Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu

Živković, Anastazija

prikaz prve stranice dokumenta Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu

Download
PDF 2.1 MB

undergraduate thesis

Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu

2020. urn:nbn:hr:200:114930

Živković, Anastazija

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

Cite this document

APA 6th Edition

Živković, A. (2020). Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu (Undergraduate 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:200:114930

MLA 8th Edition

Živković, Anastazija. "Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:114930

Chicago 17th Edition

Harvard

Živković, A. (2020). 'Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 24 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:114930

Vancouver

Živković A. Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 April 24] Available at: https://urn.nsk.hr/urn:nbn:hr:200:114930

IEEE

A. Živković, "Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:114930

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:114930

Please login to the repository to save this object to your list.

Metadata

Title	Detekcija prometnih znakova ograničenja brzine iz slike kamere na vozilu
Title (english)	Detection of speed limit traffic signs from on-vehicle camera image
Author	Anastazija Živković
Mentor	Snježana Rimac-Drlje (mentor)
Committee member	Snježana Rimac-Drlje (predsjednik povjerenstva)
Committee member	Zdravko Krpić (član povjerenstva)
Committee member	Drago Žagar (član povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Communications) (Chair of Multimedia Systems and Digital Television) Osijek
Defense date and country	2020-09-30, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Electrical Engineering Telecommunications and Informatics
Abstract	U okviru ovog završnog rada izrađena je aplikacije za prepoznavanje prometnih znakova ograničenja brzine na učitanoj slici primjenom konvolucijske neuronske mreže. Za razvoj aplikacije korišteni su Keras te OpenCV. Za treniranje i testiranje aplikacije korištene su fotografije iz GTSRB baze podataka te vlastiti videozapis iz kojega su okviri spremljeni u zasebnu mapu. Kod detekcije znakova iz videozapisa pokazalo se kako elementi okoline prometnog znaka imaju znatan utjecaj na točnost njegova prepoznavanja. Također, utvrđeno je kako točnost prepoznavanja uvelike ovisi i o udaljenosti znaka od kamere. Unatoč tome, testiranje korištene metode je pokazalo kako je prepoznavanje znaka u većini slučajeva uspješno obavljeno i da je trening nad slikama koje čine bazu podataka odrađen uspješno.
Abstract (english)	An application for recognition of the speed limit road sign on the loaded photo is made within this bachelor’s thesis. Keras and OpenCV are used for the application development. Photos from GTSRB database, as well as own videos from which video frames are extracted and saved into a folder, are utilized for training and testing the application. Detecting the signs has shown that environmental elements have a very strong influence on accuracy of the sign recognizing. Also, it has been established that the accuracy depends on distance between car camera and the traffic sign. Nevertheless, testing of the presented method showed that the sign recognition was well done and that training, performed on images which make the database, was successfully carried out.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:114930
Study programme	Title: Undergraduate University Study Programme Study programme type: university Study level: undergraduate Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike)
Type of resource	Text
File origin	Born digital
Access conditions	Open access
Terms of use
Created on	2020-11-16 16:12:52