Pronalaženje objekata jednoprolaznim konvolucijskim modelima

undergraduate thesis

• Title (english): Object Localization With One-Stage Convolutional Models
• Author: Matija Krivošić
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Petra Bevandić (član povjerenstva)
• Committee member: Marin Oršić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-09-19, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Pronalaženje objekata na slikama u današnje vrijeme ima širokom primjenu. Zato smo u ovom radu obradili jedan od modela koji rješava taj problem. To je Single shot multibox detector (SSD). Objašnjen je način na koji radi ovaj već istreniran model i kako napraviti svoju bazu podataka koju želimo evaluirati. Da bi bolje razumjeli način na koji radi ovaj model objašnjene su neuronske mreže s naglaskom na konvolucijske neuronske mreže.

Abstract (english)

Finding objects in the images at a given time is widespread. That is why we have dealt with one of the models that solve this problem in this paper. It is a Single shot multibox detector (SSD). It is explained how this model is pre learnd and how to make the database we want to evaluate. In order to better understand the way this model is used, neural networks have been studied with an emphasis on convolutional neural networks.

• Language: croatian
• URN:NBN: urn:nbn:hr:168:874034
• 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: 2019-03-13 21:59:09