TECHNICAL FIELD

The present disclosure relates to medical diagnostics, and more specifically relates to method and system for determining a physiological condition of a person.

BACKGROUND

Currently, patients suffering from infectious diseases (such as COVID-19) typically experience physiological symptoms such as a fever, cough, shortness of breath, all of which can be quantitatively measured through physiological signs. An easy and effective way to measure these physiological symptoms is essential for diagnosing presence of infectious diseases so as to support the wellbeing of an entire population. Fever is notably one of the many important physiological signs of presence of the infectious diseases in an individual, since a febrile response would indicate that the body of the individual is fighting an infection. During fever, a core temperature (in practice internal organs) of the individual is generally above 38.3 degree Celsius and a normal core temperature range is generally between 36.5 degree Celsius and 37.3 degree Celsius, with the peripheral (arms and legs) temperature being 2 to 4 degree Celsius lower than that of the core.

Currently, infrared thermography is used for screening uncovered parts, such as a face of a user, for fever detection. However, infrared thermography suffers from several limitations, for instance, infrared thermography requires removal of eyewear, face mask, and clothing that may obscure the face of the user and requires the user to be stationary while being screened. Additionally, infrared thermography has poor sensitivity versus specificity, since a low threshold setting leads to high rate of false positives and a high threshold setting leads to high rate of false negatives. Moreover, infrared thermography is susceptible to ambient temperature variations as infrared temperature of the skin is strongly affected by ambient conditions. Therefore, in light of the foregoing discussion, there is a need to overcome the aforementioned drawbacks associated with the existing techniques for providing a method and a system for determining a physiological condition of a person.

SUMMARY The present disclosure seeks to provide a method for determining a physiological condition of a person, in which the person is at least partly covered with clothing. The present disclosure also seeks to provide a system for determining a physiological condition of a person, in which the person is at least partly covered with clothing. An aim of the present disclosure is to provide a solution that overcomes at least partially the problems encountered in prior art by providing a technique for determining physiological condition of the person based on relative measurement of anomalous body temperature distribution measured with clothing penetrating waves, that provides good sensitivity and specificity without being susceptible to ambient temperature variations and serves as a robust indicator of the physiological condition.

In one aspect, the present disclosure provides a method for determining a physiological condition of a person, in which the person is at least partly covered with clothing, the method comprising: - obtaining a thermal image of the person; classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person; selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency and a second radiance value associated with a second frequency and the second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency wherein the first and the second frequencies are within a range of 200 GHz to 1 THz; calculating a correction factor a _t ) for each of the radiance values of each of the image pixels; compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors; calculating reference value based on the compensated radiance values; and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

In another aspect, an embodiment of the present disclosure provides a system for determining a physiological condition of a person, the system comprising: a thermal imaging apparatus for obtaining a thermal image of a person; and a computer system configured to receive the obtained thermal image and run a software configured to execute a method comprising: obtaining a thermal image of the person; classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person; selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency ; a second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency , wherein the first and the second frequencies are within a range of 200 GHz to 1 THz; calculating a correction factor a _t ) for each of the radiance values of each of the image pixels; compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors; calculating reference value based on the compensated radiance values; and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

Embodiments of the present disclosure substantially eliminate or at least partially address the aforementioned problems in the prior art, and provide a technique for determining physiological condition of the person based on relative measurement of anomalous body temperature distribution measured with clothing penetrating waves, that provides good sensitivity and specificity without being susceptible to ambient temperature variations and serves as a robust indicator of the physiological condition.

Additional aspects, advantages, features and objects of the present disclosure would be made apparent from the drawings and the detailed description of the illustrative embodiments construed in conjunction with the appended claims that follow.

It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein. Moreover, those skilled in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.

Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams wherein:

FIG. 1 is a schematic illustration of a system for determining a physiological condition of a person, in which the person is at least partly covered with clothing, in accordance with an embodiment of the present disclosure; FIGs. 2A-2B illustrate first exemplary thermal image of a non-febrile person and a second exemplary thermal image of a febrile person, in accordance with an exemplary scenario;

FIG. 3 depicts a graph of emissivity of skin plotted along Y-axis versus a frequency (GFIz) plotted along X-axis, in accordance with an exemplary scenario;

FIG. 4 depicts a graph of a transmission of a signal through a typical clothing material of a person plotted along Y-axis versus a frequency (TFIz) plotted along X-axis, in accordance with an exemplary scenario; FIG. 5 depicts an intersection of transmission versus frequency and radiance versus frequency graphs, in accordance with an exemplary scenario;

FIGs. 6A-6B depict segmentation process steps for a thermal image, in accordance with an embodiment of the present disclosure; FIG. 7 depicts a table indicating a correlation between temperature values corresponding to various body parts, such as torso, head and arms, in accordance with an exemplary scenario;

FIG. 8 depicts a graph showing correlation between the measured value and the body temperature corresponding to a febrile patient, in accordance with an exemplary scenario;

FIG. 9 depicts a graph showing correlation between the temperature corresponding to head/torso plotted along Y-axis versus an overall brightness/colour plotted along X-axis, in accordance with an exemplary scenario; FIG. 10 depicts a graph showing correlation of maximum radiance values corresponding to a torso of a person and the body temperature of the person, in accordance with an exemplary scenario; and FIGs. 11A-11B illustrate a flowchart listing steps involved in a method for determining a physiological condition of a person, in which the person is at least partly covered with clothing, in accordance with an embodiment of the present disclosure. In the accompanying drawings, an underlined number is employed to represent an item over which the underlined number is positioned or an item to which the underlined number is adjacent. A non-underlined number relates to an item identified by a line linking the non-underlined number to the item. When a number is non-underlined and accompanied by an associated arrow, the non-underlined number is used to identify a general item at which the arrow is pointing.

DETAILED DESCRIPTION OF EMBODIMENTS

The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.

In one aspect, the present disclosure provides a method for determining a physiological condition of a person, in which the person is at least partly covered with clothing, the method comprising: obtaining a thermal image of the person; classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person; selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency and a second radiance value associated with a second frequency and the second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency wherein the first and the second frequencies are within a range of 200 GHz to 1 THz; calculating a correction factor a _t ) for each of the radiance values of each of the image pixels; compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors; calculating reference value based on the compensated radiance values; and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

In another aspect, an embodiment of the present disclosure provides a system for determining a physiological condition of a person, the system comprising: a thermal imaging apparatus for obtaining a thermal image of a person; and a computer system configured to receive the obtained thermal image and run a software configured to execute a method comprising: obtaining a thermal image of the person; classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person; selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency ; a second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency , wherein the first and the second frequencies are within a range of 200 GHz to 1 THz; calculating a correction factor a _t ) for each of the radiance values of each of the image pixels; compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors; calculating reference value based on the compensated radiance values; and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

The present disclosure provides a method and a system for determining a physiological condition of a person based on thermography of entire body of the person. The method and the system of the present disclosure determines physiological condition of the person based on a relative measurement of anomalous body temperature distribution measured with clothing penetrating waves while providing good sensitivity and specificity. Additionally, the method and system of the present disclosure is not susceptible to ambient temperature variations, as the body of the person is thermally insulated form ambient temperature and therefore the thermography of the body of the person is not affected by any ambient temperature in the surrounding. Moreover, the method and system of the present technology facilitates a "walk-by screening" of the person who may at least be partly covered with clothing, without the need to remove clothing or other accessories such as eyewear or face mask, and thus providing a convenient and on-the-go screening technique. Also, the method and system of the present disclosure generates a relative measurement of anomalous body temperature distribution measured at different locations on the body of the person at different frequencies in a frequency range near around 500 GHz, and compensates for attenuation due to clothing based on the radiance values corresponding to the different locations and different frequencies, thereby facilitating accurate determination of physiological conditions without being affected by any attenuation due to clothing of the person.

The method comprises obtaining a thermal image of the person. Throughout the present disclosure, the term "thermal image " refers to an image representing an amount of electromagnetic energy emitted, transmitted, and reflected by an object (body of the person or individual). Herein, the thermal image is a visual representation of thermal data in the form of a digital image. Thermal image is typically obtained by a process of thermal imaging that includes using radiation/ thermal energy to gather information about objects wherein differences in temperature are observable, even in low visibility environments. In some embodiments, a thermal image of an entire body of the person is obtained, while the person may be at least partly covered with clothing. Notably, in some examples, any thick outer clothing, such as a coat, that causes a lot of attenuation in the process may be removed prior to obtaining the thermal image. Optionally, the thermal image is obtained using a thermal camera configured to capture a matrix of pixels. As used herein, the term " thermal camera" refers to a non-contact imaging apparatus that converts an energy of an object in a wavelength range into a visible light display. Notably, all objects above absolute zero emit thermal electromagnetic energy, so thermal cameras can passively see all objects, regardless of ambient light.

