KR20220036418A - Apparatus, method and computer program for correcting temperature of object - Google Patents

Abstract

A device for correcting a temperature of an object comprises: an image receiving unit for receiving a real image photographed from a real image camera and for receiving a thermal image photographed from a thermal image camera; an object recognition unit for recognizing an object from the received real image; a temperature extraction unit for extracting a temperature of the object based on a temperature value included in the received thermal image; a distance derivation unit for deriving a distance between the recognized object and the real image camera; and a temperature correction unit for correcting the extracted temperature of the object based on the derived distance and a temperature correction constant. The temperature correction constant is derived based on a temperature of the inside in which the object is located.

Description

Apparatus, method and computer program for compensating the temperature of an object

The present invention relates to an apparatus, method and computer program for correcting the temperature of an object.

In recent years, pandemics of coronaviruses such as SARS, MERS, and COVID-19 are often occurring. The typical symptoms of the coronavirus are fever and cough, and in order to prevent the spread of the corona virus, it is necessary to detect an infected person who has developed symptoms, isolate and treat them, so that they do not spread it to others.

As a method of detecting a person infected with the corona virus, there is a method of measuring the body temperature of a subject using a thermal imaging camera, and determining whether a fever occurs depending on whether the measured body temperature is 36.5 ° C or higher, a reference temperature.

Regarding the technology of measuring a subject's body temperature using such a thermal imaging camera, Korean Patent Registration No. 10-1112125, which is a prior art, discloses an apparatus and method for measuring the body temperature of a visitor.

However, when measuring a subject's body temperature using a thermal imaging camera, the emissivity is different depending on the skin surface condition of the subject, and even at the same body temperature, the emissivity increases according to the subject's constitution, which causes an error in body temperature measurement. there is.

In addition, when body temperature is measured indoors, the body temperature is measured differently depending on the room temperature, and the body temperature changes according to the indoor environment, so it is difficult to accurately measure the body temperature.

Receiving a real image taken from a real image camera, recognizing an object from a real image, receiving a thermal image taken from a thermal imaging camera, and extracting the temperature of an object based on a temperature value included in the thermal image An object temperature compensation apparatus, method, and computer program are provided.

An object, a method, and a computer program are provided for deriving a distance between an object and a real image camera, and correcting the temperature of the object using a temperature correction constant derived based on the derived distance and the room temperature where the object is located.

However, the technical problems to be achieved by the present embodiment are not limited to the technical problems described above, and other technical problems may exist.

As a means for achieving the above-described technical problem, an embodiment of the present invention provides an image receiving unit for receiving a real image photographed from a real image camera, and receiving a thermal image photographed from a thermal image camera, the received An object recognition unit for recognizing an object from a real image image, a temperature extraction unit for extracting a temperature of the object based on a temperature value included in the received thermal image, and a distance between the recognized object and the real image camera a temperature correction unit for correcting the temperature of the extracted object based on a distance derivation unit and the derived distance and temperature correction constant, wherein the temperature correction constant is derived based on the room temperature at which the object is located A correction device may be provided.

Another embodiment of the present invention includes the steps of receiving a real image photographed from a real image camera, receiving a thermal image photographed from a thermal imaging camera, recognizing an object from the received real image image, the extracting the temperature of the object based on a temperature value included in the received thermal image, deriving a distance between the recognized object and the real image camera, and based on the derived distance and temperature correction constant Comprising the step of correcting the temperature of the extracted object, the temperature correction constant may provide a temperature correction method that is derived based on the room temperature in which the object is located.

Another embodiment of the present invention, when a computer program is executed by a computing device, receives a real image image taken from a real image camera, receives a thermal image image taken from the thermal image camera, and the received real image Recognizes an object from an image, extracts a temperature of the object based on a temperature value included in the received thermal image, derives a distance between the recognized object and the real image camera, and the derived distance and temperature It is possible to provide a computer program stored in a medium including a sequence of instructions to correct the temperature of the extracted object based on the correction constant, and to derive the temperature correction constant based on the room temperature in which the object is located.

The above-described problem solving means are merely exemplary, and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the above-described problem solving means of the present invention, a human face is recognized from a real image image using a real image camera and a thermal image camera, and the temperature of the human face region recognized from the thermal image is measured, It is possible to provide an apparatus, method and computer program for correcting the temperature of a face region to provide an accurate temperature.

