In this paper, we address the hover flight and speed regulation of a quadrotor rotorcraft to perform autonomous navigation. For this purpose, we have developed a vision system which estimates the altitude, the lateral position and the forward speed of the engine during flights. We show that the visual information allows the construction of control strategies for different kinds of flying modes: hover flight, forward flight at constant speed. A hierarchical control strategy is developed and implemented. The local stabilization of the vehicle is proven. Experimental autonomous flight was successfully achieved which validates the visual algorithm and the control law.