Distance compensation for thermographic temperature measurements of endocanthial systems and methods

Abstract

Various techniques are disclosed to provide improved human temperature detection using thermal images of the inner canthus. In one example, a method includes capturing, using a thermal imager, a thermal image of a person. The method also includes determining, using corresponding pixels of the thermal image, an uncompensated temperature measurement associated with an inner canthus of a face of the person. The method also includes determining a correction term that varies with a distance between the thermal imager and the person. The method also includes applying the correction term to the uncompensated temperature measurement to provide a corrected temperature measurement associated with the inner canthus to compensate for attenuation associated with the distance. Additional methods and systems are also provided.

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to U.S. Provisional Patent Application No. 63 / 044,516, filed June 26, 2020, entitled “Distance Compensation for Thermal Imaging Temperature Measurement of Inner Canthus System and Method,” which is incorporated herein by reference in its entirety.

[0003] This application claims priority and benefit to U.S. Provisional Patent Application No. 63 / 158,273, filed March 8, 2021, entitled “Thermal Imaging Temperature Measurement of Inner Canthus System and Method,” which is incorporated herein by reference in its entirety. Technical Field

[0004] The present invention relates generally to thermal imaging, and more specifically, to compensating for distance-dependent attenuation in thermal image temperature measurements and detecting the face and inner canthus of a person. Background Technology

[0005] Thermal imaging systems are frequently used to detect the temperature of various objects or people in a scene. For example, in the case of people, such a system can be used to detect body temperature. Such a system can be particularly useful in detecting elevated body temperature associated with possible health conditions, such as infection or disease.

[0006] In some cases, the inner canthus of the human eye (e.g., the inner corner of the eye where the upper and lower eyelids meet, also called the inner canthus) can be used for temperature detection. In particular, the inner canthus can be used as a general approximation of body temperature. Thus, an elevated inner canthus temperature may be associated with an overall elevated body temperature.

[0007] However, conventional methods for inner canthus temperature detection can be prone to error. For example, the inner canthus may comprise a relatively small portion of the captured thermal image of the face or body. Therefore, the inner canthus may be associated with only a small number of pixels in the captured thermal image. Consequently, the measured temperature value associated with the inner canthus may decrease significantly with distance due to the influence of other stray heat dissipation wavelengths from other adjacent facial features. The inner canthus may also be difficult to detect, especially when the person is wearing a mask or other face covering.

[0008] Therefore, there is a need for an improved method for temperature detection using thermal imaging of the inner canthus, which provides improved accuracy compared to conventional techniques. Summary of the Invention

[0009] Various techniques are disclosed to provide improved human body temperature detection using thermal imaging of the inner canthus. In particular, thermal imaging systems and related methods are provided, wherein distance-dependent temperature attenuation is compensated for to improve the accuracy of human body temperature detection. Such techniques are particularly useful in accurately detecting potentially elevated human body temperatures associated with possible health conditions.

[0010] Various techniques are disclosed to provide improved face detection. For example, thermal imaging systems and related methods are provided, in which the face and inner canthus of a person are detected in a thermal image, and a temperature measurement of the person's inner canthus and body temperature are determined. Based on the determined temperature, alarms can be triggered and / or notifications can be generated to identify elevated body temperatures exceeding a threshold (e.g., exceeding the continuous average of a statistical model of the temperature measurement).

[0011] In one embodiment, a method includes: capturing a thermal image of a person using a thermal imager; determining a correction term that varies with the distance between the thermal imager and the person; and applying the correction term to provide a corrected temperature measurement associated with the inner canthus of the person's face to compensate for the attenuation associated with the distance.

[0012] In another embodiment, a system includes a thermal imager; and a logic device configured to operate the thermal imager to capture a thermal image of a person, determine a correction term that varies with the distance between the thermal imager and the person, and apply the correction term to provide a corrected temperature measurement associated with the inner canthus of the person's face to compensate for attenuation associated with the distance.

[0013] In another embodiment, a method includes capturing a thermal image of a person using a thermal imager, detecting the person's face and inner canthus in the thermal image using an artificial neural network, determining a temperature measurement of the inner canthus using corresponding pixels of the thermal image, and determining the person's body temperature using the temperature measurement.

[0014] In another embodiment, a system includes a thermal imager and a logic device configured to operate the thermal imager to capture a thermal image of a person, detect the person's face and inner canthus in the thermal image using an artificial neural network, determine a temperature measurement of the inner canthus using corresponding pixels of the thermal image, and determine the person's body temperature using the temperature measurement.

[0015] The scope of this invention is defined by the claims, which are incorporated herein by reference. A more complete understanding of embodiments of the invention, and the implementation of its additional advantages, will be provided to those skilled in the art through consideration of the following detailed description of one or more embodiments. Reference will be made to the accompanying drawings, which will first be briefly described. Attached Figure Description

[0016] Figure 1 A block diagram of an imaging system according to an embodiment of the present disclosure is shown.

[0017] Figure 2 A block diagram of a thermal imager according to an embodiment of the present disclosure is shown.

[0018] Figure 3A block diagram of an artificial neural network according to an embodiment of the present disclosure is shown.

[0019] Figure 4 A series of thermal images captured at different distances according to embodiments of the present disclosure are shown.

[0020] Figure 5 Thermal images of experienced distance analysis according to embodiments of the present disclosure are shown.

[0021] Figure 6 A plot of uncompensated temperature measurements according to an embodiment of the present disclosure is shown.

[0022] Figure 7 A plot of corrected temperature measurements according to an embodiment of the present disclosure is shown.

[0023] Figure 8 and 9 A thermal image with associated uncompensated temperature measurements is shown according to an embodiment of the present disclosure.

[0024] Figure 10 and 11 A thermal image with associated corrected temperature measurements is shown according to an embodiment of the present disclosure.

[0025] Figure 12 The process for determining a corrected temperature measurement value according to an embodiment of the present disclosure is illustrated.

[0026] Figures 13-18 Various overlays are illustrated according to one or more embodiments of this disclosure for providing a user with feedback on temperature calculations and determined temperature measurements.

[0027] Figure 19 The present disclosure illustrates a workflow for determining whether a person has an elevated or normal temperature using a statistical model, according to embodiments of the present disclosure.

[0028] Embodiments of the invention and their advantages can be best understood by referring to the following detailed description. It should be understood that the same reference numerals are used to identify the same elements shown in one or more of the figures. Detailed Implementation

[0029] Various methods and systems are provided, based on embodiments further discussed herein, in which thermal images are processed to determine the temperature of a person (e.g., an individual) in a manner that compensates for possible distance attenuation. In particular, the techniques discussed herein are especially useful for providing accurate temperature measurements of the inner canthus of a person.

