Autonomous dirigibles - aerial robots that are a blimp controlled by computer based on information gathered by sensors - are a new and promising research field in Robotics, offering several original work opportunities. One of them is the study of visual navigation, that would allow an autonomous dirigible to follow precise trajectories based on environmental visual information imaged by on-board cameras. The first step in the direction of the developing of such a capacity is the creation of a Computer Vision system able to supply to the autonomous dirigible its position and orientation in tridimensional space from the acquired images. This project describes such a system, capable of estimating position and orientation from images of visual beacons - objects with known geometrical properties and recognizable by the system. Experimental results showing the correct and efficient functioning of the system are shown and have your implications and future possibilities discussed.