WO2022107215A1

WO2022107215A1 - Risk information generation device, risk information generation method, and program

Info

Publication number: WO2022107215A1
Application number: PCT/JP2020/042829
Authority: WO
Inventors: 亮太油科; 陽平伊藤; 健史小島; 和希世古; 哲寺澤
Original assignee: 日本電気株式会社
Priority date: 2020-11-17
Filing date: 2020-11-17
Publication date: 2022-05-27
Also published as: JPWO2022107215A1

Abstract

This risk information generation device 10 is provided with: a first image-processing unit (120); a second image-processing unit (130); and a risk information generation unit (140). The first image-processing unit (120) processes an image obtained by capturing a target region to generate executor-identifying information for identifying an event executor who has executed a specific event, among persons exiting in the target region. The second image-processing unit (130) processes said image to generate: surrounding person-identifying information for identifying a surrounding person having at a relative position, from the event executor, satisfying a criterion; and state information indicating a state of at least one of the event executor and the surrounding person. The risk information generation unit (140) generates, for each surrounding person, infection risk information about the risk of said person to be infected by an infectious disease, using the surrounding person-identifying information and the state information.

Description

Risk information generator, risk information generator, and program

The present invention relates to a risk information generator, a risk information generation method, and a program.

Examples of transmission routes for infectious diseases are droplet infection and airborne infection. In infectious diseases with these transmission routes, those who approach the infected person are at risk of being infected with the infectious disease. In Patent Document 1, the conversation time between a resident and a visitor of a predetermined facility is measured by processing an image, and if the conversation time exceeds the predetermined time, the resident is at risk of being infected with an infectious disease. It is described that information indicating that the property is high is transmitted to the terminal device.

International Publication No. 2019/239913

In areas and facilities where a large number of people exist, there is a risk that infectious diseases will spread among people who do not know each other. An example of an object of the present invention is to be able to generate information about the risk of spreading an infectious disease even among people who do not know each other.

According to the first invention, by processing an image obtained by capturing an image of a target area, it is possible to generate executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area. Image processing means and
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing means to be
A risk information generation means for generating infection risk information regarding the risk of a person having an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
A risk information generator is provided.

According to the present invention, the computer
The first image processing that generates the executor specific information that identifies the event executor who performed the specific event among the people existing in the target area by processing the image that captured the target area, and the first image processing.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing and
Risk information generation processing that generates infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
A method of generating risk information is provided.

According to the present invention, the computer
A first image processing function that generates executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area by processing an image obtained by capturing an image of the target area.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. The second image processing function and
A risk information generation function that uses the peripheral person identification information and the state information to generate infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons.
Is provided.

According to the present invention, it is possible to generate information on the risk of spreading an infectious disease even among people who do not know each other.

The above-mentioned objectives and other objectives, features and advantages will be further clarified by the preferred embodiments described below and the accompanying drawings below.

It is a figure for demonstrating the use environment of the risk information generation apparatus which concerns on 1st Embodiment. It is a figure which shows an example of the functional structure of a risk information generator. It is a figure which shows an example of the information which the processing result storage part has stored. It is a figure which shows an example of the information which a high-risk person memory part stores. It is a figure which shows the hardware configuration example of a risk information generator. It is a flowchart which shows the 1st example of the process performed by a risk information generation apparatus. It is a flowchart which shows the 1st example of the processing performed by the infection information acquisition part and the risk information output part of a risk information generation apparatus. It is a flowchart which shows the 2nd example of the processing performed by the infection information acquisition part and the risk information output part of a risk information generation apparatus. It is a figure which shows an example of the functional structure of the risk information generation apparatus which concerns on 2nd Embodiment. The first example of the process performed by the risk information generation apparatus shown in FIG. 9 is shown, and corresponds to FIG. 6 of the first embodiment. A second example of the process performed by the risk information generator shown in FIG. 9 is shown, and corresponds to FIG. 8 of the first embodiment. It is a figure which shows an example of the functional structure of the risk information generation apparatus which concerns on 3rd Embodiment. It is a figure which shows an example of the functional structure of the risk information generation apparatus which concerns on 4th Embodiment. It is a figure for demonstrating the use environment of the risk information generation apparatus which concerns on 5th Embodiment. It is a figure which shows an example of the visitor information which a visitor management apparatus stores. It is a figure which shows an example of the functional structure of the risk information generation apparatus which concerns on 6th Embodiment. It is a figure which shows an example of the functional structure of the risk information generation apparatus which concerns on the modification of FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, similar components are designated by the same reference numerals, and the description thereof will be omitted as appropriate.

(First Embodiment)
FIG. 1 is a diagram for explaining a usage environment of the risk information generation device 10 according to the present embodiment. The risk information generation device 10 is used together with a plurality of image pickup devices 20.

The image pickup device 20 is, for example, a surveillance camera and is installed in a target area. At least two image pickup devices 20 are imaging partial regions of the target region that are separated from each other. Further, at least two image pickup devices 20 may image the same partial region from different directions. The frame rate of the image generated by the image pickup apparatus 20 is arbitrary, but it may be a frame rate for moving images or a frame rate for still images.

The risk information generation device 10 processes images generated by a plurality of image pickup devices 20 to generate information indicating the state of a person who has visited the target area (hereinafter referred to as state information) for each person. The state information includes the movement of the person, the direction of the face or the line of sight, the presence or absence of a specific wearer, and the like. Further, the risk information generation device 10 processes a person who has performed a specific event among the people existing in the target area by processing the images generated by the plurality of image pickup devices 20 (hereinafter referred to as an event executor). Identify. Certain events include the act of releasing droplets from the mouth, as represented by sneezing, coughing, and conversation (particularly conversation without a mask). In addition, a specific event may include that the density of a plurality of people is equal to or higher than a reference value. Here, the reference value of the density is defined by, for example, the number of people per predetermined area. Then, the risk information generation device 10 provides information on the risk that a person (hereinafter referred to as a peripheral person) who was around the event executor when a specific event was performed becomes infected with an infectious disease (hereinafter, infection risk information). (Description) is generated. This infection risk information is used when the event performer is found to have an infectious disease.

The infection risk information generated by the risk information generation device 10 is used, for example, by the management terminal 30 or the user terminal 40. The management terminal 30 is a terminal used by a manager of a target area or a medical person, and is used, for example, to grasp an overall picture of infection risk. The user terminal 40 is used by a person who has visited the target area to grasp his / her own infection risk. The management terminal 30 and the user terminal 40 may be a portable terminal such as a so-called smartphone or tablet, or may be a fixed terminal.

FIG. 2 is a diagram showing an example of the functional configuration of the risk information generation device 10. The risk information generation device 10 includes an image acquisition unit 110, a first image processing unit 120, a second image processing unit 130, and a risk information generation unit 140.

The image acquisition unit 110 acquires images generated by a plurality of image pickup devices 20. The image acquisition unit 110 may acquire an image in real time or may acquire an image in a batch format. When the image acquisition unit 110 acquires an image in real time, there may be a slight time lag between the timing at which the image pickup apparatus 20 generates the image and the timing at which the image acquisition unit 110 acquires the image.

The first image processing unit 120 generates the performer identification information by processing the image acquired from the image pickup device 20. The executor identification information is information for identifying an event executor existing in a target area, and includes, for example, an appearance feature amount obtained from an image. The appearance feature amount includes, for example, the feature amount of the person's face, but may further include the feature amount of the wearing object (for example, clothes).

