Temperature calculation device, temperature calculation method, program, and recording medium

Abstract

To provide a temperature calculation device which can calculate the ambient temperature of a subject from a thermal image.SOLUTION: A temperature calculation device 10 of the present invention comprises: an image acquisition unit 11 which acquires a thermal image formed by imaging a measurement target range, wherein the thermal image is divided into a plurality of sections and associated with section temperature information indicating the temperature of each of the sections; an extraction unit 13 which extracts at least one or more specific sections from the sections of the thermal image; a temperature calculation unit 14 which calculates the ambient temperature of the measurement target range, on the basis of the section temperature information and using the temperature of the at least one or more specific sections.SELECTED DRAWING: Figure 1

Description

Technical Field

[0006] , , ,

[0001] The present invention relates to a temperature calculation device, a temperature calculation method, a program, and a recording medium.

Background Art

[0002] For health management, it is important to measure body temperature. For measuring body temperature, there is a technique for measuring the surface temperature of a subject non - contact using a thermographic camera. For example, in Patent Document 1, a technique for correcting acquired infrared image data using temperature data of a temperature reference is reported.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, as described above, when measuring the surface temperature of a subject non - contact, the external environment such as room temperature and outside air temperature affects the temperature data shown in the thermal image, and an accurate surface temperature cannot be measured. Further, in the technique of Patent Document 1, there are problems such as the need for a special device such as a temperature reference system, and the problem that the special device itself is affected by the external environment and cannot provide an appropriate temperature reference. Therefore, a technique for calculating the external environment, that is, the temperature around the subject, from a thermal image is required.

[0005] Therefore, an object of the present invention is to provide a temperature calculation device, a temperature calculation method, a program, and a recording medium capable of calculating the temperature around a subject from a thermal image.

Means for Solving the Problems

[0007] The temperature calculation method of the present invention is This includes an image acquisition process, an extraction process, and a temperature calculation process. The image acquisition step involves acquiring a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction step involves extracting at least one specific area from each area of ​​the thermal image, The temperature calculation step is a method for calculating the temperature of the measurement target range using the temperatures of at least one of the specific sections based on the section temperature information. [Effects of the Invention]

[0008] According to the present invention, the temperature around a subject can be calculated from a thermal image. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is a block diagram showing the configuration of an example of a temperature calculation device of Embodiment 1. [Figure 2] Figure 2 is a block diagram showing an example of the hardware configuration of the temperature calculation device of Embodiment 1. [Figure 3] Figure 3 is a flowchart showing an example of the processing in the temperature calculation device of Embodiment 1. [Figure 4]Figure 4 is a schematic diagram showing an example in which four sections are extracted as the specific sections by the extraction unit. [Figure 5] Figure 5 is a schematic diagram showing an example in which the top row of the thermal image is extracted as a specific section by the extraction unit. [Modes for carrying out the invention]

[0010] In the temperature calculation device of the present invention, for example, The extraction unit may be configured to extract a specific section from the uppermost row of sections in the thermal image.

[0011] In the temperature calculation device of the present invention, for example, The extraction unit extracts at least four specific sections from the thermal image, The temperature calculation unit may, based on the section temperature information, calculate the temperature of the measurement target range using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature.

[0012] In the temperature calculation device of the present invention, for example, The temperature calculation unit may calculate the temperature of the measurement target range using the temperatures in at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature.

[0013] In the temperature calculation device of the present invention, for example, The temperature calculation unit may also calculate the average value of the temperatures in at least two or more specific sections and set the average value as the temperature of the measurement target range.

[0014] In the temperature calculation device of the present invention, for example, The extraction unit may be configured to extract at least one specific section from each section of the thermal image according to at least one of the following preset conditions (1) to (5). (1) Excluding sections where the temperature is outside a preset temperature range (2) As the specific section, including at least one of the sections at the four corners of the thermal image (3) Excluding sections below the section corresponding to the position of the face of the measurement target person included in the thermal image (4) Extracting, as the specific section, sections that are separated by a preset number of sections or more from the section corresponding to the position of the face of the measurement target person included in the thermal image (5) Excluding the section corresponding to the position of the face of the measurement target person included in the thermal image

[0015] In the temperature calculation device of the present invention, for example, The temperature calculation unit may be configured to calculate the surface temperature of the measurement target person included in the thermal image based on the section temperature information.

[0016] The temperature calculation device of the present invention, for example, Further includes a correction unit, The correction unit may be configured to correct the calculated surface temperature of the measurement target person using the calculated temperature of the measurement target range.

[0017] The temperature calculation device of the present invention, for example, Further includes a recording unit, a detection unit, and an authentication unit, The recording unit records registrant information including face information regarding the face of the registrant, The image acquisition unit further acquires a real photo image corresponding to the thermal image, The detection unit detects the face of the measurement target person from the real photo image, The authentication unit may be configured to compare the detected face of the measurement target person with the face of the registrant, and authenticate the measurement target person as the registrant when they match.

