JP2005237861A - Automatic thermometric device and automatic thermometric method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an automatic thermometric device and an automatic thermometric method capable of automatically measuring the body temperature of a person and an animal in a noncontact state. <P>SOLUTION: This automatic thermometric device 1 calculates a position of a body temperature measuring part in a face by recognizing the face of a measuring object person by image recognition from an image by imaging the image by an image input unit 20. Next, the automatic thermometric device 1 detects an infrared ray radiated from the body temperature measuring part by a far infrared radiation sensor 12 by positioning a measuring visual field of an infrared ray detecting unit 10 in the body temperature measuring part. The body temperature of the measuring object person is calculated on the basis of a detecting value of the far infrared radiation sensor 12. Thus, the body temperature of the measuring object person staying in an imaging area can be automatically measured in a noncontact state. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a technique for automatically measuring body temperature without contact.

  If the body temperature of a person or an animal can be automatically measured without contact, it can be applied to various situations such as a system for automatically detecting an infected person typified by SARS and a system for monitoring the condition of a patient. However, there is no example of implementing this type of automatic temperature measuring device.

  However, in a field close to this, there is a technique for measuring the temperature distribution on the surface of the object in a non-contact manner.

  For example, an infrared camera is configured by combining an infrared image sensor in which infrared sensor elements such as compound semiconductors are two-dimensionally arranged and an optical system for imaging infrared rays. Usually, a Si-based CMOS drive circuit is disposed below the two-dimensionally arranged infrared sensor elements, and reads out the signals of the individual infrared sensor elements to the outside. There are many examples of research and development of such infrared cameras, and those having hundreds of pixels × hundreds of pixels have been developed. Currently, it is mainly applied to crime prevention applications as night vision cameras.

  Further, a radiation thermometer has been put to practical use as a measuring instrument for measuring temperature without contact. In particular, the non-contact two-dimensional radiation thermometer (product name: iSquare) manufactured by HORIBA, Ltd. has a configuration in which a visible light camera and 64 infrared sensors (thermopiles) arranged two-dimensionally are juxtaposed in the horizontal direction. The temperature distribution can be overlaid on the visible image. Although the resolution of the obtained temperature distribution is as coarse as 8 × 8 pixels, it is noted that it is about 1/10 the price of an infrared camera.

In addition, there is also known a method of controlling the temperature of an air conditioner by roughly detecting the position of a person with a CCD and then finely tracking the position of the face with an infrared sensor and measuring the face temperature (Patent Document). 1).
Japanese Examined Patent Publication No. 7-101120

  When the above-described infrared camera or two-dimensional radiation thermometer is used for the purpose of measuring the body temperature of a person or an animal, there are the following problems.

  An infrared camera can grasp the temperature distribution on the body surface, but it is difficult to measure body temperature (that is, absolute temperature). In addition, an infrared camera can only obtain an image that represents the temperature distribution in the field of view with pseudo gradations, so it is difficult to grasp which part of the measurement object the obtained measurement result represents. . Therefore, it is not suitable for the purpose of automatically measuring the temperature of a large number of people at an airport or the like, or for the purpose of automatically measuring the temperature of a large number of domestic animals at a breeding ground or the like. Moreover, since the infrared camera uses a large number of sensor elements, there is also a problem that the cost is high.

  In the two-dimensional radiation thermometer, since the visible image and the temperature distribution can be displayed in an overlapping manner, it is easy to grasp the correspondence between the measurement object and the measurement result. However, the user himself / herself must issue a measurement instruction with the measurement visual field of the thermometer directed toward the measurement object, and automatic body temperature measurement cannot be performed.

  In addition, the body surface temperature of humans and animals is not uniform, and for example, the temperature varies among the forehead, nose, cheeks, lips, and chin even in the face. Therefore, in order to measure accurate body temperature, accurate alignment between the measurement visual field and the body temperature measurement site is important. In other words, if the measurement location varies depending on the individual measurement object, erroneous measurement increases, and a meaningful measurement result cannot be obtained.

  However, in the above two-dimensional radiation thermometer, there is a parallax (26 mm in the horizontal direction) between the visible light camera and the infrared sensor, and the size of the measurement field of view varies depending on the measurement distance. In other words, it is difficult to accurately align the measurement field of view with the body temperature measurement site. Especially if the user manually aligns.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an automatic temperature measuring apparatus and an automatic temperature measuring method capable of automatically measuring the body temperature of a person or an animal without contact. .

  In order to achieve the above object, in the present invention, the body temperature of the measurement object is measured by the following means or processing.

  An automatic temperature measuring device according to an aspect of the present invention includes an imaging unit and an infrared detection unit.

  The direction of the measurement visual field of the infrared detection means is variably controlled. This makes it possible to measure the body temperature of a measurement object present at an arbitrary location. It is also preferable that the direction of the imaging field of the imaging means is variably controlled. Thereby, the measurable range is further expanded.

  The imaging unit is a unit that captures an image including a measurement target, and includes, for example, a two-dimensional imaging element and an optical system that forms an image on the imaging element. The image obtained by the imaging means may be color or monochrome.

  The infrared detection means is means for detecting the intensity of infrared rays (infrared radiation). The infrared detection means includes, for example, a single-element infrared sensor and an optical system that focuses infrared light on the infrared sensor. In the case of a single element infrared sensor, there is an advantage that the apparatus cost can be reduced. Alternatively, a configuration having an infrared image sensor composed of a plurality of elements and an optical system that forms an image of infrared light on the infrared image sensor is also preferable. The sensitivity range of the infrared detecting means is preferably set to the far infrared wavelength range suitable for body temperature measurement.

