than the infection risk value calculated in the case of (meter). Based on the above contents, for example, the infection risk value can be calculated as follows. First, each element for calculating the infection risk value is set to a value between 0 and 1 as follows. For example, the body surface temperature of a person is classified into a plurality of levels, and each classification is set to a preset value in the range of 0 to 1. Further, the symptom of the person is set to a preset value in the range of 0 to 1, for example, for each corresponding symptom. Further, the degree of congestion is normalized so that the more crowded it is, the closer it is to 1, and the less crowded it is, the closer it is to 0. The infection risk value is calculated by taking the average value of each value set in this way. Similarly, the body surface temperature of the surrounding person and the symptom of the surrounding person are set to a value between 0 and 1. Then, the risk value calculation unit 113 calculates the average value of these elements as the infection risk value. The risk value calculation unit 113 may perform weighting so that the influence of a specific element is reflected relatively large when calculating the average value. The above-mentioned infection risk value indicates the risk that the infection spreads to the surrounding persons existing around the predetermined person. However, the risk value calculation unit 113 may calculate the risk of spreading the infection from a peripheral person to a predetermined person, or may calculate the risk of spreading the infection in a predetermined crowd. The above-mentioned method for calculating the infection risk value is an example, and the method for calculating the infection risk value is not limited to the above-mentioned method.
　次に、図６を参照して実施形態３にかかるリスク値算出装置１３の処理について説明する。図６は、実施形態３にかかるリスク算出方法のフローチャートである。図６に示すフローチャートは、ステップＳ１５に代えてステップＳ３１およびステップＳ３２を有する点が、図４に示した実施形態２にかかるフローチャートと異なる。 Next, the process of the risk value calculation device 13 according to the third embodiment will be described with reference to FIG. FIG. 6 is a flowchart of the risk calculation method according to the third embodiment. The flowchart shown in FIG. 6 is different from the flowchart according to the second embodiment shown in FIG. 4 in that it has steps S31 and S32 instead of step S15.
　ステップＳ２２の後、ステップＳ３１において、混雑度算出部１１５は、可視光画像データから混雑度を算出する（ステップＳ３１）。 After step S22, in step S31, the congestion degree calculation unit 115 calculates the congestion degree from the visible light image data (step S31).
　次に、リスク値算出部１１３は、温度測定部１１１から受け取った体表温度に関するデータと、症状検出部１１２から受け取った症状に関するデータと、混雑度算出部１１５から受け取った混雑度とから、特定した人物の感染リスク値を算出する（ステップＳ３２）。リスク値算出部１１３が感染リスク値を算出すると、出力部１１４はリスク値算出部１１３から受け取った感染リスク値を出力する（ステップＳ１６）。 Next, the risk value calculation unit 113 specifies from the data on the body surface temperature received from the temperature measurement unit 111, the data on the symptom received from the symptom detection unit 112, and the congestion degree received from the congestion degree calculation unit 115. The infection risk value of the person who has been infected is calculated (step S32). When the risk value calculation unit 113 calculates the infection risk value, the output unit 114 outputs the infection risk value received from the risk value calculation unit 113 (step S16).
　以上、実施形態３にかかるフローチャートについて説明した。なお、ステップＳ３１は、ステップＳ１１とステップＳ３２の間において、図６に示した順と異なるタイミングに実行されてもよい。また体表温度を測定する処理（ステップＳ１３）と、人物の症状を検出する処理（ステップＳ２１およびステップＳ２２）と、混雑度を算出する処理（ステップＳ３１）とは、処理の順序を問わない。またこれらの処理は並行して実行されてもよい。 The flowchart according to the third embodiment has been described above. Note that step S31 may be executed between steps S11 and S32 at a timing different from the order shown in FIG. The order of the processes of measuring the body surface temperature (step S13), detecting the symptoms of a person (steps S21 and S22), and calculating the degree of congestion (step S31) does not matter. Further, these processes may be executed in parallel.
　以上、実施形態３について説明した。実施形態３にかかるリスク値算出装置１３は、混雑度を算出し、算出した混雑度を加味してリスク値を算出する。これにより、リスク値算出装置１２は、精度よく感染リスク値を算出できる。またリスク値算出部１１３は、感染リスク値を算出する人物の周辺人物の状況をさらに加味することにより、さらに精度よく感染リスク値を算出できる。よって、本実施形態によれば、好適かつ精度よく感染リスクを判定できるリスク値算出装置、リスク値算出方法およびプログラムを提供することができる。 The embodiment 3 has been described above. The risk value calculation device 13 according to the third embodiment calculates the degree of congestion, and calculates the risk value by adding the calculated degree of congestion. As a result, the risk value calculation device 12 can accurately calculate the infection risk value. Further, the risk value calculation unit 113 can calculate the infection risk value more accurately by further considering the situation of the people around the person who calculates the infection risk value. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can determine the infection risk in a suitable and accurate manner.
