COMPUTER VISION GESTURE BASED CONTROL OF A DEVICE

• US 20140053115A1
• Filed: 10/27/2013
• Published: 02/20/2014
• Est. Priority Date: 10/13/2009
• Status: Abandoned Application

• Current Assignee: PointGrab Ltd.
• Original Assignee: PointGrab Ltd.
• Inventors: Perski, Haim, Kaplan, Amir, Eilat, Eran
• Application Number:
  US14/064,142
• Publication Number:
  US 20140053115A1
• Time in Patent Office: Days
• US Class Current: 715/863
• 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: G06F 3/0487 using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser

Abstract

A system and method are provided for controlling a device based on computer vision. Embodiments of the system and method of the invention are based on receiving a sequence of images of a field of view; detecting movement of at least one object in the images; applying a shape recognition algorithm on the at least one moving object; confirming that the object is a user hand by combining information from at least two images of the object; and tracking the object to control the device.

Claims

1. A method for controlling a device based on computer vision, the method comprising:

detecting within images a user'"'"'s hand and another object related to the user;

detecting, from the images, movement of the user'"'"'s hand;

determining a distance of the other object from a camera used to obtain the images;

moving a displayed graphical object according to the movement of the user'"'"'s hand while normalizing movement of the displayed graphical object according to the distance of the other object from the camera.

2. The method of claim 1, wherein the other object related to the user is selected from the group consisting of a combination of face features, a face, a head and another part of the body.

3. The method of claim 1, comprising applying a shape recognition algorithm on the images to identify the user'"'"'s hand.

4. The method of claim 1, comprising applying a shape recognition algorithm on the images to identify the other object related to the user.

5. The method of claim 1, wherein determining the distance of the other object from the camera comprises determining a size of the other object relative to the image that includes the other object.

6. The method of claim 1, wherein the displayed graphical object is a cursor.

7. The method of claim 1, wherein the camera is a forward facing camera.

8. The method of claim 1, wherein the images are 2D images.

9. A device comprising:

a display; and

a processor in communication with the display, said processor to

detect within images an object related to a user;

detect, from the images, movement of the user'"'"'s hand;

determine a distance of the object related to the user from a camera used to obtain the images; and

move a graphical object on the display according to the movement of the user'"'"'s hand while normalizing movement of the graphical object according to the distance of the object related to the user from the camera.

10. The device of claim 9, wherein the object related to the user comprises the user'"'"'s hand.

11. The device of claim 9, wherein the object related to the user is selected from the group consisting of a combination of face features, a face, a head and another part of the body.

12. The device of claim 9, wherein the processor is to apply a shape recognition algorithm on the images to identify the object related to the user.

13. The device of claim 9, wherein the processor is to determine a size of the object related to the user, relative to the image that includes the object.

14. The device of claim 9, wherein the graphical object comprises a cursor.

15. The device of claim 9, comprising a camera to obtain the images.