The first image processing unit 120 detects the occurrence of a specific event, for example, by using a posture estimation technique. In the posture estimation technique performed here, the posture information indicating the posture of a person is, for example, by a "key point" which is a characteristic point of a joint or the like and a "bone (bone link)" which indicates a link between the key points. Shown. Key points are, for example, head, neck, right shoulder, left shoulder, right elbow, left elbow, right hand, left hand, right hip, left hip, right knee, left knee, right foot, and left foot. Then, the first image processing unit 120 uses a model generated by machine learning when detecting the occurrence of an event. This model is generated by machine learning the posture information when a specific event occurs.

The second image processing unit 130 processes the image acquired from the image pickup apparatus 20 to generate peripheral person identification information and at least one state information of the event executor and the peripheral person.

The peripheral person identification information is the information for identifying the peripheral person described above, and includes the appearance feature amount obtained from the image. A peripheral person is, for example, a person whose relative position from the event executor meets the criteria. In the peripheral person identification information, the feature amount on the appearance includes, for example, the feature amount of the face of the person, but may further include the feature amount of the wearing object (for example, clothes).

As described above, the state information includes the movement of the person, the direction of the face or the line of sight, the presence or absence of a specific wearer, and the like. The second image processing unit 130 may generate only the state information of the event executor, may generate only the state information of the peripheral person, or may generate only the state information of the event executor and the state information of the peripheral person. Both may be generated. Further, at least a part of the items included in the state information of the event executor may be different from the items included in the state information of the peripheral person.

The risk information generation unit 140 generates infection risk information for each peripheral person by using the peripheral person identification information and the state information. Infection risk information is information about a person's risk of contracting an infectious disease, and includes, for example, a risk score indicating a high risk of infection. When there are multiple event executors, infection risk information is generated for each combination of event executors and surrounding persons. In addition, when the same event executor executes a specific event multiple times, the infection risk information generates infection risk information for each executed event and for each peripheral person in the event.

The risk information generation unit 140 stores the infection risk information and incidental information accompanying the infection risk information in the processing result storage unit 150. The details of the accompanying information will be described later with reference to other figures. The risk information generation unit 140 stores the infection risk information and incidental information in the processing result storage unit 150 in a state in which the combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified.

In the example shown in this figure, the processing result storage unit 150 is a part of the risk information generation device 10. However, the processing result storage unit 150 may be located outside the risk information generation device 10.

In the example shown in FIG. 2, the risk information generation device 10 further includes an infection information acquisition unit 160, a risk information output unit 170, and a high-risk person storage unit 180.

The infection information acquisition unit 160 acquires information for identifying an infected person with an infectious disease (hereinafter referred to as infected person identification information). The infected person identification information includes the appearance feature amount obtained from the image of the infected person. The appearance feature amount is, for example, the feature amount of the person's face, but further includes the feature amount of the wearing object (for example, clothes) when the target area is visited. The infection information acquisition unit 160 acquires infected person identification information from, for example, the management terminal 30.

When the performer identification information corresponding to the infected person identification information acquired by the infection information acquisition unit 160 is stored in the processing result storage unit 150, the risk information output unit 170 identifies the performer from the processing result storage unit 150. The infection risk information corresponding to the information is read out together with the peripheral person identification information corresponding to the infection risk information. Then, the risk information output unit 170 outputs the read infection risk information and peripheral person identification information. These output destinations are, for example, the management terminal 30, but may be other terminals. The risk information output unit 170 may read out other information (for example, at least a part of incidental information) from the processing result storage unit 150 and output the information. When a plurality of sets of infection risk information and peripheral person identification information are read out in this output, the risk information output unit 170 may arrange the peripheral person identification information and the infection risk information in the order of the risk score.

Further, the risk information output unit 170 stores the output infection risk information and the peripheral person identification information in the high-risk person storage unit 180 in association with each other.

In addition, the infection information acquisition unit 160 acquires the person identification information of the person who wants to confirm the infection risk information from the user terminal 40. This type of person-specific information includes appearance features obtained from an image, similar to peripheral person-specific information. The appearance feature amount is, for example, the feature amount of the person's face, but may further include the feature amount of the wearing object (for example, clothes) when the target area is visited. When the risk information output unit 170 stores the peripheral person identification information corresponding to the user specific information in the high risk person storage unit 180, the risk information output unit 170 stores the infection risk information corresponding to the peripheral person identification information in the high risk person storage unit 180. It is read from the unit 180 and transmitted to the user terminal 40. As a result, a person who visits the target area can easily confirm his / her infection risk information.

In the example shown in this figure, the high-risk person storage unit 180 is a part of the risk information generation device 10. However, the high-risk person storage unit 180 may be provided outside the risk information generation device 10.

Note that, in FIGS. 1, 2, and 5, which will be described later, the risk information generation device 10 is composed of one piece of hardware (for example, a server). However, the risk information generation device 10 may be configured by a plurality of hardware (for example, a plurality of servers). For example, the image acquisition unit 110, the first image processing unit 120, and the second image processing unit 130 are realized by the first server, the risk information generation unit 140 is realized by the second server, and the risk information output unit 170 is realized. It may be realized by a third server. Further, the image acquisition unit 110, the first image processing unit 120, the second image processing unit 130, and the risk information generation unit 140 are realized on the first server, and the risk information output unit 170 is realized on the second server. May be good.

FIG. 3 is a diagram showing an example of information stored in the processing result storage unit 150. As described above, the processing result storage unit 150 stores the infection risk information and the accompanying information in a state in which the combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified.

In the example shown in this figure, the processing result storage unit 150 stores the performer identification information, the peripheral person identification information, the infection risk information, and the accompanying information for each specific event that has occurred. The accompanying information includes, for example, the type of event that occurred, the timing (for example, the date and time of occurrence) and location of the event, the state information when the event of the event executor occurred, and the image at the time of event occurrence (when including the images before and after). There is also), and the state information of the surrounding people when the event occurs.

State information includes posture (including at least one of the vertical tilt and horizontal orientation of the body), the orientation of the face or line of sight, and the presence or absence of an attachment covering the mouth (eg, mask, muffler, face guard, etc.). Contains at least one of.

Further, the state information of the event executor may include information about the event that has occurred.

If the event that occurred is an act of splashing, such as sneezing, coughing, and conversation without covering the mouth, the state information includes the range or distance at which the splash is presumed to have flown. The first image processing unit 120 uses this information, for example, the orientation of the face of the event executor at the time of event occurrence, the presence / absence and type of a wearer covering the mouth, and the change in the posture of the event executor at the time of event occurrence. To estimate. For example, if the event is sneezing or coughing, the range or distance at which the droplets are presumed to have flown increases as the change in posture at the time of the event increases. Also, if the event is sneezing or coughing, if there is no attachment to cover the mouth, the range or distance at which the droplets are presumed to have flown will be larger than if there was an attachment. In addition, even if there is an attachment that covers the mouth, the range or distance at which the droplets are estimated to have flown varies depending on the type of the attachment.

If the event that occurred is dense, the state information includes the degree of density, that is, the number of people per unit area, and the size of the area where the people are dense.