[0030] In this regard, the inner canthus is often the hottest feature on a person's face, and is a reasonable approximation of body temperature (e.g., an elevated temperature of the inner canthus can often be correlated with an elevated core body temperature). Thus, by improving the accuracy of inner canthus temperature measurements, elevated body temperatures associated with various health conditions can be more accurately detected.

[0031] When capturing thermal images of a person's face, a large portion of the thermal radiation associated with the inner canthus is provided by a small number of pixels of the resulting thermal image. However, those pixels and other surrounding pixels can also be associated with thermal radiation contributions from other portions of the face (e.g., the eyes, eyebrows, nose, etc.). This effect can become more pronounced as the distance increases. For example, at greater distances, a smaller number of pixels (e.g., and thus a smaller proportion of the total pixels of the thermal image) will be associated with the inner canthus itself, and an increasing number (e.g., a greater proportion) of pixels will be associated with other portions of the face. As a result, as the distance to the person increases, the total contributing thermal radiation associated with the inner canthus in the captured thermal image will decrease. Thus, when processing such thermal images to detect the temperature of the inner canthus (e.g., and thus for detecting a potentially elevated body temperature), the detected temperature can vary greatly with distance. This distance-based temperature variation can create difficulties in accurately detecting a potentially elevated body temperature.

[0032] According to embodiments discussed herein, compensation techniques are provided in which a correction term can be applied to temperature measurements associated with a person's inner canthus detected using a thermal image. For example, the width of the person's face and / or the face area (e.g., in pixels) in the thermal image can be used to determine a correction term that can be applied to the detected temperature to provide a compensated temperature. By applying the correction term, the resulting compensated temperature can provide a stable representation of the inner canthus temperature regardless of the distance between the thermal imager and the imaged person.

[0033] Such implementations are particularly useful for applications in which the temperatures of multiple persons at different distances need to be measured, such as in the case of scanning a crowd of people for a potentially elevated temperature. By applying correction terms as discussed herein, accurate body temperatures can be determined in such applications even when the persons are distributed at different distances from the thermal imaging system.

[0034] Also according to embodiments discussed herein, various techniques are included to provide user feedback regarding temperature, position relative to the thermal imager, and other features. In some embodiments, a running average of a user's body temperature can be provided using statistical analysis. Such a running average can be used to determine a threshold to detect an elevated body temperature.

[0035] Turning now to the drawings, Figure 1A block diagram of an imaging system 100 is shown in accordance with embodiments of the present disclosure. As shown, the imaging system 100 includes a housing 151 (e.g., a camera body) with an aperture 158, one or more filters 160, one or more optical components 162, a thermal imager 164, an imager interface 166, a logic device 168, user controls 170, a memory 172, a communication interface 174, a machine-readable medium 176, a distance sensor 177, a display 178, other sensors 180, and other components 182.

[0036] In various embodiments, the imaging system 100 can be implemented as, for example, a camera system, such as a portable (e.g., handheld) thermal camera system, a small form factor camera system implemented as part of another device, a fixed camera system, and / or other suitable implementations. The imaging system 100 can be positioned to receive infrared radiation 194 from a scene 190 (e.g., a field of view of the imaging system 100). In various embodiments, the scene 190 can include various features of interest, such as one or more people 192 (e.g., a person).

[0037] As shown, the person 192 (e.g., a person) can be located at a distance 102 from the imaging system 100. In various embodiments, the distance 102 can change over time. For example, if the person 192 and / or the imaging system 100 are in motion while capturing a series of thermal images, different thermal images can be captured at different associated distances 102.

[0038] The distance sensor 177 can be implemented as any suitable type of device for detecting the distance 102. Such implementations can include, for example, a time-of-flight sensor, a LIDAR system, a radar system, and / or other suitable implementations. In some embodiments, other techniques can be used to determine the distance 102, such as processing thermal images to determine a number of pixels in the thermal images associated with various features of the person 192, as also discussed herein.

[0039] The infrared radiation 194 is received through the aperture 158 and passes through the one or more filters 160, which can be disposed to selectively filter particular thermal wavelengths of interest to obtain an image to be captured by the thermal imager 164. The optical components 162 (e.g., an optical assembly including one or more lenses, additional filters, transmissive windows, and / or other optical components) pass the filtered infrared radiation 194 through for capture by the thermal imager 164.

[0040] Accordingly, it should be appreciated that filter 160 and / or optical component 162 can operate together to selectively filter out portions of infrared radiation 194 such that only the desired wavelengths and / or desired thermal radiation intensities are ultimately received by thermal imager 164. In various embodiments, any desired combination of these components can be provided (e.g., various components can be included and / or omitted to suit various implementations).

[0041] Thermal imager 164 can capture thermal images of scene 190 in response to infrared radiation 194. Thermal imager 164 can include a sensor array for capturing thermal images (e.g., thermal image frames) of scene 190. In some embodiments, thermal imager 164 can also include one or more analog-to-digital converters for converting analog signals captured by the sensors into digital data (e.g., pixel values) to provide captured images. Imager interface 166 provides captured images to logic device 168, which can be used to process images, store raw and / or processed images in memory 172, and / or retrieve stored images from memory 172. Additional implementation details of embodiments of thermal imager 164 will be discussed further herein with respect to FIG. 2. Figure 2 Further discussion.

[0042] Logic device 168 can include, for example, a microprocessor, a single-core processor, a multi-core processor, a microcontroller, a programmable logic device configured to perform processing operations, a digital signal processing (DSP) device, one or more memories to store executable instructions (e.g., software, firmware, or other instructions), and / or any other suitable combination of devices and / or memories for performing any of the various operations described herein. Logic device 168 is configured to interface and communicate with various components of imaging system 100 to perform the various methods and processing steps described herein. In various embodiments, processing instructions can be integrated in software and / or hardware that is part of logic device 168, or in code (e.g., software and / or configuration data) that can be stored in memory 172 and / or machine-readable medium 176. In various embodiments, instructions stored in memory 172 and / or machine-readable medium 176 allow logic device 168 to perform the various operations discussed herein and / or control various components of system 100 for such operations.

[0043] Memory 172 can include one or more memory devices (e.g., one or more memories) for storing data and information. The one or more memory devices can include various types of memory, including volatile and non-volatile memory devices, such as RAM (random access memory), ROM (read only memory), EEPROM (electrically erasable programmable read only memory), flash memory, fixed memory, removable memory, and / or other types of memory.