Conventionally, a high cost was incurred by correcting the temperature measured using a thermal imaging camera using a black body. Thus, it is possible to provide an apparatus, method and computer program that provides generalization of temperature correction.

An apparatus, method, and computer program for notifying that an infected person is detected may be provided by classifying a subject exceeding the reference temperature as an infected person based on the corrected temperature.

1 is a block diagram of a temperature compensating device according to an embodiment of the present invention.
2A and 2B are exemplary views showing a real image and a thermal image according to an embodiment of the present invention.
3 is an exemplary diagram for explaining a process of correcting the temperature of an object based on a distance between the object and a real image camera according to an embodiment of the present invention.
4 is an exemplary view for explaining a process of correcting the temperature of an object based on the device temperature and the ambient temperature of the thermal imaging camera according to an embodiment of the present invention.
5 is an exemplary view for explaining a process of displaying the temperature of the corrected object according to an embodiment of the present invention.
6 is a flowchart of a method of correcting the temperature of an object in the temperature compensating apparatus according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware.

Some of the operations or functions described as being performed by the terminal or device in this specification may be instead performed by a server connected to the terminal or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the server.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a temperature compensating device according to an embodiment of the present invention. Referring to FIG. 1 , the temperature compensating device 100 includes an image receiving unit 110 , an object recognition unit 120 , a temperature extracting unit 130 , a distance derivation unit 140 , a temperature compensating unit 150 , and a display unit 160 . ), a determining unit 170 and a learning unit 180 may be included.

The image receiving unit 110 may receive a real image captured by the real image camera and receive a thermal image captured by the thermal imager. Here, the real image and the thermal image will be described in detail with reference to FIGS. 2A and 2B .

2A and 2B are exemplary views showing a real image and a thermal image according to an embodiment of the present invention.

Referring to FIG. 2A , the image receiving unit 110 may receive a real image obtained by photographing at least one object from a real image camera installed at a specific location in the room.

Referring to FIG. 2B , the image receiving unit 110 may receive a thermal image obtained by photographing at least one object from a thermal imaging camera installed at the same location as the real image camera indoors.

A thermal imaging camera is a device that takes a temperature distribution diagram of a target object through a non-contact method, and can take a thermal image by using the principle that infrared radiation emitted according to the surface temperature of the target object changes. The intensity of infrared rays is proportional to the temperature of the target object and has a characteristic that it is related to the emissivity. Emissivity refers to the ratio at which a target object absorbs/transmits/reflects external infrared energy, and has a characteristic that the amount of energy absorbed and reflected varies depending on the surface state (eg, gloss, roughness, etc.) of the target object.

Such a thermal image may be expressed in red as the heat of the object is high, and may be expressed in blue as the heat of the object is low.

Returning to FIG. 1 again, the object recognition unit 120 may recognize the object from the received real image. For example, the object recognizer 120 may recognize the face region of the object from the real image.

The temperature extractor 130 may extract the temperature of the object based on a temperature value included in the received thermal image. For example, the temperature extractor 130 may extract the maximum temperature value of the face of the object by matching the temperature value included in the thermal image with the position of the face region of the object.

The distance derivation unit 140 may derive a distance between the recognized object and the real image camera. For example, the distance derivation unit 140 may derive the distance between the object and the real image camera based on the face size and the inter-ocular distance of the object among the recognized face regions.

The temperature correction unit 150 may correct the temperature of the extracted object based on the derived distance and the temperature correction constant. Here, the temperature correction constant may be derived based on the room temperature at which the object is located. For example, the temperature correction unit 150 may correct the maximum temperature value of the face of the object in consideration of at least one of a derived distance, a gradient value of a temperature that changes according to the distance, a temperature value, and a temperature correction constant. . The process of correcting the temperature of the object based on the distance and the temperature correction constant will be described in detail with reference to FIG. 3 .

3 is an exemplary diagram for explaining a process of correcting the temperature of an object based on a distance between the object and a real image camera according to an embodiment of the present invention. Referring to FIG. 3 , the real image camera 300 is installed at a specific location in the room, and the measured temperature of the object measured from the real image camera 300 at a reference position (eg, 1 m) is the most accurate temperature value. It is assumed to be guaranteed.

