Horizon estimation from thermal cameras for Unmanned Aerial Vehicles
Conference Paper
Overview
Identity
Additional Document Info
View All
Overview
abstract
Copyright 2019 by the Vertical Flight Society. Obstacle avoidance is essential for the integration of autonomous Unmanned Aerial Vehicles (UAVs) into the National Airspace. Thermal imaging provides visual information in situations that a typical camera can not. Sky-ground segmentation is useful for detecting obstacles. In this paper, we propose a technique of sky-ground segmentation and obstacle detection using thermal imaging, and its use for control in quadrotor UAV systems. Sky-ground segmentation is performed by using deep neural networks and image processing techniques. We present results from flight trials in the field which demonstrate that our detection algorithms identify obstacles within the UAV's field of view.