[0044] The machine-readable medium 176 (e.g., memory, hard drive, optical disk, digital video disk, or flash memory) can be a non-transitory machine-readable medium that stores instructions for execution by the logic device 168. In various embodiments, the machine-readable medium 176 can be included as part of the imaging system 100 and / or separate from the imaging system 100, with the stored instructions provided to the imaging system 100 by coupling the machine-readable medium 176 to the imaging system 100 and / or by downloading (e.g., via a wired or wireless link) the instructions from the machine-readable medium (e.g., containing non-transitory information) by the imaging system 100.

[0045] The logic device 168 can be configured to process captured images and provide them to the display 178 for presentation to and viewing by a user. The display 178 can include a display device such as a liquid crystal display (LCD), an organic light emitting diode (OLED) display, and / or other types of displays suitable for displaying images and / or information to a user of the system 100. The logic device 168 can be configured to display images and information on the display 178. For example, the logic device 168 can be configured to retrieve images and information from the memory 172 and provide the images and information to the display 178 for presentation to a user of the system 100. The display 178 can include display electronics that can be used by the logic device 168 to display such images and information.

[0046] The user controls 170 can include any desired type of user input and / or interface device having one or more user actuation components, such as one or more buttons, sliders, knobs, keyboards, joysticks, and / or other types of controls configured to generate one or more user actuation input control signals. In some embodiments, the user controls 170 can be integrated with the display 178 as a touch screen to operate as both the user controls 170 and the display 178. The logic device 168 can be configured to sense control input signals from the user controls 170 and respond to the sensed control input signals received therefrom. In some embodiments, portions of the display 178 and / or the user controls 170 can be implemented by appropriate portions of a tablet, laptop, desktop computer, and / or other types of devices.

[0047] In various embodiments, the user controls 170 can be configured to include one or more other user activation mechanisms to provide various other control operations of the imaging system 100, such as autofocus, menu enablement and selection, field of view (FoV), brightness, contrast, gain, offset, spatial, temporal, and / or various other features and / or parameters.

[0048] The imaging system 100 can include various other sensors 180, including, for example, microphones, navigation sensors, temperature sensors, and / or other appropriate sensors.

[0049] The logic device 168 can be configured to receive images from the imager interface 166 and signals and data from the motion sensors 177, the sensors 180, and / or the user controls 170 through the communication interface 174 (e.g., through wired and / or wireless communication) and communicate them to one or more external devices (e.g., a remote system). In this regard, the communication interface 174 can be implemented to provide wired communication through a cable and / or wireless communication through an antenna. For example, the communication interface 174 can include one or more wired or wireless communication components, such as an Ethernet connection, a wireless local area network (WLAN) component based on the IEEE 802.11 standard, a wireless broadband component, a mobile cellular component, a wireless satellite component, or various other types of wireless communication components, including radio frequency (RF), microwave frequency (MWF), and / or infrared frequency (IRF) components configured for communication with a network. As such, the communication interface 174 can include an antenna coupled thereto for wireless communication purposes. In other embodiments, the communication interface 174 can be configured to interface with a DSL (e.g., digital subscriber line) modem, a PSTN (public switched telephone network) modem, an Ethernet device, and / or various other types of wired and / or wireless network communication devices configured for communication with a network.

[0050] In some embodiments, the network can be implemented as a single network or a combination of multiple networks. For example, in various embodiments, the network can include the Internet and / or one or more intranets, landline networks, wireless networks, and / or other appropriate types of communication networks. In another example, the network can include a wireless telecommunication network (e.g., a cellular telephone network) configured to communicate with other communication networks, such as the Internet. As such, in various implementations, the imaging system 100 and / or its individual associated components can be associated with a particular network link, such as a URL (uniform resource locator), an IP (Internet Protocol) address, and / or a mobile telephone number.

[0051] The imaging system 100 can include various other components 182, such as a speaker, an additional display, a visual indicator (e.g., a recording indicator), a vibration actuator, a battery or other power source (e.g., rechargeable or otherwise), and / or additional components appropriate for a particular implementation.

[0052] Although various features of the imaging system 100 are shown together in Figure 1 any of the various illustrated components and subcomponents can be implemented in a distributed manner and used remotely from one another as appropriate.

[0053] Although the imaging system 100 has been described in the context of a thermal imaging system, other embodiments are also contemplated. In some embodiments, the aperture 158, filter 160, optical component 162, and / or imager 164 can be implemented to pass and capture other wavelengths in addition to or instead of thermal wavelengths, such as visible light wavelengths. For example, the imaging system 100 can be implemented to capture both thermal and visible light images of the scene 190 for comparison with one another to detect zooming or other phenomena. As another example, different imaging systems 100 implemented for different wavelengths can be used to capture thermal and visible light images of the scene 190.

[0054] Figure 2 A block diagram of the thermal imager 164 is shown, in accordance with embodiments of the present disclosure. In the illustrated embodiment, the thermal imager 164 is a focal plane array (FPA) that includes a sensor array 230 of infrared sensors 232 (e.g., implemented as unit cells) and a readout integrated circuit (ROIC) 202. Although an 8x8 array of infrared sensors 232 is shown (e.g., corresponding to rows and columns of pixels), this is merely for example and ease of illustration purposes. Any desired sensor array size can be used as desired.

[0055] Each infrared sensor 232 can be implemented, for example, by an infrared detector such as a microbolometer and associated circuitry to provide image data (e.g., data values associated with captured voltages) for a pixel of a captured thermal image. In this regard, a time-multiplexed electrical signal can be provided by the infrared sensor 232 to the ROIC 202.

[0056] The ROIC 202 includes a bias and timing control circuit 204, column amplifiers 205, column multiplexers 206, row multiplexers 208, and output amplifiers 210. The images captured by the infrared sensors 232 can be provided by the output amplifiers 210 to the logic device 168 and / or any other appropriate components to perform the various processing techniques described herein. Further description of ROICs and infrared sensors (e.g., microbolometer circuitry) can be found in U.S. Patent No. 6,028,309, issued February 22, 2000, which is incorporated by reference herein in its entirety.

[0057] Figure 3 A block diagram of an artificial neural network 300 is shown, in accordance with embodiments of the present disclosure. For example, in some embodiments, the neural network 300 can be implemented by the logic device 168.