[0018] In the temperature calculation method of the present invention, for example, The extraction step may be an embodiment in which the specific section is extracted from the uppermost row of the thermal image sections.

[0019] In the temperature calculation method of the present invention, for example, The extraction step involves extracting at least four specific sections from the thermal image. The temperature calculation step may also be configured to calculate the temperature of the measurement target range using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature, based on the section temperature information.

[0020] In the temperature calculation method of the present invention, for example, The temperature calculation step may also be carried out in an embodiment in which the temperature of the measurement target range is calculated using the temperatures of at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature.

[0021] In the temperature calculation method of the present invention, for example, The temperature calculation step may also be configured to calculate the average value of the temperatures in at least two or more specific sections, and to use the average value as the temperature of the measurement target range.

[0022] In the temperature calculation method of the present invention, for example, The extraction step may be carried out in a manner in which at least one specific area is extracted from each area of ​​the thermal image in accordance with at least one of the following pre-set conditions (1) to (5). (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the area below the area corresponding to the position of the face of the person being measured included in the thermal image. (4) From the area corresponding to the position of the subject's face included in the thermal image, areas that are separated by a predetermined number of areas or more are extracted as the specific areas. (5) Excluding the area corresponding to the position of the subject's face included in the thermal image.

[0023] In the temperature calculation method of the present invention, for example, The temperature calculation step may also be configured to calculate the surface temperature of the subject being measured, as included in the thermal image, based on the area temperature information.

[0024] The temperature calculation method of the present invention is, for example, Furthermore, including the correction process, The correction step may also be carried out in which the calculated surface temperature of the person being measured is corrected using the calculated temperature of the measurement target range.

[0025] The temperature calculation method of the present invention is, for example, Furthermore, it includes a recording process, a detection process, and an authentication process, The aforementioned recording step records registrant information, including facial information relating to the registrant's face. The image acquisition step further acquires a real-world image corresponding to the thermal image, The aforementioned detection step involves detecting the face of the person to be measured from the actual image, The authentication step may also be configured to compare the face of the person being measured with the face of the registered person, and if they match, to authenticate the person being measured as the registered person.

[0026] The program of the present invention is a program that causes a computer to execute each step of the method of the present invention as a procedure.

[0027] The recording medium of the present invention is a computer-readable recording medium that stores the program of the present invention.

[0028] Next, embodiments of the present invention will be described with reference to the drawings. The present invention is not limited to the following embodiments. In the following drawings, the same parts are denoted by the same reference numerals. Furthermore, unless otherwise specified, the descriptions of each embodiment can be used interchangeably with those of the others, and unless otherwise specified, the configurations of each embodiment can be combined.

[0029] [Embodiment 1] Figure 1 is a block diagram showing an example configuration of the temperature calculation device 10 of this embodiment. As shown in Figure 1, the device 10 includes an image acquisition unit 11, an extraction unit 13, and a temperature calculation unit 14. The device 10 may also optionally include a detection unit 12, a recording unit 15, an authentication unit 16, and a correction unit 17. The device 10 may, for example, be a device within a device that measures the surface temperature of a person being measured from a thermal image.

[0030] The device 10 may be, for example, a single device including the aforementioned parts, or it may be a device in which each of the aforementioned parts can be connected via a communication network. Furthermore, the device 10 can be connected to an external device described later via the communication network. The communication network is not particularly limited and can use a known network, for example, it may be wired or wireless. Examples of the communication network include the Internet, WWW (World Wide Web), telephone lines, LAN (Local Area Network), SAN (Storage Area Network), DTN (Delay Tolerant Networking), LPWA (Low Power Wide Area), L5G (Local 5G), etc. Examples of wireless communication include Wi-Fi (registered trademark), Bluetooth (registered trademark), Local 5G, LPWA, etc. The wireless communication may be in the form of direct communication between devices (Ad Hoc communication), infrastructure communication, indirect communication via an access point, etc. The device 10 may be, for example, incorporated into a server as a system. Furthermore, the device 10 may be, for example, a personal computer (PC, e.g., desktop or notebook type), smartphone, tablet terminal, etc., on which the program of the present invention is installed. Moreover, the device 10 may be in a form such as cloud computing or edge computing, where, for example, at least one of the aforementioned parts is on a server and the other aforementioned parts are on a terminal.

[0031] Figure 2 illustrates a block diagram of the hardware configuration of the device 10. The device 10 includes, for example, a central processing unit (CPU, GPU, etc.) 101, memory 102, bus 103, storage device 104, input device 105, display device 106, communication device 107, imaging device 108, etc. Each part of the device 10 is interconnected via the bus 103 through its respective interface (I / F).

[0032] The central processing unit 101 is responsible for the overall control of the device 10. In the device 10, the central processing unit 101 executes, for example, the program of the present invention and other programs, and also reads and writes various types of information. Specifically, for example, the central processing unit 101 functions as an image acquisition unit 11, an extraction unit 13, and a temperature calculation unit 14. The central processing unit 101 also functions as, for example, a detection unit 12, a recording unit 15, an authentication unit 16, and a correction unit 17.

