Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data

被引:4
作者
Gong, Yulin [1 ,2 ,3 ]
Li, Xuejian [1 ,2 ,3 ]
Du, Huaqiang [1 ,2 ,3 ]
Zhou, Guomo [1 ,2 ,3 ]
Mao, Fangjie [1 ,2 ,3 ]
Zhou, Lv [1 ,2 ,4 ]
Zhang, Bo [1 ,2 ,3 ]
Xuan, Jie [1 ,2 ,3 ]
Zhu, Dien [1 ,2 ,4 ]
机构
[1] Zhejiang A&F Univ, State Key Lab Subtrop Silviculture, Hangzhou 311300, Peoples R China
[2] Zhejiang A&F Univ, Key Lab Carbon Cycling Forest Ecosyst & Carbon Seq, Hangzhou 311300, Peoples R China
[3] Zhejiang A&F Univ, Sch Environm & Resources Sci, Hangzhou 311300, Peoples R China
[4] Beijing Forestry Univ, Coll Forestry, Beijing 100083, Peoples R China
基金
中国国家自然科学基金;
关键词
tree species classifications; unmanned aerial vehicle (UAV); LiDAR; point cloud; intensity frequency; AIRBORNE LIDAR; INDIVIDUAL TREES; NORMALIZATION; PARAMETERS; FEATURES; HEIGHT; SENSOR; STAND;
D O I
10.3390/rs15010110
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The accurate classification of tree species is essential for the sustainable management of forest resources and the effective monitoring of biodiversity. However, a literature review shows that most of the previous unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)-based studies on fine tree species classification have used only limited intensity features, accurately identifying relatively few tree species. To address this gap, this study proposes developing a new intensity feature-intensity frequency-for the LiDAR-based fine classification of eight tree species. Intensity frequency is defined as the number of times a certain intensity value appears in the individual tree crown (ITC) point cloud. In this study, we use UAV laser scanning to obtain LiDAR data from urban forests. Intensity frequency features are constructed based on the extracted intensity information, and a random forest (RF) model is used to classify eight subtropical forest tree species in southeast China. Based on four-point cloud density sampling schemes of 100%, 80%, 50% and 30%, densities of 230 points/m(2), 184 points/m(2), 115 points/m(2) and 69 points/m(2) are obtained. These are used to analyze the effect of intensity frequency on tree species classification accuracy under four different point cloud densities. The results are shown as follows. (1) Intensity frequencies of trees are not significantly different for intraspecies (p > 0.05) values and are significantly different for interspecies (p < 0.01) values. (2) The intensity frequency features of LiDAR can be used to classify different tree species with an overall accuracy (OA) of 86.7%. Acer Buergerianum achieves a user accuracy (UA) of over 95% and a producer accuracy (PA) of over 90% for four density conditions. (3) The OA varies slightly under different point cloud densities, but the sum of correct classification trees (SCI) and PA decreases rapidly as the point cloud density decreases, while UA is less affected by density with some stability. (4) The priori feature selected by mean rank (MR) covers the top 10 posterior features selected by RF. These results show that the new intensity frequency feature proposed in this study can be used as a comprehensive and effective intensity feature for the fine classification of tree species.
引用
收藏
页数:22
相关论文
共 62 条
  • [1] Multi-UAV Routing for Area Coverage and Remote Sensing with Minimum Time
    Avellar, Gustavo S. C.
    Pereira, Guilherme A. S.
    Pimenta, Luciano C. A.
    Iscold, Paulo
    [J]. SENSORS, 2015, 15 (11) : 27783 - 27803
  • [2] Tree Species Classification Using Hyperspectral Imagery: A Comparison of Two Classifiers
    Ballanti, Laurel
    Blesius, Leonhard
    Hines, Ellen
    Kruse, Bill
    [J]. REMOTE SENSING, 2016, 8 (06)
  • [3] Improved k-NN Mapping of Forest Attributes in Northern Canada Using Spaceborne L-Band SAR, Multispectral and LiDAR Data
    Beaudoin, Andre
    Hall, Ronald J. J.
    Castilla, Guillermo
    Filiatrault, Michelle
    Villemaire, Philippe
    Skakun, Rob
    Guindon, Luc
    [J]. REMOTE SENSING, 2022, 14 (05)
  • [4] The Laser Vegetation Imaging Sensor: a medium-altitude, digitisation-only, airborne laser altimeter for mapping vegetation and topography
    Blair, JB
    Rabine, DL
    Hofton, MA
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 1999, 54 (2-3) : 115 - 122
  • [5] Budei BC, 2018, REMOTE SENS ENVIRON, V204, P632, DOI [10.1016/j.rse.2017.09.037, 10.1016]
  • [6] Integrating remote sensing with ecology and evolution to advance biodiversity conservation
    Cavender-Bares, Jeannine
    Schneider, Fabian D.
    Santos, Maria Joao
    Armstrong, Amanda
    Carnaval, Ana
    Dahlin, Kyla M.
    Fatoyinbo, Lola
    Hurtt, George C.
    Schimel, David
    Townsend, Philip A.
    Ustin, Susan L.
    Wang, Zhihui
    Wilson, Adam M.
    [J]. NATURE ECOLOGY & EVOLUTION, 2022, 6 (05) : 506 - 519
  • [7] Modelling lidar-derived estimates of forest attributes over space and time: A review of approaches and future trends
    Coops, Nicholas C.
    Tompalski, Piotr
    Goodbody, Tristan R. H.
    Queinnec, Martin
    Luther, Joan E.
    Bolton, Douglas K.
    White, Joanne C.
    Wulder, Michael A.
    van Lier, Oliver R.
    Hermosilla, Txomin
    [J]. REMOTE SENSING OF ENVIRONMENT, 2021, 260
  • [8] High-Density UAV-LiDAR in an Integrated Crop-Livestock-Forest System: Sampling Forest Inventory or Forest Inventory Based on Individual Tree Detection (ITD)
    Dalla Corte, Ana Paula
    da Cunha Neto, Ernandes M.
    Rex, Franciel Eduardo
    Souza, Deivison
    Behling, Alexandre
    Mohan, Midhun
    Sanquetta, Mateus Niroh Inoue
    Silva, Carlos Alberto
    Klauberg, Carine
    Sanquetta, Carlos Roberto
    Veras, Hudson Franklin Pessoa
    de Almeida, Danilo Roberti Alves
    Prata, Gabriel
    Zambrano, Angelica Maria Almeyda
    Trautenmueller, Jonathan William
    de Moraes, Anibal
    Karasinski, Mauro Alessandro
    Broadbent, Eben North
    [J]. DRONES, 2022, 6 (02)
  • [9] Tree crown delineation and tree species classification in boreal forests using hyperspectral and ALS data
    Dalponte, Michele
    Orka, Hans Ole
    Ene, Liviu Theodor
    Gobakken, Terje
    Naesset, Erik
    [J]. REMOTE SENSING OF ENVIRONMENT, 2014, 140 : 306 - 317
  • [10] Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data
    Dalponte, Michele
    Bruzzone, Lorenzo
    Gianelle, Damiano
    [J]. REMOTE SENSING OF ENVIRONMENT, 2012, 123 : 258 - 270