KR101806400B1

KR101806400B1 - A surveillance system for body heat by the dual camera using the black body

Info

Publication number: KR101806400B1
Application number: KR1020150153103A
Authority: KR
Inventors: 홍미선
Original assignee: 홍미선
Priority date: 2015-11-02
Filing date: 2015-11-02
Publication date: 2018-01-10
Also published as: KR20170050936A

Abstract

The present invention relates to a dual-camera-based body temperature monitoring system using a black body, which images a person at the same time by using an infrared camera and a visible light camera, and measures a human body temperature and simultaneously records an image of a person measured. A blackbody portion including at least two blackbody sources; A dual camera unit composed of a visible light camera that captures an object in a visible light band and a thermal camera that captures a thermal image by a thermal sensor; And a control unit for causing the thermal imaging camera to image the person and the blackbody source, to detect a body temperature of the person from the sensed thermal image, to judge whether the infectious disease is suspected by the detected body temperature, And a monitoring control unit for capturing and storing a person, wherein the monitoring control unit is configured to correct the body temperature of the person detected by the thermal image using the detection temperature and the divergence temperature of the blackbody source detected in the thermal image, .
According to the above-described surveillance system, a body temperature appearing as a thermal image can be calculated based on the temperature of a black body by imaging a black body at the same time as a human body with a thermal imaging camera, and more accurate body temperature can be measured.

Description

[0001] The present invention relates to a dual-camera based body temperature monitoring system using a black body,

The present invention relates to a dual camera-based body temperature monitoring system using a black body, which captures a person at the same time by using an infrared camera and a visible light camera, and measures the body temperature of a person and simultaneously records an image of a person.

In addition, the present invention relates to a dual-camera-based body temperature monitoring system using a black body, which images a black body that emits a specific temperature in advance and calibrates a temperature reference of the thermal imaging camera using the black body temperature and the measured temperature .

Generally, if a patient or infected person with a communicable disease freely communicates in a public place or a large building where a large number of people gather, the disease can be transmitted to another person, and particularly, spread disease widely. Therefore, these infectious persons should take early isolation from the public and block the possibility of transmission to many people.

In recent years, respiratory infectious diseases have emerged, and dangerous situations that infect a wide range of people are frequent. For example, new infectious diseases such as SARS (Severe Acute Respiratory Syndrome), H1N1, Ebola and MERS are frequent.

However, since these infectious diseases show symptoms similar to those of common diseases such as colds, the infected person himself or herself can not know the infection itself until the infectious disease is confirmed. Therefore, it is necessary to quickly check whether these infected people are passing through public places, where people gather, and take additional inspections or isolation measures.

Most of these infectious diseases are accompanied by fever, so people with severe fever can be judged primarily as suspects of the disease and can be examined through an overhaul. In other words, the first suspicious person can be judged by measuring the body temperature.

Body temperature refers to the temperature inside the body. Although body temperature varies greatly depending on the area of the body, the normal body temperature of a human is 36.9 ° C in the armpit temperature, and the child is slightly higher than the adult and the elderly tend to be lower. The high temperature condition of the body temperature causes more severe conditions than the low temperature condition. Body temperature is about 37 ℃ for adults, normal body temperature, about 41 ℃ for seizures and pain causes, 43.3 ℃ is the maximum limit of life maintenance. In addition, life can not be maintained even at body temperature of 27 ℃ or less.

The most accurate way to measure body temperature is to measure the temperature of the rectum measured at an area of more than 6 cm from the anus. However, since the measurement method is too complicated, the temperature of the noble metal is generally measured. However, since an unspecified number of people pass through public places such as airports, there is a problem that it requires a lot of manpower for the passengers to measure their own temperature by measuring their own temperature and inconvenience to passengers .

In order to solve the above problems, various devices have been proposed for monitoring the body temperature and infectious condition using a thermal imaging camera. As an example, a technique of detecting a patient's body temperature in real time by taking a patient in a patient's room and an ICU room using a thermal camera has been proposed [Patent Document 1]. As another example, an apparatus for measuring the body temperature of a visitor installed in an entrance or the like of a public place and measuring a body temperature of a person with a thermopile array sensor module, and when the measured temperature exceeds a preset temperature, And the image of the subject is captured and stored together with the measured temperature is proposed (Patent Document 2).

