SE545401C2 - Method and device for detecting a temperature of a person capturing a visual and a thermal image - Google Patents

Method and device for detecting a temperature of a person capturing a visual and a thermal image

Info

Publication number
SE545401C2
SE545401C2 SE2051080A SE2051080A SE545401C2 SE 545401 C2 SE545401 C2 SE 545401C2 SE 2051080 A SE2051080 A SE 2051080A SE 2051080 A SE2051080 A SE 2051080A SE 545401 C2 SE545401 C2 SE 545401C2
Authority
SE
Sweden
Prior art keywords
image
head
temperature
person
detecting
Prior art date
Application number
SE2051080A
Other languages
Swedish (sv)
Other versions
SE2051080A1 (en
Inventor
Agnér Christian Gál
Graham Mccarthy
Torbjörn Nyman
Original Assignee
Bmp Innovation Ab
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bmp Innovation Ab filed Critical Bmp Innovation Ab
Priority to SE2051080A priority Critical patent/SE545401C2/en
Publication of SE2051080A1 publication Critical patent/SE2051080A1/en
Publication of SE545401C2 publication Critical patent/SE545401C2/en

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/01Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • A61B5/015By temperature mapping of body part
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0022Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
    • G01J5/0025Living bodies
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/48Thermography; Techniques using wholly visual means
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01KMEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K1/00Details of thermometers not specially adapted for particular types of thermometer
    • G01K1/02Means for indicating or recording specially adapted for thermometers
    • G01K1/024Means for indicating or recording specially adapted for thermometers for remote indication
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077Imaging

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Radiation Pyrometers (AREA)
  • Image Processing (AREA)

Abstract

Disclosed is a method for detecting the temperature of a subject. The method comprises capturing (202) a visual image of an area with a visual camera and capturing (204) a thermal image of the same area with a thermal imaging camera at substantially the same point in time as the visual image is captured, thus acquiring a pair of images. The method further comprises detecting (206) a face of the subject in the visual image, and detecting (208) a temperature reading in the thermal image. The method further comprises selecting (210) a subpart of the thermal image, detecting (212) a maximum temperature in the subpart of the thermal image, and determining (214) the temperature of the subject based on the detected maximum temperature in the subpart of the thermal image.

