Camera angle setting method for capturing attendee facial images and attendee authentication device

Abstract

We propose a method for setting the shooting angle and an attendee authentication device that can obtain optimal facial image information of multiple attendees in a classroom using a small number of cameras. [Solution] When facial images of attendees seated in chairs in a classroom having a plurality of desks arranged in an orderly fashion from front to back and chairs arranged behind each desk are taken using a facial image capture device (11) attached to the top of the vertical front wall of the classroom, the imaging angle setting method of the present invention calculates the appropriate facial image capture angle y (degrees) of the facial image capture device (11) using the logarithmic function y=Aln(X)+B for the number of desk columns X (column), where A is the layout coefficient and B is the layout addition number.

Description

[Technical Field]

[0001] The present invention relates to a method for setting the shooting angle of a camera that captures facial images of attendees seated in chairs in a classroom, and to an attendee authentication device. [Background technology]

[0002] The following Patent Document 1 shows an attendance management server using a facial photographing device with a camera placed in a room where multiple attendees gather, taking multiple facial images of attendees while they are seated, and sending the data to an attendance management server to determine whether registered attendees are present. In this facial photographing device, multiple cameras for the facial photographing device are installed in the room, and facial images of attendees while they are seated are automatically captured. Furthermore, the facial images of attendees are registered in the facial photographing device in advance, and the captured data is sent to the attendance management server, which manages attendance data.

[0003] Patent Document 2 discloses a technology for evaluating individual or crowd-level behavior based on image data analysis using a social behavior recognition system 10 including a single or multiple PZT cameras 12 that capture still or video images and a computing device that implements a smartphone, smartwatch, tablet, laptop computer, or desktop computer.

[0004] Patent Document 3 discloses an imaging device that can continue tracking a subject even if tracking fails when tracking based on video analysis. The imaging device is capable of panning, tilting, and zooming and can communicate with a wireless device carried by the subject. The imaging device has: a first determination means that performs video analysis on image data obtained by the imaging means of the imaging device to determine the relative position of the subject with respect to the imaging device; a second determination means that determines the relative position of the subject with respect to the imaging device based on the direction of radio waves received by the wireless device; a determination means that determines whether tracking of the subject has failed as a result of tracking the subject using the first determination means; a position determination control means that executes either the first or second determination means based on the determination result of the determination means; and a PTZ control means that performs panning, tilting, or zooming drive control to the position determined by the first or second determination means. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2012-43389 [Patent Document 2] Patent Publication No. 2018-124972 [Patent Document 3] Patent Publication No. 2023-44924 Summary of the Invention [Problem to be solved by the invention]

[0006] Conventional attendance management servers that authenticate the faces of all students in a school classroom are equipped with facial capture devices, each with a camera installed in front of each student. However, this type of facial capture device requires a large number of cameras, network devices, and facial capture device servers, which creates the drawback of high installation costs. Furthermore, facial capture devices that install cameras above each row of desks in front of students' desks create the problem that students' faces overlap as they move toward the back, making it difficult to capture their faces. Therefore, a new imaging angle setting method and attendee authentication device are needed that can obtain optimal facial image information of attendees using a small number of cameras, regardless of the classroom floor structure, including stepped and flat floor structures. [Means for solving the problem]

[0007] In a classroom with multiple desks arranged in an orderly fashion from front to back and attendees seated in chairs arranged behind each desk, the facial images of attendees are captured by a facial image capture device (camera) attached to the top of the vertical front wall of the classroom. In this method of setting the imaging angle according to the present invention, where A is the arrangement coefficient and B is the arrangement addition number, the appropriate facial image capturing angle y (degrees) of the camera is calculated for the desk row order X using the logarithmic function: y = Aln(X) + B. The logarithmic function ln(X) is the natural logarithm function log with Napier's constant e as the base. e (X).

[0008] In a classroom where multiple desks are arranged in an orderly fashion from front to back and attendees are seated at one or more chairs arranged behind each desk, the positions of the desks, the chairs arranged behind each desk, and the faces of attendees seated at the chairs are arranged in a predetermined or planned state or in a similar manner, allowing attendees to effectively learn the content of the lecture.

