Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification

Kuei Chia Chen, Chun Yu Liu, Chi-Kuei Wang, Hone-Jay Chu, Guo Hao Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Land use classification is vital in understanding ecosystems and evaluating nature sources. Substantial studies have been done on employing the reflectance spectra from hyperspectral images to classify land cover. It is known that the full waveform LiDAR system can obtain the high-precision 3D elevation information, and the shape of the waveform packet describes the characteristics of the surface. In this study, we present an efficient approach that integrates hyperspectral images and full waveform Lidar data for detecting land use clusters. Our study area is located in upper stream of Tsengwen Reservoir watershed in Taiwan. The 72-band hyperspectral data were obtained by an Itres CASI-1500 with a pixel resolution of 1 m. The spectrum range of Itres CASI-1500 is between 362.8 and 1051.3 nm, and the spectral resolution is 9.6 nm. The Lidar data were acquired by an ALTM Pegasus with a point density of 2 points/m 2. We employed Minimum Noise Component (MNF) and Principal Components Analysis (PCA) for data fusion of multivariate statistical models. Based on fused data, Maximum Likelihood was applied to image classification. The classification results showed that fusing the full waveform LiDAR data and the hyperspecrtal data can slightly increase the classification accuracy.

Original languageEnglish
Title of host publication34th Asian Conference on Remote Sensing 2013, ACRS 2013
PublisherAsian Association on Remote Sensing
Pages359-364
Number of pages6
ISBN (Print)9781629939100
Publication statusPublished - 2013 Jan 1
Event34th Asian Conference on Remote Sensing 2013, ACRS 2013 - Bali, Indonesia
Duration: 2013 Oct 202013 Oct 24

Publication series

Name34th Asian Conference on Remote Sensing 2013, ACRS 2013
Volume1

Other

Other34th Asian Conference on Remote Sensing 2013, ACRS 2013
CountryIndonesia
CityBali
Period13-10-2013-10-24

Fingerprint

Data fusion
Optical radar
Land use
Image classification
Spectral resolution
Watersheds
Principal component analysis
Ecosystems
Maximum likelihood
Pixels

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Chen, K. C., Liu, C. Y., Wang, C-K., Chu, H-J., & Huang, G. H. (2013). Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification. In 34th Asian Conference on Remote Sensing 2013, ACRS 2013 (pp. 359-364). (34th Asian Conference on Remote Sensing 2013, ACRS 2013; Vol. 1). Asian Association on Remote Sensing.
Chen, Kuei Chia ; Liu, Chun Yu ; Wang, Chi-Kuei ; Chu, Hone-Jay ; Huang, Guo Hao. / Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification. 34th Asian Conference on Remote Sensing 2013, ACRS 2013. Asian Association on Remote Sensing, 2013. pp. 359-364 (34th Asian Conference on Remote Sensing 2013, ACRS 2013).
@inproceedings{c6959b66e5ba4df59da006c25bb2ca84,
title = "Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification",
abstract = "Land use classification is vital in understanding ecosystems and evaluating nature sources. Substantial studies have been done on employing the reflectance spectra from hyperspectral images to classify land cover. It is known that the full waveform LiDAR system can obtain the high-precision 3D elevation information, and the shape of the waveform packet describes the characteristics of the surface. In this study, we present an efficient approach that integrates hyperspectral images and full waveform Lidar data for detecting land use clusters. Our study area is located in upper stream of Tsengwen Reservoir watershed in Taiwan. The 72-band hyperspectral data were obtained by an Itres CASI-1500 with a pixel resolution of 1 m. The spectrum range of Itres CASI-1500 is between 362.8 and 1051.3 nm, and the spectral resolution is 9.6 nm. The Lidar data were acquired by an ALTM Pegasus with a point density of 2 points/m 2. We employed Minimum Noise Component (MNF) and Principal Components Analysis (PCA) for data fusion of multivariate statistical models. Based on fused data, Maximum Likelihood was applied to image classification. The classification results showed that fusing the full waveform LiDAR data and the hyperspecrtal data can slightly increase the classification accuracy.",
author = "Chen, {Kuei Chia} and Liu, {Chun Yu} and Chi-Kuei Wang and Hone-Jay Chu and Huang, {Guo Hao}",
year = "2013",
month = "1",
day = "1",
language = "English",
isbn = "9781629939100",
series = "34th Asian Conference on Remote Sensing 2013, ACRS 2013",
publisher = "Asian Association on Remote Sensing",
pages = "359--364",
booktitle = "34th Asian Conference on Remote Sensing 2013, ACRS 2013",