[0033] Bus 103 can also be connected to external devices, for example. Examples of such external devices include external storage devices (external databases, etc.), printers, external input devices, external display devices, and external imaging devices. The device 10 can be connected to an external network (the aforementioned communication network) via a communication device 107 connected to bus 103, for example, and can also be connected to other devices via the external network.

[0034] Memory 102 may be, for example, main memory. When the central processing unit 101 performs processing, memory 102 reads various operational programs, such as the program of the present invention, stored in the storage device 104 (described later), and the central processing unit 101 receives data from memory 102 and executes the program. The main memory may be, for example, RAM (random access memory). Alternatively, memory 102 may be, for example, ROM (read-only memory).

[0035] The storage device 104 is also called an auxiliary storage device, for example, in relation to the main memory (primary memory). As described above, the storage device 104 stores an operating program including the program of the present invention. The storage device 104 may be, for example, a combination of a recording medium and a drive for reading and writing to the recording medium. The recording medium is not particularly limited and may be internal or external, for example, an HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, etc. The storage device 104 may be, for example, a hard disk drive (HDD) in which the recording medium and the drive are integrated, or a solid state drive (SSD).

[0036] In this device 10, the memory 102 and storage device 104 can also store various types of information, such as log information, information obtained from an external database (not shown) or external devices, information generated by this device 10, and information used by this device 10 when executing processing. At least some of the information may be stored on an external server other than the memory 102 and storage device 104, or it may be stored in a distributed manner across multiple terminals using blockchain technology or the like. In addition, the memory 102 and storage device 104 may store various types of information recorded by the recording unit 15, for example.

[0037] The device 10 may further include, for example, an input device 105 and a display device 106. The input device 105 is, for example, a touch panel, a keyboard, a mouse, etc. The display device 106 is, for example, an LED display, a liquid crystal display, etc.

[0038] The imaging device 108 is, for example, a device for capturing thermal images (such as a thermographic camera) or a device for capturing real-world images (such as a camera). The device for capturing thermal images and the device for capturing real-world images may share an imaging lens, for example. Light incident from the imaging lens is decomposed into visible light and infrared light, with the visible light incident on the device for capturing real-world images and the infrared light incident on the device for capturing thermal images. The device for capturing thermal images may be equipped with a dedicated imaging lens separate from the shared imaging lens.

[0039] Next, an example of the temperature calculation method of this embodiment will be described based on the flowchart in Figure 3. The temperature calculation method of this embodiment is carried out as follows, for example, using the temperature calculation device 10 in Figure 1. Note that the temperature calculation method of this embodiment is not limited to the use of the temperature calculation device 10 in Figure 1. Also, the steps shown in parentheses in Figure 3 are arbitrary steps.

[0040] First, the image acquisition unit 11 acquires a thermal image of the measurement target area (S11, image acquisition step). The thermal image is, for example, an image composed of multiple pixels representing the temperature distribution of the measurement target area, and is also called an infrared image or thermography. The actual image is, for example, an image taken when visible light is incident on the imaging device 108. The thermal image is divided into multiple sections and is linked to section temperature information indicating the temperature of each section. The thermal image may be divided into multiple sections for each pixel, for example. As will be described later, the image acquisition unit 11 may, for example, further acquire an actual image corresponding to the thermal image in step (S11). The "actual image corresponding to the thermal image" is, for example, an image taken in the same direction, and may have the same field of view. The acquisition method is not particularly limited, and for example, the thermal image and the actual image may be acquired from an external imaging device via the communication network, or an image taken by the imaging device 108 may be acquired.

[0041] Next, the extraction unit 13 extracts at least one specific area from each area of ​​the thermal image (S13, extraction step). The extraction unit 13 may extract at least one area, or four or more areas. There is no particular upper limit on the number of areas extracted by the extraction unit 13.

[0042] The extraction unit 13 may, for example, extract at least one specific area from each area of ​​the thermal image according to at least one of the following pre-set conditions (1) to (5). (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the area below the area corresponding to the position of the face of the person being measured included in the thermal image. (4) From the area corresponding to the position of the subject's face included in the thermal image, areas that are separated by a predetermined number of areas or more are extracted as the specific areas. (5) Excluding the area corresponding to the position of the subject's face included in the thermal image.

[0043] In the above condition (1), the temperature range is not particularly limited and can be set arbitrarily. By excluding areas outside the temperature range from the extraction candidates in this way, even if there are heat sources (e.g., fire) or cold sources (e.g., ice) within the measurement target range, the temperature calculation unit 14 described later can calculate the temperature of the measurement target range more accurately.