[0009] When a camera is attached to the front wall of a classroom where multiple desks and chairs behind each desk are aligned in a sequential order and attendees sitting at each chair effectively learn the lecture content, the inventors have discovered that it is possible to capture clear facial images of multiple attendees with a single or small number of cameras by using a given function that represents the relationship between the row order of the chairs and the angle (depression angle) of the camera. The distance of the camera to the attendees' faces is displayed as a function of the row order X of the desks.

[0010] For example, when using a camera to capture facial images of multiple attendees seated in chairs from the first row to the tenth row, the inventors experimentally determined the camera angle for optimal facial image capture of the attendees and plotted the camera angle for each row of chairs on a graph. The inventors came up with the idea of ​​approximately displaying the camera's appropriate facial image capture angle y (degrees) for the desk row order X using the logarithmic function y = Aln(X) + B on the resulting graph. The camera's appropriate facial image capture angle y (degrees) allows attendees to be accurately and clearly recognized from the attendees' digital facial image information captured by the camera. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing the basic configuration of an attendee authentication device according to the present invention. [Figure 2] A cross-sectional view showing the angle of the camera attached to the top of the front wall of a stepped classroom relative to the horizontal ceiling plane, pointing directly at the faces of attendees. [Figure 3] A cross-section showing the angle of the camera relative to the horizontal ceiling plane and the attendee's face [Figure 4] A cross-sectional view showing the camera angle to the attendees' faces relative to a side wall positioned perpendicular and perpendicular to the front wall of the classroom. [Figure 5] Logarithmic function graph of Example 1 showing the optimal angle characteristics of the camera relative to the faces of attendees in each row in a classroom with a flat floor structure [Figure 6] Logarithmic function graphs of Examples 2 and 3 showing the optimal angle characteristics of the camera relative to the faces of attendees in each row in a stepped classroom. [Figure 7]Logarithmic function graphs of Examples 4 and 5 showing the optimal angle characteristics of the camera relative to the faces of attendees in the left and right seats in each row in a stepped classroom. [Figure 8] Logarithmic function graphs of Examples 6 and 7 showing the optimal angle characteristics of the camera for the faces of attendees in the left and right seats in each row in a flat-floored classroom DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A photographing angle setting method and an attendee authentication device according to the present invention will be described below with reference to the accompanying drawings.

[0013] The attendee authentication device of the present invention shown in Figure 1 includes one or more facial image capture devices (11), i.e., cameras (11), one or more card readers (12) that read card information from authentication cards held by each attendee, a network system (10) to which the cameras (11) and card readers (12) are connected so that they can communicate with each other, an attendance management server (13) that receives facial image information from the cameras (11) and attendee card information from the card readers (12) via the network system (10), and a facial image authentication server (14) that stores facial image information of multiple attendees and is connected to the network system (10). The camera (11) is used in the attendee authentication device to confirm the attendance of attendees by implementing the imaging angle setting method of the present invention to capture facial images of attendees at appropriate imaging angles, and the camera (11) captures facial images of attendees and then transmits the facial image information to the network system (10).

[0014] The camera (11) is equipped with a PTZ function that remotely controls the camera's tilt to cover a wide area. PTZ is an abbreviation of the initials of Pan, Tilt, and Zoom. Pan refers to horizontal tilt, tilt refers to vertical tilt, and zoom refers to zooming in (telephoto) and out (wide-angle). The PTZ function of the camera (11) is controlled via the network system (10) from the attendance management server (13), facial image authentication server (14), and / or a personal computer or smartphone.

[0015] The attendance management server (13) of the attendee authentication device compares the attendee's facial image information sent from the camera (11) with the facial image information stored in the facial image authentication server (14), and if these pieces of information match and the card information from the card reader (12) matches the attendee's proper information, it acknowledges the presence of the attendee.

