Distance compensation system and method for thermal imaging temperature measurements of the inner canthus

Abstract

Various techniques are disclosed for providing improved human body temperature detection using a thermal image of the inner canthus. As an example, a method comprises the step of capturing a thermal image of a person using a thermal imager. The method also comprises the step of determining an uncompensated temperature measurement associated with the inner canthus of the person's face using the corresponding pixels of the thermal image. The method also comprises the step of determining a correction term as a function of the distance between the thermal imager and the person. The method also comprises the step of 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

Technology Field

[0001] Cross-reference of related applications

[0002] This application claims the priority and benefit of U.S. Provisional Patent Application No. 63 / 044,516, filed June 26, 2020, titled “Distance Compensation For Thermal Imaging Temperature Measurement Of Inner Canthus Systems And Methods,” the entire contents of which are incorporated herein by reference.

[0003] This application claims the priority and benefit of U.S. Provisional Patent Application No. 63 / 158,273, filed March 8, 2021, titled “Thermal Imaging Temperature Measurement Of Inner Canthus Systems And Methods,” the entire contents of which are incorporated herein by reference.

[0004] Technology field

[0005] The present invention generally relates to thermal imaging, and more specifically, to compensating for distance-related attenuation of thermal imaging temperature measurements and detecting a person's face and canthus. Background Technology

[0006] 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, these systems can be used to detect body temperature. These systems can be particularly useful for detecting elevated body temperature associated with possible health conditions (e.g., infection or disease).

[0007] In some cases, the inner canthus of the human eye (e.g., the inner corner where the upper and lower eyelids meet, also called the medial canthus) can be used for temperature detection. In particular, the inner canthus can be used as a general approximation of body temperature. As such, an elevated inner canthus temperature can be correlated with an overall elevated body temperature.

[0008] However, existing approaches to inner canthal temperature detection are prone to errors. For example, the inner canthus may comprise a relatively small portion of the entire thermal image capturing a person's face or body. Consequently, the inner canthus may be associated with only a few pixels of the captured thermal image. As a result, the temperature value measured in relation to the inner canthus may be significantly reduced with distance due to the influence of other drifting thermal wavelengths from neighboring facial features. Furthermore, the inner canthus may be difficult to detect, particularly when a person is wearing a mask or other face covering. Meanwhile, content related to this application is disclosed in Korean Published Patent Application No. 10-2013-0113341. The problem to be solved

[0009] Therefore, an improved approach to temperature detection using thermal imaging of the inner canthus is needed, which provides improved accuracy compared to conventional technology. means of solving the problem

[0010] Various techniques are disclosed for providing improved human body temperature detection using a thermal image of the inner canthus. In particular, a thermal imaging system and a related method are provided that compensate for distance-related temperature attenuation to improve the accuracy of human body temperature detection. These techniques may be particularly useful for accurately detecting possible elevated human body temperatures associated with possible health conditions.

[0011] Various techniques for providing improved face detection are disclosed. For example, a thermal imaging system and a method are provided for detecting a person's face and inner canthus in a thermal image and determining the temperature measurement of the person's inner canthus and body temperature. For example, to identify an elevated body temperature exceeding a threshold (e.g., exceeding the moving average of a statistical model of temperature measurements), an alarm may be activated and / or a notification may be generated based on the determined temperature(s).

[0012] In one embodiment, the method of the present invention comprises the steps of: capturing a thermal image of a person using a thermal imager; determining a correction term as a function of the distance between the thermal imager and the person; and applying the correction term to provide a corrected temperature measurement related to the inner corner of the person's face to compensate for attenuation related to the distance.

[0013] In another embodiment, the system of the present invention includes a thermal imager; and a logic device configured to operate the imager to capture a thermal image of a person, determine a correction term as a function of the distance between the thermal imager and the person, and apply the correction term to provide a corrected temperature measurement related to the inner corner of the person's face to compensate for attenuation related to the distance.

[0014] In another embodiment, the method of the present invention includes the steps of capturing a thermal image of a person using a thermal imager, detecting a person's face and inner corner of the eye in the thermal image using an artificial neural network, determining a temperature measurement of the inner corner of the eye using a corresponding pixel of the thermal image, and determining the person's body temperature using the temperature measurement.

[0015] In another embodiment, the system of the present invention includes a thermal imager and a logic device configured to operate the thermal imager to capture a thermal image of a person, to detect a person's face and inner corner of the eye in the thermal image using an artificial neural network, to determine a temperature measurement of the inner corner of the eye using a corresponding pixel of the thermal image, and to determine the person's body temperature using the temperature measurement.

[0016] The scope of the invention is defined by the claims incorporated by reference in this section. By considering the following detailed description of one or more embodiments, those skilled in the art will be provided with a more complete understanding of the embodiments of the invention, as well as the realization of additional advantages of the invention. First, reference will be made to the attached drawing sheet, which will be briefly described. Brief explanation of the drawing

[0017] FIG. 1 illustrates a block diagram of an imaging system according to one embodiment of the present disclosure. FIG. 2 illustrates a block diagram of a thermal imaging device according to one embodiment of the present disclosure. FIG. 3 illustrates a block diagram of an artificial neural network according to one embodiment of the present disclosure. FIG. 4 illustrates a series of thermal images captured at different distances according to one embodiment of the present disclosure. FIG. 5 illustrates a thermal image undergoing distance analysis according to one embodiment of the present disclosure. FIG. 6 illustrates a plot of uncompensated temperature measurements according to one embodiment of the present invention. FIG. 7 illustrates a plot of corrected temperature measurements according to one embodiment of the present disclosure. FIGS. 8 and 9 illustrate thermal images having associated uncompensated temperature measurements according to an embodiment of the present disclosure. FIGS. 10 and 11 illustrate thermal images having associated corrected temperature measurements according to embodiments of the present disclosure. FIG. 12 illustrates a process for determining a corrected temperature measurement according to one embodiment of the present disclosure. FIGS. 13 to 18 illustrate various overlays used to provide feedback to a user regarding temperature calculation and determined temperature measurements according to one or more embodiments of the present disclosure. FIG. 19 illustrates a workflow for determining whether a person has an elevated or normal body temperature using a statistical model according to one embodiment of the present disclosure. Embodiments and advantages of the present invention are best understood by referring to the following detailed description. It should be understood that similar reference numbers are used to identify similar elements illustrated in one or more drawings. Specific details for implementing the invention

[0018] According to embodiments further discussed herein, various methods and systems are provided for processing thermal images to determine the temperature of a human (e.g., person) in a manner that compensates for possible distance attenuation. In particular, the techniques discussed herein are particularly useful for providing accurate temperature measurements of a person's inner canthus.