　＜実施形態４＞
　次に、実施形態４について説明する。実施形態４は、リスク値算出装置と認証装置とを少なくとも含むシステムである。図７は、実施形態４にかかるリスク算出システムの構成を示すブロック図である。図７には、リスク値算出システム７００が示されている。リスク値算出システム７００は、リスク値算出装置１４、認証装置２００、ユーザ端末２１、可視光カメラ９１およびサーマルカメラ９２を含む。 <Embodiment 4>
Next, the fourth embodiment will be described. The fourth embodiment is a system including at least a risk value calculation device and an authentication device. FIG. 7 is a block diagram showing a configuration of the risk calculation system according to the fourth embodiment. FIG. 7 shows the risk value calculation system 700. The risk value calculation system 700 includes a risk value calculation device 14, an authentication device 200, a user terminal 21, a visible light camera 91, and a thermal camera 92.
　本実施形態にかかるリスク値算出装置１４は、ネットワーク５００を介して認証装置２００に通信可能に接続している。リスク値算出装置１４は、人物の特定を行う際に認証装置２００と連携して人物についての認証を併せて行う。認証を行うことにより、リスク値算出装置１１は特定した人物に紐づく属性情報を利用できる。これにより、リスク値算出装置１１は、特定した人物における感染リスク値の履歴を記憶したり、算出した感染リスク値を個人に直接通知したりできる。 The risk value calculation device 14 according to the present embodiment is communicably connected to the authentication device 200 via the network 500. The risk value calculation device 14 also authenticates a person in cooperation with the authentication device 200 when identifying the person. By performing authentication, the risk value calculation device 11 can use the attribute information associated with the specified person. As a result, the risk value calculation device 11 can store the history of the infection risk value in the specified person and directly notify the individual of the calculated infection risk value.
　リスク値算出装置１４が有する記憶部１２０は、属性情報１２２を記憶している。属性情報は、認証にかかる人物に付随する属性情報が含まれる。属性情報１２２は例えば、人物の氏名、連絡先などの個人情報を含む。また属性情報１２２は、認証にかかる人物の既往歴や持病に関する情報が含まれていてもよい。リスク値算出装置１４は、感染リスク値を算出する際に、属性情報を利用してもよい。例えば、リスク値算出部１１３は、免疫系の持病を有する人物について、感染リスク値を比較的に高く算出するものであってもよい。 The storage unit 120 included in the risk value calculation device 14 stores the attribute information 122. The attribute information includes the attribute information associated with the person involved in the authentication. The attribute information 122 includes personal information such as a person's name and contact information, for example. Further, the attribute information 122 may include information on the medical history and chronic illness of the person involved in the authentication. The risk value calculation device 14 may use the attribute information when calculating the infection risk value. For example, the risk value calculation unit 113 may calculate the infection risk value relatively high for a person having a chronic disease of the immune system.
　認証装置２００は、ネットワーク５００を介してリスク値算出装置１４と通信可能に接続している。認証装置２００は、リスク値算出装置１４と連携して人物の顔画像データから人物の認証を行う。より具体的には、認証装置２００はリスク値算出装置１４から可視光画像データを受け取り、受け取った可視光画像データに含まれる顔画像についての認証を行う。また認証装置２００は認証の結果をリスク値算出装置１４に供給する。 The authentication device 200 is communicably connected to the risk value calculation device 14 via the network 500. The authentication device 200 cooperates with the risk value calculation device 14 to authenticate a person from the face image data of the person. More specifically, the authentication device 200 receives the visible light image data from the risk value calculation device 14, and authenticates the face image included in the received visible light image data. Further, the authentication device 200 supplies the authentication result to the risk value calculation device 14.
　次に、図８を参照して、認証装置２００の構成について詳細に説明する。図８は、認証装置２００の構成を示すブロック図である。認証装置２００は、顔特徴ＤＢ２１０、顔検出部２２０、特徴点抽出部２３０、登録部２４０及び認証部２５０を有する。 Next, the configuration of the authentication device 200 will be described in detail with reference to FIG. FIG. 8 is a block diagram showing the configuration of the authentication device 200. The authentication device 200 includes a face feature DB 210, a face detection unit 220, a feature point extraction unit 230, a registration unit 240, and an authentication unit 250.