[0044] In the above condition (2), the four corners of the thermal image are, for example, the four sections where, when the horizontal direction of the thermal image is the X-axis and the vertical direction is the Y-axis, and the position information of the section is (X, Y), the section with the maximum X value, the section with the minimum X value, the section with the maximum Y value, and the section with the minimum Y value. In this case, the extraction unit 13 only needs to extract at least one section from the four corner sections of the thermal image as the specific section, for example, it may be two, three, or four sections. When extracting two sections from the four corner sections, for example, the two sections may be diagonally opposite each other or on the same line. The central part of the realized image often contains the subject of measurement. Therefore, by extracting at least one section from the four corner sections of the thermal image as the specific section in this way, the temperature of the measurement target range can be calculated more accurately by the temperature calculation unit 14 described later, without being affected by the heat emitted by the subject of measurement. Furthermore, for example, by extracting at least two of the four corner sections of the thermal image as the specific sections, a certain distance is created between the specific sections, preventing them from interfering with each other, thus allowing for a more accurate calculation of the temperature of the measurement target area. The same applies when three or four of the four corner sections of the thermal image are extracted as the specific sections.

[0045] The "area below the area corresponding to the position of the subject's face" in condition (3) above will be explained using the example where the horizontal direction of the thermal image is the X-axis and the vertical direction is the Y-axis, and the position information of the area is (X, Y). The "area below the area corresponding to the position of the subject's face" is, for example, an area that has an X value between the maximum X value and the minimum X value of the area corresponding to the position of the subject's face, and has a Y value lower than the minimum Y value of the area corresponding to the position of the subject's face. The position of the subject's face can be detected from the actual image by the detection unit 12 described later, for example, but is not limited to this (the same applies to conditions (4) and (5) above). That is, the detection unit 12 described later may, for example, detect the position of the subject's face before step (S13) (S12, detection step). This allows the temperature of the measurement target range to be calculated more accurately by the temperature calculation unit 14 described later, without having to extract an area indicating the temperature of the clothes the subject is wearing.

[0046] In the above condition (4), the number of pre-set sections is not particularly limited and can be set arbitrarily. In addition, for example, in addition to the number of sections, a direction may be set. Specifically, for example, it may be set to "5 sections in either the left or right direction". This allows the temperature of the measurement target range to be calculated more accurately by the temperature calculation unit 14 described later, without being affected by the heat emitted by the person being measured.

[0047] According to the above condition (5), the temperature of the measurement target range can be calculated more accurately by the temperature calculation unit 14 described later, without being affected by the heat emitted by the person being measured.

[0048] The extraction unit 13 may, for example, extract the specific area from the uppermost row of areas in the thermal image. Specifically, the extraction unit 13 may, for example, extract some of the areas in the uppermost row as the specific area, or it may extract all of the areas in the uppermost row as the specific area. Among the areas extracted as the specific area, for example, areas corresponding to the position of the person being measured included in the thermal image are excluded.

[0049] Then, the temperature calculation unit 14 calculates the temperature of the measurement target range using the temperatures in at least one of the specific sections based on the section temperature information (S14a, temperature calculation step), and the process ends (END). Specifically, the temperature calculation unit 14 may, for example, calculate the average value of the temperatures in at least two of the specific sections and use the average value as the temperature of the measurement target range. Alternatively, if the extraction unit 13 extracts at least four of the specific sections, the temperature calculation unit 14 may, for example, calculate the temperature of the measurement target range using the temperatures in at least two of the specific sections, excluding the section with the maximum temperature and the section with the minimum temperature, based on the section temperature information. In this way, by excluding the section with the maximum temperature and the section with the minimum temperature from the specific sections, the error can be reduced, and the temperature of the measurement target range can be calculated more accurately.

[0050] Furthermore, if the extraction unit 13 extracts at least four specific sections, the temperature calculation unit 14 may, for example, in step (S14a), calculate the temperature of the measurement target range using the temperatures of at least two of the specific sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature. Each predetermined number is not particularly limited and may be set as a ratio to the total number of sections (for example, 30% of the total). For example, if "30% of the total number of sections" is set as each predetermined number, the temperature calculation unit 14 calculates the temperature of the measurement target range using the temperatures of the remaining 40% of the specific sections, excluding the sections that fall into the top 30% and the bottom 30% in terms of temperature. This makes it possible to reduce errors due to obstacles (for example, the person being measured) and to calculate the temperature of the measurement target range more accurately.

[0051] Furthermore, the temperature calculation unit 14 may, for example, calculate the surface temperature of the person being measured included in the thermal image based on the area temperature information (S14b, temperature calculation step). The algorithm for calculating the surface temperature of the person being measured is not particularly limited, and for example, known techniques can be used. This makes it possible to measure the surface temperature of the person being measured. Step (S14b) may be performed after step (S14a), before step (S14a), or in parallel, as shown in Figure 3, for example. The person being measured is detected from the actual image by the detection unit 12 described later, for example, but is not limited to this. That is, the detection unit 12 described later may detect the person being measured before step (S14b), for example (S12).

