Structural target recognition algorithm for visual guidance of small unmanned helicopters

In this paper we present a vision based guidance approach for small unmanned helicopters. The approach is integrated with Hu invariant moments based structural target recognition algorithm for visual acquisition of the target (a helipad) and a guidance model for locating the target. A color filter is designed to eliminate noises from the image by using HSL model. The improved structural target recognition algorithm can work robustly under the condition that the image is distorted by perspective projection. Besides, a visual guidance model is designed and implemented to locate the target accurately. With the help of the visual guidance, small unmanned helicopters can land on the target automatically. Finally, experiments are carried out to test the effectiveness and robustness of our algorithms.