Risk information generation program, risk information generation method, risk information generation device, and risk information generation system
The system processes images and audio to assess infection risk between unknown individuals, providing accurate risk information and reducing disease spread by identifying high-risk interactions and environmental factors.
Patent Information
- Application Number
- JP2022563281
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-11-17
- Publication Date
- 2025-05-20
- Estimated Expiration
- 2040-11-17
AI Technical Summary
Existing technologies fail to effectively generate risk information about the spread of infectious diseases between individuals who do not know each other, particularly in crowded areas or facilities.
A system that processes images from multiple cameras to identify individuals and determine their states, generating infection risk information based on their interactions and environmental factors, using machine learning models and audio processing to detect specific events like sneezing or coughing, and integrating environmental data to assess the risk of disease transmission.
Enables the generation of accurate infection risk information for individuals who may not know each other, reducing the spread of infectious diseases by identifying high-risk situations and notifying relevant parties.
Smart Images

Figure 0007679840000001 
Figure 0007679840000002 
Figure 0007679840000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a risk information generation device, a risk information generation method, and a program. [Background technology]
[0002] Examples of infection routes for infectious diseases include droplet infection and airborne infection. In infectious diseases that have these infection routes, people who come close to an infected person are at risk of contracting the infection. Patent Document 1 describes a method for measuring the conversation time between a resident and a visitor at a specified facility by processing an image, and transmitting information to a terminal device indicating that the resident is at high risk of contracting the infectious disease when the conversation time exceeds a specified time. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] International Publication No. 2019 / 239813 Summary of the Invention [Problem to be solved by the invention]
[0004] In areas or facilities where a large number of people are present, there is a risk of infectious diseases spreading between people who do not know each other. One object of the invention is to be able to generate information about the risk of infectious diseases spreading even between people who do not know each other. [Means for solving the problem]
[0005] According to the present invention, A process of acquiring an image; A process of identifying a first person and a second person appearing in the video; A process of determining a state of the first person; A process of determining a state of the second person; A process of determining infection risk information of the second person based on the status of the first person and the status of the second person; A risk information generating program that causes a computer to execute is provided. According to the present invention, a process for acquiring an image is provided. A process of identifying a first person and a second person appearing in the video; A process of determining a state of the first person; A process of determining a state of the second person; A process of determining infection risk information of the second person based on the status of the first person and the status of the second person; The present invention provides a risk information generating method that is executed by a computer.
[0006] According to the present invention, an image processing unit that acquires a video, identifies a first person and a second person appearing in the video, and obtains a state of the first person and a state of the second person; A risk information generation unit that obtains infection risk information of the second person based on the state of the first person and the state of the second person; A risk information generating device having is provided.
[0007] According to the present invention, an image processing unit that acquires a video, identifies a first person and a second person appearing in the video, and obtains a state of the first person and a state of the second person; A risk information generation unit that obtains infection risk information of the second person based on the state of the first person and the state of the second person; A risk information generation device having A visitor management device that stores information on visitors to the target area; Risk information generation system having is provided. Effect of the Invention
[0008] The invention makes it possible to generate information about the risk of spreading infectious diseases even between people who do not know each other. [Brief description of the drawings]
[0009] The above objects, as well as other objects, features and advantages, will become more apparent from the following preferred embodiments and the accompanying drawings.
[0010] [Figure 1] FIG. 2 is a diagram for explaining the usage environment of the risk information generation device according to the first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a functional configuration of a risk information generation device. [Diagram 3] FIG. 13 is a diagram illustrating an example of information stored in a processing result storage unit. [Figure 4] FIG. 11 is a diagram showing an example of information stored in a high-risk individual storage unit. [Diagram 5] FIG. 2 is a diagram illustrating an example of a hardware configuration of a risk information generation device. [Figure 6]4 is a flowchart showing a first example of processing performed by the risk information generation device. [Figure 7] 11 is a flowchart showing a first example of processing performed by an infection information acquisition unit and a risk information output unit of the risk information generation device. [Figure 8] 13 is a flowchart showing a second example of processing performed by the infection information acquisition unit and the risk information output unit of the risk information generation device. [Figure 9] FIG. 11 is a diagram illustrating an example of the functional configuration of a risk information generation device according to the second embodiment. [Figure 10] 10 shows a first example of processing performed by the risk information generation device shown in FIG. 9, and corresponds to FIG. 6 of the first embodiment. [Figure 11] 8 shows a second example of the processing performed by the risk information generation device shown in FIG. 9, and corresponds to FIG. 8 of the first embodiment. [Figure 12] FIG. 13 is a diagram illustrating an example of the functional configuration of a risk information generation device according to the third embodiment. [Figure 13] FIG. 13 is a diagram illustrating an example of the functional configuration of a risk information generation device according to the fourth embodiment. [Figure 14] FIG. 13 is a diagram for explaining the usage environment of the risk information generation device according to the fifth embodiment. [Figure 15] 10 is a diagram showing an example of visitor information stored in a visitor management device. FIG. [Figure 16] A diagram showing an example of the functional configuration of a risk information generation device according to the sixth embodiment. [Figure 17] FIG. 17 is a diagram illustrating an example of a functional configuration of a risk information generation device according to a modified example of FIG. 16. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are given the same reference numerals and the description will be omitted as appropriate.
[0012] (First embodiment) 1 is a diagram for explaining the usage environment of a risk information generation device 10 according to this embodiment. The risk information generation device 10 is used together with a plurality of imaging devices 20.
[0013] The imaging device 20 is, for example, a surveillance camera, and is installed in the target area. At least two imaging devices 20 capture partial areas of the target area that are separated from each other. The at least two imaging devices 20 may capture the same partial area from different directions. The frame rate of the images generated by the imaging device 20 is arbitrary, and may be a frame rate that produces a moving image or a frame rate that produces a still image.
[0014] The risk information generating device 10 processes images generated by the multiple imaging devices 20 to generate information (hereinafter referred to as status information) indicating the status of people who have visited the target area for each person. The status information includes the person's movement, the direction of the face or gaze, and the presence or absence of specific clothing. The risk information generating device 10 also processes images generated by the multiple imaging devices 20 to identify people who have performed a specific event (hereinafter referred to as event participants) among people present in the target area. The specific event includes actions that release droplets from the mouth, such as sneezing, coughing, and talking (especially talking without a mask). The specific event may also include a density of multiple people being equal to or greater than a reference value. Here, the reference value of density is defined, for example, as the number of people per a specified area. The risk information generating device 10 then generates information (hereinafter referred to as infection risk information) regarding the risk of people (hereinafter referred to as surrounding people) who were present around the event participant when the specific event was held contracting an infectious disease. This infection risk information is used when it is discovered that the event participant was infected with an infectious disease.
[0015] The infection risk information generated by the risk information generating device 10 is used, for example, by a management terminal 30 or a user terminal 40. The management terminal 30 is a terminal used by managers of the target area and medical personnel, and is used, for example, to grasp the overall picture of infection risk. The user terminal 40 is used by people who have visited the target area to understand their own infection risk. The management terminal 30 and the user terminal 40 may be portable terminals such as smartphones and tablets, or may be fixed terminals.
