WO2022050217A1

WO2022050217A1 - Information processing device, information processing method, and program

Info

Publication number: WO2022050217A1
Application number: PCT/JP2021/031723
Authority: WO
Inventors: 崇大矢
Original assignee: キヤノン株式会社
Priority date: 2020-09-01
Filing date: 2021-08-30
Publication date: 2022-03-10
Also published as: JP2022041755A; JP7476038B2

Abstract

The present invention comprises a detection means for detecting a person included in an image captured by an image capturing means, a determination means for determining at least one of whether the person detected by the detection means is wearing a mask and the age of the person, and an output control means for outputting predetermined information on the basis of a distance between persons detected by the detection means in the image and the result of the determination by the determination means.

Description

Information processing equipment, information processing methods, and programs

The present invention relates to information processing technology.

There is a technology to compare the distance between people included in the image captured by the image pickup device with the threshold value, and if the distance is less than the threshold value, notify the user of an alert as the distance to be noted. Japanese Patent Application Laid-Open No. 2019-200718 discloses a method for outputting a warning when the distance between a person belonging to a minority group and a person belonging to a majority group is less than a preset threshold value.

Japanese Unexamined Patent Publication No. 2019-2007188

However, in Japanese Patent Application Laid-Open No. 2019-200718, since the threshold value used for determining whether the distance between persons is a cautionary distance is fixed uniformly, there is a case where it is not necessary to notify an alert originally depending on the characteristics of the person. Even so, it may notify the user of an alert.

For example, the image processing apparatus according to the present invention has the following configuration so that the user can be appropriately presented whether the distance between people is a distance to be noted. That is, a detection means for detecting a person included in an image captured by the image pickup means, a determination means for determining at least one of the presence or absence of a mask of the person detected by the detection means, and the age of the person. And an output control means for outputting predetermined information based on the distance between the persons detected by the detection means in the image and the determination result by the determination means.

According to each of the above embodiments, it is possible to appropriately indicate to the user whether the distance between persons is a distance to be noted.

It is a figure which shows an example of a system configuration. It is a figure which shows the functional block of an information processing apparatus. It is a figure which shows the state which imaged the matrix. It is a figure for demonstrating the process of determining whether the distance between a person is a cautionary distance. It is a flowchart which shows the flow of the process of determining whether the distance between people is a distance to be careful. It is a figure which shows an example of person information. It is a figure for demonstrating the process of determining whether the distance between a person is a cautionary distance. It is a figure for demonstrating the process which corrects the distance between a person. It is a figure which shows an example of the hardware composition of each apparatus.

Hereinafter, embodiments according to the present invention will be described with reference to the accompanying drawings. The configuration shown in the following embodiments is merely an example, and is not limited to the configurations shown in the drawings.

(Embodiment 1)
FIG. 1 is a diagram showing a system configuration in this embodiment. The system in this embodiment includes an information processing device 100, an image pickup device 110, a recording device 120, and a display 130.

The information processing device 100, the image pickup device 110, and the recording device 120 are connected to each other via the network 140. The network 140 is realized from a plurality of routers, switches, cables and the like conforming to a communication standard such as ETHERNET (registered trademark).

The network 140 may be realized by the Internet, a wired LAN (Local Area Network), a wireless LAN (Wireless Lan), a WAN (Wide Area Network), or the like.

The information processing device 100 is realized by, for example, a personal computer or the like in which a program for realizing the information processing function described later is installed. The image pickup device 110 is a device for taking an image and functions as an image pickup means. The image pickup device 110 associates the image data of the captured image, the information on the date and time when the image was captured, and the identification information which is the information for identifying the image pickup device 110, and records the information processing device 100 and the recording via the network 140. It is transmitted to an external device such as the device 120. In the system according to the present embodiment, the number of image pickup devices 110 is one, but the number of image pickup devices 110 may be multiple. That is, a plurality of image pickup devices 110 may be connected to the information processing device 100 and the recording device 120 via the network 140. In this case, the information processing device 100 and the recording device 120 use, for example, the identification information associated with the transmitted image, and the transmitted image is captured by the image pickup device 110 of the plurality of image pickup devices 110. Judge whether it is.

The recording device 120 records the image data of the image captured by the image pickup device 110, the information on the date and time when the image was captured, and the identification information for identifying the image pickup device 110 in association with each other. Then, in accordance with the request from the information processing device 100, the recording device 120 transmits the recorded data (image, identification information, etc.) to the information processing device 100.

The display 130 is composed of an LCD (Liquid Crystal Display) or the like, and displays an image or the like captured by the image pickup device 110. The display 130 is connected to the information processing apparatus 100 via a display cable compliant with a communication standard such as HDMI (registered trademark) (High Definition Multimedia Interface). At least two or all of the display 130, the information processing device 100, and the recording device 120 may be provided in a single housing.

The image captured by the image pickup device 110 is not limited to the display 130 connected to the information processing device 100 via the display cable, and may be displayed on, for example, a display having the following external device. That is, it may be displayed on a display of a mobile device such as a smartphone or a tablet terminal connected via the network 140.

Next, the information processing of the information processing apparatus 100 according to the present embodiment will be described with reference to the functional block of the information processing apparatus 100 according to the present embodiment shown in FIG. In the case of this embodiment, each function shown in FIG. 2 uses a ROM (Read Only Memory) 920, a RAM (Random Access Memory) 910, and a CPU (Central Processing Unit) 900, which will be described later with reference to FIG. It shall be realized as follows. That is, each function shown in FIG. 2 is realized by the CPU 900 of the information processing apparatus 100 expanding the computer program stored in the ROM 920 of the information processing apparatus 100 into the RAM 910 and executing the computer program.

The acquisition unit 101 sequentially acquires images of each frame constituting the moving image captured by the image pickup device 110. The acquisition unit 101 may acquire the moving image transmitted from the imaging device 110, or may acquire the moving image transmitted from the recording device 120.

The storage unit 201 can be realized by a RAM (Random Access Memory) 900, an HDD (Hard Disk Drive) 930, etc., which will be described later with reference to FIG. 9, and for example, image data of an image acquired by the acquisition unit 200 is stored (retained). do. The operation receiving unit 202 receives an operation performed by the user via an input device (not shown) such as a keyboard or a mouse.

