INFERRING SPATIAL OBJECT DESCRIPTIONS FROM SPATIAL GESTURES

摘要

According to the present invention, three-dimensional spatial image data associated with at least one arm motion of an actor based on the free-form motion of at least one hand can be received, based on the natural gestural motion of at least one hand of the actor. Based on the received 3D spatial image data, a plurality of sequential 3D spatial representations, each containing 3D spatial map data corresponding to the 3D attitude and position of at least one hand in an instance of sequential time during freeform motion, is determined . A model time value representing the number of instances of time consumed by at least one hand occupying a plurality of 3D spatial areas during freeform motion and progressively integrating the 3D spatial map data contained within the determined sequential 3D spatial representation, Based on the comparison of the values, an integrated 3D model can be generated through the spatial object processor.