prikaz prve stranice dokumenta Sustav za raspoznavanje prometnih znakova
No public access
undergraduate thesis
Sustav za raspoznavanje prometnih znakova
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:406343
Pavlović, Matija
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pavlović, M. (2023). Sustav za raspoznavanje prometnih znakova (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:406343

Pavlović, Matija. "Sustav za raspoznavanje prometnih znakova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:406343

Pavlović, Matija. "Sustav za raspoznavanje prometnih znakova." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:406343

Pavlović, M. (2023). 'Sustav za raspoznavanje prometnih znakova', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:406343

Pavlović M. Sustav za raspoznavanje prometnih znakova [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 July 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:406343

M. Pavlović, "Sustav za raspoznavanje prometnih znakova", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:406343

Metadata
TitleSustav za raspoznavanje prometnih znakova
Title (english)System for traffic sign recognition
AuthorMatija Pavlović
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
Rad opisuje jednu moguću implementaciju sustava za klasifikaciju prometnih zna- kova u stvarnom vremenu. Razrađuju se primjene i zahtjevi sustava, opisuju se ranija ostvarenja u tom području i definira se pristup rješenju problema klasifikacije. Sustav klasificira prometne znakove uporabom jedne konvolucijske neronske mreže koja se sastoji od 12 slojeva. Za potrebe treniranja neuronske mreže korišteni su razni pristupi pretprocesiranja fotografija iz skupa podataka za učenje kako bi se povećao broj ulaz- nih podataka koje model ima na raspolaganju za učenje ali i učinio model otpornijim na poremečaje u osvjetljenju i kontrastu do kojih može doći na ulazu. Istrenirani model se koristi u testnoj aplikaciji koja konstantno uzima slike s web-kamere prijenosnog računala, zatim te slike pokušava klasificirati te ukoliko s određenom sigurnošću uspije klasificirati fotografiju ispisuje rezultat na zaslon prijensnog računala.
Abstract (english)
The paper describes a possible implementation of a real-time traffic sign classification system. The applications and requirements of the system are discussed, previous achievements in the field are described, and an approach to solving the classification problem is defined. Created system classifies traffic signs using a single convolutional neural network consisting of 12 layers. Various preprocessing approaches were used to augment the training dataset, increasing the number of input data available for the model to learn from and making the model more robust to disturbances in lighting and contrast that may occur at the input. The trained model is used in a test application that continuously captures images from a laptop’s webcam, attempts to classify those images, and if successful with a certain confidence, displays the result on the laptop’s screen.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:406343
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 10:04:22