Further, the state information of the peripheral person may include the relative direction between the peripheral person and the event executor. This orientation is, for example, the relative orientation of the face and is specified using the orientation of the face or line of sight of the event executor and the orientation of the face or line of sight of the surrounding person. Further, the state information of the peripheral person may include the relative distance between the peripheral person and the event executor.

FIG. 4 is a diagram showing an example of information stored in the high-risk person storage unit 180. As described above, the high-risk person storage unit 180 stores the infection risk information and the peripheral person identification information read from the processing result storage unit 150 by the risk information output unit 170 in association with each other. Further, in the example shown in this figure, the high-risk person storage unit 180 also stores the performer identification information. The risk information output unit 170 also reads this executor-specific information from the processing result storage unit 150 and stores it in the high-risk person storage unit 180. Further, the risk information output unit 170 may further read at least a part of the accompanying information from the processing result storage unit 150 and store it in the high-risk person storage unit 180.

One person may be exposed to the risk of infection multiple times. Specific examples include the case where the same event executor generates a specific event in succession (for example, when sneezing and coughing are repeated), or when the same event executor is close to multiple event executors at different timings. .. In such cases, multiple infection risk information is generated for the same person. Then, the high-risk person storage unit 180 associates a plurality of infection risk information with one peripheral person identification information. In addition, the high-risk person storage unit 180 also stores the performer identification information of the performer who caused the infection risk information, the type of event, the infection risk information, and the accompanying information for each of the plurality of infection risk information. ..

Then, the risk information output unit 170 generates integrated risk information that integrates a plurality of infection risk information for the one peripheral person identification information. The integrated risk information includes, for example, an integrated risk score. The integrated risk score is a score that integrates the risk scores of each of a plurality of infection risk information. The integrated risk score is generated, for example, by adding a plurality of risk scores, but the method of generating the integrated risk score is not limited to this.

Then, when new infection risk information corresponding to a certain peripheral person identification information is added to the high-risk person storage unit 180, the risk information output unit 170 updates the integrated risk information corresponding to the peripheral person identification information.

FIG. 5 is a diagram showing a hardware configuration example of the risk information generation device 10. The risk information generator 10 includes a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

The bus 1010 is a data transmission path for the processor 1020, the memory 1030, the storage device 1040, the input / output interface 1050, and the network interface 1060 to transmit and receive data to and from each other. However, the method of connecting the processors 1020 and the like to each other is not limited to the bus connection.

The processor 1020 is a processor realized by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

The memory 1030 is a main storage device realized by a RAM (RandomAccessMemory) or the like.

The storage device 1040 is an auxiliary storage device realized by an HDD (Hard Disk Drive), SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like. The storage device 1040 has each function of the risk information generation device 10 (for example, an image acquisition unit 110, a first image processing unit 120, a second image processing unit 130, a risk information generation unit 140, an infection information acquisition unit 160, and a risk information output unit. It stores a program module that realizes 170). When the processor 1020 reads each of these program modules into the memory 1030 and executes them, each function corresponding to the program module is realized. The storage device 1040 also functions as a processing result storage unit 150 and a high-risk person storage unit 180.

The input / output interface 1050 is an interface for connecting the risk information generation device 10 and various input / output devices.

The network interface 1060 is an interface for connecting the risk information generation device 10 to the network. This network is, for example, LAN (Local Area Network) or WAN (Wide Area Network). The method of connecting the network interface 1060 to the network may be a wireless connection or a wired connection. For example, the risk information generation device 10 may communicate with the image pickup device 20, the management terminal 30, and the user terminal 40 via the network interface 1060.

FIG. 6 is a flowchart showing a first example of processing performed by the risk information generation device 10. This figure shows the processing performed by the image acquisition unit 110, the first image processing unit 120, the second image processing unit 130, and the risk information generation unit 140. Each time the risk information generation device 10 acquires an image from the image pickup device 20, the risk information generation device 10 performs the processing shown in this figure on the acquired image.

First, the image acquisition unit 110 of the risk information generation device 10 acquires an image. Then, the first image processing unit 120 determines whether or not a specific event has occurred, that is, whether or not there is an event executor by processing this image (step S10). When there is an event executor (step S10: Yes), the first image processing unit 120 generates executor identification information and event executor status information (step S20). This state information includes information about the event that has occurred (eg, the range or distance at which the droplets are presumed to have flown), as described with reference to FIG.

Next, the second image processing unit 130 processes the image acquired from the image pickup apparatus 20 to generate peripheral person identification information and peripheral person state information (step S30).

Next, the risk information generation unit 140 generates infection risk information using the information generated by the first image processing unit 120 and the second image processing unit 130 (step S40). The infection risk information includes the risk score, as described above. The risk information generation unit 140 may change the method of generating infection risk information from the state information according to the type of the event that has occurred. This change may be to change the calculation formula for calculating the risk score, or may change the coefficient of the calculation formula calculation formula.

As an example, the risk information generation unit 140 calculates the neighborhood score and the splash score, and integrates (for example, adds) these scores to determine the risk score.

The neighborhood score is a score that is uniformly given to surrounding people whose relative distance to the event executor is less than or equal to the reference value when the event occurs. As a result, the risk score of the peripheral person whose relative distance is equal to or less than the reference value is higher than the risk score of the peripheral person whose relative distance exceeds the reference value. This reference value may be changed depending on the type of event that occurred. In addition, this reference value may be changed depending on the type of infectious disease being targeted.

If the state information includes a range or distance at which it is estimated that the droplets have flown, this range or distance may be used instead of the above-mentioned relative distance in assigning the neighborhood score.

The splash score is a score with the magnitude of the relative distance to the event executor as a variable. The splash score increases as the relative distance decreases. The formula for calculating the droplet score from relative distance and at least one of the coefficients used in this formula may be changed depending on the type of infectious disease being targeted.

Note that the splash score may be changed using the relative orientation to the event performer. For example, the splash score may increase as the relative orientation approaches the opposite.

Further, the risk information generation unit 140 may correct the risk score by using the presence or absence of a wearer covering the mouth in a peripheral person. As an example, the risk information generation unit 140 reduces the risk score when a person in the vicinity wears a fitting that covers the mouth.

Next, the risk information generation unit 140 stores the infection risk information and incidental information in the processing result storage unit 150 in a state in which the combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified (step S50). ).

FIG. 7 is a flowchart showing a first example of processing performed by the infection information acquisition unit 160 and the risk information output unit 170 of the risk information generation device 10.

When an infected person appears, the person who operates the management terminal 30 inputs the infected person identification information into the infection information acquisition unit 160 (step S110). Next, the risk information output unit 170 determines whether or not the executioner identification information corresponding to the infected person identification information acquired by the infection information acquisition unit 160 is recorded in the processing result storage unit 150 (step S120). When such executor specific information is recorded (step S120: Yes), the risk information output unit 170 outputs peripheral person identification information and infection risk information corresponding to the executor specific information from the processing result storage unit 150. Read (step S130) and output the read information to the management terminal 30 (step S140). At this time, the risk information output unit 170 may read out other information (for example, at least a part of incidental information) and output it to the management terminal 30 as needed. Then, the management terminal 30 displays the output information. As a result, the user of the management terminal 30 can easily identify a person who is likely to be infected with an infectious disease.

