COMPUTER VISION BASED CONTROL OF A DEVICE USING MACHINE LEARNING

• US 20140071042A1
• Filed: 05/31/2012
• Published: 03/13/2014
• Est. Priority Date: 05/31/2011
• Status: Abandoned Application

• Current Assignee: PointGrab Ltd.
• Original Assignee: PointGrab Ltd.
• Inventors: Eilat, Eran
• Application Number:
  US13/984,853
• Publication Number:
  US 20140071042A1
• Time in Patent Office: Days
• US Class Current: 345/156
• 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 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

A method for computer vision based control of a device, the method comprising: obtaining a first frame comprising an image of an object within a field of view; identifying the object as a hand by applying computer vision algorithms; storing image related information of the identified hand; obtaining a second frame comprising an image of an object within a field of view and identifying the object in the second frame as a hand by using the stored information of the identified hand; and controlling the device based on the hand identified in the first and second frames.

Claims

1. A method for computer vision based control of a device, the method comprising:

obtaining a first frame comprising an image of an object within a field of view;

identifying the object as a hand by applying computer vision algorithms;

storing image related shape information of the identified hand;

obtaining a second frame comprising an image of a hand within a field of view and identifying the shape of the hand in the second frame as a hand by using the stored shape information of the identified hand; and

controlling the device based on the shape of the hand identified in the first and second frames.

2. The method according to claim 1 comprising tracking the hand identified in the first frame and continuing the tracking only if the hand is also identified in the second image.

3. The method of claim 2 comprising controlling the device according to the tracking of the hand.

4. The method according to claim 1 comprising storing image related shape information of the hand identified in the second frame.

5. The method according to claim 1 comprising identifying a non-hand object and storing image related information of the non-hand object.

6. The method according to claim 5 comprising storing the image related shape information of the object identified as a hand and the image related information of the non-hand object, only if the information is different than any image related information already stored.

7. The method according to claim 1 comprising storing image related shape information of an object identified as a hand for a first pre-defined period.

8. The method according to claim 7 wherein the first pre-defined period is based on use.

9. The method according to claim 7 wherein the first pre-defined period is based on absolute time.

10. The method according to claim 5 comprising storing image related information of the non-hand object for a second pre-defined period.

11. The method according to claim 10 wherein the second pre-defined period is based on use.

12. The method according to claim 10 wherein the second pre-defined period is based on absolute time.

13. The method according to claim 5 wherein the non-hand object comprises a portion of a frame, said portion not including a hand.

14. The method according to claim 13 wherein the portion is located at a pre-determined distance or further from the position of the hand within the frame.

15. The method according to claim 13 wherein the portion includes an area in which no movement was detected.

16. The method according to claim 1 wherein the image related shape information comprises features selected from the group consisting of Local Binary Pattern (LBP) features, statistical parameters of grey level and Speeded Up Robust Features (SURF).

17. The method according to claim 1 wherein identifying the object in the second frame as a hand by using the shape information of the identified hand comprises:

detecting in the identified hand a set of features;

assigning a value to each feature; and

comparing the values of the features to a hand identification threshold, said hand identification threshold constructed by using values of features of formerly identified hands.

18. The method according to claim 17 comprising constructing a new hand identification threshold at predetermined intervals.

19. The method according to claim 1 comprising identifying the object in the first image as a hand only if the object is moving in a pre-defined movement.

20-29. -29. (canceled)