Sustav za raspoznavanje prometnih znakova

undergraduate thesis

• Title (english): System for Traffic Sign Recognition
• Author: Mihael Vitlov
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Josip Šarić (član povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru završnog rada obrađeno je raspoznavanje prometnih znakova koristeći vlastitu konvolucijsku neuronsku mrežu, po arhitekturi sličnoj LeNet-5. Objašnjeni su pojmovi vezani uz umjetne neuronske mreže s fokusom na konvolucijske neuronske mreže. Za izgradnju mreže korištena je biblioteka PyTorch, a za treniranje i testiranje klasifikatora korišten je javno dostupan skup slika prometnih znakova GTSRB. Sustav se pokazao zadovoljavajućim s točnošću od 93%. Taj isti sustav je testiran i na skupu... More slika FER-MASTIF TS2009 na kojem je pokazao točnost od 71%. Less

Abstract (english)

The final paper deals with the recognition of traffic signs using convolutional neural network, according to an architecture similar to LeNet-5. Concepts related to artificial neural networks with a focus on convolutional neural networks are explained. The PyTorch library was used to build the network, and a publicly available set of GTSRB traffic sign images was used to train and test the classifier. The system proved to be satisfactory with an accuracy of 93%. This same system was also... More tested on the FER-MASTIF TS2009 image set, where it showed an accuracy of 71%. Less

• Keywords: umjetne neuronske mreže; duboko učenje; konvolucijske neuronske mreže; PyTorch; računalni vid; klasifikacija; prometni znakovi; GTSRB; FER-MASTIF
• Keywords (english): artificial neural networks; deep learning; convolutional neural networks; PyTorch; computer vision; classification; traffic signs; GTSRB; FER-MASTIF
• Language: croatian
• URN:NBN: urn:nbn:hr:168:617388
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 10:12:29