Systems and methods of locating a control object appendage in three dimensional (3D) space
AssigneeUltrahaptics IP Two Limited
InventorDavid S. Holz
Life of this patent
Estimating the term…
Abstract
Methods and systems for capturing motion and/or determining the shapes and positions of one or more objects in 3D space utilize cross-sections thereof. In various embodiments, images of the cross-sections are captured using a camera based on reflections therefrom or shadows cast thereby.
Claims16
A system of 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:
- capturing images of a control object moving in 3D space using cameras having 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 images by selecting the closed curve from a family of similar closed curves that fit the observed edges of the control object as captured using an assumed parameter;
- substituting one or more fitted parameters of a first fitted closed curve for one or more of the observed edges and the assumed parameter when fitting an adjacent second closed curve;
- for a complex control object model that includes a palm and multiple fingers, applying the capturing images, calculating observed edges, fitting closed curves and substitute one or more fitted parameters 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 images;
- repeatedly capturing, calculating, and fitting closed curves to the observed edges of the control object as the control object moves in the 3D space;
- and
- analyzing differences in the positions of the fit closed curves to track motion of the control object while making a gesture in the 3D space;
- and
- wherein results of the analyzing the gesture are interpreted as an instruction to some other program executing on a processor.
A non-transitory computer readable medium storing a plurality of instructions for programming one or more processors to locate a control object appendage in three dimensional (3D) space, the instructions, when executed on the one or more processors, implementing actions including:
- capturing images of a control object moving in 3D space using cameras having 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 images by selecting the closed curve from a family of similar closed curves that fit the observed edges of the control object as captured using an assumed parameter;
- substituting one or more fitted parameters of a first fitted closed curve for one or more of the observed edges and the assumed parameter when fitting an adjacent second closed curve;
- for a complex control object model that includes a palm and multiple fingers, applying the capturing images, calculating observed edges, fitting closed curves and substitute one or more fitted parameters 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 images;
- repeatedly capturing, calculating, and fitting closed curves to the observed edges of the control object as the control object moves in the 3D space;
- and
- analyzing differences in the positions of the fit closed curves to track motion of the control object while making a gesture in the 3D space;
- and
- wherein results of the analyzing the gesture are interpreted as an instruction to some other program executing on a processor.
Dependencies are inferred from the claim text.