Vision-based responders localization techniques in urban search and rescue scenarios

Abstract

In this paper, we introduce a vision-based localization algorithm that can accurately track responders during rescue operations in urban areas that are Global Navigation Satellite System (GNSS)-denied. The proposed algorithm works successfully with the rich visual features of an urban environment and obtains an average localization accuracy of 2.5 ft. In addition, we also provide a 3D representation of the disaster field which reflects the current conditions of the site.