[0019] In this regard, the inner corner of the eye is often the warmest feature of the human face and serves as a reasonable approximation of body temperature (for example, an elevated inner corner temperature can generally be associated with an elevated core body temperature). Therefore, by improving the accuracy of inner corner temperature measurements, elevated body temperatures associated with various health conditions can be detected more accurately.

[0020] When capturing thermal images of a human face, most of the thermal radiation associated with the inner canthus is provided by a small number of pixels in the resulting thermal image. However, these pixels and other surrounding pixels may also be associated with thermal radiation contributions from other parts of the face (e.g., eyes, eyebrows, nose, etc.). This effect can become more pronounced as distance increases. For example, at greater distances, fewer pixels (and therefore a smaller proportion of the total pixels in the thermal image) will be associated with the inner canthus itself, while an increasing number (e.g., a larger proportion) of pixels will be associated with other parts of the face. Consequently, the overall influence of thermal radiation associated with the inner canthus will decrease in the captured thermal image as the distance from the person increases. Therefore, when these thermal images are used to detect the temperature of the inner canthus (e.g., to detect a possible body temperature rise), the detected temperature can vary significantly with distance. This distance-based temperature variation can make it difficult to accurately detect a possible body temperature rise.

[0021] According to embodiments discussed in this specification, a compensation technique is provided in which a correction term can be applied to a temperature measurement related to the inner corner of a person detected using a thermal image. For example, the width and / or area of ​​the person's face in the thermal image (e.g., in pixels) may 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 corner temperature regardless of the distance between the thermal imager and the person being imaged.

[0022] This implementation is particularly useful in applications where the temperature of multiple people at different distances must be measured, such as when scanning a crowd for possible elevated temperatures. By applying a correction term as discussed here, accurate body temperature can be determined in such applications even when people are dispersed at different distances from the thermal imaging system.

[0023] Additionally, according to one embodiment discussed in this specification, various techniques are included to provide user feedback regarding temperature, the position of the thermal imager, and other features. In some embodiments, statistical analysis may be used to provide a moving average of the user's body temperature. This moving average may be used to determine a threshold for detecting an elevated body temperature.

[0024] Now, returning to the drawings, FIG. 1 illustrates a block diagram of an imaging system (100) according to one embodiment of the present disclosure. As illustrated, the imaging system (100) includes a housing (151) (e.g., a camera body) having 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), a user control unit (170), a memory (172), a communication interface (I / F) (174), a machine-readable medium (176), a distance sensor (177), a display (178), other sensors (180), and other components (182).

[0025] In various embodiments, the imaging system (100) may be implemented as a camera system, such as, for example, 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) may be positioned to receive infrared (194) from a scene (190) (e.g., the field of view of the imaging system (100)). In various embodiments, the scene (190) may include various objects of interest, such as one or more people (192) (e.g., humans).

[0026] As illustrated, a human (192) (e.g., a person) may be positioned at a certain distance (102) from the imaging system (100). In various embodiments, the distance (102) may vary over time. For example, if the person (192) and / or the imaging system (100) move while a series of thermal images are being captured, different thermal images may be captured at different associated distances (102).

[0027] The distance sensor (177) may be implemented as any suitable type of device used to detect distance (102). Such implementation may include, for example, a time-of-flight (ToF) sensor, a LIDAR system, a radar system, and / or other suitable ones. In some embodiments, the distance (102) may be determined using other techniques, such as processing a thermal image to determine the number of pixels in a thermal image associated with various features of a person (192) as discussed herein.

[0028] Infrared light (194) is received through an aperture (158) and passes through one or more filters (160) which may be provided to selectively filter specific thermal wavelengths of interest for an image to be captured by a thermal imager (164). An optical component (162) (e.g., an optical assembly including one or more lenses, additional filters, a transmission window, and / or other optical components) passes the filtered infrared light (194) for capture by the thermal imager (164).

[0029] As such, it will be understood that the filter (160) and / or optical component (162) may work together to selectively filter a portion of the infrared radiation (194) so ​​that only the desired wavelength and / or desired thermal radiation intensity is ultimately received by the thermal imager (164). In various embodiments, any desired combination of these components may be provided (e.g., various components may be appropriately included or omitted for various implementations).

[0030] A thermal imager (164) may capture a thermal image of a scene (190) in response to infrared light (194). The thermal imager (164) may include an array of sensors for capturing a thermal image (e.g., a thermal image frame) of a scene (190). In some embodiments, it may include one or more analog-to-digital converters for converting an analog signal captured by a sensor into digital data (e.g., a pixel value) to provide a captured image. An imager interface (166) may be used to provide a captured image to a logic device (168), and the logic device (168) may be used to process the captured image, store the original and / or processed image in memory (172), and / or retrieve the image stored in memory (172). Further implementation details of one embodiment of the thermal imager (164) are further discussed herein in relation to FIG. 2.

[0031] The logic device (168) may 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 for storing 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. The logic device (168) is configured to interface and communicate with various components of the imaging system (100) to perform the various methods and processing steps described herein. In various embodiments, the processing instructions may be code (e.g., software and / or configuration data) that may be integrated into software and / or hardware as part of the logic device (168), or stored in memory (172) and / or a machine-readable medium (176). In various embodiments, instructions stored in memory (172) and / or machine-readable media (176) allow a logic device (168) to perform various operations discussed herein and / or control various components of the system (100) for such operations.

[0032] The memory (172) may include one or more memory devices (e.g., one or more memories) to store data and information. The one or more memory devices may include various types of memory, such as volatile and non-volatile memory devices, such as RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically-Erasable Read-Only Memory), flash memory, fixed memory, removable memory, and / or other types of memory.