[0016] The inventors have discovered that by setting the camera angle at a given angle in a classroom with multiple desks and chairs appropriately arranged behind each desk, clear facial images of all attendees can be captured with a single or small number of cameras. For example, in a classroom with a flat floor or a stepped floor, a camera can be installed on the front wall at a height of 2800 mm or 3000 mm from the floor, as shown in Figures 2 and 3, and the camera angle relative to the ceiling plane and the front-row attendees can be set at 27° or 30°. While Figure 2 shows a portion of a stepped-floor classroom, the present invention can be equally well implemented in classrooms with a flat floor structure. Figure 4 shows an example in which the camera angle relative to the side wall perpendicular to the front wall is set at 29° or less to the faces of the front-row attendees.

[0017] The inventors measured the camera angle required to capture clear facial image information of attendees seated in chairs in each row in a classroom with desks in rows 1 to 10 and chairs placed behind the desks. The actual measured values ​​of the camera angle are shown in Table 1.

[0018] [Table 1]

[0019] The first embodiment of the present invention includes Examples 1 to 8 in which the appropriate facial image capturing angle y of the camera is displayed as a logarithmic function of the desk row order X. In the first embodiment, the appropriate facial image capturing angle y of the camera is displayed as a logarithmic curve. In contrast, the second embodiment of the present invention includes Example 8 in which the appropriate facial image capturing angle y is displayed as the area of ​​an inter-logarithmic function region sandwiched between multiple logarithmic curves displayed as logarithmic functions. The placement coefficient A and placement addition number B of each example are calculated and shown to two or three decimal places in Figures 5 to 8, but in the examples, the number to the second decimal place is rounded off to display the placement coefficient A and placement addition number B as practical values.

[0020] Figure 2 shows a partial cross-sectional view of a camera used to implement the imaging angle setting method of the present invention, attached to the vertical front wall of a stepped classroom, showing the horizontal ceiling plane and the camera angle relative to the faces of attendees. Figure 2 is a cross-sectional view showing only the first and second rows of the first to tenth rows, omitting the third and subsequent rows. In fact, Figure 3 shows the first to fifth rows, omitting the sixth and subsequent rows.

[0021] Example 1 Example 1 shown in Figure 5 shows actual measurements of the relationship between the facial angles of attendees and each row, with desks and chairs arranged from the first row to the tenth row in a classroom with a stepped floor structure, and a camera installed on the front wall at a height of 2800 mm or 3000 mm. If the appropriate facial image capturing angle of the camera for the desk row order X is y (degrees), an approximate curve connecting the multiple actual measurements entered (plotted) in Figure 5 can be expressed as a logarithmic function: Example 1: y = -8.2ln(X) + 26.8 It has been found that the approximate value y of the angle at which the face image of the attendee is captured relative to the camera can be calculated by the following equation.

[0022] Examples 2 and 3 Examples 2 and 3 in Figure 6, represented by numbers 2 and 3 in Table 1, show the actual measurements of the relationship between the facial angles of attendees and each row, with the desks and chairs in rows 1 to 10 arranged with a step height of 100 mm, and the camera installed on the front wall at angles of 30° and 27° relative to the horizontal plane of the ceiling. If the appropriate facial image capturing angle of the camera relative to the desk row order X is y (degrees), the logarithmic functions of the approximation curves connecting the multiple actual measurements entered (plotted) in Figure 6 are: Example 2: y = -11.1 ln(X) + 30.2 Example 3: y = -10.4ln(X) + 27.1 It has been found that an approximate value y of the angle at which the face image of the attendee is captured relative to the camera can be calculated.

[0023] Examples 4 and 5 Examples 4 and 5 in Figure 7, represented by numbers 4 and 5 in Table 1, show actual measurements of the relationship between the facial angles of attendees and each row, with the desks and chairs in rows 1 to 10 arranged with a step height of 100 mm, and the camera installed on the front wall at angles of 30° and 27° relative to the horizontal plane of the ceiling. If the appropriate facial image capturing angle of the camera relative to the desk row order X is y (degrees), the logarithmic function of the approximation curve connecting the multiple actual measurements plotted in Figure 7 is: Example 4: y = -8.9 ln(X) + 29.5 Example 5: y = -3.7ln(X) + 12.2 It has been found that the approximate value y of the angle at which the face image of the attendee is captured relative to the camera can be calculated by the following equation.

