Fire detection apparatus utilizing a camera

• US 10,395,498 B2
• Filed: 02/19/2015
• Issued: 08/27/2019
• Est. Priority Date: 02/19/2015
• Status: Active Grant

• Current Assignee: Smoke Detective LLC
• Original Assignee: Smoke Detective LLC
• Inventors: Mills, Russell P, Rohde, Gustavo K, Lanni, Frederick, Davis, Jr., Stephen C
• Primary Examiner(s): Rahman, Mohammad J
• Application Number:
  US14/625,689
• Publication Number:
  US 20160247375A1
• Time in Patent Office: 1,650 Days
• Field of Search: None
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 17/125 by using a video camera to detect fire or smoke
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A fire detection device is provided that has a camera that captures a reference image and a measured image. A processor compares intensity of the measured image to intensity of the reference image and uses this comparison to determine if an alarm is generated to indicate the presence of fire. The intensity of the measured image may be the total number of photons of the measured image, and the intensity of the reference image may be the total number of photons of the reference image. In other arrangements, the intensity may be measured between individual corresponding pixels of the reference and measured images.

Claims

1. A fire detection device, comprising:

a camera that captures a reference image and a measured image, the measured image and the reference image each comprising a plurality of pixels, wherein each pixel in the reference image has a corresponding pixel in the measured image; and

a processor configured to;

determine an intensity of the reference image defined as a digital numerical quantity indicative of the number of photons of light detected in the reference image;

(ii) determine an intensity of the measured image defined as a digital numerical quantity indicative of the number of photons of light detected in the measured image;

(iii) determine the difference between the intensity of the measured image and the intensity of the reference image;

(iv) determine whether the difference between the intensity of the measured image and the intensity of the reference image exceeds a preselected intensity threshold;

(v) determine a pixel intensity of each individual pixel in the measure image and the reference image when the difference between the intensity of the measured image and the intensity of the reference image exceeds the preselected intensity threshold, wherein the pixel intensity is defined as a digital numerical quantity indicative of the number of photons of light detected in an individual pixel;

(vi) determine whether a preselected threshold percentage of pixels in the measured image have an increased pixel intensity compared to the pixel intensity of the corresponding pixel in the reference image;

(vii) determine the number of contiguous pixels having an increased pixel intensity in the measured image when said preselected threshold percentage of pixels is met;

(viii) when preselected threshold percentage of pixels is not met, repeat steps (ii)-(vii);

(ix) when the number of continuous pixels having an increased pixel intensity in the measured image exceeds a preselected number of pixels, indicate the presence of smoke.

2. The fire detection device as set forth in claim 1, wherein the camera is configured to capture a first reference threshold image and a second reference threshold image and the processor is configured to establish the preselected intensity threshold by:

(i) determining an intensity of the second reference image defined as a digital quantity indicative of the number of photons of light detected in the second reference threshold image;

determining an intensity of the first reference image defined as a digital quantity indicative of the number of photons of light detected in the first reference threshold image; and

defining the preselected intensity threshold as the difference between the intensity of the second reference threshold image and the intensity of the first reference threshold image.

3. The fire detection device as set forth in claim 2, wherein the measured image and the second reference threshold image are the same image.

4. The fire detection device as set forth in claim 1, wherein the preselected threshold percentage is at least fifty percent.

5. The fire detection device as set forth in claim 1, wherein the processor is further configured to determine whether the pixels having an increased pixel intensity in the measured image are located in an outer area of the measured image, the outer area being defined as the area of the measured image that includes the half of the pixels of the measured image that are furthest from the center of the measured image, wherein the processor indicates the presence of smoke based on whether a preselected number of pixels having an increased pixel intensity in the outer area of the measured image meets a pre-selected criteria.

6. The fire detection device as set forth in claim 1, wherein the measured image and the reference image are black and white images.

7. The fire detection device as set forth in claim 1, wherein said processor is further configured to (i) determine a pixel intensity difference for each pixel in the measured image as compared to the corresponding pixel in the reference image;

(ii) determine whether the pixel intensity difference for each pixel exceeds a preselected pixel intensity threshold for each particular pixel, wherein the processor indicates the presence of smoke based on whether a preselected threshold number of pixels in the measured image exceeds the preselected pixel intensity threshold.

8. The fire detection device as set forth in claim 7, wherein the processor is further configured to base the decision to indicate the presence of smoke on whether the pixels that have exceeded the preselected pixel intensity threshold in the measured image are contiguous with one another such that at least fifty percent are immediately adjacent to another pixel that has exceeded the preselected pixel intensity threshold.

9. The fire detection device as set forth in claim 7, wherein the processor is further configured to determine whether the pixels that have exceeded the preselected pixel intensity threshold in the measured image are located in an outer area of the measured image, the outer area being defined as the area of the measured image that includes the half of the pixels of the measured image that are furthest from the center of the measured image, wherein the processor indicates the presence of smoke based on whether a preselected number of pixels exceeding the preselected pixel intensity threshold in the outer area of the measured image meets a pre-selected criteria.

10. The fire detection device as set forth in claim 7, wherein the processor is further configured to calculate a detection statistic based on an analysis of a pattern selected from the group consisting of:

(a) a spatial pattern of the pixels that exceed the pixel intensity threshold for each particular pixel;

(b) a temporal pattern of pixels that exceed the pixel intensity threshold for each particular pixel in a series of measured images; and

(c) both a spatial pattern of the pixels that exceed the pixel intensity threshold for each particular pixel and a temporal pattern of pixels that exceed the pixel intensity threshold for each particular pixel in a series of measured images.

11. The fire detection device as set forth in claim 7, wherein the processor is further configured to:

(i) identify a subset of pixels in the measured image having the highest intensity;

(ii) compare the pixel intensity of each of the pixels in the subset of the measured image to the pixel intensity of the corresponding pixel of the reference image to define a pixel intensity difference for each of the pixels in the subset; and

(iii) determine if the pixel intensity difference for each of the pixels in the subset exceeds the preselected pixel intensity threshold, wherein the pixel intensity threshold may be the same or different for each pixel in the subset, and wherein the processor indicates the presence of smoke based on the result of step (iii).

12. The fire detection device as set forth in claim 11, wherein the processor is further configured to determine whether the number of pixels having a pixel intensity difference that exceeds the preselected pixel intensity threshold is greater than a preselected threshold number of pixels, wherein the processor indicates the presence of smoke based on whether the preselected threshold number of pixels is exceeded.

13. The fire detection device as set forth in claim 11, wherein the number of pixels in the subset does not exceed 10% of the total pixels of the measured image.

14. The fire detection device as set forth in claim 1, further comprising a light source that emits light into a field of view of the camera.

15. The fire detection device as set forth in claim 14, wherein the camera, the light source, and the processor are all components of a smart phone.

16. The fire detection device as set forth in claim 1, wherein the camera is configured to capture a series of reference images at a first rate, and wherein when the percentage threshold is exceeded, capture a second series of references images at a second rate, wherein the second rate is faster than the first rate.

17. The fire detection device as set forth in claim 14, further comprising a screen that displays information about the fire detection device and obtains instructions from a user of the fire detection device that are communicated to the processor.

18. The fire detection device as set forth in claim 1, wherein the processor is configured to determine the intensity of the measured image and the intensity of the reference image based on a subset of pixels in the measured image, the subset comprising those pixels having an intensity above a threshold intensity.