Sensor agnostic temperature detection system

Patent metadata

Field	Value
Publication number	US-12272170-B2
Application number	US-202117358404-A
Country	US
Kind code	B2
Filing date	Jun 25, 2021
Priority date	Jun 25, 2020
Publication date	Apr 8, 2025
Grant date	Apr 8, 2025

Abstract

A temperature detection system and method for detecting a correlation between temperatures on a subject and a temperature reference is provided. One or more calibrated temperature reference devices, such as a Body Temperature Reference blackbody system is used with an emissive source detector, such as a Mid Wave Infrared (MWIR) or Long Wave Infrared (LWIR) thermal camera that is capable of imaging both a subject and the calibrated temperature reference devices. A processor maps each pixel within the image to a specific thermal value based on the mean and median reference temperatures from the calibrated temperature reference devices and identifies any pixel in the image having a temperature greater than the reference temperature. This information can be used to detect an elevated temperature from a subject. The system and method can be used to detect fevers, tumors, infections, parasites, and the like.

First claim

The invention claimed is:

1. A temperature detection system for detecting a correlation between temperatures on a subject and a reference temperature, said system comprising:
one or more calibrated temperature reference devices;
an emissive source detector that captures one or more images;
a display; and
a processor in communication with a memory, said processor executing machine readable instructions for performing:
(a) receiving the one or more images from said emissive source detector, wherein at least one of the one or more images includes the subject and said one or more calibrated temperature reference devices;
(b) isolating said one or more calibrated temperature reference devices within the at least one of the one or more images and analyzing pixel values of said one or more calibrated temperature reference devices to find a mean reference temperature and a median reference temperature;
(c) comparing the mean reference temperature with the median reference temperature to determine when the median and mean reference temperatures are statistically similar, and using said mean and median reference temperatures to determine the reference temperature when the median and mean reference temperatures are statistically similar;
(d) mapping each pixel within the at least one of the one or more images to a specific thermal value based on said mean and median reference temperatures; and
(e) identifying any pixel in the least one of the one or more images with a temperature greater than said reference temperature and displaying said identified pixels on the display with a temperature greater than said reference temperature with a color and/or shape.

2. The system of claim 1 , further comprising the processor executing machine readable instructions for further performing:
filtering errant pixels in the at least one of the one or more images on edges or where interpolation has increased actual pixel value prior to displaying the identified pixels on the display.

3. The system of claim 1 , further comprising the processor executing machine readable instructions for further performing:
optimizing contrast and filtering errant pixels, image phenomena, and artifacts in the at least one of the one or more images prior to displaying the identified pixels on the display.

4. The system of claim 1 , further comprising the processor executing machine readable instructions for further performing:
performing facial detection/recognition/identification on said subject to identify and track specific regions of interest in the at least one of the one or more images prior to displaying the identified pixels on the display.

5. The system of claim 1 , further comprising the processor executing machine readable instructions for further performing:
displaying errors in the at least one of the one or more images as part of displaying the identified pixels on the display.

6. The system of claim 1 , further comprising the processor executing machine readable instructions for further performing:
identifying and displaying regions of importance in the at least one of the one or more images as part of displaying the identified pixels on the display.

7. A method for detecting a correlation between temperatures on a subject and a reference temperature comprising:
(a) receiving one or more images from an emissive source detector, wherein at least one of the one or more images includes the subject and one or more calibrated temperature reference devices;
(b) isolating said one or more calibrated temperature reference devices within the at least one of the one or more images and analyzing pixel values of said one or more calibrated temperature reference devices to find a mean reference temperature and a median reference temperature;
(c) comparing the mean reference temperature with the median reference temperature to determine when the median and mean reference temperatures are statistically similar, and using said mean and median reference temperatures to determine the reference temperature when the median and mean reference temperatures are statistically similar;
(d) mapping each pixel within the at least one of the one or more images to a specific thermal value based on said mean and median reference temperatures; and
(e) identifying any pixel in the least one of the one or more images with a temperature greater than said reference temperature and displaying said identified pixels on a display with a temperature greater than said reference temperature with a color and/or shape.

8. The method of claim 7 , further comprising:
filtering errant pixels in the at least one of the one or more images on edges or where interpolation has increased actual pixel value prior to displaying the identified pixels on the display.

9. The method of claim 7 , further comprising:
optimizing contrast and filtering errant pixels, image phenomena, and artifacts in the at least one of the one or more images prior to displaying the identified pixels on the display.

10. The method of claim 7 , further comprising:
performing facial detection/recognition/identification on said subject to identify and track specific regions of interest in the at least one of the one or more images prior to displaying the identified pixels on the display.

11. The method of claim 7 , further comprising:
displaying errors in the at least one of the one or more images as part of displaying the identified pixels on the display.

12. The method of claim 7 , further comprising:
identifying and displaying regions of importance in the least one of the one or more images as part of displaying the identified pixels on the display.

13. A method for detecting a correlation between temperatures on a subject and a reference temperature, said method comprising:
(a) receiving one or more images from an emissive source detector, wherein at least one of the one or more images includes the subject and said one or more calibrated temperature reference devices;
(b) executing instructions read from a computer readable memory with a processor to isolate said one or more calibrated temperature reference devices within the at least one of the one or more images and analyze pixel values of said one or more calibrated temperature reference devices to find a mean reference temperature and a median reference temperature;
(c) executing instructions read from said computer readable memory with said processor to compare the mean reference temperature with the median reference temperature to determine when the median and mean reference temperatures are statistically similar, and use said mean and median reference temperatures to determine the reference temperature when the median and mean reference temperatures are statistically similar;
(d) executing instructions read from said computer readable memory with said processor to map each pixel within the at least one of the one or more images to a specific thermal value based on said mean and median reference temperatures; and
(e) executing instructions read from said computer readable memory with said processor to identify any pixel in the least one of the one or more images with a temperature greater than said reference temperature and display said identified pixels on a display with a temperature greater than said reference temperature with a color and/or shape.

14. The method of claim 13 , further comprising:
executing instructions read from said computer readable memory with said processor to filter errant pixels in the least one of the one or more images on edges or where interpolation has increased actual pixel value prior to displaying the identified pixels

Assignees

• Us Navy
• The United States Of America Represented By The Secretary Of The Navy

Inventors

• Cole Aaron Boyd
• Malec Marcin Stanislaw

Classifications

• H04N5/33

  Transforming infrared radiation (cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20) · CPC title

• H04N23/23

  from thermal infrared radiation · CPC title

• G06T5/70

  Denoising; Smoothing · CPC title

• G06F18/211

  Selection of the most significant subset of features · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title