Computing device and method for motion detection
A computing device for motion detection in a system capable of detecting feature points of an object of interest is disclosed. The computing device includes a vector forming unit to form a plurality of vectors associated with a set of the feature points and form a vector set based on the vectors, a posture identifying unit to identify a match of a posture in a database based on the vector set, a motion similarity unit to identify a set of predetermined postures in the database based on the matched posture and an immediately previous matched posture, and a motion identifying unit to identify a predetermined motion in the database based on the set of predetermined postures.
1. A computing device for motion detection in a system capable of detecting feature points of an object of interest, the computing device comprising:
a vector forming unit to form a plurality of vectors associated with a set of the feature points and form a vector set represent a predetermined posture based on the vectors;
a posture identifying unit to identify a match of a posture in a database based on the vector set;
a motion similarity unit to identify a set of predetermined postures represent a predetermined motion in the database based on the matched posture and an immediately previous matched posture; and
a motion identifying unit to identify the predetermined motion in the database based on the set of predetermined postures.
2. The computing device of claim 1 , wherein the vector forming unit is configured to normalize the vectors.
3. The computing device of claim 1 , wherein the motion similarity unit is configured to determine the degree of similarity between two postures by calculating a dot product of the vectors associated with each of the two postures.
4. The computing device of claim 1 , wherein each of the predetermined postures includes a unique index number.
5. The computing device of claim 4 further comprising a microprocessor to assign a unique index number to each of the predetermined postures.
6. The computing device of claim 4 further comprising a motion smoothness unit to determine the degree of smoothness of postures based on the index numbers thereof.
7. The computing device of claim 1 , wherein the database stores a plurality of sets of vectors and a plurality of sets of postures, wherein each set of vectors represents a posture of the object, and each set of postures represents a motion of the object.
8. The computing device of claim 1 , wherein the database stores a plurality of sets of continuous postures, wherein each set of continuous postures includes a set of continuous index numbers.
9. A method of motion detection in a system capable of detecting feature points of an object of interest, the method comprising:
forming a plurality of vectors associated with a set of the feature points;
forming a vector set represent a predetermined posture based on the vectors;
identifying a match of a posture in a database based on the vector set;
identifying a set of predetermined postures represent a predetermined motion in the database based on the matched posture and an immediately previous matched posture; and
identifying the predetermined motion in the database based on the set of predetermined postures.
10. The method of claim 9 further comprising:
normalizing the vectors after forming the vectors associated with a set of the feature points.
11. The method of claim 9 further comprising:
determining the degree of similarity between two postures by calculating a dot product of the vectors associated with each of the two postures.
12. The method of claim 9 further comprising:
assigning a unique index number to each of the predetermined postures.
13. The method of claim 12 further comprising:
determining the degree of smoothness of postures based on the index numbers thereof.
14. The method of claim 9 , wherein the database stores a plurality of sets of vectors and a plurality of sets of postures, wherein each set of vectors represents a posture of the object, and each set of postures represents a motion of the object.
15. The method of claim 9 , wherein the database stores a plurality of sets of continuous postures, wherein each set of continuous postures includes a set of continuous index numbers.