Bridge detection in airborne laser scanner data

In a landscape bridges are ambiguous features in that they are extensions of the bare earth but they are also man made. Therefore, in a Digital Terrain Model (DTM) generation, depending on application it is necessary to keep or remove bridges. For this reason they have to be detected explicitly. A geometric bridge detection algorithm is proposed that is based on the idea that features can be detected in a landscape based on cross-sections (profiles) in a landscape. The topological information contained in the cross-sections are used to identify seed bridge points. The seed bridge points are then used to detect individual bridges. The bridge detection algorithm is novel in that the algorithm is blind to the shape of a bridge and is adaptable to different bridge designs. Therefore, bridges need not have parallel edges or uniform width. Furthermore, bridges can curve, split into parts, and contain holes. The bridge detection algorithm has been tested on various data sets and found to work very well in detecting bridges. (C) 2006 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V, All rights reserved.