Method, Apparatus and Computer Program Product for Providing Adaptive Gesture Analysis

• US 20100111358A1
• Filed: 10/30/2008
• Published: 05/06/2010
• Est. Priority Date: 10/30/2008
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Wang, Kongqiao, Chai, Xiujuan
• Granted Patent: US 8,325,978 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

A method for providing adaptive gesture analysis may include dividing a distance range into a plurality of depth ranges, generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame, determining motion variation between the two image frames for each corresponding depth range, and determining depth of a target based at least in part on the motion variation. An apparatus and computer program product corresponding to the method are also provided.

Claims

1. A method comprising:

dividing a distance range into a plurality of depth ranges;

generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame;

determining motion variation between the two image frames for each corresponding depth range; and

determining depth of a target based at least in part on the motion variation.

2. The method of claim 1, wherein dividing the distance range comprises selecting distance intervals that are wider at near and far distances than distance intervals between the near and far distances.

3. The method of claim 1, wherein generating the plurality of intensity images comprises generating the plurality of intensity images for adjacent frames.

4. The method of claim 1, wherein generating the plurality of intensity images comprises, for each corresponding depth range for a particular frame, setting data corresponding to objects not at a current depth range to a predefined value and retaining data corresponding to the current depth range.

5. The method of claim 4, wherein determining motion variation comprises comparing object data in a current frame to object data in a previous frame to determine a change in intensity from the previous frame to the current frame and setting data not indicative of the change in intensity to the predefined value.

6. The method of claim 1, wherein determining depth of the target comprises determining target depth based on an integration of the motion variation with target location cue information.

7. The method of claim 1, further comprising tracking motion of the target based on the determining of the depth of the target.

8. The method of claim 7, further comprising recognizing gesture features of the target to enable initiation of a user interface command based on a recognized gesture.

9. An apparatus comprising a processor configured to:

divide a distance range into a plurality of depth ranges;

generate a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame;

determine motion variation between the two image frames for each corresponding depth range; and

determine depth of a target based at least in part on the motion variation.

10. The apparatus of claim 9, wherein the processor is configured to divide the distance range by selecting distance intervals that are wider at near and far distances than distance intervals between the near and far distances.

11. The apparatus of claim 9, wherein the processor is configured to generate the plurality of intensity images by generating the plurality of intensity images for adjacent frames.

12. The apparatus of claim 9, wherein the processor is configured to generate the plurality of intensity images by, for each corresponding depth range for a particular frame, setting data corresponding to objects not at a current depth range to a predefined value and retaining data corresponding to the current depth range.

13. The apparatus of claim 12, wherein the processor is configured to determine motion variation by comparing object data in a current frame to object data in a previous frame to determine a change in intensity from the previous frame to the current frame and setting data not indicative of the change in intensity to the predefined value.

14. The apparatus of claim 9, wherein the processor is configured to determine depth of the target by determining target depth based on an integration of the motion variation with target location cue information.

15. The apparatus of claim 9, wherein the processor is further configured to track motion of the target based on the determining of the depth of the target.

16. The apparatus of claim 15, wherein the processor is configured to recognize gesture features of the target to enable initiation of a user interface command based on a recognized gesture.

17. A computer program product comprising at least one computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising:

first program code instructions for dividing a distance range into a plurality of depth ranges;

second program code instructions for generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame;

third program code instructions for determining motion variation between the two image frames for each corresponding depth range; and

fourth program code instructions for determining depth of a target based at least in part on the motion variation.

18. The method of claim 17, wherein the first program code instructions include instructions for selecting distance intervals that are wider at near and far distances than distance intervals between the near and far distances.

19. The computer program product of claim 17, wherein the second program code instructions include instructions for generating the plurality of intensity images for adjacent frames.

20. The computer program product of claim 17, wherein the second program code instructions include instructions for setting data corresponding to objects not at a current depth range to a predefined value and retaining data corresponding to the current depth range, for each corresponding depth range for a particular frame.

21. The computer program product of claim 20, wherein the third program code instructions include instructions for comparing object data in a current frame to object data in a previous frame to determine a change in intensity from the previous frame to the current frame and setting data not indicative of the change in intensity to the predefined value.

22. The computer program product of claim 17, wherein the fourth program code instructions include instructions for determining target depth based on an integration of the motion variation with target location cue information.

23. The computer program product of claim 17, further comprising fifth program code instructions for tracking motion of the target based on the determining of the depth of the target.

24. The computer program product of claim 23, further comprising sixth program code instructions for recognizing gesture features of the target to enable initiation of a user interface command based on a recognized gesture.

25. An apparatus comprising:

means for dividing a distance range into a plurality of depth ranges;

means for generating a plurality of intensity images for at least two image frames, each of the intensity images providing image data indicative of a presence of objects at a corresponding depth range for a respective image frame;

means for determining motion variation between the two image frames for each corresponding depth range; and

means for determining depth of a target based at least in part on the motion variation.

26. The apparatus of claim 25, wherein means for generating the plurality of intensity images comprises means for setting data corresponding to objects not at a current depth range to a predefined value and retaining data corresponding to the current depth range, for each corresponding depth range for a particular frame.