Upravljanja modelom vozila pomoću nekonvencionalnog sučelja

undergraduate thesis

• Title (english): Driving of a vehicle model using unconventional user interface
• Author: Oleg Jakovljev
• Mentor: Željka Mihajlović (mentor)
• Committee member: Željka Mihajlović (predsjednik povjerenstva)
• Committee member: Mladen Karan (član povjerenstva)
• Committee member: Marko Đurasević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu implementirana je simulacija pokretanja vozila u virtualnom okolišu pomoću algoritama računalnog vida. U programskom alatu Blender modelirano je vozilo i okoliš koji sadrži ceste s obojenim oznakama, prometne znakove i jednostavne objekte okoline. Korisnik može kontrolirati vozilo konvencionalnim načinom, putem tipkovnice i miša, a kad vozilo prepozna prometni znak, ono prelazi u autonomni način pokretanja i slijedi obojene oznake na cesti. Za prepoznavanje znakova implementiran je algoritam prepoznavanja klasifikatorom svojstava tipa Haar a za praćenje oznaka na cesti koristi se metoda prepoznavanja i praćenja boje pretvorbom iz RGB(Red Green Blue) modela slika u HSV(Hue Saturation Value) model slike. Odnos vozila i okoliša te fizički točan sustav simulacije vozila su implementirani pomoću Unity3D grafičkog pogona.

Abstract (english)

This thesis implements a simulation of a vehicle movement method in a virtual environment using computer vision algorithms. Using Blender modeling software, a vehicle has been modeled along with terrain consisting of simple environment objects, traffic signs and colored marks on the road. The user can control the vehicle using conventional mouse and keyboard input. When the vehicle detects a traffic sign, it switches to an autonomous movement state where it follows the colored markers on the road surface. The sign detector algorithm uses a cascade classifier with Haar-like features and the road tracking algorithm utilises a method of color tracking with RGB(Red Green Blue) to HSV(Hue Saturation Value) conversion. The relationship between the vehicle and the environment as well as a physically sound system of vehicle dynamics has been implemented in the Unity3D graphics engine.

• Keywords: simulacija vozila; računalni vid; virtualno okruženje; autonomna vožnja; nekonvencionalno sučelje; Unity3D; Blender; C#; C++
• Keywords (english): vehicle simulation; computer vision; virtual environment; autonomous driving; unconvenctional interface; Unity3D; Blender; C#; C++
• Language: croatian
• URN:NBN: urn:nbn:hr:168:277089
• 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: 2018-02-06 09:22:28