[0016] 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.
[0017] The image acquisition unit 110 acquires images generated by a plurality of image capture devices 20. The image acquisition unit 110 may acquire images in real time, or may acquire images in a batch format. When the image acquisition unit 110 acquires images in real time, there may be some time lag between the timing at which the image capture device 20 generates an image and the timing at which the image acquisition unit 110 acquires the image.
[0018] The first image processing unit 120 generates performer identification information by processing the image acquired from the imaging device 20. The performer identification information is information for identifying the event performer present in the target area, and includes, for example, an appearance feature amount obtained from the image. The appearance feature amount includes, for example, a face feature amount of the person, and may further include a feature amount of the wearable item (for example, clothing).
[0019] The first image processing unit 120 detects the occurrence of a specific event by using, for example, a posture estimation technique. In the posture estimation technique used here, posture information indicating the posture of a person is indicated by, for example, "key points" which are characteristic points such as joints, and "bones (bone links)" which indicate links between the key points. The key points are, for example, the 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. When detecting the occurrence of an event, the first image processing unit 120 uses a model generated by machine learning. This model is generated by machine learning posture information at the time when a specific event occurs.
[0020] The second image processing unit 130 processes the image acquired from the imaging device 20 to generate surrounding person identification information and status information of at least one of the event executor and the surrounding people.
[0021] The surrounding person identification information is information for identifying the surrounding person described above, and includes an appearance feature obtained from an image. A surrounding person is, for example, a person whose relative position from the event executor satisfies a criterion. In the surrounding person identification information, the appearance feature includes, for example, the face feature of the person, and may further include the feature of the person's wear (for example, clothing).
[0022] As described above, the status information includes the person's movement, the direction of the face or gaze, the presence or absence of a particular item of clothing, etc. The second image processing unit 130 may generate only the status information of the event executor, may generate only the status information of the surrounding people, or may generate both the status information of the event executor and the status information of the surrounding people. Furthermore, at least some of the items included in the status information of the event executor may be different from the items included in the status information of the surrounding people.
[0023] The risk information generating unit 140 generates infection risk information for each surrounding person using the surrounding person identification information and the status information. The infection risk information is information regarding the risk of a person contracting an infectious disease, and includes, for example, a risk score indicating the level of infection risk. When there are multiple event makers, the infection risk information is generated for each combination of the event maker and surrounding people. Also, when the same event maker has performed a specific event multiple times, the infection risk information is generated for each performed event and for each surrounding person at the event.
[0024] The risk information generation unit 140 stores the infection risk information and associated information associated with the infection risk information in the processing result storage unit 150. Details of the associated information will be described later with reference to other figures. The risk information generation unit 140 stores the infection risk information and the associated information in the processing result storage unit 150 in a state in which the combination of surrounding person identification information and perpetrator identification information corresponding to the infection risk information can be identified.
[0025] In the example shown in the figure, the processing result storage unit 150 is 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.
[0026] 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 individual memory unit 180.
[0027] The infection information acquisition unit 160 acquires information for identifying a person infected with an infectious disease (hereinafter referred to as infected person identification information). The infected person identification information includes appearance features obtained from an image of the infected person. The appearance features are, for example, the features of the person's face, and further include the features of the person's clothing (for example) when visiting the target area. The infection information acquisition unit 160 acquires the infected person identification information from, for example, the management terminal 30.
[0028] When the perpetrator identifying information corresponding to the infected person identifying information acquired by the infection information acquisition unit 160 is stored in the processing result storage unit 150, the risk information output unit 170 reads out the infection risk information corresponding to the perpetrator identifying information from the processing result storage unit 150 together with the surrounding person identifying information corresponding to the infection risk information. The risk information output unit 170 then outputs the read infection risk information and surrounding person identifying information. The output destination of these is, for example, the management terminal 30, but may be other terminals. The risk information output unit 170 may further read and output other information (for example, at least a part of the associated information) from the processing result storage unit 150. In this output, when multiple sets of infection risk information and surrounding person identifying information are read out, the risk information output unit 170 may arrange the surrounding person identifying information and infection risk information in order of risk score.
[0029] Furthermore, the risk information output unit 170 stores the output infection risk information and surrounding person identification information in the high-risk individual storage unit 180 in association with each other.
[0030] The infection information acquisition unit 160 also acquires from the user terminal 40 the person identification information of the person for whom the infection risk information is to be confirmed. The type of this person identification information includes appearance features obtained from an image, similar to the surrounding person identification information. The appearance features are, for example, the face features of the person, but may also include features of the person's clothing when visiting the target area. Then, when surrounding person identification information corresponding to the user identification information is stored in the high-risk person storage unit 180, the risk information output unit 170 reads out the infection risk information corresponding to the surrounding person identification information from the high-risk person storage unit 180 and transmits it to the user terminal 40. This allows people who have visited the target area to easily check their own infection risk information.
[0031] In the example shown in the figure, the high-risk individual storage unit 180 is part of the risk information generation device 10. However, the high-risk individual storage unit 180 may be provided outside the risk information generation device 10.
[0032] 1, 2, and FIG. 5 described later, the risk information generation device 10 is configured with one piece of hardware (e.g., a server). However, the risk information generation device 10 may be configured with multiple pieces of hardware (e.g., multiple servers). For example, the image acquisition unit 110, the first image processing unit 120, and the second image processing unit 130 may be realized by a first server, the risk information generation unit 140 may be realized by a second server, and the risk information output unit 170 may be realized by a third server. Also, the image acquisition unit 110, the first image processing unit 120, the second image processing unit 130, and the risk information generation unit 140 may be realized by the first server, and the risk information output unit 170 may be realized by the second server.
[0033] 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 associated information in a state in which a combination of surrounding person identification information and perpetrator identification information corresponding to the infection risk information can be identified.
[0034] In the example shown in the figure, the processing result storage unit 150 stores, for each specific event that has occurred, event performer identification information, surrounding person identification information, infection risk information, and associated information. The associated information is, for example, the type of event that has occurred, the timing (e.g., the date and time) and location of the event, status information of the event performer when the event occurred, an image at the time of the event occurrence (which may include images before and after), and status information of surrounding people when the event occurred.
[0035] The status information includes at least one of posture (e.g., at least one of the vertical tilt and horizontal orientation of the body), the direction of the face or gaze, and the presence or absence of an article of clothing covering the mouth (e.g., a mask, scarf, face guard, etc.).
[0036] Additionally, the event maker's status information may include information regarding the event that occurred.