[0058] As shown, the neural network 300 includes various nodes 302 arranged in a plurality of layers, including an input layer 304 that receives one or more inputs 310, hidden layers 306, and an output layer 308 that provides one or more outputs 320. Although a particular number of nodes 302 and layers 304, 306, and 308 are shown, any desired number of such features can be provided in various embodiments.

[0059] In some embodiments, the neural network 300 can be used to perform facial detection on various thermal images captured by the imaging system 100 and provided to the inputs 310 of the neural network 300. The results of such facial detection can be provided by the neural network at the outputs 320. In some embodiments, the neural network 300 can be trained by providing thermal images of a human face (e.g., stored in the machine-readable medium 176) to the inputs 310.

[0060] Figure 4 A series of thermal images 410-420 of a person 192 captured at different distances is shown in accordance with embodiments of the present disclosure. For example, as shown, the thermal images 410-420 have been captured at various distances ranging from 0.5 meters to 4 meters. As also shown, an inner canthus 402 of the person 192 is present in each of the thermal images 410-420. However, as the distance increases, the size of the inner canthus 402 becomes increasingly smaller in the thermal images 410-420. In this regard, as the distance increases, the number of pixels in the thermal images 410-420 associated with the inner canthus 402 also correspondingly decreases. Further, the contribution of other facial features will proportionally become higher, resulting in a decrease in the overall temperature of the captured pixels associated with the inner canthus 402.

[0061] For example, as Figure 4 As further shown in FIG. 4B, the uncompensated temperature of the detected inner canthus 402 (e.g., performed by processing the values of the pixels determined to be associated with the inner canthus 402) decreases from a high of 35.9 °C at a distance of 0.5 meters to a low of 35.1 °C at a distance of 4 meters (e.g., a change of 0.8 °C). This change can be significant in the context of elevated body temperature detection, as such errors can determine whether a person’s measured body temperature exceeds a threshold value associated with a health condition.

[0062] In accordance with various embodiments discussed herein, a correction term can be determined to compensate for this distance-based attenuation. In this regard, the correction term can be a function of distance. For example, this can generally be represented by Equation 1 below:

[0063] Compensated Temp = Measured Temp + Correction(Distance) (Equation 1)

[0064] In Equation 1, CompensatedTemp is a corrected temperature measurement (e.g., a compensated temperature value) of the inner canthus 402 at the compensated distance, MeasuredTemp is an uncompensated temperature measurement of the inner canthus 402 determined by analyzing the thermal image, and Correction is a correction term applied to MeasuredTemp as a function of Distance, where Distance is the distance 102 from the imaging system 100 and the person 192. Thus, in various embodiments, the Correction(Distance) as set forth in Equation 1 can provide the correction term using an appropriate distance-based correlation.

[0065] The distance 102 can be determined by various techniques. For example, in some embodiments, the distance 102 can be determined by the distance sensor 177 using an appropriate type of sensor and / or system as discussed. In some embodiments, the distance 102 can be determined by reference to other possible features in the scene 190 having a known distance to the imaging system 100.

[0066] In some embodiments, the distance 102 can be determined by performing analysis of one or more captured thermal images of the person 192. For example, Figure 5 A thermal image 402 undergoing distance analysis is shown in accordance with embodiments of the present disclosure. In some embodiments, the logic device 168 can perform analysis with respect to Figure 5 the analysis discussed.

[0067] In Figure 5 , the thermal image 402 is processed to detect the face 502 of the person 192 including the ears 510 and 512. In addition, a face width (e.g., also referred to as “ear2ear” or “e2e”) 514 between the ears 510 and 512 is calculated. This face width 514 can be used to determine an approximate distance 102. In this regard, the imaging system 100 can be pre-calibrated (e.g., with appropriate information stored in the machine-readable medium 176) to correlate the face width 514 (e.g., the number of pixels across the width 514) with the distance 102. For example, people generally have a face width that is within a relatively narrow range (e.g., typically 12 cm to 16 cm). As a result, the imaging system 100 can store a predetermined correlation between the number of pixels associated with a detected face (e.g., assuming the face width 514 is an average face width) and the distance 102. Thus, by determining the number of pixels of the thermal image 410 associated with the face width 514, the imaging system 100 can determine an approximate value of the distance 102.

[0068] Although the correlation between the face width 514 and the distance 102 has been discussed, other correlations can also be used, such as determining the number of pixels associated with the area of the face 502 (e.g., the number of pixels of the thermal image associated with the face) and pre-calibrating the imaging system 100 to associate an average face area with the distance 102.

[0069] Considering the face width 514 correlation in more detail, the equation 1 can be updated to specifically address the face width 514 (e.g., “ear2ear” or “e2e’”), as set forth in the following equation 2:

[0070] Compensated Temp = Measured Temp + Correction(ear2ear) (Equation 2)

[0071] In the equation 2, ear2ear is the number of pixels in the thermal image 410 associated with the face width 514. In some embodiments, the correction term Correction(ear2ear) can be determined according to the following equation 3:

[0072] Correction(ear2ear) = pi / (p2 + ear2ear) (Equation 3)

[0073] In the equation 3, pi and p2 are fitting constants corresponding to a predetermined correlation between the face width 514 (e.g., ear2ear) and the distance 102.

[0074] In viewing the equation 3, it should be appreciated that as the ear2ear value decreases (e.g., corresponding to a decrease in the face width 514 associated with a larger value of the distance 102), the magnitude of Correction(ear2ear) (e.g., the correction term) increases to compensate for the distance-based attenuation of the pixels associated with the inner canthus 402.

[0075] The result of this compensation can be further appreciated in viewing Figure 6 and 7 In this regard, Figure 6Plots 610, 620, and 630 illustrate uncompensated temperature measurements according to embodiments of the present disclosure. In particular, plots 610, 620, and 630 illustrate uncompensated temperature measurements determined for the inner canthus 402 (represented along the vertical axis as Tmax(C)) and the corresponding facial width 514 (represented along the horizontal axis as “ear2ear”) of three different people 192 determined from a series of thermal images (e.g., each of plots 610, 620, and 630 corresponds to temperature measurements associated with a different person 192). It should be appreciated that larger values of ear2ear correspond to smaller distances 102 associated with the captured thermal images. As shown, plots 610, 620, and 630 demonstrate substantial distance-based attenuation in the temperature measurements of approximately 2°C (e.g., ranging from a low of approximately 32.9°C to a high of approximately 35°C).

