Measuring Visibility using Atmospheric Transmission and Digital Surface Model

Publication from Digital

Jean Philippe Andreu and Stefan Mayer and Karlheinz Gutjahr, Harald Ganster

Proceedings of The 39th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM) , 1/2015


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 automatically derive visibility measures by means of image processing. It first exploits image based estimation of the atmospheric transmission describing the portion of the light that is not scattered by atmospheric phenomena (e.g., haze, fog, smoke) and reaches the camera. Once the atmospheric transmission is estimated, a 3D representation of the vicinity (digital surface model: DMS) is used to compute depth measurements for the haze-free pixels and then derive a global visibility estimation for the airport. Results on foggy images demonstrate the validity of the proposed method.