THREE-DIMENSIONAL MOTION IDENTIFYING METHOD AND SYSTEM

• US 20100185570A1
• Filed: 12/28/2009
• Published: 07/22/2010
• Est. Priority Date: 01/22/2009
• Status: Abandoned Application

• Current Assignee: ASUSTek Computer, Inc.
• Original Assignee: ASUSTek Computer, Inc.
• Inventors: Ou, Chun-Liang
• Application Number:
  US12/647,547
• Publication Number:
  US 20100185570A1
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 2218/12 Classification; Matching
• 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 40/23 Recognition of whole body movements, e.g. for sport training

Abstract

A three-dimensional (3D) motion identifying method and system are used for identifying a motion of an object in a 3D space. First, the method provides a database recording sets of predetermined inertial information, and each of the sets of predetermined inertial information is an inertial movement of a specific motion in the 3D space. Then, inertial information of the object in moving is retrieved via a motion sensor in the object, and the inertial information is compared with all predetermined inertial information in the database to determine similarities therebetween. Finally, whether the motion of the object is the same as any predetermined inertial information or not is determined according to a degree of the similarity. As a result, more complicated motions of the object can be directly identified via the comparison with the database.

Claims

1. A three-dimensional (3D) motion identifying method, used for identifying a motion of an object in a 3D space, comprising:

providing a database, wherein the database records multiple sets of predetermined inertial information, and each of the sets of predetermined inertial information is an inertial movement of a specific motion in the 3D space;

retrieving a inertial information of the object in moving via a motion sensor in the object;

comparing a similarity between the inertial information and each of the sets of predetermined inertial information in the database; and

determining whether a motion of the object is the same as the specific motion corresponding to one of the sets of predetermined inertial information according to the similarities.

2. The 3D motion identifying method according to claim 1, wherein the motion sensor continually retrieves the inertial information of the object, the step of retrieving the inertial information of the object in moving comprises:

determining a beginning time and a finishing time of the motion of the object;

an retaining all the inertial information between the beginning time and the finishing time.

3. The 3D motion identifying method according to claim 2, wherein the step of determining the beginning time and the finishing time of the motion of the object comprises:

determining a time point at which the inertial information of the object is greater than or equal to a first predetermined value as the beginning time and bring the object to a motion state from the stationary state; and

determining the time point at which the inertial information of the object is smaller than the first predetermined value for a specific time as the finishing time and bring the object to the stationary state from the motion state.

4. The 3D motion identifying method according to claim 1, wherein the motion sensor comprises one of a G-sensor and a Gyro sensor, and the inertial information comprises one of a velocity, acceleration, an angular velocity, and displacement.

5. The 3D motion identifying method according to claim 1, wherein the database records at least a command and a corresponding relationship between each of the commands and at least one of the predetermined inertial information.

6. The 3D motion identifying method according to claim 5, after the step of determining whether the motion of the object is the same as the specific motion corresponding to one of the sets of predetermined inertial information according to the similarities, further comprising:

triggering the command corresponding to the predetermined inertial information having the highest similarity to perform a function.

7. The 3D motion identifying method according to claim 1, further comprising:

entering a database building model;

obtaining the inertial information of the object in moving via the motion sensor, wherein the inertial information is the specific motion of the object operated by a user in the 3D space;

recording the inertial information in the database as a set of the predetermined inertial information;

obtaining a command; and

establishing the corresponding relationship between the inertial information and the command in the database.

8. The 3D motion identifying method according to claim 7, wherein the step of obtaining the command further comprises:

obtaining the command recorded in the database or inputted by a user.

9. The 3D motion identifying method according to claim 1, further comprising:

entering a motion study mode;

choosing a set of the predetermined inertial information as a reference inertial information;

retrieving the inertial information of the object in moving via the motion sensor;

comparing the inertial information and the reference inertial information to obtain the similarity between the inertial information and the reference inertial information;

when the similarity is between a first value and a second value, modifying the reference inertial information according to the inertial information and returning to the step of retrieving the inertial information of the object in moving via the motion sensor to re-obtain the similarity, wherein the first value is larger than the second value; and

returning to the step of retrieving the inertial information of the object in moving via the motion sensor to re-obtain the similarity when the similarity is smaller than the second value.

10. A 3D motion identifying system, comprising:

a database used for recording sets of predetermined inertial information, wherein each of the sets of predetermined inertial information is an inertial movement of a specific motion in a 3D space;

a motion sensor used for retrieving inertial information of an object when the object moves in the 3D space, and

a processing module coupled with the database and the motion sensor and used for comparing a similarity between the inertial information and each of the sets of predetermined inertial information in the database, respectively, and determining whether a motion of the object is the same as the specific motion corresponding to one of the sets of predetermined inertial information according to the similarities.

11. The 3D motion identifying system according to claim 10, wherein the motion sensor continually retrieves the inertial information of the object, and the processing module determines the beginning time and the finishing time of the motion of the object to retain all the inertial information between the beginning time and the finishing time.

12. The 3D motion identifying system according to claim 11, wherein the state of the object is predetermined to be a stationary state, when the state of the object is the stationary state, the processing module utilizes a time point at which the inertial information of the object is greater than or equal to a first predetermined value as the beginning time and updates the state of the object to a motion state, and when the state of the object is the motion state, the processing module utilizes the time point at which the inertial information of the object is smaller than the first predetermined value for a specific time as the finishing time and updates the state of the object to the stationary state.

13. The 3D motion identifying system according to claim 10, wherein the motion sensor comprises one of a G-sensor and a Gyro sensor, and the inertial information comprises one of a velocity, acceleration, an angular velocity, and displacement.

14. The 3D motion identifying system according to claim 10, wherein the database records at least a command and a corresponding relationship between each of the commands and at least one set of the predetermined inertial information.

15. The 3D motion identifying system according to claim 14, wherein the processing module triggers the command corresponding to the predetermined inertial information having the highest similarity to perform a function.

16. The 3D motion identifying system according to claim 10, wherein in a database building model, the processing module retrieves the inertial information of the object in moving obtained by the motion sensor, records the inertial information in the database as a set of the predetermined inertial information, obtains a command to establish the corresponding relationship between the inertial information and the command in the database, and the inertial information is the specific motion of the object operated by a user in the 3D space.

17. The 3D motion identifying system according to claim 16, wherein the processing module obtains the command recorded in the database or inputted by a user.

18. The 3D motion identifying system according to claim 10, wherein in a motion study mode, the processing module chooses a set of the predetermined inertial information as a reference inertial information, retrieves the inertial information of the object in moving via the motion sensor, and compares the inertial information and the reference inertial information to obtain the similarity between the inertial information and the reference inertial information, when the similarity is between a first value and a second value, the processing module modifies the reference inertial information according to the inertial information, re-retrieved the inertial information of the object in moving via the motion sensor to reobtain the similarity, when the similarity is less than the second value, the inertial information of the object in moving is re-retrieved via the motion sensor to reobtain the similarity, and the first value is larger than the second value.