[0052] As described above, the apparatus 10 may further include, for example, a correction unit 17. The correction unit 17 corrects the calculated surface temperature of the subject to be measured using the temperature of the measurement target range calculated after the above step (S14b) (S17, correction step). The algorithm for the correction is not particularly limited, and for example, known techniques can be used. This makes it possible to accurately measure the surface temperature of the subject to be measured.

[0053] As described above, the device 10 may further include, for example, a recording unit 15, a detection unit 12, and an authentication unit 16. In this case, the image acquisition unit 11 may, for example, acquire the actual image in step (S11) as described above. The detection unit 12 may, for example, detect the face of the person to be measured from the actual image after step (S11) (S12). The algorithm for detecting the face of the person to be measured from the actual image is not particularly limited, and for example, known techniques can be used. On the other hand, the recording unit 15 may, for example, perform a process to store registrant information, including face information relating to the face of the registrant, in advance (S15, recording step). The recording unit 15 may, for example, store the registrant information in memory 102 and storage device 104, or it may store the registrant information in an external database or server. The authentication unit 16, for example, after steps (S12) and (S15), compares the detected face of the person to be measured with the face of the registered person, and if they match, authenticates the person to be measured as the registered person (S16, authentication step). The unit then terminates after performing at least steps (S14a) and (S16) (END). On the other hand, if they do not match, the unit terminates without authenticating the person to be measured as the registered person (END). The algorithms for the comparison and authentication are not particularly limited, and for example, known technologies can be used. This allows, for example, face authentication to be performed in addition to measuring (calculating) the temperature of the measurement target range and measuring the surface temperature of the person to be measured.

[0054] According to this embodiment, for example, by extracting a specific area, the temperature of the measurement target area (e.g., around the subject) can be calculated from the thermal image. Furthermore, according to this embodiment, for example, by calculating the temperature of the measurement target area, the surface temperature of the subject can be accurately measured non-contact. Moreover, according to this embodiment, for example, facial recognition of the subject can be performed.

[0055] [Embodiment 2] An example of measuring room temperature using the present invention will be described. Note that the present invention is applicable not only indoors but also outdoors.

[0056] Figures 4(A) to (C) show examples in which the extraction unit 13 extracts four sections (sections A to D, or section D' instead of section D) as the specific sections. An example of the actual image acquired by the image acquisition unit 11 is shown at the top of Figures 4(A) to (C). In Figure 4(A), the person being measured is located in the central part of the actual image, and in Figures 4(B) and (C), the person being measured is located so as to overlap with section D. The thermal image is divided into multiple sections and is assumed to have the same field of view as the actual image, except that it is linked to section temperature information indicating the temperature of each section. In the actual image in the figures, for explanatory purposes, the positions corresponding to sections A to D and D' are indicated by dashed-dotted lines, and sections other than sections A to D and D' are omitted. The temperatures of sections A to D and D' are indicated at the bottom of Figures 4(A) and (B).

[0057] In the example shown in Figure 4(A), the extraction unit 13 extracts the four corner sections (sections A to D) of the thermal image as the specific sections. Of these sections A to D, section A has the highest temperature and section D has the lowest temperature. In this case, the temperature calculation unit 14 calculates the average temperature of sections B and C, excluding sections A and D, and sets this average value as the room temperature.

[0058] In the example shown in Figure 4(B), the extraction unit 13 extracts the four corner sections (sections A to D) of the thermal image as the specific sections. Of these sections A to D, section D has the highest temperature and section C has the lowest temperature. In this case, the temperature calculation unit 14 calculates the average temperature of sections A and B, excluding sections C and D, and sets this average value as the room temperature.

[0059] In the example shown in Figure 4(C), unlike the example shown in Figure 4(B), the extraction unit 13 extracts four sections (sections A to C, and section D') as the specific section, including section D' which does not correspond to the position of the subject's face and is far from the subject's face, instead of section D which corresponds to the position of the subject's face. Of these sections A to D', section A has the highest temperature and section C has the lowest temperature. In this case, the temperature calculation unit 14 calculates the average temperature of sections B and D', excluding sections A and C, and sets the average value as the room temperature.

[0060] When measuring the surface temperature of a subject using the technology described in Patent Document 1, etc., a thermal image is sometimes obtained in which the subject's face is positioned in the center of the field of view. Therefore, as in this embodiment, by using the four corner sections of the thermal image, the temperature of the measurement target area can be accurately measured without being affected by obstacles (heat emitted by the subject, fire, etc., or ice, etc.). Furthermore, even if a thermal image is obtained in which the subject is positioned at the four corners, the error due to obstacles can be reduced by excluding the section with the maximum temperature and the section with the minimum temperature, or by using a section far from the subject's face, to calculate the temperature of the measurement target area (room temperature). This also reduces the influence of obstacles (heat emitted by the subject, fire, etc., or ice, etc.).