Optionally, the thermal image is obtained using a first sensor directed to a first spatial direction and a second sensor directed to a second spatial direction, wherein the first spatial direction is different from the second spatial direction. In an example embodiment, the first spatial direction may be directed towards a first region of a body of a person, and the second spatial direction may be directed towards a second region of the body of the person. In an embodiment, each of the first sensor and the second sensor may be, for example, a thermal camera (as described above).

The method comprises classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person. In an embodiment, the obtained thermal image is subjected to a segmentation process, to segment the thermal image into a plurality of body parts, such as arms, legs, head or torso and to classify the thermal image into the first area and the second area. For the purpose of present disclosure, the terms "first area", "second area", "first body part" and "second body part" are used, however it is noted that the scope of the present disclosure is not restricted to "first area", "second area", "first body part", and "second body part" alone and can be extended to include a plurality of areas and a plurality of body parts of the thermal image. Notably, when the person is in a febrile condition the extremities are cooler than torso/head of the person and each of the extremities or areas have different radiance values corresponding to different signal frequencies depending on their respective temperatures.

Optionally, the classification of the obtained thermal image comprises at least one of performing image analysis of the obtained image, using predetermined areas of the image as determined areas, using a sensor configured to indicate body parts of a person or using compensation factor values. One or more of such techniques may involve use of suitable segmentation algorithms (based on computer vision techniques and the like) which are well known in the art, and thus have not been described in detail herein for the brevity of the present disclosure.

The method further comprises selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency ; and the second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency wherein the first and the second frequencies are within a range of 200 GHz to 1 THz. That is, as the obtained thermal image is classified to define the first area and the second area therein, the first image pixel is selected from the first area and the second image pixel is selected from the second area. The first image pixel may be any point in the first area, and the second image pixel may be any point in the second area. Thereby, the two selected image pixels are aimed at two different body parts. It may be understood that although the present embodiments have been described in terms of selection of a single image pixel from the respective body area; in other examples, a plurality of image pixels may be selected from each of the body areas without any limitation. Further, the radiance values for the selected image pixels are determined using two frequencies, the first frequency and the second frequency. That is, the radiance values are determined for each of the selected image pixels, including the first image pixel from the first area and the second image pixel from the second area, for each of the frequencies used. In the present examples, it is determined that the first image pixel has the first radiance value associated with the first frequency ( _1A ) and the second radiance value associated with the second frequency and the second image pixel has the third radiance value associated with the first frequency and the fourth radiance value associated with the second frequency It might be understood that the transmittivity of the skin increases as the higher frequency is implemented, while the transmittivity of the clothing decreases as the higher frequency is implemented. It has been observed that for skin transmittivity vs typical clothing transmittivity, measurements near 500 GHz provide most accurate skin temperature estimates. Notably, upon using frequencies much higher than 500 GHz, the clothing will attenuate the signal and upon using frequencies much lower than 500 GHz, the skin does not provide sufficient radiation signal for proper measurement. Furthermore the skin reflectance with lower frequencies will start to dominate this ambient temperature will have adverse effect on measurements if the frequencies are low. In the present embodiments, two frequencies are used such that the effect due to the clothing may be compensated. It may be contemplated by a person skilled in the art that thicker might be the clothing, the two frequencies used needs to be farther apart to provide such compensation. For the purposes of the present disclosure, in some examples, the two frequencies may, beforehand, need to be calibrated to correspond to same radiance values, or the radiance relationship with temperature should be known for each of the two frequencies.

Herein, the first and the second frequencies are within a range of 200 giga hertz (GHz) to 1 tera hertz (THz). In an embodiment, the first and the second frequencies are in the range of 200 GHz, 250 GHz, 300 GHz, 350 GHz, 400 GHz, 450 GHz, 500 GHz, 550 GHz, 600 GHz, 650 GHz, 700 GHz, 750 GHz, 800 GHz, 850 GHz, 900 GHz, 950 GHz up to 250 GHz, 300 GHz, 350 GHz, 400 GHz, 450 GHz, 500 GHz, 550 GHz, 600 GHz, 650 GHz, 700 GHz, 750 GHz, 800 GHz, 850 GHz, 900 GHz, 950 GHz, 1 THz. Optionally, the first and the second frequencies are within range of 400 GHz to 600 GHz. In an embodiment, the first and the second frequencies are in the range of 400 GHz, 450 GHz, 500 GHz, 550 GHz up to 450 GHz, 500 GHz, 550 GHz, 600 GHz.

