Transformable privacy mask for video camera images

• US 8,212,872 B2
• Filed: 06/02/2004
• Issued: 07/03/2012
• Est. Priority Date: 06/02/2004
• Status: Active Grant

• Current Assignee: Bosch Security Systems Incorporated (Robert Bosch GmbH), Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Sablak, Sezai
• Primary Examiner(s): Patel, Jayanti K
• Assistant Examiner(s): TORRENTE, RICHARD T
• Application Number:
  US10/858,817
• Publication Number:
  US 20050270371A1
• Time in Patent Office: 2,953 Days
• Field of Search: 348/143
• US Class Current: 348/143
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00
• CPC Class Codes: G06T 3/00 Geometric image transformations in the plane of the image
• CPC Class Codes: G08B 13/19686 Interfaces masking personal details for privacy, e.g. blurring faces, vehicle license plates
• CPC Class Codes: H04N 23/633 for displaying additional information relating to control or operation of the camera
• CPC Class Codes: H04N 23/695 Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
• 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 including a camera, display screen and processing device. A privacy mask obscures a portion of the displayed images. The processing device transforms the privacy mask in accordance with changes in the field of view of the camera, wherein, in a first field of view, the privacy mask is defined by a plurality of vertices having coordinates (x1, y1), . . . (xn, yn), and, in a second field of view, the processing device determines transformed coordinates, (x1′, y1′), . . . (xn′, yn′), for each of the vertices based upon changes in the field of view of the camera. The privacy mask is definable by pixel rows and the processing device identifies opposing ends of a plurality of the pixel rows, each of the identified ends defining one vertex of the privacy mask. The privacy mask may also include an unmasked area completely encircled by masked area.

Claims

1. A surveillance camera system comprising:

a camera having an adjustable field of view;

a display screen displaying images acquired by said camera;

a processing device operably coupled to said camera and said display screen, said processing device configured to allow a user to define a privacy mask obscuring a portion of the displayed images, said processing device further configured to transform said privacy mask in accordance with changes in the field of view of said camera, wherein, in a first field of view, said privacy mask is defined by a plurality of vertices having coordinates (x1, y1), .. . (xn, yn), and, in a second field of view differing from said first field of view, said processing device determines transformed coordinates, (x1′

, y1′

), . . . (xn′

, yn′

), for each of said vertices based upon changes in the field of view of said camera wherein said privacy mask and said transformed privacy mask obscure substantially common subject matter in both said first field of view and said second field of view respectively; and

wherein said privacy mask in said first field of view is definable by pixel rows and said processing device is configured to identify opposing ends of a plurality of said pixel rows, each of said identified ends defining one of said vertices of said privacy mask, and wherein said processing device is programmed to determine a polygon defined by said vertices of said privacy mask and to infill said polygon to form said privacy mask without scanning an entire displayed image.

2. The surveillance camera system of claim 1 wherein said processing device identifies opposing ends of each of said pixel rows defining said privacy mask and each of said identified ends defines one of said vertices of said privacy mask.

3. The surveillance camera system of claim 1 wherein a user selects a plurality of boundary locations to define said privacy mask in said first field of view, said plurality of boundary locations selected by the user being less than n.

4. The surveillance camera system of claim 1 wherein said privacy mask defines a masked area completely encircling an unmasked area.

5. The surveillance camera system of claim 1 wherein adjustment of the field of view between said first field of view and said second field of view includes adjustment of a pan angle, a tilt angle and a focal length of said camera.

6. A surveillance camera system comprising:

a camera having an adjustable field of view;

a display screen displaying images acquired by said camera;

a processing device operably coupled to said camera and said display screen, said processing device configured to allow a user to define a privacy mask obscuring a portion of the displayed images, said processing device further configured to transform said privacy mask in accordance with changes in the field of view of said camera, wherein, in a first field of view, said privacy mask is defined by a plurality of vertices having coordinates (x1, y1), . . . (xn, yn), and, in a second field of view differing from said first field of view, said processing device determines transformed coordinates, (x1′

, y1′

), . . . (xn′

, yn′

), for each of said vertices based upon changes in the field of view of said camera wherein said privacy mask and said transformed privacy mask obscure substantially common subject matter in both said first field of view and said second field of view respectively; and

wherein said privacy mask in said first field of view is definable by a plurality of pixel blocks and said processing device is configured to identify at least one location point for each said pixel block, each of said location points defining one of said vertices of said privacy mask and wherein said privacy mask includes at least one non-perimeter pixel block entirely circumscribed by other pixel blocks forming a portion of said privacy mask, and wherein said processing device is programmed to determine a polygon defined by said vertices of said privacy mask and to infill said polygon to form said privacy mask without scanning an entire displayed image.

7. The surveillance camera system of claim 6 wherein a user selects a plurality of boundary locations to define said privacy mask in said first field of view, said plurality of boundary locations selected by the user being less than n.

8. The surveillance camera system of claim 6 wherein said pixel blocks all have a common size.

9. The surveillance camera system of claim 6 wherein each of said pixel blocks is formed by a single pixel.

10. The surveillance camera system of claim 6 wherein said privacy mask defines a masked area completely encircling an unmasked area.

