基于天际线识别的无人机实时姿态角估计

Real-time attitude angle estimation for unmanned aerial vehicle based on skyline detection

以无人机天际线识别为背景,提出了一种准确、实时的天际线识别算法,并由此估计姿态角。在结合实际情况的基础上,对天际线建立能量泛函模型,利用变分原理推出相应偏微分方程。在实际应用中出于对实时性的考虑,引入直线约束对该模型进行简化,然后利用由粗到精的思想识别天际线。首先,对图像预处理并垂直剖分,然后利用简化的水平直线模型对天际线进行粗识别,通过拟合获得天际线粗识别结果,最后在基于梯度和区域混合开曲线模型约束下精确识别天际线,并由此估计无人机滚动和俯仰姿态角。实验结果表明,该算法对天际线识别具有较好的鲁棒性、准确性和实时性。

This paper presents an accurate, real-time skyline detection algorithm for Unmanned Aerial Vehicle （UAV）. On the basis of the actual situation, a functional model of skyline energy is firstly established. In practical application, the linear constraint is analyzed to simplify the model to reduce computing time, and then using coarseto-fine idea to extract the skyline. The rough local skyline is detected by a group of short horizon lines, and then the rough skyline is fitted by the rough local skylines. Finally the gradient based model is used to detect the accurate skyline, and the rolling angle of the UAV can be calculated by the final skyline. The results of the experiment show that the skyline detection algorithm has better robustness, accuracy and real-time.