PROJECT TITLE :

Building Damage Detection Using Object-Based Image Analysis and ANFIS From High-Resolution Image (Case Study: BAM Earthquake, Iran)

ABSTRACT:

Building injury detection after earthquake would help to fast relief and response of disaster. In this study, an efficient method was proposed for building injury detection in urban space when earthquake using pre-event vector map and postevent pan-sharpened high spatial resolution image. At first, preprocessing was applied on the postevent satellite image. Second, results of pixel- and object-based mostly classifications were integrated. In the subsequent, geometric options of buildings were extracted as well as space, rectangular fit ($text rect_fit$), and convexity. A decision-making system primarily based on these features and an adaptive network-based fuzzy inference system (ANFIS) model was designed to attain building harm degree. A comprehensive sensitivity analysis was applied to seek out proper parameters of the ANFIS model leading to correct injury results. The proposed method was tested over earthquake data set of Bam town in Iran. The results of our methodology indicate that an overall accuracy of seventy six.36percent and kappa coefficient of 0.63 were achieved to spot building harm degree. The obtained results indicate that the postevent geometrical options (relative amendment of different harm levels with respect to every alternative) together with the ANFIS model will help to reach higher leads to building harm detection.