Navigation through terrain recognition for on-board radar systems
V. Stefanovici (TU Delft - Aerospace Engineering)
Jerom Maas – Coach (TU Delft - Control & Simulation)
Ronald van Gent – Mentor (TU Delft - Control & Simulation)
J. Hoekstra – Mentor (TU Delft - Control & Operations)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Radar technique advancements have made it possible to equip lightweight aircraft with radar systems. These systems can help determine the relative position of the world around the aircraft. Performing calculations on the incoming radar signals, it is possible to determine the locations of the ground elements in the aircraft body of reference, which can be done using Direction of Arrival Estimation (DAE) in a lateral setting, as a Side Looking Airborne Radar (SLAR). Using traditional computing techniques for image processing as well as two pre-trained image segmentation machine learning algorithms, it is possible to identify the aforementioned structural elements onto a satellite image to determine the actual position of the aircraft. As a consequence, navigation may be possible alongside Global Positioning Systems (GPS) methods, through obtaining the coordinates of the aircraft based on radar images. Experiment results show that a high accuracy identification rate is possible, based on large features, such as highways, within the radar image.