Building change detection after earthquake using multi-criteria decision analysis based on extracted information from high spatial resolution satellite images

ABSTRACT

Change detection of ground surface objects can provide essential and precious information for experts in the fields of Geomatics, emergency management, urban management, agriculture, and forestry. Space-borne remote-sensing images are one of the main sources for change detection. Various change detection methods have been proposed on remote-sensing applications. However, often, no single efficient method can be selected for a case study because the existing methods sometimes have good performance and sometimes perform poorly. Therefore, it is necessary to propose an integrated change detection method according to some change detection methods. Multi-criteria decision analysis is a powerful framework that can integrate several criteria that may be in contrast to each other. In this study, a multi-criteria decision analysis framework was used to integrate the spectral, textural, and transformed features for detecting building changes with the help of high spatial resolution satellite images. First, the spectral, textural, and transformed features were extracted from the pre- and post-event satellite images. Second, the spectral, textural, and transformed factor maps were produced by entering the related features to three separate Adaptive Network-Based Fuzzy Inference Systems (ANFIS). Third, the ANFIS model was used again to integrate the mentioned factor maps for producing the preliminary building change map. And finally, a comprehensive sensitivity analysis was carried out to determine the proper parameters of the ANFIS models leading to accurate change detection results. The proposed method was tested on the earthquake data set of Bam City in Iran. The achieved results indicated an overall accuracy of 89.62% for identifying the changed and unchanged building regions. Moreover, the obtained results proved the efficiency and accuracy of the proposed method with respect to other implemented methods regarding the Bam earthquake. Furthermore, the aggregation of the spectral, transformed, and textural features resulted in improving the change detection accuracy by about 5–15%, compared with the accuracy of every one of them for the mentioned purpose.

Acknowledgements

The authors are grateful to the anonymous reviewers for their time and effort spent in reviewing the article and for their constructive comments. We also thank the editor-in-chief of International Journal of Remote Sensing and Dr Sotaro Tanaka (associate editor) for the rapid peer reviewing process.

Disclosure statement

No potential conflict of interest was reported by the authors.