System and Method for Identifying Handwriting Gestures In An In-Vehicle Information System

摘要

An in-vehicle information system includes a camera and a controller that accept gesture input. A controller receives frames of video data and generates trajectory data for a movement of a hand in the video data. The controller uses a first hidden Markov model (HMM) to decode a sequence of strokes from the trajectory data, removes a starting and ending stroke to form an edited stroke sequence, and re-normalizes the strokes in the edited stroke sequence. The controller uses a second HMM corresponding to a predetermined set of characters to identify a character corresponding to the re-normalized edited stroke sequence.

主权项

1. An in-vehicle information system configured to receive gesture input comprising:
a first camera configured to generate image data of an interior surface in a vehicle and a hand of an operator in the vehicle that moves on the interior surface; a controller operatively connected to the first camera and at least one component in the in-vehicle information system, the controller being configured to:
receive a plurality of frames of image data from the first camera;identify a location of the hand of the operator in each frame of the plurality of frames;generate trajectory data corresponding to changes in the location of the hand in the plurality of frames;generate a decoded sequence of strokes from the for the hand from the trajectory data with reference to a first hidden Markov model (HMM);remove at least one of a first stroke and a last stroke from the decoded sequence of strokes to generate an edited sequence of strokes;normalize trajectory data associated with each stroke in the edited sequence of strokes;identify a character corresponding to the normalized trajectory data associated with the edited sequence of strokes with reference to a second HMM; andoperate the at least one component in the in-vehicle information system in response to the identified character.