As a preliminary work for this, the temperature difference between the reference position (1m) and the previous position (50cm) is derived by measuring the temperature for the previous position (eg, 50cm) of the reference position (1m) from the visual camera 300 In addition, the operation of deriving the temperature difference between the reference position (1m) and the subsequent position (1m50cm) by measuring the temperature for the position (for example, 1m50cm) after the reference position (1m) from the real image camera 300 is preceded should be

Here, the temperature of the object measured by the real image camera 300 may vary according to whether the object is located in a vertical position or a horizontal position.

Hereinafter, a temperature of an object that varies according to a vertical position in which the object is located among indoor positions will be described. For example, if the object is located at position 2 among indoor locations, the temperature of the object is measured as 36.2 °C, and if it is located at position 5 with a vertical difference of 50 cm from position 2, the temperature of the object is 35.3 °C In the case of position 8, which is measured as , and has a vertical difference of 50 cm from position 5, the temperature of the object can be measured as 34.8°C. In this case, the measured temperature of the object may be affected by a change in the indoor temperature that varies according to a change in the indoor environment such as the door open 320 or the door close 321 in the room.

In this case, the temperature difference of the object between the 2nd position and the 5th position is -0.9°C, and the temperature difference of the object between the 5th and 8th position is -0.5°C, so that the 8th position from the 2nd position is generated. It can be confirmed that the temperature difference of the object occurs up to -1.4°C. That is, when the temperature of an object is extracted using a thermal imaging camera installed at the same location as the real image camera, it can be confirmed that the temperature value of the object decreases linearly according to the distance where the object is located.

Hereinafter, the temperature of an object that varies according to a horizontal position in which the object is located among indoor positions will be described. For example, in the case of the object's temperature at the 7th and 8th positions, a temperature difference of 0.4°C occurs, but in the case of the 8th and 9th positions, it can be confirmed that a temperature difference of -0.4°C occurs. . In this case, the measured temperature of the object may be affected by a change in the indoor temperature that varies according to a change in the indoor environment, such as the door opening 820 or the door closing 821 in the room.

For example, it is assumed that a difference of 0.7°C occurs in temperature when measuring 50 cm from the reference position 301 by 50 cm.

The distance derivation unit 140 may derive the distance between the object and the real image camera by using the size of the face region of the object and the inter-ocular distance recognized by the real image camera 300 . Here, in the case of the reference position (eg, 1 m), the size of the face area of the object may be 200px.

The temperature compensator 150 may correct the temperature of the measured object based on a temperature difference generated according to a distance between the real image camera 300 and the object. The temperature correction unit 150 may correct the temperature of the object using Equation 1 below.

Referring to Equation 1, a represents a decreasing slope value of the temperature that is changed according to the distance, x represents a derived distance between the object and the real image camera (eg, -0.7 degrees/0.5 m), and b is It may represent the maximum temperature value of the object measured by the thermal imaging camera, and c may represent a constant according to the room temperature.

Returning to FIG. 1 again, the temperature correction unit 150 may derive a temperature correction constant based on at least one of an indoor temperature in which the object is located, a device temperature of the thermal imaging camera, and an ambient temperature. The process of deriving the temperature correction constant will be described in detail with reference to FIG. 4 .

4 is an exemplary view for explaining a process of correcting the temperature of an object based on the device temperature and the ambient temperature of the thermal imaging camera according to an embodiment of the present invention.

In general, the temperature measured for about 30 minutes after the device is first booted by a thermal imaging camera is not accurate. This becomes the reference state set by the manufacturer using a blackbody only when the thermal image sensor built into the thermal imager is preheated to a certain temperature, and from this point on, accurate temperature measurement becomes possible. Here, a black body refers to an object that only absorbs external energy and does not reflect it.

Referring to FIG. 4 , the temperature correction unit 150 may derive a temperature correction constant through a difference 411 between the temperature 400 extracted through the thermal imaging camera and the indoor temperature 410 . For example, if the temperature 400 extracted through the thermal imaging camera at 9:30 is '25.7 °C' and the indoor temperature 410 is '15.6 °C', a temperature difference of '10.1 °C' will occur. can Thereafter, when the temperature 400 extracted through the thermal imaging camera at 3:54 pm is '29.8 °C' and the indoor temperature 410 is '20.0 °C', a temperature difference of '9.8 °C' may occur. there is.

