KR102487590B1 - Method for measuring of object based on face-recognition - Google Patents

Abstract

According to an embodiment of the present invention, a method comprising: receiving a real image taken by a real camera and a thermal image taken by a thermal camera, and detecting a face in each image; detecting a face from the real image and the thermal image, respectively; and measuring a distance to the object to be photographed based on the face detected in the real image and the face detected in the thermal image.

Description

Method for measuring the temperature of an object to be photographed based on face recognition {Method for measuring of object based on face-recognition}

The present invention relates to a thermal camera system capable of recognizing a face and a method for measuring the temperature of an object to be photographed.

Recently, respiratory infectious diseases such as SARS (Severe Acute Respiratory Syndrome), H1N1 influenza, MERS, and coronavirus have frequently occurred. It is widely used.

The current body temperature measurement method using a thermal camera is to install a thermal camera on the passageway to measure the body temperature of a passerby passing through the passageway to identify a person with high fever. In addition, a real image and/or a thermal image may be simultaneously displayed on a screen by simultaneously capturing a passenger with a real camera and a thermal camera.

In the case of such a thermal camera system for measuring body temperature, it is important to accurately measure body temperature. However, conventional thermal imaging cameras have a problem in that they output different temperatures depending on the distance to a photographing target due to various causes such as ambient temperature, wind, and humidity, even if the measurement target has the same temperature. For example, if you shoot an object at 50 degrees Celsius, and the distance is 1 meter, 2 meters, and 3 meters respectively, the temperature of the object will be recognized differently as 50 degrees, 49 degrees, 48 degrees, etc. In the case of , since the distance of the object to be photographed changes every moment, it is difficult to accurately measure the body temperature of the object to be measured.

In order to solve this problem, it is possible to measure the distance to the shooting target by additionally installing a distance measuring device of various measuring methods such as laser, lidar, radar, or ultrasonic, and correct the temperature by reflecting the distance. As such, it is not possible to detect multiple people at once and measure the distance to each person, and it is inconvenient to mount a separate distance measurement device to the thermal camera system.

Patent Document 1: Korean Patent Publication No. 10-2019-0063671 (published on June 10, 2019)

The present invention is to solve the above problems, by using a real camera and a thermal camera provided in an existing thermal camera system, the distance to an object to be photographed is calculated, and the temperature is compensated according to the calculated distance to determine the temperature of the object to be photographed. An object of the present invention is to provide a thermal camera system capable of accurately measuring the temperature and a method for measuring the temperature of an object to be photographed based on face recognition.

According to an embodiment of the present invention, an image processing apparatus for processing images captured by a real camera and a thermal camera, respectively, receives a real image captured by a real camera and a thermal image taken by a thermal camera of a subject to be photographed, and respectively a face recognition unit for detecting a face in an image; and a distance measuring unit for measuring a distance to the object to be photographed based on the position of the face detected in the real image and the thermal image, respectively.

According to another embodiment of the present invention, in a method for measuring the temperature of an object to be photographed in a thermal camera system having an image processing device for processing images captured by a real camera and a thermal camera, the method comprising:

receiving a real image captured by a real camera and a thermal image captured by a thermal camera and detecting a face in each image; detecting a face from the real image and the thermal image, respectively; and measuring a distance to the object to be captured based on the face detected in the real image and the face detected in the thermal image.

According to an embodiment of the present invention, the temperature of the object to be photographed can be accurately measured by calculating the distance to the object to be photographed and applying temperature compensation according to the calculated distance. In addition, according to the present invention, since the distance to the shooting target is measured using the real camera and the thermal camera already provided in the existing thermal camera system, there is no need to additionally install a separate distance measuring device, and the installation and operation of the system are easy. It has the advantage of ease and cost reduction.

In addition, according to an embodiment of the present invention, since a temperature calibrator installed in a photographing area can be automatically recognized and the temperature corrected, a more accurate temperature measurement can be performed on a subject to be photographed.

