The classification of airborne lidar data is a relevant task in different disciplines. The information about the geometry and the full waveform can be used in order to classify the 3-D point cloud. In Wadden Sea areas, the classification of lidar data is of main interest for the scientific monitoring of coastal morphology and habitats, but it becomes a challenging task due to flat areas with hardly any discriminative objects. For the classification, we combine a conditional random field framework with a random forest approach. By classifying in this way, we benefit from the consideration of context on the one hand and from the opportunity to utilize a high number of classification features on the other hand. We investigate the relevance of different features for the lidar points in coastal areas as well as for the interaction of neighboring points.