URBAN TREE CLASSIFICATION USING FULL-WAVEFORM AIRBORNE LASER SCANNING

被引:12
作者
Koma, Zs. [1 ]
Koenig, K. [2 ]
Hoefle, B. [2 ]
机构
[1] Eotvos Lorand Univ, Dept Geophys & Space Sci, H-1364 Budapest, Hungary
[2] Heidelberg Univ, LiDAR Res Grp, GISci, Inst Geog, D-69115 Heidelberg, Germany
来源
XXIII ISPRS CONGRESS, COMMISSION III | 2016年 / 3卷 / 03期
关键词
Airborne Laser Scanning; Urban Environment; Classification; Tree; Object-based; Radiometric and Geometric Features; LIDAR DATA; SPECIES CLASSIFICATION; FOREST INVENTORY; SINGLE TREE; SEGMENTATION; BIOMASS; METRICS; DISCRETE;
D O I
10.5194/isprsannals-III-3-185-2016
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Vegetation mapping in urban environments plays an important role in biological research and urban management. Airborne laser scanning provides detailed 3D geodata, which allows to classify single trees into different taxa. Until now, research dealing with tree classification focused on forest environments. This study investigates the object-based classification of urban trees at taxonomic family level, using full-waveform airborne laser scanning data captured in the city centre of Vienna (Austria). The data set is characterised by a variety of taxa, including deciduous trees (beeches, mallows, plane trees and soapberries) and the coniferous pine species. A workflow for tree object classification is presented using geometric and radiometric features. The derived features are related to point density, crown shape and radiometric characteristics. For the derivation of crown features, a prior detection of the crown base is performed. The effects of interfering objects (e.g. fences and cars which are typical in urban areas) on the feature characteristics and the subsequent classification accuracy are investigated. The applicability of the features is evaluated by Random Forest classification and exploratory analysis. The most reliable classification is achieved by using the combination of geometric and radiometric features, resulting in 87.5% overall accuracy. By using radiometric features only, a reliable classification with accuracy of 86.3% can be achieved. The influence of interfering objects on feature characteristics is identified, in particular for the radiometric features. The results indicate the potential of using radiometric features in urban tree classification and show its limitations due to anthropogenic influences at the same time.
引用
收藏
页码:185 / 192
页数:8
相关论文
共 40 条
[1]   Stem Volume and Above-Ground Biomass Estimation of Individual Pine Trees From LiDAR Data: Contribution of Full-Waveform Signals [J].
Allouis, Tristan ;
Durrieu, Sylvie ;
Vega, Cedric ;
Couteron, Pierre .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2013, 6 (02) :924-934
[2]   Mapping urban forest leaf area index with airborne lidar using penetration metrics and allometry [J].
Alonzo, Michael ;
Bookhagen, Bodo ;
McFadden, Joseph P. ;
Sun, Alex ;
Roberts, Dar A. .
REMOTE SENSING OF ENVIRONMENT, 2015, 162 :141-153
[3]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[4]   Using Small-Footprint Discrete and Full-Waveform Airborne LiDAR Metrics to Estimate Total Biomass and Biomass Components in Subtropical Forests [J].
Cao, Lin ;
Coops, Nicholas C. ;
Hermosilla, Txomin ;
Innes, John ;
Dai, Jinsong ;
She, Guanghui .
REMOTE SENSING, 2014, 6 (08) :7110-7135
[5]  
Ducic V., 2006, P WORKSH 3D REM SENS, P211
[6]   A Benchmark of Lidar-Based Single Tree Detection Methods Using Heterogeneous Forest Data from the Alpine Space [J].
Eysn, Lothar ;
Hollaus, Markus ;
Lindberg, Eva ;
Berger, Frederic ;
Monnet, Jean-Matthieu ;
Dalponte, Michele ;
Kobal, Milan ;
Pellegrini, Marco ;
Lingua, Emanuele ;
Mongus, Domen ;
Pfeifer, Norbert .
FORESTS, 2015, 6 (05) :1721-1747
[7]   Different methodologies for calculating crown volumes of Platanus hispanica trees using terrestrial laser scanner and a comparison with classical dendrometric measurements [J].
Fernandez-Sarria, A. ;
Martinez, L. ;
Velazquez-Marti, B. ;
Sajdak, M. ;
Estornell, J. ;
Recio, J. A. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2013, 90 :176-185
[8]   Effective LAI and CHP of a Single Tree From Small-Footprint Full-Waveform LiDAR [J].
Fieber, Karolina D. ;
Davenport, Ian J. ;
Tanase, Mihai A. ;
Ferryman, James M. ;
Gurney, Robert J. ;
Walker, Jeffrey P. ;
Hacker, Jorg M. .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2014, 11 (09) :1634-1638
[9]   Analysis of full-waveform LiDAR data for classification of an orange orchard scene [J].
Fieber, Karolina D. ;
Davenport, Ian J. ;
Ferryman, James M. ;
Gurney, Robert J. ;
Walker, Jeffrey P. ;
Hacker, Jorg M. .
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2013, 82 :63-82
[10]   A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales [J].
Ghosh, Aniruddha ;
Fassnacht, Fabian Ewald ;
Joshi, P. K. ;
Koch, Barbara .
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2014, 26 :49-63