Airborne laser scanning technology is primarily perceived as a means for gathering detailed three-dimensional information about the surface and objects on it. It is therefore not surprising that the majority of the laser related research has focused on the detection of the terrain within the point cloud and on distinct surficial objects like building roofs and tree canopies. Nonetheless, the dense 3D data contains information about linear entities, some of which are of subtle form. While some of the efforts have been made into extracting linear elements from laser scanning data, the attention was mostly turned to dominant elements that are very clear and distinct. We present in this paper a model for the detection of linear features of various sizes and magnitudes laser data. Our focus is on the detection of subtle linear elements. We apply the model to detect and extract paleo shorelines that have the form of small ridges. Such fossil shorelines are clear markers of receding lakes and record the annual high and low stands. Results show that ridges of ~20 cm height can be identified and separated from the surrounding features in data. 1.