Land cover classification accuracy assessment using full-waveform LiDAR data

Kuan Tsung Chang, Feng Chi Yu, Yi Chang, Jin Tsong Hwang, Jin King Liu, Wei Chen Hsu, Peter Tian Yuan Shih

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The geomorphology of Taiwan is characterized by marked changes in terrain, geological fractures, and frequent natural disasters. Because of sustained economic growth, urbanization and land development, the land cover in Taiwan has undergone frequent use changes. Among the various technologies for monitoring changes in land cover, remote sensing technologies, such as LiDAR, are efficient tools for collecting a broad range of spectral and spatial data. Two types of airborne LiDAR systems exist; full-waveform (FW) LiDAR and traditional discrete-echo LiDAR. Because reflected waveforms are affected by the land object material type and properties, the waveform features can be applied to analyze the characteristics specifically associated with land-cover classification (LCC). Five types of land cover that characterize the volcanic Guishan Island were investigated. The automatic LCC method was used to elucidate the spectral, geomorphometric and textural characteristics. Interpretation keys accompanied by additional information were extracted from the FW LiDAR data for subsequent statistical and separation analyses. The results show that the Gabor texture and geomorphometric features, such as the normalized digital surface model (nDSM) and slopes can enhance the overall LCC accuracy to higher than 90%. Moreover, both the producer and user accuracy can be higher than 92% for forest and built-up types using amplitude and pulse width. Although the waveform characteristics did not perform as well as anticipated due to the waveform data sampling rate, the data provides suitable training samples for testing the waveform feature effects.

Original languageEnglish
Pages (from-to)169-181
Number of pages13
JournalTerrestrial, Atmospheric and Oceanic Sciences
Volume29
Issue number2
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

accuracy assessment
land cover
volcanic island
natural disaster
spatial data
geomorphology
economic growth
urbanization
texture
remote sensing
sampling
monitoring

All Science Journal Classification (ASJC) codes

  • Oceanography
  • Atmospheric Science
  • Earth and Planetary Sciences (miscellaneous)

Cite this

Chang, Kuan Tsung ; Yu, Feng Chi ; Chang, Yi ; Hwang, Jin Tsong ; Liu, Jin King ; Hsu, Wei Chen ; Shih, Peter Tian Yuan. / Land cover classification accuracy assessment using full-waveform LiDAR data. In: Terrestrial, Atmospheric and Oceanic Sciences. 2015 ; Vol. 29, No. 2. pp. 169-181.
@article{0c1d9be317ee4ea498c699f40cb8f9be,
title = "Land cover classification accuracy assessment using full-waveform LiDAR data",
abstract = "The geomorphology of Taiwan is characterized by marked changes in terrain, geological fractures, and frequent natural disasters. Because of sustained economic growth, urbanization and land development, the land cover in Taiwan has undergone frequent use changes. Among the various technologies for monitoring changes in land cover, remote sensing technologies, such as LiDAR, are efficient tools for collecting a broad range of spectral and spatial data. Two types of airborne LiDAR systems exist; full-waveform (FW) LiDAR and traditional discrete-echo LiDAR. Because reflected waveforms are affected by the land object material type and properties, the waveform features can be applied to analyze the characteristics specifically associated with land-cover classification (LCC). Five types of land cover that characterize the volcanic Guishan Island were investigated. The automatic LCC method was used to elucidate the spectral, geomorphometric and textural characteristics. Interpretation keys accompanied by additional information were extracted from the FW LiDAR data for subsequent statistical and separation analyses. The results show that the Gabor texture and geomorphometric features, such as the normalized digital surface model (nDSM) and slopes can enhance the overall LCC accuracy to higher than 90{\%}. Moreover, both the producer and user accuracy can be higher than 92{\%} for forest and built-up types using amplitude and pulse width. Although the waveform characteristics did not perform as well as anticipated due to the waveform data sampling rate, the data provides suitable training samples for testing the waveform feature effects.",
author = "Chang, {Kuan Tsung} and Yu, {Feng Chi} and Yi Chang and Hwang, {Jin Tsong} and Liu, {Jin King} and Hsu, {Wei Chen} and Shih, {Peter Tian Yuan}",
year = "2015",
month = "1",
day = "1",
doi = "10.3319/TAO.2014.12.02.02(EOSI)",
language = "English",
volume = "29",
pages = "169--181",
journal = "Terrestrial, Atmospheric and Oceanic Sciences",
issn = "1017-0839",
publisher = "Chinese Geoscience Union",
number = "2",

}

Land cover classification accuracy assessment using full-waveform LiDAR data. / Chang, Kuan Tsung; Yu, Feng Chi; Chang, Yi; Hwang, Jin Tsong; Liu, Jin King; Hsu, Wei Chen; Shih, Peter Tian Yuan.