[0076] In contrast, Figure 7 Plots 710, 720, and 730 illustrate corrected (e.g., distance-compensated) temperature measurements according to embodiments of the present disclosure. In particular, plots 710, 720, and 730 illustrate corrected temperature measurements determined for the inner canthus 402 and the corresponding facial width 514 using the same thermal images of Figure 6 For example, in some embodiments, the corrected temperature measurements of Figure 6 may be determined by applying an appropriate correction term (e.g., according to the techniques discussed with respect to Equations 1-3) to the uncompensated temperature measurements of Figure 7 .

[0077] As shown, plots 710, 720, and 730 demonstrate substantially uniform temperature measurements for each person 192 within a small temperature range (e.g., ranging from a low of approximately 35.4°C to a high of approximately 36°C). Moreover, the variation in plot 710 is particularly well contained within a range of only 0.1°C. Comparing the compensated temperature measurements of plots 710, 720, and 730 with the uncompensated temperature measurements of plots 610, 620, and 630, it is clear that the compensated temperature measurements provide a reliable representation of the inner canthus temperature independent of the distance 102.

[0078] Figures 8 to 10 Further results of the temperature compensation techniques discussed herein are illustrated. For example, Figure 8 and 9 Plots 800 and 900 illustrate thermal images with associated uncompensated temperature measurements according to embodiments of the present disclosure. In Figure 8 plot 800, the thermal image 800 has been captured at a distance (e.g., approximately 20 feet) from the thermal imaging system 100. The inner canthus temperatures of the detected people 810, 812, and 814 are 31.8°C, 31.3°C, and 32.0°C, respectively. Moreover, the average temperature of all people is 31.69°C.

[0079] In Figure 9 , the thermal image 900 has been captured at close range (e.g., approximately 5 feet) from the thermal imaging system 100. The detected persons 810, 812, and 814 have an inner canthus temperature of 33.2°C, 32.5°C, and 33.1°C, respectively (e.g., all above the average temperature of Figure 8 ). Further, the average temperature of all persons is 32.93°C (e.g., above the average temperature of Figure 8 ). Thus, it should be appreciated that the uncompensated temperature measurements associated with Figure 8 and 9 indicate a significant distance-based attenuation.

[0080] Figure 10 and 11 show thermal images 1000 and 1100 with associated compensated temperature measurements according to embodiments of the present disclosure. In this regard, the thermal images 1000 and 1100 use the same originally captured thermal image data as the thermal images 800 and 900, but include the results of compensated temperature measurements.

[0081] As shown in Figure 10 (e.g., the thermal image 1000 captured at a far range of approximately 20 feet), the detected persons 810, 812, and 814 have an inner canthus temperature of 33.8°C, 33.5°C, and 34.3°C, respectively. Further, the average temperature of all persons is 33.86°C.

[0082] In Figure 11 (e.g., the thermal image 1100 captured at a close range of approximately 5 feet), the detected persons 810, 812, and 814 have an inner canthus temperature of 33.7°C, 33.3°C, and 33.6°C, respectively (e.g., all within close temperature proximity to Figure 10 ). Further, the average temperature of all persons is 33.56°C (e.g., within close temperature proximity to Figure 10 ). Thus, it should be appreciated that the compensated temperature measurements associated with Figure 10 and 11 indicate consistency independent of distance-based attenuation.

[0083] Figure 12A process 1200 of determining compensated temperature measurements according to embodiments of the present disclosure is shown. In block 1210, the logic device 168 performs pre-processing operations (e.g., pre-calibration) to determine a correlation between the distance 102 and various features of the captured thermal images to determine the fit constants pi and p2 of equation 3. For example, in some embodiments, block 1210 can include capturing multiple thermal images of a subject or person at different distances 102 from the imaging system 100 to determine a correlation between the number of pixels associated with various features (e.g., the face width 514 or other human facial features) and the different distances 102. The logic device 168 can then appropriately determine the values of the fit constants pi and p2 to compensate for distance-related variations in the features captured in the thermal images.

[0084] In block 1215, the thermal imager 164 captures one or more thermal images of one or more persons of interest 192 in the scene 190. For example, the thermal imager 164 can be operated by a logic device (e.g., the logic device 168) to capture the thermal images.

[0085] In block 1220, the logic device 168 performs face detection (e.g., using the neural network 300 and / or other appropriate face detection techniques) to detect the location of the face and the inner canthus 402 of the person 192 in the captured thermal images. For example, the logic device 168 can employ an artificial neural network (e.g., the neural network 300), a detection system (e.g., as described below with reference to Figure 19 the) and / or other appropriate face detection techniques to detect the face and the inner canthus 402 of the person 192 in the thermal images. In embodiments, block 1220 can include detecting a facial covering, such as a face mask or another type of facial covering, worn by the person 192 in the captured thermal images.

[0086] In block 1230, the logic device 168 determines the distance 102 to the person 192. As discussed, various techniques can be used. In some embodiments, a pixel-based approach can be performed by determining the face width 514 (e.g., the ear2ear value) and / or other facial features of the person 192 and correlating with the distance 102 (e.g., through a predetermined correlation provided by block 1210). For example, a predetermined correlation between the number of pixels of one or more facial features (e.g., the face width, the face area, etc.) and the distance can be used to determine the distance 102, although other configurations can be contemplated. In other embodiments, a distance sensor 177 and / or other techniques can be appropriately used.

[0087] In block 1232, a notification regarding the distance 102 can be generated. For example, the imaging system 100 can generate a notification that the person 192 needs to move relative to the thermal imager 164 based on the determined distance. For example, the imaging system 100 can generate a notification indicating that the person 192 is not positioned correctly, e.g., outside of a preferred distance range from the thermal imager 164. As a result, one or more blocks can be repeated until the person 192 is correctly positioned within the preferred distance range. In this way, the person 192 can be properly aligned prior to taking temperature measurements in subsequent steps, as described below. Figure 12

[0088] In block 1233, the logic device 168 determines an uncompensated temperature measurement of the inner canthus 402. For example, block 1233 can include determining a temperature associated with a pixel value of a thermal image corresponding to the inner canthus 402. In various embodiments, such a temperature can be determined, e.g., by averaging and / or otherwise processing corresponding pixel values.

[0089] In block 1235, the logic device 168 determines a correction term to apply to the previously detected uncompensated temperature measurement. For example, the correction term can be determined as a function of the distance between the thermal imager 164 and the person 192. In the case of a pixel-based approach as discussed, the correction term can be determined using Equation 3. In other embodiments, any appropriate correction term as a function of distance can be used, as discussed with respect to Equation 1. In embodiments, the correction term can be determined based on an attenuation associated with a facial covering, e.g., a face mask, as described below. In this way, the process 1200 can compensate for one or more facial coverings worn by the person 192, such as those described below with reference to Figures 13-18 .

