Smart Technology for Gesture Recognition Using Accelerometer

Abstract

Patients in hospitals often have to rely on others for assistance. Remote controlled devices can help such people. Our Project presents the implementation of an accelerometer enabled mobile device which can be used by patients to assist them with room maintenance, call for food and medicines, etc. with a simple mobile gesture. The main objective is to develop a low cost device which can be developed/implemented with off the shelf components. The novelty of this device is its low cost. The device can be used and implemented by patients easily. For hand gesture recognition, a HMM (Hidden Markov Model) has been used to model the sequential constraints on the gestures, which increases the recognition accuracy.