The detection unit 203 executes a process of detecting a person included in the image acquired by the acquisition unit 200. The detection unit 203 in the present embodiment detects a person in an image by performing pattern matching processing using a matching pattern (dictionary). It should be noted that the person may be detected from the image by using a plurality of matching patterns such as a matching pattern when the person is facing forward and a matching pattern when the person is facing sideways. By executing the detection process using a plurality of collation patterns in this way, improvement in detection accuracy can be expected. As a collation pattern, a collation pattern may be prepared when a specific object is viewed from another angle such as from an oblique direction or from an upward direction. In addition, when detecting a person, it is not always necessary to prepare a collation pattern (dictionary) that shows the characteristics of the whole body, and a collation pattern is prepared for a part of the person such as the upper body, lower body, head, face, and legs. You may. The detection unit 203 in the present embodiment uses pattern matching processing as a method of detecting a person from an image, but may detect a person from an image by using another conventional technique.

The tracking unit 204 tracks a person detected by the detection unit 203. When the tracking unit 204 in the present embodiment detects the same person as the person detected from the image of the frame one or more before the frame of interest by the detection unit 203, the people in each frame correspond to each other. Attach. That is, a person is tracked between images for a plurality of frames that are close in time.

As a method of determining that the tracking unit 204 is the same person over images of a plurality of frames, for example, if the predicted movement position of the person and the detected person position are within a certain distance using the movement vector of the detected person, they are the same. Suppose you are a person. Further, the tracking unit 204 may associate a person with a high correlation between images of a plurality of frames by using the color, shape, size (number of pixels), and the like of the person. As described above, the tracking unit 204 is not limited to a specific method as long as it can perform a process of determining that the person is the same person over a plurality of frames of images and performing tracking. The tracking unit 204 assigns a unique ID to each person to be tracked. For example, it is assumed that the tracking unit 204 assigns an ID “a” to a person detected by the detection unit 203 from an image of a frame one or more before the frame of interest. Then, when the detection unit 203 also detects the person from the frame of interest, the tracking unit 204 assigns the same ID “a” to the person. If a person newly detected in the frame of interest exists, the tracking unit 204 newly assigns a unique ID to the person.

The determination unit 205 determines whether or not the person wearing the mask detected from the image by the detection unit 203, and at least one of the ages of the person. In the process of determining whether or not the person detected from the image is wearing a mask, a known technique for determining whether or not the person is wearing a mask may be used. Specifically, the determination unit 205 executes the following processing using, for example, a discriminator learned by machine learning using an image of the face of a person wearing a mask as training data. That is, the determination unit 205 inputs the image of the face of the person detected from the image by the detection unit 203 into the classifier, and acquires information on whether or not the person is wearing a mask as an output. Further, a known technique may be used for the process of determining the age of the person detected from the image. For example, the determination unit 205 inputs an image of a person's face detected from the image by the detection unit 203 into a classifier learned by machine learning using images of the faces of people of different ages as learning data. The information of the age of the person concerned is acquired as an output.

The calculation unit 206 calculates the distance between the persons included in the image. Further, the calculation unit 206 compares the calculated distance between the persons with the threshold value. The details of the processing by the calculation unit 206 will be described later. The output control unit 207 outputs predetermined information based on the distance between persons calculated by the calculation unit 206 and the determination result of at least one of the presence / absence of wearing a mask and the age by the determination unit 205.

Next, information processing by the information processing apparatus 100 in the present embodiment will be described with reference to FIGS. 3 and 4. FIG. 3 is a diagram showing how people in a line are imaged by the image pickup apparatus 110. In this embodiment, a line is regulated by a guide pole or the like, and a line with an entrance and an exit is assumed. The user enters the queue from the queue entrance 301, which is the entrance of the queue, proceeds along the guide 300, and exits from the queue exit 302, which is the exit of the queue. That is, the queue is formed from the matrix exit 302 toward the inlet 301 along the guide 300. It is assumed that the image pickup apparatus 110 in the present embodiment is installed so as to image the matrix formed in the guide 300. The information processing apparatus 100 in the present embodiment detects the persons included in the matrix imaged by the image pickup apparatus 110, and counts the number of the detected persons to acquire the number of people in the matrix. In the example shown in FIG. 2, the number of image pickup devices 110 is one, but a plurality of image pickup devices 110 may be used to divide the queue into a plurality of portions for image pickup. In this case, the detection unit 203 detects a person for each of the plurality of images obtained by imaging each of the plurality of parts obtained by dividing the queue, and the calculation unit 206 totals the number of detected persons. By calculating, the number of people in a queue may be obtained.

Next, information processing by the information processing apparatus 100 in the present embodiment will be described with reference to FIG. In the procession, the shorter the distance between the people before and after (the distance between the people), the higher the possibility that the virus infection spreads between the people (hereinafter referred to as the possibility of infection). Therefore, the information processing apparatus 100 in the present embodiment notifies the user of an alert (predetermined information) according to the distance between the persons.

In the example shown in FIG. 4, the detection unit 203 in the present embodiment detects a person included in the matrix from the image obtained by capturing the matrix shown in FIG. Then, the calculation unit 206 calculates the average Davr of the distances of the front and back people in the matrix by using the equation (1) based on the detection result of the person in the image.

Davr = L / (N-1) ... Equation (1)
L is the length of the matrix, and N is the number of people in the matrix. In the equation (1), the "number of people in the matrix" is the total number of people in the matrix. In the present embodiment, the detection unit 203 detects a person included in the matrix imaged by the image pickup apparatus 110, and the calculation unit 206 acquires the number of people in the matrix by counting the number of the detected persons. In this case, the calculation unit 206 calculates, for example, the sum of the number of persons detected by the detection unit 203 in each of the regions R1 (region 411) to the region R5 (region 415) set in the image, and the calculated sum. Is obtained as the number of people in the queue N. The information processing apparatus 100 may acquire the number of people in a matrix by executing the following processing, for example. That is, the information processing apparatus 100 may calculate the number of people in a matrix by the difference Nin-Nout between the number of people passing through the procession entrance 301 and the number of people passing through the procession exit 302. At this time, the calculation unit 206 determines, for example, whether the person tracked by the tracking unit 204 has passed the procession entrance 301, and acquires the number of persons determined to have passed as the number of passing people Nin. Similarly, it is determined whether or not the person tracked by the tracking unit 204 has passed the procession exit 302, and the number of persons determined to have passed is acquired as the number of passing persons Now. Then, the calculation unit 206 acquires the number of people in the matrix N by subtracting Nout from the acquired Nin.