Optionally the first centre frequency is 0.2 to 0.7 times the second frequency. As used herein, the term "centre frequency" as applied to a frequency band denotes a frequency at the arithmetic mean of the frequencies of the boundaries of the frequency band. Notably, the compensation of the radiance values is performed to compensate for attenuation due to the clothing of the person. For a thick clothing, the first frequency and the second frequency , have to be as far as possible from one another and thicker the clothing farther the first frequency and the second frequency should be. In an embodiment, the first frequency and the second frequency are selectively chosen so as to compensate for the attenuation by the clothing, selectively based on the clothing thickness. For instance, the separation between the first frequency and the second frequency can be selectively chosen differently for winter and summer clothing, so as to achieve optimal calibration for attenuation due to clothing. In an embodiment the first centre frequency is from 0.2, 0.3, 0.4, 0.5, 0.6 to 0.3, 0.4, 0.5, 0.6, 0.7 times the second frequency.

Optionally, each of the image pixels have in addition a radiance value associated with a third frequency. That is, in addition to using the first frequency and the second frequency, the present method also comprises using a third frequency, and so on. Each of such additional frequencies may have a corresponding radiance values for the corresponding selected image pixels; for example, a fifth radiance value for the first image pixel and a sixth radiance value for the second image pixel, and so on. It may be appreciated that more the number of frequencies being implemented, a more accurate estimate of the non-linearity of clothing attenuation may be achieved. Having more than two frequencies gives possibility to selectively calculate (and measure) correction factors depending on measurement conditions. This way the correction factor can be calculated for example using the frequencies which are closer to each others (to have smaller difference between the frequencies). This is beneficial in case of having thin clothing. If clothing is thick then, for calculating correction factor a pair of frequencies which are further away would be selected.

The method further comprises calculating a correction factor a _t ) for each of the radiance values of each of the image pixels. The correction factor provides a metric to be employed for compensating the effect of item of clothing, for the frequencies employed. For example, if the first frequency is employed so as to have maximum effect in skin emissivity and the second frequency is employed so as to have maximum effect in clothing transmittivity; in such case by determining the correction factor for the first frequency for an image pixel, which would be dependent on the second frequency for the same image pixel, the effect of clothing on the said image pixel could be compensated. Optionally, a correction factor for each of the radiance values of each of the image pixels is calculated by using an equation, a _t = + 1), where b is a predetermined correction coefficient and i is the index of the image pixel being treated. It may be appreciated that the given equation is one exemplary equation for calculating such correction factor and other equivalent equations may be employed without departing from the spirit and the scope of the present disclosure. In a general form, the correction factor a _t can be calculated by using an equation is a suitable function that describes the relationship between the attenuation in the first frequency band and the normalised differences between the radiances of the other available frequency bands

The method further comprises compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors. The present disclosure utilizes the difference in clothing attenuation between the implemented two frequencies (short wavelengths are attenuated more than long wavelengths) to get a compensation factor that yields an estimate for the attenuation of the clothing covering the two selected image pixels. Herein, the correction factor is used to remove possible attenuation effects of clothing on each of the two selected image pixels. That is, once the correction factor for each of the radiance values of each of the image pixels has been calculated, the corresponding radiance values are compensate using the corresponding correction factor, as determined. Optionally, the values are compensated using equation, L _t = a _{£ £ l} wherein i is the index of the image pixel being treated. Again, it may be appreciated that the given equation is one exemplary equation for carrying out compensation of radiance values and other equivalent equations may be employed without departing from the spirit and the scope of the present disclosure.

