DEVICE AND METHOD FOR RECOGNIZING GESTURE BASED ON DIRECTION OF GESTURE

• US 20140037139A1
• Filed: 07/31/2013
• Published: 02/06/2014
• Est. Priority Date: 08/01/2012
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: LEE, Kyoobin, RYU, Hyun Surk, LEE, Jun Haeng
• Granted Patent: US 9,495,758 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• 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 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06F 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/269 using gradient-based methods
• CPC Class Codes: G06V 30/32 Digital ink
• 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 device and method for recognizing a gesture according to movement directions of an object.

Claims

1. A device for recognizing a gesture based on a direction of movement of an object, the device comprising:

a memory configured to store previous directional information that indicates a first direction of movement of the object;

a sensor configured to sense the movement of the object and output sensor data that indicates the movement of the object; and

a processor configured to determine current directional information that indicates a second direction of movement of the object based on the sensor data, and to recognize the gesture based on the first direction of movement of the object indicated by the previous directional information stored in the memory and the second direction of movement of the object indicated by the current directional information.

2. The device of claim 1, wherein the processor comprises:

a velocity generator configured to generate velocity information of the object based on the sensor data;

a direction generator configured to generate the current directional information based on the velocity information;

a direction quantization unit configured to quantize the second direction of movement of the object indicated by the current directional information to one of a plurality of predetermined directions; and

a gesture recognition unit configured to recognize the gesture based on the first direction of movement of the object and the quantized second direction of movement of the object.

3. The device of claim 1, wherein the processor is configured to recognize the gesture while the device is in a sleep mode, and activate the device in response to recognizing the gesture.

4. The device of claim 1, wherein the memory is configured to store a predetermined operation corresponding to the gesture, and the processor is configured to perform the predetermined operation in response to recognizing the gesture.

5. The device of claim 1, wherein the object comprises at least one of:

the device and another object other than the device.

6. The device of claim 1, wherein the sensor comprises at least one of an acceleration sensor, an image sensor, and an optical flow sensor.

7. The device of claim 1, wherein the memory stores a lookup table corresponding to the gesture, the lookup table having values assigned to transitions between the first direction of movement of the object and the second direction of movement of the object, and

wherein the processor is configured to increase or decrease a variable based on the value of the lookup table corresponding to the transition between the first direction of movement and the second direction of movement, and to recognize the gesture by comparing the variable to a predetermined threshold value.

8. A method of recognizing a gesture based on a direction of movement of an object, the method comprising:

sensing the movement of the object and generating sensor data that indicates the movement of the object;

determining current directional information that indicates a current direction of movement of the object based on the sensor data;

obtaining previous directional information that indicates a previous direction of movement of the object; and

recognizing the gesture based on the current direction of movement of the object indicated by the current directional information and the previous direction of movement of the object indicated by the previous directional information.

9. The method of claim 8, wherein the determining comprises:

generating velocity information of the object based on the sensor data;

generating the current directional information based on the velocity information; and

quantizing the current direction of movement of the object indicated by the current directional information to one of a plurality of predetermined directions.

10. The method of claim 8, further comprising:

switching a mode of a device from a sleep mode to an active mode in response to recognizing the gesture.

11. The method of claim 8, wherein the recognizing comprises:

increasing or decreasing a variable based on a value of a predetermined lookup table assigned to a transition between the current direction of movement of the object and the previous direction of movement of the object based on the transition between the previous direction of movement of the object and the current direction of movement of the object;

comparing the variable to a predetermined threshold value; and

recognizing the gesture based on a result of the comparing.

12. A non-transitory computer-readable medium comprising a program for instructing a computer to perform the method of claim 11.

13. A motion recognition device comprising:

a memory configured to store a direction sequence estimator that indicates a sequence of movement directions of a gesture;

a sensor configured to sense movement of an object; and

a processor configured to determine a sequence of movement directions of the object from the movement of the object sensed by the sensor, compare the sequence of movement directions of the object to the to the sequence of movement directions of the gesture pattern, and determine whether the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture pattern.

14. The motion recognition device according to claim 13, wherein the direction sequence estimator is a fully connected graph of nodes and at and least one edge between the nodes, the nodes corresponding to movement directions including the movement directions in the sequence of movement directions of the gesture and the edges corresponding to values assigned to transitions between the nodes.

15. The motion recognition device according to claim 14, wherein the processor is configured to determine whether the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture pattern by determining at least one value between the movement directions in the sequence of movement directions of the gesture that corresponds to the sequence of movement directions of the object, determine whether the at least one value meets a threshold that indicates the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture, and determine that the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture in response to determining the at least one value meets the threshold.

16. The motion recognition device according to claim 13, wherein the direction sequence estimator is a lookup table comprising rows and columns corresponding to movement directions including the movement directions in the sequence of movement directions of the gesture and values at intersections of the rows and columns corresponding to values assigned to transitions between the movement directions.

17. The motion recognition device according to claim 16, wherein the processor is configured to determine whether the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture pattern by determining at least one value between the movement directions in the sequence of movement directions of the gesture that corresponds to the sequence of movement directions of the object, determine whether the at least one value meets a threshold that indicates the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture, and determine that the sequence of movement directions of the object corresponds to the sequence of movement directions of the gesture in response to determining the at least one value meets the threshold.