Systems and methods of locating a control object appendage in three dimensional (3D) space

1. A system for recognizing gestures from a control object moving in three dimensional (3D) space, the system including:

one or more processors coupled to a memory, the memory loaded with computer instructions that, when executed by the one or more processors, implement actions including:

receiving a result of analyzing a gesture;

interpreting the result of analyzing a gesture as an instruction to perform an operation,

wherein the result of analyzing a gesture is obtained from another program, which is executed on a processor, to analyze differences in positions of fit closed curves fit to observed edges of a control object thereby tracking motion of the control object while making a gesture in a 3D space by repeatedly:

obtaining captured images of a control object moving in 3D space captured from at least two geometrically distinct predetermined vantages;

calculating observed edges of the control object from the captured images;

fitting closed curves to the observed edges of the control object as captured in the captured images by selecting a closed curve from a family of similar closed curves that fit the observed edges of the control object as captured using an assumed parameter;

whenever the control object is a complex control object that includes a palm and multiple fingers, applying actions including obtaining captured images, calculating observed edges, and fitting closed curves to construct multiple fingers of control object appendages; and

fitting cross sections of a palm to observed edges of a palm as captured in the captured images.

2. The system of claim 1 , wherein one or more fitted parameters of a first fitted closed curve are substituted for one or more of the observed edges and the assumed parameter when fitting an adjacent second closed curve.

3. The system of claim 1 , wherein a first fitted closed curve is used to filter fits of additional closed curves.

4. The system of claim 1 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying actions including obtaining captured images, calculating observed edges, and fitting closed curves actions of claim 1 over time; and

calculating motion of the control object over time based on differences between modeled locations of the control object.

5. The system of claim 3 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying actions including obtaining captured images, calculating observed edges, fitting closed curves and using a first fitted closed curve to filter fits of additional closed curves actions of claim 3 over time; and

calculating motion of a complex control object over time based on differences between modeled locations of a complex control object.

6. The system of claim 1 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

determining and fitting a circle selected from among closed curves for a plurality of portions of the control object from the captured images, including:

calculating three co planar tangents to observed edges of the control object from the captured images; and

fitting a circle to the control object using at least the three co planar tangents.

7. The system of claim 6 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

for a complex control object model that includes a palm and multiple fingers, applying the determining and fitting a circle actions of claim 6 to construct multiple fingers of control object appendages; and

fitting cross sections of a palm to observed edges of the palm as captured in the captured images.

8. The system of claim 6 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying the determining and fitting a circle actions of claim 6 over time; and

calculating motion of the control object over time based on differences between modeled locations of the control object.

9. The system of claim 7 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying the determining and fitting a circle and fitting cross sections actions of claim 7 over time; and

calculating motion of a complex control object over time based on differences between modeled locations of the complex control object.

10. A non-transitory computer readable medium storing a plurality of instructions for programming one or more processors, which instructions, when executed by one or more processors, implement actions including:

receiving a result of analyzing a gesture;

interpreting as an instruction the result of analyzing a gesture; wherein the result of analyzing a gesture is obtained from another program executing on a processor from analysis of differences in positions of fit closed curves fit to observed edges of a control object thereby tracking motion of the control object while making a gesture in a 3D space including repeatedly:

obtaining captured images of a control object moving in 3D space captured from at least two geometrically distinct predetermined vantages;

calculating observed edges of the control object from the captured images;

fitting closed curves to the observed edges of the control object as captured in the captured images by selecting a closed curve from a family of similar closed curves that fit the observed edges of the control object as captured using an assumed parameter; and

whenever the control object is a complex control object that includes a palm and multiple fingers, applying actions including obtaining captured images, calculating observed edges, and fitting closed curves actions to construct multiple fingers of control object appendages; and

fitting cross sections of a palm to observed edges of a palm as captured in the captured images.

11. The non-transitory computer readable medium of claim 10 ,

wherein one or more fitted parameters of a first fitted closed curve are substituted for one or more of the observed edges and the assumed parameter when fitting an adjacent second closed curve.

12. The non-transitory computer readable medium of claim 10 , wherein a first fitted closed curve is used to filter fits of additional closed curves to contiguous cross-sections.

13. The non-transitory computer readable medium of claim 10 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying actions including obtaining captured images, calculating observed edges, and fitting closed curves actions of claim 10 overtime; and

calculating motion of the control object over time based on differences between modeled locations of the control object.

14. The non-transitory computer readable medium of claim 12 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying actions including obtaining captured images, calculating observed edges, fitting closed curves and using a first fitted closed curve to filter fits of additional closed curves actions of claim 12 overtime; and

calculating motion of a complex control object over time based on differences between modeled locations of a complex control object.

15. The non-transitory computer readable medium of claim 10 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

determining and fitting a circle selected from among closed curves in the family of similar closed curves for a plurality of portions of the control object from the captured images, including:

calculating three co-planar tangents to observed edges of the control object from the captured images; and

fitting a circle to the control object using at least the three co-planar tangents.

16. The non-transitory computer readable medium of claim 15 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

for a complex control object model that includes a palm and multiple fingers, applying the determining and fitting a circle actions of claim 15 to construct multiple fingers of control object appendages; and

fitting cross sections of a palm to observed edges of the palm as captured in the images.

17. The non-transitory computer readable medium of claim 15 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying the determining and fitting a circle actions of claim 15 over time; and

calculating motion of the control object over time based on differences between modeled locations of the control object.

18. The non-transitory computer readable medium of claim 16 , wherein tracking motion of the control object while making a gesture in a 3D space further includes:

repeatedly applying the determining and fitting a circle and fitting cross sections actions of claim 16 overtime; and

calculating motion of a complex control object over time based on differences between modeled locations of a complex control object.

19. A method for executing a gesture command, the method including:

receiving a result of analyzing a gesture;

interpreting as an instruction the result of analyzing a gesture; wherein the result of analyzing a gesture is obtained from another program executing on a processor from analysis of differences in positions of fit closed curves fit to observed edges of a control object to track motion of the control object while making a gesture in a 3D space including repeatedly:

obtaining captured images of a control object moving in 3D space captured from at least two geometrically distinct predetermined vantages;

calculating observed edges of the control object from the captured images;

fitting closed curves to the observed edges of the control object as captured in the captured images by selecting a closed curve from a family of similar closed curves that fit the observed edges of the control object as captured using an assumed parameter; and

whenever the control object is a complex control object that includes a palm and multiple fingers, applying actions including obtaining captured images, calculating observed edges, and fitting closed curves to construct multiple fingers of control object appendages; and

fitting cross sections of a palm to observed edges of a palm as captured in the captured images.