1 is a diagram for explaining a thermal camera system according to an embodiment of the present invention;
2 is a block diagram of a thermal camera system according to one embodiment;
3 is a diagram explaining a method of calculating a distance to a photographing target by matching a real image and a thermal image according to an embodiment;
4 is a block diagram of an image processing device according to an embodiment;
5 is a flowchart of a method of measuring the temperature of a photographing target based on face recognition according to an embodiment; and
6 is a flow diagram of a method for automatically recognizing and calibrating a temperature of a temperature calibrator according to one embodiment.

The above objects, other objects, features and advantages of the present invention will be easily understood through the following preferred embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided so that the disclosed content will be thorough and complete and the spirit of the present invention will be sufficiently conveyed to those skilled in the art.

In this specification, when terms such as first and second are used to describe components, these components should not be limited by these terms. These terms are only used to distinguish one component from another. Embodiments described and illustrated herein also include complementary embodiments thereof.

In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. The expressions 'comprises', 'consists of', and 'consists of' used in the specification do not exclude the presence or addition of one or more other elements in addition to the mentioned elements.

In this specification, the term 'software' refers to technology that moves hardware in a computer, and the term 'hardware' refers to a type of device or device (CPU, memory, input device, output device, peripheral device, etc.) constituting a computer, , The term 'step' means a series of processes or operations connected in time series to achieve a predetermined goal, the term 'computer program' or 'program' means a set of instructions combined to be processed by a computer, and the term ' A program recording medium' refers to a computer-readable recording medium on which a program used to install, execute, or distribute a program is recorded.

Terms such as '~unit', '~module', '~unit', '~block', and '~board' used to refer to the components of the invention in this specification refer to those that process at least one function or operation. It may refer to a physical, functional, or logical unit, which may be implemented as one or more hardware, software, or firmware, or may be implemented as a combination of one or more hardware, software, and/or firmware.

In this specification, 'processing device', 'computer' or 'computing device' means an operating system such as Windows, Mac, or Linux, a computer processor, memory, application programs, a storage device (eg, HDD, SDD), and It may be a device equipped with a monitor. The computer may be, for example, a desktop computer or a laptop computer, but these are exemplary and the present invention is not limited to a desktop computer or a laptop computer. The mobile terminal may be one of mobile wireless communication devices such as a smart phone, a tablet PC, or a PDA.

The present invention will be described in detail with reference to the following drawings. In describing the specific embodiments below, various specific details have been prepared to more specifically describe the invention and aid understanding. However, readers who have knowledge in this field to the extent that they can understand the present invention can recognize that it can be used without these various specific details. In some cases, it is mentioned in advance that parts that are commonly known in describing the invention and are not greatly related to the invention are not described in order to prevent confusion in describing the present invention.

1 schematically illustrates a thermal camera system according to an embodiment of the present invention. Referring to the drawings, a thermal camera system according to an embodiment includes a camera module 10, an image processing device 20, and a display 30. The thermal imaging camera system of the present invention can be used to measure and display the temperature of any subject (S), and the present invention will be described on the assumption that a person's body temperature is measured as an example. .

In one embodiment, the camera module 10 includes a real camera and a thermal camera. A real image camera is a camera that generates image data by taking an image in the visible ray region of an object to be photographed. A thermal camera detects infrared rays emitted naturally from a subject and converts the amount of infrared rays into heat to create a thermal image (sometimes referred to as a 'thermal image', 'thermal image', or 'infrared image' in the industry). generate Although both the real camera and the thermal camera are illustrated in the drawing as being provided in the camera module 10, it goes without saying that the real camera and the thermal camera may be independently installed.

The image processing device 20 processes image data captured by the camera module 10 . For example, the image processing device 20 pre-processes the real image and/or thermal image received from the camera module 10 (eg, removing noise, filtering, synchronizing, matching, etc.), and performs one or more shooting subjects in the real or thermal image. It is possible to perform image processing such as detecting the face of (S), calculating the temperature of the subject (S) to be photographed, and overlapping this temperature information with a real or thermal image, and thus processed real image data, thermal image data, and / or composite data of the real image and the thermal image may be output to the display 30 . Also, in one embodiment, the image processing device 20 may calculate the distance from the camera module 10 to the subject S to be photographed and correct the temperature of the subject S to be photographed based on the calculated distance. A detailed operation of the image processing device 20 will be described later with reference to FIG. 2 .

