Method and apparatus for recognizing touch gesture

Patent metadata

Field	Value
Publication number	US-2016147376-A1
Application number	US-201514798803-A
Country	US
Kind code	A1
Filing date	Jul 14, 2015
Priority date	Nov 26, 2014
Publication date	May 26, 2016
Grant date	—

Abstract

A method and an apparatus for recognizing a touch gesture are disclosed, in which the apparatus may obtain a depth image in which a touch object and a background area are captured, detect a touch input applied by the touch object to the background area in a touch detection area, and recognize a touch gesture associated with the touch input by tracking a change in the touch input.

First claim

What is claimed is:

1 . A method of recognizing a touch gesture to be performed by an apparatus for recognizing a touch gesture, the method comprising:
obtaining a depth image in which a touch object and a background area are captured; detecting, from the depth image, a touch input applied by the touch object to the background area in a touch detection area; and recognizing a touch gesture associated with the touch input by tracking a change in the touch input.

2 . The method of claim 1 , further comprising:
learning the background area; and determining the touch detection area from the learned background area, wherein the detecting of the touch input is performed in the touch detection area based on the learned background area.

3 . The method of claim 2 , wherein the detecting of the touch input comprises:
determining a touch detection area to detect the touch input based on the learned background area; and detecting the touch input within the touch detection area.

4 . The method of claim 3 , wherein the touch detection area comprises a portion of the learned background area and an adjacent area that is adjacent to a boundary of the learned background area.

5 . The method of claim 2 , wherein the learning of the background area comprises:
determining whether an initial background area on an initial depth image satisfies a predetermined learning condition; and learning the background area based on the initial depth image when the background area satisfies the predetermined learning condition.

6 . The method of claim 2 , comprising:
determining whether a predetermined learning cycle arrives; obtaining a learning depth image when the predetermined learning cycle arrives; determining, when the predetermined learning cycle arrives, whether a touch event is present in a touch detection area of the learning depth image based on learning a background area for learning included in the learning depth image; extracting an adjacent area that is adjacent to a boundary of the background area for learning from the learning depth image when the touch event is absent in the touch detection area; and learning a new touch detection area based on the extracted adjacent area.

7 . The method of claim 3 , wherein the detecting of the touch input comprises:
determining whether the touch object makes contact on the touch detection area; and detecting a change in the touch input when the touch object is in contact on the touch detection area.

8 . The method of claim 7 , wherein the determining of whether the touch object makes contact on the touch detection area comprises:
determining whether the touch object makes contact with a boundary of the learned background area on the touch detection area based on a shape of the learned background area.

9 . The method of claim 1 , wherein:
the detecting of the touch input comprises determining at least one of a location of the touch input and a touch angle of the touch input; and the tracking of the change in the touch input comprises tracking at least one of a change in the location of the touch input and a change in the touch angle of the touch input.

10 . The method of claim 3 , wherein:
the detecting of the touch input comprises detecting touch inputs within the touch detection area, and the recognizing of the touch gesture comprises recognizing a touch gesture associated with the touch inputs based on a mutual relation between the detected touch inputs.

11 . A non-transitory computer-readable storage medium comprising a program comprising instructions to cause a computer to perform the method of claim 1 .

12 . A method of recognizing a touch gesture to be performed by an apparatus for recognizing a touch gesture, the method comprising:
learning, based on a depth image, a background area to be in contact with a touch object; determining a touch detection area based on the learned background area; detecting a touch input by the touch object based on a touch object area in the touch detection area; and recognizing a touch gesture corresponding to a motion of the touch input.

13 . The method of claim 12 , wherein the learning of the background area to be in contact with the touch object comprises:
determining whether a predetermined learning cycle arrives; determining, when the predetermined learning cycle arrives, whether a touch event is present in the depth image; extracting a background area for learning from a learning depth image when the touch event is absent depth image; and learning the background area to be in contact with the touch object based on the extracted background area.

14 . The method of claim 12 , wherein the detecting of the touch input comprises:
determining whether the touch object makes contact within the touch detection area; and detecting a change in the touch input when the touch object is in contact with the touch detection area.

15 . The method of claim 12 , wherein:
the detecting of the touch input comprises determining at least one of a location of the touch input and a touch angle of the touch input; and the recognizing of the touch gesture comprises recognizing a touch gesture associated with the touch input by tracking at least one of a change in the location of the touch input and a change in the touch angle of the touch input.

16 . An apparatus for recognizing a touch gesture, comprising:
a depth sensor configured to obtain a depth image in which a touch object is captured; and a processor configured to detect, from the depth image, a touch input applied by the touch object in a touch detection area and recognize a touch gesture associated with the touch input by tracking a change in the touch input.

17 . The apparatus of claim 16 , further comprising:
a learner configured to learn a background area for an adjacent area that is adjacent to a boundary of a background area detected in the depth image, and wherein the processor is configured to update the touch detection area based on updating the learned background area at predetermined learning cycles.

18 . The apparatus of claim 17 , wherein the learner is configured to determine whether a touch event is present on the touch detection area when a predetermined learning cycle arrives, and to extract a learning background area from a learning depth image and learn the background area from the learning depth image when the touch event is absent in the touch detection area.

19 . The apparatus of claim 17 , wherein the processor is configured to determine the touch detection area for detecting the touch input based on the learned background area, and detect a change in the touch input within the touch detection area.

20 . The apparatus of claim 16 , wherein the apparatus is included in a wearable device.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Namjoon
• Park Joonah
• Park Du-Sik
• Shin Jungsoon
• Lim Soochul

Classifications

• G06F3/04883

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06F1/163

  Wearable computers, e.g. on a belt · CPC title

• G06F3/0425 Primary

  using a single imaging device like a video camera for tracking the absolute position of a single or a plurality of objects with respect to an imaged reference surface, e.g. video camera imaging a display or a projection screen, a table or a wall surface, on which a computer generated image is displayed or projected (tracking a projected light spot to determine a position on a display surface G06F3/0386) · CPC title

• G06F2203/04101

  2.5D-digitiser, i.e. digitiser detecting the X/Y position of the input means, finger or stylus, also when it does not touch, but is proximate to the digitiser's interaction surface and also measures the distance of the input means within a short range in the Z direction, possibly with a separate measurement setup · CPC title

• G06F3/017 Primary

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title