[0037] For example, when the event that has occurred is an action that causes droplets to fly, such as sneezing, coughing, and talking without covering the mouth, the state information includes the range or distance where the droplets are estimated to have flowed. The first image processing unit 120 estimates this information using, for example, the direction of the face of the event performer when the event occurs, the presence or absence and type of an article covering the mouth, and the change in the posture of the event performer when the event occurs. For example, when the event is sneezing or coughing, the range or distance where the droplets are estimated to have flowed increases as the change in posture at the time of the event increases. Also, when the event is sneezing or coughing, if there is no article covering the mouth, the range or distance where the droplets are estimated to have flowed increases compared to when there is an article covering the mouth. Also, even if there is an article covering the mouth, the range or distance where the droplets are estimated to have flowed changes depending on the type of the article.
[0038] If the event that has occurred is congestion, the status information also includes the degree of congestion, i.e., the number of people per unit area, and the size of the area where people are crowded together.
[0039] The status information of the surrounding people may also include the relative orientation of the surrounding people and the event performer. This orientation is, for example, the relative orientation of the face, and is specified using the orientation of the face or gaze of the event performer and the orientation of the face or gaze of the surrounding people. The status information of the surrounding people may also include the relative distance between the surrounding people and the event performer.
[0040] 4 is a diagram showing an example of information stored in the high-risk individual storage unit 180. As described above, the high-risk individual storage unit 180 stores the infection risk information and the surrounding person identification information read by the risk information output unit 170 from the processing result storage unit 150 in association with each other. In the example shown in this figure, the high-risk individual storage unit 180 also stores the perpetrator identification information. The risk information output unit 170 also reads this perpetrator identification information from the processing result storage unit 150 and stores it in the high-risk individual storage unit 180. The risk information output unit 170 may also read at least a part of the associated information from the processing result storage unit 150 and store it in the high-risk individual storage unit 180.
[0041] Note that one person may be exposed to the risk of infection multiple times. Specific examples include the case where the same event entrant causes a specific event consecutively (e.g., repeated sneezing or coughing), or the person is in close proximity to multiple event entrants at different times. In such cases, multiple pieces of infection risk information are generated for the same person. The high-risk person storage unit 180 then links multiple pieces of infection risk information to one piece of surrounding person identification information. In addition, the high-risk person storage unit 180 also stores, for each piece of infection risk information, the entrant identification information of the entrant who caused the infection risk information, the type of event, the infection risk information, and associated information.
[0042] Then, the risk information output unit 170 generates integrated risk information by integrating the multiple pieces of infection risk information for that one piece of surrounding person identification information. The integrated risk information includes, for example, an integrated risk score. The integrated risk score is a score obtained by integrating the risk scores of each of the multiple pieces of infection risk information. The integrated risk score is generated, for example, by adding up the multiple risk scores, but the method of generating the integrated risk score is not limited to this.
[0043] When new infection risk information corresponding to certain surrounding person identifying information is added to the high-risk individual storage unit 180, the risk information output unit 170 updates the integrated risk information corresponding to that surrounding person identifying information.
[0044] 5 is a diagram showing an example of the hardware configuration of the risk information generation device 10. The risk information generation device 10 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.
[0045] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.
[0046] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.
[0047] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.
[0048] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, or a read only memory (ROM), etc. The storage device 1040 stores program modules that realize each function of the risk information generation device 10 (e.g., the image acquisition unit 110, the first image processing unit 120, the second image processing unit 130, the risk information generation unit 140, the infection information acquisition unit 160, and the risk information output unit 170). The processor 1020 loads each of these program modules onto the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 also functions as a processing result storage unit 150 and a high-risk individual storage unit 180.
[0049] The input / output interface 1050 is an interface for connecting the risk information generation device 10 to various input / output devices.
[0050] The network interface 1060 is an interface for connecting the risk information generation device 10 to a network. This network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method for 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 imaging device 20, the management terminal 30, and the user terminal 40 via the network interface 1060.
[0051] 6 is a flowchart showing a first example of processing performed by the risk information generation device 10. This diagram shows 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. Every time the risk information generation device 10 acquires an image from the imaging device 20, it performs the processing shown in this diagram on the acquired image.
[0052] First, the image acquisition unit 110 of the risk information generation device 10 acquires an image. The first image processing unit 120 then processes this image to determine whether a specific event has occurred, i.e., whether an event performer is present (step S10). If an event performer is present (step S10: Yes), the first image processing unit 120 generates performer identification information and status information of the event performer (step S20). As described with reference to FIG. 3, this status information includes information about the event that has occurred (for example, the range or distance where droplets are estimated to have been scattered).
[0053] Next, the second image processing unit 130 processes the image acquired from the imaging device 20 to generate surrounding person identification information and surrounding person status information (step S30).
[0054] Next, the risk information generating 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 a risk score as described above. The risk information generating unit 140 may change the method of generating infection risk information from status information depending on the type of the event that has occurred. This change may be to change the arithmetic equation for calculating the risk score, or may be to change the coefficients of this arithmetic equation.
[0055] As an example, the risk information generation unit 140 calculates a proximity score and a droplet score, and determines a risk score by integrating (for example, adding) these scores.
[0056] The proximity score is a score that is uniformly given to surrounding people whose relative distance from the event performer is equal to or less than a reference value when the event occurs. As a result, the risk scores of the surrounding people whose relative distance is equal to or less than the reference value are higher than the risk scores of surrounding people whose relative distance is greater than the reference value. This reference value may be changed depending on the type of the event that has occurred. This reference value may also be changed depending on the type of infectious disease being targeted.
[0057] In addition, if the status information includes a range or distance within which the droplets are estimated to have been scattered, this range or distance may be used in assigning the proximity score instead of the relative distance described above.
[0058] The droplet score is a score whose variable is the magnitude of the relative distance from the event maker. The droplet score increases as the relative distance decreases. At least one of the formula for calculating the droplet score from the relative distance and the coefficients used in this formula may be changed depending on the type of infectious disease being targeted.
[0059] The droplet score may be changed using the relative orientation with respect to the event executor. For example, the droplet score may be increased as the relative orientation approaches a straight-on orientation.
[0060] The risk information generating unit 140 may also modify the risk score using the presence or absence of an attachment covering the mouth of a nearby person. As an example, the risk information generating unit 140 reduces the risk score when a nearby person is wearing an attachment covering the mouth.
[0061] Next, the risk information generation unit 140 stores the infection risk information and associated information in the processing result storage unit 150 in a state in which a combination of surrounding person identification information and perpetrator identification information corresponding to the infection risk information can be identified (Step S50).
[0062] 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.
[0063] When an infected person is found, the person who operates the management terminal 30 inputs infected person identification information to the infection information acquisition unit 160 (step S110). Next, the risk information output unit 170 judges whether or not perpetrator 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). If such perpetrator identification information is recorded (step S120: Yes), the risk information output unit 170 reads out the surrounding person identification information and the infection risk information corresponding to the perpetrator identification information from the processing result storage unit 150 (step S130) and outputs the read out 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 the associated information) as necessary and output it to the management terminal 30. Then, the management terminal 30 displays the output information. This allows the user of the management terminal 30 to easily identify people who are likely to be infected with an infectious disease.
