A cluster-based morphological filter for geospatial data analysis

LIDAR (Light Detection and Ranging) is a widely used technology to measure terrain properties and topographic mapping nowadays. Many filtering methods have been developed to process the geospatial data generated by LIDAR to generate bare earth digital terrain models. Among these methods, mathematical morphological filtering is a very effective and efficient method to separate ground and non-ground objects from LIDAR data. This method can achieve ideal results in the flat terrain, while it is not working very well in the undulating and complex terrain with large non-ground objects. The reason is that it would remove ground terrain objects along with filtering large size non-ground objects when using a large filtering window size. Especially in the mountainous terrain, it would cause the hill cut-off problem, which is a common problem for morphological filters. In this paper, a cluster-based morphological filter is proposed to improve the progressive morphological filter and make it work better on more undulating and complex terrain types. The filtering results demonstrate that the proposed method is able to effectively preserve terrain ground objects and remove large non-ground objects.