}

Chen, KC, Liu, CY, Wang, C-K, Chu, H-J & Huang, GH 2013, Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification. in 34th Asian Conference on Remote Sensing 2013, ACRS 2013. 34th Asian Conference on Remote Sensing 2013, ACRS 2013, vol. 1, Asian Association on Remote Sensing, pp. 359-364, 34th Asian Conference on Remote Sensing 2013, ACRS 2013, Bali, Indonesia, 13-10-20.

Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification. / Chen, Kuei Chia; Liu, Chun Yu; Wang, Chi-Kuei; Chu, Hone-Jay; Huang, Guo Hao.

34th Asian Conference on Remote Sensing 2013, ACRS 2013. Asian Association on Remote Sensing, 2013. p. 359-364 (34th Asian Conference on Remote Sensing 2013, ACRS 2013; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification

AU - Chen, Kuei Chia

AU - Liu, Chun Yu

AU - Wang, Chi-Kuei

AU - Chu, Hone-Jay

AU - Huang, Guo Hao

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Land use classification is vital in understanding ecosystems and evaluating nature sources. Substantial studies have been done on employing the reflectance spectra from hyperspectral images to classify land cover. It is known that the full waveform LiDAR system can obtain the high-precision 3D elevation information, and the shape of the waveform packet describes the characteristics of the surface. In this study, we present an efficient approach that integrates hyperspectral images and full waveform Lidar data for detecting land use clusters. Our study area is located in upper stream of Tsengwen Reservoir watershed in Taiwan. The 72-band hyperspectral data were obtained by an Itres CASI-1500 with a pixel resolution of 1 m. The spectrum range of Itres CASI-1500 is between 362.8 and 1051.3 nm, and the spectral resolution is 9.6 nm. The Lidar data were acquired by an ALTM Pegasus with a point density of 2 points/m 2. We employed Minimum Noise Component (MNF) and Principal Components Analysis (PCA) for data fusion of multivariate statistical models. Based on fused data, Maximum Likelihood was applied to image classification. The classification results showed that fusing the full waveform LiDAR data and the hyperspecrtal data can slightly increase the classification accuracy.

AB - Land use classification is vital in understanding ecosystems and evaluating nature sources. Substantial studies have been done on employing the reflectance spectra from hyperspectral images to classify land cover. It is known that the full waveform LiDAR system can obtain the high-precision 3D elevation information, and the shape of the waveform packet describes the characteristics of the surface. In this study, we present an efficient approach that integrates hyperspectral images and full waveform Lidar data for detecting land use clusters. Our study area is located in upper stream of Tsengwen Reservoir watershed in Taiwan. The 72-band hyperspectral data were obtained by an Itres CASI-1500 with a pixel resolution of 1 m. The spectrum range of Itres CASI-1500 is between 362.8 and 1051.3 nm, and the spectral resolution is 9.6 nm. The Lidar data were acquired by an ALTM Pegasus with a point density of 2 points/m 2. We employed Minimum Noise Component (MNF) and Principal Components Analysis (PCA) for data fusion of multivariate statistical models. Based on fused data, Maximum Likelihood was applied to image classification. The classification results showed that fusing the full waveform LiDAR data and the hyperspecrtal data can slightly increase the classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84903478952&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903478952&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84903478952

SN - 9781629939100

T3 - 34th Asian Conference on Remote Sensing 2013, ACRS 2013

SP - 359

EP - 364

BT - 34th Asian Conference on Remote Sensing 2013, ACRS 2013

PB - Asian Association on Remote Sensing

ER -

Chen KC, Liu CY, Wang C-K, Chu H-J, Huang GH. Data fusion of airborne hyperspectral and full waveform LiDAR data for land cover classification. In 34th Asian Conference on Remote Sensing 2013, ACRS 2013. Asian Association on Remote Sensing. 2013. p. 359-364. (34th Asian Conference on Remote Sensing 2013, ACRS 2013).