This work proposes methodologies aiming at evaluating the sensitivity of optical and SAR change features obtained from satellite images with respect to the damage grade. The proposed methods are derived from the literature ([1], [2], [3], [4]) and the main novelty concerns the estimation of these change features at object scale. The test case is the Mw 7.0 earthquake that hit Haiti on January 12, 2010. The analysis of change detection indicators is based on ground truth information collected during a post-earthquake survey. We have generated the damage map of Port-au-Prince by considering a set of polygons extracted from the open source Open Street Map geo-database. The resulting damage map was calculated in terms of collapse ratio [5]. We selected some features having a good sensitivity with damage at object scale [6]: the Normalised Difference Index, the Kullback-Libler Divergence, the Mutual Information and the Intensity Correlation Difference. The Naive Bayes and the Support Vector Machine classifiers were used to evaluate the goodness of these features. The classification results demonstrate that the simultaneous use of several change features from EO observations can improve the damage estimation at object scale.
展开▼