[0064] In addition, the risk information output unit 170 stores the information read out in step S130 in the high-risk individual memory unit 180, and updates the integrated risk information of the surrounding individual identification information corresponding to this infection risk information using the infection risk information newly stored in the high-risk individual memory unit 180 (step S150).
[0065] FIG. 8 is a flowchart showing a second example of the process performed by the infection information acquisition unit 160 and the risk information output unit 170 of the risk information generation device 10. The process shown in this figure is the same as the process shown in FIG. 7, except that the risk information output unit 170 reads out only combinations of the infection risk information that meet the criteria from the processing result storage unit 150 among the surrounding person identification information and the infection risk information corresponding to the perpetrator identification information (step S132) and outputs them to the management terminal 30 (step S140). The criteria for the infection risk information is, for example, "the risk score is equal to or greater than a reference value." Therefore, the risk information output unit 170 outputs only combinations of the infection risk information that meet the criteria from the surrounding person identification information and the infection risk information corresponding to the perpetrator identification information to the management terminal 30, and stores them in the high-risk person storage unit 180.
[0066] According to the example shown in this figure, the surrounding people to be output are limited to those whose infection risk information meets the criteria, so the reliability of the output information (and the information stored in the high-risk individual memory unit 180) is high.
[0067] When all images generated by the imaging device 20 are stored, the risk information output unit 170 may process these images to identify people (hereinafter referred to as nearby people) who have come close to the person corresponding to the infected person identification information at a time when the above-mentioned specific event has not occurred, and store information identifying these nearby people (hereinafter referred to as nearby person identification information) in the high-risk person storage unit 180. The nearby person identification information includes, for example, external appearance features of the nearby person (for example, facial features and features of clothing).
[0068] In this way, the risk information output unit 170 can output and display nearby person identification information on the management terminal 30, thereby allowing the user of the management terminal 30 to recognize nearby persons. Furthermore, when acquiring personal identification information of a person for whom infection risk information is to be confirmed from the user terminal 40, the risk information output unit 170 determines whether or not that person corresponds to a nearby person, and transmits the determination result to the user terminal 40. This allows people who have visited the target area to easily check whether or not they have come into close proximity with an infected person.
[0069] As described above, according to this embodiment, the risk information generation device 10 processes images to detect an event maker who has performed a specific event, such as sneezing or coughing, and then detects people around the event maker. The risk information generation device 10 then generates infection risk information related to the infection risk of the people around the event maker, and stores this in the processing result storage unit 150. Therefore, information on the risk of an infectious disease spreading can be generated even between people who do not know each other.
[0070] Furthermore, when the risk information generation device 10 obtains infected person identification information that identifies a person infected with an infectious disease from the management terminal 30, it judges whether or not the person indicated by this infected person identification information was the event entrant. If the person was the event entrant, the risk information generation device 10 reads out from the processing result storage unit 150 the person identification information of people who were nearby when the event took place (i.e., surrounding person identification information) and infection risk information, and outputs them to the management terminal 30. Therefore, a user of the risk information generation device 10 (for example, an operator of the management terminal 30) can easily identify people who are likely to be infected with an infectious disease.
[0071] In addition, since image processing is terminated before acquiring infected person identification information and various information including the processing results are stored in the processing result memory unit 150, the load on the risk information generating device 10 after acquiring infected person identification information can be reduced.
[0072] Second embodiment 9 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to this embodiment. The risk information generation device 10 according to this embodiment has the same configuration as the risk information generation device 10 according to the first embodiment, except for the following points.
[0073] First, the processing result storage unit 150 stores information about the performer (for example, the performer identification information, the type of event, the performer's status information, and the image shown in FIG. 3), but does not store information about surrounding people. The processing result storage unit 150 is updated by the first image processing unit 120.
[0074] 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 individual identifying information. In other words, the infection information acquisition unit 160 acquires the infected individual identifying information after the first image processing unit 120 performs processing and before the second image processing unit 130 and the risk information generation unit 140 perform processing. The risk information output unit 170 also outputs the information generated by the second image processing unit 130 and the risk information generation unit 140, and updates the high-risk individual storage unit 180 using this information.
[0075] Fig. 10 shows a first example of the processing performed by the risk information generating device 10 shown in Fig. 9, and corresponds to Fig. 6 of the first embodiment. In this figure, the processing shown in steps S10 and S20 is as explained in Fig. 6. After step S20, the first image processing unit 120 stores the performer identifying information, the type of event, the performer's status information, and the image in the processing result storage unit 150 (step S50).
[0076] FIG. 11 shows a second example of the processing performed by the risk information generation device 10 shown in FIG. 9, and corresponds to FIG. 8 of the first embodiment.
[0077] The processes shown in steps S110 and S120 are the same as steps S110 and S120 in FIG. 8 (i.e., steps S110 and S120 in FIG. 7). If the perpetrator identifying information corresponding to the infected person identifying information is stored in the processing result storage unit 150 (step S120: Yes), the second image processing unit 130 reads out an image corresponding to this perpetrator identifying information (i.e., the image used to generate this perpetrator identifying information) from the processing result storage unit 150 (step S122), and performs the same process as step S30 in FIG. 6 on the read image (step S124). As a result, surrounding person identifying information and status information corresponding to the perpetrator who performed the specific event are generated. Then, the risk information generating 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 in FIG. 6.
[0078] The processes that are carried out thereafter (steps S132 to S150) are the same as those in Fig. 8. Note that instead of step S132 in this figure, the process described in step S130 in Fig. 7 may be carried out.
[0079] As described above, according to this embodiment, a user of the risk information generation device 10 (for example, an operator of the management terminal 30) can easily identify people who are likely to be infected with an infectious disease, as in the first embodiment. Furthermore, the second image processing unit 130 and the risk information generation unit 140 perform processing after acquiring the infected person identification information. For this reason, the second image processing unit 130 and the risk information generation unit 140 do not process event executors who do not correspond to the infected person identification information. Therefore, the overall amount of processing performed by the risk information generation device 10 can be reduced.
[0080] Third embodiment 12 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to this 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 it includes a voice processing unit 190.
[0081] The audio processing unit 190 acquires a plurality of pieces of audio information indicating sounds generated in at least a part of the target area. The audio information is generated by a plurality of microphones provided in the target area. The microphones may be provided in the imaging device 20, or may be provided as devices separate from the imaging device 20. The positions of the plurality of microphones are such that when a sound is generated in the target area, the position of the sound can be specified by analyzing the plurality of pieces of audio information. The audio processing unit 190 processes the plurality of pieces of audio information to specify the type of event that caused the sound (e.g., sneezing, coughing, and speaking), and also specifies the position and volume of the sound. Here, the audio processing unit 190 calculates the absolute volume of the sound by correcting the intensity of the sound indicated by the audio signal using the relative distance between the microphone that generated the audio signal and the position of the sound.