As such, the temperature correction unit 150 sets the temperature correction constant to ' since the temperature difference between the temperature 400 and the indoor temperature 410 measured using the thermal imaging camera is constant at about '10 °C' even with the passage of time. 10' can be derived. This may be using a characteristic in which the measured value of the thermal imaging sensor increases as the temperature of the thermal imaging camera increases to the same temperature as in the room. Here, in order to derive the temperature correction constant, it is necessary to attach an indoor temperature sensor to the thermal imaging camera or to measure the temperature of the thermal imaging sensor itself.

Returning to FIG. 1 again, the display unit 160 may display the highest temperature value of the corrected object on the face of the object recognized from the real image image. The process of displaying the temperature of the corrected object will be described in detail with reference to FIG. 5 .

5 is an exemplary view for explaining a process of displaying the temperature of the corrected object according to an embodiment of the present invention. Referring to FIG. 5 , when the object recognition unit 120 recognizes an object from a real image, the name of the recognized object (eg, Chul-soo Kim) may be displayed. If the real image camera is installed in a specific place such as a workplace, the name of the object and the department and company number to which the object belongs may be displayed together.

The display unit 160 displays '36.2°C', which is the highest temperature value 520 of the object that is corrected in relation to the distance from the object on the face region 510 of the object recognized from the real image 500 with respect to the recognized object. can be displayed. In addition, the display unit 160 may display recognition information on the temperature-measured object in the upper right corner of the screen. Through this, the present invention can collect and manage information on objects entering and leaving a specific place through a real image camera and a thermal image camera installed in a specific place.

If the reference body temperature temperature value is set to '36.5 °C', since '36.2 °C', which is the highest temperature value 520 of the object, is lower than the reference body temperature value, the display unit 160 displays an indoor access permission notification of the object. can do. In this case, when the object is permitted to enter the room, the controller (not shown) may open the entrance gate so that the object can enter the room.

On the other hand, when the corrected maximum temperature value 520 of the object is '36.9 °C', the display unit 160 displays the object because the object's maximum temperature value 520, '36.9 °C', is higher than the reference body temperature value. It is possible to display a notification of an abnormal person by determining it as an abnormal person, and a notification that an object cannot enter the room can be displayed. In this case, when the object is not allowed to enter the room, the controller (not shown) may close the entrance gate so that the object cannot enter the room.

Returning to FIG. 1 again, the object recognition unit 120 may recognize a plurality of objects and a face region of each of the plurality of objects from the real image image.

The temperature extractor 130 may extract a maximum temperature value from each face region of each of the plurality of objects.

The distance derivation unit 140 may derive a distance between the face region of each of the plurality of recognized objects and the real image camera.

The temperature compensator 150 may correct the temperature of each of the plurality of objects extracted based on the distance between the face region of each of the plurality of objects and the real image camera. When a plurality of objects enter the room at the same time, when extracting the temperature of a plurality of objects included in the real image, the temperature difference between the real image camera and the plurality of objects, the indoor temperature, the left-right deviation, and the temperature difference according to the constitution of each object As a result, various temperatures are measured for each object, and thus the temperature for each object extracted from the thermal imaging camera becomes inaccurate. Accordingly, the temperature corrector 150 may correct each maximum temperature value extracted from the face region of each of the plurality of objects extracted by the temperature extractor 130 based on the vertical distance between the plurality of objects and the indoor temperature. .

For example, the temperature correction unit 150 calculates an average temperature value for a plurality of objects from each extracted maximum temperature value, and corrects the maximum temperature value for a reference object among the plurality of objects using the calculated average temperature value. can Here, the reference object may be an object located at a reference position (eg, the center of 1 m) from the real image camera.

Thereafter, the temperature correction unit 150 may correct the highest temperature value of another object located at a vertical distance from the reference object.

The determination unit 170 may determine at least one of the plurality of objects as abnormal based on the calculated average temperature value and the reference body temperature value (eg, 37.5° C.). For example, when the temperature of the corrected first object among the plurality of objects is '38.1°C', the determination unit 170 determines the first object as abnormal and displays a notification related to the occurrence of high temperature for the first object can do.