However, since the technique disclosed in Patent Document 1 is a technique for measuring in a room such as a sickroom or an intensive care unit, it is difficult to apply it to a public place where a lot of people flow and the surrounding environment can be frequently changed. In addition, in Patent Document 2, since the measurement is performed at the entrance of a public place where the surrounding environment is frequently changed, there is a problem that the body temperature of the visitor can not be accurately measured according to the ambient temperature change.

[Patent Document 1] Korean Published Patent Application No. 10-2011-0044665 (published on April 29, 2011) [Patent Document 2] Korean Registered Patent No. 10-1420200 (issued on July 21, 2014)

SUMMARY OF THE INVENTION An object of the present invention is to solve the above-mentioned problems, and an object of the present invention is to provide a black body, which preliminarily captures a black body emitting a specific temperature, calibrates a temperature reference of a thermal imaging camera using the black body temperature and the measured temperature at this time, To provide a dual-camera-based body temperature monitoring system.

In order to accomplish the above object, the present invention provides a dual camera-based body temperature monitoring system using a black body, comprising: a black body unit including at least two black body sources for radiating a preset divergence temperature; A dual camera unit composed of a visible light camera that captures an object in a visible light band and a thermal camera that captures a thermal image by a thermal sensor; And a control unit for causing the thermal imaging camera to image the person and the blackbody source, to detect a body temperature of the person from the sensed thermal image, to judge whether the infectious disease is suspected by the detected body temperature, Wherein the monitoring control unit corrects the body temperature of the person detected by the thermal image using the detection temperature and the divergence temperature of the blackbody source detected in the thermal image .

In the dual-camera-based body temperature monitoring system using a black body, the black body unit may include a human body sensor disposed at a front side of the pass band and sensing an object in a direction perpendicular to a direction passing through the pass band, The dual camera unit is installed on the side of the passing bar, and is configured to capture an image when the human body detection sensor senses an object, and to simultaneously image a blackbody source of the black body and a person passing through the black body.

In the dual-camera-based body temperature monitoring system using a black body, the human body detecting sensor may be constituted by an infrared sensor or an ultrasonic sensor, or may be constituted by a button type input device or a keypad type input device, And a personal identification dictionary having a fingerprint recognition function.

According to another aspect of the present invention, there is provided a dual camera-based body temperature monitoring system using a black body, wherein a divergence temperature of the first black body source, which is one of the at least two black body sources, And the divergence temperature of the first and second blackbody sources is set within a human body temperature range.

According to the present invention, in the dual-camera-based body temperature monitoring system using a black body, the monitoring and controlling unit controls the first and second reference image values And normalizing the thermal image with the first and second reference image values, detecting the face region in the normalized thermal image, and detecting the body temperature with the representative image value of the detected face region do.

In the dual camera-based body temperature monitoring system using a black body, the first and second reference image values are obtained by averaging image values of the first and second black body source regions.

In addition, the present invention is characterized in that in a dual-camera-based body temperature monitoring system using a black body, the image value of the thermal image is normalized by the following equation (1).

[Equation 1]

Where T (x) is the normalized image value of the x pixel of the thermal image, t (x) is the image value of the x pixel of the thermal image, T ₁ and T ₂ are the normalized image values of the first and second blackbody sources And t ₁ and t ₂ are the first and second reference image values, respectively.

According to the present invention, in the dual-camera-based body temperature monitoring system using a black body, the monitoring and controlling unit performs filtering with a body temperature filter based on a temperature range of a body temperature region of a normalized thermal image to generate a binarized image Performing a closing operation of a morphology operation on the binarized image to perform noise removal, and detecting a final face area through at least one of position, size, and shape filtering .

In the dual camera-based body temperature monitoring system using a black body, the representative pixel value of the face region is calculated by averaging pixel values of pixels having upper pixel values corresponding to a predetermined range among the detected face regions And calculating a representative image value of the face region as an average value of pixels that are not less than the average pixel value of the detected face region.

In the dual-camera-based body temperature monitoring system using a black body, the monitoring and control unit matches the visible light image and the thermal image, detects a face region and a blackbody source region in the visible light image, A face region and a blackbody source region of the thermal image corresponding to the face region and the blackbody source region of the optical image are detected and a representative image value is detected in the face region of the detected thermal image, The reference image value is calculated in the source region, and the temperature of the representative image value is corrected by the reference image value.

