KD-Tree-Based Euclidean Clustering for Tomographic SAR Point Cloud Extraction and Segmentation

被引:25
作者
Guo, Ziye [1 ]
Liu, Hui [1 ]
Shi, Hongyin [1 ]
Li, Fang [1 ]
Guo, Xinyu [1 ]
Cheng, Bihui [1 ]
机构
[1] Beijing Univ Civil Engn & Architecture, Dept Automat, Beijing 100044, Peoples R China
基金
中国国家自然科学基金;
关键词
Point cloud compression; Buildings; Synthetic aperture radar; Data mining; Three-dimensional displays; Clustering algorithms; Nearest neighbor methods; Euclidean clustering; KD-Tree; point cloud extraction; point cloud segmentation; SAR point clouds; MORPHOLOGICAL FILTER; REGULARIZATION;
D O I
10.1109/LGRS.2023.3234406
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Tomographic Synthetic Aperture Radar (TomoSAR) has three-dimensional imaging capability. Never- theless, its building structure is full of considerable noise and wrong targets owing to the baseline distribution and the algorithm restrictions. Accordingly, efficiently extracting and segmenting buildings from SAR point clouds with huge data is a critical issue. According to the characteristics of building facade point clouds, the KD-Tree-based Euclidean clustering is introduced as a fast-clustering method for better extracting and segmenting individual building facades. At first, a simple morphological filter (SMRF) is utilized to identify the ground and non-ground point clouds. The building facades are then extracted from the non-ground point clouds based on density information. Subsequently, the KD-Tree-based Euclidean clustering method denoises the building facades and segments them into individual facades. Finally, a second Euclidean clustering is performed for each of these facades to denoise them again. Experimental results indicate that the presented approach can prepare accurate and efficient extraction and segmentation results for complex urban scenes.
引用
收藏
页数:5
相关论文
共 21 条
[1]   An optimal algorithm for approximate nearest neighbor searching in fixed dimensions [J].
Arya, S ;
Mount, DM ;
Netanyahu, NS ;
Silverman, R ;
Wu, AY .
JOURNAL OF THE ACM, 1998, 45 (06) :891-923
[2]  
Arya S., 1993, PROC DATA COMPRESS, P1
[3]   Three-Dimensional SAR Focusing From Multipass Signals Using Compressive Sampling [J].
Budillon, Alessandra ;
Evangelista, Annarita ;
Schirinzi, Gilda .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (01) :488-499
[4]  
D'Hondt O, 2013, 2013 JOINT URBAN REMOTE SENSING EVENT (JURSE), P206, DOI 10.1109/JURSE#.2013.6550701
[5]   A Comprehensive Automated 3D Approach for Building Extraction, Reconstruction, and Regularization from Airborne Laser Scanning Point Clouds [J].
Dorninger, Peter ;
Pfeifer, Norbert .
SENSORS, 2008, 8 (11) :7323-7343
[6]  
Gnlta F., 2020, Int. J. Environ. Geoinform, P165
[7]   EXTRACTION OF POINTS OF INTEREST FROM SAR TOMOGRAMS [J].
Guillaso, Stephane ;
D'Hondt, Olivier ;
Hellwich, Olaf .
2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, :471-474
[8]   DBSCAN-based point cloud extraction for Tomographic synthetic aperture radar (TomoSAR) three-dimensional (3D) building reconstruction [J].
Guo, Ziye ;
Liu, Hui ;
Pang, Lei ;
Fang, Li ;
Dou, Wenna .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2021, 42 (06) :2327-2349
[9]  
Muja M., 2009, PROC INT C COMPUT VI, P1
[10]   Signal Recovery From Incomplete and Inaccurate Measurements Via Regularized Orthogonal Matching Pursuit [J].
Needell, Deanna ;
Vershynin, Roman .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2010, 4 (02) :310-316