magistrsko delo
Jure Štefl (Author), Dušan Gleich (Mentor)

Abstract

Namen magistrske naloge je sestaviti metodo za avtomatsko zaznavo udrtin na pločevini avtomobila. Celoten sistem je sestavljen iz tunela v katerem so posebne luči in kamera preko katere zajemamo sliko. Tema naloge se nanaša na področje strojnega vida, kar pomeni, da imamo opravka s programskimi orodji za obdelavo slik. Uporabili smo metode na osnovi hitre Fourierjeve transformacije, valčne transformacije, metod nadzorovanega učenja, filtriranja in še mnogih ostalih potrebnih algoritmov za izboljšanje kakovosti slike. Računalniški program vsako zajeto sliko obdela in na njej označi zaznane udrtine. Rezultat naloge je predstavljen kot video posnetek avtomobila na katerem so označene zaznane udrtine.

Keywords

strojni vid;detekcija;udrtine;toča;avtomobili;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: J. Štefl
UDC: 007.52:62-472.3:629.331(043.2)
COBISS: 19170326 Link will open in a new window
Views: 1171
Downloads: 141
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: DENTS DETECTION ON THE SHEET METAL USING MACHINE VISION
Secondary abstract: The purpose of the master's thesis is to create a method for automatic detection of dents on the sheet metal of the car. The entire system consists of a tunnel which contains special lights and cameras. The purpose of the latter is the image capturing. The thesis's theme relates to the field of the machine vision, which means that we are dealing with the software tools for image processing. We used several methods based on the fast Fourier transform, wavelet transform, methods for supervised learning, filtering and many other necessary algorithms for improving image quality. Each captured image is being processed by computer programme and dents are being marked afterwards. The result of the thesis is presented as a video of the car on which are marked locations of the detected dents.
Secondary keywords: machine vision;detection;dents;hail;cars;
URN: URN:SI:UM:
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Elektrotehnika
Pages: IX, 77 f.
ID: 9062571