Navigation with Image Tracking for a Quadrotor UAV

In this paper, we use image processing and automatic camera calibration theory to design an unmanned aerial vehicle's image tracking method. The research includes image processing and recognition, automatic camera calibration, and target detection and tracking. After the quadrotor equipped the camera takes off, it can capture the environment image through the camera. And we obtained the parameters acquired from the orientation and distance values of the target through image processing. These parameters are converted by an automatic camera calibration into the control signal outputs for throttle, move and rotation. Those parameters can be used not only to calibrate the flight posture of the rotorcraft, but also to track the target. Experimental results show that the image processing method and automatic camera calibration can control the quadrotor and track the moving target as designed.