[0082] The first image processing unit 120 identifies the performer identification information only by image processing as in the above embodiment, and generates the performer identification information using the generation position of the sound generated by the audio processing unit 190. For example, when a sound is caused by a specific event, the audio processing unit 190 processes the image at the time when the sound is generated to identify a person who was present at the generation position of the sound, and the information identifying this person is the performer identification information. In this way, even if the face of the event performer is not shown in the image, for example, the occurrence of a specific event can be detected, and the performer identification information of the event performer can also be generated. Note that when the face of the event performer is not included in the image at the time when the specific event occurs, the first image processing unit 120 may process the image before or after the event occurrence to track the event performer and identify an image in which the face of the event performer is shown, and generate the performer identification information using this image.
[0083] Furthermore, the risk information generation unit 140 generates infection risk information using the volume of the sound generated by the audio processing unit 190. For example, the risk information generation unit 140 increases the reference value of the relative distance used to assign the proximity score as the volume of the sound increases. Furthermore, the risk information generation unit 140 may increase the droplet score as the volume of the sound increases. This processing is performed both when the perpetrator identification information can be identified by image processing alone and when the perpetrator identification information can be identified using information generated by the audio processing unit 190.
[0084] In the former case, the first image processing unit 120 identifies the performer identification information and the position of the event performer by image processing. Then, when the position identified by image processing overlaps with the generation position of the sound generated by the sound processing unit 190, the first image processing unit 120 processes the volume of the sound corresponding to the generation position as the volume of the sound generated by the event performer.
[0085] The volume of the sound generated by the sound processor 190 may be used when calculating the range or distance over which the droplets are estimated to have flown. For example, the second image processor 130 increases the range or distance over which the droplets are estimated to have flown as the sound becomes louder.
[0086] Moreover, the risk information generation device 10 shown in the second embodiment may have the functions shown in this embodiment.
[0087] As described above, according to this embodiment, a user of the risk information generation device 10 (e.g., an operator of the management terminal 30) can easily identify people who are likely to be infected with an infectious disease, as in the first embodiment. Furthermore, the risk information generation device 10 processes audio information indicating sounds generated in the target area, and generates infection risk information using the processing results. Therefore, the risk information generation device 10 can generate infection risk information with even greater accuracy.
[0088] (Fourth embodiment) 13 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to this embodiment. The risk information generation device 10 according to this embodiment has the same configuration as the risk information generation device 10 according to the first embodiment, except that it includes an environmental information acquisition unit 200.
[0089] The environmental information acquisition unit 200 acquires information about the environment of the target area (hereinafter referred to as environmental information). The environmental information indicates, for example, at least one of the changes in temperature, humidity, wind speed, and wind direction in the target area. The risk information generation unit 140 further generates infection risk information using the environmental information.
[0090] For example, the risk information generating unit 140 performs a predetermined calculation on at least one of the proximity score and the droplet score. The risk information generating unit 140 then sets this calculation formula or the coefficients included in this calculation formula using 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 generating unit 140 sets the risk score to be larger as the temperature and humidity decrease. In addition, the risk information generating unit 140 sets the risk score to be smaller as the wind speed increases.
[0091] Furthermore, when the environmental information includes wind speed and wind direction, the risk information generating unit 140 may use these wind speed and wind direction to change the area in the target area to which a proximity score should be assigned, or may change at least one of the formula for calculating the droplet score from the relative distance and the coefficients used in this formula. For example, the risk information generating unit 140 widens the area to which a proximity score should be assigned on the downwind side and narrows it on the upwind side. The amount of deformation of the area at this time increases as the wind speed increases. Furthermore, the risk information generating unit 140 sets the formula for calculating the droplet score so that the droplet score is smaller on the upwind side than on the downwind side.
[0092] The risk information generation device 10 shown in the second or third embodiment may have the functions shown in this embodiment.
[0093] According to this embodiment, a user of the risk information generation device 10 (e.g., an operator of the management terminal 30) can easily identify people who are likely to be infected with an infectious disease, as in the first embodiment. Furthermore, the risk information generation device 10 generates infection risk information using environmental information that indicates the environment of the target area. Therefore, the risk information generation device 10 can generate infection risk information with even greater accuracy.
[0094] Fifth embodiment Fig. 14 is a diagram for explaining the usage environment of the risk information generation device 10 according to this embodiment, and corresponds to Fig. 1 of the first embodiment. In this embodiment, the risk information generation device 10 is used together with a visitor management device 50 in addition to an imaging device 20, a management terminal 30, and a user terminal 40.
[0095] In this embodiment, the target area includes a system for managing visitors, such as an event venue or a specific facility. The visitor management device 50 stores information on visitors to the target area (hereinafter referred to as visitor information). Visitors register their visitor information in the visitor management device 50 before or at the time of entry. The risk information generation device 10 then generates infection risk information using the visitor information stored in the visitor management device 50. If the visitor has a mobile device with a function for detecting the current location (e.g., a GPS function), the mobile device may transmit visitor information previously registered in the mobile device to the visitor management device 50 when it detects that the current location of the mobile device is within the target area.
[0096] 15 is a diagram showing an example of visitor information stored in visitor management device 50. In the example shown in this figure, the visitor information includes, for example, information for identifying a visitor (hereinafter, referred to as user identification information), attribute information, and contact information.
[0097] The user identification information is similar to the surrounding person identification information, and includes the user's appearance characteristics, such as the user's facial characteristics, but may also include the characteristics of the user's clothing. The user identification information is generated, for example, by processing an image of the user. The risk information generation device 10 can then use the user identification information and surrounding person identification information to identify the attribute information and contact information of the surrounding people.
[0098] The attribute information includes, for example, age, the presence or absence of a chronic illness and its type, and gender.
[0099] The contact information is information for contacting the user, and includes, for example, at least one of a phone number (including a mobile phone number), an email address, and an SNS account. By using this contact information, for example, the operator of the management terminal 30 can identify the contact information of a nearby person and notify the nearby person that there is a risk of infection with an infectious disease.
[0100] 16 is a diagram showing an example of the functional configuration of the risk information generation device 10 according to this embodiment. The risk information generation device 10 shown in this diagram has the same configuration as the risk information generation device 10 according to the first embodiment, except for the following points.
[0101] First, the risk information generation device 10 includes an attribute information acquisition unit 210. The attribute information acquisition unit 210 acquires the surrounding person identification information generated by the second image processing unit 130, and identifies user identification information that matches this surrounding person identification information from among the user identification information stored in the visitor management device 50. Then, the attribute information acquisition unit 210 acquires, from the visitor management device 50, attribute information and contact information linked to the identified user identification information.
[0102] When generating infection risk information, the risk information generating unit 140 uses the attribute information acquired by the attribute information acquiring unit 210 in addition to the information shown in the first embodiment. For example, the risk information generating unit 140 makes the risk score of a person with a specific chronic disease higher than the risk score of a person without that chronic disease for a specific infectious disease. The risk information generating unit 140 also modifies the risk score for a specific infectious disease according to age. The risk information generating unit 140 also modifies the risk score for a specific infectious disease according to gender.
