Utilizing depth information to create 3D tripwires in video

1. A method of processing a digital video sequence, the method comprising:

detecting a foreground object in an image captured by a depth camera;

determining three-dimensional (3D) coordinates of the foreground object; and

comparing the 3D coordinates to a 3D video tripwire to determine if the foreground object has crossed the 3D video tripwire, wherein the 3D video tripwire comprises a user interface and wherein the user interface is further configured to receive two-dimensional (2D) coordinates of a first point in the scene selected by the user; and determine 3D coordinates of a first pixel corresponding to the first point using depth information corresponding to the scene.

2. The method of claim 1 , further comprising:

adding the 3D coordinates to a history of three-dimensional (3D) coordinates of the foreground object; and

wherein comparing the 3D coordinates further comprises comparing 3D coordinates in the history to the 3D video tripwire to determine if the foreground object has crossed the 3D video tripwire.

3. The method of claim 1 , further comprising signaling a crossing event when the foreground object is determined to have crossed the 3D video tripwire.

4. The method of claim 1 , wherein the comparing the 3D coordinates is performed periodically.

5. The method of claim 1 , wherein the 3D video tripwire is defined using a user interface configured to:

display images of a scene monitored by the depth camera on a display screen, wherein the images are captured by the depth camera; and

define the 3D video tripwire based on 3D coordinates of pixels corresponding to points selected in the scene by a user.

6. The method of claim 5 , wherein the depth information corresponding to the scene is comprised in one selected from a group consisting of a depth image and a depth background model.

7. The method of claim 5 , wherein the user interface is further configured to display an overlay on the displayed images, wherein the overlay visually indicates depths of pixels in the scene relative to a depth of the first pixel corresponding to the first point.

8. The method of claim 7 , wherein the overlay uses one of color shading or grayscale to indicate the depths of the pixels.

9. The method of claim 7 , wherein the user interface is further configured to

receive 2D coordinates of a second point in the scene selected by the user while viewing the overlaid displayed images; and

determine 3D coordinates of a second pixel corresponding to the second point using depth information corresponding to the scene,

wherein the 3D video tripwire is generated based on the 3D coordinates of the first pixel and the 3D coordinates of the second pixel.

10. A surveillance system comprising:

a three-dimensional (3D) imaging system configured to capture depth images of a scene; and

a video analytics component configured to

detect a foreground object in an image captured by the 3D imaging system;

determine 3D coordinates of the foreground object; and

compare the 3D coordinates to a 3D video tripwire to determine if the foreground object has crossed the 3D video tripwire, wherein the 3D video tripwire comprises a user interface and wherein the user interface is further configured to receive two-dimensional (2D) coordinates of a first point in the scene selected by the user; and determine 3D coordinates of a first pixel corresponding to the first point using depth information corresponding to the scene.