Real-time machine-vision-based position sensing system for UAV aerial refueling

This paper describes the design of a Real Time Machine-Vision (MV) Position Sensing System for the problem of Semi-Autonomous Docking within Aerial Refueling (AR) for Unmanned Aerial Vehicles (UAVs). In this effort, techniques and algorithms have been developed and extensively tested in the MATLAB/Simulink^® Soft Real-Time environment as well as in Linux/RTAI Hard Real-Time environment. The overall MV software performs several tasks, such as the image acquisition from a real camera, the Feature Extraction (FE) from the acquired image, the Detection and Labeling (DAL) of the features, and the tanker-UAV Pose Estimation (PE). A Cyclic Asynchronous Buffer (CAB) mechanism was implemented for inter-process communication among Real Time and Non Real Time processes. The entire sensing system was tested using an 800 MHz PC-104 computer. The results confirmed the feasibility of executing image processing algorithms in real-time using off-the-shelf commercial hardware to obtain reliable relative position and orientation estimations.