prikaz prve stranice dokumenta Detekcija dronova korištenjem slike s video kamere i strojnog učenja
Access restricted to authenticated users
master's thesis
Detekcija dronova korištenjem slike s video kamere i strojnog učenja
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. urn:nbn:hr:179:038115
Veić, Lucija
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Veić, L. (2021). Detekcija dronova korištenjem slike s video kamere i strojnog učenja (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:038115

Veić, Lucija. "Detekcija dronova korištenjem slike s video kamere i strojnog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:038115

Veić, Lucija. "Detekcija dronova korištenjem slike s video kamere i strojnog učenja." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:038115

Veić, L. (2021). 'Detekcija dronova korištenjem slike s video kamere i strojnog učenja', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 06 August 2024, https://urn.nsk.hr/urn:nbn:hr:179:038115

Veić L. Detekcija dronova korištenjem slike s video kamere i strojnog učenja [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 August 06] Available at: https://urn.nsk.hr/urn:nbn:hr:179:038115

L. Veić, "Detekcija dronova korištenjem slike s video kamere i strojnog učenja", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:038115

Metadata
TitleDetekcija dronova korištenjem slike s video kamere i strojnog učenja
Title (english)Drone detection using video camera image and machine learning
AuthorLucija Veić
MentorIvo Stančić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Današnji se sustavi za identifikaciju letećih objekata iz slika visoke rezolucije temelje na konvolucijskim neuronskim mrežama, no često su ti objekti daleko od kamere pa njihova veličina na slikama nije pogodna za korištenje spomenutog pristupa. Cilj je ovog rada bio pronaći značajke objekata prema kojima bi se mogla vršiti identifikacija i ispitati tu mogućnost korištenjem nekoliko klasifikacijskih algoritama. Budući da leteći objekti u daljini u pojedinim trenutcima i pod određenim kutom izgledaju slično, potrebno ih je malo dulje promatrati kako bi se moglo odrediti radi li se o avionu, dronu ili ptici. Stoga je napravljen sustav koji na temelju promatranja značajki oblika i kretanja unutar 30 uzastopnih slika donosi odluku o kojem se objektu radi.
Abstract (english)
Today's systems for flying object detection from high-resolution images are based on convolutional neural networks, but in case when these objects are far from the camera, mentioned approach is not suitable because of their small size in images. The aim of this paper was to find object features according to which identification could be performed using several machine learning classification algorithms. Since flying objects look similar at certain moments and at certain angles, they need to be observed in order to determine if is it an airplane, a drone or a bird. So, a system that makes decisions based on the observation of shape and motion features within 30 consecutive frames was made.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:038115
Study programmeTitle: Electronics and Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva (magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2022-07-07 11:21:04