Theme section 'Urban object detection and 3D building reconstruction'

摘要

The automatic extraction of topographic objects from aerial sensor data has been a focus of research in photogrammetry, remote sensing and computer vision for many years. Urban object extraction is still an active field of research, with the focus shifting to detailed representations of objects, to using data from new sensors, or to advanced processing techniques. The prospects for success have been improved by the availability of data from digital aerial cameras and multiple-pulse laser scanners. Relevant tasks in this context include the detection of objects such as buildings, roads, trees and cars in the sensor data and the 3D reconstruction of buildings. Despite the enormous efforts spent, the problem cannot yet be considered to be solved. One problem that has hampered progress is a lack of standard data sets for evaluating object extraction results, with the consequence that the outcomes of different approaches can usually not be compared experimentally.