Detection and recognition of fog presence within an aircraft compartment using video images

• US 8,400,502 B2
• Filed: 07/31/2008
• Issued: 03/19/2013
• Est. Priority Date: 05/20/2002
• Status: Expired due to Fees

• Current Assignee: Simmonds Precision Products, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Original Assignee: Simmonds Precision Products, Inc. (Raytheon Technologies Corporation d/b/a RTX)
• Inventors: Zakrzewski, Radoslaw Romuald, Sadok, Mokhtar, Shirer, Jeffrey James, Zeliff, Robert Lowell
• Primary Examiner(s): Moe, Aung S
• Assistant Examiner(s): DAGNEW, MEKONNEN D
• Application Number:
  US12/221,186
• Publication Number:
  US 20090040367A1
• Time in Patent Office: 1,692 Days
• Field of Search: 348/117, 348122-123, 348/131, 348/153, 348/159, 348/164
• US Class Current: 348/122
• CPC Class Codes: B64D 45/0053 using visual equipment, e.g. cameras
• CPC Class Codes: G06F 18/24765 Rule-based classification
• CPC Class Codes: G06F 18/253 of extracted features
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 10/765 using rules for classification or partitioning the feature space
• CPC Class Codes: G06V 10/806 of extracted features
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• 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

Abstract

Detecting video phenomena, such as fire in an aircraft cargo bay, includes receiving a plurality of video images from a plurality of sources, compensating the images to provide enhanced images, extracting features from the enhanced images, and combining the features from the plurality of sources to detect the video phenomena. Extracting features may include determining an energy indicator for each of a subset of the plurality of frames. Detecting video phenomena may also include comparing energy indicators for each of the subset of the plurality of frames to a reference frame. The reference frame corresponds to a video frame taken when no fire is present, video frame immediately preceding each of the subset of the plurality of frames, or a video frame immediately preceding a frame that is immediately preceding each of the subset of the plurality of frames. Image-based and non-image based techniques are described herein in connection with fire detection and/or verification and other applications.

Claims

1. A system for acquiring camera data in a space, comprising:

a plurality of cameras disposed in the space;

a first plurality of illumination units, wherein each of the first plurality of illumination units is disposed proximal to one of the cameras;

a second plurality of illumination units disposed overhead in the space, the second plurality of illumination units being different from the first plurality of illumination units and being disposed independently of the cameras; and

a control unit that controls actuation of the illumination units and the cameras, wherein the second plurality of illumination units are controlled independently of the first plurality of illumination units and of the cameras, and wherein the control unit actuates different combinations of the first plurality of illumination units and the second plurality of illumination units to provide a plurality of different lighting views of the space while the cameras acquire the camera data in the space, wherein image features are extracted from the camera data acquired during the actuation of the different combinations of illumination units, wherein the image features are used in analyzing the camera data, and wherein analyzing the camera data includes determining whether fog is present in the space.

2. A system, according to claim 1, further comprising:

a plurality of filters that filter energy provided to the cameras, wherein the filters pass energy corresponding to the output of the illumination units.

3. A system, according to claim 2, wherein the filters pass light having a wavelength of above approximately 800 nm.

4. A system, according to claim 2, wherein the filters filter out visible light.

5. A system, according to claim 4, wherein the cameras are CCD cameras and the first and second plurality of illumination units emit light in the NIR band.

6. A system, according to claim 1, where the different combinations are selected from one or more of the following:

all illumination units on, all illumination units off, only the second plurality of illumination units on, and only a subset of the first plurality of illumination units on.

7. A system, according to claim 1, wherein the cameras are CCD cameras.

8. A system, according to claim 7, wherein the first and second plurality of illumination units emit light in the NIR band.

9. A system for acquiring camera data in a space, comprising:

camera means for accepting camera data;

a first plurality of illumination means disposed proximal to the camera means;

a second plurality of illumination means disposed overhead in the space, the second plurality of illumination means being different from the first plurality of illumination means and being disposed independently of the camera means; and

control means for controlling actuation of the illumination means and the camera means, wherein the second plurality of illumination means are controlled independently of the first plurality of illumination means and of the camera means, and wherein the control means actuates different combinations of the first plurality of illumination means and the second plurality of illumination means to provide a plurality of different lighting views of the space while the camera means acquires the camera data in the space, wherein image features are extracted from the camera data acquired during the actuation of the different combinations of illumination means, wherein the image features are used in analyzing the camera data, and wherein analyzing the camera data includes determining whether fog is present in the space.

10. A system, according to claim 9, further comprising:

a plurality of filters means for filtering energy provided to the camera means and for passing energy corresponding to the output of the illumination means.

11. A system, according to claim 10, wherein the filter means pass light having a wavelength of above approximately 800 nm.

12. A method of acquiring data in a space, comprising:

placing a plurality of cameras in the space;

placing a first plurality of illumination units and a second plurality of illumination units in the space, wherein the second plurality of illumination units are overhead in the space and the first plurality of illumination units are associated with each of the cameras, the second plurality of illumination units being different from the first plurality of illumination units and being disposed independently of the cameras; and

controlling actuation of the illumination units while the cameras acquire the data, wherein the second plurality of illumination units are operated independently of the first plurality of illumination units and of the cameras, and different combinations of the first plurality of illumination units and the second plurality of illumination units are actuated to provide a plurality of different lighting views of the space while the cameras acquire the camera data in the space, wherein image features are extracted from the camera data acquired during the actuation of the different combinations of illumination units, wherein the image features are used in analyzing the camera data, and wherein analyzing the camera data includes determining whether fog is present in the space.

13. A method, according to claim 12, where the different combinations are selected from one or more of the following:

all illumination units on, all illumination units off, and only a subset of the plurality of illumination units on.

14. A method, according to claim 12, further comprising:

filtering out light having a particular range of wavelengths.

15. A method, according to claim 14, wherein the particular range of wavelengths includes visible light.

16. A method, according to claim 15, wherein the cameras are CCD cameras and the illumination units emit light in the NIR band.

17. A non-transitory computer readable medium storing computer software that acquires data in a space, the computer software comprising:

executable code that controls actuation of a plurality of cameras; and

executable code that controls actuation of a first plurality of illumination units and a second plurality of illumination units while the cameras acquire the data, the first plurality of illumination units being disposed proximal to the cameras and the second plurality of illumination units being different from the first plurality of illumination units and being disposed independently of the cameras, wherein different combinations of the illumination units to be actuated are selected from one or more of the following;

all illumination units on, all illumination units off, and only a subset of the plurality of illumination units on, wherein the second plurality of illumination units are controlled independently of the first plurality of illumination units and of the cameras, and wherein the different combinations of the first plurality of illumination units and the second plurality of illumination units provide a plurality of different lighting views of the space while the cameras acquire the camera data in the space, wherein image features are extracted from the camera data acquired during the actuation of the different combinations of illumination units, wherein the image features are used by executable code that analyzes the camera data, and wherein the executable code that analyzes the camera data includes executable code that determines whether fog is present in the space.

18. The non-transitory computer readable medium, according to claim 17, wherein the computer software further comprises:

executable code that causes undesirable light to be filtered out.