A human-machine interface with unmanned aerial vehicles

Many UAV applications rely on a ground-based computer for accomplishing all processing tasks and the power consumed by such systems are a major roadblock when it comes to portability. In this paper we present an efficient and practical human-machine interface with an unmanned aerial vehicle (UAV). One of the main goals of the proposed interface is to be ubiquitous, so we moved all computational load to a mobile device running Android. Through this interface, the UAV responds to both movement and body gestures of the user; moreover, all processing tasks are done efficiently in the mobile device. We describe how we tracked the user throughout the video stream, which techniques we used and how we implemented them in our mobile platform for achieving a good level of performance.