The problem of vision-based road following using a quad-rotor is addressed. The objective consists of estimating and tracking a road without a priori knowledge of such path. For thispurpose, two operational regions are defined: one for the case when the road is detected, and the other one for when it is not. A switching between imaging and inertial sensors measurements allows estimating the required vehicle's parameters in both regions. Also, for dealing with both aforementioned cases, a switching control strategy which stabilizes the vehicle's lateral position is proposed. The performance of the proposed switching methodologies is tested in real time experiments.