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 to analyze differences in positions of fit closed curves fit to observed edges of a control object to enable 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;

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

fitting closed curves to the observed edges of the control object, including control object appendages for multiple portions of any complex control objects, 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

using fitted closed curves to construct a complex control object from multiple portions of any complex control objects and one or more of control object appendages appended thereto.

2 . The system of claim 1 , wherein the complex control object is a hand, and further comprising: fitting cross sections of a palm to observed edges of a palm and cross sections of multiple fingers to fingers attached to the palm to represent the complex control object as captured in the captured images.

3 . 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.

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

5 . 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 over time; and

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

6 . The system of claim 4 , 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 over time; and

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

7 . 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.

8 . The system of claim 7 , 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 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.

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 actions over time; and

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

10 . The system of claim 8 , 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 over time; and

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

11 . A non-transitory computer readable medium storing a plurality of instructions for analyzing differences in positions of fit closed curves fit to observed edges of a control object to enable tracking motion of the control object while making a gesture in a 3D space, which instructions, when executed by one or more processors, implement actions including repeatedly:

obtaining captured images of a control object moving in 3D space;

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

fitting closed curves to the observed edges of the control object, including control object appendages for multiple portions of any complex control objects, 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

using fitted closed curves to construct a complex control object from multiple portions of any complex control objects of control object appendages appended thereto.

12 . The non-transitory computer readable medium of claim 11 , wherein the complex control object is a hand, and further comprising: fitting cross sections of a palm to observed edges of a palm and cross sections of multiple fingers to fingers attached to the palm to represent the complex control object as captured in the captured images.

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

14 . The non-transitory computer readable medium of claim 11 , wherein a first fitted closed curve is used to filter fits of additional closed curves to contiguous cross-sections.

15 . The non-transitory computer readable medium of claim 11 , 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 over time; and

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

16 . The non-transitory computer readable medium of claim 14 , 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 overtime; and

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

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

18 . The non-transitory computer readable medium of claim 17 , 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 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.

19 . The non-transitory computer readable medium of claim 17 , 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 over time; and

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

20 . The non-transitory computer readable medium of claim 18 , 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 overtime; and

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

21 . A method for determining a gesture command 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;

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

fitting closed curves to the observed edges of the control object, including control object appendages for multiple portions of any complex control objects, 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

using fitted closed curves to construct a complex control object from multiple portions of any complex control objects and one or more of control object appendages appended thereto.

22 . The method of claim 21 , wherein the complex control object is a hand, and further comprising: fitting cross sections of a palm to observed edges of a palm and cross sections of multiple fingers to fingers attached to the palm to represent the complex control object as captured in the captured images.