　顔特徴ＤＢ２１０は、人物のユーザＩＤと当該人物の顔特徴情報とを対応付けて記憶する顔特徴データベースである。顔検出部２２０は、撮影画像が含む顔領域を検出し、特徴点抽出部２３０に出力する。特徴点抽出部２３０は、顔検出部２２０が検出した顔領域から特徴点を抽出し、登録部２４０に顔特徴情報を出力する。顔特徴情報は、抽出した特徴点の集合である。 The face feature DB 210 is a face feature database that stores a user ID of a person in association with the face feature information of the person. The face detection unit 220 detects the face region included in the captured image and outputs it to the feature point extraction unit 230. The feature point extraction unit 230 extracts feature points from the face region detected by the face detection unit 220, and outputs face feature information to the registration unit 240. Face feature information is a set of extracted feature points.
　登録部２４０は、顔特徴情報の登録に際して、ユーザＩＤを新規に発行する。登録部２４０は、発行したユーザＩＤと、登録画像から抽出した顔特徴情報と、を対応付けて顔特徴ＤＢ２１０に登録する。認証部２５０は、顔画像から抽出された顔特徴情報と、顔特徴ＤＢ２１０内の顔特徴情報と、の照合を行う。認証部２５０は、顔特徴情報が一致している場合、顔認証が成功したと判断し、顔特徴情報が不一致の場合、顔認証が失敗したと判断する。認証部２５０は、顔認証の成否をリスク値算出装置１４に返信する。顔特徴情報の一致の有無は、認証の成否に対応する。また、認証部２５０は、顔認証に成功した場合、当該成功した顔特徴情報に対応付けられたユーザＩＤを特定し、特定されたユーザＩＤと認証成功の旨とを含めた認証結果をリスク値算出装置１４に返信する。 The registration unit 240 newly issues a user ID when registering facial feature information. The registration unit 240 registers the issued user ID and the face feature information extracted from the registered image in the face feature DB 210 in association with each other. The authentication unit 250 collates the face feature information extracted from the face image with the face feature information in the face feature DB 210. If the face feature information matches, the authentication unit 250 determines that the face recognition was successful, and if the face feature information does not match, determines that the face recognition has failed. The authentication unit 250 returns the success or failure of face authentication to the risk value calculation device 14. The presence or absence of matching of facial feature information corresponds to the success or failure of authentication. Further, when the face authentication is successful, the authentication unit 250 identifies the user ID associated with the successful face feature information, and sets the authentication result including the specified user ID and the fact that the authentication is successful as a risk value. Reply to the calculation device 14.
　以上、実施形態４について説明したが、実施形態４にかかるリスク値算出システム７００は上述の構成に限られない。例えばリスク値算出システム７００はリスク値算出装置１４と認証装置２００とが一体となったものであってもよい。リスク値算出システム７００において、ユーザ端末２１は認証にかかる人物の端末であってもよい。その場合、ユーザ端末２１は認証にかかる複数の人物それぞれが有するものである。したがって、リスク値算出システム７００は、認証にかかる複数の人物に対応した複数のユーザ端末２１を有し得る。 Although the fourth embodiment has been described above, the risk value calculation system 700 according to the fourth embodiment is not limited to the above configuration. For example, the risk value calculation system 700 may be a combination of the risk value calculation device 14 and the authentication device 200. In the risk value calculation system 700, the user terminal 21 may be a terminal of a person to be authenticated. In that case, the user terminal 21 is possessed by each of the plurality of persons involved in the authentication. Therefore, the risk value calculation system 700 may have a plurality of user terminals 21 corresponding to a plurality of persons involved in authentication.
　以上、実施形態４について説明した。実施形態４にかかるリスク値算出システム７００は、人物の認証を行い、認証にかかる人物に対する感染リスク値を算出できる。よってリスク値算出システム７００は個人情報を加味した感染リスク値の算出を行うことができる。あるいはリスク値算出システム７００は、算出した感染リスク値を個人に通知できる。よって、本実施形態によれば、個人情報を配慮したうえで好適に感染リスクを判定できるリスク値算出装置、リスク値算出方法およびプログラムを提供することができる。 The embodiment 4 has been described above. The risk value calculation system 700 according to the fourth embodiment can authenticate a person and calculate an infection risk value for the person to be authenticated. Therefore, the risk value calculation system 700 can calculate the infection risk value in consideration of personal information. Alternatively, the risk value calculation system 700 can notify the individual of the calculated infection risk value. Therefore, according to the present embodiment, it is possible to provide a risk value calculation device, a risk value calculation method, and a program that can suitably determine an infection risk in consideration of personal information.
　なお、上述したプログラムは、様々なタイプの非一時的なコンピュータ可読媒体を用いて格納され、コンピュータに供給することができる。非一時的なコンピュータ可読媒体は、様々なタイプの実体のある記録媒体を含む。非一時的なコンピュータ可読媒体の例は、磁気記録媒体（例えばフレキシブルディスク、磁気テープ、ハードディスクドライブ）、光磁気記録媒体（例えば光磁気ディスク）、ＣＤ－ＲＯＭ（Read Only Memory）ＣＤ－Ｒ、ＣＤ－Ｒ／Ｗ、半導体メモリ（例えば、マスクＲＯＭ、ＰＲＯＭ（Programmable ROM）、ＥＰＲＯＭ（Erasable PROM）、フラッシュＲＯＭ、ＲＡＭ（Random Access Memory））を含む。また、プログラムは、様々なタイプの一時的なコンピュータ可読媒体によってコンピュータに供給されてもよい。一時的なコンピュータ可読媒体の例は、電気信号、光信号、及び電磁波を含む。一時的なコンピュータ可読媒体は、電線及び光ファイバ等の有線通信路、又は無線通信路を介して、プログラムをコンピュータに供給できる。 The above-mentioned program can be stored in various types of non-temporary computer-readable media and supplied to the computer. Non-temporary computer-readable media include various types of tangible recording media. Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), optomagnetic recording media (eg, optomagnetic disks), CD-ROM (Read Only Memory) CD-R, CDs. -R / W, including semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (RandomAccessMemory)). The program may also be supplied to the computer by various types of temporary computer-readable media. Examples of temporary computer readable media include electrical, optical, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.
