Computer vision in interactive robotics

摘要

Computer vision provides many opportunities for novel man‐machine interfaces. Pointing and face gestures can be used as a simple, passive means of interfacing with computers and robots. We describe two novel algorithms to track the position and orientation of the user’s hand or face in video images. This information is used to determine where the hand or face is pointing. This can be used in interactive robotics to allow a user with manipulation disabilities or working in hazardous environments to guide a robot manipulator to pick up a simple object of interest.