prikaz prve stranice dokumenta Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila
Access restricted to students and staff of home institution
master's thesis
Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila
Rijeka: University of Rijeka, Faculty of Engineering, 2019. urn:nbn:hr:190:122760
Milković, Dražen
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Intelligent Computing Systems

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Milković, D. (2019). Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:122760

Milković, Dražen. "Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila." Master's thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:122760

Milković, Dražen. "Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila." Master's thesis, University of Rijeka, Faculty of Engineering, 2019. https://urn.nsk.hr/urn:nbn:hr:190:122760

Milković, D. (2019). 'Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 24 December 2024, https://urn.nsk.hr/urn:nbn:hr:190:122760

Milković D. Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2019 [cited 2024 December 24] Available at: https://urn.nsk.hr/urn:nbn:hr:190:122760

D. Milković, "Prepoznavanje markera RGB kamerom za navigaciju autonomnog vozila", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:190:122760

Metadata
TitlePrepoznavanje markera RGB kamerom za navigaciju autonomnog vozila
Title (english)Marker recognition with RGB camera for autonomous vehicle navigation
AuthorDražen Milković
MentorKristijan Lenac (mentor)
Committee memberMiroslav Joler (predsjednik povjerenstva)
Committee memberRenato Filjar (član povjerenstva)
Committee memberKristijan Lenac (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Intelligent Computing Systems)
Rijeka
Defense date and country2019-11-25, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Autonomnavozilaznatnosunapredovalauzadnjihnekolikogodina,većsadaserazvijaju i testiraju potpuno autonomna vozila. Tehnologije koje se koriste za autonomnu vožnju se mijenjaju i pronalaze se novi načini percipiranja okoline. Cilj natjecanja Formula Student Driverless je kreiranje autonomnih vozila koja samo uz vlastite senzoreiračunalnumoćmogupercipiratisvojuokolinu, stvoritikartuprostoraiodrediti najbolju putanju za postizanje što boljeg vremena na stazi. U ovom projektu istraženo je kako možemo koristiti RGB kameru visoke razlučivosti za navigaciju autonomnog vozila uz pomoć strojnog učenja. Da bi se sustav koristio na bolidu poželjno je da percepcija bude što brža. Istraživanjem različitih modela za detekciju objekata odlučeno je da će se za detekciju koristiti YOLOv3 tiny sustav za detekciju u stvarnom vremenu. To je iznimno brz model za detekciju objekata s visokom točnošću koji će nam omogućiti da i na slabijem sklopovlju detektiramo objekte velikom brzinom.
Abstract (english)
Autonomous vehicles have significantly progressed in the last few years, already now fully autonomous vehicles are being developed and tested. Technologies used for autonomous driving are changing and new ways of perceiving the environment are being found. The goal of the Formula Student Driverless competition is to create autonomousvehiclesthatcanperceivetheirenvironmentusingonlytheirownsensors and computing power, create a map of their surroundings, and determine the best path to get the best track time possible. This project explores how we can use a high-resolution RGB camera to navigate an autonomous vehicle using machine learning. In order to use the system on a car, perception should be as fast as possible. By researching various object detection models it was decided that YOLOv3 tiny real-time object detection system would be used for detection. It is an extremely fast object detection model with high accuracy, enabling object detection at high speed even with weaker computer hardware.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:122760
Study programmeTitle: Graduate University Study of Electrical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2020-07-27 10:33:21