SYSTEM AND METHOD FOR ADAPTIVELY DEFINING A REGION OF INTEREST FOR MOTION ANALYSIS IN DIGITAL VIDEO

• US 20100202663A1
• Filed: 02/11/2009
• Published: 08/12/2010
• Est. Priority Date: 02/11/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Yeong-Taeg, Xu, Ning
• Granted Patent: US 8,553,931 B2
• Time in Patent Office: Days
• US Class Current: 382/107
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

A system and method for adaptively defining a region of interest for motion analysis in digital video is disclosed. In one embodiment, a method of detecting a gesture is disclosed which comprises receiving a video sequence comprising a plurality of frames, determining a region of interest which excludes a portion of the frame, and detecting the gesture within the region of interest.

Claims

1. A method of detecting a gesture, the method comprising:

receiving a video sequence that includes a gesture, the video sequence comprising a plurality of frames;

determining a region of interest relative to the gesture for at least one of the frames, wherein the region of interest excludes a portion of the frame; and

detecting the gesture within the region of interest of the video sequence.

2. The method of claim 1, wherein detecting the gesture further comprises:

defining a trajectory of an object captured in the region of interest; and

determining if the trajectory of the object defines a recognized gesture.

3. The method of claim 2, wherein the trajectory comprises a sequence of ordered points.

4. The method of claim 2, wherein defining the trajectory further comprises:

analyzing the plurality of frames to determine, for each of the plurality of frames, the portion of the region of interest which shows the object; and

defining a center location for each of the plurality of frames based in part on the portion of the region of interest which shows the object.

5. The method of claim 4, wherein defining a center location for each of the plurality of frames comprises defining a motion center location for the object.

6. The method of claim 1, wherein the detected gesture is a waving motion.

7. The method of claim 1, wherein the detected gesture is a circling motion.

8. The method of claim 1, wherein the region of interest comprises a rectangular area.

9. The method of claim 1, wherein the region of interest comprises a circular area.

10. The method of claim 1, wherein determining a region of interest is based in part on a detected motion.

11. The method of claim 1, wherein determining a region of interest is based in part on a previously detected gesture.

12. The method of claim 1, wherein the spatial component of the region of interest changes between successive frames.

13. The method of claim 1, wherein the spatial component of the region of interest expands between successive frames.

14. The method of claim 1, further comprising changing a parameter of a device in response to detecting the gesture.

15. The method of claim 14, wherein the parameter of the device is a channel, a station, a volume, a track, or a power.

16. A device comprising:

a video capture device configured to capture a video sequence that includes a gesture, the video sequence comprising a plurality of frames;

a region of interest module configured to determine a region of interest relative to the gesture, wherein the region of interest excludes a portion of each of a subset of the frames; and

a gesture detection module configured to detect the gesture within the region of interest of the video sequence.

17. The device of claim 16, wherein the video capture device comprises a camera.

18. The device of claim 17, wherein the camera is sensitive to infrared light.

19. The device of claim 16, wherein the device comprises a television, a DVD player, a radio, a set-top box, a music player, or a video player.

20. A device comprising:

means for receiving a video sequence that includes a gesture, the video sequence comprising a plurality of frames;

means for determining a region of interest relative to the gesture, wherein the region of interest excludes a portion of each of a subset of the frames; and

means for detecting the gesture within the region of interest of the video sequence.

21. A programmable storage device comprising code which, when executed, causes a processor to perform a method of detecting a gesture, the method comprising:

receiving a video sequence that includes a gesture, the video sequence comprising a plurality of frames;

determining a region of interest relative to the gesture, wherein the region of interest excludes a portion of each of a subset of the frames; and

detecting the gesture within the region of interest of the video sequence.