Navigation through terrain recognition for on-board radar systems

Title

Navigation through terrain recognition for on-board radar systems

 Author

Stefanovici, Vlad (TU Delft Aerospace Engineering)

Contributor

Maas, J.B. (graduation committee)
van Gent, Ronald (mentor)
Hoekstra, Jacco (mentor)

Degree granting institution

Delft University of Technology

 Programme

Aerospace Engineering

 Date

2019-12-13

 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.

 To reference this document use:

http://resolver.tudelft.nl/uuid:216b45cf-6756-4252-93b6-ba91780b93a9

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2019 Vlad Stefanovici
Files
PDF Thesis_report_Vlad_Stefan ... 423682.pdf 18.24 MB
Close viewer