Description

Technical field id="p-1" id="p-1"
[0001] The present disclosure relates generally to methods, systems and devices for detecting the temperature of a subject.
Background id="p-2" id="p-2"
[0002] Today, there are systems and methods available for detecting the temperature of subjects. However, these are generally intrusive, and requires relatively much time before an accurate assessment can be made. These problems, and others, results in it being very difficult to realize temperature detecting systems as automated or semi-automated systems. id="p-3" id="p-3"
[0003] lt has become increasingly important to be able to screen people and determine whether they are likely to have a body temperature above a certain threshold, for various reasons. One of them is that an elevated body temperature can be indicative of contagious diseases, and in such cases it is especially important to detect it as early as possible, so that the diseases do not spread. id="p-4" id="p-4"
[0004] There are thermal imaging cameras available today which can make temperature detections based on captured images. However, they cannot reliably be used for making fast and accurate temperature determination of subjects without causing significant time delays, due to being error-prone and slow. These issues are further magnified when trying to achieve automated or semi-automated systems for performing automatic temperature detection. id="p-5" id="p-5"
[0005] lt would be beneficial if such analyses could be made in an effective, efficient and to at least some degree automated manner, which is not possible within the prior art today. id="p-6" id="p-6"
[0006] Consequently, there exists a need for improvement when it comes to systems for quickly and accurately determining the body temperature of subjects.
Summary id="p-7" id="p-7"
[0007] lt is an object of the invention to address at least some of the problems and issues outlined above. An object of embodiments of the invention is to provide methods and systems for detecting the temperature of a subject, which are efficient, cheap and accurate. lt is further an object to provide methods and systems which can operate with no or relatively low amounts of human intervention. id="p-8" id="p-8"
[0008] According to one aspect, a method for detecting the temperature of a subject is provided. The method comprises capturing a visual image of an area with a visual camera and capturing a thermal image of the same area with a thermal imaging camera at substantially the same point in time as the visual image is captured, thus acquiring a pair of images. The method further comprises detecting a face of the subject in the visual image, detecting a temperature reading in the thermal image and selecting a subpart of the thermal image. The method further comprises detecting a maximum temperature in the subpart of the thermal image and determining the temperature of the subject based on the detected maximum temperature in the subpart of the thermal image. id="p-9" id="p-9"
[0009] According to another aspect, a system operable for detecting the temperature of a subject is provided. The system comprises processing circuitry and a memory. The memory contains instructions executable by said processing circuitry, whereby the system is operative for capturing a visual image of an area with a visual camera and capturing a thermal image of the same area with a thermal imaging camera at substantially the same point in time as the visual image is captured, thus acquiring a pair of images. The system is further operative for detecting a face of the subject in the visual image, detecting a temperature reading in the thermal image and selecting a subpart of the thermal image. The system is further operative for detecting a maximum temperature in the subpart of the thermal image and determining the temperature of the subject based on the detected maximum temperature in the subpart of the thermal image.
[OOO10] According to other aspects, computer programs and carriers are also provided, the details of which will be described in the claims and the detailed description.
[OOO11] Further possible features and benefits of this solution will become apparent from the detailed description below.
Brief description of drawinos [OOO12] The solution will now be described in more detail by means of exemplary embodiments and with reference to the accompanying drawings, in which: [OOO13] Fig. 1 shows a flow chart of a method according to an embodiment.
[OOO14] Fig. 2A shows a subject standing in a valid position within a temperature detection area, according to some embodiments. id="p-15" id="p-15"
[00015] Fig. 2B shows a subject standing in an invalid position within a temperature detection area, according to some embodiments.
[OOO16] Figs. 3A-3C show how the face of a subject is detected selected in the thermal image, according to some embodiments.
[OOO17] Figs. 4A-4D show pixel grids with some warm and some cold pixels.
[OOO18] Fig. 5 shows a block schematic of a system according to an embodiment.
Detailed description [OOO19] Briefly described, the present invention relates to systems and methods for detecting temperature by using a combination of a visual camera and a thermal imaging camera. One or multiple pairs of images, each pair comprising one visual image and one IR image, are captured by the visual camera and IR camera. Each pair of images are taken at substantially the same point in time and cover substantially the same area. A detection is made based on the visual image, in order to determine that there is a subject present in the image. A detection is made based on the IR image, in order to determine that there is a temperature reading present. After this, a subpart of the thermal image is selected, preferably one comprising the head of the user, and a maximum temperature is determined in the subpart of the therma| image.
[OOO20] One aim of the present disc|osure is to achieve a system for detecting the temperature of subjects as they are passing by, without causing too much of a disturbance for the subjects. lt is further an aim to provide a system which can work automatically or semi-automatically, i.e. with minimized intervention needed in order for the system to work.
