Method and device for consistent region of interest

• US 20090086022A1
• Filed: 04/29/2005
• Published: 04/02/2009
• Est. Priority Date: 04/29/2005
• Status: Active Grant

• Current Assignee: Chubb International Holdings Ltd. (Carrier Global Corporation)
• Original Assignee: Chubb International Holdings Ltd. (Carrier Global Corporation)
• Inventors: Lin, Lin, Peng, Pei-Yuan, Xiong, Ziyou, Finn, Alan M., Kang, Pengju, Misra, Meghna, Netter, Christian Maria
• Granted Patent: US 8,964,029 B2
• Time in Patent Office: Days
• US Class Current: 348/143
• 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 13/1963 Arrangements allowing camera rotation to change view, e.g. pivoting camera, pan-tilt and zoom [PTZ]
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm
• CPC Class Codes: G08B 13/19689 Remote control of cameras, e.g. remote orientation or image zooming control for a PTZ camera

Abstract

The present invention describes a system and method for surveillance cameras that maintain proper mapping of a mapped region of interest with an imaged region of interest based on feedback received regarding the current orientation of a surveillance camera. The system or method first determines the location of the imaged region of interest within the surveillance camera'"'"'s imaged current field of view based on mechanical or imaged feedback, or a combination of both. The system or method then remaps the mapped region of interest within the surveillance camera'"'"'s imaged current field of view such that the mapped region of interest is coextensive with the imaged region of interest.

Claims

1. A method for maintaining proper mapping of a mapped region of interest with respect to a region of interest, the method including:

receiving feedback regarding motion of a surveillance camera; and

remapping the mapped region of interest based on feedback received such that the mapped region of interest corresponds with the region of interest.

2. The method of claim 1, wherein remapping the mapped region of interest is based on an inverse relationship between movement of the surveillance camera and location of the region of interest within a current field of view of the surveillance camera.

3. The method of claim 1, wherein:

receiving feedback includes;

capturing an image corresponding with a current field of view of the surveillance camera;

comparing the captured image received with a composite image representing an entire possible field of view of the surveillance camera; and

determining current orientation of the surveillance camera based on results of the comparison between the composite image and the captured image; and

remapping the mapped region of interest is based on the determined orientation of the surveillance camera.

4. The method of claim 3, wherein comparing the captured image received with a composite image includes:

using registration algorithms to determine location of the captured image within the composite image.

5. The method of claim 3, including:

creating a composite image representing an entire possible field of view of the surveillance camera, the method of creating the composite image including;

moving the surveillance camera through the entire possible field of view;

recording a number of images corresponding to the current field of view of the surveillance camera as the surveillance camera is moved through the entire possible field of view; and

combining the number of images into the composite image.

6. The method of claim 5, including:

recording the locations of the region of interest with respect to the composite image.

7. The method of claim 6, wherein remapping the mapped region of interest based on the determined orientation of the surveillance camera with respect to the composite image includes:

retrieving the recorded locations of the region of interest with respect to the composite image;

determining based on the recorded locations of the region of interest with respect to the composite image the location of an imaged region of interest with respect to the current field of view of the surveillance camera; and

remapping the mapped region of interest to be coextensive with the imaged region of interest within the current field of view of the surveillance camera.

8. A system for maintaining proper mapping of a mapped region of interest with respect to a region of interest, the method including:

means for receiving feedback regarding motion of a surveillance camera; and

means for remapping the mapped region of interest based on feedback received.

9. The system of claim 8, wherein the means for remapping the mapped region of interest bases the remapping on an inverse relationship between movement of the surveillance camera and location of the region of interest within a current field of view of the surveillance camera.

10. The system of claim 8, wherein:

the means for receiving feedback includes;

means for capturing an image corresponding with a current field of view of the surveillance camera;

means for comparing the captured image received with a composite image representing an entire possible field of view of the surveillance camera; and

means for determining current orientation of the surveillance camera based on results of the comparison between the composite image and the captured image; and

the means for remapping the mapped region of interest bases the remapping on the determined orientation of the surveillance camera.

11. The system of claim 10, wherein the means for comparing the captured image received with a composite image includes:

means for performing registration algorithms between the captured image and the composite image to determine location of the captured image within the composite image.

12. The system of claim 10, including:

means for creating a composite image representing an entire possible field of view of the surveillance camera, the means for creating the composite image including;

means for moving the surveillance camera through the entire possible field of view;

means for recording a number of images corresponding to the current field of view of the surveillance camera as the surveillance camera is moved through the entire possible field of view; and

means for combining the number of images into the composite image.

13. The system of claim 12, including:

means for recording a location of the region of interest with respect to the composite image.

14. The system of claim 13, wherein the means for remapping the mapped region of interest based on the determined orientation of the surveillance camera with respect to the composite image includes:

means for retrieving the recorded location of the region of interest with respect to the composite image;

means for determining based on the recorded location of the region of interest with respect to the composite image the location of an imaged region of interest with respect to the current field of view of the surveillance camera; and

means for remapping the mapped region of interest to be coextensive with the imaged region of interest within the current field of view of the surveillance camera.

15. A method for maintaining a mapped region of interest in the proper location, the method comprising:

compiling an image database representative of a total possible viewing area available to a camera;

using the image database to complete a composite field of view of the total possible viewing area available to the camera;

defining a region of interest with respect to a location of the region of interest within the composite field of view;

moving the camera to a current field of view within the total possible viewing area available to the camera;

comparing the current field of view with the composite field of view to determine orientation of the camera and location of the region of interest within; and

setting a mapped region of interest to be coextensive with the location of the region of interest.

16. The method of claim 15, wherein the step of compiling an image database includes:

moving the camera through the total possible viewing area available to the camera; and

storing a number of images as the camera moves through the total possible viewing area corresponding to the total possible field of view of the camera at the highest magnification level.

17. The method of claim 16, wherein the step of using the image database to complete a composite field of view includes:

comparing the number of stored images using image registration techniques; and

using the result of the image registration techniques to create composite field of view.

18. The method of claim 15, wherein the step of comparing the current field of view with the composite field of view to determine orientation of the camera includes:

performing a fast Fourier transform on both the current field of view and the composite field of view;

providing frequency domain results of the fast Fourier transform to a correlation algorithm; and

determining with the correlation algorithm where the current field of view is located within the composite field of view.

19. The method of claim 18, wherein after determining where the current field of view is located within the composite field of view, the method includes:

using the locations of the region of interest defined with respect to the composite field of view to determine the location of the region of interest with respect to the current field of view.

20. The method of claim 19, where the step of setting the mapped region of interest to be coextensive with the location of the region of interest is determined with respect to the current field of view.