Detekcija osebe v globinski sliki s pomočjo konvolucijskih nevronskih mrež : magistrsko delo

Kokol, Patrik

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Detekcija osebe v globinski sliki s pomočjo konvolucijskih nevronskih mrež : magistrsko delo
Authors:	ID Kokol, Patrik (Author) ID Holobar, Aleš (Mentor) More about this mentor... ID Cigale, Boris (Comentor)
Files:	MAG_Kokol_Patrik_2020.pdf (16,56 MB) MD5: A3592C4874793F700AD61A36D3622EB4 PID: 20.500.12556/dkum/ca1861f0-579b-4a81-b4ec-24d195f08209
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	Cilj magistrskega dela je bil implementirati sistem za avtomatsko nastavljanje višine mize uporabniku z uporabo globinskega senzorja. S pomočjo konvolucijskih nevronskih mrež smo uporabnika detektirali znotraj globinske scene ter tako izračunali njegovo višino. Na podlagi izračunane višine smo nastavili tudi pravilno višino mize za stoječi ali sedeči položaj uporabnika. Pri detekciji osebe v globinski sceni smo dosegli 85,5% natančnost po metriki preseka proti uniji (angl. Intersection over Union - IoU) in 92,3% natančnost po metriki F1. Napaka pri izračunu višine je v povprečju znašala 0,092 metra.
Keywords:	nevronske mreže, konvolucijske nevronske mreže, umetna inteligenca, globoko učenje, detekcija osebe
Place of publishing:	Maribor
Place of performance:	Maribor
Publisher:	[P. Kokol]
Year of publishing:	2020
Number of pages:	XI, 49 str.
PID:	20.500.12556/DKUM-76243
UDC:	004.85:004.932(043.2)
COBISS.SI-ID:	27324931
NUK URN:	URN:SI:UM:DK:14N0EPXO
Publication date in DKUM:	03.07.2020
Views:	1685
Downloads:	107
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	01.05.2020

Secondary language

Language:	English
Title:	Detection of single person in depth image using convolutional neural networks
Abstract:	The goal of this thesis was the implementation of a system for automatic table height adjustment using a depth sensor. With the help of convolutional neural networks we have detected the user in the depth scene captured by the depth sensor. Using the detection we have also calculated the height of the user and based on his height we have adjusted the table height accordingly to the needs of the user (standing or sitting). We measured the user detection based on two metrics intersection over union (IoU) and F1 score. We achieved IoU value of 85,5% and F1 score of 92,3%. The average height calculation error was 0,092 meters.
Keywords:	neural networks, convolutional neural network, artificial inteligence, deep learning, human detection

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back