AUTO-EXTRACTION OF URBAN FEATURES FROM VEHICLE-BORNE LASER DATA

Laser mapping has become quite popular in recent days due to its capability of providing information directly in three dimensions. These days, we observe the emergence of new demands for ‘along-street’ 3-D data. ‘Along-street’ 3-D data provide a real or true visualization of the environment that is different from virtual reality. However, there still lacks a reliable and quick method of acquiring 3-D ‘along-street’ data of the urban area at higher resolution. Most of the vehicle-borne systems developed so far are based on stereo photographs as the main source of data. In order to overcome the problem of acquiring 3-D data in urban area reliably, quickly and at high resolution, we have developed a vehicle-borne laser mapping system (VLMS). The system is equipped with laser scanners and line cameras for data acquisition. The system will assist in building 3-D GIS database of urban areas. In this paper we focus our discussions on auto-extraction of building faces from the laser data captured by VLMS. In an urban area we encounter many different types of features like buildings, roads, utility facilities, vehicles, trees and others. Geo-referenced raw laser data were used for extraction of urban features. The raw laser data were simply point cloud data in 3-D space without any other information like intensity value. We have classified the laser data into various classes like building faces, road surfaces, tunnels, utility poles, vehicles and trees. Our discussions will be basically limited to the extraction of building faces with some explanation on extraction of road surfaces, trees and tunnels.