In: Terrestrial, Atmospheric and Oceanic Sciences, Vol. 29, No. 2, 01.01.2015, p. 169-181.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Land cover classification accuracy assessment using full-waveform LiDAR data

AU - Chang, Kuan Tsung

AU - Yu, Feng Chi

AU - Chang, Yi

AU - Hwang, Jin Tsong

AU - Liu, Jin King

AU - Hsu, Wei Chen

AU - Shih, Peter Tian Yuan

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The geomorphology of Taiwan is characterized by marked changes in terrain, geological fractures, and frequent natural disasters. Because of sustained economic growth, urbanization and land development, the land cover in Taiwan has undergone frequent use changes. Among the various technologies for monitoring changes in land cover, remote sensing technologies, such as LiDAR, are efficient tools for collecting a broad range of spectral and spatial data. Two types of airborne LiDAR systems exist; full-waveform (FW) LiDAR and traditional discrete-echo LiDAR. Because reflected waveforms are affected by the land object material type and properties, the waveform features can be applied to analyze the characteristics specifically associated with land-cover classification (LCC). Five types of land cover that characterize the volcanic Guishan Island were investigated. The automatic LCC method was used to elucidate the spectral, geomorphometric and textural characteristics. Interpretation keys accompanied by additional information were extracted from the FW LiDAR data for subsequent statistical and separation analyses. The results show that the Gabor texture and geomorphometric features, such as the normalized digital surface model (nDSM) and slopes can enhance the overall LCC accuracy to higher than 90%. Moreover, both the producer and user accuracy can be higher than 92% for forest and built-up types using amplitude and pulse width. Although the waveform characteristics did not perform as well as anticipated due to the waveform data sampling rate, the data provides suitable training samples for testing the waveform feature effects.

AB - The geomorphology of Taiwan is characterized by marked changes in terrain, geological fractures, and frequent natural disasters. Because of sustained economic growth, urbanization and land development, the land cover in Taiwan has undergone frequent use changes. Among the various technologies for monitoring changes in land cover, remote sensing technologies, such as LiDAR, are efficient tools for collecting a broad range of spectral and spatial data. Two types of airborne LiDAR systems exist; full-waveform (FW) LiDAR and traditional discrete-echo LiDAR. Because reflected waveforms are affected by the land object material type and properties, the waveform features can be applied to analyze the characteristics specifically associated with land-cover classification (LCC). Five types of land cover that characterize the volcanic Guishan Island were investigated. The automatic LCC method was used to elucidate the spectral, geomorphometric and textural characteristics. Interpretation keys accompanied by additional information were extracted from the FW LiDAR data for subsequent statistical and separation analyses. The results show that the Gabor texture and geomorphometric features, such as the normalized digital surface model (nDSM) and slopes can enhance the overall LCC accuracy to higher than 90%. Moreover, both the producer and user accuracy can be higher than 92% for forest and built-up types using amplitude and pulse width. Although the waveform characteristics did not perform as well as anticipated due to the waveform data sampling rate, the data provides suitable training samples for testing the waveform feature effects.

UR - http://www.scopus.com/inward/record.url?scp=84983274026&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983274026&partnerID=8YFLogxK

U2 - 10.3319/TAO.2014.12.02.02(EOSI)

DO - 10.3319/TAO.2014.12.02.02(EOSI)

M3 - Article

VL - 29

SP - 169

EP - 181

JO - Terrestrial, Atmospheric and Oceanic Sciences

JF - Terrestrial, Atmospheric and Oceanic Sciences

SN - 1017-0839

IS - 2

ER -