Progressive image stitching algorithm for vision based automated inspection

Abstract

The increasing number of skyscrapers along with the large number of tall bridges throughout the world also increases the demand of a robust, automated and remotely controlled health monitoring system for civil architectures. It is very difficult and sometimes not feasible to inspect the structures whose heights are beyond the limit of an average traditional structure of the same type. Therefore, in this paper an unmanned aerial vehicle is utilized to provide real time images of the structural site. A gradient of temporal range of images is used for such applications but the uncertainties caused by the camera locations make it quite difficult to evaluate the images from a same position on the structure to reveal any apparent structural damage. These images are, therefore, pre-processed for registration and are then classified automatically. A Speeded Up Robust Features (SURF) based feature detection algorithm is the heart of the scheme presented here in order to determine its performance in image registration and classification for civil structures. Also, the damage detection has been shown, which is achieved using the complete algorithm presented here.