According to another aspect of the present invention, there is provided a dual-camera-based body temperature monitoring system using a black body, wherein the monitoring control unit extracts feature points using the blackbody source region, and matches the visible image and the thermal image using the extracted feature points .

According to the present invention, in the dual-camera-based body temperature monitoring system using a black body, the surveillance control unit extracts a forehead region and a ball region by subdividing the detected face region, calculates a representative image value in the forehead region, When the forehead area is not detected or the size of the area is smaller than a predetermined size, the representative image value is calculated in the ball area.

As described above, according to the dual-camera-based body temperature monitoring system using the black body according to the present invention, when a thermal image camera and a visible light camera are simultaneously imaged, the face of a person to be measured is recorded together with the measured body temperature, It is possible to track and manage the infected person and to analyze past measurement results.

In addition, according to the dual-camera-based body temperature monitoring system using the black body according to the present invention, by imaging the black body at the same time as the human body with the thermal camera, the body temperature appearing as a thermal image is calculated based on the temperature of the black body, A measurable effect is obtained.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram of an entire system for implementing the present invention. FIG.
2 is a block diagram of a dual-camera based body temperature monitoring system using a black body according to an embodiment of the present invention.
3 is a flowchart illustrating a dual camera-based body temperature monitoring method according to an embodiment of the present invention.
4 is a flowchart illustrating a step of detecting a body temperature by detecting a face region according to the first embodiment of the present invention.
FIG. 5 is a flowchart illustrating steps of detecting a body temperature by detecting a face region according to a second embodiment of the present invention; FIG.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the drawings.

In the description of the present invention, the same parts are denoted by the same reference numerals, and repetitive description thereof will be omitted.

First, a configuration of a dual camera-based body temperature monitoring system using a black body according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2. FIG.

1, the dual-camera-based body temperature monitoring system using the black body according to the present invention includes a dual camera unit 30 installed in the passage 20, a black body unit 40 installed at a front side of the passage 20, And a monitoring control unit (not shown) 50 for controlling the dual camera unit 30 and the black body unit 40 or for taking data and analyzing the data.

First, the pass table 20 refers to a door, a test stand, a passage, etc. through which the person 10 can walk and pass. Preferably, it is a door, passage or walkway through which the person 10 can pass by one person.

Next, the black body portion 40 will be described in detail.

The blackbody part (40) is provided on the front side of the pass bar (20). As an example, it can be realized as a stand type as shown in Fig. Or, as another example, if the passage bar 20 is formed in the shape of a passage, the black body portion 40 can be installed in the wall of the passage. Particularly, the blackbody portion 40 is provided in front of the passband 20 so that the blackbody portion 40 passes first before the person 10 passes through the passband 20.

2, the black body portion 40 has a first black body source 41 for diverging at a specific temperature and a second black body source 42 having a temperature lower than the temperature of the first black body source 41 . Preferably, the black body portion 40 may further comprise a human body sensor 43 for recognizing that the human body 10 passes. The second signal processing unit 45 (not shown) performs signal processing on the measured values measured by the first and second black body sources 41 and 42 and the human body sensor 43, ).

The first and second blackbody sources 41 and 42 are black bodies having (or diverging) a specific temperature, that is, a predetermined temperature set in advance. Preferably, the first and second blackbody sources 41 and 42 are set using the human body temperature range. The temperature of the first black body source 41 is set to a higher temperature than the temperature of the second black body source 42. [

Preferably, the temperature of the first black body source 41 is set within the range of 15% of the maximum value of the body temperature or the body temperature, and the temperature of the second black body source 42 is set within the range of 15% do. More preferably, the temperature of the first black body source 41 is set within 37-43 占 폚, and the temperature of the second black body source 42 is set within 30-37 占 폚.

The first and second blackbody sources 41 and 42 are installed in the upper half of the person or in the face height of the person. Preferably, the first and second blackbody sources 41 and 42 are installed at a height of 1 m to 2 m from the ground or the bottom surface. The people who pass through are various, such as tall, single, adult, child, or wheelchair person. It is therefore desirable that they are installed at their average face height. That is, the first and second blackbody sources 41 and 42 are installed at a height of 1.2 m to 1.5 m from the ground or the bottom surface.