　なお、本発明は上記実施形態に限られたものではなく、趣旨を逸脱しない範囲で適宜変更することが可能である。 The present invention is not limited to the above embodiment, and can be appropriately modified without departing from the spirit.
　上記の実施形態の一部又は全部は、以下の付記のようにも記載され得るが、以下には限られない。
（付記１）
　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する画像データ取得手段と、
　前記可視光画像データおよび前記熱画像データに含まれる人物を特定し、特定した前記人物の体表温度を測定する温度測定手段と、
　前記可視光画像データに基づいて前記人物の感染症の症状を検出する症状検出手段と、
　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出するリスク値算出手段と、
　前記感染リスク値を出力する出力手段と、を備える
リスク値算出装置。
（付記２）
　前記症状検出手段は、前記人物の姿勢から前記症状を検出する、
付記１に記載のリスク値算出装置。
（付記３）
　前記感染症の症状に関連する姿勢パターンを記憶する記憶部をさらに備え、
　前記症状検出手段は、前記人物の姿勢と前記姿勢パターンとを照合することにより前記症状を検出する、
付記２に記載のリスク値算出装置。
（付記４）
　前記症状検出手段は、前記人物の姿勢と前記姿勢パターンとが所定期間内に所定の割合以上に一致した場合に、前記症状を検出する、
付記３に記載のリスク値算出装置。
（付記５）
　前記記憶部は、所定の肺炎の症状に関連する前記姿勢パターンを記憶する、
付記３または４に記載のリスク値算出装置。
（付記６）
　前記可視光画像データから空間の混雑度を算出する混雑度算出手段をさらに備え、
　リスク値算出手段は、前記可視光画像データにおいて前記人物が含まれる所定空間の混雑度をさらに加味して前記感染リスク値を算出する、
付記１～５のいずれか一項に記載のリスク値算出装置。
（付記７）
　前記混雑度算出手段は、所定空間の人数に基づいて前記混雑度を算出する、
付記６に記載のリスク値算出装置。
（付記８）
　前記リスク値算出手段は、前記人物の周辺に存在する周辺人物の前記体表温度と前記症状とをさらに加味して前記人物の前記前記感染リスク値を算出する、
付記６または７に記載のリスク値算出装置。
（付記９）
　前記リスク値算出手段は、前記周辺人物の前記感染リスク値が第１リスク値の場合に算出する前記人物の感染リスク値は、前記周辺人物の前記感染リスク値が前記第１リスク値より低い第２リスク値の場合に算出する感染リスク値よりも比較的に高く算出する、
付記８に記載のリスク値算出装置。
（付記１０）
　前記リスク値算出手段は、前記人物の周辺に存在する周辺人物との距離をさらに加味して前記人物の前記前記感染リスク値を算出する、
付記６～９のいずれか一項に記載のリスク値算出装置。
（付記１１）
　前記リスク値算出手段は、前記周辺人物の距離が第１距離の場合に算出する前記人物の感染リスク値は、前記周辺人物の前記感染リスク値が前記第１距離より遠い第２距離の場合に算出する感染リスク値よりも比較的に高く算出する、
付記１０に記載のリスク値算出装置。
（付記１２）
　前記可視光画像データから人物の認証を行う認証装置と、
　前記認証にかかる前記人物の感染リスク値を算出して出力する付記１～１１のいずれか一項に記載のリスク値算出装置と、を備える
　リスク値算出システム。
（付記１３）
　コンピュータが、
　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得し、
　前記可視光画像データおよび前記熱画像データに含まれる人物を特定し、
　特定した前記人物の体表温度を測定し、
　前記可視光画像データに基づいて前記人物の感染症の症状を検出し、
　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出し、
　前記感染リスク値を出力する、
リスク値算出方法。
（付記１４）
　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する処理と、
　前記可視光画像データおよび前記熱画像データに含まれる人物を特定する処理と、
　特定した前記人物の体表温度を測定する処理と、
　前記可視光画像データに基づいて前記人物の感染症の症状を検出する処理と、
　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出する処理と、
　前記感染リスク値を出力する処理と、
を、コンピュータに実行させるリスク値算出プログラムが格納された非一時的なコンピュータ可読媒体。 Some or all of the above embodiments may also be described, but not limited to:
(Appendix 1)
An image data acquisition means for acquiring visible light image data generated by a visible light camera and thermal image data generated by an infrared camera having a shooting range corresponding to at least a part of the visible light image data.
A temperature measuring means for identifying a person included in the visible light image data and the thermal image data and measuring the body surface temperature of the specified person.
A symptom detecting means for detecting a symptom of an infectious disease of the person based on the visible light image data, and a symptom detecting means.
A risk value calculating means for calculating an infection risk value of the person based on the body surface temperature and the symptom, and a risk value calculating means.
A risk value calculation device including an output means for outputting the infection risk value.
(Appendix 2)
The symptom detecting means detects the symptom from the posture of the person.
The risk value calculation device according to Appendix 1.
(Appendix 3)
Further equipped with a storage unit for storing postural patterns associated with the symptoms of the infectious disease.
The symptom detecting means detects the symptom by collating the posture of the person with the posture pattern.
The risk value calculation device described in Appendix 2.
(Appendix 4)
The symptom detecting means detects the symptom when the posture of the person and the posture pattern match at a predetermined ratio or more within a predetermined period.
The risk value calculation device described in Appendix 3.
(Appendix 5)
The storage unit stores the posture pattern associated with a predetermined pneumonia symptom.
The risk value calculation device according to Appendix 3 or 4.
(Appendix 6)
