Automation of landslide detection using optical images and lidar data

Kuo Hsin Hsiao, Jin King Liu, Chi Chung Lau, Jiann-Yeou Rau

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

Abstract

Both of optical images and airborne LiDAR data are used to recognize landslide features in this study. NDVI and green index derived from spectral information of optical images are used at the first to obtain a preliminary distribution of landslides. Subsequently, parameters derived from DSM and DEM of airborne LiDAR data are applied, including slope gradients, OHM and surface roughness. The study area is in Shimen Watershed of northern Taiwan. After a comparison of the automated-recognized landslides and those interpreted manually by aerial photo-interpretation, an accuracy of 63.32 % is achieved when only NDVI is applied whereas it is 84.79% when slope gradient is included. An accuracy of 94.5 % is achieved after manual editing with additional thematic information is included such as known agriculture land-use, roads and rivers. Four parameters are included in an automated recognition of landslides, namely greenness, slope, OHM and roughness. The foremost one is derived from orthophoto and the other three are derived from LiDAR data. They can be applied by selecting training areas for automatically setting of default values for region-growing and adoptive thresholds. This can effectively recognize local distribution of landslides.

Original languageEnglish
Title of host publication30th Asian Conference on Remote Sensing 2009, ACRS 2009
Pages1889-1894
Number of pages6
Publication statusPublished - 2009 Dec 1
Event30th Asian Conference on Remote Sensing 2009, ACRS 2009 - Beijing, China
Duration: 2009 Oct 182009 Oct 23

Publication series

Name30th Asian Conference on Remote Sensing 2009, ACRS 2009
Volume3

Other

Other30th Asian Conference on Remote Sensing 2009, ACRS 2009
CountryChina
CityBeijing
Period09-10-1809-10-23

Fingerprint

Landslides
Optical radar
Automation
Surface roughness
Watersheds
Land use
Agriculture
Rivers
Antennas

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Hsiao, K. H., Liu, J. K., Lau, C. C., & Rau, J-Y. (2009). Automation of landslide detection using optical images and lidar data. In 30th Asian Conference on Remote Sensing 2009, ACRS 2009 (pp. 1889-1894). (30th Asian Conference on Remote Sensing 2009, ACRS 2009; Vol. 3).
Hsiao, Kuo Hsin ; Liu, Jin King ; Lau, Chi Chung ; Rau, Jiann-Yeou. / Automation of landslide detection using optical images and lidar data. 30th Asian Conference on Remote Sensing 2009, ACRS 2009. 2009. pp. 1889-1894 (30th Asian Conference on Remote Sensing 2009, ACRS 2009).
@inproceedings{b6355d9ac43c43b19ba0fbcdefbb6ae5,
title = "Automation of landslide detection using optical images and lidar data",
abstract = "Both of optical images and airborne LiDAR data are used to recognize landslide features in this study. NDVI and green index derived from spectral information of optical images are used at the first to obtain a preliminary distribution of landslides. Subsequently, parameters derived from DSM and DEM of airborne LiDAR data are applied, including slope gradients, OHM and surface roughness. The study area is in Shimen Watershed of northern Taiwan. After a comparison of the automated-recognized landslides and those interpreted manually by aerial photo-interpretation, an accuracy of 63.32 {\%} is achieved when only NDVI is applied whereas it is 84.79{\%} when slope gradient is included. An accuracy of 94.5 {\%} is achieved after manual editing with additional thematic information is included such as known agriculture land-use, roads and rivers. Four parameters are included in an automated recognition of landslides, namely greenness, slope, OHM and roughness. The foremost one is derived from orthophoto and the other three are derived from LiDAR data. They can be applied by selecting training areas for automatically setting of default values for region-growing and adoptive thresholds. This can effectively recognize local distribution of landslides.",
author = "Hsiao, {Kuo Hsin} and Liu, {Jin King} and Lau, {Chi Chung} and Jiann-Yeou Rau",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781615679843",
series = "30th Asian Conference on Remote Sensing 2009, ACRS 2009",
pages = "1889--1894",
booktitle = "30th Asian Conference on Remote Sensing 2009, ACRS 2009",