The human body detection sensor 43 is a sensor for detecting a person passing through, and is an object for detecting an object such as an infrared (IR) sensor or an ultrasonic sensor. At this time, the human body detection sensor 43 detects an object or a human body in a direction perpendicular to a direction passing through the passband 20. Accordingly, the moment the person passes the black body portion 40, the human body sensor 43 senses the person to pass through.

Alternatively, as another embodiment, the human body detection sensor 43 may be implemented as a personal identification device such as a magnetic card, RFID, fingerprint recognition, or the like. When a person who is going to pass an ID card or a mobile terminal with a built-in RFID or the like to a reader (human body monitoring sensor or the like), it is detected that there is a person who wants to pass. In this case, the person who is going to pass can be identified. The above embodiment is suitable for a place where entrance and exit are controlled after confirming the identity of a passenger at a door.

As another embodiment, the human body detection sensor 43 may be implemented by a button or a keypad-type input device, and a person may be detected by pressing a button or a keypad.

When the human body detection sensor 43 recognizes that the human body passes, the monitoring control unit 50 or the like receives it and controls the first and second black body portions 41 and 42 or the dual camera unit 30 to operate .

The second signal processing unit 45 performs signal processing on the measured values measured by the first and second black body sources 41 and 42 and the human body detection sensor 43. That is, the measurement value is converted into digital data, and the processed signal is transmitted to the monitoring control unit 50 or the like. The second signal processing unit 45 receives commands and the like from the monitoring control unit 50 and transmits control signals to the black body sources 41 and 42 and the human body monitoring sensor 43 and the like.

Next, the dual camera unit 30 will be described in more detail.

As shown in FIG. 2, the dual camera unit 30 is composed of a visible light camera 31 for capturing an object in a visible light band, and a thermal imager 32 for capturing a thermal image by a heat sensor. The image processing apparatus further includes a first signal processing unit 35 for signal processing the images photographed by the cameras 31 and 32 or transmitting control commands to the cameras 31 and 32.

The visible light camera 31 is a general camera that captures an image of a subject in a visible light band. An image photographed through the visible light camera 31 can generally acquire an RGB image (or a color image).

The thermal imaging camera 32 refers to a camera that measures heat (temperature) distribution in a space photographed through infrared rays or the like. Since the infrared camera 32 generates an image due to the temperature difference and all objects with an absolute temperature of 0 K or more generate infrared rays themselves, the shape of the object can be obtained by the temperature distribution difference.

Preferably, the photographing area and the focus of the visible light camera 31 and the infrared camera 32 are preset and fixed. In particular, the two types of cameras 31 and 32 are set so that they can capture the same area.

The first signal processing unit 35 stores the image or image captured by the visible light camera 31 and the thermal imaging camera 32 in the image or image data format and transmits the image or image data to the monitoring control unit 50 or the like . The first signal processing unit 35 also receives commands and the like from the monitoring control unit 50 and transmits control commands to the cameras 31 and 32 and the like.

Next, the monitoring control unit 50 and the remote server 60 will be described.

The monitoring control unit 50 or the remote server 60 receives the temperature of the dual camera unit 30 and the visible light image (or image), the thermal image, and the blackbody source sensed or measured by the blackbody unit 40 Or fetching it by request), detects the body temperature of the photographed person, and judges whether the infectious disease is suspected by the detected body temperature. In addition, the monitoring control unit 50 or the remote server 60 records the visible light image, the thermal image, or the detected body temperature.

If the surveillance control unit 50 or the remote server 60 determines that the infectious disease is suspected based on the detected body temperature, the surveillance control unit 50 or the remote server 60 outputs the suspicious result to the passband 20 as an alarm or notifies the person in charge.

When the monitor control unit 50 or the remote server 60 receives a signal indicating that a person is passing from the human body detection sensor 43 in front of the pass band 20, the black body source 41, 31 and 32 are operated to control the photographing of the visible light image or the thermal image.

