期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2009
卷号：XXXVIII-3/W4
页码：59-64
出版社：Copernicus Publications
摘要：3D object extraction is one of the main interests and has lots of applications in photogrammetry and computer vision. In recentyears, airborne laser-scanning has been accepted as an effective 3D data collection technique for extracting spatial object modelssuch as digital terrain models (DTM) and building models. Data clustering, also known as unsupervised learning is one of the keytechniques in object extraction and is used to understand structure of unlabeled data. Classical clustering methods such as k-meansattempt to subdivide a data set into subsets or clusters. A large number of recent researches have attempted to improve theperformance of clustering. In this paper, the boost-clustering algorithm which is a novel clustering methodology that exploits thegeneral principles of boosting is implemented and evaluated on features extracted from LiDAR data. This method is a multiclusteringtechnique in which At each iteration, a new training set is created using weighted random sampling from the originaldataset and a simple clustering algorithm such as k-means is applied to provide a new data partitioning. The final clustering solutionis produced by aggregating the weighted multiple clustering results. This clustering methodology is used for the analysis of complexscenes in urban areas by extracting three different object classes of buildings, trees and ground, using LiDAR datasets. Experimentalresults indicate that boost clustering using k-means as its underlying training method provides improved performance and accuracycomparing to simple k-means algorithm
关键词：LIDAR; Feature; Object; Extraction; Training; Fusion; Urban; Building
