| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba algoritmov globokega učenja za zaznavo brezpilotnih letalnikov
Authors:ID Andov, Pane (Author)
ID Sarjaš, Andrej (Mentor) More about this mentor... New window
ID Gleich, Dušan (Comentor)
Files:.pdf MAG_Andov_Pane_2025.pdf (4,09 MB)
MD5: 2FBEF89C5433B21B377750204398A6F6
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V magistrskem delu je bila predstavljena metoda za zaznavanje brezpilotnih letalnikov, ki združuje optično kamero in radar. V optičnem podsistemu so bili objekti zaznavani z uporabo algoritma YOLOv8, implementiranega na energijsko učinkoviti platformi NVIDIA Jetson Orin Nano, ki omogoča obdelavo v realnem času. Radarski podsistem temelji na FMCW radarju, ki izkorišča Dopplerjev pojav pri frekvenci 10 GHz in pasovni širini 500 MHz, kar omogoča natančno merjenje razdalje in hitrosti. Eksperimentalni rezultati so pokazali, da združevanje optičnih in radarskih podatkov poveča robustnost in zanesljivost zaznavanja brezpilotnih letalnikov v različnih okolijskih pogojih.
Keywords:dron, detekcija dronov, radar, Dopplerjev radar, YOLOv8
Place of publishing:Maribor
Publisher:[P. Andov]
Year of publishing:2025
PID:20.500.12556/DKUM-94488 New window
UDC:621.396.969.3:004.8.021(043.2)
COBISS.SI-ID:254099203 New window
Publication date in DKUM:04.09.2025
Views:171
Downloads:71
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:19.08.2025

Secondary language

Language:English
Title:A deep learning approach for drone detection using camera and radar data
Abstract:This master's thesis presents a method for drone detection that using a system that integrates an optical camera and a radar. In the visual subsystem, objects were detected with the YOLOv8 algorithm, implementeed on the energy-efficient NVIDIA Jetson Orin Nano platform, enabling real-time processing. The radar subsystem is based on an FMCW radar exploiting the Doppler effect, operating at 10 GHz with a 500 MHz bandwidth, which allows precise range and velocity estimation. Experimental results showed that combining visual and radar data increases the robustness and reliability of drone detection in diverse environmental conditions.
Keywords:drone, drone detection, radars, Doppler radar, YOLOv8


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica