Smoke detection method and apparatus

• US 7,805,002 B2
• Filed: 11/08/2004
• Issued: 09/28/2010
• Est. Priority Date: 11/07/2003
• Status: Active Grant

• Current Assignee: FIKE Video Analytics Corporation
• Original Assignee: Axonx Fike Corporation
• Inventors: Privalov, George
• Primary Examiner(s): Bella; Matthew C
• Assistant Examiner(s): MACKOWEY, ANTHONY M
• Application Number:
  US10/983,791
• Publication Number:
  US 20050100193A1
• Time in Patent Office: 2,150 Days
• Field of Search: 382/100, 382/103, 382/106, 382/168, 382/170, 382/171, 382/172, 348/82, 348/83, 356/432, 356/433, 356/434, 356/438
• US Class Current: 382/170
• CPC Class Codes: G08B 17/103 using a light emitting and receiving device
• CPC Class Codes: G08B 17/107 for detecting light-scattering due to smoke
• CPC Class Codes: G08B 17/125 by using a video camera to detect fire or smoke

Abstract

A smoke detection method and system, which uses the effects of the diffusion of light to identify the presence of smoke in a monitored area, are disclosed. This method comprises the steps of: (1) electronically capturing a sequence of images of a light source in the monitored area, (2) transferring these images into an image buffer, (3) scanning these images to identify the chunks of adjacent pixels with brightness values above a prescribed threshold, (4) maintaining the sequence of such chunks obtained from consecutive images in a cluster stack, (5) analyzing the evolution of the features of each of these cluster over a prescribed period of time to identify the patterns that are caused by particle-induced light diffusion, and (6) issuing a prescribed system response in the event such light diffused patterns are identified.

Claims

1. A method of detecting smoke in a monitored area containing a light source, said method comprising the steps of:

capturing, at a point in said monitored area that is distant from said light source at a prescribed frequency, a sequence of two-dimensional, pixel bitmaps of the video images of said light source;

storing said sequence of two-dimensional, pixel bitmaps;

extracting from said stored sequence of bitmaps those pixels that make up a bright spot area within each of said bitmaps that is due to the presence of said light source in said monitored area, wherein said extractions yield a sequential collection of bright spot areas having characteristics including a distribution of different brightness values observed across the spatial extent of said bright spot areas; and

identifying an increase in diversity of the different brightness values observed across the spacial extent of said bright spot areas, based on said sequential collection, as being indicative of the presence of smoke in said monitored area acting to diffuse the light from said light source.

2. The method of smoke detection as recited in claim 1, wherein said extraction of those pixels that make up said bright spot areas involves selecting those pixels whose brightness values exceed a prescribed threshold value.

3. The method of smoke detection as recited in claim 1, wherein:

the increase in diversity of the different brightness values is determined by changes in the Shannon entropy for those pixels that comprise said bright spot areas.

4. The method of smoke detection as recited in claim 1, further comprising the step of:

in the event that said presence of smoke in said monitored area is identified, signaling the detection of said monitored area.

5. The method of smoke detection as recited in claim 1, wherein an increase in diversity of the different brightness values is determined by identifying an increase in the quantity of different brightness values measured for the pixels within said bright spot areas.