[0103] Furthermore, when outputting the infection risk information and surrounding person identification information read from the infection information acquisition unit 160, the risk information output unit 170 uses the contact information acquired by the attribute information acquisition unit 210. Specifically, the risk information output unit 170 links the contact information and the infection risk information using the surrounding person identification information and the user identification information. Then, the risk information output unit 170 transmits the infection risk information to the contact information indicated in the contact information linked to the infection risk information. This allows surrounding people to recognize their own infection risk information even if they do not inquire of the risk information generation device 10.
[0104] As described with reference to Fig. 2, the infection information acquisition unit 160 acquires person identification information of a person for whom infection risk information is to be confirmed from the user terminal 40. At this time, the infection information acquisition unit 160 may acquire attribute information of that person. In this case, before transmitting infection risk information corresponding to the acquired user identification information to the user terminal 40, the risk information output unit 170 modifies the risk score using the attribute information and transmits the modified risk score to the user terminal 40.
[0105] Fig. 17 is a diagram showing an example of a functional configuration of the risk information generation device 10 according to the modified example of Fig. 16. In this modified example, the attribute information acquisition unit 210 is provided in the risk information generation device 10 shown in Fig. 9.
[0106] In this modified example, the attribute information and 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 correction is similar to the example performed by the risk information generation unit 140 shown in FIG.
[0107] Among the attribute information, the age and gender may be generated by processing images of people nearby.
[0108] According to this embodiment, a user of the risk information generating device 10 (e.g., an operator of the management terminal 30) can easily identify people who are likely to be infected with an infectious disease, as in the first embodiment. In addition, the risk score can be modified according to the attributes of surrounding people. Furthermore, even if there is no inquiry from a surrounding person, the infection risk information can be notified to the surrounding people.
[0109] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various configurations other than those described above can also be adopted.
[0110] In addition, in the flowcharts used in the above description, multiple steps (processes) are described in order, but the order of execution of the steps performed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the figures can be changed to the extent that the content is not affected. In addition, the above-mentioned embodiments can be combined to the extent that the content is not contradictory.
[0111] A part or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. A first image processing means for generating event executor identification information for identifying an event executor who performed a specific event among people present in the target area by processing an image captured in the target area; a second image processing means for processing the image to generate surrounding person identification information for identifying surrounding people whose relative positions from the event person satisfy a criterion, and status information indicating a status of at least one of the event person and the surrounding people; a risk information generating means for generating infection risk information regarding a risk of each of the surrounding persons contracting an infectious disease, for each of the surrounding persons, using the surrounding person identification information and the status information; A risk information generating device comprising: 2. In the risk information generation device according to the above item 1, The second image processing means identifies the relative distance between the event entrant and the surrounding people as at least a part of the status information, in the risk information generation device. 3. In the risk information generation device according to the above item 2, The infection risk information includes a risk score indicating a level of infection risk, The risk information generation means of the risk information generation device increases the risk score of the surrounding person whose relative distance is less than or equal to a standard value compared to the risk score of the surrounding person whose relative distance is greater than the standard value. 4. In the risk information generation device according to any one of 1 to 3 above, the risk information generation means stores the infection risk information in a processing result storage means in a state in which a combination of the surrounding person identification information and the perpetrator identification information corresponding to the infection risk information can be identified; moreover, An infection information acquisition means for acquiring infected person identification information for identifying a person infected with an infectious disease; a risk information output means for reading, when the perpetrator identifying information corresponding to the infected individual identifying information is stored in the processing result storage means, from the processing result storage means, the infection risk information corresponding to the perpetrator identifying information, together with the surrounding person identifying information corresponding to the infection risk information, and outputting the infection risk information and the surrounding person identifying information; A risk information generating device comprising: 5. In the risk information generation device according to any one of 1 to 3 above, an infection information acquisition means for acquiring infected person identification information for identifying a person infected with an infectious disease after the first image processing means generates the perpetrator identification information and before the second image processing means generates the status information; the second image processing means generates the status information using the image used when the first image processing means generated the perpetrator identifying information corresponding to the infected individual identifying information; Then, the risk information generating means generates the infection risk information, The risk information generating device further comprises a risk information output means for outputting the infection risk information together with the surrounding person identification information corresponding to the infection risk information. 6. In the risk information generation device according to 4 or 5 above, The risk information output means is a risk information generating device that outputs the infection risk information that meets the criteria together with the surrounding person identification information corresponding to the infection risk information. 7. In the risk information generation device according to any one of claims 4 to 6, When multiple pieces of infection risk information correspond to one piece of surrounding person identification information, the risk information output means of the risk information generating device uses the multiple pieces of infection risk information to generate integrated risk information corresponding to the one piece of surrounding person identification information. 8. In the risk information generation device according to any one of claims 4 to 7, The risk information output means includes: The infection risk information and the surrounding person identification information are stored in a high-risk person storage means in association with each other, Furthermore, when the risk information generating device obtains person identification information corresponding to the surrounding person identification information from the terminal, it reads out the infection risk information corresponding to the surrounding person identification information from the high-risk person memory means and outputs it to the terminal. 9. In the risk information generation device according to any one of 1 to 8 above, A risk information generating device, wherein the specific event is at least one of coughing, sneezing, speaking without covering the mouth, and crowding meeting a standard. 10. In the risk information generation device according to the above item 9, The risk information generation means of the risk information generation device changes the method of generating the infection risk information from the status information depending on the type of the specific event. 11. In the risk information generation device according to any one of 1 to 10 above, The risk information generating device, wherein the status information includes at least one of posture, face or gaze direction, and the presence or absence of an attachment covering the mouth. 12. In the risk information generation device according to any one of 1 to 11 above, A risk information generating device, wherein the status information includes the relative orientation of the surrounding people and the event performer. 13. In the risk information generation device according to any one of 1 to 12 above, The particular event is at least one of a cough, a sneeze, and a speech; a sound processing means for detecting the occurrence of the particular event by processing sound information indicative of sounds occurring in at least a portion of the target area; The first image processing means further generates the perpetrator identifying information using a processing result of the audio processing means. 14. In the risk information generation device according to any one of 1 to 12 above, The particular event is at least one of a cough, a sneeze, and a speech; a sound processing unit that processes sound information indicating a sound generated in at least a part of the target area to identify a volume of a sound generated in the specific event identified by the first image processing unit; The risk information generation means further generates the infection risk information using the sound volume, this risk information generation device. 15. In the risk information generation device according to any one of 1 to 14 above, Further comprising an environmental information acquisition means for acquiring environmental information relating to an environment of the target area, The risk information generation means further generates the infection risk information using the environmental information, a risk information generation device. 16. In the risk information generation device according to claim 15, A risk information generating device, wherein the environmental information includes at least one of temperature, humidity, wind speed, and wind direction in the target area. 17. In the risk information generation device according to any one of 1 to 16 above, The information acquisition unit further includes an attribute information acquisition unit for acquiring attribute information indicating attributes of the surrounding people, The risk information generation means further generates the infection risk information using the attribute information, a risk information generation device. 