Further, the risk information output unit 170 stores the information read in step S130 in the high-risk person storage unit 180, and also uses the infection risk information newly stored in the high-risk person storage unit 180 to provide this infection risk information. Update the integrated risk information of the peripheral person specific information corresponding to (step S150).

FIG. 8 is a flowchart showing a second example of processing performed by the infection information acquisition unit 160 and the risk information output unit 170 of the risk information generation device 10. In the processing shown in this figure, the risk information output unit 170 reads only the combination of the peripheral person identification information and the infection risk information corresponding to the performer identification information from the processing result storage unit 150 (in the processing result storage unit 150). The process is the same as that shown in FIG. 7, except that the process is output to the management terminal 30 (step S140) in step S132). The standard for infection risk information is, for example, "the risk score is equal to or higher than the standard value". Therefore, the risk information output unit 170 outputs only the combination of the peripheral person identification information and the infection risk information corresponding to the performer identification information to the management terminal 30, and the high risk person storage unit. Store in 180.

According to the example shown in this figure, since the peripheral persons to be output are limited to those whose infection risk information meets the criteria, the output information (and the information stored in the high-risk person storage unit 180) The reliability is high.

When all the images generated by the image pickup apparatus 20 are saved, the risk information output unit 170 responds to the infected person identification information at the timing when the above-mentioned specific event does not occur by processing this image. A person who is close to the person (hereinafter referred to as a proximity person) may be specified, and information for identifying this proximity person (hereinafter referred to as a proximity person identification information) may be stored in the high-risk person storage unit 180. The proximity person identification information includes, for example, the feature amount of the appearance of the proximity person (for example, the feature amount of the face and the feature amount of the wearing object).

By doing so, the risk information output unit 170 can make the user of the management terminal 30 recognize the proximity person by outputting and displaying the proximity person identification information on the management terminal 30. Further, when the person identification information of the person who wants to confirm the infection risk information is acquired from the user terminal 40, the risk information output unit 170 determines whether or not the person corresponds to a nearby person, and uses the determination result. It is transmitted to the person terminal 40. As a result, a person who visits the target area can easily confirm whether or not he / she is close to the infected person.

As described above, according to the present embodiment, when the risk information generation device 10 detects an event executor who has performed a specific event such as sneezing or coughing by processing an image, the surrounding area around the event executor is detected. Detect a person. Then, the risk information generation device 10 generates infection risk information regarding the infection risk of the surrounding person and stores it in the processing result storage unit 150. Therefore, it is possible to generate information about the risk of spreading an infectious disease even among people who do not know each other.

Further, when the risk information generation device 10 acquires the infected person identification information for identifying the infected person of the infectious disease from the management terminal 30, it determines whether or not the person indicated by the infected person identification information is the event executor. .. Then, when the person is the event executor, the risk information generation device 10 can from the processing result storage unit 150 the person identification information (that is, peripheral person identification information) of the person who was nearby when the event was performed. The infection risk information is read out and output to the management terminal 30. Therefore, the user of the risk information generation device 10 (for example, the operator of the management terminal 30) can easily identify a person who is likely to be infected with an infectious disease.

Further, since the image processing is terminated before the infected person identification information is acquired and various information including the processing result is stored in the processing result storage unit 150, the risk information generation device 10 is obtained after the infected person identification information is acquired. The load applied to can be reduced.

(Second Embodiment)
FIG. 9 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to the present embodiment. The risk information generation device 10 according to the present embodiment has the same configuration as the risk information generation device 10 according to the first embodiment, except for the following points.

First, the processing result storage unit 150 stores information about the executor (for example, the executor specific information shown in FIG. 3, the type of event, the state information of the executor, and the image), but the information about the peripheral person is stored. I don't remember. Then, the processing result storage unit 150 is updated by the first image processing unit 120.

Then, the second image processing unit 130 and the risk information generation unit 140 perform processing after the infection information acquisition unit 160 acquires the infected person identification information. In other words, the infection information acquisition unit 160 acquires the infected person identification information after the first image processing unit 120 performs the processing and before the second image processing unit 130 and the risk information generation unit 140 perform the processing. .. Further, the risk information output unit 170 outputs the information generated by the second image processing unit 130 and the risk information generation unit 140, and updates the high-risk person storage unit 180 using this information.

FIG. 10 shows a first example of the process performed by the risk information generation device 10 shown in FIG. 9, and corresponds to FIG. 6 of the first embodiment. In this figure, the processes shown in steps S10 and S20 are as described in FIG. After step S20, the first image processing unit 120 stores the performer identification information, the event type, the state information of the performer, and the image in the processing result storage unit 150 (step S50).

FIG. 11 shows a second example of the process performed by the risk information generation device 10 shown in FIG. 9, and corresponds to FIG. 8 of the first embodiment.

The process shown in step S110 and step S120 is the same as step S110 and step S120 in FIG. 8 (that is, step S110 and step S120 in FIG. 7). When the performer identification information corresponding to the infected person identification information is stored in the processing result storage unit 150 (step S120: Yes), the second image processing unit 130 has an image corresponding to the performer identification information (that is, this). The image used when generating the executor specific information) is read from the processing result storage unit 150 (step S122), and the read image is subjected to the same processing as in step S30 of FIG. 6 (step S124). As a result, peripheral person identification information and state information corresponding to the performer who performed the specific event are generated. Then, the risk information generation unit 140 generates infection risk information using the information generated in step S124 (step S126). The process performed here is as described in step S40 of FIG.

The processing performed after that (step S132 to step S150) is the same as in FIG. Instead of step S132 in this figure, the process described in step S130 in FIG. 7 may be performed.

As described above, also in this embodiment, the user of the risk information generation device 10 (for example, the operator of the management terminal 30) can easily identify a person who is highly likely to be infected with an infectious disease, as in the first embodiment. can. In addition, the second image processing unit 130 and the risk information generation unit 140 perform processing after acquiring the infected person identification information. Therefore, the second image processing unit 130 and the risk information generation unit 140 do not process the event executor who does not correspond to the infected person identification information. Therefore, the total amount of processing performed by the risk information generation device 10 can be reduced.

(Third Embodiment)
FIG. 12 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to the present embodiment. The risk information generation device 10 shown in this figure has the same configuration as the risk information generation device 10 according to the first embodiment, except that the voice processing unit 190 is provided.

The voice processing unit 190 acquires a plurality of voice information indicating the voice generated in at least a part of the target area. The voice information is generated by a plurality of microphones provided in the target area. The microphone may be provided in the image pickup apparatus 20, or may be provided as a device separate from the image pickup apparatus 20. With respect to the positions of the plurality of microphones, when a sound is generated in the target area, the position where the sound is generated can be specified by analyzing a plurality of voice information. Then, the voice processing unit 190 identifies the type of event (for example, sneezing, coughing, and utterance) that caused the sound by processing a plurality of voice information, and also determines the position and magnitude of the sound generation. Identify. Here, the voice processing unit 190 calculates the absolute loudness of the sound by correcting the intensity of the sound indicated by the voice signal by using the relative distance between the microphone that generated the voice signal and the position where the sound is generated. ..