The display 30 is a device for displaying image data processed by the image processing device 20 to a user, and may be implemented as an arbitrary image output device such as, for example, an LCD display and an LED display. In one embodiment, the image processing device 20 may output the real image and the thermal image to the display 30 in various ways. For example, only one of the real image and the thermal image may be output to the display 30, or a composite image in which the real image and the thermal image overlap each other may be output. It is also possible to output the real image and the thermal image in parallel by dividing .

In one embodiment, the thermal camera system of the present invention may further include a temperature calibrator 40 . The temperature calibrator 40 is a device used to calibrate the temperature of a thermal camera, and may include an infrared emitter 41 and a case 42 accommodating the infrared emitter 41 in one embodiment. The infrared emitter 41 is an object that emits infrared rays, and a black body is preferably used. An ideal black body is an object that absorbs all light coming from the outside and does not reflect it, but only emits light of a wavelength corresponding to its own energy. Therefore, the black body can be used for temperature correction of an infrared camera (thermal camera) that measures the exact temperature of an object by taking an infrared image of the object, and in one embodiment, the black body can be made of a carbon material such as carbon black. The infrared emitter 41 is connected to an arbitrary heating/cooling device and is thereby configured to be maintained at a predetermined temperature.

The infrared emitter 41 is accommodated in the case 42 and is configured to be visible from the outside through a through-hole on one surface of the case 42 . In one embodiment of the present invention, the case 42 has a predetermined shape such as a hexahedron and is configured to view the infrared emitter 41 through the front surface of the case. At this time, the remaining area of the front surface of the case 42 surrounding the radiator 41 is painted in a predetermined color (for example, red) or a predetermined pattern is formed.

In one embodiment, the temperature calibrator 40 is disposed so as to be located within the viewing angle of the camera for photographing the subject S, and therefore, the thermal camera of the camera module 10 simultaneously photographs the subject S to be photographed and the temperature calibrator 40 ) can also be taken. Temperature calibration of the thermal camera using the temperature calibrator 40 will be described later with reference to FIG. 6 .

Figure 2 is a block diagram of a thermal camera system according to one embodiment. In FIG. 2 , the camera module 10 , the image processing device 20 , and the display 30 correspond to the camera module 10 , the image processing device 20 , and the display 30 of FIG. 1 , respectively.

The camera module 10 may include a real camera 11 and a thermal camera 12 . The real image camera 11 may generate image data by capturing an image of the subject S in the visible ray region. In one embodiment, the real image camera 11 is implemented in hardware and/or software, such as a lens, a CCD, and an analog-to-digital (A/D) converter. The intensity of the light entering through the lens is converted into an electrical signal by the CCD, and this signal is converted into image data, which is a digital signal, by the A/D converter. Since the configuration and operation of the real image camera 11 are known technologies, a detailed description thereof will be omitted.

The thermal camera 12 may generate temperature data of the object to be photographed by detecting infrared rays naturally radiated from the object S to be photographed and converting the amount of infrared rays into heat. In one embodiment, the thermal imaging camera 12 includes an infrared lens that transmits infrared rays, a detection element array that detects infrared rays incident to the infrared lens and converts them into electrical signals, and an analog-digital converter that converts the electrical signals into digital temperature data. (A/D) converter.

The infrared lens is a lens that transmits infrared rays, and the detection element array detects infrared rays incident to the infrared lens and converts them into electrical signals. The detection element array may have, for example, a Focal Plane Array (FPA) structure in which a plurality of pixels are arranged in a two-dimensional array, but is not limited to such a structure. The A/D converter converts an electrical signal, which is an analog signal, generated by the detection element array into temperature data, which is a digital signal. The thermal camera 12 may additionally perform non-uniformity correction (NUC) and dead pixel processing on the temperature data converted by the A/D converter. Since non-uniformity correction and dead pixel processing are known technologies in the field of thermal cameras, detailed descriptions thereof will be omitted.