  The automatic temperature measuring apparatus includes a measurement target determining unit that recognizes a measurement target by image recognition from an image captured by the imaging unit and obtains a position of a body temperature measurement site in the measurement target.

  Here, “measuring objects” include people and animals. Further, the whole body of a person or animal may be regarded as a measurement target, or a part thereof (for example, a face, a torso, etc.) may be regarded as a measurement target. The “body temperature measurement site” refers to a region suitable for measuring body temperature, and is determined in advance according to the type of measurement target. For example, when the measurement target is a human face, a cheek or forehead may be determined as a body temperature measurement site. The body temperature measurement site is not limited to one location, and may be a plurality of locations such as both cheeks and forehead. Noise can be reduced if measurements are taken at multiple locations and averaged.

According to the measurement object determining means, in order to recognize the measurement object by image recognition, the measurement object (human face, etc.) and its constituent elements (eyes, mouth, nose, eyebrows, etc.) and the characteristics, meanings and You can know the spatial positional relationship. Then, by using such a recognition result, it is possible to accurately specify the position of the body temperature measurement site (such as the position of the cheek or forehead) in the measurement target.

  Further, according to the image recognition, it is possible to recognize obstacle elements such as glasses, hair, a mask, a hat, and the like that are obstacles in body temperature measurement. When such an obstacle element exists, it is preferable to set the body temperature measurement site at a position avoiding the obstacle element. Thereby, erroneous measurement and measurement error can be avoided.

  The automatic temperature measuring device is based on the measurement visual field control means for controlling the measurement visual field of the infrared detection means so that the infrared detection means detects the infrared rays emitted from the body temperature measurement site, and the detection value of the infrared detection means. Body temperature calculating means for calculating the body temperature of the measurement object.

  According to the automatic temperature measuring device having the above configuration, the imaging unit captures an image, the measurement target determining unit recognizes the measurement target from the image by image recognition, and then calculates the position of the body temperature measurement site in the measurement target. The measurement visual field control means aligns the measurement visual field of the infrared detection means with the body temperature measurement part, the infrared detection means detects the infrared rays emitted from the body temperature measurement part, and the body temperature calculation means determines the object to be measured based on the detection value of the infrared detection means. Body temperature can be calculated. Thereby, it becomes possible to automatically measure the body temperature of the measurement target existing in the imaging area in a non-contact manner. Moreover, since the body temperature measurement site can be specified by image recognition, the measurement field of view of the infrared detection means can be accurately positioned at the body temperature measurement site, and variations in measurement sites and erroneous measurements are reduced, and the reliability of measurement results is improved. improves.

  Various specific configurations of the measurement visual field control means are assumed. Measurement field control items include the direction of the measurement field and the size of the measurement field.

  For example, the measurement visual field control means emits an invisible light beam in a wavelength range within the sensitivity range of the imaging means and outside the sensitivity range of the infrared detection means in a direction that coincides with the optical axis of the infrared detection means, and an image And an azimuth control means for controlling the direction of the measurement visual field of the infrared detection means so that the irradiation point of the invisible light beam in the body coincides with the body temperature measurement site.

  Since the invisible light beam is detected by the imaging means, the irradiation points of the invisible light beam appear in spots in the image. This irradiation point corresponds to the center of the measurement visual field of the infrared detecting means. Therefore, based on the relative positional relationship between the irradiation point and the body temperature measurement site in the image, it is possible to calculate the control amount for which direction and how much the direction of the measurement visual field of the infrared detection means should be moved. And an azimuth | direction control means moves an infrared rays detection means according to this control amount, and exact alignment with a measurement visual field and a body temperature measurement site | part can be performed. That is, it can be said that this invisible light beam serves as a pointer for adjusting the aim of the infrared detection means (the direction of the measurement visual field).

  At this time, since the invisible light beam cannot be detected by the human naked eye, it does not give a sense of discomfort or discomfort to the person to be measured or those around him. Further, since the invisible light beam is not sensed by the infrared detecting means, it does not affect the body temperature measurement. Note that near-infrared light, near-ultraviolet light, or the like can be used as the wavelength region of the invisible light beam.

  The optical axis of the imaging unit and the infrared detection unit are configured to coincide with each other (that is, the directions of the imaging unit and the infrared detection unit are interlocked), and the measurement visual field control unit matches the body temperature measurement site with the center of the image. It is also preferable to employ a configuration having azimuth control means for controlling the direction of the measurement visual field of the infrared detection means.

  If the optical axes of the image pickup means and the infrared detection means coincide with each other, the center of the image and the center of the measurement visual field of the infrared detection means always coincide with each other. Therefore, it is possible to accurately align the measurement visual field and the body temperature measurement site based on the relative positional relationship between the image center and the body temperature measurement site without providing a pointer for aiming separately.

  By the way, since the body surface temperature to be measured is not uniform, it is desirable that the size of the measurement visual field is small to some extent in order to accurately measure the temperature of the body temperature measurement site. Furthermore, it is desirable that the size is substantially constant regardless of the measurement distance (the distance from the infrared detection means to the body temperature measurement site). This is because if the size of the measurement field of view depends on the measurement distance, the measurement results may vary.

  Therefore, the measurement visual field control means is a distance calculation means for obtaining the distance from the infrared detection means to the body temperature measurement site, and the viewing angle of the infrared detection means is set so that the size of the measurement visual field at the distance becomes a predetermined size. It is preferable to adopt a configuration having a viewing angle control means for controlling.

