Comparison between automated and manual mapping of typhoon-triggered landslides from SPOT-5 imagery
Resource
International Journal of Remote Sensing 28 (8): 1843-1856
Journal
International Journal of Remote Sensing
Journal Volume
28
Journal Issue
8
Pages
1843-1856
Date Issued
2007-04
Date
2007-04
Author(s)
Abstract
Two large tropical cyclones struck Taiwan in the summer of 2004 and landslides
triggered by these events caused not only casualties and housing damage but also
produced large volumes of sediment that entered rivers and reservoirs. For
reservoir and watershed management it is important to quickly identify the
location and areal extent of new landslides for coordinating mitigation efforts. In
this study, two automated methods, supervised and unsupervised classification of
10m multi-spectral SPOT-5 imagery, were tested for their ability to identify and
map landslide areas before and after the two storm events. A slope map was
applied to mask roads, riverbeds and agricultural fields erroneously commissioned
as landslides. The automated classification results were compared with
manually delineated landslides using SPOT-5 supermode satellite imagery with a
resolution of 2.5 m. Statistical testing and spatial analysis of the mapping results
were performed. Finally, the results from all three methods were validated by
using 0.35m orthophotographs. This paper reports the results and discusses the
salient differences between the automated and manual methods.
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
Comparison between automated and manual mapping of typhoon-triggered landslides from SPOT-5 imagery.pdf
Size
547.95 KB
Format
Adobe PDF
Checksum
(MD5):1ab62f92ea562799ef673b7c9164732d