[0033] A machine-readable medium (176) (e.g., memory, hard drive, compact disc, digital video disc, or flash memory) may be a non-transient machine-readable medium that stores instructions for execution by a logic device (168). In various embodiments, the machine-readable medium (176) may be included as part of an imaging system (100) and / or separated from the imaging system (100), in which case the stored instructions may be provided by connecting the machine-readable medium (176) to the imaging system (100) or by downloading instructions from the machine-readable medium (e.g., containing non-transient information) by the imaging system (100) (e.g., via a wired or wireless link).

[0034] A logic device (168) may be configured to process a captured image and display it on a display (178) so that a user can view it. The display (178) may 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) may be configured to display images and information on the display (178). For example, the logic device (168) may be configured to retrieve images and information from memory (172) and provide images and information to the display (178) for display to a user of the system (100). The display (178) may include display electronics that can be utilized by the logic device (168) to display such images and information.

[0035] The user control unit (170) may include any desired type of user input and / or interface device having one or more user-operable components, such as one or more buttons, slide bars, knobs, keyboards, joysticks, and / or other types of control units configured to generate one or more user-operable input control signals. In some embodiments, the user control unit (170) may be integrated with the display (178), such as a touchscreen, to operate as both the user control unit (170) and the display (178). A logic device (168) may be configured to detect control input signals from the user control unit (170) and to respond to the detected control input signals received therefrom. In some embodiments, parts of the display (178) and / or the user control unit (170) may be implemented by a suitable part of a tablet, a laptop computer, a desktop computer, and / or other types of devices.

[0036] In various embodiments, the user control unit (170) may be configured to include one or more other user-operable mechanisms for providing various other control operations of the imaging system (100), such as autofocus, menu activation and selection, field of view (FoV), brightness, contrast, gain, offset, space, time and / or various other functions and / or parameters.

[0037] The imaging system (100) may include various types of other sensors (180), such as a microphone, a navigation sensor, a temperature sensor, and / or other suitable sensors.

[0038] The logic device (168) may be configured to receive images from the imager interface (166) and signals and data from the distance sensor (177), other sensors (180) and / or the user control unit (170) and to transmit them to one or more external devices (e.g., remote systems) via the communication interface (174) (e.g., via wired and / or wireless communication). In this regard, the communication interface (174) may be implemented to provide wired communication via a cable and / or wireless communication via an antenna. For example, the communication interface (174) may 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) may include an antenna coupled thereto for wireless communication purposes. In another embodiment, the communication interface (174) may be configured to interface with a Digital Subscriber Line (DSL) modem, a Public Switched Telephone Network (PSTN) modem, an Ethernet device, and / or various other types of wired and / or wireless network communication devices configured to communicate with a network.

[0039] In some embodiments, the network may be implemented as a single network or a combination of multiple networks. For example, in various embodiments, the network may include the Internet and / or one or more intranets, wired networks, wireless networks, and / or other suitable types of communication networks. In other examples, the network may include a wireless communication network (e.g., a cellular phone network) configured to communicate with other communication networks, such as the Internet. As such, in various embodiments, the imaging system (100) and / or its individual related components may be associated with specific network links, such as a Uniform Resource Locator (URL), an Internet Protocol (IP) address, and / or a mobile phone number.

[0040] The imaging system (100) may include various other components (182), such as a speaker, an additional display, a visual indicator (e.g., a record indicator), a vibration actuator, a battery or other power supply (e.g., rechargeable, etc.), and / or additional components suitable for a specific implementation.

[0041] Although various feature parts of the imaging system (100) are shown together in FIG. 1, any of the various exemplified components and sub-components can be implemented in a distributed manner and appropriately used remotely from each other.

[0042] Although the imaging system (100) has been described in the context of a thermal imaging system, other embodiments are also considered. In some embodiments, the aperture (158), filter (160), optical component (162) and / or imager (164) may be implemented to pass and capture other wavelengths, such as visible light wavelengths, in addition to or instead of thermal wavelengths. For example, the imaging system (100) may be implemented to capture both the thermal image and the visible light image of the scene (190) for comparison to detect scaling or other phenomena. As another example, different imaging systems (100) implemented for different wavelengths may be used to capture the thermal image and the visible light image of the scene (190).

[0043] FIG. 2 illustrates a block diagram of a thermal imager (164) according to one embodiment of the present disclosure. In this illustrated embodiment, the thermal imager (164) is a focal plane array (FPA) comprising a sensor array (230) of infrared sensors (232) (e.g., implemented in unit cells) and a readout integrated circuit (ROIC) (202). Although an 8x8 array of infrared sensors (232) is illustrated (e.g., corresponding to rows and columns of pixels), this is merely for illustrative and easy-to-understand purposes. Any desired sensor array size may be used as desired.

[0044] Each infrared sensor (232) may be implemented by an infrared detector, such as a microbolometer and associated circuitry, to provide image data (e.g., data values ​​related to captured voltage) for pixels of a captured thermal image. In this regard, a time-multiplexed electrical signal may be provided to the ROIC (202) by the infrared sensor (232).

[0045] The ROIC (202) includes a bias generation and timing control circuit (204), a column amplifier (205), a column multiplexer (206), a row multiplexer (208), and an output amplifier (210). An image captured by the infrared sensor (232) may be provided by the output amplifier (210) to a logic device (168) and / or any other suitable component to perform the various processing techniques described herein. Further description of the ROIC and the infrared sensor (e.g., a microbolometer circuit) can be found in U.S. Patent No. 6,028,309, issued February 22, 2000, the entire contents of which are incorporated herein by reference.

[0046] FIG. 3 illustrates a block diagram of an artificial neural network (300) according to one embodiment of the present disclosure. For example, in some embodiments, the neural network (300) may be implemented by a logic device (168).

[0047] As illustrated, the neural network (300) comprises various nodes (302) arranged in a plurality of layers, including an input layer (304) that receives one or more inputs (310), a hidden layer (306), and an output layer (308) that provides one or more outputs (320). Although a specific number of nodes (302) and layers (304, 306 and 308) are illustrated, any desired number of these features may be provided in various embodiments.

[0048] In some embodiments, the neural network (300) may be used to perform face detection on various thermal images captured by the imaging system (100) and provided to the input (310) of the neural network (300). The result of such face detection may be provided by the neural network at the output (320). In some embodiments, the neural network (300) may be trained by providing a thermal image of a human face (e.g., stored in a machine-readable medium (176)) to the input (310).

