A Disaster Invariant Feature for localization

In this paper we present a Disaster Invariant Feature (DIF), which is used for localization of Unmanned Aerial Vehicles (UAV). There exist numerous researches that address the problem of localization of UAVs using aerial images. However, after a disaster such as a tornado or an earthquake many features in aerial images like monuments and unique buildings may change, and the image-based localization would become hard or even impossible. Consequently it is important to find features that remain unchanged or with fairly small changes, and can be detected both before and after a disaster. We have used a recent method for street detection from aerial images and shown that road networks and segments are disaster invariant and could be utilized for localization and mapping. The algorithm has been implemented and tested on satellite images from Google, with nearly equivalent resolution to aerial images. The successful result of detecting this DIF on Port-au-Prince, in Haiti, images before and after the recent earthquake is presented.