[0090] In block 1240, the logic device 168 applies the correction term to the uncompensated temperature measurement (previously determined in block 1225) to provide a corrected temperature measurement as discussed with respect to Figure 7 , 10 and 11. For example, the correction term can be applied to provide a corrected temperature measurement associated with the inner canthus 402 to compensate for attenuation associated with the distance 102, a facial covering, or other factors, as described herein.

[0091] In block 1245, the imaging system 100 provides the corrected temperature measurement to a user of the imaging system 100. For example, in some embodiments, the imaging system 100 can provide the corrected temperature measurement as part of a thermal image presented to the user on the display 178, similar to the thermal images 1000 and 1100 of Figure 10 and 11 or Figures 13-18 ​The thermal image. The calibrated temperature measurement can be correlated with the body temperature of person 192. For example, logic device 168 can employ a measurement system and / or other suitable temperature determination techniques to determine the body temperature of person 192 based on the temperature of inner canthus 402, as described herein.

[0092] In block 1247, logic device 168 processes the calibrated temperature measurement using a statistical model. For example, statistical analysis can be used to provide a continuous average of the calibrated temperature measurement (e.g., user body temperature), such as a reference... Figure 19 The continuous average value can be used to determine the threshold for detecting elevated body temperature, as explained below.

[0093] In block 1250, logic device 168 determines whether a corrected temperature measurement is associated with an elevated body temperature. For example, the corrected temperature measurement could be used to identify a possible health condition associated with person 192. An elevated body temperature can be determined based on the corrected temperature measurement exceeding a threshold (e.g., a continuous average provided by a statistical model in block 1247). If no elevated body temperature is detected, then... Figure 12 The process returns to box 1215, where additional thermal images can be captured and subsequently processed, as discussed.

[0094] If an elevated body temperature is detected in box 1250, then Figure 12 The process continues to box 1255, where the imaging system 100 can generate a notification regarding the elevated body temperature. For example, in various embodiments, the imaging system 100 can appropriately utilize various components of the imaging system 100 to generate visible and / or audible notifications in the form of text, icons, colors, flashlights, sounds, alarms, and / or other types of notifications. Notifications regarding elevated body temperature can include many configurations, as referenced below. Figures 13-18 The configurations described. After that, Figure 12 The process returns to box 1215, where additional thermal images can be captured and subsequently processed, as discussed.

[0095] In some embodiments, the action can be performed on multiple people 192 present in the captured thermal image. Figure 12 Operations (e.g., such as regarding) Figure 10 and 11 (Similarly discussed and illustrated). In some embodiments, the movement can be repeated as one or more persons 192 move through scene 190 and / or at varying distances 102. Figure 12 The operation is to provide updated calibrated temperature measurements.

[0096] Additional embodiments are also contemplated. For example, although it has been discussed that correlations between facial dimensions (e.g., width and / or area) and distances are used to determine correction terms, other correlations are possible. For example, in some embodiments, thermal images of a person 192 having different facial dimensions (e.g., corresponding to different head sizes) at the same distance 102 from the imaging system 100 can result in different temperature measurements (e.g., due to different sizes of the inner canthi of the different facial dimensions and thus different numbers of pixels associated therewith accordingly). Thus, in some embodiments, the correction terms can be further adjusted and / or correlated as appropriate to further compensate for such differences associated with different sized faces of the person 192 at the same distance 102 from the imaging system 100.

[0097] As discussed with respect to blocks 1232, 1245, and 1255 of FIG. 12, various techniques are contemplated to provide user feedback regarding the corrected temperature measurement of the inner canthus 402. In embodiments, a user (e.g., the person 192) can look at the thermal imager 164 and receive feedback regarding the user’s position relative to the thermal imager 164 and / or the determined body temperature of the user. For example, the user can see an overlay or other notification in the thermal image that provides a visual indication of the status of the thermal imager 164, the position of the user (e.g., too close, too far, etc.), and / or the determined body temperature of the user (e.g., below normal, normal, or elevated). Figure 12

[0098] As discussed with respect to block 1247 of FIG. 12, various embodiments utilize statistical analysis methods in determining an elevated body temperature of a user. For example, a threshold can be set using a running average of determined body temperatures to accurately determine whether a user is running a fever. For example, such a running average can take into account environmental factors (e.g., ambient temperature or other characteristics) that can otherwise affect a human body temperature. Figures 13-18

[0099] Various notifications or indications for providing feedback to a user regarding temperature calculations and determined temperature measurements are illustrated in accordance with one or more embodiments of the present disclosure. For example, as discussed with respect to block 1232 of FIG. 12, the logic device 168 can generate a notification regarding the distance 102 to the person 192. As discussed with respect to block 1245 of FIG. 12, the logic device 168 can generate a notification providing the corrected temperature measurement of the person 192. Additionally, as discussed with respect to block 1255 of FIG. 12, the logic device 168 can generate a notification of an elevated body temperature. Figure 12 Figure 12 Figure 12 Figure 13

[0100] Figure 12 ​​​​​A first notification 1300 is shown. As illustrated, the first notification 1300 can be an overlay on the face of the person 192, although other configurations are contemplated, including for example one or more notifications or interfaces (e.g., web page interfaces) provided on the display 178. The first notification 1300 can be configured to provide a first indication to the user regarding the temperature calculation. For example, the first notification 1300 can indicate that the system is currently calculating the temperature of the person 192, that the person 192 is properly positioned (e.g., within a preferred distance range), and / or the like. The first notification 1300 can be a first pattern, type, and / or color (e.g., a cyan overlay) to distinguish from other indications, as provided herein. The first notification 1300 can be generated in block 1232 of the method 1200. Figure 14 The first notification 1300 can be generated in block 1232 of the method 1200.

[0101] Figure 12 A second notification 1400 is shown. Similar to the first notification 1300, the second notification 1400 can be an overlay on the face of the person 192, a notification, and / or an interface (e.g., a web page interface) provided on the display 178. The second notification 1400 can be configured to provide a second indication to the user regarding the temperature calculation. For example, the second notification 1400 can indicate that the system is in a calibration mode, that the person 192 is positioned too close, and / or the like. The second notification 1400 can be a second pattern, type, and / or color (e.g., a yellow overlay) to distinguish from other indications, as provided herein. The second notification 1400 can be generated in block 1232 of the method 1200. Figure 15 The second notification 1400 can be generated in block 1232 of the method 1200.