[OOO21] The present disc|osure builds upon a realization that a combination of facial recognition software based on visual cameras, and temperature detection based on therma| cameras, may be used to achieve a automated or semi- automated system for detecting the temperature of a subject. By using image recognition technology based on visual images, for which the technology is much better developed than for IR cameras, and the temperature detection technology based on the therma| images, a cheap, efficient and accurate system may be achieved.
[OOO22] Throughout this disc|osure, the term "visual camera" denotes a regular camera which captures images in the visual spectrum. The term "therma| imaging camera" denotes a camera which captures therma| images containing temperature measurements, such as an infrared, IR, camera. The terms "IR camera", "therma| camera" and "therma| imaging camera" may be used interchangeably throughout the disc|osure, and the same goes for "IR image" and "therma| image".
[OOO23] Looking now at Fig. 1, steps of a method according to an embodiment will now be described. The method may be a computer-implemented method. The method may be performed by processing circuitry operatively connected to either or both of the visual and IR camera. ln some embodiments, the processing circuitry may be incorporated into either or both of the cameras, and in some embodiments it may be located remotely from both cameras.
[OOO24] The method comprises capturing 202 a visual image of an area with a camera. The method further comprises capturing 204 a therma| image of the same area, at substantially the same point in time, such that the images comprise substantially the same content, in order to enable comparisons and correlations between image pairs. For example, both cameras may be mounted at the entrance to a building, or at a security check, or another place where subjects are naturally passing by. id="p-25" id="p-25"
[00025] ln some embodiments, the capturing 202 step requires the visual camera and the thermal imaging camera to by synchronized to a predetermined standard, expressed as to how much of a time difference is allowed between the images in an image pair. ln some embodiments, the time difference allowed between images is 1 millisecond. id="p-26" id="p-26"
[00026] The method further comprises detecting 206 a subject in the visual image. ln some embodiments, detecting a subject comprises detecting the face of a subject. This step may typically be performed by using conventionally available image recognition technology, and the aim is to ensure that the captured images actually have a subject in them, and not other objects. lf only the IR image was used, and the determination was only based on having a temperature available, it is not unlikely to produce false positives by capturing e.g. light sources and similar objects that also radiate heat. id="p-27" id="p-27"
[00027] ln some embodiments, the step of detecting a face of the subject may be performed in the IR image as well as in the visual image. ln such embodiments, it may be required to detect a face in both the visual image and in the IR image in order for the measurements of an image pair to be deemed as acceptable, such that they are used for further analysis. id="p-28" id="p-28"
[00028] The method further comprises detecting 208 a temperature reading in the IR image. This step is performed in addition to the detecting 206 a subject in the visual image, in order to ensure that a temperature reading is available. l\/lost of the time, if a face is detected then there should also be a temperature reading available, but there are cases in which subjects for some reason do not provide an acceptable temperature reading, for example by wearing clothes or accessories that interfere with the thermal detection of the IR camera. For example, if a subject is wearing glasses, there may not be an acceptable temperature reading available.
[OOO29] ln some embodiments, the detecting 208 a temperature reading in the IR image may comprise detecting a temperature reading in the face area of the subject. id="p-30" id="p-30"
[00030] The method further comprises selecting 210 a subpart of the thermal image. This step is performed in order to use the most representative temperature reading of the available readings in the thermal image. ln some embodiments, the selecting 210 a subpart comprises selecting the face area of the subject, which has been shown to be suitable for providing accurate temperature readings.
[OOO31] The method further comprises detecting 212 a maximum temperature in the subpart of the thermal image. By basing the temperature detecting on a subpart of the image, rather than the entire thermal image, a more accurate and representative temperature reading may be achieved than if the entire image was used as a basis for the temperature determination. ln other words, in embodiments wherein the selecting 210 a subpart of the image comprises selecting the face of the subject, the detecting 212 a maximum temperature in a subpart of the thermal image comprises detecting 212 a maximum temperature in the face area of the subject. id="p-32" id="p-32"
[00032] The method further comprises determining 214 a temperature of the subject based on the detected maximum temperature in the subpart of the thermal image. Depending on a number of factors, it may be relevant to perform some additional operations after a maximum temperature has been determined in a subpart of the image. For example, an average of a plurality of maximum temperatures, determined from a plurality of thermal images of the same subject, may be used to determine the temperature. id="p-33" id="p-33"
[00033] The method may further comprise outputting the determined temperature, or performing an action based on the determined temperature. For example, if the temperature is determined to be below a certain threshold, such as 38 °C, the subject may be allowed to pass through a gate or similar mechanism where a system for detecting the temperature according to the present disclosure is installed, whereas if the temperature is above the threshold, a warning or alert may be issued, and/or the subject may not be allowed to pass through where the temperature detection system is situated. id="p-34" id="p-34"
[00034] ln some embodiments, the steps of capturing 202 a visual image and/or capturing 204 a thermal image, may comprise capturing multiple image pairs, each image pair comprising one visual image and one thermal image of substantially the same area, captured at substantially the same point in time. ln some embodiments, that the image pairs are captured at substantially the same point in time entails that they are captured within a predetermined time threshold, such as one millisecond. lf the subject is e.g. blinking in one of the images in an image pair, the subject should also be blinking in the other of the images of the image pair. id="p-35" id="p-35"
