Computer vision based tracking of a hand

• US 8,938,124 B2
• Filed: 06/25/2013
• Issued: 01/20/2015
• Est. Priority Date: 05/10/2012
• Status: Active Grant

• Current Assignee: PointGrab Ltd.
• Original Assignee: PointGrab Ltd.
• Inventors: Eilat, Eran, Kaplan, Amir, Menadeva, Ovadya, Perski, Haim
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): GILLIARD, DELOMIA L
• Application Number:
  US13/926,445
• Publication Number:
  US 20130301926A1
• Time in Patent Office: 574 Days
• Field of Search: 382/195
• US Class Current: 382/195
• 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 computer vision based tracking of a hand may include receiving a sequence of images, the images including at least one object having a shape of a hand. A first selected feature is tracked from within the hand shaped object. Shape recognition algorithms are applied at a suspected location of the hand shaped object in an image from the sequence of images to detect a shape of a hand in the image and a second feature from within the detected shape of the hand is then selected and tracked, thereby providing verification and updating of the location of the hand shaped object.

Claims

1. A method for computer vision based tracking of a hand, the method comprising:

i) receiving a sequence of images of a field of view, said images comprising at least one object having a shape of a hand;

ii) tracking at least one first selected feature from within the shape of the object;

iii) applying a shape recognition algorithm at a suspected location of the object in an image from the sequence of images to detect a newly detected shape of a hand in the image;

iv) selecting at least one newly selected feature to be tracked from within the newly detected shape of the hand; and

v) tracking the newly selected feature.

2. The method of claim 1 comprising repeating steps (iii)-(v) to track a hand throughout a plurality of images.

3. The method of claim 2 comprising:

assigning a probability grade to a detected shape for each of the plurality of images;

using the probability grades to obtain a combined probability grade; and

determining that no shape of a hand is detected if the combined probability grade is below a predetermined threshold.

4. The method of claim 1 comprising terminating tracking if no shape of a hand is detected at the suspected location.

5. The method of claim 1 wherein the first and newly selected features comprise pixels, patterns or vectors.

6. The method of claim 1 comprising detecting a size of the object having a shape of the hand and determining the suspected location based on the detected size.

7. The method of claim 1 wherein tracking the first feature and the newly selected feature comprises tracking a hand, the method further comprising controlling a device according to the tracking of the hand.

8. The method of claim 7 wherein controlling the device comprises controlling movement of an icon on a display according to movement of the hand.

9. The method of claim 8 wherein the icon is a cursor.

10. The method of claim 1 comprising controlling a display of a device according to the detection of the newly detected shape of the hand.

11. The method of claim 10 wherein controlling a display of the device comprises changing a color or transparency of an icon on the display.

12. The method of claim 11 wherein the icon is a symbol or a representation of a hand.

13. The method of claim 1 comprising

classifying a first set of selected features to groups;

determining multiple suspected locations according to locations of the groups;

applying a shape recognition algorithm at each suspected location;

determining, based on the shape recognition algorithm, a shape at one of the suspected locations, with the highest probability of being a shape of a hand;

selecting at least one newly selected feature to be tracked from within the determined shape; and

tracking the newly selected feature.

14. The method of claim 1 wherein the newly detected shape of a hand comprises a shape of a hand in a specific posture.

15. A method for computer vision based tracking of a hand, the method comprising:

receiving a sequence of images, said images comprising at least one object having a shape of a hand;

tracking a feature from within the shape of the object;

applying a shape recognition algorithm at a suspected location of the object in an image from the sequence of images to detect a newly detected shape of the object;

if the newly detected shape of the object is a shape of a hand then selecting a newly selected feature to be tracked from within the newly detected shape of the object and tracking the newly selected feature; and

terminating tracking if the shape of the newly detected shape of the object is not a hand shape.

16. The method of claim 15 comprising moving an icon on a display according to the tracking of the newly selected feature.

17. The method of claim 16 comprising stopping movement of the icon when tracking is terminated.

18. The method of claim 17 comprising resuming movement of the icon according to tracking of the newly selected feature, the location of the icon when resuming movement being the last location of the icon when movement of the icon was stopped.

19. A system for computer vision based tracking of a hand, the system comprising

a processor configured to:

detect within an image from a sequence of images an object having a shape of a hand;

track at least one first selected feature from within the shape of the object;

detect a newly detected shape of a hand at a suspected location of the object;

select at least one newly selected feature to be tracked from within the newly detected shape of the hand; and

track the newly selected feature; and

control a device based on the tracking of the newly selected feature.