The monitoring control unit 50 may be implemented in a dedicated computing circuit having a microprocessor, a memory, or the like, or a computing terminal such as a personal computer (PC). Preferably, the supervisory control section 50 is provided at a site where the pass band 20 is installed. More preferably, the supervisory control unit 50 may be provided inside the apparatus having the dual camera unit 30 or the black body unit 40. Alternatively, the monitoring control unit 50 may be implemented as a separate apparatus independent of the dual camera unit 30 or the black body unit 40. [

The remote server 60 is a device having a computing processing function such as a personal computer (PC) or a server device. The remote server 60 is connected to the monitoring and controlling unit 50 via a network and receives a visible light image, And transmits a command or the like to the monitoring control unit 50. [0050] The remote server 60 is a server installed in a central control room or a central control room, and transmits / receives data to / from the monitoring control unit 50 via a network.

On the other hand, the remote server 60 can share the roles with the monitoring control unit 50 and process them. For example, when the human body is sensed by the human body monitoring sensor 43, the monitoring control unit 50 drives the visible light camera 31 and the infrared camera 32 to pick up an image, and receives the visible light image and the thermal image The captured date and two images are bundled and transmitted. Then, the remote server 60 performs a function of detecting the body temperature from the thermal image and judging whether or not the infectious disease is suspicious. In particular, the remote server 60 has excellent performance such as data storage capacity and computing capability, and the monitoring and control unit 50 may be inferior in performance to the remote server 60 as equipment installed in the field. In consideration of such a difference in performance, the functions between the remote server 60 and the monitoring control unit 50 can be shared. Hereinafter, it will be described that the monitoring control unit 50 performs all the above functions.

Next, a dual camera-based body temperature monitoring method according to a first embodiment of the present invention will be described with reference to FIG. 3 and FIG.

As shown in FIG. 3, first, it is detected whether there is a human body passing through the passband 20 (S10). That is, the human body detection sensor 43 of the black body part 40 detects whether there is a human body or a person to pass through the pass band 20. As described above, since the black body portion 40 is provided on the front side of the pass band 20, the person who is going to pass through the pass band 20 will pass the black body portion 40, Is detected.

Next, when a human body is sensed, a human body is imaged through the dual camera unit 30 to obtain a condensed light and a thermal image (S20). That is, a visible light image is acquired through the visible light camera 31, and a thermal image is obtained through the thermal image.

Preferably, the visible light camera 31 and the thermal imaging camera 32 simultaneously capture the first and second black body sources 41 and 42 of the black body portion 40 in the image together with the person to pass through.

Next, the body temperature is detected from the obtained thermal image (S30).

As shown in FIG. 4, the body temperature detection step S30 includes a step S31 of calculating a reference image value with a thermal image value of the blackbody source region, a step S32 normalizing the thermal image with a reference image value, A step S33 of detecting the face region in the thermal image, and a step S34 of detecting the body temperature with the representative image value of the face region.

The thermal image is the image in which the first and second blackbody sources 41 and 42 are captured together. The reference image value is set as an average value of the blackbody source region in the thermal image. All the pixels in the blackbody source region do not have the same image value due to noise or errors. Therefore, the reference image value is set to a value obtained by averaging the values.

The reference image value obtained from the first black body source 41 is referred to as a first reference image value and the reference image value obtained from the second black body source 42 is referred to as a second reference image value.

On the other hand, each of the first and second blackbody sources 41 and 42 emits a specific temperature. This is called the actual temperature or the divergence temperature of the blackbody source. However, the reference image value obtained before is different from the actual temperature. That is, the actual temperature differs from the reference image value due to the error due to the characteristics of the thermal sensor of the thermal imager 42 or the influence of the surrounding environment.

Therefore, normalization is performed to map the thermal image to the actual temperature using the actual temperature of the blackbody sources 41 and 42 and the reference image value (S32).

The actual temperature and the image value of the thermal image have a proportional relationship with each other. Therefore, the actual temperature and the image value are proportional to each other as in the following equation.

[Equation 1]

Here, T (x) is the actual temperature or normalized image value of the x pixel of the thermal image, and t (x) is the image value (pixel value) of the x pixel of the thermal image. Further, T ₁ and T ₂ are the actual temperatures of the first and second blackbody sources 41 and 42, respectively, and t ₁ and t ₂ are the first and second reference image values, respectively.

Therefore, the image values of x pixels of the thermal image are normalized to T (x) by the following equation.

