Security cameras integrating 3D sensing for virtual security zone

1. A method of providing a virtual security zone comprising the steps of:

receiving pixel data corresponding to a monitored area; and

processing said pixel data arranged as video frames by

(i) performing computer vision operations to detect an object in said video frames, wherein said computer vision operations are performed by (a) applying a feature detection window 8 to each of a plurality of layers in each of said video frames and (b) sliding said feature detection window along each of said plurality of layers,

(ii) extracting characteristics about said object detected,

(iii) generating a three-dimensional (3D) map of said object utilizing said pixel data corresponding to said object,

(iv) determining whether said object is within a three-dimensional (3D) virtual security zone based on said 3D map 17 of said object, wherein said 3D virtual security zone is determined by a user during a setup procedure, and

(v) generating a trigger signal in response to all or a portion of said object being within said 3D virtual security zone.

2. The method according to claim 1 , further comprising:

communicating said trigger signal to at least one of (i) a security system and (ii) an intrusion alarm.

3. The method according to claim 1 , wherein performing said computer vision operations further comprises applying a convolution operation using matrix multiplication of said plurality of layers defined by said feature detection window.

4. The method according to claim 1 , wherein performing said computer vision operations further comprises (i) performing feature extraction based on weight values for each of said plurality of layers in said video frames and (ii) said weight values are determined based on an analysis of training data performed prior to said feature extraction.

5. The method according to claim 1 , wherein performing said computer vision operations further comprises analyzing at least one of (a) depth information and (b) disparity information to determine a position of said object relative to said 3D virtual security zone.

6. The method according to claim 5 , further comprising generating said depth information using a time-of-flight sensor.

7. The method according to claim 5 , further comprising generating said depth information using a structured light pattern.

8. The method according to claim 1 , further comprising:

generating a disparity map of said 3D virtual security zone utilizing said pixel data of said video frames; and

determining depth coordinates of said 3D map of said object utilizing said disparity map.

9. The method according to claim 1 , further comprising:

generating control signals to control a structured light projector and a camera, wherein said camera comprises one or more image sensors configured to generate said pixel data for a field of view of said camera and said structured light projector is configured to project a structured light pattern into said monitored area in response to one or more of said control signals; and

generating a disparity map of said 3D virtual security zone utilizing said structured light pattern contained in said pixel data of said video frames.

10. The method according to claim 9 , wherein said one or more image sensors comprise at least one of an infrared (IR) image sensor, a color (RGB) image sensor, and an RGB-IR image sensor.

11. The method according to claim 1 , further comprising:

receiving (i) a first portion of said pixel data for a first field of view of a first camera comprising a first image sensor and (ii) a second portion of said pixel data for a second field of view of a second camera comprising a second image sensor, wherein said first camera and said second camera are arranged as a stereo camera pair; and

generating a disparity map of said 3D virtual security zone utilizing said first portion of said pixel data and said second portion of said pixel data arranged as said video frames.

12. The method according to claim 11 , wherein said first image sensor and said second image sensor comprise one or more of an infrared (IR) image sensor, a color (RGB) image sensor, and an RGB-IR image sensor.

13. The method according to claim 1 , wherein said 3D virtual security zone is defined by:

prompting said user to enter coordinates of a plurality of vertices of said 3D virtual security zone via a user interface;

receiving said plurality of vertices of said 3D virtual security zone via said user interface; and

displaying a representation of said 3D virtual security zone overlaid on an image of the monitored area.

14. The method according to claim 1 , wherein said 3D virtual security zone is defined by:

prompting said user to enter one or more of coordinates and parameters defining said 3D virtual security zone via a user interface;

receiving coordinates of an anchor point of said 3D virtual security zone and a number of parameters defining dimensions of said 3D virtual security zone via said user interface; and

displaying a representation of said 3D virtual security zone overlaid on an image of the monitored area.

15. The method according to claim 14 , wherein the number of parameters defining dimensions of said 3D virtual security zone comprise one or more of a height parameter, a width parameter and a depth parameter.

16. The method according to claim 1 , wherein said 3D virtual security zone is defined by:

provide one or more default 3D virtual security zones; and

enabling said user to customize said one or more default 3D virtual security zones via a user interface.

17. The method according to claim 1 , wherein said 3D virtual security zone is defined by:

providing one or more dynamically adjusted 3D virtual security zones; and

enabling said user to customize said one or more dynamically adjusted 3D virtual security zones.

18. The method according to claim 1 , wherein said 3D virtual security zone is defined by:

enabling said user to define a plurality of dynamically selected 3D virtual security zones; and

switching between the plurality of dynamically selected 3D virtual security zones based on one or more of time of day, day of week, and presence of a predefined object.

19. The method according to claim 1 , further comprising determining whether said object is a person.

20. The method according to claim 19 , further comprising:

when said object is determined to be a person, further determining whether said person is authorized to enter said 3D virtual security zone.