  Thereby, the viewing angle of the infrared detecting means is variably controlled in accordance with the measurement distance, and the size of the measurement field is always kept at a predetermined size. Therefore, a highly reliable measurement result can be obtained regardless of the measurement distance.

  Here, the “predetermined size” may be appropriately set according to the type of measurement object and body temperature measurement site. Basically, a smaller measurement field of view is more suitable for body temperature measurement, but if it is too small, it is more susceptible to noise. Therefore, it is preferable to preliminarily define the size of the measurement visual field suitable for the body temperature measurement in consideration of the body surface temperature distribution to be measured, the area of the body temperature measurement site, the influence of noise, and the like.

  In addition to the above, the configuration for reducing the variation in the measurement result due to the measurement distance adopts a configuration for narrowing the infrared detection means or a configuration for correcting the influence of the measurement distance by computer processing. Also good.

  As the distance calculation means, a distance sensor that measures the measurement distance can be used. In this case, there is an advantage that an accurate measurement distance can be obtained. Or the structure which estimates a distance based on the magnitude | size of the measuring object in an image is also preferable. In this case, there is an advantage that a special configuration such as a distance sensor is unnecessary, and the configuration can be simplified and the cost can be reduced.

  It is also preferable that the body temperature calculation means calculates the body temperature from the detection value of the infrared detection means and the distance from the infrared detection means to the body temperature measurement site. Thereby, the attenuation of infrared rays depending on the measurement distance can be corrected.

  It is also preferable that the body temperature calculation means outputs information including the calculation result of the body temperature and the recognition result by the measurement target determination means as the temperature measurement result. Thereby, even when the body temperature is automatically measured from a large number of measurement objects, it becomes easy to take correspondence between the measurement objects and the measurement results.

  In addition, a database in which individual (individual) information to be measured is registered is provided, the measurement target determining unit identifies the individual (individual) based on the recognition result, and the body temperature calculating unit displays the calculation result of the body temperature for the individual ( (Individual) It is also preferable to write in the database in association with information or images. As a result, the management of the temperature measurement results becomes easy, and it is possible to use the system in which the body temperature is periodically measured for one measurement object, and the body temperature fluctuation is automatically recorded.

It is also preferable to have an illuminating unit that emits invisible light in a wavelength region within the sensitivity range of the imaging unit and outside the sensitivity range of the infrared detection unit toward the imaging area of the imaging unit. Since this illumination light is invisible light, body temperature can be measured without being detected by the measurement object at night or in a dark place. In addition, since the illumination light is not sensed by the infrared detection means, the measurement result is not affected.

  In addition, this invention can be grasped | ascertained as an automatic temperature measuring device which has at least one part of the said means. Moreover, this invention can also be grasped | ascertained as an automatic temperature measuring method including at least one part of the said process, or a program for implement | achieving this method. Each of the above means and processes can be combined with each other as much as possible to constitute the present invention.

  According to the present invention, the body temperature of a person or animal can be automatically measured without contact.

  Exemplary embodiments of the present invention will be described in detail below with reference to the drawings.

<First Embodiment>
The main components of the automatic temperature measuring device according to the first embodiment of the present invention are shown in FIG. The automatic thermometer 1 automatically measures the body temperature of a measurement target (human or animal) in a non-contact manner. FIG. 1 shows a state in which the body temperature of a patient waiting for medical care is automatically measured in a waiting room of a hospital.

  The automatic temperature measuring device 1 includes an infrared detection unit 10, an image input unit 20, an orientation adjustment unit 30 for adjusting the orientation of both units, and a computer 40 for automatically controlling these components. Composed.

  The main components including the infrared detection unit 10 and the image input unit 20 will be described with reference to the cross-sectional views of FIGS. 1 and 2.

(Infrared detection unit)
The infrared detection unit 10 includes a lens unit 11, a far infrared sensor 12, a near infrared laser 13, a mirror 14, and a half mirror 15 arranged as shown in FIG.

  The far infrared sensor 12 is composed of a single element. The far-infrared sensor 12 has sensitivity only to far-infrared rays and does not feel near-infrared rays. Far-infrared is infrared radiation in the wavelength range of about 4 μm to 1 mm (IEC60841), but the sensitivity range of the far-infrared sensor 12 is the wavelength of infrared radiation from the body surface of a measurement target (such as a human face). It is enough to cover the area. In the present embodiment, the far infrared sensor 12 having a sensitivity range of about 8.0 μm to 13 μm is used as a wavelength range suitable for body temperature measurement.

  As the near-infrared laser 13, a laser that emits near-infrared light in the form of a beam is used. Near-infrared radiation is infrared radiation in the wavelength range of 0.78 μm to 2.0 μm (IEC60841), but the wavelength range of the near-infrared laser 13 is within the sensitivity range of the image sensor of the image input unit 20 and is far-infrared. An invisible region outside the sensitivity region of the sensor 12 is used. In this embodiment, a near infrared ray of about 1.0 μm is used. The near-infrared laser 13 corresponds to the invisible light source of the present invention, and beam-shaped near-infrared light (hereinafter referred to as “near-infrared light beam”) corresponds to the invisible light beam of the present invention.

The optical system for the far infrared sensor 12 includes a lens unit 11, a half mirror 15, and
It is composed of a mirror 14. The lens unit 11 includes an optical zoom mechanism. That is, the lens unit 11 has at least two lenses, and the magnification (viewing angle) can be changed by changing the distance between the lenses. The half mirror 15 is configured to reflect light incident from the lens unit 11 side and transmit light incident from the opposite side. The mirror 14 is arranged so that the light incident on the lens unit 11 is focused on the far-infrared sensor 12 after being reflected by the half mirror 15. This optical system and the far-infrared sensor 12 correspond to the infrared detecting means of the present invention.

