Razumijevanje scena iz perspektive vozača semantičkom segmentacijom

undergraduate thesis

• Title (english): Scene understanding from the driver's perspective with semantic segmentation
• Author: Klara Marijan
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Committee member: Petra Bevandić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu objašnjen je princip funkcioniranja umjetnih neuronskih mreža s naglaskom na konvolucijske neuronske mreže. U radu su opisane rezidualne neuronske mreže kao i njihova implementacija na primjeru mreže ResNet-18. Programski je ostvareno rješenje problema raspoznavanja prometnih sudionika te elemenata okoliša iz perspektive vozača. Uz osnovni model mreže ResNet-18, programski je ostvarena i nadogradnja modela ljestvičastim naduzorkovanjem. Napravljena je usporedba rezultata koje daju oba modela te su oni navedeni na kraju rada.

Abstract (english)

This paper explains the principle of functioning of artificial neural networks with emphasis on convolutional neural networks. The paper describes residual neural networks as well as their implementation on the example of ResNet-18 network. The problem of recognizing traffic participants and elements of the environment from the perspective of the driver was solved programatically. In addition to the basic model of the ResNet-18 network, the model was also upgraded with ladder upsampling. A comparison of the results given by both models is made and they are listed at the end of the paper.

• Keywords: neuronske mreže; konvolucijske neuronske mreže; ResNet; semantička segmentacija; ljestvičasto naduzorkovanje
• Keywords (english): neural networks; convolutional neural networks; ResNet; semantic segmentation; ladder upsampling
• Language: croatian
• URN:NBN: urn:nbn:hr:168:624066
• 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 09:24:22