Then, the first image processing unit 120 specifies the performer identification information only by image processing as in the above-described embodiment, and generates the performer identification information by using the sound generation position generated by the voice processing unit 190. do. For example, when the sound is caused by a specific event, the voice processing unit 190 processes an image of the timing at which the sound is generated to identify the person in which the sound generation position exists. Information that identifies a person is defined as performer-specific information. By doing so, for example, even if the face of the event executor is not shown in the image, the occurrence of a specific event can be detected, and the executor identification information of the event executor can also be generated. When the image at the timing when a specific event occurs does not include the face of the event executor, the first image processing unit 120 processes the image before or after the event occurrence to execute the event. A person may be tracked to identify an image showing the face of the event executor, and this image may be used to generate executor identification information.

Further, the risk information generation unit 140 generates infection risk information using the loudness of the sound generated by the voice processing unit 190. For example, the risk information generation unit 140 increases the reference value of the relative distance used for giving the neighborhood score as the loudness of the sound increases. Further, the risk information generation unit 140 may increase the splash score as the loudness of the sound increases. This processing is performed both when the executor-specific information can be specified only by image processing and when the executor-specific information can be specified using the information generated by the voice processing unit 190.

In the former case, the first image processing unit 120 specifies the executor identification information and the position of the event executor by image processing. Then, when the position specified by the image processing and the sound generation position generated by the voice processing unit 190 overlap, the first image processing unit 120 determines the loudness of the sound corresponding to the generation position at the event execution. Processing is performed as the loudness of the sound generated by the person.

The loudness of the sound generated by the voice processing unit 190 may be used when calculating the range or distance at which the droplets are estimated to have flown. For example, the second image processing unit 130 increases the range or distance at which the droplets are presumed to have flown as the sound becomes louder.

Further, the risk information generation device 10 shown in the second embodiment may have the function shown in the present embodiment.

As described above, also in this embodiment, the user of the risk information generation device 10 (for example, the operator of the management terminal 30) can easily identify a person who is highly likely to be infected with an infectious disease, as in the first embodiment. can. Further, the risk information generation device 10 processes voice information indicating a sound generated in the target area, and generates infection risk information using the processing result. Therefore, the risk information generation device 10 can generate infection risk information more accurately.

(Fourth Embodiment)
FIG. 13 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to the present embodiment. The risk information generation device 10 according to the present embodiment has the same configuration as the risk information generation device 10 according to the first embodiment, except that the environmental information acquisition unit 200 is provided.

The environmental information acquisition unit 200 acquires information on the environment of the target area (hereinafter referred to as environmental information). The environmental information shows, for example, at least one transition of temperature, humidity, wind speed, and wind direction in the target area. Then, the risk information generation unit 140 further generates infection risk information using environmental information.

For example, the risk information generation unit 140 performs a predetermined calculation on at least one of the neighborhood score and the splash score. Then, the risk information generation unit 140 sets this calculation formula or the coefficient included in this calculation formula by using the environmental information. For example, in the case of an infectious disease that is easily transmitted when the temperature and humidity are low, the risk information generation unit 140 increases the risk score as the temperature and humidity decrease. Further, the risk information generation unit 140 makes the risk score decrease as the wind speed increases.

Further, when the environmental information includes the wind speed and the wind direction, the risk information generation unit 140 may change the area to which the neighborhood score should be given among the target areas by using these wind speeds and the wind direction. At least one of the formula for calculating the splash score from the relative distance and the coefficient used in this formula may be changed. For example, the risk information generation unit 140 widens the area to which the neighborhood score should be given downwind and narrows it upwind. The amount of deformation in the region at this time increases as the wind speed increases. Further, the risk information generation unit 140 sets an equation for calculating the splash score so that the splash score on the windward side is smaller than that on the leeward side.

The risk information generation device 10 shown in the second or third embodiment may have the function shown in the present embodiment.

Also in this embodiment, the user of the risk information generation device 10 (for example, the operator of the management terminal 30) can easily identify a person who has a high possibility of being infected with an infectious disease, as in the first embodiment. Further, the risk information generation device 10 generates infection risk information using environmental information indicating the environment of the target area. Therefore, the risk information generation device 10 can generate infection risk information more accurately.

(Fifth Embodiment)
FIG. 14 is a diagram for explaining the usage environment of the risk information generation device 10 according to the present embodiment, and corresponds to FIG. 1 of the first embodiment. In the present embodiment, the risk information generation device 10 is used together with the visitor management device 50 in addition to the image pickup device 20, the management terminal 30, and the user terminal 40.

In this embodiment, the target area has a system for managing visitors such as an event venue and a specific facility. The visitor management device 50 stores information on visitors in the target area (hereinafter referred to as “visitor information”). A visitor registers the visitor information in the visitor management device 50 before or at the time of admission. Then, the risk information generation device 10 generates infection risk information using the visitor information stored in the visitor management device 50. If the visitor has a mobile terminal having a function of detecting the current position (for example, a GPS function), when the mobile terminal detects that the current position of the mobile terminal is within the target area. , The visitor information registered in advance in the mobile terminal may be transmitted to the visitor management device 50.

FIG. 15 is a diagram showing an example of visitor information stored in the visitor management device 50. In the example shown in this figure, the visitor information includes, for example, information that identifies a visitor (hereinafter referred to as user-specific information), attribute information, and contact information.

The user-specific information is the same information as the peripheral person-specific information, and includes the feature amount on the appearance of the user, for example, the feature amount on the face of the user, but further, the wearer (for example, clothes). It may contain a feature amount. User-specific information is generated, for example, by processing an image of a user. Then, the risk information generation device 10 can specify the attribute information and the contact information of the peripheral person by using the user identification information and the peripheral person identification information.

Attribute information includes, for example, age, presence or absence of chronic disease and its type, and gender.

Contact information is information for contacting a user, and includes, for example, a telephone number (including the case of a mobile phone number), an email address, and at least one of SNS accounts. By using this contact information, for example, the operator of the management terminal 30 can identify the contact information of a peripheral person and notify the peripheral person that there is a risk of infection with an infectious disease.

FIG. 16 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to the present embodiment. The risk information generation device 10 shown in this figure has the same configuration as the risk information generation device 10 according to the first embodiment, except for the following points.

First, the risk information generation device 10 includes an attribute information acquisition unit 210. The attribute information acquisition unit 210 acquires the peripheral person identification information generated by the second image processing unit 130, and among the user identification information stored in the visitor management device 50, the usage that matches the peripheral person identification information. Identify person-specific information. Then, the attribute information acquisition unit 210 acquires the attribute information and the contact information associated with the specified user specific information from the visitor management device 50.

Then, the risk information generation unit 140 uses the attribute information acquired by the attribute information acquisition unit 210 in addition to the information shown in the first embodiment when generating the infection risk information. For example, the risk information generation unit 140 raises the risk score of a person having a specific disease in a specific infectious disease higher than the risk score of a person who does not have the disease. In addition, the risk information generation unit 140 corrects the risk score according to the age in a specific infectious disease. In addition, the risk information generation unit 140 corrects the risk score according to the gender in a specific infectious disease.

Further, the risk information output unit 170 uses the contact information acquired by the attribute information acquisition unit 210 when outputting the infection risk information read from the infection information acquisition unit 160 and the peripheral person identification information. Specifically, the risk information output unit 170 associates the contact information with the infection risk information by using the peripheral person identification information and the user identification information. Then, the risk information output unit 170 transmits the infection risk information to the contact indicated by the contact information associated with the infection risk information. As a result, the peripheral person can recognize his / her infection risk information even if he / she does not make an inquiry to the risk information generation device 10.

