As one of the most important geo-spatial objects and military establishment, airport is always a key target in fields of
transportation and military affairs. Therefore, automatic recognition and extraction of airport from remote sensing
images is very important and urgent for updating of civil aviation and military application. In this paper, a new
multi-source data fusion approach on automatic airport information extraction, updating and 3D modeling is addressed.
Corresponding key technologies including feature extraction of airport information based on a modified Ostu algorithm,
automatic change detection based on new parallel lines-based buffer detection algorithm, 3D modeling based on gradual
elimination of non-building points algorithm, 3D change detecting between old airport model and LIDAR data, typical
CAD models imported and so on are discussed in detail. At last, based on these technologies, we develop a prototype
system and the results show our method can achieve good effects.