Sustav za detekciju i raspoznavanje prometnih znakova

master's thesis

• Title (english): Traffic sign detection and recognition system
• Author: Mislav Mandarić
• Mentor: Zoran Kalafatić (mentor)
• Committee member: Zoran Kalafatić (predsjednik povjerenstva)
• Committee member: Siniša Šegvić (član povjerenstva)
• Committee member: Tomislav Hrkać (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rješavanje problema detekcije i raspoznavanja prometnih znakova za ograničenje brzine može se iskoristiti u mnogim segmentima auto industrije. Rješenje tog problema uz zadovoljavajuće rezultate mogu biti općeniti algoritmi za detekciju i raspoznavanje bez kompleksne obrade slika kao što su Viola-Jones detektor i klasifikator slučajne šume. Iskorišteni Viola-Jones detektor ima dobre rezultate uz problem lažno pozitivnih odziva. Taj problem riješio se korištenjem dulje kaskade uz posljedicu smanjenja broja točnih detekcija. Klasifikacija algoritmom slučajne šume daje vrlo dobre rezultate čak i uz korištenje jednostavnih značajki poput vrijednosti slikovnih elemenata slike sivih razina.

Abstract (english)

Speed limit traffic sign detection and recognition system can be used in car industry. Satisfactorily solution to this problem can be achived using general purpuse detection and recognition algorithms like Viola-Jones and Random forests, all without complex image processing. Used Viola-Jones detector gave good results but problem was large number of false positives. That problem is solved using longer cascade that raised number of false negatives. Random forests classification algorithm gave very good results even though very simple features like grayscale pixel values are used.

• Keywords: detekcija prometnih znakova; raspoznavanje prometnih znakova; prometni znakovi za ograničenje brzine; Viola-Jones algoritam; algoritam slučajne šume
• Keywords (english): traffic sign detection; traffic sign recognition; speed limit traffic signs; Viola-Jones algorithm; Random forests algorithm
• Language: croatian
• URN:NBN: urn:nbn:hr:168:747337
• Study programme: Title: Computing; 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: Closed access
• Created on: 2018-02-06 10:20:04