Information processing device and method, program and recording medium for identifying a gesture of a person from captured image data
An information processing device includes: an outline extraction unit extracting an outline of a subject from a picked-up image of the subject; a characteristic amount extraction unit extracting a characteristic amount, by extracting sample points from points making up the outline, for each of the sample points; an estimation unit estimating a posture of a high degree of matching as a posture of the subject by calculating a degree of the characteristic amount extracted in the characteristic amount extraction unit being matched with each of a plurality of characteristic amounts that are prepared in advance and represent predetermined postures different from each other; and a determination unit determining accuracy of estimation by the estimation unit using a matching cost when the estimation unit carries out the estimation.
1. An information processing apparatus, comprising:
circuitry that
captures an image of a human subject;
outputs data indicative of a position of at least one joint of the human subject, the at least one joint being a place at which two parts of the human subject are joined;
outputs, as a result, the captured image of the human subject and the output data by overlapping a plurality of points and lines indicative of the position of the at least one joint of the human subject on the captured image of the human subject; and
determines a gesture of the human subject based on the output data.
2. The information processing apparatus of claim 1 , wherein the circuitry
obtains values of pixels corresponding to positions of one or more sample points within an image of the human subject; and
computes the data based on the obtained pixel values, the data being indicative of a match between a corresponding one of the sample point positions and a position of a predetermined joint of the human subject.
3. The information processing apparatus of claim 2 , wherein the circuitry extracts the image of the human subject from a picked-up image.
4. The information processing apparatus of claim 3 , wherein the circuitry extracts an outline of the human subject from the picked-up image.
5. The information processing apparatus of claim 3 , wherein the circuitry obtains the picked-up image from a stereo camera.
6. The information processing apparatus of claim 5 , wherein the circuitry
detects a signal indicative of a reflection of the human subject in response to irradiation; and
obtains the picked-up image based on the detected signal.
7. The information processing apparatus of claim 2 , wherein the circuitry computes the data based on at least one pixel value associated with the corresponding sample point position and pixel values associated with one or more stored images.
8. The information processing apparatus of claim 2 , wherein the circuitry computes the data between each of a plurality of the sample point positions and the predetermined joint position.
9. The information processing apparatus of claim 1 , wherein the circuitry computes the data using a tree-structure algorithm.
10. The information processing apparatus of claim 1 , wherein the circuitry generates an instruction to control a gaming application in accordance with the determined gesture.
11. The information processing apparatus of claim 1 , wherein the circuitry
estimates a posture of the human subject; and
determines the gesture of the human subject based on the estimated posture.
12. A computer-implemented method, comprising:
capturing an image of a human subject;
outputting data indicative of a position of at least one joint of the human subject, the at least one joint being a place at which two parts of the human subject are joined;
outputting, as a result, the captured image of the human subject and the output data by overlapping a plurality of points and lines indicative of the position of the at least one joint of the human subject on the captured image of the human subject; and
determining, using at least one processor, a gesture of the human subject based on the output data.
13. The method of claim 12 , wherein:
the method further comprises obtaining values of pixels corresponding to positions of one or more sample points within an image of the human subject; and
the computing comprises computing the data based on the obtained pixel values, the data being indicative of a match between a corresponding one of the sample point positions and a position of a predetermined joint of the human subject.
14. The method of claim 13 , further comprising extracting the image of the human subject from a picked-up image.
15. The method of claim 14 , further comprising extracting an outline of the human subject from the picked-up image.
16. The method of claim 14 , further comprising obtaining the picked-up image from a stereo camera.
17. The method of claim 14 , further comprising:
detecting a signal indicative of a reflection of the human subject in response to irradiation; and
obtaining the picked-up image based on the detected signal.
18. The method of claim 13 , wherein the computing further comprises computing the data based on at least one pixel value associated with the corresponding sample point position and pixel values associated with one or more stored images.
19. The method of claim 13 , wherein the computing further comprises computing the data between each of a plurality of the sample point positions and the predetermined joint position.
20. The method of claim 12 , wherein the computing further comprises computing the data using a tree-structure algorithm.
21. The method of claim 12 , further comprising generating an instruction to control a gaming application in accordance with the determined gesture.
22. The method of claim 12 , wherein:
the method further comprises estimating a posture of the human subject; and
determining the gesture of the human subject based on the estimated posture.
23. A tangible, non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a method, comprising:
capturing an image of a human subject;
outputting data indicative of a position of at least one joint of the human subject, the at least one joint being a place at which two parts of the human subject are joined;
outputting, as a result, the captured image of the human subject and the output data by overlapping a plurality of points and lines indicative of the position of the at least one joint of the human subject on the captured image of the human subject; and
determining a gesture of the human subject based on the output data.
24. The tangible, non-transitory computer-readable medium of claim 23 , wherein:
the method further comprises obtaining values of pixels corresponding to positions of one or more sample points within an image of the human subject; and
the computing comprises computing the data based on the obtained pixel values, the data being indicative of a match between a corresponding one of the sample point positions and a position of a predetermined joint of the human subject.
25. The tangible, non-transitory computer-readable medium of claim 24 , wherein the method further comprises extracting the image of the human subject from a picked-up image.
26. The tangible, non-transitory computer-readable medium of claim 25 , wherein the method further comprises extracting an outline of the human subject from the picked-up image.
27. The tangible, non-transitory computer-readable medium of claim 25 , wherein the method further comprises obtaining the picked-up image from a stereo camera.
28. The tangible, non-transitory computer-readable medium of claim 25 , wherein the method further comprises:
detecting a signal indicative of a reflection of the human subject in response to irradiation; and
obtaining the picked-up image based on the detected signal.
29. The tangible, non-transitory computer-readable medium of claim 24 , wherein the computing further comprises computing the data based on at least one pixel value associated with the corresponding sample point position and pixel values associated with one or more stored images.
30. The tangible, non-transitory computer-readable medium of claim 24 , wherein the estimating further comprises computing the data between each of a plurality of the sample point positions and the predetermined joint position.
31. The tangible, non-transitory computer-readable medium of claim 23 , wherein the estimating further comprises computing the data using a tree-structure algorithm.
32. The tangible, non-transitory computer-readable medium of claim 23 , wherein the method further comprises generating an instruction to control a gaming application in accordance with the determined gesture.
33. The tangible, non-transitory computer-readable medium of claim 23 , wherein:
the method further comprises estimating a posture of the human subject; and
determining the gesture of the human subject based on the estimated posture.