GRADIENT PRIVACY MASKS

• US 20150145992A1
• Filed: 11/20/2014
• Published: 05/28/2015
• Est. Priority Date: 11/22/2013
• Status: Active Grant

• Current Assignee: Axis AB (Canon Inc.)
• Original Assignee: Axis AB (Canon Inc.)
• Inventors: Trff, Gustav
• Granted Patent: US 9,875,530 B2
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

An apparatus and a method implemented in a computer system for obscuring a first region of an image composed by a plurality of pixels. The method comprising obtaining a mask, the mask defining an obscurity level for each pixel in the first region of the image, and obscuring pixels in the first region of the image based on the mask'"'"'s obscurity level for each pixel.

Claims

1. A method implemented in a computer system for producing a masked image having an obscured first region, the method comprising:

capturing, by a camera, an image composed by a plurality of pixels;

analyzing the content of the image;

creating a privacy mask by applying one or more rules to the results of the analysis, the rules defining a gradual transition around the edges of a first region of the image to create a smooth transition between masked and unmasked regions of the image and thereby obtaining the privacy mask defining an obscurity level for each pixel in the first region of the image on a pixel-by-pixel basis; and

applying the privacy mask to the image, thereby producing the masked image having obscured pixels in the first region of the masked image based on the privacy mask'"'"'s obscurity level for each pixel.

2. The method of claim 1, further comprising:

creating the mask by applying one or more rules to the results of the analysis, the rules defining obscurity levels with respect to image content.

3. The method of claim 1, wherein obscuring pixels includes blurring pixels to a degree that is based on the mask'"'"'s obscurity level for each pixel.

4. The method of claim 1, wherein pixels that represent objects in the image that are located close to the camera capturing the image have a higher obscurity level than pixels that represent objects in the image that are located further away from the camera capturing the image.

5. The method of claim 1, wherein the mask covers the entire image and wherein the obscurity levels are in the range from 0% to 100%.

6. The method of claim 1, wherein the first region represents an object that is identified using an object-tracking algorithm applied to successive captured images.

7. The method of claim 1, wherein the first region represents an object that is identified by determining a temperature differential between the object and the object'"'"'s surroundings.

8. The method of claim 1, wherein the first region represents a background of the image and a second region of the image is emphasized as a result of obscuring the background of the image.

9. A computer-readable recording medium having recorded thereon a program for implementing the method according to claim 1 when executed on a computer.

10. A system for producing a masked image having an obscured first region, the system comprising:

a processor configured to receive at least an image composed by a plurality of pixels from a camera;

the processor configured to analyze the content of the image;

the processor configured to create a privacy mask by applying one or more rules to the results of the analysis, the rules defining a gradual transition around the edges of a first region of the image to create a smooth transition between masked and unmasked regions of the image and obtaining the privacy mask defining an obscurity level for each pixel in the first region of the image on a pixel-by-pixel basis; and

the processor configured to apply the privacy mask to the image, producing the masked image having obscured pixels in the first region of the masked image based on the privacy mask'"'"'s obscurity level for each pixel.

11. The system of claim 10, wherein the processor is further configured to create the mask by applying one or more rules to the results of the analysis, the rules defining obscurity levels with respect to image content.

12. The system of claim 10, wherein obscuring pixels includes blurring pixels to a degree that is based on the mask'"'"'s obscurity level for each pixel.

13. The system of claim 10, wherein pixels that represent objects in the image that are located close to the camera capturing the image have a higher obscurity level than pixels that represent objects in the image that are located further away from the camera capturing the image.

14. The system of claim 10, wherein the mask covers the entire image and wherein the obscurity levels are in the range from 0% to 100%.

15. The system of claim 10, wherein the first region represents an object that is identified using an object-tracking algorithm applied to successive captured images.

16. The system of claim 10, wherein the first region represents an object that is identified by determining a temperature differential between the object and the object'"'"'s surroundings.

17. The system of claim 10, wherein the first region represents a background of the image and a second region of the image is emphasized as a result of obscuring the background of the image.