prikaz prve stranice dokumenta Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki
Access restricted to students and staff of home institution
undergraduate thesis
Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki
2021. urn:nbn:hr:200:024976
Brođanac, Marko
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

Brođanac, M. (2021). Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:024976

Brođanac, Marko. "Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:024976

Brođanac, Marko. "Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:024976

Brođanac, M. (2021). 'Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 15 August 2022, https://urn.nsk.hr/urn:nbn:hr:200:024976

Brođanac M. Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2022 August 15] Available at: https://urn.nsk.hr/urn:nbn:hr:200:024976

M. Brođanac, "Prepoznavanje prometnih znakova zasnovani na izdvajanju značajki", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:024976

Please login to the repository to save this object to your list.
Metadata
TitlePrepoznavanje prometnih znakova zasnovani na izdvajanju značajki
Title (english)Traffic sign recognition based on feature extraction
AuthorMarko Brođanac
MentorMario Vranješ (mentor)
Committee memberMario Vranješ (predsjednik povjerenstva)
Committee memberGoran Knežević (član povjerenstva)
Committee memberKrešimir Grgić (član povjerenstva)
GranterJosip 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 country2021-09-10, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Abstract
Jedan od osnovnih problema kojima se bavi računalni vid jest detekcija i prepoznavanje objekata. U svrhu klasifikacije odnosno prepoznavanja prometnih znakova, u ovom radu je dana metoda zasnovana na detekciji značajki sa slike referentnog znaka iz baze podataka i usporedbi tih značajki sa značajkama fotografiranih prometnih znakova. Pri tome su se usporedila tri različita algoritma detekcije ključnih točaka: SIFT, SURF i ORB. Testiranje je provedeno na vlastito izrađenoj bazi od 130 testnih fotografija, gdje su u obzir uzeti prometni znakovi različitih oblika koji su fotografirani pod različitim kutovima. Prema dobivenim rezultatima prepoznavanja znakova, najveću točnost od 83 % postiže ORB algoritam kada se koristi izdvajanje najbolje uparenih ključnih točaka računanjem najkraćih udaljenosti, uz svrstavanje znakova u određene grupe prema njihovoj boji i obliku.
Abstract (english)
Object detection and recognition is one of the most importatnt tasks in computer vision. For the purpose of traffic sign recognition, this paper provides method based on detecting features from sign in referent database and comparing them with features from captured images of traffic signs. Also, three algorithms for keypoint detection were compared: SIFT, SURF and ORB. The proposed recognition method is applied to self-made base of 130 test images captured from different angles. Traffic signs of different shapes were also taken in consideration. Before recognition procedure, signs are classified by their color and shape. According to obtained results, the best recognition rate of 83 % is accomplished by ORB algorithm used with the extraction of the best matched features that are computed by the shortest distances between them.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:024976
Study programmeTitle: Undergraduate University Study Programme
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-11-22 12:29:58