Aplikacija za določanje optimalnih nastavitev kolesa

magistrsko delo

Matevž Bencik (Author), Danilo Korže (Mentor)

Abstract

V diplomskem delu opisujemo razvoj aplikacije za optimalno nastavitev kolesa. Spoznamo pomen pravilne nastavitve kolesa in naredimo pregled obstoječih rešitev na tržišču. Za namen določanja človeškega položaja uporabljamo optični tok s pomočjo označevalcev in oceno položaja na podlagi globokega učenja. Razvijemo sistem, ki omogoča hitro, enostavno in natančno optimizacijo nastavitve kolesa, brez potrebe po profesionalni opremi. Zaledje naše rešitve poganja programski jezik Python, medtem ko je aplikacija narejena v ogrodju React. Svojo rešitev preizkusimo, analiziramo in primerjamo z ostalimi rešitvami.

Keywords

nastavitev kolesa;optični tok;ocena človeškega položaja;magistrske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.09 - Master's Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[M. Bencik]
UDC:	004.773.4(043.2)
COBISS:	98517507
Views:	77
Downloads:	19
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Application for determining optimal bike settings
Secondary abstract:	The diploma thesis deals with the application for determining optimal bike settings. In this thesis, we get to know the meaning of correct bike settings and make a comparison between existing products on the market. For purpose of determining human position, we are using optical flow in combination with markers and human pose estimation methods based on deep learning. We develop a system that allows fast, easy, and accurate optimization of bike settings, without the need for any professional equipment. The backend of our application is written in Python, while the frontend is based on React framework. Our solution is tested, analysed, and compared to others similar products.
Secondary keywords:	bike settings;optical flow;human pose estimation;
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages:	1 spletni vir (1 datoteka PDF (VIII, 51 f.))
ID:	14154990