[00035] ln some embodiments, capturing a plurality of images may comprise capturing a video sequence, which is then used as a basis for obtaining the plurality of images. ln some embodiments, the video sequence is between one and five seconds long. id="p-36" id="p-36"
[00036] ln some embodiments, the steps of capturing 202 a visual image and/or capturing 204 a thermal image, may comprise moving the visual camera and/or the IR camera slightly, such that the area of which the images are captured changes slightly in between images and/or image pairs, but without making the images blurry. This may be done in order to have different pixels of the IR camera capturing different parts of the subject. Sometimes, there may be errors with certain pixels in an IR camera, and by moving the IR camera such that the same pixels do not always cover the same area, a more accurate temperature reading may be achieved, by averaging the temperature readings over multiple images where different pixels cover different parts of the subject. Even in cases where the IR camera is fully functional, it may still be preferable to have different pixels covering different areas of the subject. id="p-37" id="p-37"
[00037] ln some embodiments, a similar effect as described above may be achieved by directing the gaze of the user, such that the subject slowly moves its head throughout the capturing of multiple image pairs. For example, the method may comprises providing a focal point for the gaze of the user, wherein the focal point moves slightly over time. Such a focal point may be provided in various different ways, in some embodiments it may be done with a digital display showing the user where to look, and in some embodiments it may be done using physical objects. id="p-38" id="p-38"
[00038] ln some embodiments, the steps of capturing a visual image and the step of detecting a face of the subject in the visual image ay be performed prior to the rest of the steps, such that the following steps are only performed in case a face is detected in the visual image. id="p-39" id="p-39"
[00039] ln some embodiments, the method may further comprise a step of determining 207 that the subject is in a valid position. ln some embodiments, the determining 207 that the subject is in a valid position comprises determining that no warm part of the subject, in the IR images, is outside of a preset boundary 310, as shown in Figs. 3A and 3B. lf there are warm pixels in any of the outermost parts of the thermal image, it may be an indication that the images are captured such that the warmest part of the subject is not contained in the thermal image, which can lead to incorrect determinations of temperature. id="p-40" id="p-40"
[00040] ln some embodiments, determining that no warm part of the subject in the IR images is outside of the preset boundary 310 comprises determining that there are no warm pixels on the uppermost, leftmost or rightmost part of the thermal image. ln some embodiments, determining that there are no warm pixels on the uppermost, leftmost or rightmost part of the thermal image comprises determining that there are no warm pixels in the upper row, leftmost row, and rightmost row of pixels in the thermal image. ln some embodiments, determining there are no warm pixels on the uppermost, leftmost or rightmost part of the thermal image comprises determining that there are no warm pixels in the uppermost, leftmost and rightmost two, three, four or five rows of pixels. id="p-41" id="p-41"
[00041] ln some embodiments, this may comprise ensuring that no other body parts than the head constitute the uppermost part of the subject in the images. lf the top of the head is not the uppermost warm part in the thermal image, the subsequent analysis may be negatively impacted. For example, if a subject would be holding one or two arms up in the air, such that at least part of the arms and/or hands are above the head of the subject, as illustrated in Fig. 2B, the image would not be as suitable as basis for performing methods according to the present disclosure. lt is also possible that there are other sources of heat than the subject's body parts, such as light sources and electrical devices which radiate heat.
[OOO42] ln some embodiments, ensuring that no other body pars than the head constitute the uppermost part of the subject comprises ensuring that there are no warm parts above a height threshold. ln some embodiments, ensuring that there are no warm parts above a height threshold comprises determining that there are no warm pixels in the uppermost row. ln some embodiments, it may comprise determining that there are no warm pixels in the uppermost two, three four or five rows of pixels in the thermal image.
[OOO43] ln some embodiments, the height threshold may be a predetermined height. ln some embodiments, the height above which no warm parts should be present are determined individually for each subject, based on image recognition technology, such that the shape of the person is recognized, and the height is determined as approximately the top of the head of the subject.
[OOO44] Examples of this are found in Fig. 2A and Fig 2B. Fig 2A shows a subject 300 standing in a valid position, such that there are no warm parts, such as the subject's body parts, above or outside of a predefined boundary 31 O. id="p-45" id="p-45"
[00045] Fig. 2B shows a subject 300 standing in a position which is not accepted in some embodiments, since a part of the subject's arm is above the height threshold 31 O. id="p-46" id="p-46"
[00046] lt is important that the images are taken in such a way that the subsequent determinations based on the images are correct. There are a number of potential error sources that should be avoided to as large of an extent as possible. Some of the possible error sources include heat sources such as lights, clothes and accessories which block heat radiation, electrical devices which radiate heat, and similar. id="p-47" id="p-47"
