Apparatus and method for recognizing spatial gesture

• US 9,524,031 B2
• Filed: 11/18/2013
• Issued: 12/20/2016
• Est. Priority Date: 09/09/2013
• Status: Active Grant

• Current Assignee: Korea Advanced Institute of Science and Technology
• Original Assignee: Center of Human-centered Interaction for Coexistence (Government of South Korea)
• Inventors: Yeom, Kiwon, Han, Hyejin, You, Bumjae
• Primary Examiner(s): XAVIER, ANTONIO J
• Application Number:
  US14/349,063
• Publication Number:
  US 20150138088A1
• Time in Patent Office: 1,128 Days
• Field of Search: None
• US Class Current: 1/1
• 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 3/0346 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: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

The present invention relates to an apparatus for recognizing a gesture in a space. In accordance with an embodiment, a spatial gesture recognition apparatus includes a pattern formation unit for radiating light onto a surface of an object required to input a gesture in a virtual air bounce, and forming a predetermined pattern on the surface of the object, an image acquisition unit for acquiring a motion image of the object, and a processing unit for recognizing a gesture input by the object based on the pattern formed on the surface of the object using the acquired image. In this way, depending on the depths of an object required to input a gesture in a space, haptic feedbacks having different intensities are provided, and thus a user can precisely input his or her desired gesture.

Claims

1. An apparatus for recognizing a spatial gesture, comprising:

a pattern formation unit for radiating light onto a surface of an object required to input a gesture in a virtual air bounce, and forming a predetermined pattern on the surface of the object;

an image acquisition unit for acquiring a motion image of the object;

a processing unit for recognizing a gesture input by the object based on the pattern formed on the surface of the object using the acquired image;

a gesture recognition unit for recognizing a motion of the object as a gesture, the gesture recognition unit extracts vector values from the gesture and differentiates velocities of the vector values to eliminate or correct a meaningless portion of the gesture;

wherein the gesture recognition unit recognizes the motion of the object made in a predetermined area of the air bounce as a gesture based on the calculated depth information of the object;

wherein the gesture recognition unit extracts information about one or more feature vectors from the recognized gesture, and eliminates a ligature from the motion of the object using the extracted feature vectors;

wherein the gesture recognition unit extracts one or more segmentation points using the extracted feature vectors and the calculated depth information of the object, and determines a portion for connecting the extracted segmentation points to be a ligature; and

wherein the gesture recognition unit extracts the segmentation points by applying the feature vectors and the depth information of the object to any one of the following feature point extraction techniques;

a matching probability technique and a pattern model technique.

2. The apparatus of claim 1, wherein the processing unit comprises:

a pattern analysis unit for analyzing the pattern formed on the object and calculating depth information of the object entering the air bounce.

3. The apparatus of claim 2, wherein the pattern analysis unit calculates one or more of size information and density information of the pattern formed on the object, and calculates the depth information of the object using the calculated information.

4. The apparatus of claim 1, wherein the differentiated velocities comprise acceleration values.

5. A method of recognizing a spatial gesture, comprising:

radiating light onto a surface of an object required to input a gesture in a virtual air bounce, and forming a predetermined pattern on the surface of the object;

acquiring a motion image of the object;

recognizing a gesture input by the object based on the pattern formed on the surface of the object using the acquired image;

extracting vector values from the gesture input and differentiating velocities of the vector values to eliminate or correct a meaningless portion of the gesture input;

wherein recognizing the gesture comprises;

analyzing the pattern formed on the object and calculating depth information of the object entering the air bounce;

wherein a motion of the object made in a predetermined area of the air bounce is recognized as a gesture based on the calculated depth information of the object;

wherein recognizing the gesture comprises;

eliminating a ligature from the motion of the object using the vector values;

wherein eliminating the ligature comprises;

extracting one or more segmentation points using the vector values and the calculated depth information of the object; and

determining a portion for connecting the extracted segmentation points to be the ligature; and

wherein extracting the segmentation points is configured to extract the segmentation points by applying the vector values and the depth information of the object to any one of feature point extraction techniques including a matching probability technique and a pattern model technique.

6. The method of claim 5, wherein calculating the depth information is configured to calculate one or more of size information and density information of the pattern formed on the object, and calculate the depth information of the object using the calculated information.

7. The apparatus of claim 5, wherein the differentiating velocities comprise acceleration values.