The method further comprises calculating reference value based on the compensated radiance values. Herein, the reference value may represent radiance value, for example for the skin, after compensating for the effect of the clothing. Optionally, the reference value is calculated by dividing the first compensated reference value with the second compensated reference value or by subtracting the second compensated reference value with the first compensated reference value. That is, reference value may be calculated using one of the equations: V _ref = L _X !L ₂ or alternatively, V _re† = L _x - L ₂ . Yet again, it may be appreciated that the given equations are exemplary only and other equivalent equations may be employed without departing from the spirit and the scope of the present disclosure. In one example, the calculated reference value may be determined by averaging of corresponding reference values for the various image pixels of a particular body area. In another example, the calculated reference value may be determined by selecting an extreme reference value from the corresponding reference values for the various image pixels of a particular body area. In still other examples, the calculated reference value may be determined by using a spatial distribution or some other statistical properties of corresponding reference values for the various image pixels of a particular body area. In yet on other embodiment the reference value can be calculated by comparing the compensated radiance values associated with the first body part with the compensated radiance values associated with the second body part. This way a comparison of for example temperature of hand to temperature of torso can be made.

The method further comprises determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value. That is, the teachings of the present disclosure may be implemented for diagnosis, whether a person is febrile/ non-febrile. The present disclosure utilizes the fact that a person suffering from infection will exhibit anomalous temperature distribution across the different body areas. For instance, if a core temperature (head and thorax) of the person (as determined by the reference value) is close to 40 degrees Celsius and a core temperature of the skin is close to 37 degrees Celsius, then it is determined that the skin temperature is 3 degrees Celsius below the core temperature, which is indicative of fever. Herein, the predetermined value may be a defined threshold for the reference value above which it may be considered that the person may have fever. It may be appreciated that the predetermined value may be defined (may vary) based on how the reference value is calculated. In some examples, the present disclosure may further utilize some suitable descriptors to classify the person as healthy / sick based on statistical analysis or some other similar method or machine learning. Optionally, the first condition is an infectious fever, such as for example SAR-COV-2 viral infection. As a further example if there is a temperature differences between peripheral body parts (such as arms and legs) in comparison to proximal body parts (such as head and torso) which are larger than predefined value the condition can be determined to be an infectious fever.

The present disclosure also relates to the system as described above. Various embodiments and variants disclosed above apply mutatis mutandis to the system.

The system of the present disclosure determines a physiological condition of a person based on thermography of entire body of the person based on a relative measurement of anomalous body temperature distribution measured with clothing penetrating waves and thereby provides good sensitivity and specificity. Additionally, the system of the present disclosure determines the physiological condition of the person without being affected by any ambient temperature variations, as the body of the person is thermally insulated form ambient temperature and therefore the thermography of the body of the person is not affected by any ambient temperature in the surrounding. Moreover, the system of the present technology facilitates a walk by screening of the person being at least partly covered with clothing without the need to remove clothing or other accessories such as eyewear or face mask and thus providing a convenient and on the go screening technique. Also, the system of the present disclosure generates a relative measurement of anomalous body temperature distribution measured at different locations on the body of the person at different frequencies in a frequency range close to around 500 GHz, and compensates for the clothing based on the radiance values corresponding to the different parts of the body of the person and different frequencies, thereby facilitating accurate determination of physiological conditions without being affected by any attenuation due clothing of the person.

The system comprises a thermal imaging apparatus for obtaining a thermal image of a person. The thermal imaging apparatus comprises a device that translates thermal energy (heat) from the body of a person into visible light to generate the thermal image of the person. Examples of the thermal imaging apparatus, includes but is not limited to, an infrared camera, a thermographic camera, a thermal imager, a digital infrared thermal imager, and the like. The system comprises a computer system configured to receive the obtained thermal image and run a software configured to execute a method comprising: obtaining a thermal image of the person; classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person; selecting a first image pixel from the first area and a second image pixel from the second area, with: the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency ; a second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency , wherein the first and the second frequencies are within a range of 200 GHz to 1 THz; calculating a correction factor a _t ) for each of the radiance values of each of the image pixels; compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors; calculating reference value based on the compensated radiance values; and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

An example of the computer system includes, but is not limited to, a mobile phone, a laptop, a desktop, a notebook computer, and the like, configured to run the software. In several embodiments, the software is installed as an application in the computer system. In several other embodiments, the software is installed on a remote server, such that the computer system is communicatively coupled to the remoter server via a network for executing the software on the server and receiving one or more results of execution from the server via the network. In an example, the server may include components such as memory, at least one processor, a network adapter and the like, to store, process and/or share information with other entities, such as a broadcast network or a database for receiving and storing the thermal image.

Optionally, the system further comprises a visual imaging sensor for determining at least a first body part and a second body part of the person. The visual imaging sensor is configured to provide results of the determination for classification of areas of the thermal images. In an embodiment, the visual imaging sensor is configured to segment the thermal image into the first body part and the second body part. In an embodiment, the visual imaging sensor is implemented as a programmable software module executable by the computer system.

