Tracking Moving Objects Using a Camera Network

• US 20120169882A1
• Filed: 12/30/2010
• Published: 07/05/2012
• Est. Priority Date: 12/30/2010
• Status: Active Grant

• Current Assignee: Pelco (Schneider Electric SE)
• Original Assignee: Pelco (Schneider Electric SE)
• Inventors: Millar, Greg, Aghdasi, Farzin, Wang, Lei
• Granted Patent: US 9,615,064 B2
• Time in Patent Office: Days
• US Class Current: 348/159
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

Techniques are described for tracking moving objects using a plurality of security cameras. Multiple cameras may capture frames that contain images of a moving object. These images may be processed by the cameras to create metadata associated with the images of the objects. Frames of each camera'"'"'s video feed and metadata may be transmitted to a host computer system. The host computer system may use the metadata received from each camera to determine whether the moving objects imaged by the cameras represent the same moving object. Based upon properties of the images of the objects described in the metadata received from each camera, the host computer system may select a preferable video feed containing images of the moving object for display to a user.

Claims

1. A method for tracking an object with a plurality of cameras, the method comprising:

capturing, using a first camera, a first set of frames, wherein;

the plurality of cameras comprises the first camera;

the first set of frames comprises a first set of images of the object; and

the first set of frames is captured from a first point of view;

capturing, using a second camera, a second set of frames, wherein;

the plurality of cameras comprises the second camera;

the second set of frames comprises a second set of images of the object; and

the second set of frames is captured from a second point of view;

determining, using the first camera, a presence of the object in the first set of frames;

linking, by the first camera, metadata to the presence of the object, wherein the metadata indicates at least one characteristic of the first set of images of the object;

transmitting the metadata from the first camera to a computing system; and

identifying, by the computing system, based at least in part on the metadata received from the first camera, that the second set of images captured by the second camera represents the same object as the object in the first set of images in the first set of frames.

2. The method of claim 1, further comprising selecting, by the computing system, according to a set of predefined rules, the first set of frames or the second set of frames for display to a user.

3. The method of claim 2, wherein selecting, according to the set of predefined rules, the first set of frames or the second set of frames for display to the user occurs substantially in real time, wherein real time refers to frames being displayed that represent a current location of the object.

4. The method of claim 2, wherein selecting, according to the set of predefined rules, the first set of frames or the second set of frames for display to the user occurs at least an hour after the first set of frames and the second set of frames were captured.

5. The method of claim 2, wherein the set of predefined rules comprises a rule for determining whether the first set of images of the object in the first set of frames is larger than the second set of images of the object in the second set of frames.

6. The method of claim 1, further comprising receiving, by the computing system, a selection from a user, wherein the selection indicates to track the object using frames captured by the plurality of cameras.

7. The method of claim 1, wherein the at least one characteristic comprises two-dimensional coordinates of a location of the object in a two-dimensional coordinate system associated with the first camera.

8. The method of claim 7, further comprising converting, by the computing system, the two-dimensional coordinates of the location to three-dimensional coordinates.

9. The method of claim 1, wherein a first field of view associated with the first point of view and a second field of view associated with the second point of view at least partially overlap.

10. The method of claim 1, wherein a first field of view associated with the first point of view and a second field of view associated with the second point of view do not overlap.

11. The method of claim 1, further comprising:

receiving, by the computing system, a first set of coordinates that corresponds to a first location in a first field of view of the first camera;

receiving, by the computing system, a second set of coordinates that corresponds to the location in a second field of view of the second camera; and

mapping, by the computing system, using the first set of coordinates and the second set of coordinates, a first two-dimensional coordinate system linked with the first camera and a second two-dimensional coordinate system linked with the second camera to a three-dimensional coordinate system.

12. A system for identifying an object in frames captured by a plurality of cameras, the system comprising:

the plurality of cameras, wherein;

the plurality of cameras comprises a first camera and a second camera;

the first camera is configured to capture a first set of frames from a first point of view with a first field of view;

the first camera is configured to identify a first set of images of a first object in the first set of frames;

the first camera is configured to determine a first set of metadata associated with the first object in the first set of frames;

the second camera is configured to capture a second set of frames from a second point of view with a second field of view;

the second camera is configured to identify a second set of images of a second object in the second set of frames; and

the second camera is configured to determine a second set of metadata associated with the second object in the second set of frames; and

a host computer system configured to;

receive the first set of metadata from the first camera;

receive the second set of metadata from the second camera;

receive the first set of frames from the first camera;

receive the second set of frames from the second camera; and

determine, based at least in part on the first set of metadata received from the first camera and the second set of metadata received from the second camera, that the first set of images of the first object and the second set of images of the second object represent the same object.

