System and method for stabilized single moving camera object tracking

• US 20060078162A1
• Filed: 10/11/2005
• Published: 04/13/2006
• Est. Priority Date: 10/08/2004
• Status: Abandoned Application

• Current Assignee: Dynapel Systems, Inc.
• Original Assignee: Dynapel Systems, Inc.
• Inventors: Wonneberger, Siegfried
• Application Number:
  US11/246,261
• Publication Number:
  US 20060078162A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: H04N 23/68 for stable pick-up of the scene, e.g. compensating for camera body vibrations
• CPC Class Codes: H04N 23/6811 based on the image signal
• CPC Class Codes: H04N 23/6812 based on additional sensors, e.g. acceleration sensors
• CPC Class Codes: H04N 23/6845 by combination of a plurality of images sequentially taken

Abstract

A system including a moveable camera adapted to obtain a sequence of video images of an object, a determiner adapted to identify an object border in a current video image of said sequence of video images, said determiner being adapted to determine an object area and a background area based on said object border; an estimator adapted to estimate a camera motion estimate of said moveable camera and to estimate an object motion estimate of the object, said estimator being adapted to generate a camera motion model from said camera motion estimate and being adapted to generate an object motion model from at least one of said object motion estimate and said camera motion model; a stabilizer adapted to adjust at least one video image within said sequence of video images based on said camera motion model; and a controller adapted to control said moveable camera to track the object based on said object motion model and said camera motion model.

Claims

1. A system comprising:

a moveable camera adapted to obtain a sequence of video images of an object;

a determiner adapted to identify an object border in a current video image of said sequence of video images, said determiner being adapted to determine an object area and a background area based on said object border;

an estimator adapted to estimate a camera motion estimate of said moveable camera based on said background area and to estimate an object motion estimate of the object based on said object area, said estimator being adapted to generate a camera motion model from said camera motion estimate and being adapted to generate an object motion model from at least one of said object motion estimate and said camera motion model;

a stabilizer adapted to adjust at least one video image within said sequence of video images based on said camera motion model; and

a controller adapted to control said moveable camera to track the object based on said object motion model and said camera motion model.

2. The system of claim 1, further comprising:

an output device adapted to receive said adjusted video image.

3. The system of claim 1, wherein said stabilizer warps said at least one video image during said adjustment of said at least one video image.

4. The system of claim 1, wherein said stabilizer is adapted to stabilize said sequence of video images produced by said moveable camera and simultaneously said controller is adapted to control said moveable camera to track the object.

5. The system of claim 1, wherein said controller is adapted to control said movable camera to maintain the object within the outer border of each video image while the object is within the range of the camera.

6. The system of claim 1, wherein said moveable camera is adapted to perform at least one of pan, tilt, and/or zoom.

7. The system of claim 1, wherein said stabilizer is adapted to generate a correction model from said camera motion model.

8. The system of claim 7, wherein said stabilizer is adapted to filter said camera motion model and to generate said correction model based on a comparison of said camera motion model and said filtered camera motion model.

9. The system of claim 8, wherein said stabilizer adjusts at least one of said sequence of video images using said correction model.

10. The system of claim 1, wherein said determiner is adapted to adjust said object border in a next video image based on said object motion model.

11. A system comprising:

a moveable camera adapted to obtain a sequence of video images,

an estimator adapted to generate a camera motion estimate of motion of said moveable camera and to generate a camera motion model from said camera motion estimate;

a controller adapted to receive an initial direction of an optical axis, said controller controlling said moveable camera to maintain the optical axis in the initial direction based on the initial direction and said camera motion model; and

a stabilizer adapted to adjust said sequence of video images based on said camera motion model to stabilize said sequence of video images.

12. The system of claim 11, wherein said stabilizer is adapted to stabilize said sequence of video images simultaneously to said controller being adapted to control said moveable camera to maintain the optical axis of said moveable camera in the initial direction.

13. The system of claim 11, wherein said controller is adapted to control said moveable camera to at least one of pan, tilt, and/or zoom.

14. The system of claim 11, wherein said stabilizer is adapted to generate a correction model based on said camera motion model.

15. The system of claim 14, wherein said stabilizer is adapted to adjust at least one of said sequence of video images using said correction model.

16. A method comprising:

obtaining, at a moveable camera, a sequence of video images of a scene having an object;

identifying an object border within a current video image that substantially surrounds said object;

determining a background area and an object area of said current video image in said sequence of video images based on said object border;

determining optical flow data of said background area and of said object area;

calculating a camera motion model based on said optical flow data of said background area;

calculating an object motion model based on said optical flow data of said object area;

adjusting said object border based on said object motion model;

calculating a correction model based on said camera motion model; and

adjusting said current video image based on said correction model.

17. The method of claim 16, wherein said adjusting said object border further comprises warping the object border based on said object model.

18. The method of claim 16, wherein adjusting said current video image comprises warping said current video image based on said correction model.

19. The method of claim 16, further comprising:

controlling said moveable camera to track said object based on said object motion model and on said camera motion model.

20. The method of claim 16, further comprising:

outputting said adjusted current video image to an output device.