Image processing of regions in a wide angle video camera

• US 7,366,359 B1
• Filed: 07/08/2005
• Issued: 04/29/2008
• Est. Priority Date: 07/08/2004
• Status: Expired due to Fees

• Current Assignee: Grandeye Limited (Oncam Global Group AG)
• Original Assignee: Grandeye Limited (Oncam Global Group AG)
• Inventors: Castellari, Andrea Elvis, Ahiska, Yavuz, Davey, Mark Kenneth
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Koziol; Stephen R
• Application Number:
  US11/178,232
• Time in Patent Office: 1,026 Days
• Field of Search: 382/274, 348/143, 348/159
• US Class Current: 382/274
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• 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: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A system and method for providing privacy regions in a picture or video. In one example embodiment, a camera is provided which has a lens system and detector, image processing circuitry, compression and formatting circuitry, and control circuitry. Images or video taken from the camera are preferably corrected for distortion (such as that introduced by an anamorphic lens system) and sent to an operator'"'"'s workstation, where a privacy region is defined. The privacy region is merged with the rest of the image, whether constant or dynamic, and displayed. Other processing, such as object tracking and alarms, can also be implemented at varying points in the process.

Claims

1. A method of manipulating an image, comprising the steps of:

capturing a non-perspective wide angle view;

correcting the non-perspective wide angle view to create a first corrected view;

defining a first region of said first corrected view to be obscured;

projecting the first region onto the non-perspective wide angle view;

obscuring the first region in the non-perspective wide angle view;

correcting the non-perspective wide angle view with the obscured first region to create a second corrected view; and

outputting the second corrected view;

wherein said method is conducted using a non-mechanical pan-tilt-zoom wide angle camera.

2. The method of claim 1, wherein motion detection processing is performed and moving regions of the image are determined on the distorted image before the first region is obscured.

3. The method of claim 1, wherein moving objects within the first region are obscured, but non-moving objects in the first region are not obscured.

4. The method of claim 1, wherein the first region is obscured or not depending upon an alarm being triggered.

5. The method of claim 1, wherein the first region is obscured or not depending on contents of the first region.

6. The method of claim 1, wherein some or all of a corrected view is outputted with the first region unobscured, and wherein some or all of the corrected view is outputted with the first region obscured.

7. The method of claim 1, wherein non-moving objects are identified by background estimation.

8. The method of claim 1, wherein non-moving objects are obscured within the first region, but moving objects are not obscured within the first region.

18. The method of claim 1, wherein the first region is stored after the projection step.

20. The method of claim 1, wherein the method is carried out in an anamorphic optical system.

9. A wide angle video camera, comprising:

an input device for defining a region of a perspectively-correct wide angle view from a non-mechanical pan-tilt-zoom wide angle video camera suitable for image processing;

first circuitry for projecting the region onto a non-perspective version of the wide angle view;

second circuitry for processing the region in the non-perspective wide angle view; and

an output device for outputting a corrected view.

10. The camera of claim 9, wherein the second circuitry for processing obscures the region.

11. The camera of claim 9, wherein the second circuitry for processing includes motion detection and object tracking capability.

12. The camera of claim 9, wherein the region is obscured prior to being outputted.

13. The camera of claim 12, wherein moving objects in the region are not obscured.

15. The camera of claim 9, wherein the wide angle view is stereographically projected before the region is defined.

16. The camera of claim 9, wherein the wide angle view is stereographically projected after the region is defined;

and

after stereographic projection, the region is merged with the wide angle view.

17. The camera of claim 9, wherein the wide angle view is stereographically projected after merging the region and the wide angle view.

14. A method of manipulating an image, comprising the steps of:

determining the pixels of a distorted wide angle image corresponding to a region of the distorted image after correction by the use of mapping tables that define the projection of the corrected image to the distorted image, and

outputting said pixels.

19. The method of claim 14, wherein the method is carried out using a computer program product on a computer readable medium.