Deep Learning-Based Classification and Reconstruction of Residential Scenes From Large-Scale Point Clouds

作者:Zhang, LQ (Zhang, Liqiang)[ 1 ] ; Zhang, L (Zhang, Liang)[ 2 ]

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

卷: 56  期: 4  頁: 1887-1897

DOI: 10.1109/TGRS.2017.2769120

出版年: APR 2018

文獻(xiàn)類型:Article

摘要

The reconstruction of urban buildings from large-scale airborne laser scanning point clouds is an important research topic in the geoscience field. Large-scale urban scenes usually contain a large number of object categories and many overlapped or closely neighboring objects, which poses great challenges for classifying and modeling buildings from these data sets. In this paper, we propose a deep reinforcement learning framework that integrates a 3-D convolutional neural network, a deep Q-network, and a residual recurrent neural network for the efficient semantic parsing of large-scale 3-D point clouds. The proposed framework provides an end-to-end automatic processing method that maps the raw point cloud to the classification results of the given categories. After obtaining the building classes, we utilize an edge-aware resampling algorithm to consolidate the point set with noise-free normals and clean preservation of sharp features. Finally, 2.5-D dual contouring, which is a data-driven approach, is introduced to generate urban building models from the consolidated point clouds. Our method can generate lightweight building models with arbitrarily shaped roofs while preserving the verticality of connecting walls.

通訊作者地址: Zhang, LQ (通訊作者)

Beijing Normal Univ, Fac Geog Sci, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China.

地址:

[ 1 ] Beijing Normal Univ, Fac Geog Sci, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China

[ 2 ] Shi Jiazhuang Tiedao Univ, Sch Civil Engn, Shijiazhuang 050043, Hebei, Peoples R China