Classification of raw LiDAR point cloud using point-based methods with spatial features for 3D building reconstruction

被引:14
|
作者
Yastikli N. [1 ]
Cetin Z. [1 ]
机构
[1] Department of Geomatics Engineering, Civil Engineering Faculty, YTU, 34210 Davutpasa Campus, Esenler, Istanbul
关键词
3D city model; Building reconstruction; Classification; LiDAR; Point cloud;
D O I
10.1007/s12517-020-06377-5
中图分类号
学科分类号
摘要
Building extraction from light detection and ranging (LiDAR) data for 3-dimensional (3D) reconstruction requires accurately classified LiDAR points. In recent years, approaches developed for the classification mostly based on gridded LiDAR data. In the gridding process of LiDAR data, there is a characteristic point loss which results in reduced height accuracy. The effect of such loss can be eliminated using classified raw LiDAR data. In this study, an automatic point-based classification approach for raw LiDAR data classification with spatial features has been proposed for 3D building reconstruction. Using spatial features, the hierarchical rules have been determined. The spatial features, such as height, the local environment, and multi-return, of the LiDAR points were analyzed, and every single LiDAR points automatically assigned to the classes based on these features. The proposed classification approach based on raw LiDAR data had an overall accuracy of 79.7% in the test site located in Istanbul, Turkey. Finally, 3D building reconstruction was performed using the results of the proposed automatic point-based classification approach. © 2021, Saudi Society for Geosciences.
引用
收藏
相关论文
共 50 条
  • [1] 3D Building Scene Reconstruction Based on 3D LiDAR Point Cloud
    Yang, Shih-Chi
    Fan, Yu-Cheng
    2017 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW), 2017,
  • [2] 3D Building Reconstruction Using Dense Photogrammetric Point Cloud
    Malihi, S.
    Zoej, M. J. Valadan
    Hahn, M.
    Mokhtarzade, M.
    Arefi, H.
    XXIII ISPRS CONGRESS, COMMISSION III, 2016, 41 (B3): : 71 - 74
  • [3] 3D LiDAR-Based Point Cloud Map Registration Using Spatial Location of Visual Features
    Shin, Minhwan
    Kim, Jaeseung
    Jeong, Jongmin
    Park, Jin Bae
    2017 2ND INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION ENGINEERING (ICRAE), 2017, : 373 - 378
  • [4] Methods for LiDAR point cloud classification using local neighborhood statistics
    Kim, Angela M.
    Olsen, Richard C.
    Kruse, Fred A.
    LASER RADAR TECHNOLOGY AND APPLICATIONS XVIII, 2013, 8731
  • [5] PEMCNet: An Efficient Multi-Scale Point Feature Fusion Network for 3D LiDAR Point Cloud Classification
    Zhao, Genping
    Zhang, Weiguang
    Peng, Yeping
    Wu, Heng
    Wang, Zhuowei
    Cheng, Lianglun
    REMOTE SENSING, 2021, 13 (21)
  • [6] A Hierarchical Approach for Point Cloud Classification With 3D Contextual Features
    Feng, Chen-Chieh
    Guo, Zhou
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 5036 - 5048
  • [7] Evaluation of LiDAR-Derived Features Relevance and Training Data Minimization for 3D Point Cloud Classification
    Morsy, Salem
    Shaker, Ahmed
    REMOTE SENSING, 2022, 14 (23)
  • [8] Multiview 3D Reconstruction and Human Point Cloud Classification
    Nasab, Sarah Ershadi
    Kasaei, Shohreh
    Sanaei, Esmaeil
    Ossia, Ali
    Mobini, Majid
    2014 22ND IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2014, : 1119 - 1124
  • [9] CLASSIFICATION OF LiDAR DATA WITH POINT BASED CLASSIFICATION METHODS
    Yastikli, N.
    Cetin, Z.
    XXIII ISPRS CONGRESS, COMMISSION III, 2016, 41 (B3): : 441 - 445
  • [10] LiDAR attribute based point cloud labeling using CNNs with 3D convolution layers
    Diaz-Medina, Miguel
    Fuertes, Jose M.
    Segura-Sanchez, Rafael J.
    Lucena, Manuel
    Ogayar-Anguita, Carlos J.
    COMPUTERS & GEOSCIENCES, 2023, 180