Detecting and assessment of tsunami building damage using high‐resolution satellite images with GIS data

Abstract

Purpose

The purpose of this paper is to present a method and results of evaluating damaged building extraction using an object recognition task in pre‐ and post‐tsunami event. The advantage of remote sensing and its applications made it possible to extract damaged building images and vulnerability easement of wide urban areas due to natural disasters.

Design/methodology/approach

The proposed approach involves several advanced morphological operators, among which are adaptive transforms with varying size, shape and grey level of the structuring elements. IKONOS‐2 satellite images consisting of pre‐ and post‐2004 Indian Ocean Tsunami site of the Kalmunai area on the East coast of Sri Lanka were used. Morphological operation using structural element are applied for segmented images, then extracted remaining building foot print using random forest classification method. This work extended further the road lines extraction using Hough transform.

Findings

The result was investigated using geographic information system (GIS) data and global positioning system (GPS) ground survey in the field and it appeared to have high accuracy: the confidence measures produced of a completely destroyed structure give 86 percent by object‐based, respectively, after the tsunami in one segment of Maruthamune GN Division.

Research limitations/implications

This study has also identified significant limitations, due to the resolution and clearness of satellite images and vegetation canopy over the building footprint.

Originality/value

The authors develop an automated method to detect damaged buildings and compare the results with GIS‐based ground survey.

Citation

Dinesh, C.P., Bari, A.U., Dissanayake, R.P.G. and Tamura, M. (2013), "Detecting and assessment of tsunami building damage using high‐resolution satellite images with GIS data", International Journal of Disaster Resilience in the Built Environment, Vol. 4 No. 2, pp. 132-144. https://doi.org/10.1108/IJDRBE-09-2011-0039