[0049] FIG. 4 illustrates a series of thermal images (410 to 420) capturing a person (192) at different distances according to one embodiment of the present disclosure. For example, as illustrated, the thermal images (410 to 420) were captured at various distances ranging from 0.5 meters to 4 meters. Also, as illustrated, the inner corner (402) of the person (192) is present in each of the thermal images (410 to 420). However, the size of the inner corner (402) becomes progressively smaller in the thermal images (410 to 420) as the distance increases. In this regard, the number of pixels in the thermal images (410 to 420) associated with the inner corner (402) decreases correspondingly as the distance increases. Furthermore, the contribution of other facial features will increase proportionally and thus reduce the overall temperature of the captured pixels associated with the inner corner (402).

[0050] For example, as further illustrated in FIG. 4, the detected uncompensated temperature of the inner corner (402) (performed, for example, by processing the values ​​of pixels determined to be associated with the inner corner (402)) decreases with distance 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). Since this error can determine whether a person's measured body temperature exceeds a threshold related to health status, the change may be important in the context of detecting an elevated body temperature.

[0051] According to the various embodiments discussed herein, a correction term may be determined to compensate for such distance-based attenuation. In this regard, said correction term may be a function of distance. For example, this can generally be expressed by the following Equation 1:

[0052] CompensatedTemp = MeasuredTemp + Correction(distance) (Equation 1)

[0053] In Equation 1, CompensatedTemp is a corrected temperature measurement of the inner corner (402) compensated for with respect to distance (e.g., a compensated temperature value), MeasuredTemp is an uncompensated temperature measurement of the inner corner (402) determined by analyzing a thermal image, and Correction is a correction term applied to MeasuredTemp as a function of distance. Here, distance is the distance (102) between the imaging system (100) and the person (192). Thus, the Correction (distance) presented in Equation 1 may use an appropriate distance-based correlation to provide the correction term in various embodiments.

[0054] The distance (102) can be determined through various techniques. For example, in some embodiments, the distance (102) may be determined by a distance sensor (177) using a suitable type of sensor and / or system as discussed. In some embodiments, the distance (102) may be determined by referring to other possible features within the scene (190) having a known distance to the imaging system (100).

[0055] In some embodiments, the distance (102) may be determined by performing an analysis of one or more captured thermal images of a person (192). For example, FIG. 5 illustrates a thermal image (402) on which a distance analysis is performed according to one embodiment of the present disclosure. In some embodiments, a logic device (168) may perform the analysis discussed in relation to FIG. 5.

[0056] In FIG. 5, a thermal image (402) is processed to detect the face (502) of a person (192) including ears (510, 512). Additionally, the face width (514) between the ears (510, 512) (e.g., referred to as "ear2ear" or "e2e") is calculated. This face width (514) can be used to determine an approximate distance (102). In this regard, the imaging system (100) may be pre-calibrated to correlate the face width (514) (e.g., the number of pixels across the width (514)) with the distance (102) (e.g., with appropriate information stored in a machine-readable medium (176)). For example, a person generally has a relatively narrow face width (e.g., generally 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., the face width (514) is assumed to be the average face width) and the distance (102). In this way, 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 for the distance (102).

[0057] Although the correlation between face width (514) and distance (102) has been discussed, other correlations may also be used, such as pre-calibrating the imaging system (100) to determine the number of pixels related to the area of ​​the face (502) (e.g., the number of pixels of a thermal image related to the face) and to correlate the average face area and distance (102).

[0058] To consider the face width (514) correlation in more detail, Equation 1 can be updated to specifically address the face width (514) (e.g., "ear2ear" or "e2e") as presented in the following Equation 2:

[0059] CompensatedTemp = MeasuredTemp + Correction(ear2ear) (Equation 2)

[0060] In Equation 2, ear2ear is the number of pixels of the thermal image (410) associated with the face width (514). In some embodiments, the correction term Correction(ear2ear) may be determined according to the following Equation 3:

[0061] Correction(ear2ear) = p1 / (p2 + ear2ear) (Equation 3)

[0062] In Equation 3, p1 and p2 are fitting constants corresponding to a predetermined correlation between face width (514) (e.g., ear2ear) and distance (102).

[0063] Looking at Equation 3, as the ear2ear value decreases (e.g., in response to a decrease in face width (514) associated with a larger value of distance (102)), the magnitude of Correction (ear2ear) (e.g., correction term) increases to compensate for distance-based attenuation for pixels associated with the inner corner (402).

[0064] The result of this compensation can be further understood by reviewing FIGS. 6 and 7. In this regard, FIG. 6 illustrates plots (610, 620, and 630) of uncompensated temperature measurements according to one embodiment of the present disclosure. In particular, plots (610, 620, and 630) show uncompensated temperature measurements determined for the inner corner of the eye (402) (indicated as Tmax(C) along the vertical axis) and corresponding face widths (514) of three different people (192) determined from a series of thermal images (indicated as ear2ear along the horizontal axis) (e.g., each plot (610, 620, and 630) corresponds to a temperature measurement associated with a different person (192)). It can be seen that a larger value of ear2ear corresponds to a smaller distance (102) associated with the captured thermal image. As shown, plots (610, 620, and 630) show a significant distance-based attenuation of about 2°C in the temperature measurements (e.g., over a range from a minimum of about 32.9°C to a maximum of about 35°C).

[0065] In contrast, FIG. 7 illustrates plots (710, 720, and 730) of corrected temperature measurements according to one embodiment of the present disclosure. In particular, plots (710, 720, and 730) illustrate corrected (e.g., distance-compensated) temperature measurements determined for the inner corner of the eye (402) and the corresponding face width (514) using the same thermal image of FIG. 6. For example, in some embodiments, the corrected temperature measurements of FIG. 7 may be determined by applying an appropriate correction term to the uncompensated temperature measurements of FIG. 6 (e.g., according to the technique discussed in relation to Equations 1 through 3).