Optionally, the system further comprises a user interface for indicating the physiological condition of the person. In an embodiment, the user interface is associated with the computer system. The said computer system may include a display to provide the user interface which may indicate by using different colours or some other indicators, to indicate the physiological condition of a person.

Optionally, the system comprises a means to capture two or more radiance values for each image pixel of the thermal image. In an embodiment, the means may include a programmable module that evaluates a radiometric equation for each image pixel of each frame during runtime of the software for determining the radiance values for each image pixel.

DETAILED DESCRIPTION OF THE DRAWINGS FIG. 1 depicts a schematic illustration of a system 100 for determining a physiological condition of a person, in which the person is at least partly covered with clothing, in accordance with an embodiment of the present disclosure. The system 100 comprises a thermal imaging apparatus 102 and a computer system 104 communicably coupled to the thermal imaging apparatus 102. In an embodiment, the thermal imaging apparatus 102 is communicably coupled to the computer system 104 via a communication network (not shown). The computer system 104 is configured to receive the obtained thermal image and run a software configured to execute a method comprising: obtaining a thermal image of the person, classifying the obtained thermal image to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person, selecting a first image pixel from the first area and a second image pixel from the second area, with the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency and a second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency , wherein the first and the second frequencies are within a range of 200 GHz to 1 THz, calculating a correction factor a _t ) for each of the radiance values of each of the image pixels, compensating the radiance values of each of the image pixels using the calculated pixel wise correction factors, calculating reference value based on the compensated radiance values, and determining the physiological condition of the person by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value. The system 100 can optionally include a visual imaging sensor 106 for determining at least a first body part and a second body part of the person. The visual imaging sensor 106 is configured to provide results of the determination for classification of areas of the thermal images. The system 100 further includes a user interface 108 for indicating the physiological condition of the person. The user interface 108 is associated with the computer system 104. The system 100 comprises a means to capture two or more radiance values for each image pixel of the thermal image.

It may be understood by a person skilled in the art that the FIG. 1 is merely an example for sake of clarity, which should not unduly limit the scope of the claims herein. The person skilled in the art will recognize many variations, alternatives, and modifications of embodiments of the present disclosure.

FIGs. 2A-2B illustrate a first exemplary thermal image 202 of a non- febrile person and a second exemplary thermal image 204 of a febrile person, in accordance with an exemplary scenario. As depicted in FIG. 2A, the first exemplary thermal image 202 shows uniform radiance when compared to the second exemplary thermal image 204 that shows a variation in radiance indicated by difference in colour in various regions of the second exemplary thermal image 204. Flowever, as depicted in FIG. 2B, a head region 206a and a torso region 206b in the second exemplary thermal image 204 seem to have more radiance when compared to other regions indicative of a higher temperature of extremities, such as the head region 206a and the torso region 206b. Flowever, in the first exemplary thermal image 202 of a non-febrile person, the radiance remains almost uniform across various regions. The method and system of the present disclosure leverages the difference in temperature of various body parts in the febrile person to determine the physiological condition of the person. FIG. 3 depicts a graph 300 of emissivity of skin plotted along Y-axis 302 versus a frequency plotted along X-axis 304, in accordance with an exemplary scenario. The graph 300 shows a gradual increase in emissivity of skin with increase in frequency from 0 to around 500 giga hertz (GFIz) and has an almost flat region 306 between 500 (GFIz) to around 1000 GFIz. Emissivity of the skin is close 90% (0.9) when the frequency is larger than 500GFIz.

FIG. 4 depicts a graph 400 of a transmission 402 of a signal through an item of clothing of a person plotted along Y-axis versus a frequency 404 plotted along X-axis, in accordance with an exemplary scenario. The graph 400 indicates a decrease in transmission through the item of clothing with an increase in frequency.

FIG. 5 depicts a plot 500 showing intersection of graphs 300 and 400 in accordance with an exemplary scenario, with a transmission or a radiance plotted along Y-axis and a frequency plotted along X-axis. As depicted in FIG. 5, the intersection 500 of the graphs 300 and 400 at around 500 GFIz suggests that the best range of frequencies to get through the clothing is near around 500 GFIz. Notably, upon using frequencies much higher than 500 GFIz, the clothing will attenuate the signal and upon using frequencies much lower than 500 GFIz a signal from the skin is distorted by effect caused by an ambient temperature when it reflects from the skin. Accordingly, measurements near 500 GFIz give most accurate skin temperature estimates.