[0024] Examples 6 and 7 Examples 6 and 7 in Figure 8, represented by numbers 6 and 7 in Table 1, show actual measurements of the relationship between the facial angles of attendees and each row, with desks and chairs arranged in rows 1 to 10 in a flat-floored classroom, and a camera installed on the front wall at angles of 30° and 27° relative to the horizontal plane of the ceiling. If the appropriate facial image capturing angle of the camera relative to the desk row order X is y (degrees), then the logarithmic functions of the approximation curves connecting the multiple actual measurements entered (plotted) in Figure 8 are: Example 6: y = -10.8ln(X) + 36.9 Example 7: y = -6.6ln(X) + 21.1 It has been found that the approximate value y of the angle at which the face image of the attendee is captured relative to the camera can be calculated by the following equation.

[0025] Example 8 In Examples 4 and 5 of Figure 7, the appropriate facial image capturing angles y (degrees) for the camera's left and right seats are expressed by logarithmic functions: y = -8.9ln(X) + 29.5 and y = -3.7ln(X) + 12.2, respectively. In Example 7, it was found that the camera angle falling within the logarithmic function region sandwiched between the double logarithmic function curves of Examples 4 and 5 can be adopted as the appropriate facial image capturing angle.

[0026] Example 9 In Examples 6 and 7 of Figure 8, the appropriate facial image capturing angles y (degrees) for the camera on the left and right seats are expressed on logarithmic function curves displayed as logarithmic functions: y = -10.8ln(X) + 36.9 and y = -6.6ln(X) + 21.1, respectively. In Example 8, as in Examples 4 and 5, it was found that the camera angle falling into the logarithmic function region sandwiched between the double logarithmic function curves of Examples 6 and 7 can be adopted as the appropriate facial image capturing angle.

[0027] In the above Examples 1 to 7, where A is the arrangement coefficient and B is the arrangement addition number, the general formula for the camera's appropriate facial image capturing angle y (degrees), which is a logarithmic function of the desk row order X, is expressed as y = Aln(X) + B. The arrangement function A and the arrangement addition number B are constants that differ depending on the size of the classroom, the arrangement of the desks and chairs, and the facial angles of the attendees relative to the camera, but the camera angles relative to the faces of the attendees seated in a classroom where a lecture is held do not vary greatly.

[0028] The examples and embodiments of the present invention are not limited to the above description and can be further modified. For example, even in a classroom where desks and chairs are arranged in less than 10 rows or more than 11 rows, the appropriate facial image capturing angle y (degrees) of the camera can be displayed as a logarithmic function, and attendees can be recognized from the facial image. Even in a classroom where 1 to 4 attendees are seated in chairs behind a single desk, the appropriate facial image capturing angle y (degrees) of the camera can be displayed as a logarithmic function.

[0029] The logarithmic function's appropriate facial image capturing angle y is the angle at which the camera lens focuses on the attendee's face, but even if the angle is not on the logarithmic function curve and is slightly off the focus of the camera lens, and the angle error value is within 10% of the logarithmic function curve, it can be adopted as an appropriate facial image capturing angle image that is clear enough to identify the attendee's face image. While Figures 2 and 3 show a classroom with a stepped floor structure, it will be understood that the capturing angle setting method and attendee authentication device of the present invention can also be applied to classrooms with flat floor structures.

[0030] The imaging angle setting method of the present invention can provide the following effects. 1. By determining the seat position and direction relative to the camera, selecting the placement coefficient A and placement adder B, and setting the appropriate facial image capture angle y for one or a small number of cameras using a logarithmic function, clear facial images of all attendees can be captured. This makes it possible to confirm whether or not someone is present. 2. The camera (11) itself or the attendance management server (13) that controls the camera's attitude stores a logarithmic function, and the placement function A and placement addition number B are determined to match the classroom conditions, allowing the camera to capture clear facial images of all attendees. 3. In a typical classroom, an optical magnification of 20x to 30x for a camera with PTZ functionality is sufficient. 4. It is possible to capture clear facial images of attendees in classrooms with flat floors or floors with 100mm, 150mm or any other step height. [Industrial Applicability]

