Detecting fever from images and temperatures
Described herein are embodiments of systems and methods that utilize temperature measurements taken with head-mounted sensors as well as images of a user's face to detect fever and/or intoxication. One embodiment of a system to detect fever includes a first head-mounted temperature sensor that measures skin temperature (T skin ) at a first region on a user's head, a second head-mounted temperature sensor that measures a temperature of the environment (T env ), and a computer. The computer receives images of a second region on the user's face, captured by a camera sensitive to wavelengths below 1050 nanometer, and calculates, based on the images, values indicative of hemoglobin concentrations at three or more regions on the user's face. The computer can then detect whether the user has a fever based on T skin , T env and the values.
1. A system configured to detect fever, comprising:
a head-mounted inward-facing non-contact thermal camera configured to measure skin temperature (T skin ) at a first region on a user's head;
a head-mounted temperature sensor configured to measure temperature of the environment (T env );
a head-mounted camera sensitive to wavelengths below 1050 nanometer, configured to capture images of e second region on the user's face; and
a computer configured to:
calculate, based on the images, values indicative of hemoglobin concentrations at three or more regions on the user's face; and
detect whether the user has a fever based on T skin , T env , and the values indicative of hemoglobin concentrations.
2. The system of claim 1 , wherein the first region covers a portion of skin that is not located above a portion of a branch of the external carotid artery, and the computer is configured to perform the detection of whether the user has the fever by (i) generating feature values based on: T skin , T env , and the values indicative of hemoglobin concentrations, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a values indicative of whether the user has the fever.
3. The system of claim 1 , wherein the head-mounted inward-facing non-contact thermal camera is located more than 2 mm away from the user's head, the second region is larger than 2 cm 2 , and the head-mounted camera sensitive to wavelengths below 1050 nanometer is an inward-facing head-mounted camera configured to capture the images from a distance between 5 mm and 5 cm from the user's head.
4. The system of claim 1 , wherein the computer is further configured to utilize one or more calibration measurements of the user's core body temperature, taken by a thermometer that is not the head-mounted inward-facing non-contact thermal camera: or the head-mounted temperature sensor, to calibrate a model, and to utilize said calibrated model to calculate the user's core body temperature based on T skin , T env and the values; and the computer is further configured to share fever history of the user upon receiving a permission from the user.
5. The system of claim 1 , wherein the computer is further configured to extract imaging photoplethysmogram signals from the image and to calculate the values indicative of hemoglobin concentrations based on the imaging photoplethysmogram signals: and the computer is further configured to utilize one or more calibration measurements of the user's core body temperature, taken by a thermometer that is not the head-mounted inward-facing non-contact thermal camera or the head-mounted temperature sensor, prior to a certain time, and to calculate the user's core body temperature based on T skin , T env , which were taken after the certain time, and the values indicative of the hemoglobin concentrations detected in the images that were taken after the certain time.
6. The system of claim 1 , further comprising a head-mounted acoustic sensor configured to take audio recordings of the user, and a head-mounted movement sensor configured to measure a signal indicative of movements of the user's head (head-movement signal); wherein the computer is further configured to: (i) generate feature values based on T skin , T env , the values indicative of hemoglobin concentrations, the audio recordings, and the head-movement signal, and (ii) utilize a machine learning-based model to calculate, based on the feature values, a level of dehydration of the user.
7. The system of claim 6 , wherein, for generating the feature values based on the audio recordings, the computer is further configured to extract features indicative of the user's respiratory rate and vocal changes; whereby dehydration is associated with an increase in the respiratory rate and a decrease in the speed quotient at low-pitch phonation.
8. The system of claim 1 , further comprising a head-mounted acoustic sensor configured to take audio recordings of the user; wherein the detection of whether the user has the fever comprises the computer performing the following: (i) generating feature values based on T skin , T env , the values indicative of hemoglobin concentrations, and the audio recordings, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a value indicative of whether the user has the fever; and wherein one or more of the feature values, which were generated based on the audio recordings, are indicative of the user's respiration rate.
9. The system of claim 1 , further comprising a head-mounted movement sensor configured to measure a signal indicative of movements of the user's head (head-movement signal); wherein the detection of whether the user has the fever comprises the computer performing the following: (i) generating feature values based on T skin , env , the values indicative of hemoglobin concentrations, and the head-movement signal, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a value indicative of whether the user has the fever; and wherein one or more of the feature values, which were generated based on the head-movement signal are indicative of the user's physical activity level.
