Feature recognition and tracking of aircraft tanker and refueling drogue for UAV aerial refueling

This paper describes the results of the analysis of specific `feature detection and recognition´ algorithms within a Machine Vision approach for the problem of aerial refueling for unmanned aerial vehicles. In order to precisely obtain the center of the features of the aircraft tanker and refueling drogue in the images of vision-based navigation during automated aerial refueling docking, a feature extraction method based on the HSV color space information of images is proposed. The HSV color space is introduced and the features of the aircraft tanker and refueling drogue are made based on the principle of choosing features. By using of least square ellipse fitting, after making color converted, color phase filter, binary and edge detection on images. The feature locations of the aircraft tanker and refueling drogue are precisely obtained and tracked. The experiment shows that the method proposed can not only extract the features accurately but can also calculate their locations in real-time, which provides a more reliable feature extraction and tracking method for vision-based navigation for automated aerial refueling.