[0102] Figure 12 A third notification 1500 is shown, which can be an overlay on the face of the person 192, a notification, and / or an interface (e.g., a web page interface) provided on the display 178. The third notification 1500 can be configured to provide a third indication to the user regarding the temperature calculation. For example, the third notification 1500 can indicate that the person 192 is not properly positioned, e.g., outside of a preferred distance range. In such embodiments, the third notification 1500 can provide feedback indicating that the person 192 move relative to the camera to provide a thermal image with sufficient pixels for canthus radiometric measurements, as described above. The third notification 1500 can be a third pattern, type, and / or color (e.g., a purple overlay) to distinguish from other indications, as provided herein. The third notification 1500 can be generated in block 1232 of the method 1200. Figure 16 The third notification 1500 can be generated in block 1232 of the method 1200.

[0103] Figure 12A fourth notification 1600 is shown, which can be an overlay, notification, and / or interface (e.g., web interface) provided on the face of the person 192 on the display 178. The fourth notification 1600 can be configured to provide a fourth indication to the user, e.g., regarding the determined temperature measurement of the person 192. For example, the fourth notification 1600 can indicate that the detected temperature of the person 192 is below normal, e.g., below a normal range specific to the person 192 or in general. The fourth notification 1600 can be a fourth pattern, type, and / or color (e.g., blue overlay) to distinguish from other indications, as provided herein. The fourth notification 1600 can be generated in block 1245 or block 1255 of the method 1200. Figure 17 The fourth notification 1600 can be generated in block 1245 or block 1255 of the method 1200.

[0104] Figure 12 A fifth notification 1700 is shown, which can be an overlay, notification, and / or interface (e.g., web interface) provided on the face of the person 192 on the display 178. The fifth notification 1700 can be configured to provide a fifth indication to the user, e.g., regarding the determined temperature measurement of the person 192. For example, the fifth notification 1700 can indicate that the detected temperature of the person 192 is normal, e.g., within a normal range specific to the person 192 or in general. The fifth notification 1700 can be a fifth pattern, type, and / or color (e.g., green overlay) to distinguish from other indications, as provided herein. The fifth notification 1700 can be generated in block 1245 or block 1255 of the method 1200. Figure 18 The fifth notification 1700 can be generated in block 1245 or block 1255 of the method 1200.

[0105] Figure 12 A sixth notification 1800 is shown, which can be an overlay, notification, and / or interface (e.g., web interface) provided on the face of the person 192 on the display 178. The sixth notification 1800 can be configured to provide a sixth indication to the user, e.g., regarding the determined temperature measurement of the person 192. For example, the sixth notification 1800 can indicate that the detected temperature of the person 192 is elevated, e.g., above a normal range specific to the person 192 or in general. The sixth notification 1800 can be a sixth pattern, type, and / or color (e.g., red overlay) to distinguish from other indications, as provided herein. The sixth notification 1800 can be generated in block 1245 or block 1255 of the method 1200. Figures 13-18 The sixth notification 1800 can be generated in block 1245 or block 1255 of the method 1200.

[0106] Reference is made to Figure 19Each notification 1300, 1400, 1500, 1600, 1700, or 1800 may be a rectangular overlay that captures the face of person 192. Such examples are merely illustrative, and notifications 1300, 1400, 1500, 1600, 1700, and 1800 may have other configurations, including, for example, circular, oval, or polygonal configurations. In an embodiment, each notification 1300, 1400, 1500, 1600, 1700, or 1800 may capture the inner canthus 402 of person 192. In an embodiment, notifications 1300, 1400, 1500, 1600, 1700, and 1800 may highlight the inner canthus 402.

[0107] As shown, the imaging system 100 (e.g., neural network 300) can detect or adapt to one or more face masks 1310 (or other face coverings) worn by the person 192. For example, a correction term can be determined to compensate for face covering attenuation. In this regard, the correction term can be a function of the type of mask 1310, the color of mask 1310, the material properties of mask 1310, the position of mask 1310 relative to the inner canthus 402, and / or other mask properties, etc. One or more mask properties can be determined by performing analysis of one or more captured thermal images of the person 192.

[0108] Figure 12 A workflow 1900, executed by system 100 according to an embodiment of the present disclosure, is illustrated to determine whether a person has elevated or normal temperature using a statistical model. Workflow 1900 provides a method for updating the statistical model and providing the resulting elevated or normal temperature determination, indicating whether the person 192 has elevated temperature compared to a previous sample. It can be... Figure 12 Workflow 1900 is executed in box 1247.

[0109] As shown in the figure, one or more thermal images can be captured (e.g., by thermal imager 164, for example in...). Figure 12 The detection system 1902 is provided in box 1215. The detection system 1902 may be a module or program running on logic device 168 and / or other logic devices of system 100. The detection system 1902 may detect one or more facial and / or facial features in a thermal image. For example, the detection system 1902 may detect and highlight the inner canthus 402 of a person 192 within a thermal image. In an embodiment, the detection system 1902 may detect a face covering (e.g., a mask 1310) worn by the person 192 (e.g., using neural network 300). In an embodiment, the detection system 1902 may... Figure 12 The thermal image is processed in box 1220. The detection system 1902 can add a tracking ID 1904 to the detection (e.g., "ID01" as shown in the figure).

[0110] The output of the detection system 1902 (e.g., thermal images with tracking IDs 1904) can be provided to a measurement system 1906. Similar to the detection system 1902, the measurement system 1906 can be a module or program running on the logic device 168 and / or other logic devices of the system 100. The measurement system 1906 can determine temperature measurements 1908 at selected points of the thermal images. For example, the measurement system 1906 can use corresponding pixels of the thermal images to determine a temperature measurement 1908 at the inner canthus 402 of the person 192, as described above, for example, in block 1233 of Figure 12 The measurement system 1906 can determine and / or apply a correction term to the temperature measurements 1908 (e.g., prior to detection) to compensate for attenuation associated with the facial covering 1310, as described above, for example, in block 1235 and / or block 1240 of Figure 12 In some embodiments, the measurement system 1906 can use the temperature measurements 1908 to determine a body temperature of the person 192.

[0111] The output of the measurement system 1906 (e.g., thermal images with tracking IDs 1904 and measured temperatures 1908) can be provided to a sampling system 1910. The sampling system 1910 can be a module or program running on the logic device 168 and / or other logic devices of the system 100. The sampling system 1910 can create one sample 1914 for each tracking ID 1904. For example, the sample 1914 can include the tracking ID 1904 and the measured temperature 1908.

