prikaz prve stranice dokumenta Sustav za detekciju prometnih znakova
No public access
undergraduate thesis
Sustav za detekciju prometnih znakova
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:417183
Kos, Barbara
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Kos, B. (2023). Sustav za detekciju prometnih znakova (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:417183

Kos, Barbara. "Sustav za detekciju prometnih znakova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:417183

Kos, Barbara. "Sustav za detekciju prometnih znakova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:417183

Kos, B. (2023). 'Sustav za detekciju prometnih znakova', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 20 May 2024, https://urn.nsk.hr/urn:nbn:hr:168:417183

Kos B. Sustav za detekciju prometnih znakova [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 May 20] Available at: https://urn.nsk.hr/urn:nbn:hr:168:417183

B. Kos, "Sustav za detekciju prometnih znakova", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:417183

Metadata
TitleSustav za detekciju prometnih znakova
Title (english)System for traffic sign detection
AuthorBarbara Kos
MentorTomislav Hrkać (mentor)
Committee memberTomislav Hrkać (predsjednik povjerenstva)
Committee memberEda Jovičić (član povjerenstva)
Committee memberVjeko Kužina (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad bavi se izradom sustava za detekciju prometnih znakova. Korišten je model SSD MobileNet FPNLite koji svojom preciznošću i brzinom učinkovito obavlja zadatak detekcije prometnih znakova u stvarnom vremenu. U radu su opisani koraci procesa prikupljanja i označavanja vlastitog skupa podataka za učenje i testiranje te je opisan proces treniranja modela detekcije. Objašnjeni su osnovni pojmovi poput transfernog učenja, nadziranog strojnog učenja i drugi pojmovi koji olakšavaju shvaćanje korištenih metoda. Provedena je analiza implementiranog sustava te su prikazane i objašnjene metrike evaluacije modela.
Abstract (english)
This paper deals with the creation of a system for traffic sign detection. The SSD MobileNet FPNLite model was used which, with its precision and speed, effectively performs the task of detecting traffic signs in real time. The paper describes the steps of the process of collecting and labeling the data set for learning and testing, and describes the process of training the detection model. Basic terms such as transfer learning, supervised machine learning and other terms that facilitate the understanding of the methods used are explained. An analysis of the implemented system was carried out and the evaluation metrics of the model were presented and explained.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:417183
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-10-11 09:20:39