Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain

Purnama B. Santosa, Yasuhiro Mitani, Tetsuro Esaki, Hiro Ikemi

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

Abstract

Land cover classification has become routine works done based on satellite images. However, the resolution size of the available satellite images as well as the degree of expected accuracy classification results have been the major concern for many researchers. In many cases, classification results accuracy positively correlated with image resolution; the higher the image resolution, the higher the degree of classification result accuracy. For the purpose of land cover classification of Hitotsuse area which is located on a mountainous terrain in Miyazaki Prefecture, Kyushu, Japan, SPOT5/HRG and ALOS satellite images have been utilized. The research methodology have been done by applying different method of image fusion such as IHS, HPF, Wavelet, Subtractive and Multiplicative. The high resolution image for fusing the multispectral images are SPOT panchromatic and ALOS PRISM image with resolution of 2.5 m. Supervised and unsupervised classification was then conducted on the fused images, as well as the results assessment. The results show that even though there is spectral distortion on the fused images, the spatial information is much improved. The classification result accuracy from the fused images also increases about 3.89% and 2.79% for SPOT5 and ALOS respectively. The slope failure area detection is hindered by the similar spectral values of bare-land, slope failure and some vegetated area. Hence, slope failure detection task could not give satisfactory results. However, if it is combined with further scenario, the fused images show its potential for detecting slope failure in the study area.

Original languageEnglish
Title of host publication30th Asian Conference on Remote Sensing 2009, ACRS 2009
Pages275-280
Number of pages6
Volume1
Publication statusPublished - 2009
Event30th Asian Conference on Remote Sensing 2009, ACRS 2009 - Beijing, China
Duration: Oct 18 2009Oct 23 2009

Other

Other30th Asian Conference on Remote Sensing 2009, ACRS 2009
CountryChina
CityBeijing
Period10/18/0910/23/09

Fingerprint

Image fusion
Image resolution
Satellites

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Santosa, P. B., Mitani, Y., Esaki, T., & Ikemi, H. (2009). Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain. In 30th Asian Conference on Remote Sensing 2009, ACRS 2009 (Vol. 1, pp. 275-280)

Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain. / Santosa, Purnama B.; Mitani, Yasuhiro; Esaki, Tetsuro; Ikemi, Hiro.

30th Asian Conference on Remote Sensing 2009, ACRS 2009. Vol. 1 2009. p. 275-280.

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

Santosa, PB, Mitani, Y, Esaki, T & Ikemi, H 2009, Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain. in 30th Asian Conference on Remote Sensing 2009, ACRS 2009. vol. 1, pp. 275-280, 30th Asian Conference on Remote Sensing 2009, ACRS 2009, Beijing, China, 10/18/09.
Santosa PB, Mitani Y, Esaki T, Ikemi H. Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain. In 30th Asian Conference on Remote Sensing 2009, ACRS 2009. Vol. 1. 2009. p. 275-280
Santosa, Purnama B. ; Mitani, Yasuhiro ; Esaki, Tetsuro ; Ikemi, Hiro. / Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain. 30th Asian Conference on Remote Sensing 2009, ACRS 2009. Vol. 1 2009. pp. 275-280
@inproceedings{de2559a788fc41c1af64ef61caa3300e,
title = "Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain",
abstract = "Land cover classification has become routine works done based on satellite images. However, the resolution size of the available satellite images as well as the degree of expected accuracy classification results have been the major concern for many researchers. In many cases, classification results accuracy positively correlated with image resolution; the higher the image resolution, the higher the degree of classification result accuracy. For the purpose of land cover classification of Hitotsuse area which is located on a mountainous terrain in Miyazaki Prefecture, Kyushu, Japan, SPOT5/HRG and ALOS satellite images have been utilized. The research methodology have been done by applying different method of image fusion such as IHS, HPF, Wavelet, Subtractive and Multiplicative. The high resolution image for fusing the multispectral images are SPOT panchromatic and ALOS PRISM image with resolution of 2.5 m. Supervised and unsupervised classification was then conducted on the fused images, as well as the results assessment. The results show that even though there is spectral distortion on the fused images, the spatial information is much improved. The classification result accuracy from the fused images also increases about 3.89{\%} and 2.79{\%} for SPOT5 and ALOS respectively. The slope failure area detection is hindered by the similar spectral values of bare-land, slope failure and some vegetated area. Hence, slope failure detection task could not give satisfactory results. However, if it is combined with further scenario, the fused images show its potential for detecting slope failure in the study area.",
author = "Santosa, {Purnama B.} and Yasuhiro Mitani and Tetsuro Esaki and Hiro Ikemi",
year = "2009",
language = "English",
isbn = "9781615679843",
volume = "1",
pages = "275--280",
booktitle = "30th Asian Conference on Remote Sensing 2009, ACRS 2009",