The real image and the thermal image generated by the real camera 11 and the thermal camera 12 of the camera module 10 are transferred to the image processing device 20 and processed. In one embodiment, the image processing device 20 includes a face recognition unit 21, a matching point detection unit 22, a resolution adjusting unit 23, a distance measurement unit 24, a temperature measurement unit 25, and a black recognition unit. (26) may be included.

The face recognition unit 21 receives a real image of the subject S photographed by the real camera 11 and a thermal image photographed by the thermal camera 12, respectively, and detects one or more faces in each image. In an embodiment, the face recognition unit 21 may detect a face region of the photographing target S in each of the real image and the thermal image, and calculate detection region information including coordinates of the detected face region.

Known techniques can be used to detect faces in images. For example, the face recognition unit 21 detects a face using pattern recognition based on the shape of the face. With pattern recognition for a set of training images of various face poses, face patterns can be learned and faces can be detected using the learned model. For example, eigenface generated by PCA, linear discrimination Methods such as equation analysis (LDA), artificial neural network (ANN), Adaboost, Haar feature filter, and support vector machine (SVM) may be used. However, the face recognition unit 21 is not limited to this face detection method and may recognize and detect a face in a real image and a thermal image using various known methods and algorithms.

The matching point detection unit 22 detects matching points in each of the real image and the thermal image. In one embodiment of the present invention, the matching point is a feature point or feature region that is a standard when calculating the distance to the shooting target S based on the real image and the thermal image, and the same feature point in each of the real image and the thermal image detect each

In an embodiment, the face recognition unit 21 may select arbitrary feature points, such as pupils, noses, and foreheads, in the facial regions detected in each of the real image and the thermal image, and detect them as matching points. Preferably, in one embodiment, the center point between the two eyes of the face is set as a matching point, and in this case, the matching point can be detected by calculating the center of gravity of the two pupils in each image. The center of gravity can be calculated using a known algorithm for calculating a center of gravity in a general 2D shape area or pixel area. In addition, in a preferred embodiment, for example, when the subject S is wearing glasses or sunglasses, the center of gravity of the entire shape of the glasses or sunglasses (hereinafter simply referred to as 'glasses') is obtained and the center of gravity is used as a matching point. can

In particular, when the photographing subject S wears glasses, pupils can be identified in the real image, but infrared rays do not pass through the glass in the thermal image, so the glasses are displayed as black overall and the pupils cannot be identified. Therefore, the matching point detection unit 22 according to an embodiment of the present invention, when identifying pupils in each of the real image and the thermal image, calculates the center of gravity of the two pupils and sets it as a matching point, and when the pupil is not identified The center of gravity of the entire shape of the spectacles is calculated and each is set as a matching point.

The resolution adjusting unit 23 is a functional unit that adjusts the resolution of at least one of the real image and the thermal image so that the two images have the same resolution. In the case of the generally used camera module 10, since the price of a thermal camera is relatively very high, it is common to use a camera whose resolution of a thermal image is lower than that of a real image. For example, when the real image camera of the camera module 10 has an HD level (eg 1280*720) or FHD level (eg 1920*1080) image quality, the thermal camera 12 has a VGA level (eg 640*480) or 384* resolution. 288 quality camera. However, it is preferable to match the resolutions of the two images so that the matching point calculated from the real image and the matching point calculated from the thermal image point to the same point (pixel). In one embodiment of the present invention, the resolution adjusting unit 23 The resolution of the two images can be identically matched.

In an embodiment, the resolution adjusting unit 23 may lower the resolution of the real image to match the resolution of the thermal image or increase the resolution of the thermal image to match the real image by using a known algorithm for changing the resolution of the image. Alternatively, resolutions of the real image and the thermal image may be adjusted to match the third resolution.

The distance measurement unit 24 calculates the distance from the camera module 10 to the subject S to be photographed based on the matching points detected in the real image and the thermal image, respectively. In one embodiment, the distance measurement unit 24 may measure the distance to the photographing target by matching the real image and the thermal image.