[0061] Figures 5(A) and (B) show examples in which the extraction unit 13 extracts the top row of the thermal image as the specific section. Figures 5(A) and (B) show examples of the actual images acquired by the image acquisition unit 11. In Figure 5(A), the person being measured is located in the central part of the actual image, and in Figure 5(B), the person being measured is positioned so that the upper part of their face is cut off. The thermal image is divided into multiple sections and is the same as the actual image, except that it is linked to section temperature information indicating the temperature of each section. In the actual image in the figures, for explanatory purposes, the position corresponding to the specific section is indicated by a dashed-dotted line frame, and sections other than the specific section are omitted. The temperature of each section is written at the bottom of Figure 5(A).

[0062] In the example shown in Figure 5(A), the extraction unit 13 extracts all the sections in the topmost column (a total of 160 sections) as the specific sections. In this example, for example, suppose that "30% of the total number of sections" is set as the preset number in the temperature calculation unit 14. In this case, the temperature calculation unit 14 calculates the average value of each temperature in the remaining 40% of the specific sections (i.e., 64 sections) after excluding the sections whose temperatures fall in the top 30% (i.e., the top 48 sections) and the sections whose temperatures fall in the bottom 30% (i.e., the bottom 48 sections), and sets the average value as the room temperature.

[0063] In the example shown in Figure 5(B), the extraction unit 13 extracts a portion of the uppermost row as the specific portion. Specifically, in Figure 5(B), the extraction unit 13 extracts the portions other than the portion corresponding to the position of the face of the person being measured as the specific portion. The processing in the temperature calculation unit 14 is the same as in Figure 5(A), for example.

[0064] In this way, by extracting the top row of the thermal image as the specific section, the temperature of the measurement target area can be accurately measured without being affected by obstacles (such as the heat emitted by the person being measured or a fire, or ice). Furthermore, even if a thermal image is obtained in which the person being measured is located at the top of the thermal image, the error caused by the obstacles can be reduced by excluding the section in which the person is located from the specific section and calculating the temperature of the measurement target area (room temperature).

[0065] [Embodiment 3] The program of this embodiment is a program that causes a computer to execute each step of the method of the present invention as a procedure. In the present invention, "procedure" may be read as "process". Furthermore, the program of this embodiment may be recorded on a computer-readable recording medium, for example. The recording medium is not particularly limited and includes, for example, read-only memory (ROM), hard disk (HD), optical disc, etc.

[0066] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments. Various modifications to the configuration and details of the present invention can be understood by those skilled in the art within the scope of the present invention.