As described with reference to FIG. 2, the infection information acquisition unit 160 acquires the person identification information of the person who wants to confirm the infection risk information from the user terminal 40. At this time, the infection information acquisition unit 160 may acquire the attribute information of the person. In this case, the risk information output unit 170 corrects the risk score using the attribute information before transmitting the infection risk information corresponding to the acquired user specific information to the user terminal 40, and obtains the corrected risk score. It is transmitted to the user terminal 40.

FIG. 17 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to the modified example of FIG. In this modification, the attribute information acquisition unit 210 is provided in the risk information generation device 10 shown in FIG.

In this modification, the attribute information and the contact information acquired by the attribute information acquisition unit 210 from the visitor management device 50 are both used by the risk information output unit 170. The risk information output unit 170 corrects the risk score included in the infection risk information generated by the risk information generation unit 140. A specific example of this modification is the same as the example performed by the risk information generation unit 140 shown in FIG.

Note that the age and gender of the attribute information may be generated by processing the images of surrounding people.

Also in this embodiment, the user of the risk information generation device 10 (for example, the operator of the management terminal 30) can easily identify a person who has a high possibility of being infected with an infectious disease, as in the first embodiment. In addition, the risk score can be modified according to the attributes of surrounding persons. Further, even if there is no inquiry from a peripheral person, the infection risk information can be notified to the peripheral person.

Although the embodiments of the present invention have been described above with reference to the drawings, these are examples of the present invention, and various configurations other than the above can be adopted.

Further, in the plurality of flowcharts used in the above description, a plurality of steps (processes) are described in order, but the execution order of the steps executed in each embodiment is not limited to the order of description. In each embodiment, the order of the illustrated steps can be changed within a range that does not hinder the contents. In addition, the above-mentioned embodiments can be combined as long as the contents do not conflict with each other.