  The near-infrared light beam emitted from the near-infrared laser 13 passes through the half mirror 15 and enters the lens unit 11 and is emitted to the outside. Here, the optical axis of the near-infrared light beam is made to coincide with the optical axis of the lens unit 11.

(Image input unit)
The image input unit 20 is configured by arranging a lens unit 21 and an image sensor 22 as shown in FIG. That is, these components are arranged so that light from the outside world forms an image on the image sensor 22 by the lens unit 21. This image input unit 20 corresponds to the imaging means of the present invention. The imaging unit may be color or monochrome, but here, monochrome imaging unit is used.

  As the image sensor 22, a Si-based CCD or CMOS image sensor generally used for digital cameras and mobile phones can be used. However, it is assumed that a filter that cuts near infrared light is not inserted in the optical path from the lens unit 21 to the image sensor 22 and that the image sensor 22 can input images of visible light and near infrared light.

  Here, the purpose of making the imaging device 22 sensitive to near-infrared light is to acquire an irradiation point of the near-infrared light beam emitted from the near-infrared laser 13 as an image. Therefore, it is sufficient that the sensitivity range of the image sensor 22 includes at least the wavelength of the near-infrared light beam (about 1.0 μm in the present embodiment).

(Direction adjustment unit)
Both the infrared detection unit 10 and the image input unit 20 are supported by the orientation adjustment unit 30. The azimuth adjustment unit 30 includes a support frame 31 to which the infrared detection unit 10 and the image input unit 20 are fixed, and two rotation mechanisms 32 that allow the support frame 31 to rotate (in FIG. 2, one rotation mechanism). 32 only). The rotation axes of the two rotation mechanisms 32 are orthogonal to each other. One rotation mechanism 32 rotates the support frame 31 in the horizontal plane, and the other rotation mechanism 32 rotates the support frame 31 in the vertical plane. With such a mechanism, the directions of the measurement visual field of the infrared detection unit 10 and the imaging visual field of the image input unit 20 can be freely moved in the horizontal direction and the vertical direction in conjunction with each other. The optical axis A1 of the infrared detection unit 10 and the optical axis A2 of the image input unit 20 are provided substantially in parallel.

  The three components are disposed inside the hemispherical cover 33. The cover 33 is made of a material that transmits infrared light in the infrared detection unit 10 and a material that transmits visible light to near infrared light in the image input unit 20.

(Computer)
The computer 40 is configured by a general-purpose personal computer including a CPU (Central Processing Unit), a main storage device (memory), an auxiliary storage device (such as a hard disk), and the like. The computer 40 and the above three components are connected by wire or wirelessly.

  The auxiliary storage device of the computer 40 includes a program for controlling the zoom of the image input unit 20, a program for extracting a person and face area from an image captured by the image input unit 20, and identifying an individual by recognizing a face Program for controlling the orientation adjustment unit 30 (that is, the direction of the infrared detection unit 10 and the image input unit 20), a program for controlling the zoom of the infrared detection unit 10, and an output (detection) of the infrared detection unit 10 A program for calculating the body temperature based on the value), a program for controlling the near-infrared laser 13, and the like are stored. When the automatic temperature measuring device 1 is activated, these programs are appropriately read from the auxiliary storage device to the main storage device and executed by the CPU, thereby realizing various functions related to the automatic temperature detection processing.

  The auxiliary storage device stores a patient's electronic medical record (database). In this electronic medical record, patient personal information (including face information) and temperature measurement results are stored in association with medical record information such as medical history and examination results.

  In the present embodiment, the measurement object determining means and the body temperature calculating means of the present invention are realized by a computer program, and the measurement visual field control means of the present invention is realized by the cooperation of the azimuth adjusting unit 30 and the computer program. It has been realized.

(Automatic temperature measurement)
Next, the operation of the automatic temperature measuring device will be described with reference to FIGS.

  In step S1, the image input unit 20 captures an image of the imaging area. The input image information is sent to the computer 40, and the person to be measured and the face area of the person are recognized by image recognition.

  In step S2, the computer 40 calculates the center position of the face portion from the recognition result obtained in step S1, and the direction and amount of movement of the imaging field of view from the relative position between the center position of the face portion and the center point of the image. Ask for. Then, the computer 40 sends a control signal to the azimuth adjustment unit 30 to control the azimuth of the image input unit 20 (and the infrared detection unit 10) so that the face portion is at the center of the imaging field.

  In step S3, the computer 40 sends a control signal to the image input unit 20, and adjusts the zoom magnification of the lens unit 21 so that the face portion is projected with a predetermined target size. Then, the computer 40 calculates the distance (measurement distance) from the apparatus 1 to the measurement subject's face based on the zoom magnification when the face portion in the image reaches the target size. This is based on the knowledge that the size of the human face is generally constant. This function of the computer 40 corresponds to the distance calculating means of the present invention.

  Note that there is a slight difference in the average face size between adults and children, or men and women, so the measurement distance can be corrected according to the recognition result of face image recognition (age group and gender) It is also preferable to change the target size for zoom adjustment.