Further provided with a congestion degree calculation means for calculating the congestion degree of the space from the visible light image data is provided.
The risk value calculating means calculates the infection risk value by further adding the degree of congestion of the predetermined space including the person in the visible light image data.
The risk value calculation device according to any one of Supplementary note 1 to 5.
(Appendix 7)
The congestion degree calculation means calculates the congestion degree based on the number of people in a predetermined space.
The risk value calculation device according to Appendix 6.
(Appendix 8)
The risk value calculating means calculates the infection risk value of the person by further considering the body surface temperature of the surrounding person existing around the person and the symptom.
The risk value calculation device according to Appendix 6 or 7.
(Appendix 9)
The risk value calculating means calculates when the infection risk value of the peripheral person is the first risk value, the infection risk value of the person is such that the infection risk value of the peripheral person is lower than the first risk value. 2 Calculated relatively higher than the infection risk value calculated in the case of risk value,
The risk value calculation device according to Appendix 8.
(Appendix 10)
The risk value calculating means calculates the infection risk value of the person by further adding the distance to the surrounding person existing in the vicinity of the person.
The risk value calculation device according to any one of Supplementary note 6 to 9.
(Appendix 11)
The risk value calculating means calculates the infection risk value of the person when the distance of the peripheral person is the first distance, when the infection risk value of the peripheral person is the second distance farther than the first distance. Calculated relatively higher than the calculated infection risk value,
The risk value calculation device according to Appendix 10.
(Appendix 12)
An authentication device that authenticates a person from the visible light image data,
A risk value calculation system including the risk value calculation device according to any one of Supplementary note 1 to 11, which calculates and outputs an infection risk value of the person to be authenticated.
(Appendix 13)
The computer
The visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data are acquired, respectively.
Identify the person included in the visible light image data and the thermal image data,
The body surface temperature of the identified person was measured and
Based on the visible light image data, the symptom of the infectious disease of the person is detected.
Based on the body surface temperature and the symptom, the infection risk value of the person is calculated.
Output the infection risk value,
Risk value calculation method.
(Appendix 14)
The process of acquiring the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data, respectively.
A process for identifying a person included in the visible light image data and the thermal image data,
The process of measuring the body surface temperature of the identified person and
The process of detecting the symptom of the infectious disease of the person based on the visible light image data,
The process of calculating the infection risk value of the person based on the body surface temperature and the symptom, and
The process of outputting the infection risk value and
A non-temporary computer-readable medium containing a risk value calculation program that causes a computer to execute.
　１１　リスク値算出装置
　１２　リスク値算出装置
　１３　リスク値算出装置
　１４　リスク値算出装置
　２１　ユーザ端末
　９０　施設
　９１　可視光カメラ
　９２　サーマルカメラ
　１１０　画像データ取得部
　１１１　温度測定部
　１１２　症状検出部
　１１３　リスク値算出部
　１１４　出力部
　１１５　混雑度算出部
　１２０　記憶部
　１２１　症状ＤＢ
　１２２　属性情報
　２００　認証装置
　２１０　顔特徴ＤＢ
　２２０　顔検出部
　２３０　特徴点抽出部
　２４０　登録部
　２５０　認証部
　５００　ネットワーク
　７００　リスク値算出システム 11 Risk value calculation device 12 Risk value calculation device 13 Risk value calculation device 14 Risk value calculation device 21 User terminal 90 Facility 91 Visible light camera 92 Thermal camera 110 Image data acquisition unit 111 Temperature measurement unit 112 Symptom detection unit 113 Risk value calculation unit 114 Output unit 115 Congestion degree calculation unit 120 Storage unit 121 Symptom DB
122 Attribute information 200 Authentication device 210 Face feature DB
220 Face detection unit 230 Feature point extraction unit 240 Registration unit 250 Authentication unit 500 Network 700 Risk value calculation system

