Classification of Tree Species and Standing Dead Trees with Lidar Point Clouds Using Two Deep Neural Networks: PointCNN and 3DmFV-Net

被引:0
|
作者
Maximilian Hell
Melanie Brandmeier
Sebastian Briechle
Peter Krzystek
机构
[1] Esri Deutschland GmbH,Faculty of Plastics Engineering and Surveying
[2] FHWS University of Applied Sciences Würzburg-Schweinfurt,Faculty of Geoinformatics
[3] HM University of Applied Sciences München,undefined
关键词
Classification; Tree species; Dead wood; Lidar; Point clouds; Deep neural networks;
D O I
暂无
中图分类号
学科分类号
摘要
Knowledge about tree species distribution is important for forest management and for modeling and protecting biodiversity in forests. Methods based on images are inherently limited to the forest canopy. Airborne lidar data provide information about the trees’ geometric structure, as well as trees beneath the upper canopy layer. In this paper, the potential of two deep learning architectures (PointCNN, 3DmFV-Net) for classification of four different tree classes is evaluated using a lidar dataset acquired at the Bavarian Forest National Park (BFNP) in a leaf-on situation with a maximum point density of about 80 pts/m2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{2}$$\end{document}. Especially in the case of BFNP, dead wood plays a key role in forest biodiversity. Thus, the presented approaches are applied to the combined classification of living and dead trees. A total of 2721 single trees were delineated in advance using a normalized cut segmentation. The trees were manually labeled into four tree classes (coniferous, deciduous, standing dead tree with crown, and snag). Moreover, a multispectral orthophoto provided additional features, namely the Normalized Difference Vegetation Index. PointCNN with 3D points, laser intensity, and multispectral features resulted in a test accuracy of up to 87.0%. This highlights the potential of deep learning on point clouds in forestry. In contrast, 3DmFV-Net achieved a test accuracy of 73.2% for the same dataset using only the 3D coordinates of the laser points. The results show that the data fusion of lidar and multispectral data is invaluable for differentiation of the tree classes. Classification accuracy increases by up to 16.3% points when adding features generated from the multispectral orthophoto.
引用
收藏
页码:103 / 121
页数:18
相关论文
共 28 条
  • [1] Classification of Tree Species and Standing Dead Trees with Lidar Point Clouds Using Two Deep Neural Networks: PointCNN and 3DmFV-Net
    Hell, Maximilian
    Brandmeier, Melanie
    Briechle, Sebastian
    Krzystek, Peter
    [J]. PFG-JOURNAL OF PHOTOGRAMMETRY REMOTE SENSING AND GEOINFORMATION SCIENCE, 2022, 90 (02): : 103 - 121
  • [2] Classification of objects in the LIDAR point clouds using Deep Neural Networks based on the PointNet model
    Kowalczuk, Zdzislaw
    Szymanski, Karol
    [J]. IFAC PAPERSONLINE, 2019, 52 (08): : 416 - 421
  • [3] Spatial Analysis of Dense LiDAR Point Clouds for Tree Species Group Classification Using Individual Tree Metrics
    Slavik, Martin
    Kuzelka, Karel
    Modlinger, Roman
    Surovy, Peter
    [J]. FORESTS, 2023, 14 (08)
  • [4] Classification of Tree Species as Well as Standing Dead Trees Using Triple Wavelength ALS in a Temperate Forest
    Amiri, Nina
    Krzystek, Peter
    Heurich, Marco
    Skidmore, Andrew
    [J]. REMOTE SENSING, 2019, 11 (22)
  • [5] Urban Tree Species Classification Using UAV-Based Multispectral Images and LiDAR Point Clouds
    Li, Xiaofan
    Wang, Lanying
    Guan, Haiyan
    Chen, Ke
    Zang, Yufu
    Yu, Yongtao
    [J]. JOURNAL OF GEOVISUALIZATION AND SPATIAL ANALYSIS, 2024, 8 (01)
  • [6] Classification of tree forms in aerial LiDAR point clouds using CNN for 3D tree modelling
    Vivek Nanda, Vishnu Mahesh
    Baran, Perver
    Tateosian, Laura
    Nelson, Stacy A. C.
    Hu, Jianxin
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (22) : 7156 - 7186
  • [7] Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees
    Hamraz, Hamid
    Jacobs, Nathan B.
    Contreras, Marco A.
    Clark, Chase H.
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2019, 158 : 219 - 230
  • [8] Data Preparation Impact on Semantic Segmentation of 3D Mobile LiDAR Point Clouds Using Deep Neural Networks
    Kouhi, Reza Mahmoudi
    Daniel, Sylvie
    Giguere, Philippe
    [J]. REMOTE SENSING, 2023, 15 (04)
  • [9] Deep Learning Neural Networks for 3D Point Clouds Shape Classification: A Survey
    Lai, Bing Hui
    Sia, Chun Wan
    Lim, King Hann
    Phang, Jonathan Then Sien
    [J]. 2022 INTERNATIONAL CONFERENCE ON GREEN ENERGY, COMPUTING AND SUSTAINABLE TECHNOLOGY (GECOST), 2022, : 394 - 398
  • [10] Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks
    Mayra, Janne
    Keski-Saari, Sarita
    Kivinen, Sonja
    Tanhuanpaa, Topi
    Hurskainen, Pekka
    Kullberg, Peter
    Poikolainen, Laura
    Viinikka, Arto
    Tuominen, Sakari
    Kumpula, Timo
    Vihervaara, Petteri
    [J]. REMOTE SENSING OF ENVIRONMENT, 2021, 256