The graphs of FIGs. 3 to 5 indicate that the radiance of skin increases with an increase in frequency and measurement around 500 GFIz will give most accurate skin temperature estimates.

FIGs. 6A-6B depict segmentation process steps for a thermal image, in accordance with an embodiment of the present disclosure. As illustrated, the thermal image 602 of a person is subjected to a segmentation, prior to classification, to segment the thermal image into a plurality of body parts, such as arms 604, legs 606, head 608, or torso 610 for classifying the thermal image 602 into the first area and the second area to obtain a segmented image 612. Flerein, the segmentation is performed using a suitable image segmentation algorithm. FIG. 7 depicts a table 700 indicating a correlation between temperature values corresponding to various body parts, such as torso, head and arms, in accordance with an exemplary scenario. The correlation as indicated in the table 700 implies that a p-value for the" temperature versus torso is approximately 0.017, where the "p-value" is the probability that a null hypothesis is true.

FIG. 8 depicts a graph 800 showing correlation between the measured value and the body temperature corresponding to a febrile patient, in accordance with an exemplary scenario. The graph 800 is obtained by plotting temperature values 802 corresponding to arms, head and torso (specifically, Arms/(Head + Torse)) plotted along Y-axis versus a body temperature 804 of the patient plotted along X-axis.

FIG. 9 depicts a graph 900 showing correlation between the temperature corresponding to head/torso 902 plotted along Y-axis versus an overall brightness/colour 904 plotted along X-axis, in accordance with an exemplary scenario. The graph 900 indicates that attenuation due to clothing is wavelength dependent and can be used to compensate for loss of an overall brightness due to clothing. The method and the system of the present disclosure leverage such correlation for determining physiological condition of the person.

FIG. 10 depicts a graph 1000 showing correlation of maximum radiance values 1002 corresponding to a torso of a person plotted along Y-axis versus the body temperature 1004 of the person plotted along X-axis, in accordance with an exemplary scenario.

FIGs. 11A-11B illustrate a flowchart listing steps involved in a method for determining a physiological condition of a person, in which the person is at least partly covered with clothing, in accordance with an embodiment of the present disclosure. At step 1102, a thermal image of the person is obtained. At step 1104, the obtained thermal image is classified to determine a first area of the obtained image which comprises image data associated with a first body part of the person and a second area of the obtained image which comprises image data associated with a second body part of the person. At step 1106, a first image pixel from the first area and a second image pixel from the second area, is selected with the first image pixel having a first radiance value associated with a first frequency ( _1A ) and a second radiance value associated with a second frequency and the second image pixel having a third radiance value associated with the first frequency and a fourth radiance value associated with the second frequency , where the first and the second frequencies are within a range of 200 GHz to 1 THz. At step 1108, a correction factor a _t ) for each of the radiance values of each of the image pixels is calculated. At step 1110, the radiance values of each of the image pixels is compensated using the calculated pixel wise correction factors. At step 1112, a reference value is calculated based on the compensated radiance value. At step 1114, the physiological condition of the person is determined by comparing the reference value with a predetermined value to be a first condition if the reference value is higher than the predetermined value and to be a second condition if the reference value is same or less than the predetermined value.

It has to be noted that all devices, modules, and means described in the present application could be implemented in the software or hardware elements or any kind of combination thereof. All steps which are performed by the various entities described in the present application as well as the functionalities described to be performed by the various entities are intended to mean that the respective entity is adapted to or configured to perform the respective steps and functionalities. Even if, in the following description of specific embodiments, a specific functionality or step to be performed by external entities is not reflected in the description of a specific detailed element of that entity which performs that specific step or functionality, it should be clear for a skilled person that these methods and functionalities can be implemented in respective software or hardware elements, or any kind of combination thereof. It will be appreciated that features of the present disclosure are susceptible to being combined in various combinations without departing from the scope of the present disclosure as defined by the appended claims.

Modifications to embodiments of the present disclosure described in the foregoing are possible without departing from the scope of the present disclosure as defined by the accompanying claims. Expressions such as "including", "comprising", "incorporating", "have", "is" used to describe and claim the present disclosure are intended to be construed in a non exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural.