Dynamically Directing Interpretation of Input Data Based on Contextual Information

摘要

Technologies are described herein for dynamically directing an interpretation of input data based on contextual information associated with a virtual environment. According to one aspect of the disclosure, a computing device and a camera operate in concert to capture and interpret gestures of a human target to control a virtual skeleton, which may be visually represented as an avatar. Embodiments disclosed herein utilize filtering parameters in the interpretation of input data representing a state of the human target to generate output data that is used to direct the virtual skeleton and/or the avatar. The filtering parameters may be dynamically adjusted during runtime based on contextual information and other factors to dynamically change the way input data is interpreted. Dynamic adjustment of the filtering parameters during runtime may allow for an interpretation of input data that is more accurately aligned with a scenario presented in the virtual environment.

主权项

1. A computer-implemented method for processing a plurality of input data samples, wherein individual data samples of the plurality of input data samples indicate a state of an input object, and wherein the input object is represented by a virtual object, the computer-implemented method comprising:
associating, at a computing device, one or more weight values with the plurality of input data samples; selecting, at the computing device, a threshold based on a scenario associated with the virtual object; determining, at the computing device, if a product of the one or more weight values associated with the plurality of input data samples meets the threshold; and changing a state of the virtual object, at the computing device, if it is determined that the product of the one or more weight values associated with the plurality of input data samples meets the threshold.