Inferring spatial object descriptions from spatial gestures

1. A system comprising:

at least one device processor; and

a machine readable storage device storing executable instructions that, when executed, cause the at least one device processor to:

receive, from one or more cameras, three-dimensional (3-D) spatial image data associated with at least one arm motion of an actor based on free-form movements of at least one hand of the actor, based on natural gesture motions of the at least one hand;

determine a plurality of sequential 3-D spatial representations that each include 3-D spatial map data corresponding to a 3-D posture and position of the at least one hand at sequential instances of time during the free-form movements, based on the received 3-D spatial image data; and

generate an integrated 3-D model based on incrementally aggregating the 3-D spatial map data included in the determined sequential 3-D spatial representations and comparing a threshold time value with model time values indicating numbers of instances of time spent by the at least one hand occupying a plurality of 3-D spatial regions during the free-form movements.

2. The system of claim 1 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine a volume associated with the at least one hand of the actor based on the received 3-D spatial image data;

determine a 3-D representation of the at least one hand in a 3-D virtual map space based on the determined volume; and

determine at least one hand posture based on the 3-D representation of the at least one hand.

3. The system of claim 2 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine whether the at least one hand posture of the at least one hand indicates a 3-D enclosed space, wherein

generating the integrated 3-D model includes:

if it is determined that the enclosed 3-D space is indicated,

activate a plurality of volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to the enclosed space, for sequential instances of time associated with the posture indicating the enclosed space, and

otherwise,

activate a plurality of the volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to a depth, location, and orientation of the at least one hand.

4. The system of claim 2 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine that the at least one hand posture includes one or more of a flat hand posture, a curved hand posture, a hand clinched as a fist, or a hand postured with pinched fingers.

5. The system of claim 1 , wherein the executable instructions, when executed, cause the at least one device processor to:

initiate access to a database including a plurality of database objects, each database object associated with a predefined three-dimensional (3-D) model that simulates an appearance of a predetermined 3-D item;

determine at least one of the predefined 3-D models associated with at least one database object that matches the integrated 3-D model, wherein

the natural gesture motions emulate an appearance of a predetermined three-dimensional (3-D) item.

6. The system of claim 5 , wherein the executable instructions, when executed, cause the at least one device processor to:

obtain an update 3-D model that simulates an appearance of a predefined update 3-D item; and

initiate storage, in the database, of an update database object associated with the update 3-D model.

7. The system of claim 1 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine a volume associated with the at least one hand of the actor based on tracking visible portions of the at least one hand over time, based on the received 3-D spatial image data;

determine a yaw angle of the at least one hand based on a rotation of the tracked visible portions of the one of the hands in a top-down, view, based on the received 3-D spatial image data; and

determine a roll angle and a pitch angle of the at least one hand based on variations in depth values associated with the tracked visible portions.

8. A method comprising:

receiving, from one or more cameras, three-dimensional (3-D) spatial image data associated with at least one arm motion of an actor based on free-form movements of at least one hand of the actor, based on natural gesture motions of the at least one hand;

determining, via at least one device processor, a plurality of sequential 3-D spatial representations that each include 3-D spatial map data corresponding to a 3-D posture and position of the at least one hand at sequential instances of time during the free-form movements, based on the received 3-D spatial image data; and

generating, via at least one device processor, an integrated 3-D model based on incrementally aggregating the 3-D spatial map data included in the determined sequential 3-D spatial representations and comparing a threshold time value with model time values indicating numbers of instances of time spent by the at least one hand occupying a plurality of 3-D spatial regions during the free-form movements.

9. The method of claim 8 , further comprising:

determining a volume associated with the at least one hand of the actor based on the received 3-D spatial image data;

determining a 3-D representation of the at least one hand in a 3-D virtual map space based on the determined volume; and

determining at least one hand posture based on the 3-D representation of the at least one hand.

10. The method of claim 9 , further comprising:

determining, via at least one device processor, whether the at least one hand posture of the at least one hand indicates a 3-D enclosed space, wherein

generating the integrated 3-D model includes:

if it is determined that the enclosed 3-D space is indicated,

activating a plurality of volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to the enclosed space, for sequential instances of time associated with the posture indicating the enclosed space, and

otherwise,

activating a plurality of the volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to a depth, location, and orientation of the at least one hand.

11. The method of claim 9 , further comprising:

determining that the at least one hand posture includes one or more of a flat hand posture, a curved hand posture, a hand clinched as a fist, or a hand postured with pinched fingers.

12. The method of claim 8 , further comprising:

initiating access to a database including a plurality of database objects, each database object associated with a predefined three-dimensional (3-D) model that simulates an appearance of a predetermined 3-D item;

determining, via at least one device processor, at least one of the predefined 3-D models associated with at least one database object that matches the integrated 3-D model, wherein

the natural gesture motions emulate an appearance of a predetermined three-dimensional (3-D) item.

13. The method of claim 12 , further comprising:

obtaining an update 3-D model that simulates an appearance of a predefined update 3-D item; and

initiating storage, in the database, of an update database object associated with the update 3-D model.

14. The method of claim 8 , further comprising:

determining a volume associated with the at least one hand of the actor based on tracking visible portions of the at least one hand over time, based on the received 3-D spatial image data;

determining a yaw angle of the at least one hand based on a rotation of the tracked visible portions of the one of the hands in a top-down view, based on the received 3-D spatial image data; and

determining a roll angle and a pitch angle of the at least one hand based on variations in depth values associated with the tracked visible portions.

15. A computer program product that includes a hardware machine readable storage device storing executable instructions that, when executed, cause at least one device processor to:

receive, from one or more cameras, three-dimensional (3-D) spatial image data associated with at least one arm motion of an actor based on free-form movements of at least one hand of the actor, based on natural gesture motions of the at least one hand;

determine a plurality of sequential 3-D spatial representations that each include 3-D spatial map data corresponding to a 3-D posture and position of the at least one hand at sequential instances of time during the free-form movements, based on the received 3-D spatial image data; and

generate an integrated 3-D model based on incrementally aggregating the 3-D spatial map data included in the determined sequential 3-D spatial representations and comparing a threshold time value with model time values indicating numbers of instances of time spent by the at least one hand occupying a plurality of 3-D spatial regions during the free-form movements.

16. The computer program product of claim 15 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine a volume associated with the at least one hand of the actor based on the received 3-D spatial image data;

determine a 3-D representation of the at least one hand in a 3-D virtual map space based on the determined volume; and

determine at least one hand posture based on the 3-D representation of the at least one hand.

17. The computer program product of claim 16 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine whether the at least one hand posture of the at least one hand indicates a 3-D enclosed space, wherein

generating the integrated 3-D model includes:

if it is determined that the enclosed 3-D space is indicated,

activate a plurality of volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to the enclosed space, for sequential instances of time associated with the posture indicating the enclosed space, and

otherwise,

activate a plurality of the volumized elements associated with portions of the integrated 3-D model that represent a depth, location, and orientation corresponding to a depth, location, and orientation of the at least one hand.

18. The computer program product of claim 16 , wherein the executable instructions, when executed, cause the at least one device processor to:

determine that the at least one hand posture includes one or more of a flat hand posture, a curved hand posture, a hand clinched as a fist, or a hand postured with pinched fingers.

19. The computer program product of claim 15 , wherein the executable instructions, when executed, cause the at least one device processor to:

initiate access to a database including a plurality of database objects, each database object associated with a predefined three-dimensional (3-D) model that simulates an appearance of a predetermined 3-D item;

determine, via the spatial object processor, at least one of the predefined 3-D models associated with at least one database object that matches the integrated 3-D model, wherein

the natural gesture motions emulate an appearance of a predetermined three-dimensional (3-D) item.

20. The computer program product of claim 19 , wherein the executable instructions, when executed, cause the at least one device processor to:

obtain an update 3-D model that simulates an appearance of a predefined update 3-D item; and

initiate storage, in the database, of an update database object associated with the update 3-D model.