Method and apparatus for masking surveillance video images for privacy protection

• US 8,194,127 B2
• Filed: 11/07/2006
• Issued: 06/05/2012
• Est. Priority Date: 11/07/2005
• Status: Expired due to Fees

• Current Assignee: LG Innotek Company Limited (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: Kang, Kyun Ho, Seo, Sung Ha, Park, Byung Jin, Choi, Jong Tae
• Primary Examiner(s): Ustaris, Joseph
• Assistant Examiner(s): BAILEY, FREDERICK D
• Application Number:
  US11/593,480
• Publication Number:
  US 20070115356A1
• Time in Patent Office: 2,037 Days
• Field of Search: None
• US Class Current: 348/143
• CPC Class Codes: G06T 7/32 using correlation-based methods
• CPC Class Codes: G08B 13/19636 pertaining to the camera
• CPC Class Codes: G08B 13/19686 Interfaces masking personal details for privacy, e.g. blurring faces, vehicle license plates

Abstract

The present invention makes a privacy protection area set on a video frame always match a masking block for the privacy protection area, thereby preventing video images taken from the privacy protection area from being exposed. One embodiment of the invention sets a masking zone corresponding to a privacy protection area on a taken video frame, keeps examining if the set masking zone does not match the privacy protection area, and adjusts the position of the masking zone on the video frame if it is determined that the masking zone does not match the privacy protection area, thereby preventing video signals taken from the initially set privacy protection area from being outputted.

Claims

1. A method for masking a surveillance image taken with a camera, comprising:

(a) setting a masking zone corresponding to a protection area on a video frame being taken with the camera and obtaining initial video data from the set masking zone;

(b) after a predetermined time, determining whether the masking zone is deviated from the protection area by calculating a correlation between the initial video data and video data obtained from the masking zone, wherein the correlation is calculated using high-frequency components of luminance signals of the initial video data and the video data obtained from the masking zone; and

(c) adjusting a position of the masking zone on the video frame, if it is determined that the masking zone is deviated, by repeatedly searching a new masking zone on the video frame until the correlation between the initial video data and video data obtained from the new masking zone is less than a predetermined limit,

wherein the new masking zone is obtained by moving the previous masking zone by a predetermined distance,

wherein steps (b) and (c) are performed periodically, and

wherein the correlation is a value determined based on;

a sum of products of corresponding pixel values of two video data groups obtained from the masking zone at different times,

an average of pixel values of the two video data groups, or

a standard deviation of pixel values of the two video data groups.

2. The method of claim 1, wherein a shape of the masking zone is rectangular.

3. The method of claim 1,

wherein the step (b) determines that the masking zone is deviated from the protection area if the calculated correlation is less than the threshold value.

4. The method of claim 1, wherein the step (b) uses partial components of the video data obtained from the masking zone to calculate the correlation.

5. The method of claim 1, further comprising:

(d) re-adjusting the position of the masking zone on the video frame based on an amount of a horizontal and/or vertical movement of a view angle of the camera or based on a picture-taking magnification of the camera.

6. The method of claim 1, further comprising:

(d) outputting the video frame being taken with the camera after blocking a video signal corresponding to the set masking zone.

7. A method for masking a surveillance image taken with a camera, comprising:

(a) setting a masking zone corresponding to a protection area on a video frame being taken with the camera and obtaining initial video data from the set masking zone;

(b) after a predetermined time, determining whether the masking zone is deviated from the protection area by calculating a correlation between the initial video data and video data obtained from the masking zone, wherein the correlation is calculated using high-frequency components of luminance signals of the initial video data and the video data obtained from the masking zone; and

(c) adjusting a position of the masking zone on the video frame, if it is determined that the masking zone is deviated, by repeatedly searching a new masking zone on the video frame until the correlation between the initial video data and video data obtained from the new masking zone is less than a predetermined limit,

wherein the new masking zone is obtained by moving the previous masking zone by a predetermined distance,

wherein steps (b) and (c) are performed periodically, with the video data obtained from the masking zone being video data obtained from a predetermined reference zone of the masking zone, and

wherein the correlation is a value determined based on;

a sum of products of corresponding pixel values of two video data groups obtained from the masking zone at different times,

an average of pixel values of the two video data groups, or

a standard deviation of pixel values of the two video data groups.

8. The method of claim 7, wherein the step (b) determines that the masking zone is deviated from the protection area if the calculated correlation is less than the threshold value.

9. The method of claim 7, wherein the step (b) uses partial components of the video data obtained from the masking zone to calculate the correlation.

10. The method of claim 7, wherein a shape of the masking zone is rectangular.

11. The method of claim 7, further comprising:

(d) re-adjusting the position of the masking zone on the video frame based on an amount of a horizontal and/or vertical movement of a view angle of the camera or based on a picture-taking magnification of the camera.

