Selective viewing of a scene

• US 9,172,919 B2
• Filed: 11/12/2014
• Issued: 10/27/2015
• Est. Priority Date: 06/10/2008
• Status: Active Grant

• Current Assignee: Irisity AB
• Original Assignee: Mindmancer AB
• Inventors: Strandevall, Jan, Berlic, Johnny
• Primary Examiner(s): Carter, Aaron W
• Application Number:
  US14/539,502
• Publication Number:
  US 20150070490A1
• Time in Patent Office: 349 Days
• Field of Search: None
• US Class Current: 1/1
• 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 7/183 for receiving images from a single remote source

Abstract

Among other disclosed subject matter, a computer-implemented method for performing selective viewing of a scene includes acquiring an image of a real scene using a camera. The method includes identifying, in the acquired image, a first object in the real scene located on a first side of a virtual plane defined for the real scene and a second object located on a second side of the virtual plane. The method includes modifying the acquired image by removing image content corresponding to the identified first object, wherein image content corresponding to the identified second object is not removed based on the second object being located on the second side. The method includes displaying the modified acquired image for a person to view the real scene.

Claims

1. A computer-implemented method for performing selective viewing of a scene, the method comprising:

acquiring an image of a real scene using a camera;

identifying at least a first feature in the acquired image based on the first feature moving in the real scene, wherein the real scene further includes a second feature that is not moving in the real scene;

modifying the acquired image by removing the first feature and not removing the second feature; and

displaying the modified acquired image for a person to view the real scene without the first feature,

wherein identifying the at least first feature in the acquired image comprises;

defining a virtual plane in the image that separates image features based on which side of the virtual plane the image features are located; and

determining that the first feature is located on a particular side of the virtual plane,

wherein the virtual plane is defined at a specific location in a passageway in the real scene such that any feature passing through the virtual plane in the passageway is only visible in the modified acquired image while on one of the first and second sides.

2. The computer-implemented method of claim 1, further comprising identifying that a size of the first feature or a distance of the first feature from the camera corresponds to a size or distance, respectively, of features that have been specified for removal,

wherein the first feature is removed from the acquired image in response to identifying that the size of the first feature or the distance of the first feature from the camera corresponds to the size or distance, respectively, of features that have been specified for removal.

3. The computer-implemented method of claim 2, wherein the virtual plane comprises a polygonal plane.

4. The computer-implemented method of claim 2, wherein the virtual plane spans an entirety of the acquired image.

5. The computer-implemented method of claim 1, wherein the first feature comprises a face of a person.

6. The computer-implemented method of claim 1, wherein the camera comprises a surveillance camera.

7. The computer-implemented method of claim 1, wherein removing the first feature from the image comprises replacing the first feature with background features that simulate how the real scene would appear had the image been captured by the camera without the first feature being present in the real scene.

8. A non-transitory computer-readable media having instructions stored thereon that, when executed by a processor, cause performance of operations comprising:

acquiring an image of a real scene using a camera;

identifying at least a first feature in the acquired image based on the first feature moving in the real scene, wherein the real scene further includes a second feature that is not moving in the real scene;

modifying the acquired image by removing the first feature and not removing the second feature; and

displaying the modified acquired image for a person to view the real scene without the first feature,

wherein identifying the at least first feature in the acquired image comprises;

defining a virtual plane in the image that separates image features based on which side of the virtual plane the image features are located; and

determining that the first feature is located on a particular side of the virtual plane,

wherein the virtual plane is defined at a specific location in a passageway in the real scene such that any feature passing through the virtual plane in the passageway is only visible in the modified acquired image while on one of the first and second sides.

9. The non-transitory computer-readable storage media of claim 8, wherein:

the operations further comprise identifying that a size of the first feature or a distance of the first feature from the camera corresponds to a size or distance, respectively, of features that have been specified for removal, and

the first feature is removed from the acquired image in response to identifying that the size of the first feature or the distance of the first feature from the camera corresponds to the size or distance, respectively, of features that have been specified for removal.

10. The non-transitory computer-readable storage media of claim 8, wherein the virtual plane comprises a polygonal plane.

11. The non-transitory computer-readable storage media of claim 8, wherein the virtual plane spans an entirety of the acquired image.

12. The non-transitory computer-readable storage media of claim 8, wherein the virtual plane has a free-form shape and includes one or more holes that permit portions of image features that are located behind the one or more holes to not be removed from the image.

13. The non-transitory computer-readable storage media of claim 8, wherein the first feature comprises a face of a person.

14. The non-transitory computer-readable storage media of claim 8, wherein the camera comprises a surveillance camera.

15. The non-transitory computer-readable storage media of claim 8, wherein removing the first feature from the image comprises replacing the first feature with background features that simulate how the real scene would appear had the image been captured by the camera without the first feature being present in the real scene.

16. A computer-implemented system for selective viewing of a scene, the system comprising:

a camera; and

one or more computers configured to cause performance of operations comprising;

acquiring an image of a real scene using the camera;

identifying at least a first feature in the acquired image based on the first feature moving in the real scene, wherein the real scene further includes a second feature that is not moving in the real scene;

modifying the acquired image by removing the first feature and not removing the second feature; and

displaying the modified acquired image for a person to view the real scene without the first feature,

wherein identifying the at least first feature in the acquired image comprises;

defining a virtual plane in the image that separates image features based on which side of the virtual plane the image features are located; and

determining that the first feature is located on a particular side of the virtual plane,

wherein the virtual plane is defined at a specific location in a passageway in the real scene such that any feature passing through the virtual plane in the passageway is only visible in the modified acquired image while on one of the first and second sides.