A novel artificial surface anomaly index (ASAI) based on post-disaster texture features using single-temporal and high-resolution imagery

Earthquake is one of the most divesting natural events that threaten human life during history. After the earthquake, having information about the damaged or anomaly artificial surface area can be a great help in the relief and reconstruction for disaster managers. It is very important that these measures should be taken immediately after the earthquake because any negligence could be more criminal losses. In this study, we developed a method for near real-time, general and robustly identify anomaly artificial surfaces using 3DTF and ASAI. This method was designed to identify the impervious surface areas using single-temporal imagery without pre-disaster data. The features of the contrast, Gabor, and Con-Gabor features were used to construct 3DTF, which distinguish forest, bare land, shadows with artificial surface. And then it was then used with the K-means classifier to map the artificial surfaces area. Based on the different textures of normal and anomaly artificial surfaces, we constructed the ASAI using entropy and homogeneity, and used the index to detect anomalies in mapped artificial surface areas. The performance of the detecting anomalies method was developed at three different sites in Turkey Earthquake and the mapped results of artificial surface showed that the overall accuracies at sites A-C, and C were > 93%. Using The mapped artificial surface area and ASAI identified anomaly artificial surface. The results showed the overall accuracies were 93.76%, 91.4% and 90.07%. Given the promising and accurate outcomes of this study, further developments remain warranted to determine the robustness of the anomaly artificial surface detecting method in areas with complex artificial surface distribution.