}

TY - GEN

T1 - Image fusion methods for land cover classification and its potential for slope failure detection on a mountainous terrain

AU - Santosa, Purnama B.

AU - Mitani, Yasuhiro

AU - Esaki, Tetsuro

AU - Ikemi, Hiro

PY - 2009

Y1 - 2009

N2 - Land cover classification has become routine works done based on satellite images. However, the resolution size of the available satellite images as well as the degree of expected accuracy classification results have been the major concern for many researchers. In many cases, classification results accuracy positively correlated with image resolution; the higher the image resolution, the higher the degree of classification result accuracy. For the purpose of land cover classification of Hitotsuse area which is located on a mountainous terrain in Miyazaki Prefecture, Kyushu, Japan, SPOT5/HRG and ALOS satellite images have been utilized. The research methodology have been done by applying different method of image fusion such as IHS, HPF, Wavelet, Subtractive and Multiplicative. The high resolution image for fusing the multispectral images are SPOT panchromatic and ALOS PRISM image with resolution of 2.5 m. Supervised and unsupervised classification was then conducted on the fused images, as well as the results assessment. The results show that even though there is spectral distortion on the fused images, the spatial information is much improved. The classification result accuracy from the fused images also increases about 3.89% and 2.79% for SPOT5 and ALOS respectively. The slope failure area detection is hindered by the similar spectral values of bare-land, slope failure and some vegetated area. Hence, slope failure detection task could not give satisfactory results. However, if it is combined with further scenario, the fused images show its potential for detecting slope failure in the study area.

AB - Land cover classification has become routine works done based on satellite images. However, the resolution size of the available satellite images as well as the degree of expected accuracy classification results have been the major concern for many researchers. In many cases, classification results accuracy positively correlated with image resolution; the higher the image resolution, the higher the degree of classification result accuracy. For the purpose of land cover classification of Hitotsuse area which is located on a mountainous terrain in Miyazaki Prefecture, Kyushu, Japan, SPOT5/HRG and ALOS satellite images have been utilized. The research methodology have been done by applying different method of image fusion such as IHS, HPF, Wavelet, Subtractive and Multiplicative. The high resolution image for fusing the multispectral images are SPOT panchromatic and ALOS PRISM image with resolution of 2.5 m. Supervised and unsupervised classification was then conducted on the fused images, as well as the results assessment. The results show that even though there is spectral distortion on the fused images, the spatial information is much improved. The classification result accuracy from the fused images also increases about 3.89% and 2.79% for SPOT5 and ALOS respectively. The slope failure area detection is hindered by the similar spectral values of bare-land, slope failure and some vegetated area. Hence, slope failure detection task could not give satisfactory results. However, if it is combined with further scenario, the fused images show its potential for detecting slope failure in the study area.

UR - http://www.scopus.com/inward/record.url?scp=84866055257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866055257&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84866055257

SN - 9781615679843

VL - 1

SP - 275

EP - 280

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

ER -