Also, in equation (1), the "matrix length" is the distance from the beginning to the end of the matrix obtained along the path. In FIG. 4, the information processing apparatus 100 in the present embodiment sets regions R1 to R5 on the path of the matrix reflected in the image, and maintains the distance along the path of the matrix for each region. For example, the region Rn is set on the image according to the user operation, and the information of the distance along the path of the matrix in the real space of the region Rn is acquired. Next, the detection unit 203 executes a process of detecting a person in each region of the image, and the calculation unit 206 identifies the region Rend in which n is the largest among the regions Rn in which the stationary person exists. Then, the calculation unit 206 can obtain the total matrix length by adding the distances along the path in order from R1 to End. As a method for obtaining the queue length, other known techniques such as a method of individually measuring the positions between people waiting in a queue and calculating the distance may be used.

The calculation unit 206 further compares the average Davr of the distance between the persons calculated by obtaining the equation (1) with the threshold value. Then, when the average Davr is less than the threshold value, the output control unit 207 notifies the user of predetermined information, assuming that there is a high possibility of infection and the distance between the persons is a distance to be noted. On the other hand, when the average Davr is equal to or greater than the threshold value, the output control unit 207 does not notify the user of predetermined information because the possibility of infection is low and the distance between persons is not a cautionary distance. The output control unit 207 may display a message, a mark, or the like indicating a warning as predetermined information on the display 130. Further, the output control unit 207 may make a voice indicating a warning flow from a speaker (not shown) as a method of notifying the user of predetermined information.

Note that the calculation unit 206 in the present embodiment may calculate the latest average Davr at predetermined time intervals using the equation (1) and compare the calculated latest average Davr with the threshold value. Then, when the average Davr is continuously less than the threshold value a predetermined number of times, the output control unit 207 may notify the user of the predetermined information. For example, when the average Davr is less than the threshold value three times in a row, the output control unit 207 causes the display 130 to display a message indicating a warning as predetermined information. On the other hand, the output control unit 207 may not display the warning message on the display 130 when the average Davr is not less than the threshold value three times in a row.

Further, the calculation unit 206 in the present embodiment may correct the average Davr depending on whether or not the mask is worn. Specifically, the calculation unit 206 in the present embodiment corrects so that the calculated average Davr value becomes large, assuming that the possibility of virus infection is reduced when the person wears a mask. The calculation unit 206 calculates, for example, the corrected average Davr', which is a value obtained by correcting the average davr, using the equation (2).

Davr'= (1 + Cm) Davr ... Equation (2)
However, 0 ≦ Cm ≦ 1
In addition, Cm in the formula (2) indicates the ratio "mask wearing rate" of the person wearing a mask among the persons in a procession. The determination unit 205 in the present embodiment determines whether or not each of the persons located along the route from the matrix entrance 301 to the matrix exit 302 shown in FIG. 4 is wearing a mask. Then, the calculation unit 206 calculates the mask wearing rate Cm by dividing the number of people determined by the determination unit 205 to be wearing the mask by the number of people in the matrix N. As shown in the formula (2), the calculation unit 206 in the present embodiment corrects the calculated average Davr value of the distance between the persons to be larger as the mask wearing rate is higher, thereby calculating the corrected average Davr'. calculate. Then, the calculation unit 206 compares the corrected average Davr'with the threshold value. When the corrected average Davr'is less than the threshold value, the output control unit 207 notifies the user of a message indicating a warning as predetermined information, assuming that the distance is likely to be infected and should be noted. Then, when the corrected average Davr'is equal to or greater than the threshold value, the output control unit 207 does not notify the user of a message indicating a warning because the possibility of infection is low and the distance should be noted. As described above, the information processing apparatus 100 in the present embodiment corrects the average Davr of the distance between people according to the mask wearing rate, and determines the information (alert) to the user according to the result of comparing the average Davr'and the threshold value. May be notified. By doing so, when the mask wearing rate is high and it is not necessary to notify the user of the alert, it is possible to reduce the notification of the alert to the user. In other words, it is possible to adaptively determine whether the distance between persons is a distance to be noted, and notify the user of an alert based on the result of the determination.

Further, the calculation unit 206 in the present embodiment may correct the average Davr according to the age of the person. In the present embodiment, it is assumed that the older the person is, the higher the possibility of becoming severe when infected with the virus. Therefore, the calculation unit 206 in the present embodiment corrects so that the calculated average Davr value becomes smaller so that the user is more likely to be notified of the alert as the number of elderly people increases. Specifically, the calculation unit 206 calculates the corrected average Davr', which is a value obtained by correcting the average Davr, using, for example, the equation (3).

Davr'= (1-Ck / 2) Davr ... Equation (3)
However, 0 ≦ Ck ≦ 1
In addition, Ck in the formula (3) indicates the ratio of elderly people among the persons in the matrix "elderly person rate". The determination unit 205 in the present embodiment determines the age of each of the persons lined up in the matrix along the route from the matrix entrance 301 to the matrix exit 302 shown in FIG. 4, and determines whether the person is an elderly person based on the determined age. .. At this time, the determination unit 205 determines, for example, the age of each of the persons in the line, determines that the person of the predetermined age or older is an elderly person, and determines that the person of less than the predetermined age is not an elderly person. In the present embodiment, the predetermined age is 70 years old, but other criteria such as 65 years old and 75 years old may be followed. Then, the calculation unit 206 calculates the elderly rate Ck by dividing the number of people determined to be elderly by the determination unit 205 by the number of people in the matrix N. As shown in the formula (3), the calculation unit 206 in the present embodiment corrects so that the higher the elderly rate Ck, the smaller the value of the calculated average Davr of the distance between the persons, so that the corrected average Davr' Is calculated. Then, the calculation unit 206 compares the corrected average Davr'with the threshold value. When the corrected average Davr'is less than the threshold value, the output control unit 207 notifies the user of predetermined information as a distance to be noted. Then, when the corrected average Davr'is equal to or greater than the threshold value, the output control unit 207 does not notify the user of predetermined information because it is not a distance to be noted. As described above, the information processing apparatus 100 in the present embodiment notifies the user of an alert according to the result of comparing the average Davr of the distance between the persons with the corrected average Davr'according to the age of the person and the threshold value. You may. By doing so, it is possible to reduce the fact that the alert is not notified to the user when the alert should be notified to the user because the person is old. In other words, it is possible to adaptively determine whether the distance between persons is a distance to be noted, and notify the user of an alert based on the result of the determination.

Note that the calculation unit 206 in the present embodiment may correct the average Davr according to the presence or absence of wearing a mask and the age of the person. At this time, the calculation unit 206 may acquire the corrected average Davr'corrected by the calculated average Davr, for example, by using the equation (4).