10. The system of claim 1 , further comprising a head-mounted anemometer configured to measure a signal indicative of wind speed hitting the user's head (wind signal), and a head-mounted hygrometer configured to measure a signal indicative of humidity (humidity signal); wherein the detection of whether the user has the fever comprises the computer performing the following: (i) generating feature values based on T skin , T env , the values indicative of hemoglobin concentrations, the wind signal, and the humidity signal, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a value indicative of whether the user has the fever.
11. The system of claim 1 , further comprising an helmet or goggles configured to be worn on the user's head, the head-mounted inward-facing non-contact thermal camera is physically coupled to the helmet or goggles, and the first region is located on the user's forehead, cheekbone, or temple.
12. The system of claim 1 , further comprising an eyeglasses frame configured to be worn on the user's head, the head-mounted inward-facing non-contact thermal camera is physically coupled to the frame, and the first region is located on the user's nose or temple; and wherein the computer is further configured to: calculate, based on additional images captured with the head-mounted camera sensitive to wavelengths below 1050 nanometer while the user had a fever, additional values indicative of hemoglobin concentrations at the three or more regions on the user's face while the user had the fever, and base the detection of whether the user has the fever also on a deviation of the values from the additional values.
13. The system of claim 1 , wherein the images comprise a first channel corresponding to wavelengths that are mostly below 580 nanometers and a second channel corresponding to wavelengths mostly above 580 nanometers; and wherein the values indicative of hemoglobin concentrations comprise: (i) first values derived based on the first channel in the images, and (ii) second values derived based on the second channel in the images.
14. The system of claim 1 , further comprising at least one sensor selected from among the following sensors: a head-mounted acoustic sensor configured to take audio recordings of the user, a head-mounted movement sensor configured to measure a signal indicative of movements of the user's head, a head-mounted anemometer configured to measure a signal indicative of wind speed hitting the user's head, and a head-mounted hygrometer configured to measure a signal indicative of humidity; wherein the computer is further configured to: (i) generate feature values based on T skin , T env , the values indicative of hemoglobin concentrations, measurements taken with the at least one sensor, and (ii) utilize a machine learning-based model to calculate, based on the feature values, a value indicative of the core body temperature of the user.
15. A method for detecting fever, comprising:
receiving, from a head-mounted inward-facing non-contact thermal camera, measurements of skin temperature (T skin ) at a first region on a user's head;
receiving, from a head-mounted temperature sensor, measurements of temperature of the environment (T env );
receiving, from a head-mounted camera sensitive to wavelengths below 1050 nanometer, images of a second region on the user's face;
calculating, based on the images, values indicative of hemoglobin concentrations at three or more regions on the user's face; and
detecting whether the user has a fever based on T skin , T env , and the values indicative of hemoglobin concentrations.
16. The method of claim 15 , wherein the first region covers a portion of skin that is not located above a portion of a branch of the external carotid artery, and the detecting of whether the user has the fever comprises (i) generating feature values based on: T skin , T env , and the values indicative of hemoglobin concentrations, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a values indicative of whether the user has the fever.
17. The method of claim 15 , further comprising: utilizing one or more calibration measurements of the user's core body temperature, taken by a different device, to calibrate a model, and utilizing said calibrated model to calculate the user's core body temperature based on T skin , T env , and the values indicative of hemoglobin concentrations.
18. A non-transitory computer readable medium storing one or more computer programs configured to cause a processor based system to execute steps comprising:
receiving, from a head-mounted inward-facing non-contact thermal camera, measurements of skin temperature (T skin ) at a first region on a user's head;
receiving, from a head-mounted temperature sensor, measurements of temperature of the environment (T env );
receiving, from a head-mounted camera sensitive to wavelengths below 1050 nanometer, images of a second region on the user's face;
calculating, based on the images, values indicative of hemoglobin concentrations at three or more regions on the user's face; and
detecting whether the user has a fever based on T skin , T env , and the values indicative of hemoglobin concentrations.
19. The non-transitory computer readable medium of claim 18 , further comprising instructions for execution of the following steps involved in detecting whether the user has the fever: (i) generating feature values based on: T skin , T env , and the values indicative of hemoglobin concentrations, and (ii) utilizing a machine learning-based model to calculate, based on the feature values, a values indicative of whether the user has the fever.
20. The non-transitory computer readable medium of claim 18 , further comprising instructions for execution of the following steps: utilizing one or more calibration measurements of the user's core body temperature, taken by a different device, to calibrate a model, and utilizing said calibrated model to calculate the user's core body temperature based on T skin , T env , and the values indicative of hemoglobin concentrations.