Some or all of the above embodiments may also be described, but not limited to:
1. 1. A first image processing means for generating executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area by processing an image obtained by capturing an image of the target area.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing means to be
A risk information generation means for generating infection risk information regarding the risk of a person having an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
A risk information generator equipped with.
2. 2. In the risk information generator described in 1 above,
The second image processing means is a risk information generation device that specifies the relative distance between the event executor and the surrounding person as at least a part of the state information.
3. 3. In the risk information generator described in 2 above,
The infection risk information includes a risk score indicating a high risk of infection.
The risk information generating means is a risk information generating device that raises the risk score of the peripheral person whose relative distance is equal to or less than the reference value in comparison with the risk score of the peripheral person whose relative distance exceeds the reference value. ..
4. In the risk information generator according to any one of 1 to 3 above,
The risk information generation means stores the infection risk information in the processing result storage means in a state in which a combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified.
moreover,
Infection information acquisition means for acquiring infected person identification information to identify infected persons with infectious diseases,
When the performer identification information corresponding to the infected person identification information is stored in the processing result storage means, the infection risk information corresponding to the performer identification information is stored in the processing result storage means from the processing result storage means. A risk information output means that reads out together with the peripheral person identification information corresponding to the information and outputs the infection risk information and the peripheral person identification information.
A risk information generator equipped with.
5. In the risk information generator according to any one of 1 to 3 above,
An infection that acquires infected person identification information that identifies an infected person of an infectious disease after the first image processing means generates the performer identification information and before the second image processing means generates the state information. Equipped with information acquisition means
The image used when the first image processing means generated the performer identification information corresponding to the infected person identification information, and the second image processing means generated the performer identification information. To generate the above state information using
After that, the risk information generating means generates the infection risk information, and the infection risk information is generated.
Further, a risk information generation device including a risk information output means for outputting the infection risk information together with the peripheral person identification information corresponding to the infection risk information.
6. In the risk information generator according to 4 or 5 above,
The risk information output means is a risk information generation device that outputs the infection risk information satisfying the criteria together with the peripheral person identification information corresponding to the infection risk information.
7. In the risk information generator according to any one of 4 to 6 above,
When a plurality of the infection risk information correspond to one peripheral person identification information, the risk information output means corresponds to the one peripheral person identification information by using the plurality of infection risk information. A risk information generator that generates integrated risk information.
8. In the risk information generator according to any one of 4 to 7 above,
The risk information output means is
The infection risk information to be output and the peripheral person identification information are associated with each other and stored in the high-risk person storage means.
Further, when the person identification information corresponding to the peripheral person identification information is acquired from the terminal, the infection risk information corresponding to the peripheral person identification information is read out from the high-risk person storage means and output to the terminal. Information generator.
9. In the risk information generator according to any one of 1 to 8 above,
The particular event is a risk information generator, which is at least one of coughing, sneezing, speaking without a covering over the mouth, and meeting the criteria for density.
10. In the risk information generator described in 9 above,
The risk information generating means is a risk information generating device that changes a method of generating the infection risk information from the state information according to the type of the specific event.
11. In the risk information generator according to any one of 1 to 10 above,
The state information includes at least one of a posture, a direction of a face or a line of sight, and the presence or absence of an attachment covering the mouth, a risk information generator.
12. In the risk information generator according to any one of 1 to 11 above,
The state information is a risk information generator including the relative orientation of the peripheral person and the event executor.
13. In the risk information generator according to any one of 1 to 12 above,
The particular event is at least one of coughing, sneezing, and speech.
A voice processing means for detecting the occurrence of the specific event by processing voice information indicating voice generated in at least a part of the target area is provided.
The first image processing means is a risk information generation device that further generates the performer identification information using the processing result of the voice processing means.
14. In the risk information generator according to any one of 1 to 12 above,
The particular event is at least one of coughing, sneezing, and speech.
A voice processing means for specifying the loudness of the sound generated in the specific event specified by the first image processing means by processing voice information indicating the sound generated in at least a part of the target area is provided.
The risk information generation means is a risk information generation device that further generates the infection risk information using the loudness of the sound.
15. In the risk information generator according to any one of 1 to 14 above,
Further equipped with an environmental information acquisition means for acquiring environmental information regarding the environment of the target area,
The risk information generation means is a risk information generation device that further generates the infection risk information using the environmental information.
16. In the risk information generator according to 15 above,
The environmental information is a risk information generator including at least one of temperature, humidity, wind speed, and wind direction in the target area.
17. In the risk information generator according to any one of 1 to 16 above,
Further provided with an attribute information acquisition means for acquiring attribute information indicating the attributes of the surrounding person,
The risk information generation means is a risk information generation device that further generates the infection risk information by using the attribute information.
18. In the risk information generator according to 17 above,
The attribute is a risk information generator including age, presence / absence of chronic disease and its type, and gender.
19. The computer
The first image processing that generates the executor specific information that identifies the event executor who performed the specific event among the people existing in the target area by processing the image obtained by capturing the image of the target area, and the first image processing.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing and
Risk information generation processing that generates infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
How to generate risk information.
20. In the risk information generation method described in 19 above,
In the second image processing, the computer is a risk information generation method for specifying the relative distance between the event executor and the peripheral person as at least a part of the state information.
21. In the risk information generation method described in 20 above,
The infection risk information includes a risk score indicating a high risk of infection.
In the risk information generation process, the computer increases the risk score of the peripheral person whose relative distance is equal to or less than the reference value with respect to the risk score of the peripheral person whose relative distance exceeds the reference value. Risk information generation method.
22. In the risk information generation method according to any one of 19 to 21 above,
In the risk information generation process, the computer stores the infection risk information in the processing result storage means in a state in which a combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified. ,
Further, the computer is
Infection information acquisition processing to acquire infected person identification information to identify infected persons with infectious diseases,
When the performer identification information corresponding to the infected person identification information is stored in the processing result storage means, the infection risk information corresponding to the performer identification information is stored in the processing result storage means from the processing result storage means. Risk information output processing that reads out together with the peripheral person identification information corresponding to the information and outputs the infection risk information and the peripheral person identification information.
How to generate risk information.
23. In the risk information generation method according to any one of 19 to 21 above,
The computer
Infection information acquisition to acquire infected person identification information that identifies an infected person of an infectious disease after the performer identification information is generated in the first image processing and before the state information is generated in the second image processing. Do the processing,
In the second image processing, when the performer identification information corresponding to the infected person identification information was generated in the first image processing, the image used when generating the performer identification information is used. To generate the above state information
After that, the infection risk information is generated in the risk information generation process, and the infection risk information is generated.
Further, a risk information generation method for performing risk information output processing for outputting the infection risk information together with the peripheral person identification information corresponding to the infection risk information.
24. In the risk information generation method described in 22 or 23 above,
In the risk information output process, the computer outputs the infection risk information satisfying the criteria together with the peripheral person identification information corresponding to the infection risk information, which is a risk information generation method.
25. In the risk information generation method according to any one of 22 to 24 above,
When a plurality of the infection risk information correspond to the one peripheral person identification information, in the risk information output process, the computer uses the plurality of the infection risk information to use the one peripheral person. A risk information generation method that generates integrated risk information corresponding to specific information.
26. In the risk information generation method according to any one of 22 to 25 above,
In the risk information output process, the computer
The infection risk information to be output and the peripheral person identification information are associated with each other and stored in the high-risk person storage means.
Further, when the person identification information corresponding to the peripheral person identification information is acquired from the terminal, the infection risk information corresponding to the peripheral person identification information is read out from the high-risk person storage means and output to the terminal. Information generation method.
27. In the risk information generation method described in any one of 19 to 26 above,
The specific event is at least one of coughing, sneezing, speaking without a covering over the mouth, and the density meeting the criteria, a method of generating risk information.
28. In the risk information generation method described in 27 above,
In the risk information generation process, the computer changes the method of generating the infection risk information from the state information according to the type of the specific event, the risk information generation method.
29. In the risk information generation method according to any one of 19 to 28 above,
The state information is a risk information generation method including at least one of a posture, a direction of a face or a line of sight, and the presence or absence of an attachment covering the mouth.
30. In the risk information generation method according to any one of 19 to 29 above,
The state information is a risk information generation method including the relative orientation of the peripheral person and the event executor.
31. In the risk information generation method according to any one of 19 to 30 above,
The particular event is at least one of coughing, sneezing, and speech.
The computer
By processing voice information indicating voice generated in at least a part of the target area, voice processing for detecting the occurrence of the specific event is performed.
A risk information generation method for generating the performer-specific information using the processing result of the voice processing in the first image processing.
32. In the risk information generation method according to any one of 19 to 30 above,
The particular event is at least one of coughing, sneezing, and speech.
The computer
By processing the voice information indicating the voice generated in at least a part of the target area, the voice processing for specifying the loudness of the sound generated in the specific event specified in the first image processing is performed.
A risk information generation method for generating infection risk information using the loudness of the sound in the risk information generation process.
33. In the risk information generation method according to any one of 19 to 32 above,
The computer
Further performing the environment information acquisition process for acquiring the environment information related to the environment of the target area,
A risk information generation method for generating the infection risk information by further using the environmental information in the risk information generation process.
34. In the risk information generation method described in 33 above,
The environmental information is a risk information generation method including at least one of temperature, humidity, wind speed, and wind direction in the target area.
35. In the risk information generation method according to any one of 19 to 34 above,
The computer
Further, the attribute information acquisition process for acquiring the attribute information indicating the attributes of the surrounding persons is performed.
A risk information generation method for generating the infection risk information by further using the attribute information in the risk information generation process.
36. In the risk information generation method described in 35 above,
The attribute is a risk information generation method including age, presence / absence of chronic disease and its type, and gender.
37. On the computer
A first image processing function that generates executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area by processing an image obtained by capturing an image of the target area.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. The second image processing function and
A risk information generation function that uses the peripheral person identification information and the state information to generate infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons.
A program to have.
38. In the program described in 37 above,
The second image processing function is a program that specifies the relative distance between the event executor and the surrounding person as at least a part of the state information.
39. In the program described in 38 above,
The infection risk information includes a risk score indicating a high risk of infection.
The risk information generation function is a program for increasing the risk score of the peripheral person whose relative distance is equal to or less than the reference value in comparison with the risk score of the peripheral person whose relative distance exceeds the reference value.
40. In the program described in any one of 37 to 39 above,
The risk information generation function stores the infection risk information in the processing result storage means in a state in which a combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified.
In addition, to the computer
Infection information acquisition function to acquire infected person identification information to identify infected person of infectious disease,
When the performer identification information corresponding to the infected person identification information is stored in the processing result storage means, the infection risk information corresponding to the performer identification information is stored in the processing result storage means from the processing result storage means. A risk information output function that reads out together with the peripheral person identification information corresponding to the information and outputs the infection risk information and the peripheral person identification information, and
A program to have.
41. In the program described in any one of 37 to 39 above,
Infected person identification information that identifies an infected person of an infectious disease on the computer after the first image processing function generates the performer identification information and before the second image processing function generates the state information. Have an infection information acquisition function to acquire
The second image processing function is the image used when the performer identification information is generated when the first image processing function is generating the performer identification information corresponding to the infected person identification information. To generate the above state information using
After that, the risk information generation function generates the infection risk information,
Further, a program provided with a risk information output function for outputting the infection risk information to the computer together with the peripheral person identification information corresponding to the infection risk information.
42. In the program according to 40 or 41 above,
The risk information output function is a program that outputs the infection risk information satisfying the criteria together with the peripheral person identification information corresponding to the infection risk information.
43. In the program described in any one of 40 to 42 above,
When a plurality of the infection risk information correspond to one peripheral person identification information, the risk information output function corresponds to the one peripheral person identification information by using the plurality of infection risk information. A program that generates integrated risk information.
44. In the program described in any one of 40 to 43 above,
The risk information output function is
The infection risk information to be output and the peripheral person identification information are associated with each other and stored in the high-risk person storage means.
Further, when the person identification information corresponding to the peripheral person identification information is acquired from the terminal, the infection risk information corresponding to the peripheral person identification information is read from the high-risk person storage means and output to the terminal. ..
45. In the program described in any one of 37 to 44 above,
The particular event is at least one of coughing, sneezing, speaking without a covering over the mouth, and the density meeting the criteria.
46. In the program described in 45 above,
The risk information generation function is a program that changes a method of generating the infection risk information from the state information according to the type of the specific event.
47. In the program described in any one of 37 to 46 above,
The state information includes at least one of posture, face or gaze orientation, and presence or absence of a wearer covering the mouth.
48. In the program described in any one of 37 to 47 above,
The state information is a program including the relative orientation of the peripheral person and the event executor.
49. In the program described in any one of 37 to 48 above,
The particular event is at least one of coughing, sneezing, and speech.
The computer is provided with a voice processing function for detecting the occurrence of the specific event by processing voice information indicating voice generated in at least a part of the target area.
The first image processing function is a program that further generates the performer identification information using the processing result of the voice processing function.
50. In the program described in any one of 37 to 48 above,
The particular event is at least one of coughing, sneezing, and speech.
Voice processing that specifies the loudness of the sound generated in the specific event specified by the first image processing function by processing the computer with voice information indicating the sound generated in at least a part of the target area. Have a function,
The risk information generation function is a program that further generates the infection risk information using the loudness of the sound.
51. In the program described in any one of 37 to 50 above,
The computer is further provided with an environment information acquisition function for acquiring environment information regarding the environment of the target area.
The risk information generation function is a program that further generates the infection risk information using the environmental information.
52. In the program described in 51 above,
The environmental information is a program including at least one of temperature, humidity, wind speed, and wind direction in the target area.
53. In the program described in any one of 37 to 52 above,
The computer is further provided with an attribute information acquisition function for acquiring attribute information indicating the attributes of the surrounding persons.
The risk information generation function is a program that further generates the infection risk information using the attribute information.
54. In the program described in 53 above,
The attributes include age, presence or absence of chronic illness and its type, and gender.