11. The surveillance camera system of claim 6 wherein adjustment of the field of view between said first field of view and said second field of view includes adjustment of a pan angle, a tilt angle and a focal length of said camera.

12. A method of obscuring a selected portion of video images, said method comprising:

acquiring images with a camera;

displaying the acquired images on a display screen;

defining a privacy mask with a plurality of mask vertices having coordinates (x1, y1), . . . (xn, yn), the privacy mask obscuring a selected portion of the displayed images;

adjusting the field of view of the camera from a first field of view to a second field of view;

determining transformed coordinates, (x1′

, y1′

), . . . (xn′

, yn′

), for each of the mask vertices to define a transformed privacy mask for the second field of view, the transformed coordinates being determined based upon changes in the field of view of the camera wherein the privacy mask and the transformed privacy mask obscure substantially common subject matter in both the first field of view and the second field of view respectively;

determining a polygon defined by said mask vertices of said transformed privacy mask; and

infilling said polygon to provide said transformed privacy mask in the second field of view without scanning an entire displayed image;

wherein the privacy mask in the first field of view is definable by pixel rows and said step of defining the privacy mask with a plurality of mask vertices includes identifying opposing ends of a plurality of the pixel rows with each of the identified ends defining one of the mask vertices.

13. The method of claim 12 wherein the privacy mask is defined by a user selecting a plurality of boundary locations to define the privacy mask in the first field of view and wherein the plurality of boundary locations selected by the user is less than the number of mask vertices.

14. The method of claim 12 wherein the opposing ends of each of the pixel rows in the privacy mask are identified and define one of the mask vertices.

15. The method of claim 12 wherein said step of adjusting the field of view of the camera between the first field of view and the second field of view includes adjusting a pan angle, a tilt angle and a focal length of the camera.

16. A method of obscuring a selected portion of video images, said method comprising:

acquiring images with a camera;

displaying the acquired images on a display screen;

defining a privacy mask with a plurality of mask vertices having coordinates (x1, y1), . . . (xn, yn), the privacy mask obscuring a selected portion of the displayed images;

adjusting the field of view of the camera from a first field of view to a second field of view;

determining transformed coordinates, (x1′

, y1′

), . . . (xn′

, yn′

), for each of the mask vertices to define a transformed privacy mask for the second field of view, the transformed coordinates being determined based upon changes in the field of view of the camera wherein the privacy mask and the transformed privacy mask obscure substantially common subject matter in both the first field of view and the second field of view respectively;

determining a polygon defined by said mask vertices of said transformed privacy mask; and

infilling said polygon to provide said transformed privacy mask in the second field of view without scanning an entire displayed image;

wherein the privacy mask in the first field of view is definable by a plurality of pixel blocks and said step of defining the privacy mask with a plurality of mask vertices includes identifying a location point for each of the pixel blocks, each of the location points defining one of the mask vertices and wherein at least one of the pixel blocks is a non-perimeter pixel block entirely circumscribed by other pixel blocks forming a portion of the privacy mask.

17. The method of claim 16 wherein the pixel blocks all have a common size.

18. The method of claim 16 wherein each of the pixel blocks is formed by a single pixel.

19. The method of claim 16 wherein the privacy mask is defined by a user selecting a plurality of boundary locations to define the privacy mask in the first field of view and wherein the plurality of boundary locations selected by the user is less than the number of mask vertices.

20. The method of claim 16 wherein the privacy mask defines a masked area completely encircling an unmasked area.

21. The method of claim 16 wherein said step of adjusting the field of view of the camera between the first field of view and the second field of view includes adjusting a pan angle, a tilt angle and a focal length of the camera.

22. A surveillance camera system comprising:

a camera having an adjustable field of view;

a display screen displaying images acquired by said camera;

a processing device operably coupled to said camera and said display screen, said processing device configured to allow a user to define a privacy mask obscuring a portion of the displayed images, said privacy mask defining a masked area completely encircling an unmasked area, said processing device further configured to transform said privacy mask in accordance with changes in the field of view of said camera, wherein, in a first field of view, said privacy mask is defined by a plurality of vertices having coordinates (x1, y1), . . . (xn, yn), and, in a second field of view differing from said first field of view, said processing device determines transformed coordinates, (x1′

, y1′

), . . . (xn′

, yn′

), for each of said vertices based upon changes in the field of view of said camera wherein said privacy mask and said transformed privacy mask obscure substantially common subject matter in the masked area, while displaying substantially common subject matter in the unmasked area surrounded by the masked area of the privacy mask, in both said first field of view and said second field of view.

23. The surveillance camera system of claim 22 wherein said privacy mask in said first field of view is definable by pixel rows and said processing device is configured to identify opposing ends of a plurality of said pixel rows, each of said identified ends defining one of said vertices of said privacy mask.

24. The surveillance camera system of claim 22 wherein said privacy mask in said first field of view is definable by a plurality of pixel blocks and said processing device is configured to identify at least one location point for each said pixel block, each of said location points defining one of said vertices of said privacy mask and wherein said privacy mask includes at least one non-perimeter pixel block entirely circumscribed by other pixel blocks forming a portion of said privacy mask.