Three Dimensional (3D) Modeling of a Complex Control Object
AssigneeUltrahaptics Limited
InventorKevin A. HOROWITZ
Life of this patent
Estimating the term…
Abstract
The technology disclosed relates to automatically (e.g., programmatically) initializing predictive information for tracking a complex control object (e.g., hand, hand and tool combination, robot end effector) based upon information about characteristics of the object determined from sets of collected observed information. Automated initialization techniques obviate the need for special and often bizarre start-up rituals (place your hands on the screen at the places indicated during a full moon, and so forth) required by conventional techniques. In implementations, systems can refine initial predictive information to reflect an observed condition based on comparison of the observed with an analysis of sets of collected observed information.
Claims20
A method of initializing predictive information that models a complex control object in a three dimensional (3D) sensory space, the method including:
- accessing observed information including a set of contour points corresponding to surface points on a surface of a complex control object in a three dimensional (3D) sensory space;
- sensing an actual position of at least one complex control object in a first reference frame of the 3D sensory space;
- sensing an apparent position of the complex control object, wherein the apparent position sensed is different from the actual position sensed;
- calculating a second reference frame that accounts for apparent position of the complex control object;
- using a transformation that renders the actual position in the first reference frame and the apparent position in the second reference frame into a common reference frame, transforming the actual and apparent positions of the complex control object into the common reference frame, whereby the sensed apparent position is transformed to an actual position and the set of contour points is transformed to a normalized orientation of the control object;
- selecting from a plurality of observed information archetypes, an archetype that represents a pose of the control object in the normalized orientation;
- and
- initializing predictive information that models the complex control object from initialization parameters associated with the archetype selected.
A non-transitory computer readable medium having instructions to initialize predictive information that models a complex control object in a three dimensional (3D) sensory space stored thereon, which instructions when executed by a processor, perform actions including:
- accessing observed information including a set of contour points corresponding to surface points on a surface of a complex control object in a three dimensional (3D) sensory space;
- sensing an actual position of at least one complex control object in a first reference frame of the 3D sensory space;
- sensing an apparent position of the complex control object, wherein the apparent position sensed is different from the actual position sensed;
- calculating a second reference frame that accounts for apparent position of the complex control object;
- using a transformation that renders the actual position in the first reference frame and the apparent position in the second reference frame into a common reference frame, transforming the actual and apparent positions of the complex control object into the common reference frame, whereby the sensed apparent position is transformed to an actual position and the set of contour points is transformed to a normalized orientation of the control object;
- selecting from a plurality of observed information archetypes, an archetype that represents a pose of the control object in the normalized orientation;
- and
- initializing predictive information that models the complex control object from initialization parameters associated with the archetype selected.
A system including:
- an optical sensor;
- a processor;
- and a memory storing instructions to initialize predictive information that models a complex control object in a three dimensional (3D) sensory space, which instructions when executed by the processor perform:
- accessing observed information including a set of contour points corresponding to surface points on a surface of a complex control object in a three dimensional (3D) sensory space;
- sensing an actual position of at least one complex control object in a first reference frame of the 3D sensory space;
- sensing an apparent position of the complex control object, wherein the apparent position sensed is different from the actual position sensed;
- calculating a second reference frame that accounts for apparent position of the complex control object;
- using a transformation that renders the actual position in the first reference frame and the apparent position in the second reference frame into a common reference frame, transforming the actual and apparent positions of the complex control object into the common reference frame, whereby the sensed apparent position is transformed to an actual position and the set of contour points is transformed to a normalized orientation of the control object;
- selecting from a plurality of observed information archetypes, an archetype that represents a pose of the control object in the normalized orientation;
- and
- initializing predictive information that models the complex control object from initialization parameters associated with the archetype selected.
Dependencies are inferred from the claim text.