A vision-based line following strategy for an autonomous UAV

Unmanned Aerial Vehicles (UAVs) are versatile machines that can be used in a variety of applications, such as automatic monitoring of crops and water channels, pest detection, animal counting etc. Autonomous flying is a desirable feature for UAVs, especially for those that are frequently used in monitoring and inspection of large areas. In some situations, global positioning system signal is not guaranteed or its error might be too large, hence other methods of local position feedback are required. In such a context, we present the development of a vision-based line following strategy for an autonomous UAV. The proposed system is intended to guide an autonomous UAV to follow water channel margins, crop lines and other similar patterns, to support automatic monitoring and inspection activities. We present the design of a nonlinear path following controller and we show that the resulting closed-loop system is stable in the sense of Lyapunov. We also propose a visual-based line detection algorithm that it is capable of detecting the average position and orientation of the main lines on the image frames captured by the UAV downwards facing camera. Finally, we present and discuss some experimental results that show the good performance of the proposed system.