[0066] As illustrated, plots (710, 720, 730) show substantially uniform temperature measurements for each person (192) within a small temperature range (e.g., a range from a minimum of about 35.4°C to a maximum of about 36°C). Furthermore, the variation in plot (710) is particularly well contained within a range of only 0.1°C. When comparing the compensated temperature measurements of plots (710, 720, 730) with the uncompensated temperature measurements of plots (610, 620, 630), the compensated temperature measurements provide a reliable representation of the angle temperature independently of the distance (102).

[0067] FIGS. 8 through 10 further illustrate the results of the temperature compensation technology discussed herein. For example, FIGS. 8 and 9 illustrate thermal images (800 and 900) having associated uncompensated temperature measurements according to an embodiment of the present disclosure. In FIG. 8, the thermal image (800) was captured from a distance (e.g., about 20 feet) from the thermal imaging system (100). The detected eye temperatures of the people (810, 812, 814) are 31.8 degrees Celsius, 31.3 degrees Celsius, and 32.0 degrees Celsius. Additionally, the average temperature of all people is 31.69 degrees Celsius.

[0068] In FIG. 9, the thermal image (900) was captured from a short distance (e.g., about 5 feet) from the thermal imaging system (100). The detected eye temperatures of the people (810, 812, 814) are 33.2°C, 32.5°C, and 33.1°C, respectively (e.g., all are higher than the temperatures in FIG. 8). Additionally, the average temperature of all people is 32.93°C (e.g., higher than the temperatures in FIG. 8). Thus, it can be seen that the uncompensated temperature measurements associated with FIG. 8 and 9 exhibit significant distance-based attenuation.

[0069] FIGS. 10 and 11 illustrate thermal images (1000, 1100) having associated compensated temperature measurements according to an embodiment of the present disclosure. In this regard, the thermal images (1000, 1100) use the same original captured thermal image data as the thermal images (800, 900), but include the results of compensated temperature measurements.

[0070] As shown in FIG. 10 (e.g., a thermal image (1000) captured from a distance of about 20 feet), the detected eye temperatures of people (810, 812, 814) are 33.8 degrees Celsius, 33.5 degrees Celsius, and 34.3 degrees Celsius, respectively. Additionally, the average temperature of all people is 33.86 degrees Celsius.

[0071] In FIG. 11, (e.g., a thermal image (1100) captured at a close distance of about 5 feet), the detected eye temperatures of people (810, 812, 814) are 33.7°C, 33.3°C, and 33.6°C, respectively (e.g., all are close to the temperatures in FIG. 10). Also, the average temperature of all people is 33.56°C (e.g., close to the temperatures in FIG. 10). Thus, the compensated temperature measurements associated with FIG. 10 and 11 show consistency independent of distance-based attenuation.

[0072] FIG. 12 illustrates a process (1200) for determining a compensated temperature measurement according to one embodiment of the present disclosure. In block 1210, a logic device (168) performs a preprocessing operation (e.g., pre-calibration) to determine the correlation between various features of a captured thermal image and a distance (102) in order to determine the fitting constants (p1, p2) of Equation 3. For example, in some embodiments, block 1210 includes capturing a plurality of thermal images of an object or person at different distances (102) from an imaging system (100) to determine the correlation between the number of pixels associated with various features (e.g., face width (514) or other human face features) and various distances (102). The logic device (168) can then determine the values ​​of fitting constants (p1, p2) suitable for compensating for distance-related variations of the features captured in the thermal images.

[0073] In block 1215, the thermal imager (164) captures one or more thermal images of one or more people (192) of interest in the scene (190).

[0074] In block 1220, the logic device (168) performs face detection (e.g., using a neural network (300) and / or other suitable face detection technology) to detect the location of the inner corner (402) and the face of a person (192) in a captured thermal image. For example, an artificial neural network (e.g., neural network (300)), a detection system (e.g., described below with reference to FIG. 19), and / or other suitable face detection technology may be used by the logic device (168) to detect the face and inner corner (402) of a person (192) in a thermal image. In an embodiment, block 1220 may include detecting a face covering, such as a mask or other type of face covering worn by the person (192), in a captured thermal image.

[0075] In block 1230, the logic device (168) determines the distance (102) to a person (192). As discussed, various techniques may be used. In some embodiments, a pixel-based approach may be performed by determining the face width (514) (e.g., ear2ear value) and / or other face features of the person (192) and correlating the distance (102) (e.g., through a predetermined correlation provided by block 1210). For example, the distance (102) may be determined using a predetermined correlation between the number of pixels of one or more face features (e.g., face width, face area, etc.) and the distance, but other configurations are considered. In other embodiments, a distance sensor (177) and / or other techniques may be appropriately used.

[0076] In block 1232, a notification regarding the distance (102) may be generated. For example, the imaging system (100) may generate a notification of the need for a person (192) to move in relation to the thermal imager (164) based on the determined distance. For example, the imaging system (100) may generate a notification indicating that the person (192) is mispositioned, such as being outside the desired distance range from the thermal imager (164). As a result, one or more blocks of FIG. 12 may be repeated until the person (192) is correctly positioned within the desired distance range. In this way, the person (192) can be properly aligned before temperature measurements are taken in the subsequent steps described below.

[0077] ============

[0078] In block 1233, the logic device (168) determines an uncompensated temperature measurement of the inner eye (402). For example, block 1233 may include determining a temperature associated with a pixel value of a thermal image corresponding to the inner eye (402). In various embodiments, this temperature may be determined, for example, by averaging and / or otherwise processing the corresponding pixel values.

[0079] In block 1235, the logic device (168) determines a correction term to be applied to a previously detected uncompensated temperature measurement. For example, the correction term may 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 may be determined using Equation 3. In other embodiments, any suitable correction term may be used as a function of distance as discussed in relation to Equation 1. In an embodiment, the correction term may be determined based on attenuation related to a face covering (e.g., a mask), as described below. In this way, process 1200 can compensate for one or more face coverings worn by the person (192), as described below with reference to FIGS. 13 through 18.

[0080] In block 1240, the logic device (168) applies a correction term to an uncompensated temperature measurement (previously determined in block 1225) to provide a corrected temperature measurement as discussed in relation to FIGS. 7, 10 and 11. For example, the correction term may be applied to provide a corrected temperature measurement related to the inner corner of the eye (402) to compensate for attenuation related to distance (102), face shield, or other factors as described herein.

