Fast Dense Depth Estimation from UAV-borne Aerial Imagery for the Assistance of Emergency Forces

Abstract

This work addresses the use of commercial off-the-shelf rotor-based unmanned aerial vehicles (UAVs) to facilitate emergency forces in the rapid structural assessment of a disaster site by means of aerial image-based reconnaissance. It proposes a framework that consists of two parts and relies on the integrated stereo vision sensor and the visual payload camera of the UAV to execute three high-level applications that aim at facilitating first responders in disaster relief missions.