Claims (14)

  1. 　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する画像データ取得手段と、
    　前記可視光画像データおよび前記熱画像データに含まれる人物を特定し、特定した前記人物の体表温度を測定する温度測定手段と、
    　前記可視光画像データに基づいて前記人物の感染症の症状を検出する症状検出手段と、
    　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出するリスク値算出手段と、
    　前記感染リスク値を出力する出力手段と、を備える
    リスク値算出装置。     An image data acquisition means for acquiring visible light image data generated by a visible light camera and thermal image data generated by an infrared camera having a shooting range corresponding to at least a part of the visible light image data.
    A temperature measuring means for identifying a person included in the visible light image data and the thermal image data and measuring the body surface temperature of the specified person.
    A symptom detecting means for detecting a symptom of an infectious disease of the person based on the visible light image data, and a symptom detecting means.
    A risk value calculating means for calculating an infection risk value of the person based on the body surface temperature and the symptom, and a risk value calculating means.
    A risk value calculation device including an output means for outputting the infection risk value.
  2. 　前記症状検出手段は、前記人物の姿勢から前記症状を検出する、
    請求項１に記載のリスク値算出装置。     The symptom detecting means detects the symptom from the posture of the person.
    The risk value calculation device according to claim 1.
  3. 　前記感染症の前記症状に関連する姿勢パターンを記憶する記憶部をさらに備え、
    　前記症状検出手段は、前記人物の姿勢と前記姿勢パターンとを照合することにより前記症状を検出する、
    請求項２に記載のリスク値算出装置。     Further equipped with a storage unit for storing the posture pattern associated with the symptom of the infectious disease.
    The symptom detecting means detects the symptom by collating the posture of the person with the posture pattern.
    The risk value calculation device according to claim 2.
  4. 　前記症状検出手段は、前記人物の姿勢と前記姿勢パターンとが所定期間内に所定の割合以上に一致した場合に、前記症状を検出する、
    請求項３に記載のリスク値算出装置。     The symptom detecting means detects the symptom when the posture of the person and the posture pattern match at a predetermined ratio or more within a predetermined period.
    The risk value calculation device according to claim 3.
  5. 　前記記憶部は、所定の肺炎の前記症状に関連する前記姿勢パターンを記憶する、
    請求項３または４に記載のリスク値算出装置。     The storage unit stores the posture pattern associated with the symptom of a predetermined pneumonia.
    The risk value calculation device according to claim 3 or 4.
  6. 　前記可視光画像データから空間の混雑度を算出する混雑度算出手段をさらに備え、
    　リスク値算出手段は、前記可視光画像データにおいて前記人物が含まれる所定空間の混雑度をさらに加味して前記感染リスク値を算出する、
    請求項１～５のいずれか一項に記載のリスク値算出装置。     Further provided with a congestion degree calculation means for calculating the congestion degree of the space from the visible light image data is provided.
    The risk value calculating means calculates the infection risk value by further adding the degree of congestion of the predetermined space including the person in the visible light image data.
    The risk value calculation device according to any one of claims 1 to 5.
  7. 　前記混雑度算出手段は、所定空間の人数に基づいて前記混雑度を算出する、
    請求項６に記載のリスク値算出装置。     The congestion degree calculation means calculates the congestion degree based on the number of people in a predetermined space.
    The risk value calculation device according to claim 6.
  8. 　前記リスク値算出手段は、前記人物の周辺に存在する周辺人物の前記体表温度と前記症状とをさらに加味して前記人物の前記前記感染リスク値を算出する、
    請求項６または７に記載のリスク値算出装置。     The risk value calculating means calculates the infection risk value of the person by further considering the body surface temperature of the surrounding person existing around the person and the symptom.
    The risk value calculation device according to claim 6 or 7.
  9. 　前記リスク値算出手段は、前記周辺人物の前記感染リスク値が第１リスク値の場合に算出する前記人物の前記感染リスク値は、前記周辺人物の前記感染リスク値が前記第１リスク値より低い第２リスク値の場合に算出する前記感染リスク値よりも比較的に高く算出する、
    請求項８に記載のリスク値算出装置。     The risk value calculating means calculates the infection risk value of the peripheral person when the infection risk value of the peripheral person is the first risk value. The infection risk value of the peripheral person is lower than the infection risk value of the peripheral person. Calculated relatively higher than the infection risk value calculated in the case of the second risk value,
