Comparative Study of Landmark Detection Techniques for Airport Visibility Estimation


Reliable and exact assessment of visibility is essential for safe air traffic. In order to overcome the drawbacks of the currently subjective reports from human observers, we present an approach to utomatically derive visibility measures by means of image processing. It is based on identification of visibility of individual landmarks and compiling an overall visibility range. The methods used are based on concepts of illumination compensation as well as structural (edges) and texture recognition. Validation on individual landmarks showed a reliable performance of 96% correct detections. Furthermore, a solution for compiling the overall visibility report is presented, that resembles the currently used standard in air traffic management.