Detekcija i raspoznavanje prometnih znakova

undergraduate thesis

• Title (english): Traffic sign detection and recognition
• Author: Luka Matošević
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Danko Ivošević (član povjerenstva)
• Committee member: Zvonimir Pavlić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-09-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu razmatraju se osnovne metode računalnog vida za detekciju i raspoznavanje kružnih i trokutastih prometnih znakova s video sekvenci snimljenih iz pokretnog vozila. Detekcija se provodi na temelju modela oblika primjenom Houghove transformacije za kružnice prilikom detekcije kružnih znakova, odnosno metode praćenja brida za detekciju trokutastih znakova. Raspoznavanje detektiranih znakova se obavlja uporabom metode usporedbe uzoraka iz postojeće baze znakova. U sklopu ovog rada programski je ostvaren sustav temeljen na metodama računalnog vida te je nad istim provedeno ispitivanje uporabom reprezentativnog uzorka sekvenci uz uspješnost raspoznavanja od 28,09%.

Abstract (english)

This work discusses the basic methods of computer vision for detection and recognition of circular and triangular traffic signs from video sequences taken from a moving vehicle. The detection is performed based on the shape model using the Hough transform for circle detection in circular signs, and border following method for detection of triangular signs. Recognizing the detected signs is done using the template matching method from the existing traffic signs database. As part of this work there is realized a system based on computer vision methods and it is tested using a representative sample sequences with the recognition performance of 28.09%.

• Keywords: prometni znakovi; detekcija na temelju oblika; Houghova transformacija; detekcija boje; računalni vid
• Keywords (english): traffic signs; shape based detection; Hough transformation; color segmentation; computer vision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:572031
• 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: 2018-02-05 17:44:25