    The risk value calculation device according to claim 8.
  10. 　前記リスク値算出手段は、前記人物の周辺に存在する周辺人物との距離をさらに加味して前記人物の前記前記感染リスク値を算出する、
    請求項６～９のいずれか一項に記載のリスク値算出装置。     The risk value calculating means calculates the infection risk value of the person by further adding the distance to the surrounding person existing in the vicinity of the person.
    The risk value calculation device according to any one of claims 6 to 9.
  11. 　前記リスク値算出手段は、前記周辺人物の距離が第１距離の場合に算出する前記人物の前記感染リスク値は、前記周辺人物の前記感染リスク値が前記第１距離より遠い第２距離の場合に算出する前記感染リスク値よりも比較的に高く算出する、
    請求項１０に記載のリスク値算出装置。     The risk value calculating means calculates when the distance of the peripheral person is the first distance. The infection risk value of the person is the case where the infection risk value of the peripheral person is a second distance farther than the first distance. Calculated relatively higher than the above-mentioned infection risk value calculated in
    The risk value calculation device according to claim 10.
  12. 　前記可視光画像データから前記人物の認証を行う認証装置と、
    　前記認証にかかる前記人物の前記感染リスク値を算出して出力する請求項１～１１のいずれか一項に記載のリスク値算出装置と、を備える
    　リスク値算出システム。     An authentication device that authenticates the person from the visible light image data,
    A risk value calculation system comprising the risk value calculation device according to any one of claims 1 to 11, which calculates and outputs the infection risk value of the person to be authenticated.
  13. 　コンピュータが、
    　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得し、
    　前記可視光画像データおよび前記熱画像データに含まれる人物を特定し、
    　特定した前記人物の体表温度を測定し、
    　前記可視光画像データに基づいて前記人物の感染症の症状を検出し、
    　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出し、
    　前記感染リスク値を出力する、
    リスク値算出方法。     The computer
    The visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data are acquired, respectively.
    Identify the person included in the visible light image data and the thermal image data,
    The body surface temperature of the identified person was measured and
    Based on the visible light image data, the symptom of the infectious disease of the person is detected.
    Based on the body surface temperature and the symptom, the infection risk value of the person is calculated.
    Output the infection risk value,
    Risk value calculation method.
  14. 　可視光カメラが生成した可視光画像データと前記可視光画像データの少なくとも一部に対応した撮影範囲を持つ赤外線カメラが生成した熱画像データとをそれぞれ取得する処理と、
    　前記可視光画像データおよび前記熱画像データに含まれる人物を特定する処理と、
    　特定した前記人物の体表温度を測定する処理と、
    　前記可視光画像データに基づいて前記人物の感染症の症状を検出する処理と、
    　前記体表温度と前記症状とに基づいて、前記人物の感染リスク値を算出する処理と、
    　前記感染リスク値を出力する処理と、
    を、コンピュータに実行させるリスク値算出プログラムが格納された非一時的なコンピュータ可読媒体。     The process of acquiring the visible light image data generated by the visible light camera and the thermal image data generated by the infrared camera having a shooting range corresponding to at least a part of the visible light image data, respectively.
    A process for identifying a person included in the visible light image data and the thermal image data,
    The process of measuring the body surface temperature of the identified person and
    The process of detecting the symptom of the infectious disease of the person based on the visible light image data,
    The process of calculating the infection risk value of the person based on the body surface temperature and the symptom, and
    The process of outputting the infection risk value and
    A non-temporary computer-readable medium containing a risk value calculation program that causes a computer to execute.
PCT/JP2020/044863 2020-12-02 2020-12-02 Risk value calculation device, system, method, and non-transitory computer-readable medium storing program WO2022118397A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022566547A JPWO2022118397A5 (en) 2020-12-02 Risk value calculation device, risk value calculation method, and risk value calculation program
PCT/JP2020/044863 WO2022118397A1 (en) 2020-12-02 2020-12-02 Risk value calculation device, system, method, and non-transitory computer-readable medium storing program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/044863 WO2022118397A1 (en) 2020-12-02 2020-12-02 Risk value calculation device, system, method, and non-transitory computer-readable medium storing program