[00047] ln some embodiments, selecting 210 a subpart of the thermal image comprises selecting the head of the subject. This may be done in various ways. ln some embodiments, there may be a matching between a visual image and a thermal image in an image pair, and image analysis can be performed on the visual image in order to determine the location of the face. For this analysis, it is an advantage if the image pairs are synchronized, since if the time difference between when the images are captured is too large, the location of the head may have changed between the time when the visual image was captured and the time when the thermal image was captured. id="p-48" id="p-48"
[00048] ln some embodiments, selecting the head of the subject comprises an extra step to decrease the risk of accidentally selecting a subpart which is not the head and/or face of the subject, comprising determining that the head is contiguous with the largest continuous area comprising warm pixels, in the thermal image. ln the thermal image, the whole body of the subject, or at least a majority of the body should appear as warm pixels, depending on factors such as the clothing and appearance of the person. Either way, the largest continuous area with warm pixels in the thermal image should represent the body of the subject, including the head. By ensuring that the head of the subject is continuous with the largest continuous area of pixels in the thermal image, the risk for false measurements decreases. For example, if there was a light source close to the head of the subject, this could erroneously be thought to be the head portion. However, as long as the light source is not appearing to be continuous with the rest of the subject's body, it would then get filtered out in this step, and the actual head could instead be selected. As will be understood, there may still be a small risk of errors since light sources and other warm objects may appear as continuous with thebody of the subject in the thermal images even if they are not, but this risk may be decreased. id="p-49" id="p-49"
[00049] Another embodiment of how to select 210 a subpart of the thermal image will now be described in relation to Figs. 3A-3C. ln some embodiments, selecting 210 a subpart of the thermal image may comprise selecting the head 410 of the subject 300. ln some embodiments, selecting the head 410 comprises the steps of determining the location of the upper part of the head 430 of the subject, determining the location of both sides of the head 410, 415 of the subject, and then determining a square 420 bounded by the upper part of the head 430 and the sides of the head 410, 415. The method then comprises extending the square downward, thus forming a rectangle, as shown in Fig. 3B, in order to cover the entire head of the subject, which may in some embodiments include the neck of the subject. The square is extended until it can no longer fit all warm parts of the subject 300, which in most cases means the entire body of the subject, without having to increase the width of the rectangle. ln most embodiments, depending on the position and body composition of the subject, this comprises extending the rectangle downward until it reaches the shoulder portion 440 of the subject 400. When it is noticed that the rectangle would have to be widened, as shown in Fig. 3G, the part enclosed by the rectangle is chosen as the head of the subject. ln other words, the rectangle 460 shown in Fig. 3G is too large, and would not be used as the selected portion. lnstead, the rectangle 450 shown in Fig. SB would be selected as the subpart of the thermal image. id="p-50" id="p-50"
[00050] ln some embodiments, detecting 212 the maximum temperature in a subpart of the image requires a certain amount of pixels in order to make an accurate detection. The amount of pixels available depends on various factors, such as the distance between the camera and the subject, the quality of the camera, how much the subject is moving, and similar. ln some embodiments, nine pixels are used for detecting 212 the maximum temperature. ln some such embodiments, the nine pixels are chosen such that the warmest pixel in the subpart of the image is determined, and then the eight pixels surrounding that one are also selected.[00051] ln some embodiments, the step of detecting 212 a maximum temperature in a subpart of the image is performed such that only pixels which are completely "filled with heat" are used. As used in this disclosure, the term "filled with heat" entails that all the temperature measurements in the pixel are above a certain threshold value.
[OOO52] ln some embodiments, the threshold value may be set to a predefined value, such as 30 degrees Celsius. ln some embodiments, the threshold value may be determined based on the temperature of the environment in which the images are to be captured. lf the images would be captured in a warm environment, the threshold value would typically be higher than if they were captured in a cold environment. ln some embodiments, the threshold value is continuously determined. id="p-53" id="p-53"
[00053] ln other words, the method may in some embodiments comprise a step of determining a threshold value above which the temperature readings are determined to warm. ln some embodiments, the determining may be performed continuously. The determining may further be performed based on the environmental conditions in which the images are to be captured. id="p-54" id="p-54"
[00054] ln some embodiments, detecting 212 the maximum temperature in a subpart of the image comprises using the average temperature of a plurality of pixels. ln some such embodiments, the average temperature of the three warmest pixels in a 3x3 pixel grid, for each pixel is used. ln some embodiments, the three warmest connected pixels in a 3x3 pixel grid may be used for each pixel. That it is used "for each pixel" denotes that instead of using the actual temperature value of a pixel, the average of a plurality of pixels is used, which may or may not comprise the actual pixel for which the temperature is calculated. id="p-55" id="p-55"
[00055] This will now be explained in relation to Figs. 4A-4D, which show examples of four different 3x3 pixel grids. The black squares in each of Figs. 4A- 4D represent the three warmest pixels in each 3x3 pixel grid. The middle pixel of each figures is the one for which the temperature is determined.[00056] Figs. 4A, 4B and 4C all show examples wherein the three warmest pixels in each pixel grid are connected. ln embodiments wherein the three warmest connected pixels are used for determining the temperature of each pixel, the average value of the three black squares would be used in each of these three figures. This is even true for the case of Fig. 4B, where the middle pixel, for which the temperature is being determined, does not constitute one of the three warmest pixels in the grid. id="p-57" id="p-57"