}

Hsiao, KH, Liu, JK, Lau, CC & Rau, J-Y 2009, Automation of landslide detection using optical images and lidar data. in 30th Asian Conference on Remote Sensing 2009, ACRS 2009. 30th Asian Conference on Remote Sensing 2009, ACRS 2009, vol. 3, pp. 1889-1894, 30th Asian Conference on Remote Sensing 2009, ACRS 2009, Beijing, China, 09-10-18.

Automation of landslide detection using optical images and lidar data. / Hsiao, Kuo Hsin; Liu, Jin King; Lau, Chi Chung; Rau, Jiann-Yeou.

30th Asian Conference on Remote Sensing 2009, ACRS 2009. 2009. p. 1889-1894 (30th Asian Conference on Remote Sensing 2009, ACRS 2009; Vol. 3).

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

TY - GEN

T1 - Automation of landslide detection using optical images and lidar data

AU - Hsiao, Kuo Hsin

AU - Liu, Jin King

AU - Lau, Chi Chung

AU - Rau, Jiann-Yeou

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Both of optical images and airborne LiDAR data are used to recognize landslide features in this study. NDVI and green index derived from spectral information of optical images are used at the first to obtain a preliminary distribution of landslides. Subsequently, parameters derived from DSM and DEM of airborne LiDAR data are applied, including slope gradients, OHM and surface roughness. The study area is in Shimen Watershed of northern Taiwan. After a comparison of the automated-recognized landslides and those interpreted manually by aerial photo-interpretation, an accuracy of 63.32 % is achieved when only NDVI is applied whereas it is 84.79% when slope gradient is included. An accuracy of 94.5 % is achieved after manual editing with additional thematic information is included such as known agriculture land-use, roads and rivers. Four parameters are included in an automated recognition of landslides, namely greenness, slope, OHM and roughness. The foremost one is derived from orthophoto and the other three are derived from LiDAR data. They can be applied by selecting training areas for automatically setting of default values for region-growing and adoptive thresholds. This can effectively recognize local distribution of landslides.

AB - Both of optical images and airborne LiDAR data are used to recognize landslide features in this study. NDVI and green index derived from spectral information of optical images are used at the first to obtain a preliminary distribution of landslides. Subsequently, parameters derived from DSM and DEM of airborne LiDAR data are applied, including slope gradients, OHM and surface roughness. The study area is in Shimen Watershed of northern Taiwan. After a comparison of the automated-recognized landslides and those interpreted manually by aerial photo-interpretation, an accuracy of 63.32 % is achieved when only NDVI is applied whereas it is 84.79% when slope gradient is included. An accuracy of 94.5 % is achieved after manual editing with additional thematic information is included such as known agriculture land-use, roads and rivers. Four parameters are included in an automated recognition of landslides, namely greenness, slope, OHM and roughness. The foremost one is derived from orthophoto and the other three are derived from LiDAR data. They can be applied by selecting training areas for automatically setting of default values for region-growing and adoptive thresholds. This can effectively recognize local distribution of landslides.

UR - http://www.scopus.com/inward/record.url?scp=84866126368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866126368&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781615679843

T3 - 30th Asian Conference on Remote Sensing 2009, ACRS 2009

SP - 1889

EP - 1894

BT - 30th Asian Conference on Remote Sensing 2009, ACRS 2009

ER -

Hsiao KH, Liu JK, Lau CC, Rau J-Y. Automation of landslide detection using optical images and lidar data. In 30th Asian Conference on Remote Sensing 2009, ACRS 2009. 2009. p. 1889-1894. (30th Asian Conference on Remote Sensing 2009, ACRS 2009).