Davr'= (1 + Cm) (1-Ck / 2) Davr ... Equation (4)
In the example of the formula (4), the higher the mask wearing rate, the larger the average Davr, and the higher the elderly rate, the smaller the average Davr.

Subsequently, with reference to FIG. 5, information processing by the information processing apparatus 100 in the present embodiment will be described. The flow processing shown in FIG. 5 is, for example, started or terminated according to an instruction by the user. The processing of the flowchart shown in FIG. 5 is executed by, for example, the functional block shown in FIG. 2 realized by executing the computer program stored in the ROM 920 of the information processing apparatus 100 by the CPU 900 of the information processing apparatus 100. And.

First, in S501, the acquisition unit 200 acquires the image captured by the image pickup device 120. At this time, the acquisition unit 200 acquires an image of one frame among the images of a plurality of frames constituting the moving image captured by the image pickup apparatus 110 as an image to be processed (hereinafter referred to as an image to be processed). Next, in S502, the detection unit 203 detects a person included in the image to be processed. At this time, the detection unit 203 detects a person included in the image to be processed, for example, by pattern matching processing using a person matching pattern. Next, in S503, the tracking unit 204 tracks the person detected by the detection unit 203. When the same person as the person detected by the detection unit 203 from the image of the frame one or more before the processing target image is detected from the processing target image by the detection unit 203, the tracking unit 204 is a person in each frame. By associating with, the person is tracked. The tracking unit 204 assigns a unique ID to each person to be tracked. For example, it is assumed that the tracking unit 204 assigns an ID “a” to a person detected by the detection unit 203 from an image of a frame one or more before the image to be processed. Then, when the detection unit 203 also detects the person from the image to be processed, the tracking unit 204 assigns the same ID “a” to the person. If there is a newly detected person in the image to be processed, the tracking unit 204 newly assigns a unique ID to the person. Further, the storage unit 201 stores the ID assigned by the tracking unit 204 to the persons currently in line in the person information 600 shown in FIG. The person information 600 shown in FIG. 6 stores (retains) information about people currently in a line. Specifically, in the person information 600, the ID 601 of the person given by the tracking unit 204, the age information 602 which is the information of the age of the person, and the mask information 603 which is the information of whether or not the person wears a mask. Is recorded (retained) in association with. The person information 600 is not limited to the example shown in FIG. 6, and may include, for example, information on the size and position of the person for each frame for each person to which the ID 601 is assigned. When a unique ID is assigned to the newly detected person in S503, the storage unit 201 newly stores the newly assigned ID in the ID 601 of the person information 600. When a person tracked by the tracking unit 204 in the present embodiment passes through the procession exit 302 and exits the procession, the storage unit 201 provides information about the person (ID601, age information 602, mask information 603) to the person. Delete from information 600.

Next, in S504, the determination unit 205 determines whether or not the person being tracked by the tracking unit 204 is wearing a mask. In S504, the determination unit 205 in the present embodiment may determine whether or not the mask is worn only for a person who has not yet been determined whether or not the mask is worn. In the present embodiment, in the person information 600 shown in FIG. 6, the mask information 603 of the person with ID 601 "c" is blank, and it is determined whether or not the person with ID 601 "c" is still wearing the mask. It shows that it is not. This may occur when it is not properly determined whether or not the mask is worn, such as when the face image of the front face of the person is not acquired. In S504, the determination unit 205 may determine whether or not the mask is worn for the person with the person ID “c” for whom the presence or absence of the mask has not been determined. Further, in this case, the determination unit 205 does not determine whether or not the mask is worn for the person with ID 601 "a, b, d" who has already been determined whether or not the mask is worn. Here, when the information on whether or not the person ID “c” is worn is obtained according to the determination by the determination unit 205, the storage unit 201 stores the information on whether or not the mask is worn in the mask information 603.

Next, in S505, the determination unit 205 determines the age of the person tracked by the tracking unit 204. In S505, the determination unit 205 in the present embodiment may determine the age of a person whose age has not yet been determined. In the person information 600 shown in FIG. 6, the age information 602 of the person whose ID 601 is "d" is blank, indicating that the age of the person whose ID 601 "d" has not been determined yet. This may occur when the age is not properly determined, such as when the face image of the front face of the person is not acquired. In S505, the determination unit 205 determines the age of the person with the person ID "d" whose age has not been determined, and for the person with ID 601 "a, b, c" whose age has already been determined. The age may not be determined. Here, when the age information is obtained for the person ID "d" according to the determination by the determination unit 205, the age information is stored in the age information 602.

Next, in S506, the calculation unit 206 calculates the number of people in the line N, which is the number of people in the line. For example, the calculation unit 206 can be obtained by the difference Nin-Nout between the number of passers Nin passing through the matrix entrance 301 and the number of passers Nout passing through the matrix exit 302.

Next, in S507, the calculation unit 206 specifies the matrix length, which is the distance along the matrix path from the beginning to the end of the matrix. For example, in the example shown in FIG. 4, the calculation unit 206 in the present embodiment specifies the region Rmax in which n is the largest among the regions Rn in which a stationary person exists. Then, based on the information of the distance along the path of the matrix held in advance for each of the regions R1 to R5, the calculation unit 206 can obtain the total matrix length by adding the distances in order from R1 to Rmax. ..

Next, in S508, the calculation unit 206 calculates the average Davr of the distance between people. The calculation unit 206 in the present embodiment calculates the average Davr using the formula (1), but the average Davr of the distance between people may be calculated by using another method.

Next, in S509, it is determined whether or not to correct the average Davr. For example, if the user has been instructed to correct the average Davr in advance (Yes in S509), the transition to S510 has been performed, and the user has not been instructed to correct the average Davr (No in S509). Transition to S511. In S510, the calculation unit 206 corrects the average Davr based on at least one of the presence or absence of the person wearing a mask and the age of the person. Here, for example, the calculation unit 206 obtains the corrected average Davr'by correcting the average Davr using any one of the equations (2) to (4).

In S511, the calculation unit 206 executes a comparison process of comparing the calculated average Davr or the corrected average Davr'corrected with the average Davr with the threshold value. When the average Davr is not corrected in S510 (when transitioning from S509 to S511), the calculation unit 206 compares the calculated average Davr with the threshold value in S511. On the other hand, when the average Davr is corrected in S510 (when transitioning from S509 to S510), in S511, the calculation unit 206 compares the average Davr' obtained by correcting the average Davr with the threshold value. .. It should be noted that the threshold value here is a parameter that is preset by the user and can be changed as appropriate.

