Scientific- Research Quarterly of Geographical Data (SEPEHR)

Scientific- Research Quarterly of Geographical Data (SEPEHR)

Evaluation of physical data extraction of damaged buildings due to earthquake and proposing an algorithm using GIS and remote sensing layers

Document Type : Research Paper

Authors
Hamid Reza Ranjbar
Ali Reza Azmoude Ardalan
Hamid Dehghani
Mohamad Reza Serajeyan
Ali Alidousti
10.22131/sepehr.2014.12860
Abstract
Earthquake is one of the most catastrophic natural disasters to affect mankind. One of the critical problems after an earthquake is building damage assessment. The area, amount, rate, and type of the damage are essential information for rescue, humanitarian and reconstruction operations in the disaster area. On the other hand, to deal with the situation requires well organized and effective emergency planning. How quickly the event is responded and how efficiently response activities are managed are the main determinants of the overall costs of a disaster, both in terms of economic damages and fatalities. Remote sensing techniques play an important role in obtaining building damage information because of their non-contact, low cost, wide field of view, and fast response capacities. Now that more and diverse types of remote sensing data become available, various methods are designed and reported for building damage assessment. This paper provides a comprehensive review of these methods based on using optical images in three categories: mono, multi temporal and combination of images and vector map approach and also implements an automatic damage assessment method of buildings using high resolution satellite images and GIS layers. In this method, after extracting texture features of candidate buildings from both pre- and post-event images and defining optimized features, a neurofuzzy inference system was designed that determines buildings to four damage levels: Undamaged, Moderate damaged, Heavy damaged and Destroyed levels. Evaluation results show that the designed system has the overall accuracy of 89% in classifying buildings to the four damage levels.
Keywords
Destroyed Buildings
Damage Map
Texture Analysis
genetic algorithm
Neurofuzzy Inference system