Addressing corner detection issues for machine vision based UAV aerial refueling

Abstract

This paper describes the results of the analysis of specific ‘corner detection’ algorithms within a Machine Vision approach for the problem of aerial refueling for unmanned aerial vehicles. Specifically, the performances of the SUSAN and the Harris corner detection algorithms have been compared. A critical goal of this study was to evaluate the interface of these feature extraction schemes with the successive detection and labeling, and pose estimation schemes in the overall scheme. Closed-loop simulations were performed using a Simulink®-based simulation environment to reproduce docking maneuvers using the US Air Force refueling boom.