18. In the risk information generation device according to claim 17, The attributes include age, presence or absence of chronic illness and its type, and gender, in a risk information generating device. 19. The computer a first image processing for generating event executor identification information for identifying an event executor who performed a specific event among people present in the target area by processing an image of the target area; a second image processing for generating surrounding person identification information for identifying surrounding people whose relative positions from the event person satisfy a criterion, and status information indicating a status of at least one of the event person and the surrounding people by processing the image; a risk information generation process for generating infection risk information regarding a risk of each of the surrounding persons contracting an infectious disease by using the surrounding person identification information and the status information; A method for generating risk information. 20. In the risk information generation method according to claim 19, A risk information generation method in which, in the second image processing, the computer identifies the relative distance between the event executor and the surrounding people as at least part of the status information. 21. The risk information generation method according to claim 20, The infection risk information includes a risk score indicating a level of infection risk, A risk information generation method in which, in the risk information generation process, the computer increases the risk score of the surrounding person whose relative distance is below a standard value compared to the risk score of the surrounding person whose relative distance is above the standard value. 22. In the risk information generation method according to any one of claims 19 to 21, In the risk information generation process, the computer stores the infection risk information in a processing result storage means in a state in which a combination of the surrounding person identification information and the perpetrator identification information corresponding to the infection risk information can be identified; Furthermore, the computer An infection information acquisition process for acquiring infected person identification information for identifying a person infected with an infectious disease; a risk information output process for reading, when the perpetrator identifying information corresponding to the infected individual identifying information is stored in the processing result storage means, from the processing result storage means, the infection risk information corresponding to the perpetrator identifying information, together with the surrounding person identifying information corresponding to the infection risk information, and outputting the infection risk information and the surrounding person identifying information; A method for generating risk information. 23. In the risk information generation method according to any one of claims 19 to 21, The computer includes: performing an infection information acquisition process for acquiring infected person identification information for identifying a person infected with an infectious disease after generating the executer identification information in the first image processing and before generating the status information in the second image processing; in the second image processing, when the perpetrator identifying information corresponding to the infected individual identifying information is generated in the first image processing, the status information is generated using the image used when the perpetrator identifying information is generated, Then, the risk information generation process generates the infection risk information, The risk information generating method further comprises a risk information output process for outputting the infection risk information together with the surrounding person identification information corresponding to the infection risk information. 24. The risk information generation method according to claim 22 or 23, A risk information generating method in which, in the risk information output process, the computer outputs the infection risk information that meets a criteria together with the surrounding person identification information corresponding to the infection risk information. 25. In the risk information generation method according to any one of claims 22 to 24, A risk information generation method in which, when multiple pieces of infection risk information correspond to one piece of surrounding person identification information, in the risk information output process, the computer uses the multiple pieces of infection risk information to generate integrated risk information corresponding to the one piece of surrounding person identification information. 26. In the risk information generation method according to any one of claims 22 to 25, In the risk information output process, the computer The infection risk information and the surrounding person identification information are stored in a high-risk person storage means in association with each other, Furthermore, when personal identification information corresponding to the surrounding person identification information is obtained from the terminal, the risk information generating method reads out the infection risk information corresponding to the surrounding person identification information from the high-risk person memory means and outputs it to the terminal. 27. In the risk information generation method according to any one of claims 19 to 26, The risk information generating method, wherein the specific event is at least one of coughing, sneezing, speaking without covering the mouth, and crowding meeting a standard. 28. The risk information generation method according to claim 27, A risk information generation method in which, in the risk information generation process, the computer changes a method of generating the infection risk information from the status information depending on the type of the specific event. 29. In the risk information generation method according to any one of claims 19 to 28, A risk information generating method, wherein the status information includes at least one of posture, face or gaze direction, and the presence or absence of an attachment covering the mouth. 30. In the risk information generation method according to any one of claims 19 to 29, A risk information generating method, wherein the status information includes a relative orientation between the surrounding people and the event performer. 31. In the risk information generation method according to any one of claims 19 to 30, The particular event is at least one of a cough, a sneeze, and a speech; The computer includes: processing audio information indicative of audio occurring within at least a portion of the region of interest to detect the occurrence of the particular event; A risk information generating method, comprising: in the first image processing, further generating the perpetrator identifying information using a processing result of the audio processing. 32. In the risk information generation method according to any one of claims 19 to 30, The particular event is at least one of a cough, a sneeze, and a speech; The computer includes: performing audio processing to identify the volume of the sound generated in the specific event identified in the first image processing by processing audio information indicating the sound generated in at least a part of the target area; A risk information generation method, in which the risk information generation process further generates the infection risk information using the sound volume. 33. In the risk information generation method according to any one of claims 19 to 32, The computer includes: further performing an environment information acquisition process for acquiring environment information related to the environment of the target area; A risk information generation method, in which the risk information generation process further generates the infection risk information using the environmental information. 34. In the risk information generation method according to claim 33, A risk information generating method, wherein the environmental information includes 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 claims 19 to 34, The computer includes: further performing an attribute information acquisition process for acquiring attribute information indicating attributes of the surrounding people; A risk information generation method, in which the risk information generation process further generates the infection risk information using the attribute information. 36. In the risk information generation method according to claim 35, A risk information generating method, wherein the attributes include age, presence or absence of a chronic illness and its type, and gender. 37. To the computer, a first image processing function for generating event executor identification information for identifying an event executor who performed a specific event among people present in the target area by processing an image of the target area; a second image processing function for generating, by processing the image, surrounding person identification information for identifying surrounding people whose relative positions from the event person satisfy a criterion, and status information indicating a status of at least one of the event person and the surrounding people; a risk information generating function that generates infection risk information regarding a risk of each of the surrounding persons contracting an infectious disease by using the surrounding person identification information and the status information; A program that allows you to have 38. In the program according to 37 above, The second image processing function is a program for identifying a relative distance between the event performer and the surrounding people as at least a part of the status information. 39. In the program according to 38 above, The infection risk information includes a risk score indicating a level of infection risk, The risk information generation function is a program that increases the risk score of the surrounding person whose relative distance is below a standard value compared to the risk score of the surrounding person whose relative distance is above the standard value. 