&Quot; (2) "

Next, the face region is detected in the normalized thermal image (S33).

A normalized thermal image is filtered by a temperature filter based on the temperature range of the body temperature region to generate a binarized image. The binarized image is performed by the following equation.

&Quot; (3) "

Here, I (x) is the pixel value of the binarized image of the pixel x, and T (x) is the image value of the x pixel of the normalized thermal image. T _BL and T _BH are the minimum temperature and maximum temperature of the body temperature, respectively.

Then, a closing operation of the morphology operation is performed on the binary image generated by the body temperature filter to perform correction to remove noise. Binary images that have been subjected to body temperature filtering contain noise, and morphology operations are required to remove such noise. By performing Erosion and Dilation operations on the filtered body temperature region through the body temperature filtering, the contour is smoothed and the hole formed in the body temperature filtering process is filled. That is, for the filtered region through the morphology operation, the disappearance information generated in the pixel included in the body temperature region is filled and the noise component is removed. The closure operation of the morphology operation performs the shrink operation after expansion. The closure operation of the computation has the effect of magnifying the object, while at the same time removing the noise isolated in the object.

The final face region is detected by filtering the position, size, and shape of the body temperature region obtained by the above-mentioned morphological operation. That is, since the photographing position of the infrared camera 42 and the position where the person stands as the subject are determined in advance, the position where the face can appear, the face size, or the shape of the circle can be known. Thus, the face region is detected in a body temperature region having a predicted position, size, shape, and the like. The filtering by position, size, and shape as described above is for judging which body temperature region is a face region when a plurality of body temperature regions are detected.

Next, the representative image value of the detected face region is calculated and detected by body temperature (S34).

As an example, the pixel values (image values) of the upper pixels among the pixel values higher than the detected face area are averaged to be calculated as a representative image value of the face area. Preferably, the representative image value is calculated as an average value for the upper 10 to 30% of the pixels.

As another example, a representative image value of the face region is calculated as an average value for pixels having an average pixel value or more of the detected face region.

In the face region, the skin temperature may not appear in these areas including the eyes and the like. Therefore, the temperature of the remaining skin is averaged except the image value (pixel value) of the non-skin region, and is detected as the body temperature of the subject.

Next, when the body temperature is detected, the detected body temperature is compared with the reference temperature (S40), and if it is larger than the reference temperature, it is determined that there is a contagious disease suspicion (S50). If an infectious disease is suspected, additional investigation is required, so the result of the suspicion is output as an alarm or notified to the terminal of the person in charge.

Further, the visible light image and the body temperature are stored and recorded (S60). For each person, the detected body temperature and visible light image, or the result of the judgment of whether or not there is an infectious disease, and the measurement time are stored together. Therefore, it is possible to track and manage the results of body temperature measurement in the future.

Next, a dual camera-based body temperature monitoring method according to a second embodiment of the present invention will be described with reference to FIG.

The second embodiment of the present invention is the same as the method of the first embodiment described above and the overall steps. However, there is a difference in the step S30 of detecting the body temperature from the thermal image. Hereinafter, the body temperature detecting step S30, which is different from the first embodiment, will be described in detail. Other steps or methods refer to the first embodiment.

As shown in FIG. 5, first, the visible light image and the thermal image are registered (S131). Both the visible light image and the thermal image are images that capture the same object. The two images are matched using the feature points corresponding to each other in the virtual optical image and the thermal image.

By matching the visible light image with the thermal image, an area of the thermal image corresponding to a specific area of the visible light image can be found immediately. A method of matching two images using feature points is used. That is, since both the virtual optical image and the thermal image are images on the same plane, if at least three corresponding minutiae points (at least three points that are not on the parallel lines) are used, .

In particular, the minutiae points are set in advance or the area of the first and second blackbody sources 41 and 42, or the edge or vertex portions thereof, are set. The visible light camera 31 or the infrared camera 32 can fix the focus to a specific area in advance. In this case, there is always the same shape or feature point in the background image to be captured. Therefore, the shape of the object and the temperature (or the temperature at which the image value is detected as the image value, which is different from the adjacent image value) can be detected as the feature point, and the matching based on the feature point can be performed.