When the average Davr (or the corrected average Davr') is less than the threshold value (Yes in S512), the transition to S513 is performed, and in S513, the output control unit 207 notifies the user of a message indicating a warning as predetermined information. .. On the other hand, when the average Davr (or the corrected average Davr') is equal to or greater than the threshold value (No in S512), the transition to S514 occurs. When the user has instructed the end in S514 (Yes in S514), the process of the flow shown in FIG. 5 is terminated. On the other hand, if the user has not instructed the end (NO in S514), the transition to S501 is performed, and the acquisition unit 200 newly acquires the image to be processed next.

As described above, the information processing apparatus 100 in the present embodiment calculates the average Davr of the distance between the persons, and calculates it based on at least one of the presence or absence of the person wearing a mask and the age of the person. Correct the average Davr. Then, the information processing apparatus 100 compares the corrected average Davr' obtained by correcting the average Davr with the threshold value, and notifies the user of a message indicating a warning as predetermined information according to the comparison result. By doing so, it is possible to adaptively determine whether the distance between the persons is a cautionary distance, and notify the user of an alert based on the result of the determination.

In the above description, the information processing apparatus 100 uses the average Davr of the distance between people to notify the user of predetermined information according to the comparison result with the threshold value, but the present invention is not limited to this. For example, only the distance between two people may be used instead of the average distance between the people. Specifically, in the example shown in FIG. 4, the calculation unit 206 calculates the distance D between the first person in the line and the second person located in front of or behind the first person. .. At this time, the calculation unit 206 identifies, for example, the position of the first person and the position of the second person detected from the image, and on the image from the position of the first person to the position of the second person on the image. Let the distance be the distance D. The calculation unit 206 may convert the distance on the image from the position of the first person on the image to the distance on the second person into the distance in the real space, and may use the distance in the real space as the distance D. The process of converting the distance on the image into the distance on the real space shall be performed using a known technique. Further, the determination unit 205 determines whether or not the mask is worn and at least one of the ages of each of the first person and the second person. Then, the calculation unit 206 corrects the distance D between the first person and the second person based on whether or not the mask is worn and at least one of the ages. At this time, for example, the calculation unit 206 corrects the distance D by using the equation (5).

D'= (1 + M × Rm) (1-K × Rk) D ... Equation (5)
Here, M indicates the ratio of the person wearing the mask among the first person and the second person. For example, if both people are wearing masks, only one person is wearing the mask. If there is no mask wearer, it will be 1/2, and if there is no mask wearer, it will be 0. Further, K indicates the ratio of elderly people among the first person and the second person, for example, 1 if both are elderly, 1/2 if only 1 person is elderly, and no elderly person. In the case, it becomes 0. Further, Rm and Rk each indicate a predetermined coefficient. Here, for example, when Rm is zero and Rk is a predetermined value, the higher K is, the smaller the distance D between the first person and the second person is corrected, and the alert is more likely to be notified. Further, when Rm is a predetermined value and Rk is zero, the higher M is, the larger the distance D between the first person and the second person is corrected, and the alert is less likely to be notified. Then, when the distance D'corrected for the distance D between the first person and the second person is less than the threshold value, the output control unit 207 notifies the user of a message indicating a warning as predetermined information, and the distance D'is set. If it is above the threshold value, the message is not notified. As described above, in the information processing apparatus 100 of the present embodiment, the distance between a certain person (first person) and another person (second person) is set to at least one of the presence / absence of a mask and the age. Correct based on the judgment result. Then, the information processing apparatus 100 notifies the user of predetermined information according to the comparison result between the correction distance corrected for the distance between the first person and the second person and the threshold value. By doing so, it is possible to adaptively determine whether the distance between the persons is a cautionary distance, and notify the user of an alert based on the result of the determination.

(Embodiment 2)
In the information processing apparatus 100 in the first embodiment, the distance between the persons is corrected according to the mask wearing rate and the age of the person, and the corrected distance between the persons and the threshold value are compared. In the second embodiment, the distance between the persons is compared. Correct the threshold value to be compared with the distance of. That is, the information processing apparatus 100 in the second embodiment corrects the threshold value according to the mask wearing rate of the person and the age of the person, compares the corrected threshold value with the distance between the people, and determines the predetermined value according to the result of the comparison. Notify the user of a warning message as information about. The parts different from those of the first embodiment will be mainly described, and the same components and the same reference numerals are given to the components and the processes which are the same as or the same as those of the first embodiment, and the duplicated description will be omitted.

In the example shown in FIG. 4, the calculation unit 206 in the present embodiment calculates the average Davr of the distances of the front and back persons in the matrix by using the equation (1). Since the process of calculating the average Davr is the same as that of the first embodiment, the description thereof will be omitted. Then, the calculation unit 206 in the present embodiment acquires the threshold value r'by correcting the threshold value r using the equation (6).

Threshold r'= r-Cm * Rm + Ck * Rk ... Equation (6)
As in the formula (5), Cm indicates the mask wearing rate, Ck indicates the elderly rate, and Rm and Rk indicate predetermined coefficients, respectively. Here, for example, when Rm is zero and Rk is a predetermined value, the threshold value r is corrected to be larger as the elderly rate Ck is higher. That is, the higher the elderly rate Ck, the larger the threshold value r, so that the alert is more likely to be notified to the user. Further, when Rm is a predetermined value and Rk is zero, the higher the mask wearing rate Cm, the smaller the threshold value r is corrected. In other words, the higher the mask wearing rate, the smaller the threshold value r is corrected, so that the alert is less likely to be notified to the user. In addition, each of Rm and Rk may have a predetermined value. That is, the threshold value r'may depend on both the mask wearing rate and the elderly rate.

The calculation unit 206 compares the average Davr of the distance between people with the corrected threshold value r'. At this time, if the average Davr of the distance between the persons is less than the corrected threshold value r', the output control unit 207 notifies the user of a message indicating a warning as an alert. On the other hand, the output control unit 207 does not notify the user of a message indicating a warning when the average Davr of the distance between people is equal to or greater than the corrected threshold value r'.

In the above example, the average Davr of the distance between people and the corrected threshold value r'are compared, but the present invention is not limited to this. For example, the calculation unit 206 in the present embodiment may compare the distance D between a certain person (first person) and another person (second person) with the corrected threshold value r'. At this time, when the distance D between the first person and the second person is less than the corrected threshold value r', the output control unit 207 notifies the user of a message indicating a warning as an alert. On the other hand, the output control unit 207 does not notify the user of a warning message when the distance D between the first person and the second person is equal to or greater than the corrected threshold value r'.

