prikaz prve stranice dokumenta Automatsko zaustavljanje vozila na osnovu prometne signalizacije
  Download
PDF 4.29 MB
master's thesis
Automatsko zaustavljanje vozila na osnovu prometne signalizacije
2019. urn:nbn:hr:200:913978
Mikulić, Frane
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

Cite this document

Mikulić, F. (2019). Automatsko zaustavljanje vozila na osnovu prometne signalizacije (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:913978

Mikulić, Frane. "Automatsko zaustavljanje vozila na osnovu prometne signalizacije." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:913978

Mikulić, Frane. "Automatsko zaustavljanje vozila na osnovu prometne signalizacije." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:913978

Mikulić, F. (2019). 'Automatsko zaustavljanje vozila na osnovu prometne signalizacije', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 17 March 2023, https://urn.nsk.hr/urn:nbn:hr:200:913978

Mikulić F. Automatsko zaustavljanje vozila na osnovu prometne signalizacije [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2023 March 17] Available at: https://urn.nsk.hr/urn:nbn:hr:200:913978

F. Mikulić, "Automatsko zaustavljanje vozila na osnovu prometne signalizacije", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:913978

Please login to the repository to save this object to your list.
Metadata
TitleAutomatsko zaustavljanje vozila na osnovu prometne signalizacije
Title (english)Automatic vehicle stopping based on traffic signaling
AuthorFrane Mikulić
MentorMario Vranješ (mentor)
Committee memberMario Vranješ (predsjednik povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Multimedia Systems and Digital Television)
Osijek
Defense date and country2019-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom radu razvijan je algoritam za detekciju i klasifikaciju prometnih znakova i prometne signalizacije, koji nalažu izričito zaustavljanje vozila, u različitim vremenskim uvjetima. Algoritam ja razvijan u svrhu primjene u sustavima autonomne vožnje. Za detekciju trenirao se YOLOv3 algoritam na označenim slikama iz trening skupa s područja grada Osijeka. Za razvoj algoritma koristio se programski okvir Darknet. Osim algoritma detekcije razvijen je i algoritam za procjenu udaljenosti vozila od detektiranog objekta. Algoritam postiže visoke performanse pri radu u uvjetima danjeg osvjetljenja, dok pri kišnom vremenu i noćnim uvjetima postiže lošije performanse.
Abstract (english)
In this paper, an algorithm for the detection and recognition of traffic signs and traffic signalization was developed, which requires explicit stopping of vehicles under different weather conditions. Algorithm is for application in autonomous driving systems. For detection, the YOLOv3 algorithm was trained on tagged images from a training session in the Osijek city. The Darknet programming framework was used to develop the algorithm. In addition to the detection algorithm, an algorithm was developed to estimate the distance of the vehicle from the detected object. The algorithm achieves high performance when operating in daylight conditions, while in poor weather and night conditions it achieves poor performance.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:913978
Study programmeTitle: UNIVERSITY STUDY AUTOMOBILE COMPUTER AND COMMUNICATION
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija (magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-09-16 13:38:33