[0081] In block 1245, the imaging system (100) provides a corrected temperature measurement to the user of the imaging system (100). For example, in some embodiments, the imaging system (100) may provide the corrected temperature measurement as part of a thermal image provided to the user on a display (178) similar to the thermal images (1000, 1100) of FIGS. 10 and 11 or the thermal images of FIGS. 13 through 18. The corrected temperature measurement may be correlated with the body temperature of a person (192). For example, the measurement system and / or other suitable temperature determination technique may be used by a logic device (168) to determine the body temperature of a person (192) based on the temperature of the inner canthus (402), as described herein.

[0082] In block 1247, the logic device (168) processes the corrected temperature measurement with a statistical model. For example, as described with reference to FIG. 19, statistical analysis may be used to provide a moving average of the corrected temperature measurement (e.g., user body temperature). The moving average may be used to determine a threshold for detecting an elevated body temperature, as described below.

[0083] In block 1250, the logic device (168) determines whether the corrected temperature measurement is associated with an elevated body temperature. For example, the corrected temperature measurement may be used to identify a possible health condition associated with a person (192). An elevated body temperature may be determined based on a corrected temperature measurement that exceeds a threshold, such as a moving average, provided by a statistical model in block 1247. If no elevated body temperature is detected, the process of FIG. 12 returns to block 1215, where an additional thermal image is captured and subsequently processed as discussed.

[0084] When an elevated body temperature is detected in block 1250, the process of FIG. 12 continues to block 1255, where the imaging system (100) can generate a notification regarding the elevated body temperature. For example, in various embodiments, the imaging system (100) may use various components of the imaging system (100) to appropriately generate visual and / or auditory notifications in the form of text, icons, colors, flashing lights, sounds, alarms, and / or other types of notifications. Notifications regarding the rise in body temperature may include many configurations, as described below with reference to FIGS. 13 through 18. Then, the process of FIG. 12 returns to block 1215, where additional thermal images are captured and can be processed as subsequently discussed.

[0085] In some embodiments, the operations of FIG. 12 may be performed on a plurality of people (192) present in the captured thermal image (e.g., as similarly discussed and illustrated in connection with FIG. 10 and 11). In some embodiments, the operations of FIG. 12 may be repeated to provide an updated corrected temperature measurement as one or more people (192) move through the scene (190) and / or with a change in distance (102).

[0086] Additional embodiments are also considered. For example, although it has been discussed that the correction term is determined using a correlation between face size (e.g., width and / or area) and distance, other correlations are possible. For example, in some embodiments, thermal images of a person (192) having different face sizes (e.g., corresponding to different head sizes) at the same distance (102) from the imaging system (100) may result in different temperature measurements (e.g., due to different sizes of the inner corners of the eyes for different face sizes and the corresponding different number of associated pixels). Accordingly, in some embodiments, the correction term may be further appropriately adjusted and / or correlated to further compensate for these differences related to the different face sizes of the person (192) at the same distance (102) from the imaging system (100).

[0087] As discussed in relation to blocks 1232, 1245, and 1255 of FIG. 12, various techniques are considered to provide feedback to a user regarding the corrected temperature measurement of the inner eye (402). In embodiments, a user (e.g., person (192)) looks into a thermal imager (164) and receives feedback regarding the user's location relative to the thermal imager (164) and / or the user's determined body temperature. For example, the user may see an overlay or other notification in the thermal image providing a visual indication of the status of the thermal imager (164), the user's location (e.g., too close or too far, etc.), and / or the user's determined body temperature (e.g., below normal, normal, or elevated).

[0088] As discussed in relation to block 1247 of FIG. 12, various embodiments utilize a statistical analysis approach to determine the user's elevated body temperature. For example, the moving average of the determined body temperature can be used to set a threshold to accurately determine whether the user has a fever. For example, such a moving average can account for environmental factors (e.g., ambient temperature or other characteristics) that might otherwise affect a person's body temperature.

[0089] FIGS. 13-18 illustrates various notifications or indications used to provide feedback to a user regarding temperature calculations and determined temperature measurements according to one or more embodiments of the present disclosure. For example, as discussed in relation to block 1232 of FIG. 12, a logic device (168) may generate a notification regarding the distance (102) to a person (192). As discussed in relation to block 1245 of FIG. 12, a logic device (168) may generate a notification providing a corrected temperature measurement of the person (192). Additionally, as discussed in relation to block 1255 of FIG. 12, a logic device (168) may generate a notification regarding an elevated body temperature.

[0090] FIG. 13 illustrates a first notification (1300). As illustrated, the first notification (1300) may be an overlay on the face of a person (192), but other configurations are considered, such as one or more notifications or interfaces (e.g., a web interface) provided on a display (178). The first notification (1300) may be configured to provide a first indication to the user regarding temperature calculation. For example, the first notification (1300) may indicate that the system is currently calculating the temperature of the person (192), that the person (192) is located appropriately (e.g., within a desirable distance range), etc. The first notification (1300) may be a first pattern, type, and / or color, e.g., a cyan overlay, to distinguish it from other indications, as provided herein. The first notification (1300) may be generated in block 1232 of FIG. 12.

[0091] FIG. 14 illustrates a second notification (1400). Like the first notification (1300), the second notification (1400) may be a face of a person (192), a notification, and / or an overlay on an interface (e.g., a web interface) provided on a display (178). The second notification (1400) may be configured to provide the user with a second indication regarding temperature calculations. For example, the second notification (1400) may indicate that the system is in calibration mode, that the person (192) is located too close, etc. The second notification (1400) may be a second pattern, type, and / or color, e.g., a yellow overlay, to distinguish it from other indications, as provided herein. The second notification (1400) may be generated in block 1232 of FIG. 12.

[0092] FIG. 15 illustrates a third notification (1500) which may be the face of a person (192) provided on a display (178), a notification, and / or an overlay on an interface (e.g., a web interface). The third notification (1500) may be configured to provide a third indication to the user regarding temperature calculations. For example, the third notification (1500) may indicate that the person (192) is mispositioned, such as being outside a desirable distance range. In such an embodiment, the third notification (1500) may provide feedback instructing the person (192) to move in relation to the camera to provide a thermal image with sufficient pixels for an angle thermal radiation measurement, as provided above. The third notification (1500) may be a third pattern, type, and / or color, e.g., a purple overlay, to distinguish it from other indications, as provided herein. The third notification (1500) may be generated in block 1232 of FIG. 12.