As described above, the information processing apparatus 100 in the present embodiment compares the threshold value corrected based on at least one of the age of the person and whether or not the person wears a mask and the distance between the persons (average Davr and distance D). Then, an alert is notified to the user according to the result of the comparison. By doing so, it is possible to adaptively determine whether the distance between the persons is a cautionary distance, and notify the user of an alert based on the result of the determination.

(Embodiment 3)
The information processing apparatus 100 according to the third embodiment uses information on the queue length and the number of people waiting, as well as information on the waiting time, to calculate a degree of attention, which is an index indicating whether the distance between persons is a distance to be noted. explain. The lower the degree of attention, the more the distance between people is not the distance to be careful, and the higher the degree of attention, the more the distance between people is the distance to be careful. For example, in a procession, the shorter the distance between the person before and after, and the longer the waiting time, the higher the possibility of infection, and the higher the degree of caution. It should be noted that the parts different from each of the above-described embodiments will be mainly described, and the same or equivalent components and processes as those of each of the above-described embodiments are designated by the same reference numerals, and duplicated description will be omitted.

The calculation unit 206 in this embodiment calculates the attention level R using the equation (7).

R = C1 × Tavr / Davr ... Equation (7)
In the formula (7), the average Davr of the distance between people is obtained by the formula (1). Further, Tavr indicates an "estimated waiting time" which is the result of estimating the waiting time of the queue. In the example shown in FIG. 4, a person enters the line from the line entrance 301 and then exits from the line exit 302. Corresponds to the result of estimating the time to do. Further, the constant C1 is a normalization coefficient for keeping the attention level R within a predetermined range.

Here, a method of calculating the estimated waiting time Tavr will be described with reference to FIG. In the example shown in FIG. 4, the calculation unit 206 in the present embodiment acquires the number of persons who have passed through the matrix exit 302 and exited from the matrix within a predetermined time. Then, the calculation unit 206 calculates the number of people leaving the matrix per unit time by dividing the number of acquired people by a predetermined time. At this time, the number of people leaving the procession per unit time is defined as the exit frequency. Then, the calculation unit 206 acquires the number of people N in the matrix, which is the number of people lined up in the matrix formed along the path from the matrix entrance 301 to the matrix exit 302. Since the method of calculating the number of people in the matrix N is the same as that of the first embodiment, the description thereof will be omitted. The calculation unit 206 calculates the estimated waiting time Tavr by dividing the number of people in the queue N by the exit frequency.

As a method for calculating the estimated waiting time Tavr, another known technique may be used. For example, the tracking unit 204 tracks a person from the matrix entrance 301 to the matrix exit 302, and the calculation unit 206 acquires the movement time required for the person to move from the matrix entrance 301 to the matrix exit 302. Then, the calculation unit 206 may calculate the average value of the travel time acquired for each of the plurality of persons, and acquire the average value as the estimated waiting time Tavr.

Then, the calculation unit 206 in the present embodiment executes a comparison process for comparing the attention level R calculated using the equation (7) with the threshold value. When the attention level R is less than the threshold value, the output control unit 207 does not notify the user as an alert, assuming that the distance between the persons is not the distance to be noted. On the other hand, when the attention level R is equal to or higher than the threshold value, the output control unit 207 notifies the user as an alert with a message indicating a warning, assuming that the distance between the persons is a distance to be noted. The calculation unit 206 in the present embodiment may use the equation (7) to calculate the latest attention level R at predetermined time intervals and compare the calculated latest attention level R with the threshold value. .. Then, when the attention level R is continuously equal to or higher than the threshold value a predetermined number of times, the output control unit 207 may notify the user of a message indicating a warning as an alert. For example, the output control unit 207 causes the display 130 to display a message indicating a warning when the attention level R is equal to or higher than the threshold value three times in a row. On the other hand, the output control unit 207 does not display a warning message on the display 130 when the attention level R is not equal to or higher than the threshold value three times in a row.

Further, the calculation unit 206 in the present embodiment may correct the caution level R depending on whether or not the mask is worn. Specifically, the calculation unit 206 in the present embodiment corrects the calculated caution level R to be small, assuming that the possibility of virus infection is reduced when the person is wearing a mask. For example, the calculation unit 206 calculates the correction caution level R', which is a value obtained by correcting the attention level R, using the equation (8).

R'= R / (1 + Cm) ... Equation (8)
Similar to the first embodiment, Cm indicates the mask wearing rate of the persons in a line. Further, in the example of the equation (8), it is assumed that the attention level R of the matrix is halved when all the persons in the matrix wear masks.

Further, the calculation unit 206 in the present embodiment may correct the attention level R according to the age of the person. Here, if the people in the line are elderly people, it is assumed that there is a relatively high possibility that they will become seriously ill if they are infected with the virus. Therefore, the calculation unit 206 in the present embodiment corrects the calculated attention level R so that the larger the number of elderly people, the easier it is for the user to be notified of the alert. Specifically, the calculation unit 206 calculates the correction attention level R', which is a value obtained by correcting the attention level R, using, for example, the equation (9).

R'= R * (1 + Ck / 2) ... Equation (9)
As in the first embodiment, Ck indicates the elderly rate, which is the ratio of the elderly among the persons in the line.

Further, the calculation unit 206 in the present embodiment may correct the caution level R based on whether or not the person wears a mask and the age of the person. At this time, the calculation unit 206 calculates the correction caution level with the attention level R corrected by using, for example, the equation (10).

R'= R * (1-Cm / 2 + Ck / 2) ... Equation (10)
In the example of the formula (10), the higher the mask wearing rate of the people in the line, the lower the degree of attention, and the larger the number of elderly people in the line, the higher the degree of attention.

As described above, the calculation unit 206 calculates the corrected caution level R'by correcting the calculated caution level R based on at least one of the presence or absence of the person wearing a mask and the age of the person. Then, the calculation unit 206 executes a comparison process for comparing the corrected attention level R'acquired by correcting the attention level R with the threshold value. When the correction attention level R'is less than the threshold value, the output control unit 207 does not notify the user as an alert, assuming that the distance between the persons is not the distance to be noted. On the other hand, when the correction attention level R'is equal to or greater than the threshold value, the output control unit 207 notifies the user as an alert with a message indicating a warning, assuming that the distance between the persons is a distance to be noted. As described above, the information processing apparatus 100 in the present embodiment corrects the attention level R based on at least one of the presence / absence of the mask of the person and the age of the person, and the corrected caution level R obtained by the correction. Notify the user of an alert depending on the result of the comparison between'and the threshold. By doing so, it is possible to adaptively determine whether the distance between the persons is a cautionary distance, and notify the user of an alert based on the result of the determination.