In this regard, FIG. 3 shows an exemplary method of calculating a distance to a photographing target by registering a real image and a thermal image according to an exemplary embodiment.

Referring to FIG. 3 , a real image camera 11 and a thermal image camera 12 of the camera module 10 are installed so as to face the front of each camera at the same viewing angle, respectively, and take an image of an object S. At this time, the two cameras 11 and 12 are installed apart from each other by a predetermined distance D. Therefore, for example, when the photographing subject S is in the position shown in FIG. 3, the angle between the matching point of the photographing subject S and the center of the real image in the real image captured by the real image camera 11 is the first angle ( θ1), while in the thermal image captured by the thermal camera 12, the angle between the matching point of the subject S and the center of the thermal image is measured as the second angle θ2. Therefore, the distance measuring unit 24 calculates the first angle θ1 and the second angle θ2 in each image, and based on the angle and the distance D between the cameras, the camera module 10 to the shooting target ( S) can be calculated.

Referring to FIG. 2 again, the temperature measurement unit 25 calculates the temperature of the object S to be photographed from the thermal image, and preferably, the distance to the measurement object S calculated by the distance measurement unit 24 After correcting the temperature based on the temperature, it is possible to finally calculate the temperature of the photographing target (S). For example, a temperature correction value according to a predetermined distance from the camera module 10 may be stored in advance in the form of a look-up table, etc., and the temperature correction value may be calculated by applying the look-up table to the distance calculated by the distance measuring unit 24. . Alternatively, a temperature correction formula may be defined in advance according to the distance from the camera module 10 and the distance measured by the distance measurement unit 24 may be input into this formula to calculate the temperature correction value. The corrected temperature of the object S to be photographed may be calculated by adding the temperature correction value to the temperature calculated from the thermal image.

The black body recognizing unit 26 may recognize the temperature calibrator 40 within a photographed image. In one embodiment, if information on the shape and color of the temperature calibrator 40 is stored in advance, the blackbody recognizing unit 26 can recognize the temperature calibrator 40 in the real image and the temperature calibrator 40 in the thermal image. After calculating the temperature of the infrared emitter 41, this temperature information is transmitted to the temperature measurement unit 25, and the temperature measurement unit 25 can further correct the temperature based on the temperature information of the infrared emitter 41. there is. An exemplary embodiment of recognizing the temperature calibrator 40 and performing a temperature calibration operation will be described later with reference to FIG. 8 .

The face recognition unit 21, the matching point detection unit 22, the resolution adjusting unit 23, the distance measurement unit 24, the temperature measurement unit 25, and black recognition, which are each functional unit of the image processing device 20 described above. Unit 26 may be composed of software programmed to perform the function and/or hardware supporting it as needed. For example, FIG. 4 is a block diagram of an image processing device according to an exemplary embodiment. Referring to FIG. 4 , the image processing device 20 according to an embodiment may be any computer device, and may include a processor 110, a memory 120, and a storage device 130 as shown. .

The storage device 130 is a storage medium capable of semi-permanently storing data, such as a hard disk drive or flash memory, and includes, for example, a face recognition algorithm 210, a matching point detection algorithm 220, a resolution control algorithm 230, and a distance measurement algorithm. 240, a temperature measurement algorithm 250, a black recognition algorithm 260, and the like can be stored. At this time, the face recognition algorithm 210 is, for example, software that performs at least some functions of the face recognition unit 21, and the matching point detection algorithm 220 is software that performs, for example, at least some functions of the matching point detection unit 22. , The resolution control algorithm 230 is, for example, software that performs at least some functions of the resolution control unit 23, the distance measurement algorithm 240 is software that, for example, performs at least some functions of the distance measurement unit 24, and the temperature The measurement algorithm 250 may be, for example, software that performs at least some functions of the temperature measurement unit 25, and the black recognition algorithm 260 may be software that performs at least some functions of the temperature measurement unit 26, for example.