The first and second black body sources 41 and 42 can know the value of the image or the temperature of the black body source 41 or 42 detected before the temperature measurement. Therefore, it is possible to extract feature points from images or image values at the edge or vertex of the region of the first and second blackbody sources 41 and 42, preferably.

Next, the face region is detected in the visible light image (S132). The face detection method detects face using skin color and eye detection. That is, a skin region is detected using a skin color filter, a pupil is detected in a corresponding region of a plurality of skin regions, and a skin region in which a pupil is detected is detected as a face. At this time, it is possible to judge more accurately by considering the size and position of the face.

At this time, if the visible light image is an RGB color model image, it is converted into an image having a YCbCr color model. In general RGB color model used in image processing field, it is sensitive to change of illumination. Therefore, the distribution of color changes due to the influence of external illumination change and the like. Color filtering is performed using a YCbCr model with relatively robust characteristics for various illumination changes. Here, Y represents a luminance component, and Cb and Cr represent chrominance components. The advantage of using the YCbCr color model is that the color feature information from which the influence of the luminance value is removed from the color information can be used, thereby extracting the feature that is robust against the illumination change.

On the other hand, if the face region is not detected in the visible light image, an alarm or a warning is output or the person in charge is notified. When a person who wants to pass through the pass band 20 wears a hat, glasses, mask, or the like that considerably covers the face, the face due to skin color can not be detected. Therefore, in this case, you are asked to remove glasses, masks, etc. from your face through the guidance.

Next, the representative image value is calculated in the face region of the thermal image (S133).

When the region of the thermal image corresponding to the face region extracted from the visible light image is extracted, the extracted region corresponds to the face region in the thermal image. At this time, since the two images are matched in advance, the face region of the thermal image region can be extracted simply.

On the other hand, the pixel values (image values) of the upper pixels among the pixel values higher than the face area are averaged to be calculated as representative image values of the face area. Preferably, the representative image value is calculated as an average value for the upper 10 to 30% of the pixels. As another example, a representative image value of the face area is calculated as an average value for pixels having an average pixel value or more of the face area.

Next, the blackbody source region is detected in the visible light image (S134).

In order to detect the blackbody source region, a black body color filter is used.

Preferably, the color of the black body portion 40 is markedly different from the color of the maroon blackbody source of the first and second blackbody sources 41 and 42. By using the color of the blackbody source and the peripheral color of the blackbody source, the area of the blackbody can be accurately detected.

On the other hand, if the black body source region can not be detected in the visible light image, an alarm or warning is output or the person in charge is notified. The blackbody sources 41 and 42 may be blocked from the visual field of the forensic light or thermal imagers 31 and 32 by the person 10 or the object or other object intended to pass through the passband 20. In this case, since the blackbody source region can not be detected, the black body portion 40 is requested to remove the object from the black body portion 40 through the guidance or notify the person in charge.

Next, the blackbody source region is extracted from the thermal image and the reference image value is calculated from the blackbody source region (S135). When the region of the thermal image corresponding to the blackbody source region extracted from the visible light image is extracted, the extracted region corresponds to the blackbody source region in the thermal image.

Preferably, the reference image value is set as an average value of the blackbody source regions in the thermal image.

Next, the actual temperature of the representative image value is calculated using the reference image value, and the body temperature is detected (S136).

The actual temperature T _B of the representative image value is calculated as follows. The actual temperature T _B of the representative image value is the body temperature to be detected immediately.

&Quot; (4) "

Here, t _B is the representative image value of the thermal image. Further, T ₁ and T ₂ are the actual temperatures of the first and second blackbody sources 41 and 42, respectively, and t ₁ and t ₂ are the first and second reference image values, respectively.

Next, a dual camera-based body temperature monitoring method according to a third embodiment of the present invention will be described.

The third embodiment of the present invention is the same as the above-described second embodiment method and the overall steps. However, there is a difference in the step of detecting the face region in the step of detecting the body temperature from the thermal image (S30) and calculating the representative image value in the face region. Hereinafter, differences will be specifically described, and other steps or methods will be referred to the second embodiment.

The face region is detected from the visible light image and the face region is segmented to extract the forehead region and the ball region. The skin temperature in the forehead region more accurately represents the human body temperature. However, when the bangs are lowered to the eyebrow area, the forehead area can not be detected. In this case, therefore, the body temperature is detected in the ball area.