(Embodiment 4)
The information processing apparatus 100 in the fourth embodiment calculates the distance between each person in the matrix and the people around the person, and calculates the density of the matrix based on the calculated distance. Then, the information processing apparatus 100 notifies the user of an alert according to the result of comparing the calculated density and the threshold value. It should be noted that the parts different from each of the above-described embodiments will be mainly described, and the same or equivalent components and processes as those of each of the above-described embodiments are designated by the same reference numerals, and duplicated description will be omitted.

FIG. 8 is a diagram for explaining a method of calculating the distance between persons in the present embodiment. It is assumed that the person P1 (person 711) located at the head of the matrix is arranged in order. Here, assuming that the position of the i-th person is Pi (x, y), the distance between the i-th person and the j-th person is Dij = | Pi-Pj |. The position of the person may be a position on the screen or a position converted into a real space. Next, for person i, if the number of people whose distance to the surrounding people is less than the predetermined value Dth is defined as Ni people,
Ni = COUNTIF (Dij <Dth), (j ≠ i, j = 1, 2, ... n). .. .. Equation (11)
Can be written as. Note that n indicates the number of people in the queue. Further, the predetermined value Dth is a numerical value specified in advance by the user, for example, 1.8 m. Here, assuming that the density Den of the matrix is the total number of people whose distance to the surrounding people is less than Dth,
Den = ΣNi, (i = 1, 2, ... n) Equation (12)
Is. Then, the calculation unit 206 compares the calculated density Den with the threshold value, and if the density Den is equal to or greater than the threshold value, determines that the distance between the persons in the matrix is a distance to be noted. Then, the output control unit 207 notifies the user of the alert. On the other hand, when the calculated density Den is less than the threshold value, the calculation unit 206 determines that the distance between the persons in the matrix is not the distance to be noted. Then, the output control unit 207 notifies the user of the alert.

Further, the calculation unit 206 in the present embodiment calculates the distance Dij between the i-th person and the j-th person, and further corrects the calculated Dij based on at least one of the presence / absence of wearing a mask and the age. You may. Specifically, the calculation unit 206 may calculate the correction distance Dij'by correcting the distance Dij using the equation (13).

Dij'= (1 + Mij × Rm) (1-Kij × Rk) Dij ... Equation (13)
In addition, Mij here indicates the ratio of the person wearing a mask among the two people of the i-th and j-th, for example, if both of them are wearing masks, only one person is wearing a mask. If you are wearing a mask, it will be 1/2, and if there is no mask wearer, it will be 0. In addition, Kij indicates the ratio of elderly people among the two people at the i-th and j-th, for example, 1 if both are elderly, 1/2 if only 1 is elderly, and elderly. If there is no person, it will be 0. Further, Rm and Rk each indicate a predetermined coefficient. Here, for example, when Rm is zero and Rk is a predetermined value, the higher the elderly rate Kij, the smaller the distance Dij between the i-th person and the j-th person is corrected. That is, the higher the elderly rate Kij, the easier it is for the user to be notified of the alert. Further, when Rm is a predetermined value and Rk is zero, the higher the mask wearing rate Mij, the larger the distance Dij between the i-th person and the j-th person is corrected. In other words, the higher the mask wearing rate Mij, the less likely it is that the alert will be notified to the user.

Next, for the i-th person, if the number of people whose correction distance Dij'is less than the predetermined value Dth is defined as Ni'person,
Ni'= COUNTIF (Dij'<Dth), (j ≠ i, j = 1, 2, ... n). .. .. Equation (14)
Can be written as. Here, assuming that the density Den'of the matrix is the total number of people whose correction distance Dij'is less than Dth, it is assumed.
Den'= ΣNi' (i = 1, 2, ... n) Equation (15)
Is. Then, the calculation unit 206 compares the density Den'calculated based on the correction distance Dij'with the threshold value, and when the density Den'is equal to or greater than the threshold value, the distance between the persons in the matrix is a distance to be noted. Is determined. Then, the output control unit 207 notifies the user of the alert. On the other hand, when the calculated density Den'is less than the threshold value, the calculation unit 206 determines that the distance between the persons in the matrix is not the distance to be noted. Then, the output control unit 207 does not notify the user of the alert. By doing so, it is possible to adaptively determine whether the distance between the persons is a cautionary distance, and notify the user of an alert based on the result of the determination.

(Modification example)
Hereinafter, as a modification of the fourth embodiment, another method for calculating the correction distance Dij'will be described. The calculation unit 206 according to this modification corrects the distance Dij between the i-th person and the j-th person in the matrix based on the orientations of the faces of the i-th person and the j-th person. The determination unit 205 in the present embodiment determines the orientation of the face of the person detected by the detection unit 203 from the image. A known technique may be used to determine the orientation of the face. For example, the information processing apparatus 100 creates in advance, for example, a classifier trained by machine learning using face images having different face orientations as learning data. Then, for example, the determination unit 205 inputs the face image of the person detected from the image by the detection unit 203 into the discriminator, and obtains the information on the orientation of the face of the person as output. Here, based on the same orientation that is usually seen for people in a queue, the distance Dij is small when the people are facing each other, and conversely, the distance Dij is large when the people are back to back. Correct to.

Here, the process of correcting the distance Dij will be described with reference to FIG. In the example shown in FIG. 8, the counterclockwise direction is positive with respect to the straight line drawn from the center position of the face area of the i-th person 801 toward the center position of the face area of the j-th person 802. At this time, in the unit circle with the straight line as the x-axis, the face orientation of the person 801 with the center of the face area of the i-th person 801 as the origin is the arc degree Θi with respect to the straight line, and the center of the face area of the j-th person 802. Let the face orientation of the person 802 with the origin be the radian Θj with respect to the straight line. At this time, the calculation unit 206 in this modification calculates the correction distance D'ij by correcting the distance Dij using the equation (16).

D'ij = {sin ((Θi-Θj) /2.0)/2.0+1.0}*Dij ... Equation (16)
Using the correction distance D'ij, the calculation unit 206 calculates the density Den'using the equations (14) and (15) described in the fourth embodiment. Then, when the density Den'is equal to or greater than the threshold value, the output control unit 207 in the present embodiment notifies the user of an alert, assuming that the distance between the persons in the matrix is a distance to be noted. On the other hand, when the calculated density Den'is less than the threshold value, the output control unit 207 does not notify the user of the alert because the distance between the persons in the matrix is not the distance to be noted. It is possible to adaptively determine whether the distance between people is a cautionary distance, and notify the user of an alert based on the result of the determination.

