Change search
ReferencesLink to record
Permanent link

Direct link
Towards a quick damage detection system based on grid-computing
KTH, School of Architecture and the Built Environment (ABE), Urban Planning and Environment, Geoinformatics (closed 20110301).
AIST. (GEO Grid)
2010 (English)In: Geographic Information and Cartography for Risk and Crisis Management: Towards Better Solutions / [ed] KONECNY M., ZLATANOVA S. and BANDROVA T.L, Springer Berlin/Heidelberg, 2010, 155-170 p.Chapter in book (Refereed)
Abstract [en]

This chapter develops a quick damage detection system prototype, which produces reasonably detailed information of damaged buildings and accommodates high spatial resolution data. Parallel processing based on grid-computing is chosen to reduce computation time as well as to provide end-users with cost-effective access. The clusters of the GEO (Global Earth Observation) Grid system ( at the National Institute of Advanced Industrial Science and Technology (AIST) in Japan will serve as the main platform. The automated damage detection runs through a scale-space analysis . It is developed as a context-based approach integrating texture, shape, size, and spectral reflectance. QuickBird imagery acquired over Yingxiu town which was heavily damaged due to the 2008 Sichuan Earthquake is used to demonstrate the performance of damage detection algorithms. Damage information at building block level is successfully mapped. At the current stage of development, damage detection focuses on producing quick orientation damage maps. The data grid component of the GEO Grid with data federation capability will be employed to connect to various satellite image and field-survey databases in the next stage of development. This is to enhance the mapping capability for more accurate maps. In addition, future work will practically perform the processing of large-scale damage detection on the GEO Grid , and test the system performance with remote sensing data acquired in various catastrophes.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2010. 155-170 p.
, Lecture Notes in Geoinformation and Cartography, 1
National Category
Natural Sciences
URN: urn:nbn:se:kth:diva-89083DOI: 10.1007/978-3-642-03442-8_11OAI: diva2:502672
QC 20120420Available from: 2012-02-14 Created: 2012-02-14 Last updated: 2012-04-20Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Vu, Tuong Thuy
By organisation
Geoinformatics (closed 20110301)
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 33 hits
ReferencesLink to record
Permanent link

Direct link