| 摘要 |
<p>Human machine interaction (HMI) via gesture pointing actions with particular relevance to use within a moving vehicle, determining an intended target of an object (e.g. a finger or stylus). A location of the object is determined at time intervals, and a metric associated with each of the targets. The metric is indicative of a respective target being the intended target of the object. The metric is determined based upon a model and the location of the object at the plurality of time intervals, and may determine the trajectory of the object. A Bayesian reasoning process is used to determine the intended target from the plurality of targets based on the metric associated with each of the plurality of targets. The intended target may be an item on a graphical user interface (GUI) or a physical control. The model may be a Bayesian intentionality prediction model, nearest neighbour model, a linear or nonlinear destination reversion model, a equilibrium reverting model or mean reverting diffusion model. Environmental information (e.g. indicating the acceleration of an associated vehicle) may also be received and used as in the model.</p> |