[00057] However, the average value of the three black squares in Fig. 4D would not be used, in embodiments wherein the temperature is determined based on the three warmest connected pixels. ln such embodiments, the method may comprise determining the average temperature for each possible combination of three connected pixels within the pixel grid, and the highest determined temperature out of those is used as the detected temperature. id="p-58" id="p-58"
[00058] ln some embodiments, a plurality of image pairs may be determined as comprising a face of the subject, even if no face is detected in all images. For example, if five image pairs, each comprising one visual image and one thermal image, are captured of the same subject, and a face is detected in one of them but not in the other four, all five visual images may still be determined as comprising a face. Such determinations may in some embodiments be based on e.g. the time difference between the images, and if it low enough the images captured close enough in time to one where a face is accurately detected, may also be accepted. id="p-59" id="p-59"
[00059] Fig. 5 shows a system 600, operable for detecting the temperature of a subject. The system 600 comprises processing circuitry 603 and a memory 604. The processing circuitry and the memory 604 are operatively connected to a visual camera 610 and a thermal imaging camera 615. The processing circuitry 603 may comprise one or more programmable processor, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. The memory contains instructions executable by said processing circuitry, whereby the system 600 is operative for capturing a visual image of an area with a visual camera, and capturing a thermal image of the same area with a thermal imaging camera at substantially the same point in timeas the visual image is captured, thus acquiring a pair of images. The system 600 is further operative for detecting a face of the subject in the visual image, detecting a temperature reading in the therma| image, and selecting a subpart of the therma| image. The system 600 is further operative for detecting a maximum temperature in the subpart of the therma| image, and for determining the temperature of the subject based on the detected maximum temperature in the subpart of the therma| image. id="p-60" id="p-60"
[00060] ln some embodiments, the visual camera 610, the therma| camera 615, the processing circuitry and the memory 604 may be incorporated into one device. ln other embodiments, they may be incorporated on different devices, as long as they are operatively connected. id="p-61" id="p-61"
[00061] The system 600 that performs the method may be a group of devices, wherein functionality for performing the method are spread out over different physical, or virtual, devices of the system. ln other words, the system 600 for detecting the temperature of a subject may be a cloud-solution, i.e. the system 600 may be deployed as cloud computing resources that may be distributed in the syste m. id="p-62" id="p-62"
[00062] According to an embodiment, the system 600 is further operative for performing any other method steps described throughout this disclosure as possible embodiments of a method for detecting the temperature of a subject as disclosed herein. id="p-63" id="p-63"
[00063] According to other embodiments, the system 600 may further comprise a communication unit 602, which may be considered to comprise conventional means for communicating with other parts of the system, and/or with other systems. The instructions executable by said processing circuitry 603 may be arranged as a computer program 605 stored e.g. in the memory 604. The processing circuitry 603 and the memory 604 may be arranged in a sub- arrangement 601. The sub-arrangement 601 may be a micro-processor and adequate software and storage therefore, a Programmable Logic Device, PLD, or other electronic component(s)/processing circuit(s) configured to perform the methods mentioned above. id="p-64" id="p-64"
[00064] The computer program 605 may comprise computer readable code means, which when run in a system 600 causes the system 600 to perform the steps described in any of the described embodiments of the system 600. The computer program 605 may be carried by a computer program product connectable to the processing circuitry 603. The computer program product may be the memory 604. The memory 604 may be realized as for example a RAIVI (Random-access memory), ROIVI (Read-Only l\/lemory) or an EEPROIVI (Electrical Erasable Programmable ROIVI). Further, the computer program may be carried by a separate computer-readable medium, such as a CD, DVD or flash memory, from which the program could be downloaded into the memory 604. Alternatively, the computer program may be stored on a server or any other entity to which the system 600 has access via the communication unit 602. The computer program may then be downloaded from the server into the memory id="p-65" id="p-65"
[00065] Although the description above contains a plurality of specificities, these should not be construed as limiting the scope of the concept described herein but as merely providing illustrations of some exemplifying embodiments of the described concept. lt will be appreciated that the scope of the presently described concept fully encompasses other embodiments which may become obvious to those skilled in the art, and that the scope of the presently described concept is accordingly not to be limited. Reference to an element in the singular is not intended to mean "one and only one" unless explicitly so stated, but rather "one or more." All structural and functional equivalents to the elements of the above- described embodiments that are known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be encompassed hereby. l\/loreover, it is not necessary for an apparatus or method to address each and every problem sought to be solved by the presently described concept, for it to be encompassed hereby. ln the exemplary figures, a broken line generally signifies that the feature within the broken line is optional.

