System and method for ensuring the performance of a video-based fire detection system

• US 8,538,063 B2
• Filed: 05/08/2008
• Issued: 09/17/2013
• Est. Priority Date: 05/08/2008
• Status: Active Grant

• Current Assignee: UTC Fire & Security (Rtx Corporation)
• Original Assignee: UTC Fire & Security (Rtx Corporation)
• Inventors: Caballero, Rodrigo E., Finn, Alan Matthew, Peng, Pei-Yuan, Xiong, Ziyou, Wang, Hongcheng
• Primary Examiner(s): SHAH, UTPAL D
• Application Number:
  US12/736,750
• Publication Number:
  US 20110051993A1
• Time in Patent Office: 1,958 Days
• Field of Search: 382/190, 382/195, 382/100
• US Class Current: 382/100
• 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 13/194 using image scanning and comparing systems
• CPC Class Codes: G08B 13/196 using television cameras

Abstract

A video-based fire detection system receives video data comprised of a plurality of individual frames, and determines based on the video data the ability of the system to detect the presence of fire. The system includes a video recognition system connectable to receive the video data and to calculate one or more background features associated with the video data. Based on the calculated background features, the video recognitions system assesses the ability of the video-based fire detection system to detect the presence of fire. The system includes one or more outputs operably connectable to communicate the results of the assessment made by the video recognitions system.

Claims

1. A method of initializing a video-based fire detection system to detect the presence of fire, the method comprising:

acquiring video data comprised of individual frames from a video detector;

calculating background features associated with one or more of the individual frames;

assessing the ability of the video-based fire detection system to detect the presence of fire based on the calculated background features; and

generating an output indicating the ability of video-based fire detection system to detect the presence of fire.

2. The method of claim 1, wherein calculating background features includes:

calculating an edge-based feature that characterizes the edge content of the individual frame.

3. The method of claim 2, wherein assessing the ability of the video-based fire detection system to detect the presence of fire based on the calculated background features includes:

comparing the edge-based feature to a threshold value using decisional logic that determines whether the individual frame contains sufficient edge content to allow the video-based fire detection system to detect the presence of fire.

4. The method of claim 1, wherein calculating background features includes:

calculating a color-based feature that characterizes the color content of the individual frame.

5. The method of claim 4, wherein assessing the ability of the video-based fire detection system to detect the presence of fire based on the calculated background features includes:

comparing the color-based feature to a threshold value using decisional logic that determines whether the individual frame contains sufficient color content to allow the video-based fire detection system to detect the presence of fire.

6. The method of claim 1, wherein calculating background features includes calculating background features selected from the group consisting of:

a color-based feature, a spatial frequency feature, an edge-based feature, a motion-based feature, an illumination feature, a contrast feature, and combinations thereof.

7. The method of claim 1, wherein generating an output indicating the ability of video-based fire detection system to detect the presence of fire includes:

displaying an image that indicates visually the assessed ability of the video-based fire detection system to detect the presence of fire with respect to areas defined within the field of view of the video detector.

8. The method of claim 1, wherein generating an output includes:

generating a recommendation regarding steps to improve the assessed ability of the video-based fire detection system to detect the presence of fire.

9. The method of claim 1, wherein generating an output includes:

generating a real-valued output indicating a confidence level associated with the assessed ability of the video-based fire detection system to detect the presence of fire.

10. A method of monitoring an ability of a video-based fire detection system to detect the presence of fire, the method comprising:

calculating video-quality features associated with individual frames during operation of the video-based fire detection system;

detecting video quality degradation that adversely affects the ability of video-based fire detection system to detect the presence of fire based on the calculated video quality features; and

generating an output indicating the ability of the video-based fire detection system to detect the presence of fire based on the detected video quality degradation.

11. The method of claim 10, further including:

calculating video-quality features during installation of the video-based fire detections system; and

storing the video-quality features calculating during installation, wherein detecting video quality degradation includes comparing the video-quality features calculated during operation of the video-based fire detection system to the stored video-quality features calculated during installation to determine whether the detected degradation of video quality adversely affects the ability of the video-based fired detection system to detect the present of fire.

12. The method of claim 11, wherein calculating video-quality features includes generating a distribution with respect to each video-quality feature and wherein calculating video-quality features during installation includes calculating a target spatial distribution comprised of equally-sized sub-images defined by a uniform distribution, and wherein detecting video quality degradation includes comparing the distributions calculated with respect to each video-quality feature to the target-spatial distribution.

13. The method of claim 10, wherein calculating video-quality features includes calculating a plurality of video-quality features over a defined interval, and wherein detecting video quality degradation that adversely affects the ability of video-based fire detection system to detect the presence of fire includes distinguishing between video-quality degradation and a fire-based event based on the plurality of video-quality features calculated over the defined interval.

14. A video-based fire detection system comprising:

inputs operably connectable to receive video data comprised of a plurality of individual frames from one or more video detectors;

a video recognition system connectable to receive the video data and to provide an output assessing the ability of the video recognition system to detect the presence of fire, wherein the video recognition system is operable to calculate background features associated with each individual frame, and to assess the ability of the video-based fire detection system to detect the presence of fire based on the calculated background features; and

outputs operably connectable to communicate the assessed ability of the video recognition system to detect the presence of fire.

15. The video-based fire detection system of claim 14, wherein the background features calculated by the video recognition system includes at least one feature selected from the group consisting of:

a color-based feature, a spatial frequency feature, an edge-based feature, a motion-based feature, an illumination feature, a contrast feature, and combinations thereof.

16. The video-based fire detection system of claim 14, wherein the output generated by the video recognition system includes a visual display that illustrates the assessed ability of the video recognition system to detect the presence of fire with respect to areas within the field of view of the video detector.

17. The video-based fire detection system of claim 14, wherein the video recognition system is operable to calculate video-quality features associated with each individual frame, wherein the video-recognition system detects degradation in the quality of video provided by the video detectors that would adversely affect the ability of the video recognition system to detect the presence of fire.

18. The video-based fire detection system of claim 17, wherein the output generated by the video recognition system is a notification that indicates the assessed ability of the video-based fire detection system to detect the presence of fire has been reduced.