Object-Based Tree Species Classification in Urban Ecosystems Using LiDAR and Hyperspectral Data

被引:65
|
作者
Zhang, Zhongya [1 ,2 ]
Kazakova, Alexandra [3 ]
Moskal, Ludmila Monika [2 ]
Styers, Diane M. [4 ]
机构
[1] China Univ Geosci Beijing, Sch Land Sci & Technol, 29 Xueyuan Rd, Beijing 100083, Peoples R China
[2] Univ Washington, Remote Sensing & Geospatial Anal Lab, Precis Forestry Cooperat, Sch Environnemental & Forest Sci,Coll Environm, Box 352100, Seattle, WA 98195 USA
[3] Microsoft, Bing Maps, 555 110th Ave NE, Bellevue, WA 98004 USA
[4] Western Carolina Univ, Dept Geosci & Nat Resources, Coll Arts & Sci, Cullowhee, NC 28723 USA
来源
FORESTS | 2016年 / 7卷 / 06期
关键词
LiDAR; hyperspectral; tree species classification; urban forests; BOREAL FORESTS; COVER; DISCRIMINATION; DELINEATION; EXTRACTION; BIOMASS; METRICS; HEIGHT; FUSION; MODEL;
D O I
10.3390/f7060122
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
In precision forestry, tree species identification is key to evaluating the role of forest ecosystems in the provision of ecosystem services, such as carbon sequestration and assessing their effects on climate regulation and climate change. In this study, we investigated the effectiveness of tree species classification of urban forests using aerial-based HyMap hyperspectral imagery and light detection and ranging (LiDAR) data. First, we conducted an object-based image analysis (OBIA) to segment individual tree crowns present in LiDAR-derived Canopy Height Models (CHMs). Then, hyperspectral values for individual trees were extracted from HyMap data for band reduction through Minimum Noise Fraction (MNF) transformation which allowed us to reduce the data to 20 significant bands out of 118 bands acquired. Finally, we compared several different classifications using Random Forest (RF) and Multi Class Classifier (MCC) methods. Seven tree species were classified using all 118 bands which resulted in 46.3% overall classification accuracy for RF versus 79.6% for MCC. Using only the 20 optimal bands extracted through MNF, both RF and MCC achieved an increase in overall accuracy to 87.0% and 88.9%, respectively. Thus, the MNF band selection process is a preferable approach for tree species classification when using hyperspectral data. Further, our work also suggests that RF is heavily disadvantaged by the high-dimensionality and noise present in hyperspectral data, while MCC is more robust when handling high-dimensional datasets with small sample sizes. Our overall results indicated that individual tree species identification in urban forests can be accomplished with the fusion of object-based LiDAR segmentation of crowns and hyperspectral characterization.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Object-Based Tree Species Classification Using Airborne Hyperspectral Images and LiDAR Data
    Wu, Yanshuang
    Zhang, Xiaoli
    [J]. FORESTS, 2020, 11 (01):
  • [2] OBJECT-BASED FUSION OF HYPERSPECTRAL AND LIDAR DATA FOR CLASSIFICATION OF URBAN AREAS
    Marpu, Prashanth Reddy
    Martinez, Sergio Sanchez
    [J]. 2015 7TH WORKSHOP ON HYPERSPECTRAL IMAGE AND SIGNAL PROCESSING: EVOLUTION IN REMOTE SENSING (WHISPERS), 2015,
  • [3] URBAN AREA OBJECT-BASED CLASSIFICATION BY FUSION OF HYPERSPECTRAL AND LIDAR DATA
    Kiani, Kamel
    Mojaradi, Barat
    Esmaeily, Ali
    Salehi, Bahram
    [J]. 2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2014,
  • [4] Object-based fusion for urban tree species classification from hyperspectral, panchromatic and nDSM data
    Aval, Josselin
    Fabre, Sophie
    Zenou, Emmanuel
    Sheeren, David
    Fauvel, Mathieu
    Briottet, Xavier
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2019, 40 (14) : 5339 - 5365
  • [5] Object-Based Crop Species Classification Based on the Combination of Airborne Hyperspectral Images and LiDAR Data
    Liu, Xiaolong
    Bo, Yanchen
    [J]. REMOTE SENSING, 2015, 7 (01): : 922 - 950
  • [6] Seasonal effect on tree species classification in an urban environment using hyperspectral data, LiDAR, and an object-oriented approach
    Voss, Matthew
    Sugumaran, Ramanathan
    [J]. SENSORS, 2008, 8 (05): : 3020 - 3036
  • [7] TREE SPECIES CLASSIFICATION BASED ON AIRBORNE LIDAR AND HYPERSPECTRAL DATA
    Lu, Xukun
    Liu, Gang
    Ning, Silan
    Su, Zhonghua
    He, Ze
    [J]. IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2020, : 2787 - 2790
  • [8] An Object-Based Method for Urban Land Cover Classification Using Airborne Lidar Data
    Chen, Ziyue
    Gao, Bingbo
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2014, 7 (10) : 4243 - 4254
  • [9] Urban tree species mapping using hyperspectral and lidar data fusion
    Alonzo, Michael
    Bookhagen, Bodo
    Roberts, Dar A.
    [J]. Remote Sensing of Environment, 2014, 148 : 70 - 83
  • [10] Urban tree species mapping using hyperspectral and lidar data fusion
    Alonzo, Michael
    Bookhagen, Bodo
    Roberts, Dar A.
    [J]. REMOTE SENSING OF ENVIRONMENT, 2014, 148 : 70 - 83