  In step S <b> 4, the computer 40 recognizes the face part to be measured by face image recognition from the image captured at the target size. Compared with the process of step S2, the more accurate and detailed recognition result can be obtained because the size of the face portion is larger. According to facial image recognition, it is possible to recognize items such as contours, face orientation, position and size of each facial organ, age group, gender, presence or absence of glasses and masks (however, all items are recognized) do not have to.).

And the computer 40 calculates | requires the position of the body temperature measurement site | part in a face based on these recognition results. For example, when the body temperature measurement site is a forehead, the position of the forehead may be specified from the positional relationship with facial organs such as eyes, nose, mouth, and eyebrows. At this time, when a part of the forehead is hidden by glasses, a hat, hair, etc., the body temperature measurement site is set at a position avoiding that part, that is, a position where the skin is exposed. Thereby, erroneous measurement and measurement error can be avoided. Such a function of step S4 corresponds to the measuring object determining means of the present invention.

  Furthermore, in this embodiment, the computer 40 refers to the electronic medical record stored in the auxiliary storage device, and collates the recognition result obtained by the face image recognition with the patient's face information registered in the electronic medical record. Identify individuals.

  In step S <b> 5, the computer 40 sends a control signal to the near infrared laser 13 to emit a near infrared light beam from the near infrared laser 13. Then, an irradiation point of the near-infrared light beam, that is, a narrow region that reflects the near-infrared light (hereinafter, this region is referred to as “near-infrared light spot”) appears in the image. Since the optical axis of the near-infrared light beam coincides with the optical axis of the lens unit 11, the near-infrared light spot corresponds to the center of the measurement visual field of the infrared detection unit 10.

  In step S6, the computer 40 receives a face image including a near-infrared light spot from the image input unit 20, and compares the position of the near-infrared light spot in the image with the position of the body temperature measurement site obtained in step S4. .

  When the near-infrared light spot and the body temperature measurement site do not match (step S7; no), the moving direction and the moving amount of the measurement visual field are obtained from the relative positions of both. In step S8, the computer 40 sends a control signal to the azimuth adjustment unit 30 to control the azimuth of the infrared detection unit 10 and the image input unit 20 so that the near-infrared light spot coincides with the body temperature measurement site. Thereafter, the processes in steps S5 to S8 are repeated until the near-infrared light spot and the body temperature measurement site match, and if they match (step S7; yes), the process proceeds to step S9.

  In step S9, the computer 40 sends a control signal to the infrared detection unit 10 in accordance with the measurement distance obtained in step S3, so that the size of the measurement visual field at the measurement distance becomes a predetermined size. Adjust the zoom magnification (viewing angle). In the present embodiment, the size of the measurement visual field is about 2 to 3 cm in diameter. Thereby, only the far infrared rays radiated from the region having a diameter of 2 to 3 cm of the body temperature measurement site are incident on the infrared detection unit 10. The functions of steps S5 to S9 described above correspond to the measurement visual field control means of the present invention.

  In step S10, the far-infrared sensor 12 detects the intensity of the far-infrared emitted from the body temperature measurement site. This detected value is sent to the computer 40.

  In step S11, the computer 40 calculates the body temperature from the detection value obtained in step S10. Note that isotropically emitted light attenuates in inverse proportion to the square of the distance. Therefore, in the present embodiment, the intensity decrease due to such attenuation is corrected in consideration of the measurement distance obtained in step S3. Thereby, the reliability of the body temperature calculation result can be improved.

  In step S12, the computer 40 displays the calculation result of the body temperature on the display or writes it on the electronic medical record. In addition, when the measurement subject is not registered in the electronic medical record, a new data record for the first visit patient is created, and the calculation result of the body temperature and the face information (face image, recognition result in step S4, etc.) Should be written as the temperature measurement result. Thereby, even when the personal information cannot be specified, it is possible to specify which patient has the temperature measurement result by referring to the face information.

  According to this embodiment described above, it becomes possible to automatically measure the temperature of a plurality of people in a non-contact manner at a place where a large number of people gather. Compared to measuring the temperature of each person individually, the test efficiency is greatly improved.

  Moreover, since the body temperature measurement site such as the forehead can be specified by the face image recognition, the measurement visual field of the infrared detection unit 10 can be accurately positioned at the body temperature measurement site, and the measurement location variation and erroneous measurement can be reduced. The reliability of the result is improved.

  In addition, since the directions of the infrared detection unit 10 and the image input unit 20 can be variably controlled, it is possible to measure the body temperature of a person existing in an arbitrary place over a wide range.

  In addition, since the single-element far-infrared sensor 12 is used in the present embodiment, the manufacturing cost can be reduced as compared with a conventional non-contact two-dimensional radiation thermometer having a plurality of infrared sensors.

  Furthermore, since the patient can be identified by facial image recognition, the temperature measurement result can be sent to the intended medical department along with the chart information and personal information via the LAN. This has the effect of reducing waiting time for patients and reducing labor costs for hospitals.

<Second Embodiment>
In the first embodiment, the direction of the measurement visual field is controlled so that the irradiation point of the near-infrared light beam in the image coincides with the body temperature measurement site. However, the method for matching the measurement field of view with the body temperature measurement site is limited to this. Absent. In the second embodiment of the present invention, a configuration in which the optical axis of the imaging means and the optical axis of the infrared detection means are matched, and the orientation of the measurement visual field is adjusted by making the body temperature measurement site coincide with the center of the image. Do.

(Device configuration)
FIG. 4 shows a configuration of an automatic temperature measuring device according to the second embodiment. The figure (a) shows the external appearance of the automatic temperature measuring device 2, (b) has shown sectional drawing seen from the right side of (a). Hereinafter, a description will be given centering on the configuration specific to the present embodiment, the same reference numerals are given to the same portions as those of the first embodiment, and detailed description thereof will be omitted.

