The collapse of buildings and other structures in heavily populated areas often result in multiple human victims becoming trapped within the resulting rubble. This rubble is often unstable, difficult to traverse and dangerous for emergency first responders who are tasked with finding, stabilizing and extricating the victims through access holes in the rubble. Recent work in scene mapping and reconstruction using RGB-D data collected by unmanned aerial vehicles (UAVs) suggest the possibility of automatically identifying potential access holes (holes) into the interior of rubble—allowing limited human search capacity to be concentrated in areas where potential access holes can be verified as useful entry points. In this paper, we present a system to automatically identify access holes in rubble. Our investigation begins with defining a hole in terms that allow their algorithmic identification as potential means of accessing the interior of rubble. From this definition we propose a set of features that highlight “holes”. We conducted experiments using RGB-D data collected over several disaster training facilities using a UAV. Our empirical evaluation indicates the efficacy of the proposed system for successfully identifying access holes in disaster rubble scenes.
Citation: C. Kong, A. Ferworn, J. Tran, S. Herman, E. Coleshill and K. Derpanis, “Toward the Automatic Detection of Access Holes in Disaster Rubble,” in IEEE International Workshop on Safety, Security & Rescue Robotics (SSRR-2013), Oct 24-26 2013, Linköping, Sweden, 2013