Smart wheelchair controlled by head gesture based on vision

Abstract

Head Gesture Recognition has been developed using a variety of devices that mostly contain a sensor, such as a gyroscope or an accelerometer, for determining the direction and magnitude of movement. This paper explains how to control a smart wheelchair using Head-Gesture Recognition based on Computer Vision. Using the Haar Cascade Algorithm Method for determining the position of the face and nose, determining the order of the head gesture would be easy to do. We classify head gestures to become four, namely: Look down, Look up/center, Turn right and Turn left. The four gesture information is used to control the smart wheelchair as Brake, Accelerate, Turn right and Turn left. The experiment result shows that our system has successfully controlled the smart wheelchair using head gestures.