Randomized Hough transform-based vision algorithm for small unmanned aerial vehicles using an airbag

Safe landing of small unmanned aerial vehicles (UAVs) is not an easy task due to complex external aiding devices. Likewise external piloting also involves risks of false landings. Hu's moment based vision algorithms that aids automatic landing of UAVs prove to be satisfying regarding speed but lack accuracy and efficiency. This paper proposes Randomized Hough transform (RHT) based vision algorithm for accurate landing of small UAVs employing an inflated bag. Uniqueness of the airbag's color and shape are well exploited for its detection from any viewing angle. Color based detection of the airbag is soon followed by Randomized Hough transform based shape detection. The accuracy of proposed method and Hu's method is tested in a series of flight trials and the results are tabulated.