Publications (1)

Publication Number Publication Date
WO2022118397A1 true WO2022118397A1 (en) 2022-06-09

Family

ID=81853045

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/044863 WO2022118397A1 (en) 2020-12-02 2020-12-02 Risk value calculation device, system, method, and non-transitory computer-readable medium storing program

Country Status (1)

Country Link
WO (1) WO2022118397A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019083395A (en) * 2017-10-30 2019-05-30 パナソニックＩｐマネジメント株式会社 Infectious substance monitoring system, and infectious substance monitoring method
JP2020027364A (en) * 2018-08-09 2020-02-20 株式会社リクルート Medical institution reception system, medical institution reception device, and program
WO2020059442A1 (en) * 2018-09-21 2020-03-26 パナソニックＩｐマネジメント株式会社 Space cleaning system and space cleaning method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019083395A (en) * 2017-10-30 2019-05-30 パナソニックＩｐマネジメント株式会社 Infectious substance monitoring system, and infectious substance monitoring method
JP2020027364A (en) * 2018-08-09 2020-02-20 株式会社リクルート Medical institution reception system, medical institution reception device, and program
WO2020059442A1 (en) * 2018-09-21 2020-03-26 パナソニックＩｐマネジメント株式会社 Space cleaning system and space cleaning method

Also Published As

Publication number Publication date
JPWO2022118397A1 (en) 2022-06-09

Similar Documents

Publication Publication Date Title
US11935301B2 (en) Information processing method, recording medium, and information processing system
JP7318691B2 (en) Image processing device, image processing method, face authentication system and program
JP6550094B2 (en) Authentication device and authentication method
EP2546782B1 (en) Liveness detection
US9792484B2 (en) Biometric information registration apparatus and biometric information registration method
JP2015097000A (en) Image recognition device and data registration method to the same
JP2003346149A (en) Face collating device and bioinformation collating device
JP6822482B2 (en) Line-of-sight estimation device, line-of-sight estimation method, and program recording medium
US11694476B2 (en) Apparatus, system, and method of providing a facial and biometric recognition system
US20230368582A1 (en) Authentication device, authentication method, and recording medium
JP6769475B2 (en) Information processing system, management method for authentication, and program
JP2011210126A (en) Apparatus and method for recognizing pattern
JP2002236666A (en) Personal authentication device
JP2008009689A (en) Face registering device, face authentication device, and face registration method
WO2022118397A1 (en) Risk value calculation device, system, method, and non-transitory computer-readable medium storing program
CN112964376A (en) Intelligent temperature measurement method and device, computer equipment and storage medium
JP2022048464A (en) Nose print collation device, method and program
WO2022014026A1 (en) Temperature management device, system, method, and non-transitory computer-readable medium storing program
CN112883809B (en) Target detection method, device, equipment and medium
WO2022130822A1 (en) Image display device, image display system, image display method and non-transitory computer readable medium
JPWO2020152917A1 (en) Face recognition devices, face recognition methods, programs, and recording media
JP7067593B2 (en) Information processing system, management method for authentication, and program
US20240185609A1 (en) Information processing method, recording medium, and information processing system
JP2023079045A (en) Image processing apparatus, image processing method, and program
WO2020213284A1 (en) Image processing device, image processing method, and program

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: 20964251

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022566547

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20964251

Country of ref document: EP

Kind code of ref document: A1