40. In the program according to any one of the above items 37 to 39, the risk information generation function stores the infection risk information in a processing result storage means in a state in which a combination of the surrounding person identification information and the perpetrator identification information corresponding to the infection risk information can be identified; The computer further comprises: An infection information acquisition function that acquires infection identification information to identify people infected with an infectious disease; a risk information output function that, when the perpetrator identifying information corresponding to the infected individual identifying information is stored in the processing result storage means, reads out from the processing result storage means the infection risk information corresponding to the perpetrator identifying information together with the surrounding person identifying information corresponding to the infection risk information, and outputs the infection risk information and the surrounding person identifying information; A program that allows you to have 41. In the program according to any one of the above items 37 to 39, the computer has an infection information acquisition function for acquiring infected person identification information for identifying a person infected with an infectious disease after the first image processing function generates the perpetrator identification information and before the second image processing function generates the status information; the second image processing function generates the status information using the image used when the first image processing function generated the perpetrator identifying information corresponding to the infected individual identifying information; Then, the risk information generation function generates the infection risk information, The program further comprises a risk information output function for outputting the infection risk information together with the surrounding 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 that meets the criteria together with the surrounding person identification information corresponding to the infection risk information. 43. In the program according to any one of the above 40 to 42, When multiple pieces of infection risk information correspond to one piece of surrounding person identification information, the risk information output function is a program that uses the multiple pieces of infection risk information to generate integrated risk information corresponding to the one piece of surrounding person identification information. 44. In the program according to any one of the above 40 to 43, The risk information output function is The infection risk information and the surrounding person identification information are stored in a high-risk person storage means in association with each other, Furthermore, when personal identification information corresponding to the surrounding person identification information is obtained from the terminal, the program reads out the infection risk information corresponding to the surrounding person identification information from the high-risk person storage means and outputs it to the terminal. 45. In the program according to any one of the above 37 to 44, The particular event is at least one of a cough, a sneeze, speaking without covering the mouth, and meeting a crowding criterion. 46. In the program according to 45 above, A program in which the risk information generation function changes a method for generating the infection risk information from the status information depending on the type of the specific event. 47. In the program according to any one of the above 37 to 46, The state information includes at least one of posture, face or gaze direction, and the presence or absence of an attachment covering the mouth. 48. In the program according to any one of the above items 37 to 47, The state information includes a relative orientation between the surrounding people and the event performer. 49. In the program according to any one of the above items 37 to 48, The particular event is at least one of a cough, a sneeze, and a speech; providing the computer with audio processing capability to detect the occurrence of the particular event by processing audio information indicative of audio occurring within at least a portion of the region of interest; The first image processing function further generates the performer identifying information using a processing result of the audio processing function. 50. In the program according to any one of the above items 37 to 48, The particular event is at least one of a cough, a sneeze, and a speech; a sound processing function for processing sound information indicating a sound generated in at least a portion of the target area to identify a loudness of a sound generated in the specific event identified by the first image processing function; The risk information generation function further generates the infection risk information using the sound volume, the program. 51. In the program according to any one of the above items 37 to 50, The computer is further provided with an environmental information acquisition function for acquiring environmental information related to the environment of the target area; The risk information generation function further generates the infection risk information using the environmental information, a program. 52. In the program according to 51 above, The environmental information includes at least one of temperature, humidity, wind speed, and wind direction in the target area. 53. In the program according to any one of the above 37 to 52, The computer is further provided with an attribute information acquisition function for acquiring attribute information indicating attributes of the surrounding people, The risk information generation function further generates the infection risk information using the attribute information, the program. 54. In the program according to 53 above, The attributes include age, presence and type of chronic illness, and gender. [Explanation of symbols]
[0112] 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 Department 150 Processing result storage unit 160 Infection information acquisition department 170 Risk information output unit 180 High-Risk Persons Memory Department 190 Audio Processing Unit 200 Environmental Information Acquisition Department 210 Attribute information acquisition section
Claims
1. A process of acquiring an image; A process of identifying a first person and a second person appearing in the video; A process of determining a state of the first person; determining a state of the second person; A process of determining infection risk information of the second person based on the state of the first person and the state of the second person; a process of storing the obtained infection risk information in a storage means in association with the first person and the second person corresponding to the infection risk information; acquiring infected person identification information for identifying an infected person, and if the first person is determined to be infected, identifying the second person corresponding to the first person and the infection risk information using the storage means; A risk information generating program that causes a computer to execute the above.
2. The state of the first person includes information regarding an orientation of the first person, and the state of the second person includes information regarding an orientation of the second person.
2. The risk information generating program according to claim 1.
3. performing a process of determining an infection risk of the second person based on a distance between the first person and the second person; 2. The risk information generating program according to claim 1.
4. The closer the orientation of the first person and the orientation of the second person are to facing each other, the higher the infection risk information indicates the higher the infection risk of the second person.
3. The risk information generating program according to claim 2.
5. The closer the distance between the first person and the second person, the higher the infection risk information indicates the higher the infection risk of the second person.
4. The risk information generating program according to claim 3.
6. The first person is a person who performed a specific event related to the act of releasing droplets from the mouth.
2. The risk information generating program according to claim 1.
7. The second person is a person who was in the vicinity of the first person.
2. The risk information generating program according to claim 1.
8. When the first person is determined to be infected, the computer is caused to execute a process of identifying infection risk information that is equal to or greater than a predetermined level among the infection risk information corresponding to the first person using the storage means, and identifying the second person corresponding to the infection risk information that is equal to or greater than the predetermined level.
2. The risk information generating program according to claim 1.
9. A process of acquiring an image; A process of identifying a first person and a second person appearing in the video; A process of determining a state of the first person; determining a state of the second person; A process of determining infection risk information of the second person based on the state of the first person and the state of the second person; a process of storing the obtained infection risk information in a storage means in association with the first person and the second person corresponding to the infection risk information; acquiring infected person identification information for identifying an infected person, and if the first person is determined to be infected, identifying the second person corresponding to the first person and the infection risk information using the storage means; A risk information generating method implemented by a computer.
10. an image processing unit that acquires a video, identifies a first person and a second person appearing in the video, and obtains a state of the first person and a state of the second person; A risk information generation unit that obtains infection risk information of the second person based on the state of the first person and the state of the second person; a storage unit that stores the determined infection risk information in association with the first person and the second person corresponding to the infection risk information; an identification unit that acquires infected person identification information that identifies an infected person, and, when the first person is determined to be an infected person, identifies the second person corresponding to the first person and the infection risk information using the storage unit; A risk information generating device having the above configuration.
11. an image processing unit that acquires a video, identifies a first person and a second person appearing in the video, and obtains a state of the first person and a state of the second person; A risk information generation unit that obtains infection risk information of the second person based on the state of the first person and the state of the second person; A risk information generation device having A visitor management device that stores information on visitors to the target area; having The risk information generation device includes: The infection risk information thus obtained is associated with the first person and the second person corresponding to the infection risk information, and the associated information is stored in a visitor management device; A risk information generation system that acquires infected person identification information that identifies an infected person, and when the first person is determined to be infected, uses the visitor management device to identify the second person corresponding to the first person and the infection risk information.
Citation Information
Patent Citations
Portable terminal, apparatus, method and system for processing information
JP2010277452A
Infection notification method and infection notification device
JP2012194808A
Pathogen contagion risk estimation device and program therein, and pathogen contagion risk estimation system
JP2014137754A
Infection candidate specifying device, infection candidate specifying method, and infection candidate specifying program
JP2017117416A
Infectious substance monitoring system, and infectious substance monitoring method
JP2019083395A