[0031] The imaging angle setting method and attendee authentication device according to the present invention can be used to check the status of meetings and conference attendance within organizations such as various universities, groups, or companies, including medical and pharmaceutical universities. [Explanation of symbols]

[0032] (10) Network system, (11) Camera with PTZ function (face image capture device), (12) Card reader, (13) Attendance management server, (14) Face image authentication server,

Claims

1. When facial images of attendees seated on chairs in a classroom having a plurality of desks arranged in an orderly fashion from front to back and chairs arranged behind each desk are captured by a facial image capture device attached to the upper part of the vertical front wall of the classroom, If A is the arrangement coefficient and B is the arrangement addition number, then for the row order of the desks, X, we have the logarithmic function: y=Aln(X)+B A method for setting an imaging angle, characterized by calculating an appropriate facial image imaging angle y (degrees) of a facial image acquisition device by the above method.

2. The logarithmic function representing the appropriate facial image capturing angle y (degrees) of the facial image capturing device is: y=-8.2ln(X)+26.8 y=-11.1ln(X)+30.2 y=-10.4ln(X)+27.1 y=-8.9ln(X)+29.5 y = -3.7ln(X) + 12.2 y = -10.8ln(X) + 36.9 or y=-6.6ln(X)+21.1 2. The method for setting a shooting angle according to claim 1, wherein the angle is displayed as one of the following.

3. When attendees are seated at a left seat arranged behind each of a plurality of desks and a right seat arranged adjacent to the left seat, the appropriate facial image capturing angle y (degrees) of the facial image capturing device for the left seat and the right seat is expressed as a logarithmic function: y=-10.8ln(X)+36.9 and y=-6.6ln(X)+21.1 3. The method for setting a photographing angle according to claim 2, wherein a camera angle in a region corresponding to the double logarithmic function curve of the above formula is adopted as the appropriate photographing angle for the face image.

4. When attendees are seated at a left seat arranged behind each of a plurality of desks and a right seat arranged adjacent to the left seat, the appropriate facial image capturing angle y (degrees) of the facial image capturing device for the left seat and the right seat is expressed as a logarithmic function: y=-8.9ln(X)+29.5 y = -3.7ln(X) + 12.2 3. The method for setting a photographing angle according to claim 2, wherein a camera angle in a region corresponding to the double logarithmic function curve of the above formula is adopted as the appropriate photographing angle for the face image.

5. 2. The method of claim 1, wherein even if a face image photographing angle does not fall on a logarithmic function curve, an error value within 10% of the logarithmic function angle is adopted as the appropriate face image photographing angle.

6. 2. The method for setting a photographing angle according to claim 1, wherein the angle of the camera attached to the vertical front wall of the classroom to the desk at the front seat is 29 degrees or less with respect to a vertical side wall disposed at a right angle to the front wall.

7. 2. The imaging angle setting method according to claim 1, wherein the classroom has a plurality of desks arranged in an orderly fashion from front to back and chairs arranged behind each desk, and the classroom has a flat floor structure or a stepped floor structure.

8. 8. The method for setting an imaging angle according to claim 7, wherein the stepped floor structure has each step having a height of 100 mm, 150 mm or other heights.

9. a facial image acquisition device that performs the imaging angle setting method according to any one of claims 1 to 8 and captures facial image information of attendees at an appropriate facial image imaging angle y; A card reader for inputting card information of a card owned by each attendee; an attendance management server that receives face image information from the face image capture device and attendee card information from the card reader; a facial image authentication server that stores facial image information of a large number of attendees; A network system that interconnects a face image capture device, a card reader, an attendance management server, and a face image authentication server, An attendee authentication device characterized in that the attendance management server compares the facial image information of the attendee sent from the facial image acquisition device with the facial image information stored in the facial image authentication server, and when these pieces of information match and the card information from the card reader matches the attendee information, approves the attendance of the attendee.

Images