[0093] FIG. 16 illustrates a fourth notification (1600) which may be a face of a person (192) provided on a display (178), a notification, and / or an overlay on an interface (e.g., a web interface). The fourth notification (1600) may be configured to provide the user with a fourth notification regarding, for example, a determined temperature measurement of the person (192). For example, the fourth notification (1600) may indicate that the detected temperature of the person (192) is below normal, such as that it is below the normal range for, for example, a specific person (192) or a general person. The fourth notification (1600) may be a fourth pattern, type, and / or color, for example, a blue overlay, to distinguish it from other indications, as provided herein. The fourth notification (1600) may be generated in block 1245 or block 1255 of FIG. 12.

[0094] FIG. 17 illustrates a fifth notification (1700) which may be a face of a person (192) provided on a display (178), a notification, and / or an overlay on an interface (e.g., a web interface). The fifth notification (1700) may be configured to provide a fifth indication to the user, for example, regarding the determined temperature of the person (192). For example, the fifth notification (1700) may indicate that the detected temperature of the person (192) is normal, such as being within a normal range for a specific person (192) or for a general person. The fifth notification (1700) may be a fifth pattern, type, and / or color, for example, a green overlay, to distinguish it from other indications, as provided herein. The fifth notification (1700) may be generated in block 1245 or block 1255 of FIG. 12.

[0095] FIG. 18 illustrates a sixth notification (1800) which may be a face of a person (192) provided on a display (178), a notification, and / or an overlay on an interface (e.g., a web interface). The sixth notification (1800) may be configured to provide a sixth indication to the user, for example, regarding a determined temperature of the person (192). For example, the sixth notification (1800) may indicate that the detected temperature of the person (192) has risen above a normal range, for example, for a specific person (192) or for people in general. The sixth notification (1800) may be a sixth pattern, type, and / or color, for example, a red overlay, to distinguish it from other indications, as provided herein. The sixth notification (1800) may be generated in block 1245 or block 1255 of FIG. 12.

[0096] As illustrated in FIG. 13-18, each notification (1300, 1400, 1500, 1600, 1700, or 1800) may be a rectangular overlay capturing the face of a person (192). These examples are merely exemplary, and the notification (1300, 1400, 1500, 1600, 1700, or 1800) may have other configurations, such as circular, elliptical, or polygonal configurations. In the embodiments, each notification (1300, 1400, 1500, 1600, 1700, or 1800) may capture the inner corner of the eye (402) of the person (192). In the embodiments, the notification (1300, 1400, 1500, 1600, 1700, 1800) may highlight the inner corner (402).

[0097] As described, the imaging system (100) (e.g., neural network (300)) may detect or receive one or more masks (1310) (or other face coverings) worn by a person (192). For example, a correction term may be determined to compensate for face covering attenuation. In this regard, the correction term may be a function of the type of mask (1310), the color of the mask (1310), the material properties of the mask (1310), the position of the mask (1310) relative to the inner corner (402), and / or other mask properties. The one or more mask properties may be determined by performing an analysis of one or more captured thermal images of the person (192).

[0098] FIG. 19 illustrates a workflow (1900) performed by a system (100) to determine whether a person's body temperature has risen or is normal using a statistical model according to one embodiment of the present disclosure. The workflow (1900) provides a method for updating the statistical model and providing a resulting determination of the rise or normal temperature, indicating whether the person (192) has a risen temperature compared to a previous sample. The workflow (1900) may be performed in block 1247 of FIG. 12.

[0099] As illustrated, one or more thermal images (e.g., as captured by a thermal imager (164) as in block 1215 of FIG. 12) may be provided to a detection system (1902). The detection system (1902) may be a module or program running on a logic device (168) and / or other logic device of the system (100). The detection system (1902) may detect one or more faces and / or facial features in the thermal image(s). For example, the detection system (1902) may detect and highlight the inner corner (402) of a person (192) within the thermal image(s). In embodiments, the detection system (1902) may detect a face covering (e.g., a mask (1310)) worn by the person (192) (e.g., using a neural network (300)). In the embodiments, the detection system (1902) can process the thermal image in block 1220 of FIG. 12. The detection system (1902) can add a track ID (1904) to the detection (e.g., "ID01" as illustrated).

[0100] The output of the detection system (1902) (e.g., thermal image(s) having a track ID (1904)) may be provided to the measurement system (1906). Like the detection system (1902), the measurement system (1906) may be a module or program running on the logic device (168) and / or other logic device of the system (100). The measurement system (1906) may determine a temperature measurement (1908) for a selected point of the thermal image(s). For example, the measurement system (1906) may determine the temperature measurement (1908) of the inner corner (402) of a person (192) using the corresponding pixel of the thermal image as described above, as in block (1233) of FIG. 12. The measuring system (1906) may determine a temperature measurement (1908) and apply a correction term thereto to compensate for attenuation associated with the face covering (1310), as in block 1235 and / or block 1240 of FIG. 12 (e.g., before detection). In some embodiments, the measuring system (1906) may use the temperature measurement (1908) to determine the body temperature of a person (192).

[0101] The output of the measurement system (1906) (e.g., thermal image(s) having a track ID (1904) and measured temperature(s) (1908)) may be provided to the sampling system (1910). The sampling system (1910) may be a module or program running on a logic device (168) and / or another logic device of the system (100). The sampling system (1910) may generate one sample (1914) per track ID (1904). For example, the sample (1914) may include the track ID (1904) and the measured temperature(s) (1908).

[0102] The sample (1914) may be provided to an anomaly detection system (1920). The anomaly detection system (1920) may be a module or program running on a logic device (168) and / or another logic device of the system (100). The anomaly detection system (1920) may process (e.g., compare with a statistical model (1922)) the temperature (1908) measured, for example, in block 1247 of FIG. 12. If the measured temperature(s) (1908) are within the threshold of the statistical model (1922), the temperature of the person (192) is determined to be normal (e.g., in block 1250 of FIG. 12). However, if the measured temperature(s) (1908) are higher than the statistical model (1922), the temperature of the person (192) is determined to be elevated (e.g., in block 1250 of FIG. 12).