10 Risk information generation device 20 Imaging device 30 Management terminal 40 User terminal 50 Visitor management device 110 Image acquisition unit 120 First image processing unit 130 Second image processing unit 140 Risk information generation unit 150 Processing result storage unit 160 Infection information acquisition Unit 170 Risk information output unit 180 High-risk person storage unit 190 Voice processing unit 200 Environmental information acquisition unit 210 Attribute information acquisition unit

Claims

A first image processing means for generating executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area by processing an image obtained by capturing an image of the target area.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing means to be
A risk information generation means for generating infection risk information regarding the risk of a person having an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
A risk information generator equipped with.
In the risk information generator according to claim 1,
The second image processing means is a risk information generation device that specifies the relative distance between the event executor and the surrounding person as at least a part of the state information.
In the risk information generator according to claim 2,
The infection risk information includes a risk score indicating a high risk of infection.
The risk information generating means is a risk information generating device that raises the risk score of the peripheral person whose relative distance is equal to or less than the reference value in comparison with the risk score of the peripheral person whose relative distance exceeds the reference value. ..
In the risk information generator according to any one of claims 1 to 3, the risk information generator
The risk information generation means stores the infection risk information in the processing result storage means in a state in which a combination of the peripheral person identification information and the performer identification information corresponding to the infection risk information can be specified.
moreover,
Infection information acquisition means for acquiring infected person identification information to identify infected persons with infectious diseases,
When the performer identification information corresponding to the infected person identification information is stored in the processing result storage means, the infection risk information corresponding to the performer identification information is stored in the processing result storage means from the processing result storage means. A risk information output means that reads out together with the peripheral person identification information corresponding to the information and outputs the infection risk information and the peripheral person identification information.
A risk information generator equipped with.
In the risk information generator according to any one of claims 1 to 3, the risk information generator
An infection that acquires infected person identification information that identifies an infected person of an infectious disease after the first image processing means generates the performer identification information and before the second image processing means generates the state information. Equipped with information acquisition means
The image used when the first image processing means generated the performer identification information corresponding to the infected person identification information, and the second image processing means generated the performer identification information. To generate the above state information using
After that, the risk information generating means generates the infection risk information, and the infection risk information is generated.
Further, a risk information generation device including a risk information output means for outputting the infection risk information together with the peripheral person identification information corresponding to the infection risk information.
In the risk information generator according to claim 4 or 5.
The risk information output means is a risk information generation device that outputs the infection risk information satisfying the criteria together with the peripheral person identification information corresponding to the infection risk information.
In the risk information generator according to any one of claims 4 to 6.
When a plurality of the infection risk information correspond to one peripheral person identification information, the risk information output means corresponds to the one peripheral person identification information by using the plurality of infection risk information. A risk information generator that generates integrated risk information.
In the risk information generator according to any one of claims 4 to 7.
The risk information output means is
The infection risk information to be output and the peripheral person identification information are associated with each other and stored in the high-risk person storage means.
Further, when the person identification information corresponding to the peripheral person identification information is acquired from the terminal, the infection risk information corresponding to the peripheral person identification information is read out from the high-risk person storage means and output to the terminal. Information generator.
In the risk information generator according to any one of claims 1 to 8.
The particular event is a risk information generator, which is at least one of coughing, sneezing, speaking without a covering over the mouth, and meeting the criteria for density.
In the risk information generator according to claim 9,
The risk information generating means is a risk information generating device that changes a method of generating the infection risk information from the state information according to the type of the specific event.
In the risk information generator according to any one of claims 1 to 10.
The state information includes at least one of a posture, a direction of a face or a line of sight, and the presence or absence of an attachment covering the mouth, a risk information generator.
In the risk information generator according to any one of claims 1 to 11.
The state information is a risk information generator including the relative orientation of the peripheral person and the event executor.
In the risk information generator according to any one of claims 1 to 12,
The particular event is at least one of coughing, sneezing, and speech.
A voice processing means for detecting the occurrence of the specific event by processing voice information indicating voice generated in at least a part of the target area is provided.
The first image processing means is a risk information generation device that further generates the performer identification information using the processing result of the voice processing means.
In the risk information generator according to any one of claims 1 to 12,
The particular event is at least one of coughing, sneezing, and speech.
A voice processing means for specifying the loudness of the sound generated in the specific event specified by the first image processing means by processing voice information indicating the sound generated in at least a part of the target area is provided.
The risk information generation means is a risk information generation device that further generates the infection risk information using the loudness of the sound.
In the risk information generator according to any one of claims 1 to 14,
Further equipped with an environmental information acquisition means for acquiring environmental information regarding the environment of the target area,
The risk information generation means is a risk information generation device that further generates the infection risk information using the environmental information.
In the risk information generator according to claim 15,
The environmental information is a risk information generator including at least one of temperature, humidity, wind speed, and wind direction in the target area.
In the risk information generator according to any one of claims 1 to 16.
Further provided with an attribute information acquisition means for acquiring attribute information indicating the attributes of the surrounding person,
The risk information generation means is a risk information generation device that further generates the infection risk information by using the attribute information.
In the risk information generator according to claim 17,
The attribute is a risk information generator including age, presence / absence of chronic disease and its type, and gender.
The computer
The first image processing that generates the executor specific information that identifies the event executor who performed the specific event among the people existing in the target area by processing the image obtained by capturing the image of the target area, and the first image processing.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. Second image processing and
Risk information generation processing that generates infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons using the peripheral person identification information and the state information.
How to generate risk information.
On the computer
A first image processing function that generates executor-specific information that identifies an event executor who has performed a specific event among the people existing in the target area by processing an image obtained by capturing an image of the target area.
By processing the image, peripheral person identification information that identifies a peripheral person whose relative position from the event executor meets the criteria, and state information indicating the state of at least one of the event executor and the peripheral person are generated. The second image processing function and
A risk information generation function that uses the peripheral person identification information and the state information to generate infection risk information regarding the risk of the person getting an infectious disease for each of the peripheral persons.
A program to have.