Smoke detection

• US 20020024446A1
• Filed: 04/20/2001
• Published: 02/28/2002
• Est. Priority Date: 10/20/1998
• Status: Active Grant

• Current Assignee: VSD Limited
• Original Assignee: VSD Limited
• Inventors: Grech-Cini, Henry Joseph
• Granted Patent: US 6,844,818 B2
• Time in Patent Office: Days
• US Class Current: 340/628
• 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 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 17/125 by using a video camera to detect fire or smoke

Abstract

A smoke detection system comprising video camera monitoring means, video frame comparison means, signal processing means, and alarm generating means dependant on an output from the signal processing means; the signal processing means being arranged to analyse successive frames acquired by the video camera monitoring means and to compare the intensity and/or colour of individual pixels or group of pixels so as to consider the overall characteristics and inter-relationships of these pixels so as to detect the presence of smoke characterised in that the signal processing means analyses a plurality of different types of change in the said characteristics and inter-relationships.

Claims

1. A smoke detection system comprising video camera monitoring means, video frame comparison means, signal processing means, and alarm generating means dependent on an output from the signal processing means;

the signal processing means being arranged to analyse successive frames acquired by the video camera monitoring means and to compare the intensity and/or colour of individual pixels or group of pixels so as to consider the overall characteristics and inter-relationships of these pixels so as to detect the presence of smoke characterised in that the signal processing means analyses a plurality of different types of change in the said characteristics and inter-relationships.

2. A smoke detection system according to claim 1 in which the signal processing means is arranged to analyse the changes by a combination of a weighted rule based analysis and a statistically based analysis.

3. A smoke detection system according to claim 2 in which the statistically based analysis is a Bayesian analysis.

4. A smoke detection system according to claim 1 in which a change to be analysed is that the value of at least some of the pixels being analysed are identified as converging towards a mean value.

5. A smoke detection system according to claim 1 in which a change to be analysed is that pixels defining edge information change from showing structured definition to showing a less structured level of information.

6. A smoke detection system according to claim 1 in which a change to be analysed is that dynamic parts of the overall image are identified as becoming static.

7. A smoke detection system according to claim 1 in which a change to be analysed is that measured differences are identified as being distributed in small isolated groups.

9. A smoke detection system according to claim 1 in which a change to be analysed is that new regions are identified as appearing which have characteristics of shape which resemble those of known shape characteristics of an emerging smoke or fire condition.

10. A smoke detection system according to claim 1 or 2 in which a plurality of the changes in accordance with at least any two of claims 4 to 9 is arranged to be analysed.

11. A smoke detection system according to claim 4 in which a number of frames are arranged to be analysed and the value of each pixel or pixel group is examined to see whether it is converging to a mean value.

12. A smoke detection system according to claim 1 in which the signal processing means is arranged to analyse four different types of change, the first change being that the value of at least some of the pixels within the region are identified as converging towards a mean value, the second change being that pixels defining edge information change from showing structured definition to showing a less structured level of information, the third change being that the overall image ceases to be static and is identified as moving in an unpredictable manner and the fourth change being that new regions are identified as appearing which have shaped characteristics which resemble those of known shaped characteristics of an emerging smoke or fire condition.

8. A smoke detection system in which a change to be analysed is that the value of changed pixels as between a current image and a reference image indicates a reduction in visibility.