Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila

Kulić, Filip

master's thesis

Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila

Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. urn:nbn:hr:200:488545

Kulić, Filip

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

APA 6th Edition

Kulić, F. (2018). Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:488545

MLA 8th Edition

Kulić, Filip. "Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:488545

Chicago 17th Edition

Harvard

Kulić, F. (2018). 'Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:488545

Vancouver

Kulić F. Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 May 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:488545

IEEE

F. Kulić, "Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:488545

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:488545

Metadata

Title	Klasifikacija objekata detektiranih ispred vozila pomoću kamere na prednjoj strani vozila
Title (english)	Classificaton of the objects detected in front of the vehicle using front view camera
Author	Filip Kulić
Mentor	Ratko Grbić (mentor)
Committee member	Ratko Grbić (predsjednik povjerenstva)
Committee member	Mario Vranješ (član povjerenstva)
Committee member	Marijan Herceg (član povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Computer Engineering and Automation) (Chair of Automation and Robotics) Osijek
Defense date and country	2018-09-27, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Computing Artificial Intelligence
Abstract	U današnje doba pokušava se postići što veća autonomija vozila, a za to su zaduženi napredni sustavi za pomaganje vozaču (ADAS, engl. Advanced driver-assistance systems). Krajnji cilj razvoja jednog takvog sustava jest omogućiti potpunu autonomiju vozila. Kako bi jedan takav sustav mogao donositi odluke, treba raspolagati informacijama koje pružaju uvid u okolinu vozila, tj. objekte koji okružuju automobil. Prilikom normalne vožnje (unaprijed), sustavu je najbitnije raspolagati informacijama o objektima koji se nalaze ispred vozila. Ovaj rad se bavi klasifikacijom objekata detektiranih s prednje strane vozila gdje ulaz u algoritam klasifikacije predstavljaju slike objekata. Diplomski rad opisuje klasifikaciju objekata koristeći duboke konvolucijske mreže te je kao dio rada opisan postupak izrade jedne takve mreže, od prikupljanja slika koje predstavljaju podatke pa do samog učenja mreže. Također, opisani su i pojedini slojevi od kojih se takva duboka neuronska mreža sastoji. U radu je izvršena evaluacija izrađenih mreža i razmatrani su problemi koji se mogu stvoriti kod krive klasifikacije i zašto do njih dolazi.
Abstract (english)	Nowadays, we are trying to achieve as much vehicle autonomy as possible by developing Advanced driver-assistance systems (ADAS). The ultimate goal of developing such a system is allowing complete autonomy of the vehicle. In order for such a system to make decisions, it should have information that provides insight into the environment of the vehicle, i.e. the objects surrounding the car. During forward driving, it is most important for the system to have information about the objects in front of the vehicle. This paper describes the classification method of using deep convolutional neural networks of the objects detected in the front of the vehicle. The input into the classification algorithm is represented by the image of the object. This paper describes the process of making such a network, from collecting and grouping the images that represent the data up to the learning of the network itself. This paper also describes individual layers which comprise such a deep neural network. In this paper, an evaluation of created networks has been carried out and the paper also discusses why and what problems could occur when using such a method for classification.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:488545
Study programme	Title: Graduate University Study Programme in Computer Engineering Study programme type: university Study level: graduate Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Created on	2018-10-03 10:24:26

Search form