Specifically, when the forehead region is detected as a region of sufficient size, the representative image value is calculated within the forehead region. However, if the forehead area is not detected or the size of the area is smaller than the predetermined size, the representative image value is calculated in the ball area.

Although the present invention has been described in detail with reference to the above embodiments, it is needless to say that the present invention is not limited to the above-described embodiments, and various modifications may be made without departing from the spirit of the present invention.

10: Person 20: Passage band
30: dual camera unit 31: visible light camera
32: thermal imager 35: first signal processor
40: black body part 41: first black body source
42: second black body source 43: human body detection sensor
45: second signal processor
50: monitoring control unit 60: remote server

Claims

A dual camera-based body temperature monitoring system using a black body,
A blackbody portion including at least two blackbody sources that emit a predetermined divergence temperature;
A dual camera unit composed of a visible light camera that captures an object in a visible light band and a thermal camera that captures a thermal image by a thermal sensor; And
And a controller for controlling the infrared camera to pick up a person and the blackbody source to obtain a thermal image, to detect a human body temperature from the thermal image, to judge whether the infectious disease is suspected by the detected body temperature, And a monitoring control unit for acquiring and storing a visible light image,
The monitoring control unit corrects the body temperature of the person detected by the thermal image using the detection temperature and the divergence temperature of the blackbody source detected in the thermal image,
The divergence temperature of the first blackbody source being one of the at least two blackbody sources is set to be higher than the divergence temperature of the second blackbody source being the other one of the at least two blackbody sources, And the divergence temperature of the second black body source is set within a human body temperature range.

The method according to claim 1,
Wherein the black body portion is provided at a front side of the pass band and includes a human body sensor for sensing an object in a direction perpendicular to a direction passing through the pass band,
Wherein the dual camera unit is installed on the side of the passing carriage and is configured to capture an image when the human body detecting sensor senses an object to simultaneously image a blackbody source of the black body and a person passing through the black body, Camera based body temperature monitoring system.

3. The method of claim 2,
Wherein the human body detection sensor is constituted by an infrared sensor or an ultrasonic sensor, a button type input device, a keypad type input device, or a personal identification device having a magnetic card, RFID, or fingerprint recognition function. Dual camera based body temperature monitoring system using.

delete

The system according to claim 1,
Calculating first and second reference image values respectively from the thermal image values of the first and second blackbody source regions in the thermal image, normalizing the thermal image with the first and second reference image values, A dual camera-based body temperature monitoring system using a black body, characterized by detecting a face region in a normalized thermal image and detecting a body temperature with a representative image value of the detected face region.

6. The method of claim 5,
Wherein the first and second reference image values are obtained by averaging image values of the first and second blackbody source regions.

6. The method of claim 5,
Wherein the image value of the thermal image is normalized by the following equation (1).
[Equation 1]

6. The method of claim 5,
The monitoring control unit performs a filtering operation on a normalized thermal image with a body temperature filter based on a temperature range of a body temperature region to generate a binarized image and performs a closing operation of a morphological operation on the binarized image And a final face region is detected through at least one of a position, a size, and a shape. The dual-camera-based body temperature monitoring system using the black body according to claim 1,

6. The method of claim 5,
A representative pixel value of the face region is calculated by averaging pixel values of pixels having upper pixel values corresponding to a predetermined range among the detected face regions or a mean value of pixels Area based on the image data of the black body.

The method according to claim 1,
Wherein the monitoring control unit is configured to match the visible light image and the thermal image to detect a face region and a blackbody source region in the visible light image and detect the face region of the visible light image and the face of the thermal image corresponding to the blackbody source region And a blackbody source region, detects a representative image value in a face region of the detected thermal image, calculates a reference image value in a blackbody source region of the detected thermal image, And the temperature of the temperature sensor is corrected.

10. The method of claim 9,
Wherein the monitoring control unit extracts a feature point using the blackbody source region and matches the visible image with the thermal image using the extracted feature points.

10. The method of claim 9,
The surveillance control unit may extract the forehead area and the ball area by subdividing the detected face area, calculate a representative image value in the forehead area, and if the forehead area is not detected or the size of the area is smaller than a predetermined size And if it is smaller, the representative image value is calculated in the ball area.