Earthquake building damage detection with object-oriented change detection

Author

Lixia Gong ; Qiang Li ; Jingfa Zhang

Author_Institution

Inst. of Crustal Dynamics, China Earthquake Adm., Beijing, China

fYear

2013

fDate

21-26 July 2013

Firstpage

3674

Lastpage

3677

Abstract

Remote sensing image change detection is an effective method to estimate earthquake damage. With the improvement of spaceborne image resolution, single pixel is gradually replaced by object as the basic unit for change detection. The principle of object-oriented change detection method is described in this paper. And then data processing flow is stated. Taking high-resolution remote sensing images pre- and post- the Yushu earthquake as an example, the accuracy of this method to extract building damage is shown. This method is compared with direct change detection method based on pixel, and based on principal component analysis. The results show object-oriented change detection method has the highest accuracy in building damage estimation, which is 83%, while the accuracy of the latter two methods are 72% and 61%.

Keywords

buildings (structures); earthquakes; feature extraction; geophysical image processing; geophysical techniques; image resolution; object detection; principal component analysis; remote sensing; basic change detection unit; building damage estimation; building damage estimation highest accuracy; building damage extraction; data processing flow; direct change detection method; earthquake building damage detection; earthquake damage estimation; effective method accuracy; high-resolution remote sensing image post-Yushu earthquake; high-resolution remote sensing image pre-Yushu earthquake; object-oriented change detection; object-oriented change detection method; object-oriented change detection method principle; principal component analysis; remote sensing image change detection; single pixel; spaceborne image resolution improvement; Accuracy; Buildings; Data mining; Earthquakes; Image resolution; Image segmentation; Remote sensing; Change detection; Earthquake building damage; Object-oriented; Remote sensing;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International

Conference_Location

Melbourne, VIC

ISSN

2153-6996

Print_ISBN

978-1-4799-1114-1

Type

conf

DOI

10.1109/IGARSS.2013.6723627

Filename

6723627