  The automatic temperature measuring device 2 includes an image input / infrared detection unit 50 and an azimuth adjustment unit 30 for adjusting the azimuth thereof. These components are controlled by the computer 40 (not shown in FIG. 4), as in the first embodiment.

  The image input / infrared detection unit 50 is configured by disposing the far-infrared sensor 12, the imaging device 22, the far-infrared light lens unit 51, the visible light lens unit 52, and the mirror 53 as shown in FIG. Among these, the far-infrared sensor 12 and the far-infrared light lens unit 51 correspond to the infrared detection means of the present invention, and the imaging element 22, the visible light lens unit 52, and the mirror 53 correspond to the imaging means of the present invention. To do.

  As shown in the perspective view of FIG. 5, the far-infrared light lens unit 51 includes two lenses 51a and 51b, and the magnification can be changed by changing the distance between the lenses. The far-infrared light incident on the far-infrared light lens unit 51 is focused on the far-infrared sensor 12. The lens 51a is a combination of two semicircular lens elements, and the two lens elements are spaced apart from each other when viewed from the front. The other lens 51b has the same configuration.

A visible light lens unit 52 is arranged in the center of the separated portion of the far infrared light lens unit 51. The visible light lens unit 52 and the mirror 53 constitute an optical system of the image sensor 22. In other words, the light incident on the visible light lens unit 52 from the outside is arranged on the image sensor 22 after being reflected by the mirror 53. The visible light lens unit 52 includes an optical zoom mechanism as in the lens unit 21 of the first embodiment.

  In the present embodiment, the optical axis of the far-infrared light lens unit 51 and the optical axis of the visible light lens unit 52 coincide. That is, the center of the measurement visual field and the center of the imaging visual field always coincide.

  The image input / infrared detection unit 50 is disposed inside a substantially spherical cover. This cover includes a far-infrared light cover 34 that does not transmit visible light but transmits far-infrared light, and a visible-light cover 35 that does not transmit far-infrared light but transmits visible light. The visible light cover 35 is disposed so as to cover the separated portion of the far-infrared light lens unit 51. Thereby, it is possible to prevent the far-infrared light from entering the separated portion of the far-infrared light lens unit 51.

  The azimuth adjustment unit 30 includes two rotation mechanisms 32a and 32b. The image input / infrared detection unit 50 is supported by a rotation mechanism 32a so as to be rotatable in a vertical plane. Further, the image input / infrared detection unit 50 and the cover are supported rotatably by a rotation mechanism 32b in a horizontal plane. With such a mechanism, the direction of the image input / infrared detection unit 50 can be freely moved in the horizontal direction and the vertical direction.

(Automatic temperature measurement)
Next, operation | movement of the automatic temperature measuring apparatus 2 of this embodiment is demonstrated.

  In the automatic temperature measuring apparatus 2, when an image of the imaging area is captured, the computer 40 recognizes the face portion of the measurement subject by facial image recognition. And the position of the body temperature measurement site | part in a face is calculated | required similarly to 1st Embodiment.

  Next, the computer 40 calculates the moving direction and moving amount of the image input / infrared detection unit 50 based on the relative position between the body temperature measurement site and the center of the image. Then, the computer 40 sends a control signal to the azimuth adjustment unit 30 to control the azimuth of the image input / infrared detection unit 50 so that the body temperature measurement site coincides with the center of the image.

  Thereafter, the computer 40 controls the zoom magnification of the far-infrared light lens unit 51 according to the measurement distance, sets the size of the measurement field of view to a predetermined size, and emits the far-infrared radiation from the body temperature measurement site. Measure the strength. The subsequent processing is the same as in the first embodiment.

  Also with the configuration of the present embodiment described above, the same operational effects as those of the first embodiment can be obtained.

  In addition, in this embodiment, since the optical axes of the imaging unit and the infrared detection unit are matched, the configuration and control for positioning the measurement visual field becomes extremely simple.

  In addition, since the far-infrared light lens unit 51 is provided with a separation portion at the center and the visible light lens unit 52 is disposed therebetween, the apparatus can be miniaturized.

<Third Embodiment>
FIG. 6 shows the configuration of an automatic temperature measuring device according to the third embodiment of the present invention. The figure (a) shows the external appearance of the automatic temperature measuring device 3, (b) has shown sectional drawing seen from the right side of (a).

  The automatic temperature measuring device 3 of the present embodiment has a configuration in which the far-infrared light lens unit 54 is configured by combining two circular lenses 54a and 54b, and uses a small visible light camera 55 for far-infrared light as an imaging means. The lens unit 54 is characterized in that it is arranged at the center of the front side (incident side) of the lens unit 54, and the other configuration is the same as that of the second embodiment.

  As the visible light camera 55, it is preferable to use a camera in which an optical system and an image pickup device are integrated, as incorporated in a mobile phone or a small digital camera. This optical system also has a zoom mechanism.

  Even with such a configuration, it is possible to obtain the same operational effects as those of the second embodiment.

<Fourth Embodiment>
In relation to face image input and infrared detection, the lighting situation in the scene of use is important. For example, visible light cannot be used to input images of patients or care recipients at night.

