Enhanced detection of circular engagement gesture

• US 8,146,020 B2
• Filed: 07/24/2009
• Issued: 03/27/2012
• Est. Priority Date: 07/24/2008
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Clarkson, Ian
• Primary Examiner(s): Lo, Weilun
• Assistant Examiner(s): Hassan, Rashedul
• Application Number:
  US12/508,637
• Publication Number:
  US 20100050134A1
• Time in Patent Office: 977 Days
• Field of Search: 715/863, 382/103, 382/187
• US Class Current: 715/863
• CPC Class Codes: G06F 16/786 using motion, e.g. object motion or camera motion
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06V 40/1335 Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
• 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

The enhanced detection of a circular engagement gesture, in which a shape is defined within motion data, and the motion data is sampled at points that are aligned with the defined shape. It is determined whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data. An application is controlled if determining that the moving object is performing the gesture.

Claims

1. A non-transitory computer-readable medium encoded with a computer program comprising instructions that, when executed, operate to cause a computer to perform operations comprising:

defining a shape within motion data, the motion data comprising a motion history map that includes motion history data values providing, for each point of an image, an indication of time since a moving object was detected at the point;

determining, for each point, whether the moving object has been detected within a predetermined period of time, and grouping adjacent points determined to have detected motion of the moving object within the predetermined period of time;

sampling the motion data at one or more of the grouped points that are aligned with the defined shape;

determining whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data; and

controlling an application if determining that the moving object is performing the gesture.

2. The computer-readable medium of claim 1, further comprising instructions that, when executed, operate to cause the computer to perform operations comprising:

accessing the image; and

generating the motion history data history map based on the accessed image.

3. The computer-readable medium of claim 2, wherein the motion history map is generated using optical flow.

4. The computer-readable medium of claim 1, wherein the moving object is determined not to be performing the gesture if, at a particular time, more that a predetermined quantity of consecutive points that are aligned with the defined shape comprise a same sampled motion history data value.

5. The computer-readable medium of claim 1, wherein the pattern comprises a consistently upward or consistently downward sloping shape on a graph of the motion history data values for consecutive points that are aligned with the defined shape, at a particular time.

6. The computer-readable medium of claim 1, wherein the pattern comprises a consistently upward or consistently downward stepped shape on a graph of the motion history data values for consecutive points that are aligned with the defined shape, at a particular time.

7. The computer-readable medium of claim 1, wherein a center of the shape is defined at a centroid, a center of mass, or a median pixel of the grouped points.

8. The computer-readable medium of claim 1, further comprising instructions that, when executed, operate to cause the computer to perform operations comprising:

defining a bounding box around the grouped points,

wherein a size and a location of the shape within the motion data are defined with respect to the bounding box.

9. The computer-readable medium of claim 8, wherein:

the shape comprises a circle, and

a diameter of the circle is less than a smaller dimension of the bounding box.

10. The computer-readable medium of claim 9, wherein the diameter of the circle is 60% to 70% of the smaller dimension of the bounding box.

11. The computer-readable medium of claim 8, wherein a center of the shape is aligned within the bounding box according to a function of a dimension or an aspect ratio of the bounding box.

12. The computer-readable medium of claim 8, wherein, if the bounding box is square-shaped, a center of the shape is defined at a center of the bounding box.

13. The computer-readable medium of claim 8, wherein, if a height h of the bounding box is greater than a width w of the bounding box, a center of the shape is horizontally aligned with w/2, and is vertically aligned with (h−

w/2) with respect to a bottom left corner of the bounding box.

14. The computer-readable medium of claim 8, wherein, if a width w of the bounding box is greater than a height h of the bounding box, a center of the shape is horizontally aligned with w/2, and is vertically aligned with h/2 with respect to a bottom left corner of the bounding box.

15. The computer-readable medium of claim 1, wherein the gesture comprises a single stroke alphanumeric character.

16. The computer-readable medium of claim 1, wherein the shape comprises a circle shape, a figure-eight-shape, or an infinity-shape.

17. The computer-readable medium of claim 1, further comprising instructions that, when executed, operate to cause the computer to perform operations comprising:

detecting groups of points within the motion data; and

selecting one of the groups of points,

wherein the shape is defined within the one selected group.

18. The computer-readable medium of claim 17, wherein the one group is selected based on relative size.

19. The computer-readable medium of claim 1, wherein:

the motion data is sampled at a sampled quantity of points that are aligned with the defined shape, and

the sampled quantity comprises a fixed quantity or is based on a size of the defined shape or an aligned quantity of points that are aligned with the defined shape within the motion data.

20. The computer-readable medium of claim 1, wherein:

the motion data is sampled at a first quantity of points aligned with the defined shape, and

if determining that the moving object is performing the gesture, the application is controlled based on sampling a second, lesser quantity of the points aligned with the defined shape.

21. A computer-implemented method comprising:

defining a shape within motion data, the motion data comprising a motion history map that includes motion history data values providing, for each point of an image, an indication of time since a moving object was detected at the point;

determining, for each point, whether the moving object has been detected within a predetermined period of time, and grouping adjacent points determined to have detected motion of the moving object within the predetermined period of time;

sampling the motion data at one or more of the grouped points that are aligned with the defined shape;

determining whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data; and

controlling an application if determining that the moving object is performing the gesture.

22. A device comprising a processor configured to:

define a shape within motion data, the motion data comprising a motion history map that includes motion history data values providing, for each point of an image, an indication of time since a moving object was detected at the point;

determine, for each point, whether the moving object has been detected within a predetermined period of time, and grouping adjacent points determined to have detected motion of the moving object within the predetermined period of time;

sample the motion data at one or more of the grouped points that are aligned with the defined shape;

determine whether a moving object is performing a gesture correlating to the defined shape based on a pattern exhibited by the sampled motion data; and

control an application if determining that the moving object is performing the gesture.