13. The system of claim 12, wherein the host computer system is further configured to:

select, according to a set of predefined rules, the first set of frames for display to a user; and

after a period of time of the first set of frames being selected, select, according to the set of predefined rules, the second set of frames for display to the user.

14. The system of claim 12, wherein the host computer system is further configured to receive a selection from a user, wherein the selection indicates to track the first object.

15. The system of claim 12, wherein:

the first set of metadata comprises two-dimensional coordinates of a location of the object in a first two-dimensional coordinate system associated with the first camera; and

the second set of metadata comprises two-dimensional coordinates of the location in a second two-dimensional coordinate system associated with the second camera.

16. The system of claim 12, wherein the first camera is further configured to segment a foreground of the first set of frames from a background of the first set of frames, wherein:

the background comprises a first set of objects that substantially are not moving;

the foreground comprises a second set of objects that are moving;

the second set of objects comprises the first object; and

the foreground is configured to be segmented from the background using a Gaussian mixture model.

17. The system of claim 12, further comprising:

a slave camera, wherein;

the slave camera is configured to capture a third set of frames; and

the slave camera is configured to transmit the third set of frames to the host computer system;

wherein the host computer system is further configured to determine metadata associated with a third object in the third set of frames.

20. The apparatus of claim 16, further comprising:

a sixth means for receiving a selection from a user, wherein the selection indicates to track the object.

21. The apparatus of claim 16, wherein the metadata comprises two-dimensional coordinates of a location of the object in a two-dimensional coordinate system associated with the first means.

18. An apparatus for tracking an object, the apparatus comprising:

a first means for capturing a first set of frames, wherein;

the first set of frames comprises a first set of images of an object; and

the first set of frames is captured from a first point of view with a first field of view;

a second means for capturing a second set of frames, wherein;

the second set of frames comprises a second set of images of the object; and

the second set of frames is captured from a second point of view with a second field of view;

a third means for identifying a presence of the object in the first set of frames;

a fourth means for determining metadata associated with the first set of images of the object, wherein the metadata indicates at least one characteristic of the first set of images of the object; and

a fifth means for identifying, based at least in part on the metadata, that the second set of images comprises the same object as the first set of images.

19. The apparatus for tracking the object of claim 18, wherein the metadata comprises:

a height measurement of the first set of images of the object; and

a width measurement of the first set of images of the object.

22. A method for calibrating a PTZ (pan, tilt, and zoom) camera using a fixed camera, the method comprising:

adjusting a pan and tilt of the PTZ camera such that a field of view of the PTZ camera overlaps a field of view of a fixed camera;

receiving, by a computing system, a first set of coordinates associated with a first location in the field of view of the fixed camera;

receiving, by the computing system, a second set of coordinates associated with the first location in the field of view of the PTZ camera; and

calculating, by the computing system, a set of transform parameters, using the first set of coordinates associated with the first location in the field of view of the fixed camera and the second set of coordinates associated with the first location in the field of view of the PTZ camera.

23. The method of claim 22 for calibrating the PTZ camera using the fixed camera, further comprising:

receiving, by the computing system, at least four sets of coordinates associated with four locations in the field of view of the fixed camera;

adjusting the pan, tilt, and zoom of the PTZ camera to center the field of view of the PTZ camera on each of the four locations; and

calculating, by the computing system, a set of transform parameters using the pan and tilt positions of the PTZ camera when the field of view is centered on each of the four locations.

24. The method of claim 23 for calibrating the PTZ camera using the fixed camera, further comprising:

receiving, by the computer system, measurements of a first distance and a second distance within a third field of view of the PTZ camera, wherein;

the first distance and the second distance are the same distance; and

the first distance is located closer to the PTZ camera than the second distance; and

calculating, by the computer system, zoom parameters using the measurements of the first distance and the second distance within the PTZ camera'"'"'s third field of view.

25. The method of claim 24 for calibrating the PTZ camera using the fixed camera, wherein, the third field of view and the second field of view are the same.