[0067] <Note> Some or all of the above embodiments may be described as follows, but are not limited to the following: (Note 1) Including an image acquisition unit, an extraction unit, and a temperature calculation unit, The image acquisition unit acquires a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction unit extracts at least one specific area from each area of ​​the thermal image, The temperature calculation unit is a temperature calculation device that calculates the temperature of the measurement target range using the temperatures of at least one of the specific sections based on the section temperature information. (Note 2) The extraction unit is a temperature calculation device as described in Appendix 1, which extracts a specific section from the uppermost row of sections in the thermal image. (Note 3) The extraction unit extracts at least four specific sections from the thermal image, The temperature calculation unit calculates the temperature of the measurement target range based on the section temperature information, using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature. This is the temperature calculation device according to Appendix 1 or 2. (Note 4) The temperature calculation unit calculates the temperature of the measurement target range using the temperatures in at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature, from among at least four of the specified sections. (Note 5) The temperature calculation device according to any one of the appendices 1 to 4, wherein the temperature calculation unit calculates the average value of the temperatures in at least two or more specific sections, and sets the average value as the temperature of the measurement target range. (Note 6) The temperature calculation device according to any one of the appendices 1 to 5, wherein the extraction unit extracts at least one specific area from each area of ​​the thermal image according to at least one of the following pre-set conditions (1) to (5). (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the area below the area corresponding to the position of the face of the person being measured included in the thermal image. (4) From the area corresponding to the position of the subject's face included in the thermal image, areas that are separated by a predetermined number of areas or more are extracted as the specific areas. (5) Excluding the area corresponding to the position of the subject's face included in the thermal image. (Note 7) The temperature calculation unit calculates the surface temperature of the subject being measured in the thermal image based on the compartment temperature information, as described in any of the appendices 1 to 6. (Note 8) Furthermore, including the correction unit, The correction unit corrects the calculated surface temperature of the subject of measurement using the calculated temperature of the measurement target range, as described in Appendix 7 of the temperature calculation device. (Note 9) Furthermore, it includes a recording unit, a detection unit, and an authentication unit, The recording unit records registrant information, including facial information relating to the registrant's face. The image acquisition unit further acquires a real-world image corresponding to the thermal image, The detection unit detects the face of the person to be measured from the actual image, The temperature calculation device according to any one of the appendices 1 to 8, wherein the authentication unit compares the face of the person being measured with the face of the registered person, and if they match, authenticates the person being measured as the registered person. (Note 10) This includes an image acquisition process, an extraction process, and a temperature calculation process. The image acquisition step involves acquiring a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction step involves extracting at least one specific area from each area of ​​the thermal image, The temperature calculation step is a temperature calculation method that calculates the temperature of the measurement target range using the temperatures of at least one of the specific sections based on the section temperature information. (Note 11) The extraction step is the temperature calculation method described in Appendix 10, which extracts the specific section from the uppermost row of the thermal image sections. (Note 12) The extraction step involves extracting at least four specific sections from the thermal image. The temperature calculation step is the temperature calculation method according to Appendix 10 or 11, which calculates the temperature of the measurement target range using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature, based on the section temperature information. (Note 13) The temperature calculation step is the temperature calculation method according to Appendix 12, which calculates the temperature of the measurement target range using the temperatures in at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature. (Note 14) The temperature calculation step is the method according to any one of the appendices 10 to 13, wherein the temperature calculation step calculates the average value of the temperatures in at least two or more specific sections, and the average value is set to be the temperature of the measurement target range. (Note 15) The temperature calculation method according to any one of the appendices 10 to 14, wherein the extraction step involves extracting at least one specific area from each area of ​​the thermal image in accordance with at least one of the following pre-set conditions (1) to (5). (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the area below the area corresponding to the position of the face of the person being measured included in the thermal image. (4) From the area corresponding to the position of the subject's face included in the thermal image, areas that are separated by a predetermined number of areas or more are extracted as the specific areas. (5) Excluding the area corresponding to the position of the subject's face included in the thermal image. (Note 16) The temperature calculation step is a temperature calculation method according to any one of appendices 10 to 15, which calculates the surface temperature of the subject to be measured included in the thermal image based on the compartment temperature information. (Note 17) Furthermore, including the correction process, The correction step is the temperature calculation method described in Appendix 16, which corrects the calculated surface temperature of the person being measured using the calculated temperature of the measurement target range. (Note 18) Furthermore, it includes a recording process, a detection process, and an authentication process, The aforementioned recording step records registrant information, including facial information relating to the registrant's face. The image acquisition step further acquires a real-world image corresponding to the thermal image, The aforementioned detection step involves detecting the face of the person to be measured from the actual image, The temperature calculation method according to any one of appendices 10 to 17, wherein the authentication step involves comparing the face of the person being measured with the face of the registered person, and if they match, certifying the person being measured as the registered person. (Note 19) A program that causes a computer to perform procedures including image acquisition, extraction, and temperature calculation: The aforementioned image acquisition procedure acquires a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction procedure involves extracting at least one specific area from each area of ​​the thermal image, The temperature calculation procedure calculates the temperature of the measurement target range using the temperatures of at least one of the specific sections based on the section temperature information. (Note 20) The extraction procedure is the program described in Appendix 19, which extracts the specific section from the uppermost column of the thermal image sections. (Note 21) The extraction procedure involves extracting at least four specific sections from the thermal image, The temperature calculation procedure is a program according to Appendix 19 or 20, which calculates the temperature of the measurement target range using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature, based on the section temperature information. (Note 22) The temperature calculation procedure is the program described in Appendix 21, which calculates the temperature of the measurement target range using the temperatures in at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature. (Note 23) The program described in any of Appendix 19 to 22 comprises a temperature calculation procedure which calculates the average value of the temperatures of at least two specific sections and sets the average value as the temperature of the measurement range. (Note 24) The extraction procedure is a program according to any one of the appendices 19 to 23, which extracts at least one specific area from each area of ​​the thermal image in accordance with at least one of the pre-set conditions (1) to (5) below. (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the area below the area corresponding to the position of the face of the person being measured included in the thermal image. (4) From the area corresponding to the position of the subject's face included in the thermal image, areas that are separated by a predetermined number of areas or more are extracted as the specific areas. (5) Excluding the area corresponding to the position of the subject's face included in the thermal image. (Note 25) The temperature calculation procedure is a program described in any of Appendix 19 to 24, which calculates the surface temperature of the subject being measured included in the thermal image based on the compartment temperature information. (Note 26) Furthermore, including correction procedures, The correction procedure is the program described in Appendix 25, which corrects the calculated surface temperature of the subject of measurement using the calculated temperature of the measurement range. (Note 27) Furthermore, it includes recording procedures, detection procedures, and authentication procedures, The aforementioned recording procedure records registrant information, including facial information relating to the registrant's face. The aforementioned image acquisition procedure further acquires a real-world image corresponding to the thermal image, The aforementioned detection procedure involves detecting the face of the person to be measured from the actual image, The authentication procedure is a program according to any one of the appendices 19 to 26, which compares the face of the detected person being measured with the face of the registered person, and if they match, authenticates the person being measured as the registered person. (Note 28) A computer-readable recording medium containing a program described in any of the appendices 19 to 27. [Industrial applicability]