The learning unit 180 may learn temperature correction based on the extracted temperature of the object, the corrected temperature of the object, and the recognized face of the object. For example, the temperature extraction unit 130 stores the temperature extracted for each object in the database, and the temperature of the stored object, the temperature of the corrected object, and the face of the object are learned to correct the temperature using artificial intelligence, thereby temperature correction. It is possible to provide the effect of improving the performance of the engine and increasing the accuracy of temperature correction.

The temperature correction apparatus 100 may be executed by a computer program stored in a medium including a sequence of instructions for correcting the temperature of an object. When the computer program is executed by the computing device, it receives a real image image taken from the real image camera, receives a thermal image image taken from the thermal image camera, recognizes an object from the received real image image, and receives heat The temperature of the object is extracted based on the temperature value included in the image, the distance between the recognized object and the real image camera is derived, the temperature of the extracted object is corrected based on the derived distance and the temperature correction constant, and the temperature The calibration constant may include a sequence of instructions that is to be derived based on the room temperature in which the object is located.

6 is a flowchart of a method of correcting the temperature of an object in the temperature compensating apparatus according to an embodiment of the present invention. The method of correcting the temperature of an object in the temperature compensating apparatus 100 illustrated in FIG. 6 includes time-series processing according to the embodiments illustrated in FIGS. 1 to 5 . Therefore, even if omitted below, it is also applied to the method of correcting the temperature of an object in the temperature compensating apparatus 100 according to the embodiment shown in FIGS. 1 to 5 .

In operation S610, the temperature compensating apparatus 100 may receive a real image captured by the real image camera.

In step S620 , the temperature compensating apparatus 100 may receive a thermal image captured by the thermal imaging camera.

In step S630, the temperature compensation apparatus 100 may recognize an object from the received real image.

In operation S640, the temperature compensation apparatus 100 may extract the temperature of the object based on the temperature value included in the received thermal image.

In operation S650, the temperature compensating apparatus 100 may derive a distance between the recognized object and the real image camera.

In operation S660, the temperature compensating apparatus 100 may correct the temperature of the extracted object based on the derived distance and temperature correction constant. Here, the temperature correction constant may be derived based on the room temperature at which the object is located.

In the above description, steps S610 to S660 may be further divided into additional steps or combined into fewer steps according to an embodiment of the present invention. In addition, some steps may be omitted as needed, and the order between the steps may be switched.

The method of correcting the temperature of an object in the temperature compensating device described through FIGS. 1 to 6 may be implemented in the form of a computer program stored in a medium executed by a computer or a recording medium including instructions executable by the computer. there is. Also, the method of correcting the temperature of an object in the temperature compensating apparatus described with reference to FIGS. 1 to 6 may be implemented in the form of a computer program stored in a medium executed by a computer.

Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalents should be interpreted as being included in the scope of the present invention. do.

100: temperature compensation device
110: video receiver
120: object recognition unit
130: temperature extraction unit
140: distance elicitation unit
150: temperature compensation unit
160: display unit
170: determination unit
180: study department

Claims (20)