  Therefore, in the automatic temperature measuring device 4 of the present embodiment, a lighting device 60 for nighttime measurement is provided as shown in FIG. The illumination device 60 is an illumination unit that emits invisible light toward the imaging area of the image input unit 20. As the invisible light, light having a wavelength within the sensitivity range of the image sensor 22 of the image input unit 20 and outside the sensitivity range of the far infrared sensor 12 of the infrared detection unit 10 is used. In the present embodiment, near infrared light is used.

  The specific structural example of this kind of illuminating device 60 is given. As the illuminating device 60, a plurality of light emitting diodes (LEDs) that output near-infrared rays are arranged in an array, and a combination of diffusion sheets for diffusing light on the top to obtain a uniform illuminance distribution is used. Can do. Here, the reason why the wavelength is near infrared is to completely eliminate the influence on the temperature measurement due to the reflection of illumination light by separating it from the far infrared used for body temperature measurement. Further, the illumination device 60 may be turned on only when measuring the body temperature. Therefore, it is desirable to use an LED having a characteristic that the range of the emission wavelength is narrow and a stable output can be obtained in a short time. Since lighting is short, power consumption is not a big problem.

  According to this embodiment, body temperature can be measured at night or in the dark without being sensed by the patient or care recipient.

  While the present invention has been described in detail with reference to a plurality of embodiments, these embodiments are merely examples of the present invention. The scope of the present invention is not limited to the above embodiment, and various modifications can be made within the scope of the technical idea.

  For example, although the single-element far-infrared sensor is used in the above-described embodiment, a far-infrared image sensor in which a plurality of elements are two-dimensionally arranged can be used as the infrared detection means. In the case of a far-infrared image sensor, the temperature distribution at the body temperature measurement site can be detected. If the detection values of the sensors are integrated, a value similar to the detection value in the above embodiment can be obtained. At this time, if the detection value of each sensor is integrated after applying a noise removal filter, the reliability of the detection value can be improved.

  Moreover, although the example which made the face part of a person the measurement object was given in the said embodiment, the measurement object may be another part or the whole body, and may be not only a person but an animal. In the case of animals, facial image recognition is not very effective, but it is preferable to recognize components of the entire body.

  In the above embodiment, the measurement distance is calculated from the zoom magnification. However, a distance sensor for measuring the measurement distance may be added. As the distance sensor, a sensor that determines the distance based on the principle of triangulation using ultrasonic waves, near infrared light, or the like can be used. Alternatively, a reference light source that emits near infrared rays may be placed in the imaging area and used as a reference for distance calculation. That is, since the distance between the place where the reference light source is placed and the image input unit and the intensity of light emitted from the reference light source are known, the output of the infrared detection unit may be calibrated based on these.

  In the above embodiment, the attenuation of far-infrared light is corrected according to the measurement distance. However, a standard light source having a known temperature is arranged in the imaging area, and the detection value by the radiated light from the standard light source is set. As a reference, it is also preferable to convert the detected value of far-infrared light emitted from the measurement object into body temperature.

  Below, an example of the application field of the automatic temperature measuring apparatus and automatic temperature measuring method of this invention is described.

(1) Automatic detection system for infectious disease infected persons Early detection of infected persons is desired as a countermeasure against infectious diseases represented by SARS. As a measure against the water at the airport, the video of measuring the body temperature of each person using a thermometer inserted into the ear is new to memory. However, with conventional thermometers, the measurement time is long, and in many cases it is necessary to contact the subject, so it was necessary to measure each individual person.

  Therefore, a system to which the present invention is applied may be installed in a place where an unspecified number of people gather such as an airport, and the body temperature of each person may be automatically measured. In this case, instead of recognizing an individual by face, the face of a person determined to be abnormal by screening may be registered together with body temperature data. Thereby, compared with the conventional method which measures each person's body temperature individually, the screening of an infected person, such as SARS, can be carried out efficiently.

(2) Condition monitoring system Improvement of medical and nursing care services is desired. In other words, in order to maintain and improve a rich and happy life, it is urgently necessary to improve the quality of medical and nursing care services and to increase costs.

  For example, at present, the shortage of nurses working in nursing care facilities and palliative care wards is a problem. Especially at night, the number of nurses is reduced, and there is a risk that the response to sudden changes in patient conditions may be delayed at these facilities. Currently, a buzzer is provided on the side of the bed for the patient to call a nurse, but depending on the patient's condition, the buzzer may not be able to be pushed by himself. Therefore, a system that automatically and continuously monitors the condition of a person is desired.

  In addition, accidents caused by patient misuse have become a problem in the medical field. It is difficult to eradicate human accidents through measures such as thorough contact by the parties and name tags on patients. Therefore, it is desirable to introduce a system that automatically identifies individuals at the medical site.

  Therefore, if a system to which the present invention is applied is introduced into a hospital or a care facility, it becomes easy to continuously monitor the temperature of a specific individual such as an inpatient or a care recipient for 24 hours. Body temperature is the most common index that reflects a person's condition. Therefore, if a warning is sent to a nurse or doctor when the system detects changes in the patient's body temperature, a sudden change in condition can be handled quickly.

Also, if a patient is specified by image recognition (face recognition) and body temperature fluctuation information is recorded in the patient's electronic medical record, there is no mistake in the patient and medical record, and the safety of medical care and nursing care is improved. In addition, there is a possibility that the body temperature fluctuation information can be effectively used for treatment and nursing care, and new knowledge about a precursor of a lesion can be obtained.

  Furthermore, by arranging a plurality of automatic temperature measuring devices in the facility so that they can cooperate with each other, it is possible to track when an individual moves inside the facility. In this case, since the person is specified by the face wherever he goes in the facility, personal data can be easily retrieved via the LAN. Therefore, it is good news for facilities that suffer from the shortage of nurses.