Claims (11)

Claims
1. A method for detecting the temperature of a person, comprising: a) capturing (202) a visual image of an area with a visual camera; b) capturing (204) a therma| image of the same area with a therma| imaging camera at substantially the same point in time as the visual image is captured, thus acquiring a pair of images; c) detecting (206) a face of the person in the visual image; d) detecting (208) a temperature reading in the therma| image; e) selecting (210) a subpart of the therma| image comprising a head or a face of the person, wherein the selecting (210) comprises: determining the location of the upper part of the head of the person; determining the location of both sides of the head; determining a square bounded by the upper part of the head and both sides of the head; extending the square downward, thereby forming a rectangle, until the entire head of the person is contained in the rectangle; and selecting the rectangle as the subpart of the therma| image; and f) detecting (212) a maximum temperature in the subpart of the therma| image; and g) determining (214) the temperature of the person based on the detected maximum temperature in the subpart of the therma| image.
2. The method according to claim 1, wherein selecting the head and/or face of the person comprises determining that the head and/or face is contiguous with the largest continuous area of warm pixels.
3. The method according to any one of claims 1-2, wherein selecting the head and/or face of the person further comprises determining that the head of the person is contiggræuous with the largest area comprising warm pixels in the thermal image.
4. The method according to any one of claims 1-3, further comprising determining (207) that the person is in a valid position.
5. The method according to any one of claims 1-4, wherein capturing a visual image comprises capturing a plurality of visual images, and wherein capturing a thermal image comprises capturing a plurality of thermal images.
6. The method according to claim 5, wherein the visual images are obtained from a video sequence from the visual camera, and the thermal images are obtained from a video sequence from the thermal camera.
7. The method according to any one of claims 1-6, wherein the detecting (212) a maximum temperature in a subpart of the image comprises using an average temperature value of a plurality of pixels as the temperature for each pixel.
8. A system (600) operable for detecting the temperature of a person, the system (600) comprising: processing circuitry (603); and a memory (604), said memory (604) containing instructions executable by said processing circuitry (603), whereby said system (600) is operative for: capturing a visual image of an area with a visual camera; capturing a thermal image of the same area with a thermal imaging camera at substantially the same point in time as the visual image is captured, thus acquiring a pair of images; detecting a face of the person in the visual image; detecting a temperature reading in the thermal image;selecting a subpart of the thermal image comprising a head or a face of the person, wherein the selecting (210) comprises: determining the location of the upper part of the head of the person; determining the location of both sides of the head; determining a square bounded by the upper part of the head and both sides of the head; extending the square downward, thereby forming a rectangle, until the entire head of the person is contained in the rectangle; and selecting the rectangle as the subpart of the thermal image; and detecting a maximum temperature in the subpart of the thermal image; and determining the temperature of the person based on the detected maximum temperature in the subpart of the thermal image.
9. The system (600) according to claim 8, further operative for performing the steps of a method according to any one of claims 2-
10. A computer program (605) comprising computer readable code means to be run in the system (600), which computer readable code means when run in the system (600) causes the system (600) to perform the following steps: detecting a face of the person in the visual image; detecting a temperature reading in the thermal image; selecting a subpart of the thermal image comprising a head or a face of the person, wherein the selecting (210) comprises: determining the location of the upper part of the head of the person; determining the location of both sides of the head;determining a square bounded by the upper part of the head and both sides of the head; extending the square downward, thereby forming a rectangle, until the entire head of the person is contained in the rectangle; and selecting the rectangle as the subpart of the therma| image; and detecting a maximum temperature in the subpart of the therma| image; and determining the temperature of the person based on the detected maximum temperature in the subpart of the therma| image.
11. A carrier containing the computer program (605) according to c|aim 10, wherein the carrier is one of an electronic signal, optical signal, radio signal or computer readable storage medium.
SE2051080A 2020-09-16 2020-09-16 Method and device for detecting a temperature of a person capturing a visual and a thermal image SE545401C2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
SE2051080A SE545401C2 (en) 2020-09-16 2020-09-16 Method and device for detecting a temperature of a person capturing a visual and a thermal image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
SE2051080A SE545401C2 (en) 2020-09-16 2020-09-16 Method and device for detecting a temperature of a person capturing a visual and a thermal image

