Sledenje očem z uporabo spletne kamere

diplomsko delo

Luka Vranješ (Author), Jure Žabkar (Mentor)

Abstract

V diplomski nalogi se soočimo s problemom napovedovanja točke pogleda z uporabo spletne kamere za potrebe aplikacije za zaznavo disleksije. Specifični primer uporabe nam omogoča dodatne omejitve problema. V osnovi je problem razdeljen na dva dela. Prvi del rešimo z metodami računalniškega vida in vključuje zaznavo obraza, interesnih točk in središča zenice. V drugem delu z uporabo globoke nevronske mreže napovemo točko pogleda. Z opravljenimi eksperimenti definiramo parametre kalibracije. V najboljšem primeru smo dobili povprečno napako napovedi v radiju 3,37 cm. To nam pogojno omogoča uporabo predstavljenega pristopa za potrebe aplikacije.

Keywords

računalnik;oči;sledenje;kamera;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2019
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[L. Vranješ]
UDC:	004.93:004.5(043.2)
COBISS:	1538347459
Views:	539
Downloads:	181
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Eye-tracking with a web camera
Secondary abstract:	We consider a problem of gaze prediction using a simple webcam for use with an application that screens for dyslexia. The specific use case enables us to define additional boundaries that simplify our problem. On a higher level the problem is composed of two sub problems. The first one requires us to detect the users face, find its landmarks and in the end locate the eye center. We solve this as a computer vision problem. The second sub problem is mapping the features to a point on the screen. For this we used a deep neural network. For optimal results we preform experiments on how to most efficiently calibrate. In the best test case we were able to achieve an average of 3,37 cm prediction error. This puts our approach at most conditionally suitable for use with the target application.
Secondary keywords:	computer;eyes;tracking;webcam;computer and information science;diploma;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	30 str.
ID:	11225343