[0068] According to the present invention, by extracting the specific area, the temperature around the subject (measurement target range) can be calculated from the thermal image. For this reason, the present invention is useful, for example, in fields where the surface temperature of a subject is measured non-contact. [Explanation of Symbols]

[0069] 10 Temperature calculation device 11 Image acquisition unit 12 Detection unit 13 Extraction part 14 Temperature calculation section 15 Records Section 16. Authentication Department 17 Correction Unit 101 Central Processing Unit 102 memory 103 Bus 104 Storage device 105 Input device 106 Display device 107 Communication devices

Claims

1. It includes an image acquisition unit, an extraction unit, a temperature calculation unit, a recording unit, a detection unit, and an authentication unit. The image acquisition unit acquires a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction unit is From each section of the thermal image, at least one specific section is extracted. From the thermal image, sections that are separated by a predetermined number of sections or more from the section corresponding to the position of the subject's face are extracted as the specific section. The aforementioned specific area is an area other than the area corresponding to the position of the subject's face included in the thermal image, The temperature calculation unit calculates the temperature of at least one of the indoor and outdoor areas within the measurement target range, using the temperatures of at least one of the specific sections based on the section temperature information. The recording unit records registrant information, including facial information relating to the registrant's face. The image acquisition unit further acquires a real-world image corresponding to the thermal image, The detection unit detects the face of the person to be measured from the actual image, The authentication unit compares the face of the person being measured with the face of the registered person, and if they match, authenticates the person being measured as the registered person.

2. The temperature calculation device according to claim 1, wherein the extraction unit extracts the specific section from the uppermost row of sections in the thermal image.

3. The extraction unit extracts at least four specific sections from the thermal image, The temperature calculation device according to claim 1 or 2, wherein the temperature calculation unit calculates the temperature of the measurement target range based on the section temperature information, using the temperatures in at least two of the four or more specific sections, excluding the section with the maximum temperature and the section with the minimum temperature.

4. The temperature calculation unit calculates the temperature of the measurement target range using the temperatures in at least two of the specified sections, excluding the sections that fall into a predetermined number of categories in descending order of temperature and the sections that fall into a predetermined number of categories in descending order of temperature, from among at least four of the specified sections.

5. The temperature calculation device according to any one of claims 1 to 4, wherein the extraction unit extracts at least one specific section from each section of the thermal image according to at least one of the following pre-set conditions (1) to (3). (1) Excluding areas where the temperature is outside the range of the preset temperature. (2) The specific section includes at least one of the sections at the four corners of the thermal image. (3) Excluding the section below the section corresponding to the position of the subject's face included in the thermal image.

6. The temperature calculation device according to any one of claims 1 to 5, wherein the temperature calculation unit calculates the surface temperature of the subject to be measured included in the thermal image based on the compartment temperature information.

7. Furthermore, including the correction unit, The temperature calculation device according to claim 6, wherein the correction unit corrects the calculated surface temperature of the person being measured using the calculated temperature of the measurement target range.

8. This includes an image acquisition process, an extraction process, a temperature calculation process, a recording process, a detection process, and an authentication process. The image acquisition step involves acquiring a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction step described above is: From each section of the thermal image, at least one specific section is extracted. From the thermal image, sections that are separated by a predetermined number of sections or more from the section corresponding to the position of the subject's face are extracted as the specific section. The aforementioned specific area is an area other than the area corresponding to the position of the subject's face included in the thermal image, The temperature calculation step calculates the temperature of at least one of the indoor and outdoor areas within the measurement target range using the temperatures of at least one of the specific sections based on the section temperature information. The aforementioned recording step records registrant information, including facial information relating to the registrant's face. The image acquisition step further acquires a real-world image corresponding to the thermal image, The aforementioned detection step involves detecting the face of the person to be measured from the actual image, The authentication step is a temperature calculation method that compares the face of the person being measured with the face of the registered person, and if they match, authenticates the person being measured as the registered person.

9. A program that causes a computer to perform procedures including image acquisition, extraction, temperature calculation, recording, detection, and authentication: The aforementioned image acquisition procedure acquires a thermal image of the measurement target area, The thermal image is divided into multiple sections, and is linked to section temperature information indicating the temperature of each section. The extraction procedure described above is: From each section of the thermal image, at least one specific section is extracted. From the thermal image, sections that are separated by a predetermined number of sections or more from the section corresponding to the position of the subject's face are extracted as the specific section. The aforementioned specific area is an area other than the area corresponding to the position of the subject's face included in the thermal image, The temperature calculation procedure calculates the temperature of at least one of the indoor and outdoor areas within the measurement target range using the temperature of at least one of the specific sections based on the section temperature information. The aforementioned recording procedure records registrant information, including facial information relating to the registrant's face. The aforementioned image acquisition procedure further acquires a real-world image corresponding to the thermal image, The aforementioned detection procedure involves detecting the face of the person to be measured from the actual image, The authentication procedure compares the face of the person being measured with the face of the registered person, and if they match, authenticates the person being measured as the registered person.

Images