In this configuration, these various software or algorithms may be stored in the storage device 130 and then loaded into the memory 120 under the control of the processor 110 and executed. Alternatively, these functional units 210 , 220 , 230 , 240 , 250 , and 260 may be implemented as independent software, or may be implemented as software in which two or more functional units are integrated, and at least some of these functional units are used for arbitrary processing outside the image processing device 20 . It can also be installed and run on a device.

5 is a flowchart of a method of measuring the temperature of a subject to be photographed according to an embodiment. Referring to the drawing, the method includes a step of photographing a real image and a thermal image of a subject S (S10), recognizing a face in the real image and a thermal image (S20), measuring a distance, and correcting the temperature for each distance (S60). Here, the step of measuring the distance includes a step of detecting a matching point in each of the real image and the thermal image (S30), adjusting the resolution of each of the real image and the thermal image (S40), and the step of adjusting the resolution of the real image and the thermal image. It may include calculating a distance by matching (S50).

Hereinafter, the present method will be described in more detail. First, in step S10, a real image and a thermal image are generated by photographing an object S to be photographed with a real image camera 11 and a thermal image camera 12, respectively, and using the image processing device ( 20) is forwarded. The image processing device 20 may perform pre-processing on the received real image and thermal image. For example, image enhancement may be performed by processing noise removal, high-pass/low-pass filtering, and the like, and synchronization of real and thermal images may be performed.

Thereafter, in step S20, the face recognition unit 21 of the image processing device 20 detects a face in each of the real image and the thermal image, and in step S30, the matching point detector 22 detects the face in the real image and the thermal image. Each matching point is detected in each detected face in the image. For example, the matching point detector 22 calculates the center of gravity of the two pupils or the center of gravity of glasses in the detected face area, and sets this center of gravity as a matching point.

After that, in step S40, the resolution adjusting unit 23 of the image processing device 20 changes the resolution of at least one of the real image and the thermal image to match the resolution of the two images. The resolution adjusting unit 23 may completely match the resolutions of the two images, or may adjust the resolution of at least one of the two images to the extent that the resolution difference between the two images falls within a predetermined range. The step of adjusting the resolution (S40) may be performed immediately after each of the real image and the thermal image is captured (for example, immediately after step S10), but is preferably performed immediately before matching the two images. Matching points can be more accurately detected in each image by performing an operation of detecting matching points in each of the real image and the thermal image, targeting the original resolution image.

Next, in step S50, the distance measurement unit 24 of the image processing device 20 calculates the distance to the subject S by matching the real image and the thermal image. For example, as described with reference to FIG. 3, the distance measuring unit 24 calculates the position of the matching point in the real image, the position of the matching point in the thermal image, and the distance D between the real camera and the thermal camera. The distance to the target can be measured.

Next, in step S60, the temperature measuring unit 25 may calculate the corrected temperature of the imaging object by adding the temperature of the imaging object calculated from the thermal image and a preset temperature correction value according to the distance to the imaging object. Therefore, according to the embodiment of the present invention, the temperature compensation according to the distance of the photographing target S is possible, so that the temperature of the photographing target can be more accurately measured.

Referring now to FIG. 6, an exemplary embodiment of automatically recognizing and performing temperature calibration of a temperature calibrator according to one embodiment will be described.

As an exemplary method of calibrating the temperature, first, information such as the shape and/or color of the temperature calibrator 40 is transmitted to the image processing device 20 so that the black recognition unit 26 can recognize the temperature calibrator 40 in an image. ) can be registered. For example, when the temperature calibrator 40 is photographed by the real image camera 11 and/or the thermal camera 12 and a pixel area including the temperature calibrator 40 is designated in the photographed image, the black recognition unit 26 transmits the designated pixel Recognizes the edge line (outline) of the case 42 of the temperature calibrator 40 and the color or pattern of the front surface of the case 42 within the region, and converts the recognized edge line, color, and/or pattern information to an image processing device ( 20) to register.