(Other embodiments)
Next, with reference to FIG. 9, the hardware configuration of the information processing apparatus 100 for realizing each function of each embodiment will be described. Although the hardware configuration of the information processing device 100 will be described in the following description, it is assumed that the recording device 120 and the image pickup device 110 are also realized by the same hardware configuration.

The information processing apparatus 100 in the present embodiment has a CPU 900, a RAM 910, a ROM 920, an HDD 930, and an I / F 940.

The CPU 900 is a central processing unit that controls the information processing device 100 in an integrated manner. The RAM 910 temporarily stores a computer program executed by the CPU 900. The RAM 910 also provides a work area used by the CPU 900 to execute processing. Further, the RAM 910 functions as, for example, a frame memory or a buffer memory.

The ROM 920 stores a program or the like for the CPU 900 to control the information processing apparatus 100. The HDD 930 is a storage device for recording image data and the like.

The I / F 910 communicates with an external device via the network 140 according to TCP / IP, HTTP, or the like.

In the description of each of the above-described embodiments, an example in which the CPU 900 executes the processing will be described, but at least a part of the processing of the CPU 900 may be performed by dedicated hardware. For example, the process of displaying a GUI (GRAPHICAL USER INTERFACE) or image data on the display 130 may be executed by a GPU (GRAPHICS PROCESSING UNIT). Further, the process of reading the program code from the ROM 920 and expanding it to the RAM 910 may be executed by a DMA (Direct Memory Access) that functions as a transfer device.

The present invention can also be realized by a process in which one or more processors read and execute a program that realizes one or more functions of the above-described embodiment. The program may be supplied to a system or device having a processor via a network or storage medium. The present invention can also be realized by a circuit (for example, an ASIC) that realizes one or more functions of the above-described embodiment. Further, each part of the information processing apparatus 100 may be realized by the hardware shown in FIG. 9 or by software.

It should be noted that another device may have one or more functions of the information processing device 100 according to each of the above-described embodiments. For example, the image pickup apparatus 110 may have one or more functions of the information processing apparatus 100 according to each embodiment. It should be noted that each of the above-described embodiments may be combined, and for example, the above-mentioned embodiments may be arbitrarily combined.

Although the present invention has been described above with the embodiments, the above embodiments are merely examples of embodiment of the present invention, and the technical scope of the present invention is limitedly interpreted by these. It's not a thing. That is, the present invention can be implemented in various forms within a range that does not deviate from the technical idea or its main features. For example, a combination of the respective embodiments is also included in the disclosure contents of the present specification.

The present invention is not limited to the above embodiment, and various changes and modifications can be made without departing from the spirit and scope of the present invention. Therefore, the following claims are attached in order to publicize the scope of the present invention.

This application claims priority based on Japanese Patent Application No. 2020-147156 submitted on September 1, 2020, and all the contents thereof are incorporated herein by reference.

Claims

A detection means for detecting a person included in an captured image,
A determination means for determining whether or not a person wearing a mask is detected by the detection means, and at least one of the ages of the person.
A correction means for correcting the distance between persons detected by the detection means in the image according to the determination result by the determination means, and a correction means.
An information processing apparatus comprising: an output control means for outputting predetermined information according to a distance between the persons corrected by the correction means.
The information processing according to claim 1, wherein the output control means outputs the predetermined information according to the result of comparing the distance between the persons corrected by the correction means and the threshold value. Device.
The information processing device according to claim 2, wherein the output control means outputs the predetermined information when the distance between the persons corrected by the correction means is less than the threshold value.
The information processing device according to claim 1, wherein the correction means corrects the distance between the persons so that the distance between the persons becomes large when the detected person wears a mask.
The information processing device according to claim 1, wherein the correction means corrects the distance between the people so that the distance between the people becomes smaller when the detected person is older than a predetermined age.
The detection means detects the person in the queue included in the image obtained by the imaging means that captures the queue.
The information processing apparatus according to claim 1, wherein the correction means corrects the distance between the persons in the queue based on the determination result by the determination means.
The distance between the persons is an average value of the distances between the persons lined up before and after the queue, and the correction means is the number of persons wearing a mask for the number of persons lined up in the queue, and The information processing apparatus according to claim 6, wherein the distance between the persons is corrected based on at least one of the number of persons under a predetermined age with respect to the number of persons in the queue.
The correction means corrects the distance between the persons so that the greater the number of people wearing the mask or the greater the number of persons under the predetermined age, the greater the distance between the persons. The information processing apparatus according to claim 7.
A detection means that detects a person contained in an image,
A determination means for determining whether or not a person wearing a mask is detected by the detection means, and a determination means.
A correction means for correcting a threshold value used for determining whether to output predetermined information according to a determination result by the determination means, and a correction means.
An information processing apparatus comprising: an output control means for outputting the predetermined information based on a distance between persons detected by the detection means and a threshold value corrected by the correction means.
The information according to claim 9, wherein the output control means outputs the predetermined information when the distance between the persons detected by the detection means is less than the threshold value corrected by the correction means. Processing equipment.
The information processing apparatus according to claim 9, wherein the correction means corrects the threshold value so that the threshold value becomes smaller when the person detected by the detection means wears a mask.
The distance between the persons is the distance between the first person and the second person detected by the detection means.
The correction means determines that the threshold value when it is determined that the first person and the second person are wearing a mask is that either the first person or the second person is wearing a mask. The information processing apparatus according to claim 11, wherein the threshold value is corrected so as to be smaller than the threshold value when the threshold value is set.
A detection process that detects a person included in the captured image, and
A determination step of determining whether or not the person wearing a mask detected in the detection step and at least one of the ages of the person are determined.
A correction step of correcting the distance between persons detected in the detection step in the image according to the determination result in the determination step, and a correction step.
An information processing method comprising an output control step of outputting predetermined information according to the distance between the persons corrected in the correction step.
A detection process that detects people contained in images, and
A determination step for determining whether or not a person wearing a mask is detected in the detection step, and a determination step.
A correction step of correcting a threshold value used for determining whether to output predetermined information according to a determination result in the determination step, and a correction step.
An information processing method comprising: an output control step for outputting the predetermined information based on a distance between persons detected in the detection step and a threshold value corrected in the correction step.
A program for making a computer function as each means of the information processing apparatus according to any one of claims 1 to 12.