In the device for correcting the temperature of an object,
an image receiving unit for receiving the real image captured by the real image camera and receiving the thermal image photographed from the thermal imager;
an object recognition unit for recognizing an object from the received real image;
a temperature extractor configured to extract a temperature of the object based on a temperature value included in the received thermal image;
a distance derivation unit for deriving a distance between the recognized object and the real image camera; and
And a temperature correction unit for correcting the temperature of the extracted object based on the derived distance and temperature correction constant,
The temperature correction constant will be derived based on the room temperature in which the object is located, the temperature correction device.
The method of claim 1,
The object recognition unit recognizes the face region of the object from the real image,
wherein the distance derivation unit derives a distance between the object and the real image camera based on a face size and an inter-ocular distance of the object among the recognized face regions.
3. The method of claim 2,
wherein the temperature extractor extracts the highest temperature value for the face of the object by matching the temperature value included in the thermal image with the position of the face of the object.
4. The method of claim 3,
The temperature compensator corrects the highest temperature value for the face of the object in consideration of at least one of the derived distance, the gradient value of the temperature changed according to the distance, the temperature value, and the temperature correction constant, temperature correction device.
The method of claim 1,
Wherein the temperature compensator derives the temperature correction constant based on at least one of an indoor temperature in which the object is located, a device temperature of the thermal imaging camera, and an ambient temperature.
The method of claim 1,
The object recognition unit recognizes a plurality of objects and a face region of each of the plurality of objects from the real image image,
wherein the distance derivation unit derives a distance between the face region of each of the recognized plurality of objects and the real image camera.
7. The method of claim 6,
The temperature extraction unit extracts the maximum temperature value from the face region of each of the plurality of objects,
The temperature correction unit calculates an average temperature value for the plurality of objects from the extracted maximum temperature value,
Correcting a maximum temperature value of a reference object among the plurality of objects by using the calculated average temperature value, and correcting a maximum temperature value of another object located at a vertical distance from the reference object.
8. The method of claim 7,
The temperature compensating device further comprising a determining unit that determines at least one of the plurality of objects as abnormal based on the calculated average temperature value and the reference body temperature value.
3. The method of claim 2,
The temperature correction apparatus of claim 1, further comprising: a learning unit configured to learn temperature correction based on the extracted temperature of the object, the corrected temperature of the object, and the recognized face of the object.
5. The method of claim 4,
The temperature compensating device further comprising a display unit for displaying the highest temperature value of the corrected object on the face of the object recognized from the real image image.
In the method of compensating the temperature of the object in the temperature compensating device,
Receiving a real image image taken from the real image camera;
Receiving a thermal image taken from the thermal imaging camera;
recognizing an object from the received real image;
extracting the temperature of the object based on a temperature value included in the received thermal image;
deriving a distance between the recognized object and the real image camera; and
Comprising the step of correcting the temperature of the extracted object based on the derived distance and temperature correction constant,
Wherein the temperature correction constant is derived based on the room temperature in which the object is located, the temperature correction method.
12. The method of claim 11,
Recognizing the object comprises:
Recognizing the face region of the object from the real image,
The step of deriving the distance is
and deriving a distance between the object and the real image camera based on a face size and an eye-to-eye distance of the object among the recognized face regions.
13. The method of claim 12,
The step of extracting the temperature of the object,
and extracting the highest temperature value for the face of the object by matching the temperature value included in the thermal image with the position of the face of the object.
14. The method of claim 13,
The step of correcting the temperature of the object,
Compensating the maximum temperature value for the face of the object in consideration of at least one of the derived distance, the gradient value of the temperature changed according to the distance, the temperature value, and the temperature correction constant, temperature Calibration method.
12. The method of claim 11,
The step of correcting the temperature of the object,
and deriving the temperature correction constant based on at least one of an indoor temperature in which the object is located, a device temperature of the thermal imaging camera, and an ambient temperature.
12. The method of claim 11,
Recognizing the object comprises:
Recognizing a plurality of objects and face regions of each of the plurality of objects from the real image image,
The step of deriving the distance is
and deriving a distance between a face region of each of the recognized plurality of objects and the real image camera.
17. The method of claim 16,
The step of extracting the temperature of the object,
extracting the highest temperature value from the face region of each of the plurality of objects,
The step of correcting the temperature of the object,
calculating an average temperature value for the plurality of objects from the extracted maximum temperature value;
correcting a maximum temperature value of a reference object among the plurality of objects by using the calculated average temperature value; and
Comprising the step of correcting the highest temperature value of another object located at a vertical distance from the reference object, the temperature correction method.
18. The method of claim 17,
The method further comprising the step of determining at least one of the plurality of objects as abnormal based on the calculated average temperature value and the reference body temperature temperature value.
13. The method of claim 12,
The method further comprising the step of learning temperature correction based on the extracted temperature of the object, the corrected temperature of the object, and the recognized face of the object.
A computer program stored in a medium comprising a sequence of instructions for correcting the temperature of an object, the computer program comprising:
When the computer program is executed by a computing device,
Receive the real image image taken from the real image camera, receive the thermal image image taken from the thermal image camera,
Recognizing an object from the received real image,
extracting the temperature of the object based on the temperature value included in the received thermal image,
deriving a distance between the recognized object and the real image camera,
Correcting the temperature of the extracted object based on the derived distance and temperature correction constant,
The computer program stored in the medium comprising a sequence of instructions such that the temperature correction constant is derived based on the room temperature in which the object is located.

Images