Thereafter, the temperature calibrator is photographed together with the object to be photographed using real and/or thermal cameras 11 and 12, and the temperature calibrator 40 is recognized in the photographed image based on the registered temperature calibrator information. For example, the temperature calibrator 40 may be identified by recognizing the outline, color, or pattern of the case 42 of the temperature calibrator 40 in the real image. Thereafter, the black recognition unit 26 may identify the infrared emitter 41 of the temperature calibrator 40 in the thermal image and measure the temperature of the infrared emitter 41 . For example, the black recognition unit 26 determines that the central region of the exterior (case) 42 of the temperature calibrator 40 identified in the real image is the region of the infrared emitter 41, and sets the temperature of this central region to the infrared emitter 41. can be judged as the temperature of

Thereafter, the black recognition unit 46 transfers information about the measured temperature of the infrared emitter 41 to the temperature measurement unit 25, and the temperature measurement unit 25 uses the temperature of the infrared emitter 41 as a reference temperature. The temperature information of the thermal image can be calibrated. For example, if there is a difference between the temperature value of a pixel corresponding to the infrared emitter 41 and the actual temperature of the infrared emitter 41, the temperature of the thermal image may be corrected by applying the temperature difference value to all pixels, In addition, other known temperature calibration methods may be used.

The temperature calibration operation using the temperature calibrator 40 may be performed every predetermined time period, or alternatively, the image processing device 20 may automatically determine whether or not to perform the temperature calibration and execute the temperature calibration operation. For example, the thermal imaging camera 12 calculates an average value of the body temperature of the target subject to be photographed and measured for a predetermined time, and the image processing device 20 executes the above-described temperature calibration method when the average value is out of a preset temperature range. can

Also, in one embodiment, the operation of recognizing the temperature calibrator and calibrating the temperature may be performed simultaneously or sequentially with the operation of measuring the distance to the object S to be photographed and measuring the temperature described with reference to FIG. 5 . That is, the camera module 10 may take a picture of the subject S, measure the distance, calculate the temperature of the subject based on this, and calibrate the calculated temperature using the temperature calibrator 40 .

As described above, those skilled in the art to which the present invention pertains can understand that various modifications and variations are possible from the description of this specification. Therefore, the scope of the present invention should not be limited to the described embodiments and should not be defined, but should be defined by not only the claims to be described later, but also those equivalent to these claims.

10: camera module 11: real camera
12: thermal camera 20: image processing device
21: face recognition unit 22: matching point detection unit
23: resolution control unit 24: distance measurement unit
25: temperature measuring unit 26: black recognition unit
30: display 40: temperature calibrator
41: infrared emitter 42: case

Claims (6)

A method for measuring the temperature of an object to be photographed in a thermal camera system having an image processing device for processing a real image and a thermal image captured by a real camera and a thermal camera, respectively, of one object to be photographed, the method comprising the steps of:
receiving a real image captured by a real camera and a thermal image captured by a thermal camera and detecting a face in each image;
Recognizing an infrared emitter emitting a predetermined temperature in a thermal image; and
A first matching point is detected in a face detected in the real image, a second matching point is detected in a face detected in the thermal image, a position of the first matching point in the real image, a second matching point in the thermal image, Measuring a distance to the photographing target based on a location of a matching point and a distance between the real camera and the thermal camera;
The image processing device registers and stores at least one of the shape, color, and pattern of the case of the temperature calibrator with the infrared emitter,
In the step of recognizing the infrared emitter, identifying the temperature calibrator in a real image based on one of the registered shape, color, and pattern and then identifying the infrared emitter in a thermal image;
and setting the temperature of the infrared emitter in the thermal image as a reference temperature for temperature calibration. delete According to claim 1,
To measure the distance,
The method of measuring the temperature of the object to be photographed further comprising measuring the distance to the object to be photographed by matching the real image with the thermal image. delete According to claim 3,
The method of measuring the temperature of the photographing target further comprising calculating the temperature of the photographing target from the thermal image and correcting the temperature of the photographing target based on the measured distance to the photographing target. According to claim 5,
In the temperature correction step, the temperature of the photographing target is calculated by adding a temperature of the photographing target calculated from the thermal image and a predetermined temperature correction value according to a distance to the photographing target. How to measure.

Images