[0112] The samples 1914 can be provided to an anomaly detection system 1920. The anomaly detection system 1920 can be a module or program running on the logic device 168 and / or other logic devices of the system 100. The anomaly detection system 1920 can process (e.g., compare) the measured temperatures 1908 to a statistical model 1922, as described above, for example, in block 1247 of Figure 12 If the measured temperature 1908 is within a threshold of the statistical model 1922, then the temperature of the person 192 is determined to be normal (e.g., at block 1250 of Figure 12 However, if the measured temperature 1908 is above the statistical model 1922, then the temperature of the person 192 is determined to be elevated (e.g., at block 1250 of Figure 12

[0113] The statistical model 1922 can be any mathematical model that embodies one or more statistical assumptions about inner canthus temperature measurements. The normal temperature determination can be based on one or more measured temperatures 1908 exceeding a threshold (e.g., exceeding a threshold probability). The elevated temperature determination can be based on one or more measured temperatures 1908 exceeding or falling below a threshold (e.g., falling below a threshold probability).

[0114] As described above with respect to​​ As discussed above with respect to block 1255, one or more notifications can be generated to identify an elevated body temperature in response to the body temperature exceeding a threshold value. For example, a normal temperature determination can be provided at notification 1926 (e.g., fifth notification 1700). An elevated temperature determination can be provided at notification 1928 (e.g., sixth notification 1800). Notifications 1926 and 1928 can be provided on display 178, a user interface, or other device. In embodiments, the elevated temperature determination can trigger an alarm and / or a request for appropriate follow-up procedures. For example, a secondary measurement method can be triggered to determine whether person 192 is feverish.

[0115] Statistical model 1922 can be dynamic. For example, each time a face is within an appropriate distance for measurement, a measured alar region temperature (e.g., a measured temperature of alar 402) can be added to statistical model 1922 to provide a continuous average. The continuous average can be maintained from all previous alar temperature measurements to identify a temperature above average. For example, an elevated temperature determination can be made if a measured alar region temperature is above the current continuous average.

[0116] Where applicable, various embodiments provided by the present disclosure can be implemented using hardware, software, or combinations of hardware and software. Moreover, where applicable, the various hardware components and / or software components set forth herein can be combined into composite components comprising software, hardware, and / or both without departing from the spirit of the present disclosure. Where applicable, the various hardware components and / or software components set forth herein can be separated into sub-components comprising software, hardware, and / or both without departing from the spirit of the present disclosure. In addition, where applicable, it is contemplated that software components can be implemented as hardware components, and vice versa, without departing from the spirit of the present disclosure.

[0117] Software (e.g., program code and / or data) of the present disclosure, where applicable, can be stored on one or more computer-readable media. It is also contemplated that software identified herein can be implemented using one or more general purpose or special purpose computers and / or computer systems, networked and / or otherwise.

[0118] The embodiments described above illustrate but do not limit the application. It should also be understood that numerous modifications and variations are possible in light of the above teachings. It is therefore to be understood that the scope of the application should be limited only by the appended claims.

Claims

1. A method for distance compensation in medial canthal thermal imaging temperature measurement, the method comprising: Use a thermal imager to capture thermal images of a person; The corresponding pixels of the thermal image are used to determine the uncompensated temperature measurement associated with the inner canthus of a human face; Based on the correlation between the width and distance of the face of each of multiple objects, multiple original thermal images of multiple objects are preprocessed to determine one or more fitting constants; Determine a correction term that varies with the distance between the thermal imager and the person and the one or more fitting constants, wherein determining the correction term includes determining the number of pixels in the thermal image associated with the width of the face; as well as The correction term is applied to the uncompensated temperature measurement to provide a corrected temperature measurement associated with the inner canthus, thereby compensating for the attenuation associated with the distance.

2. The method according to claim 1, further comprising: The distance is determined using a predetermined correlation between the number of pixels and the distance.

3. The method according to claim 1, wherein, The width of the face includes the width from ear to ear.

4. The method of claim 1, further comprising detecting a person's face and inner canthus in the thermal image.

5. The method according to claim 4, wherein, The detection includes processing the thermal image using an artificial neural network.

6. The method according to claim 1, further comprising: Based on a defined continuous average body temperature, a threshold is determined using a statistical model; and The elevated body temperature of a person is determined by using the corrected temperature measurement to determine whether the corrected temperature measurement exceeds the threshold.

7. The method of claim 6, further comprising generating a notification to inform the user of the thermal imager of an increase in body temperature.

8. The method of claim 1, further comprising repeating the method for multiple persons at multiple distances from the thermal imager.

9. The method according to claim 1, wherein, The method is performed using a portable thermal imaging camera that includes the thermal imager.

10. A system for distance compensation in inner canthal thermal imaging temperature measurement, the system comprising: Thermal imager; as well as A logic device, the logic device being configured to: Operate the thermal imager to capture thermal images of a person; Using the corresponding pixels of the thermal image, an uncompensated temperature measurement associated with the inner canthus of a human face is determined; Based on the correlation between the width and distance of the face of each of multiple objects, multiple original thermal images of multiple objects are preprocessed to determine one or more fitting constants; Determine a correction term that varies with the distance between the thermal imager and the person and the one or more fitting constants, wherein determining the correction term includes determining the number of pixels in the thermal image associated with the width of the face; as well as The correction term is applied to the uncompensated temperature measurement to provide a corrected temperature measurement associated with the inner canthus, thereby compensating for the attenuation associated with the distance.

11. The system according to claim 10, wherein, The logic device is configured to: The distance is determined using a predetermined correlation between the number of pixels and the distance.

12. The system according to claim 10, wherein, The width of the face includes the width from ear to ear.

13. The system according to claim 10, wherein, The logic device is configured to detect a person's face and inner canthus in the thermal image.

14. The system according to claim 13, wherein, The logic device is configured to process the thermal image via an artificial neural network to detect the face and inner canthus.

15. The system according to claim 10, wherein, The logic device is configured to: Based on a defined continuous average body temperature, a threshold is determined using a statistical model; and The elevated body temperature of a person is determined by using the corrected temperature measurement to determine whether the corrected temperature measurement exceeds the threshold.

16. The system according to claim 15, wherein, The logic device is configured to generate a notification to inform the user of the thermal imager of an increase in body temperature.

17. The system according to claim 10, wherein, The logic device is configured to determine calibrated temperature measurements for multiple individuals at multiple distances from the thermal imager.

18. The system according to claim 10, wherein, The system is a portable thermal imaging camera.

Images