Method and system for vision-based interaction in a virtual environment
A method and system for vision-based interaction in a virtual environment is disclosed. According to one embodiment, a computer-implemented method comprises receiving data from a plurality of sensors to generate a meshed volumetric three-dimensional representation of a subject. A plurality of clusters is identified within the meshed volumetric three-dimensional representation that corresponds to motion features. The motion features include hands, feet, knees, elbows, head, and shoulders. The plurality of sensors is used to track motion of the subject and manipulate the motion features of the meshed volumetric three-dimensional representation.
1. A computer-implemented method for tracking movement of motion features of a subject, comprising:
receiving data from a plurality of fixed position sensors comprising a distributed network of time of flight camera sensors to generate a volumetric three-dimensional representation of the subject;
identifying a plurality of clusters within the volumetric three-dimensional representation that correspond to motion features indicative of movement of the motion features of the subject relative to the fixed position sensors and one or more other portions of the subject, the motion features including one or more of hands, feet, knees, elbows, head and shoulders;
presenting one or more objects on one or more three dimensional display screens; and
using the plurality of fixed position sensors to track motion of the motion features of the subject and track manipulation of the motion features of the meshed volumetric three-dimensional representation to determine interaction of one or more of the motion features of the subject and one or more of the one or more objects on the three dimensional display.
2. The computer-implemented method of claim 1 , further comprising identifying one or more events corresponding to the tracked motion of the subject.
3. The computer-implemented method of claim 2 , wherein identifying one or more events further comprises matching the motion of the subject with an event stored in an event library.
4. The computer-implemented method of claim 3 , further comprising adding new events to the event library using a supervised computer-implemented learning process that uses Hidden Markov and Bayesian models.
5. The computer-implemented method of claim 4 , further comprising generating the new events taking into account anatomical constraints, sensor resolution, pixel depth and a total number of sensors.
6. The computer-implemented method of claim 3 , further comprising displaying the volumetric three-dimensional representation, wherein the volumetric three-dimensional representation moves according to instructions generated by a software development kit that links the motion features to a skeletal structure.
7. The computer-implemented method of claim 6 , wherein the software development kit provides a graphical representation of the skeletal structure having a plurality of points corresponding to the motion features, the plurality of points used to select a desired motion feature.
8. The computer implemented method of claim 1 , wherein the tracked motion is used to operate a video game.
9. The computer implemented method of claim 1 , further comprising the steps of:
acquiring an image of the face of the user; and
integrating a non-real photo avatar resembling the acquired image of the user into the game.
10. The computer implemented method of claim 1 , wherein the tracked motion is used in a virtual learning environment.
11. The computer implemented method of claim 1 , wherein the tracked motion is used in a virtual collaboration workspace.
12. A non-transitory computer-readable medium having stored thereon a plurality of instructions, the plurality of instructions when executed by a computer, cause the computer to perform:
receiving data from a plurality of fixed position sensors comprising a distributed network of time of flight camera sensors to generate a volumetric three-dimensional representation of the subject;
identifying a plurality of clusters within the volumetric three-dimensional representation that correspond to motion features indicative of movement of the motion features of the subject relative to the fixed position sensors and one or more other portions of the subject, the motion features including one or more of hands, feet, knees, elbows, head and shoulders;
presenting one or more objects on one or more three dimensional display screens; and
using the plurality of fixed position sensors to track motion of the motion features of the subject and track manipulation of the motion features of the volumetric three-dimensional representation to determine interaction of one or more of the motion features of the subject and one or more of the one or more objects on the three dimensional display.
13. The computer-readable medium of claim 12 , having stored thereon additional instructions, the additional instructions when executed by a computer, cause the computer to further perform identifying one or more events corresponding to the motion of the subject.
14. The computer-readable medium of claim 13 , having stored thereon additional instructions, the additional instructions when executed by a computer for identifying one or more events, cause the computer to further perform matching the motion of the subject with an event stored in an event library.
15. The computer-readable medium of claim 14 , having stored thereon additional instructions, the additional instructions when executed by a computer, cause the computer to further perform adding new events to the event library using a supervised computer-implemented learning process that uses Hidden Markov and Bayesian models.
16. The computer-readable medium of claim 15 , having stored thereon additional instructions, the additional instructions when executed by a computer, cause the computer to further perform generating the new events taking into account anatomical constraints, sensor resolution, pixel depth and a total number of sensors.
17. The computer-readable medium of claim 14 , having stored thereon additional instructions, the additional instructions when executed by a computer, cause the computer to further perform displaying the volumetric three-dimensional representation, wherein the volumetric three-dimensional representation moves according to instructions generated by a software development kit that links the motion features to a skeletal structure.
18. The computer-readable medium of claim 17 , wherein the software development kit provides a graphical representation of the skeletal structure having a plurality of points corresponding to the motion features, the plurality of points used to select a desired motion feature.