Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data

被引:383
作者
Dalponte, Michele [1 ,2 ]
Bruzzone, Lorenzo [2 ]
Gianelle, Damiano [1 ]
机构
[1] Fdn E Mach, Res & Innovat Ctr, Sustainable Agroecosyst & Bioresources Dept, I-38010 San Michele All Adige, TN, Italy
[2] Univ Trento, Dept Informat Engn & Comp Sci, I-38123 Povo, Trento, Italy
关键词
Tree species classification; Hyperspectral data; Multispectral data; GeoEye-1; LiDAR data; LiDAR point density; Support vector machine; Random forest; RADIOMETRIC NORMALIZATION; MULTISPECTRAL IMAGERY; COVER CLASSIFICATION; CHLOROPHYLL CONTENT; AIRBORNE LIDAR; STEM VOLUME; INTENSITY; UTILITY; STAND; AREA;
D O I
10.1016/j.rse.2012.03.013
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The identification of tree species is an important issue in forest management. In recent years, many studies have explored this topic using hyperspectral, multispectral, and LiDAR data. In this study we analyzed two multi-sensor set-ups: 1) airborne high spatial resolution hyperspectral images combined with LiDAR data; and 2) high spatial resolution satellite multispectral images combined with LiDAR data. Two LiDAR acquisitions were considered: low point density (approx. 0.48 points per m(2)) and high point density (approx. 8.6 points per m(2)). The aims of this work were: i) to understand what level of classification accuracy can be achieved using a high spectral and spatial resolution multi-sensor data set-up (very high spatial and spectral resolution airborne hyperspectral images integrated with high point density LiDAR data), over a mountain area characterized by many species, both broadleaf and coniferous; ii) to understand the implications of a downgrading of the data characteristics (in terms of spectral resolution of spectral data and point density of LiDAR data), on species separability, with respect to the previous set-up; and iii) to understand the differences between high- and low-point density LiDAR acquisitions on tree species classification. The study region was a mountain area in the Southern Alps characterized by many tree species (7 species and a "non-forest" class), either coniferous or broadleaf. For each set-up a specific processing chain was adopted, from the pre-processing of the raw data to the classification (two classifiers were used: support vector machine and random forest). Different class definitions were tested, including general macro-classes, forest types, and finally single tree species. Experimental results showed that the set-up based on hyperspectral data was effective with general macro-classes, forest types, and single species, reaching high kappa accuracies (93.2%, 82.1% and 76.5%, respectively). The use of multispectral data produced a reduction in the classification accuracy, which was sharp for single tree species, and still high for forest types. Considering general macro-classes, the multispectral set-up was still very accurate (85.8%). Regarding LiDAR data, the experimental analysis showed that high density LiDAR data provided more information for tree species classification with respect to low density data, when combined with either hyperspectral or multispectral data. (C) 2012 Elsevier Inc. All rights reserved.
引用
收藏
页码:258 / 270
页数:13
相关论文
共 36 条
[1]   Radiometric normalization, compositing, and quality control for satellite high resolution image mosaics over large areas [J].
Du, Y ;
Cihlar, J ;
Beaubien, J ;
Latifovic, R .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (03) :623-634
[2]   Detecting Tamarisk species (Tamarix spp.) in riparian habitats of Southern California using high spatial resolution hyperspectral imagery [J].
Hamada, Yuki ;
Stow, Douglas A. ;
Coulter, Lloyd L. ;
Jafolla, Jim C. ;
Hendricks, Leif W. .
REMOTE SENSING OF ENVIRONMENT, 2007, 109 (02) :237-248
[3]   Simulated Multispectral Imagery for Tree Species Classification Using Support Vector Machines [J].
Heikkinen, Ville ;
Tokola, Timo ;
Parkkinen, Jussi ;
Korpela, Ilkka ;
Jaaskelainen, Timo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2010, 48 (03) :1355-1364
[4]   Operational wide-area stem volume estimation based on airborne laser scanning and national forest inventory data [J].
Hollaus, M. ;
Dorigo, W. ;
Wagner, W. ;
Schadauer, K. ;
Hoefle, B. ;
Maier, B. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2009, 30 (19) :5159-5175
[5]   Utility of an image-based canopy reflectance modeling tool for remote estimation of LAI and leaf chlorophyll content at the field scale [J].
Houborg, Rasmus ;
Anderson, Martha ;
Daughtry, Craig .
REMOTE SENSING OF ENVIRONMENT, 2009, 113 (01) :259-274
[6]   ON MEAN ACCURACY OF STATISTICAL PATTERN RECOGNIZERS [J].
HUGHES, GF .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1968, 14 (01) :55-+
[7]   Assessing the utility of airborne hyperspectral and LiDAR data for species distribution mapping in the coastal Pacific Northwest, Canada [J].
Jones, Trevor G. ;
Coops, Nicholas C. ;
Sharma, Tara .
REMOTE SENSING OF ENVIRONMENT, 2010, 114 (12) :2841-2852
[8]   Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification [J].
Ke, Yinghai ;
Quackenbush, Lindi J. ;
Im, Jungho .
REMOTE SENSING OF ENVIRONMENT, 2010, 114 (06) :1141-1154
[9]   Forest Cover Classification by Optimal Segmentation of High Resolution Satellite Imagery [J].
Kim, So-Ra ;
Lee, Woo-Kyun ;
Kwak, Doo-Ahn ;
Biging, Greg S. ;
Gong, Peng ;
Lee, Jun-Hak ;
Cho, Hyun-Kook .
SENSORS, 2011, 11 (02) :1943-1958
[10]   Multi-source land cover classification for forest fire management based on imaging spectrometry and LiDAR data [J].
Koetz, B. ;
Morsdorf, F. ;
van der Linden, S. ;
Curt, T. ;
Allgoewer, B. .
FOREST ECOLOGY AND MANAGEMENT, 2008, 256 (03) :263-271