ABSTRACT
This chapter examines the automatic recognition of topographic objects and their geometric reconstruction by vectors that can easily be used in Geographical Information Systems or computer-aided design systems. It focuses on the extraction of buildings and roads from Light Detection and Ranging (LiDAR) data, and in the case of buildings also from digital aerial imagery. LiDAR sensors deliver a three dimensional point cloud with the intensity of the returned signal. Compared to aerial imagery, LiDAR has both advantages and disadvantages with respect to automatic object extraction. LiDAR data essentially deliver a Digital Surface Model representing the surface from which the laser pulse is reflected that is trees, terrain surface and buildings. In LiDAR data of a resolution better than or equal to 1 m, roads appear as two-dimensional areas rather than one-dimensional lines; they have width as well as length.