(3) Automatic temperature measurement system for outpatients The length of waiting time when visiting a hospital for general outpatient examinations is inconvenient for users. In the case of outpatients, examinations are generally conducted in the order received, but some diseases with high fever require immediate attention.

  Therefore, if a system to which the present invention is applied is installed in a waiting room of a hospital, the body temperature of many outpatients can be automatically measured and recorded together with personal information (face images and electronic medical records) of the patients. In addition, it is possible to expect a reduction in waiting time for outpatient examinations, and it is also possible to take measures such as preferentially examining high fever patients.

(4) Livestock plague inspection system In recent years, food safety has become a major social problem due to the epidemic of livestock plague such as bovine spongiform encephalopathy (BSE) and avian influenza. However, large-scale livestock farms raise hundreds to thousands of livestock, and enormous costs and labor are required to perform a full head test for epidemics.

  Therefore, if a system to which the present invention is applied is installed on a farm, body temperature fluctuations of livestock can be automatically monitored over 24 hours, and abnormal livestock infected with the plague can be detected at an early stage. At this time, if the tag or mark attached to the livestock is captured as an image and recorded together with the body temperature fluctuation information, the sick livestock can be easily identified.

It is a figure showing the whole automatic temperature measuring device composition concerning a 1st embodiment. It is a figure which shows the structure of the image input unit and infrared detection unit in the automatic temperature measuring device of FIG. It is a flowchart which shows the flow of the automatic temperature detection process in the automatic temperature detection apparatus of FIG. It is a figure which shows the structure of the automatic temperature measuring apparatus which concerns on 2nd Embodiment. It is a perspective view which shows the structure of the lens unit for far-infrared light in the automatic temperature measuring device of FIG. It is a figure which shows the structure of the automatic temperature measuring apparatus which concerns on 3rd Embodiment. It is a figure which shows the whole structure of the automatic temperature measuring apparatus which concerns on 4th Embodiment.

Explanation of symbols

1, 2, 3, 4 Automatic temperature detector 10 Infrared detection unit 11 Lens unit 12 Far infrared sensor 13 Near infrared laser 14 Mirror 15 Half mirror 20 Image input unit 21 Lens unit 21 Optical system 22 Image sensor 30 Orientation adjustment unit 31 Support frame 32 Rotating Mechanism 32a, 32b Rotating Mechanism 33 Cover 34 Far Infrared Light Cover 35 Visible Light Cover 40 Computer 50 Image Input / Infrared Detection Unit 51 Far Infrared Light Lens Unit 51a, 51b Lens 52 Visible Light Lens Unit 53 Mirror 54 Lens unit for far infrared light 54a, 54b Circular lens 55 Visible light camera 60 Illuminating device A1 Optical axis of infrared detection unit A2 Optical axis of image input unit

Claims (9)

Imaging means;
Infrared detection means;
A measurement object determining means for recognizing a measurement object by image recognition from an image captured by the imaging means and obtaining a position of a body temperature measurement site in the measurement object;
A measurement visual field control means for controlling the measurement visual field of the infrared detection means so that the infrared detection means detects infrared radiation emitted from the body temperature measurement site;
Body temperature calculating means for calculating the body temperature of the measurement object based on the detection value of the infrared detecting means,
An automatic thermometer equipped with. The measurement visual field control means is
An invisible light source that emits an invisible light beam in a wavelength range within the sensitivity range of the imaging means and outside the sensitivity range of the infrared detection means in a direction that coincides with the optical axis of the infrared detection means;
Direction control means for controlling the direction of the measurement visual field of the infrared detection means so that the irradiation point of the invisible light beam in the image coincides with the body temperature measurement site;
The automatic temperature measuring device according to claim 1, comprising: The optical axes of the imaging means and infrared detection means match,
2. The automatic temperature measuring device according to claim 1, wherein the measurement visual field control means includes an azimuth control means for controlling the direction of the measurement visual field of the infrared detection means so that the body temperature measurement site coincides with the center of the image. The measurement visual field control means is
Distance calculating means for obtaining the distance from the infrared detecting means to the body temperature measurement site;
Viewing angle control means for controlling the viewing angle of the infrared detection means so that the size of the measurement visual field at that distance becomes a predetermined size;
The automatic temperature measuring device according to any one of claims 1 to 3, further comprising:   The automatic temperature measuring device according to claim 4, wherein the body temperature calculation means calculates the body temperature from the detection value of the infrared detection means and the distance from the infrared detection means to the body temperature measurement site. The measurement target is the human face,
The automatic temperature measuring device according to any one of claims 1 to 5, wherein the measurement target determining means recognizes a face portion included in the image by face image recognition.   The automatic temperature measuring device according to any one of claims 1 to 6, wherein the infrared detecting means comprises a single element infrared sensor.   The automatic lighting device according to any one of claims 1 to 7, further comprising an illuminating unit that emits invisible light in a wavelength region within the sensitivity range of the imaging unit and outside the sensitivity range of the infrared detection unit toward the imaging area of the imaging unit. Thermometer. Capturing an image with an imaging means;
Recognizing a measurement object from the image by image recognition;
Calculating the position of the body temperature measurement site in the measurement object;
A step of matching the measurement visual field of the infrared detection means with the body temperature measurement site;
Detecting infrared rays emitted from the body temperature measurement site by infrared detection means;
Calculating the body temperature of the measurement object based on the detection value of the infrared detection means;
Automatic temperature measuring method including.

Images