12. The method of claim 7, further comprising:

(d) outputting the video frame being taken with the camera after blocking a video signal corresponding to the set masking zone.

13. An apparatus for masking a surveillance image taken with a camera, comprising:

an opto-electric processing unit configured to convert an input optical ray into electrical video frames;

a controller operatively connected to the opto-electric processing unit and configured to

set a masking zone corresponding to a protection area on a video frame,

obtain initial video data from the set masking zone,

after a predetermined time, determine whether the masking zone is deviated from the protection area by calculating a correlation between the initial video data and video data obtained from the masking zone, wherein the correlation is calculated using high-frequency components of luminance signals of the initial video data and the video data obtained from the masking zone, and

adjust a position of the masking zone on the video frame, if it is determined that the masking zone is deviated from the protection area, by repeatedly searching a new masking zone on the video frame until the correlation between the initial video data and video data obtained from the new masking zone is less than a predetermined limit,

wherein the new masking zone is obtained by moving the previous masking zone by a predetermined distance; and

a mask blocking unit configured to block the video signal corresponding to the set masking zone on the video frame,

wherein the controller is configured to

periodically determine whether the masking zone is deviated from the protection area by periodically calculating the correlation between the initial video data and video data obtained from the masking zone, and

periodically adjust the position of the masking zone on the video frame if it is determined that the masking zone is deviated from the protection area, and wherein the correlation is a value determined based on;

a sum of products of corresponding pixel values of two video data groups obtained from the masking zone at different times,

an average of pixel values of the two video data groups, or

a standard deviation of pixel values of the two video data groups.

14. The apparatus of claim 13, wherein a shape of the masking zone is rectangular.

15. The apparatus of claim 13, wherein the controller is configured to determine that the masking zone is deviated from the protection area if the calculated correlation is less than the threshold value.

16. The apparatus of claim 13, wherein the controller is configured to use partial components of the video data obtained from the masking zone to calculate the correlation.

17. The apparatus of claim 13, further comprising:

a panning/tilting unit configured to adjust an optical axis of the opto-electric processing unit horizontally and/or vertically,

wherein the controller is configured to re-adjust the position of the masking zone on the video frame based on an amount of the horizontal and/or vertical adjustment by the panning/tilting unit.

18. The apparatus of claim 13, wherein the controller is configured to re-adjust the position of the masking zone on the video frame based on a picture-taking magnification of the opto-electric processing unit.

19. An apparatus for masking a surveillance image taken with a camera, comprising:

an opto-electric processing unit configured to convert an input optical ray into electrical video frames;

a controller operatively connected to the opto-electric processing unit and configured to

set a masking zone corresponding to a protection area on a video frame,

obtain initial video data from the set masking zone,

after a predetermined time, determine whether the masking zone is deviated from the protection area by calculating a correlation between the initial video data and video data obtained from the masking zone, wherein the correlation is calculated using high-frequency components of luminance signals of the initial video data and the video data obtained from the masking zone, and

adjust a position of the masking zone on the video frame, if it is determined that the masking zone is deviated from the protection area, by repeatedly searching a new masking zone on the video frame until the correlation between the initial video data and video data obtained from the new masking zone is less than a predetermined limit,

wherein the new masking zone is obtained by moving the previous masking zone by a predetermined distance; and

a mask blocking unit configured to block the video signal corresponding to the set masking zone on the video frame,

wherein the controller is configured to

periodically determine whether the masking zone is deviated from the protection area by periodically calculating the correlation between the initial video data and video data obtained from a predetermined reference zone of the masking zone, and

periodically adjust the position of the masking zone on the video frame if it is determined that the masking zone is deviated from the protection area, and wherein the correlation is a value determined based on;

a sum of products of corresponding pixel values of two video data groups obtained from the masking zone at different times,

an average of pixel values of the two video data groups, or

a standard deviation of pixel values of the two video data groups.

20. The apparatus of claim 19, wherein a shape of the reference zone is rectangular.

21. The apparatus of claim 19, wherein the controller is configured to determine that the masking zone is deviated from the protection area if the calculated correlation is less than the threshold value.

22. The apparatus of claim 19, wherein the controller is configured to use partial components of the video data obtained from the masking zone to calculate the correlation.

23. The apparatus of claim 19, further comprising:

a panning/tilting unit configured to adjust an optical axis of the opto-electric processing unit horizontally and/or vertically,

wherein the controller is configured to re-adjust the position of the masking zone on the video frame based on an amount of the horizontal and/or vertical adjustment by the panning/tilting unit.

24. The apparatus of claim 19, wherein the controller is configured to re-adjust the position of the masking zone on the video frame based on a picture-taking magnification of the opto-electric processing unit.