Motion estimation for human-machine interaction

Abstract

Human machine interaction is an evolving research area which deals with interactions with machines that will be as natural as an interaction between humans. Vision based motion estimation can also be said as the interpretation of motions via mathematical algorithms. This system have applications in domains such as sign language translation, virtual environments, smart surveillance, controlling robots, control of machines, medical systems etc. The task is challenging due to the accuracy, further the items in the background or distinct features of the users may make recognition more difficult. In this survey, we address these challenges. We provide an overview of current advances in the field. Further, we discuss limitations and outline promising directions of research. A brief overview of methodologies implemented by earlier researcher on vision based gesture recognition for human machine interaction is discussed here.