[0103] The statistical model (1922) may be any mathematical model that implements one or more statistical assumptions regarding the measurement of the angle temperature. The determination of the normal temperature may be based on one or more measured temperatures (1908) that exceed a threshold (e.g., exceeding the threshold probability). The determination of the elevated temperature may be based on one or more measured temperatures (1908) that exceed or fall below a threshold (e.g., below the threshold probability).

[0104] As discussed in relation to block 1255 of FIG. 12, one or more notifications may be generated to identify elevated body temperature in response to a body temperature exceeding a threshold. For example, a normal temperature determination may be provided in notification (1926) (e.g., the fifth notification (1700)). An elevated temperature determination may be provided in notification (1928) (e.g., the sixth notification (1800)). Notifications (1926, 1928) may be provided on a display (178), a user interface, or other device. In embodiments, an elevated temperature determination may trigger an alarm and / or a request for an appropriate follow-up procedure. For example, a secondary measurement method may be triggered to determine whether a person (192) has a fever.

[0105] The statistical model (1922) may be dynamic. For example, whenever the face is within an appropriate distance for measurement, the measured inner canthal area temperature (e.g., the measured temperature of the inner canthus (402)) may be added to the statistical model (1922) to provide a moving average. The moving average may be maintained from all previous canthal temperature measurements to identify temperatures above the average. For example, if the measured inner canthal area temperature is higher than the current moving average, an elevated temperature determination may be made.

[0106] Where applicable, the various embodiments provided by this disclosure may be implemented using hardware, software, or a combination of hardware and software. Additionally, where applicable, the various hardware components and / or software components described herein may be combined into composite components including software, hardware, and / or both without departing from the spirit of this disclosure. Where applicable, the various hardware components and / or software components described herein may be separated into sub-components including software, hardware, or both without departing from the spirit of this disclosure. Additionally, where applicable, it is considered that software components may be implemented as hardware components and vice versa.

[0107] Software according to the present disclosure, such as program code and / or data, may be stored on one or more computer-readable media. It is also considered that the software identified herein may be implemented using one or more general-purpose or dedicated computers and / or computer systems, network connections and / or others. Where applicable, the order of the various steps described herein may be changed, combined into complex steps, and / or separated into sub-steps to provide the functions described herein.

[0108] The foregoing embodiments illustrate but do not limit the invention. Furthermore, it should be understood that numerous modifications and variations may be made in accordance with the principles of the invention. Accordingly, the scope of the invention is defined only by the following claims.

Claims

Claim 1 A method performed by a logic device comprising: capturing a thermal image of a person using a thermal imager; determining an uncompensated temperature measurement related to the inner corner of the person's face using a corresponding pixel of the thermal image; preprocessing a plurality of thermal images of a plurality of subjects to determine one or more fitting constants based on the correlation between the distance and the face width of each of the plurality of subjects; determining a correction term as a function of the one or more fitting constants and the distance between the thermal imager and the person—determining the correction term includes determining the number of pixels of the thermal image related to the face width—; and applying the correction term to the uncompensated temperature measurement to provide a corrected temperature measurement related to the inner corner to compensate for attenuation related to the distance. Claim 2 A method according to claim 1, wherein the distance is determined according to a predetermined association between the number of pixels and the distance. Claim 3 A method according to claim 1, wherein the width of the face includes an ear-to-ear width. Claim 4 A method according to claim 1, further comprising the step of detecting the person's face and the inner corner of the eye in the thermal image after the step of capturing a thermal image of a person using the thermal imager. Claim 5 A method according to claim 4, wherein the detecting step comprises processing the thermal image by an artificial neural network. Claim 6 A method according to claim 1, further comprising, after the step of applying the correction term to the uncompensated temperature measurement, the step of determining a threshold based on the moving average of the determined body temperature using a statistical model; and the step of determining the elevated body temperature of the person using the corrected temperature measurement by determining whether the corrected temperature measurement exceeds the threshold. Claim 7 A method according to claim 6, further comprising generating a notification to the user of the thermal imaging device indicating an elevated body temperature. Claim 8 delete Claim 9 A method according to claim 1, further comprising the step of repeating the method described in claim 1 for a plurality of people located at a plurality of distances from the thermal imager. Claim 10 A method according to claim 1, wherein the method is performed by a portable thermal imager comprising the thermal imager. Claim 11 A system comprising a thermal imager; and a logic device, wherein the logic device: operates the thermal imager to capture a thermal image of a person; uses a corresponding pixel of the thermal image to determine an uncompensated temperature measurement related to the inner corner of the person's face; preprocesses a plurality of thermal images of a plurality of subjects to determine one or more fitting constants based on the correlation between the distance and the face width of each of the plurality of subjects; determines a correction term as a function of the one or more fitting constants and the distance between the thermal imager and the person—determining the correction term includes determining the number of pixels of the thermal image related to the face width—and is configured to apply the correction term to the uncompensated temperature measurement to provide a corrected temperature measurement related to the inner corner of the face to compensate for attenuation related to the distance. Claim 12 In paragraph 11, the logic device is configured to determine the distance using a predetermined association between the number of pixels and the distance, a system. Claim 13 In claim 11, the system wherein the width of the face includes the ear-to-ear width. Claim 14 In claim 11, the system is configured such that the logic device detects a human face and inner corner of the eye in the thermal image. Claim 15 In claim 14, the system is configured such that the logic device processes the thermal image by an artificial neural network to detect the face and the inner corner of the eye. Claim 16 In claim 11, the logic device is configured to determine a threshold based on a moving average of a determined body temperature using a statistical model, and to determine whether the corrected temperature measurement exceeds the threshold, thereby determining the elevated body temperature of a person using the corrected temperature measurement. Claim 17 In paragraph 16, the system is configured such that the logic device generates a notification to the user of the thermal imager indicating an elevated body temperature. Claim 18 delete Claim 19 In claim 11, the system is configured such that the logic device determines corrected temperature measurements for a plurality of people located at a plurality of distances from the thermal imager. Claim 20 In Clause 11, the system is a portable thermal camera.

Images