Publications (2)

Publication Number Publication Date
SE2051080A1 SE2051080A1 (en) 2022-03-17
SE545401C2 true SE545401C2 (en) 2023-08-01

Family

ID=81127166

Family Applications (1)

Application Number Title Priority Date Filing Date
SE2051080A SE545401C2 (en) 2020-09-16 2020-09-16 Method and device for detecting a temperature of a person capturing a visual and a thermal image

Country Status (1)

Country Link
SE (1) SE545401C2 (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109846463A (en) * 2019-03-04 2019-06-07 武汉迅检科技有限公司 Infrared face temp measuring method, system, equipment and storage medium
CN209043461U (en) * 2018-06-06 2019-06-28 深圳市凯利博实业有限公司 Body temperature measuring device
WO2019182355A1 (en) * 2018-03-20 2019-09-26 주식회사 엠테이크 Smartphone, vehicle and camera having thermal image sensor, and display and sensing method using same
CN110411570A (en) * 2019-06-28 2019-11-05 武汉高德智感科技有限公司 Infrared human body temperature screening method based on human testing and human body tracking technology
CN110567582A (en) * 2018-06-06 2019-12-13 深圳市凯利博实业有限公司 body temperature measuring device and method
CN110934572A (en) * 2019-11-26 2020-03-31 新疆爱华盈通信息技术有限公司 Body temperature monitoring method and device and readable storage medium
CN111337142A (en) * 2020-04-07 2020-06-26 北京迈格威科技有限公司 Body temperature correction method and device and electronic equipment
CN111358443A (en) * 2020-03-06 2020-07-03 深圳市爱深盈通信息技术有限公司 Body temperature monitoring method and device
CN111507200A (en) * 2020-03-26 2020-08-07 北京迈格威科技有限公司 Body temperature detection method, body temperature detection device and dual-optical camera
CN111664946A (en) * 2020-06-19 2020-09-15 中国电子科技集团公司第十一研究所 Wide-area temperature screening equipment

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019182355A1 (en) * 2018-03-20 2019-09-26 주식회사 엠테이크 Smartphone, vehicle and camera having thermal image sensor, and display and sensing method using same
CN209043461U (en) * 2018-06-06 2019-06-28 深圳市凯利博实业有限公司 Body temperature measuring device
CN110567582A (en) * 2018-06-06 2019-12-13 深圳市凯利博实业有限公司 body temperature measuring device and method
CN109846463A (en) * 2019-03-04 2019-06-07 武汉迅检科技有限公司 Infrared face temp measuring method, system, equipment and storage medium
CN110411570A (en) * 2019-06-28 2019-11-05 武汉高德智感科技有限公司 Infrared human body temperature screening method based on human testing and human body tracking technology
CN110934572A (en) * 2019-11-26 2020-03-31 新疆爱华盈通信息技术有限公司 Body temperature monitoring method and device and readable storage medium
CN111358443A (en) * 2020-03-06 2020-07-03 深圳市爱深盈通信息技术有限公司 Body temperature monitoring method and device
CN111507200A (en) * 2020-03-26 2020-08-07 北京迈格威科技有限公司 Body temperature detection method, body temperature detection device and dual-optical camera
CN111337142A (en) * 2020-04-07 2020-06-26 北京迈格威科技有限公司 Body temperature correction method and device and electronic equipment
CN111664946A (en) * 2020-06-19 2020-09-15 中国电子科技集团公司第十一研究所 Wide-area temperature screening equipment

Also Published As

Publication number Publication date
SE2051080A1 (en) 2022-03-17

Similar Documents

Publication Publication Date Title
AU2018247216B2 (en) Systems and methods for liveness analysis
US8212210B2 (en) IR camera and method for presenting IR information
CN101523411B (en) Eye opening detection system and method of detecting eye opening
KR101791305B1 (en) Apparatus and method for diagnosing electric power equipment using infrared thermal imaging camera
US7457441B2 (en) System and method for detecting thermal anomalies
RU2331107C2 (en) Method of identification through iris and device for implementing this method
US10891479B2 (en) Image processing method and system for iris recognition
JP2008158922A (en) Eyelid detection apparatus, eyelid detection method, and program
JP2018510669A5 (en)
US20180174309A1 (en) Eye Motion Detection Method, Program, Program Storage Medium, and Eye Motion Detection Device
US11375133B2 (en) Automatic exposure module for an image acquisition system
KR101921610B1 (en) Method and Apparatus for Monitoring Objects from Video
US10163009B2 (en) Apparatus and method for recognizing iris
EP3912124A1 (en) System and methods for automatic detection of product insertions and product extraction in an open shopping cart
KR102207650B1 (en) Method for temperature calibration in thermal camera system
JPWO2019044898A1 (en) Gas detection system
SE545401C2 (en) Method and device for detecting a temperature of a person capturing a visual and a thermal image
IL296367A (en) Dynamic adjustment of flash intensity based on retinal pigmentation
KR102251307B1 (en) Thermal camera system with distance measuring function
US11556006B2 (en) Method and device for detecting a shadow in a head mounted device
US20180005020A1 (en) Method and a device for detecting fraud by examination using two different focal lengths during automatic face recognition
CN115868920B (en) Quantitative evaluation method, device and storage medium for conjunctival congestion
CN114359776B (en) Flame detection method and device integrating light and thermal imaging
US20190316966A1 (en) Image processing device and image processing method
WO2021109458A1 (en) Object recognition method and apparatus, electronic device and readable storage medium