Deep Learning Classification of 2D Orthomosaic Images and 3D Point Clouds for Post-Event Structural Damage Assessment

被引:16
|
作者
Liao, Yijun [1 ]
Mohammadi, Mohammad Ebrahim [1 ]
Wood, Richard L. [1 ]
机构
[1] Univ Nebraska, Dept Civil & Environm Engn, Lincoln, NE 68588 USA
关键词
convolutional neural network; deep learning; transfer learning; point clouds; structural damage assessment; NEURAL-NETWORKS;
D O I
10.3390/drones4020024
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Efficient and rapid data collection techniques are necessary to obtain transitory information in the aftermath of natural hazards, which is not only useful for post-event management and planning, but also for post-event structural damage assessment. Aerial imaging from unpiloted (gender-neutral, but also known as unmanned) aerial systems (UASs) or drones permits highly detailed site characterization, in particular in the aftermath of extreme events with minimal ground support, to document current conditions of the region of interest. However, aerial imaging results in a massive amount of data in the form of two-dimensional (2D) orthomosaic images and three-dimensional (3D) point clouds. Both types of datasets require effective and efficient data processing workflows to identify various damage states of structures. This manuscript aims to introduce two deep learning models based on both 2D and 3D convolutional neural networks to process the orthomosaic images and point clouds, for post windstorm classification. In detail, 2D convolutional neural networks (2D CNN) are developed based on transfer learning from two well-known networks AlexNet and VGGNet. In contrast, a 3D fully convolutional network (3DFCN) with skip connections was developed and trained based on the available point cloud data. Within this study, the datasets were created based on data from the aftermath of Hurricanes Harvey (Texas) and Maria (Puerto Rico). The developed 2DCNN and 3DFCN models were compared quantitatively based on the performance measures, and it was observed that the 3DFCN was more robust in detecting the various classes. This demonstrates the value and importance of 3D datasets, particularly the depth information, to distinguish between instances that represent different damage states in structures.
引用
收藏
页码:1 / 19
页数:19
相关论文
共 50 条
  • [1] Deep Scene Flow Learning: From 2D Images to 3D Point Clouds
    Harbin Engineering University, School of Information and Communication Engineering, Heilongjiang, Harbin
    150001, China
    不详
    150001, China
    不详
    ON
    K1N 6N5, Canada
    [J]. IEEE Trans Pattern Anal Mach Intell, 2024, 1 (185-208):
  • [2] Deep Scene Flow Learning: From 2D Images to 3D Point Clouds
    Xiang, Xuezhi
    Abdein, Rokia
    Li, Wei
    El Saddik, Abdulmotaleb
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (01) : 185 - 208
  • [3] Learning to Match 2D Images and 3D LiDAR Point Clouds for Outdoor Augmented Reality
    Liu, Weiquan
    Lai, Baiqi
    Wang, Cheng
    Bian, Xuesheng
    Yang, Wentao
    Xia, Yan
    Lin, Xiuhong
    Lai, Shang-Hong
    Weng, Dongdong
    Li, Jonathan
    [J]. 2020 IEEE CONFERENCE ON VIRTUAL REALITY AND 3D USER INTERFACES WORKSHOPS (VRW 2020), 2020, : 655 - 656
  • [4] Texture Mapping of 3D Point Clouds with Freely Recorded 2D Images
    Xiang Zhuolong
    Zhang Qican
    Chen Chaowen
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (18)
  • [5] Detection, classification and estimation of individual shapes in 2D and 3D point clouds
    Su, J.
    Srivastava, A.
    Huffer, F. W.
    [J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2013, 58 : 227 - 241
  • [6] Deep Learning for 3D Point Clouds: A Survey
    Guo, Yulan
    Wang, Hanyun
    Hu, Qingyong
    Liu, Hao
    Liu, Li
    Bennamoun, Mohammed
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) : 4338 - 4364
  • [7] Review: Deep Learning on 3D Point Clouds
    Bello, Saifullahi Aminu
    Yu, Shangshu
    Wang, Cheng
    Adam, Jibril Muhmmad
    Li, Jonathan
    [J]. REMOTE SENSING, 2020, 12 (11)
  • [8] Sparse 3D Point Clouds Segmentation Considering 2D Image Feature Extraction with Deep Learning
    Li, Yusheng
    Tian, Yong
    Tian, Jiandong
    [J]. ELEVENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2019), 2019, 11179
  • [9] A Review of Deep Learning Techniques for 3D Reconstruction of 2D Images
    Yuniarti, Anny
    Suciati, Nanik
    [J]. PROCEEDINGS OF 2019 12TH INTERNATIONAL CONFERENCE ON INFORMATION & COMMUNICATION TECHNOLOGY AND SYSTEM (ICTS), 2019, : 327 - 331
  • [10] A Simple Deep Learning Network for Classification of 3D Mobile LiDAR Point Clouds
    Yanjun WANG
    Shaochun LI
    Mengjie WANG
    Yunhao LIN
    [J]. Journal of Geodesy and Geoinformation Science, 2021, 4 (03) : 49 - 59