Tree species mapping by combining hyperspectral with LiDAR data

Pieter Kempeneers; Frieke Vancoillie; Wenzhi Liao; Flore Devriendt; Kris Vandekerkhove; Monique Bernier; Josée Lévesque; Jean-Marc Garneau; Ellsworth LeDrew

Tree species mapping by combining hyperspectral with LiDAR data

Pieter Kempeneers, Frieke Vancoillie, Wenzhi Liao, Flore Devriendt, Kris Vandekerkhove, Monique Bernier (Editor), Josée Lévesque (Editor), Jean-Marc Garneau (Editor), Ellsworth LeDrew (Editor)

Electronic And Electrical Engineering

Research output: Contribution to conference › Paper › peer-review

17 Downloads (Pure)

Abstract

This study deals with data fusion of hyperspectral and LiDAR sensors for forest applications. In particular, the added value of different data sources on tree species mapping has been analyzed. A total of seven species have been mapped for a forested area in Belgium: Beech, Ash, Larch, Poplar, Copper beech, Chestnut and Oak. Hyperspectral data is obtained from the APEX sensor in 286 spectral bands. LiDAR data has been acquired with a TopoSys sensor Harrier 56 at full waveform. Conﬁrming previous research [1], it has been found that airborne LiDAR data, when combined with hyperspectral data, can improve classiﬁcation results. The novelty of this study is in the quantiﬁcation of the contribution of the individual data sources and their derived parameters. LiDAR information was combined with the hyperspectral image in a data fusion approach. Different data fusion techniques were tested, including feature and decision fusion. Decision fucsion produced optimal results, reaching an overall accuracy of 96% (Kappa [3] of 0:95).

Original language	English
Number of pages	4
Publication status	Published - 18 Jul 2014
Event	2014 IEEE Geoscience and Remote Sensing Symposium IGARSS - Quebec City, Canada Duration: 13 Jul 2014 → 18 Jul 2014

Conference

Conference	2014 IEEE Geoscience and Remote Sensing Symposium IGARSS
Abbreviated title	IGARSS 2014
Country/Territory	Canada
City	Quebec City
Period	13/07/14 → 18/07/14

Keywords

LiDAR
hyperspectral images
tree species mapping
image classification

Access to Document

Kempeneers-etal-IGARSS2014-Tree-species-mapping-combining-hyperspectral-LiDAR-dataAccepted author manuscript, 3.41 MB

Cite this

@conference{62f1f7f421f64d5e9da166834a8e29f7,

title = "Tree species mapping by combining hyperspectral with LiDAR data",

abstract = "This study deals with data fusion of hyperspectral and LiDAR sensors for forest applications. In particular, the added value of different data sources on tree species mapping has been analyzed. A total of seven species have been mapped for a forested area in Belgium: Beech, Ash, Larch, Poplar, Copper beech, Chestnut and Oak. Hyperspectral data is obtained from the APEX sensor in 286 spectral bands. LiDAR data has been acquired with a TopoSys sensor Harrier 56 at full waveform. Conﬁrming previous research [1], it has been found that airborne LiDAR data, when combined with hyperspectral data, can improve classiﬁcation results. The novelty of this study is in the quantiﬁcation of the contribution of the individual data sources and their derived parameters. LiDAR information was combined with the hyperspectral image in a data fusion approach. Different data fusion techniques were tested, including feature and decision fusion. Decision fucsion produced optimal results, reaching an overall accuracy of 96% (Kappa [3] of 0:95).",

keywords = "LiDAR, hyperspectral images, tree species mapping, image classification",

author = "Pieter Kempeneers and Frieke Vancoillie and Wenzhi Liao and Flore Devriendt and Kris Vandekerkhove and Monique Bernier and Jos{\'e}e L{\'e}vesque and Jean-Marc Garneau and Ellsworth LeDrew",

year = "2014",

month = jul,

day = "18",

language = "English",

note = " 2014 IEEE Geoscience and Remote Sensing Symposium IGARSS , IGARSS 2014 ; Conference date: 13-07-2014 Through 18-07-2014",

}

TY - CONF

T1 - Tree species mapping by combining hyperspectral with LiDAR data

AU - Kempeneers, Pieter

AU - Vancoillie, Frieke

AU - Liao, Wenzhi

AU - Devriendt, Flore

AU - Vandekerkhove, Kris

A2 - Bernier, Monique

A2 - Lévesque, Josée

A2 - Garneau, Jean-Marc

A2 - LeDrew, Ellsworth

PY - 2014/7/18

Y1 - 2014/7/18

N2 - This study deals with data fusion of hyperspectral and LiDAR sensors for forest applications. In particular, the added value of different data sources on tree species mapping has been analyzed. A total of seven species have been mapped for a forested area in Belgium: Beech, Ash, Larch, Poplar, Copper beech, Chestnut and Oak. Hyperspectral data is obtained from the APEX sensor in 286 spectral bands. LiDAR data has been acquired with a TopoSys sensor Harrier 56 at full waveform. Conﬁrming previous research [1], it has been found that airborne LiDAR data, when combined with hyperspectral data, can improve classiﬁcation results. The novelty of this study is in the quantiﬁcation of the contribution of the individual data sources and their derived parameters. LiDAR information was combined with the hyperspectral image in a data fusion approach. Different data fusion techniques were tested, including feature and decision fusion. Decision fucsion produced optimal results, reaching an overall accuracy of 96% (Kappa [3] of 0:95).

AB - This study deals with data fusion of hyperspectral and LiDAR sensors for forest applications. In particular, the added value of different data sources on tree species mapping has been analyzed. A total of seven species have been mapped for a forested area in Belgium: Beech, Ash, Larch, Poplar, Copper beech, Chestnut and Oak. Hyperspectral data is obtained from the APEX sensor in 286 spectral bands. LiDAR data has been acquired with a TopoSys sensor Harrier 56 at full waveform. Conﬁrming previous research [1], it has been found that airborne LiDAR data, when combined with hyperspectral data, can improve classiﬁcation results. The novelty of this study is in the quantiﬁcation of the contribution of the individual data sources and their derived parameters. LiDAR information was combined with the hyperspectral image in a data fusion approach. Different data fusion techniques were tested, including feature and decision fusion. Decision fucsion produced optimal results, reaching an overall accuracy of 96% (Kappa [3] of 0:95).

KW - LiDAR

KW - hyperspectral images

KW - tree species mapping

KW - image classification

UR - http://hdl.handle.net/1854/LU-5663359

M3 - Paper

T2 - 2014 IEEE Geoscience and Remote Sensing Symposium IGARSS

Y2 - 13 July 2014 through 18 July 2014

ER -

Tree species mapping by combining hyperspectral with LiDAR data

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this