王震等:A Multiscale and Hierarchical Feature Extraction Method for Terrestrial Laser Scanning Point Cloud Classification
被阅读 1087 次
2015-10-20
A Multiscale and Hierarchical Feature Extraction Method for Terrestrial Laser Scanning Point Cloud Classification
作者:Wang, Z (Wang, Zhen)[ 1 ] ; Zhang, LQ (Zhang, Liqiang)[ 1 ] ; Fang, T (Fang, Tian)[ 2 ] ; Mathiopoulos, PT (Mathiopoulos, P. Takis)[ 4,5 ] ; Tong, XH (Tong, Xiaohua)[ 6 ] ; Qu, HM (Qu, Huamin)[ 3 ] ; Xiao, ZQ (Xiao, Zhiqiang)[ 1 ] ; Li, F (Li, Fang)[ 1 ] ; Chen, D (Chen, Dong)[ 7 ]
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷: 53  期: 5  页: 2409-2425
DOI: 10.1109/TGRS.2014.2359951
出版年: MAY 2015
 
摘要
The effective extraction of shape features is an important requirement for the accurate and efficient classification of terrestrial laser scanning (TLS) point clouds. However, the challenge of how to obtain robust and discriminative features from noisy and varying density TLS point clouds remains. This paper introduces a novel multiscale and hierarchical framework, which describes the classification of TLS point clouds of cluttered urban scenes. In this framework, we propose multiscale and hierarchical point clusters (MHPCs). In MHPCs, point clouds are first resampled into different scales. Then, the resampled data set of each scale is aggregated into several hierarchical point clusters, where the point cloud of all scales in each level is termed a point-cluster set. This representation not only accounts for the multiscale properties of point clouds but also well captures their hierarchical structures. Based on the MHPCs, novel features of point clusters are constructed by employing the latent Dirichlet allocation (LDA). An LDA model is trained according to a training set. The LDA model then extracts a set of latent topics, i.e., a feature of topics, for a point cluster. Finally, to apply the introduced features for point-cluster classification, we train an AdaBoost classifier in each point-cluster set and obtain the corresponding classifiers to separate the TLS point clouds with varying point density and data missing into semantic regions. Compared with other methods, our features achieve the best classification results for buildings, trees, people, and cars from TLS point clouds, particularly for small and moving objects, such as people and cars.
 
通讯作者地址: Wang, Z (通讯作者)
Beijing Normal Univ, Sch Geog, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China.
地址:
[ 1 ] Beijing Normal Univ, Sch Geog, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China
[ 2 ] Hong Kong Univ Sci & Technol, Kowloon, Hong Kong, Peoples R China
[ 3 ] Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Kowloon, Hong Kong, Peoples R China
[ 4 ] Natl Observ Athens, Inst Astron Astrophys Space Applicat & Remote Sen, Athens 14536, Greece
[ 5 ] Univ Athens, Dept Informat & Telecommun, Athens 15784, Greece
[ 6 ] Tongji Univ, Sch Surveying & Geoinformat, Shanghai 200092, Peoples R China
[ 7 ] Nanjing Forestry Univ, Coll Civil Engn, Nanjing 210037, Jiangsu, Peoples R China