| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document

Title:Avtomatizacija ergonomsko oblikovanega delovnega mesta s pomočjo računalniškega vida in naprave Kinect
Authors:Bratanović, Alen (Author)
Haložan, David (Mentor) More about this mentor... New window
Stričević, Jadranka (Co-mentor)
Kokol, Marko (Co-mentor)
Files:.pdf MAG_Bratanovic_Alen_2018.pdf (5,43 MB)
MD5: 12CD57C17D165D0FC9FB0AA14BD925E5
 
Language:Slovenian
Work type:Master's thesis/paper (mb22)
Typology:2.09 - Master's Thesis
Organization:FZV - Faculty of Health Sciences
Abstract:Izhodišča: V okviru našega magistrskega dela smo raziskovali povezavo naprednih računalniških tehnologij, kot je računalniški vid, pri reševanju problemov na področju ergonomije delovnega mesta. Z uporabo naprave Kinect, ki ponuja možnost razvoja aplikacij na omenjenem področju, smo pripravili lastno aplikacijo za avtomatiziran izračun tveganja po metodi RULA. Metodologija: Potrjevali smo dve hipotezi: da je računalniška ocena podobna ročni oceni in da lahko Kinect aplikacija zazna primere, ki so problematični iz ergonomskega vidika na podlagi RULA ocene. Aplikacijo smo empirično preizkusili s pomočjo eksperimenta, ki smo ga izvedli na delovnem mestu medicinske sestre. Rezultate raziskave smo statistično obdelali in izvedli Wilcoxonov test predznačenih rangov med ročno in avtomatično oceno in s pomočjo Fisherjevega eksaktnega testa za male vzorce preverili, ali Kinect aplikacija pravilno klasificira problematične položaje. Rezultati: Rezultati so pokazali, da se ročne in avtomatične ocene bistveno ne razlikujejo (Z= -1,414, p = 0,157) in da klasifikacija položajev bistveno odstopa od naključja (p=0,007). Sklep: Na podlagi pridobljenih rezultatov in izvedene statistične analize smo dokazali sposobnost, uporabnost in sprejemljivo natančnost naprave Kinect za avtomatsko ocenjevanje ergonomskih položajev po metodi RULA na delovnem mestu.
Keywords:ergonomija, metoda RULA, programska oprema, informacijski sistem, obdelava slik
Year of publishing:2018
Publisher:[A. Bratanović]
Source:Maribor
UDC:331.101.1:004(043.2)
COBISS_ID:2466212 New window
NUK URN:URN:SI:UM:DK:GZQW1W0I
Views:562
Downloads:85
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:FZV
:
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

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:19.05.2018

Secondary language

Language:English
Title:Automation of ergonomically designed workplace using computer vision and Kinect device
Abstract:Starting points: Our study was focused on the use of advanced computing technologies, specifically computer vision algorithms in workplace ergonomics. By utilizing Kinect, we developed an application for automated RULA assessment. Methodology: We studied two hypotheses: that a grade calculated by automated assessment methods is like the one calculated by a human and that the Kinect based application can determine, which positions are more problematic from an ergonomics point of view, based on the RULA grade. Using the application, we designed an empirical study using an experiment, which we performed on the case of typical work that a nurse must perform as part of her job. Results from the study were analysed using statistical methods and we performed Wilcoxon signed-rank test between human based and computer based grades and Fisher exact test for small sample size to determine if Kinect application correctly classifies positions determined to be problematic. Results: The results showed that manual and automatic estimates do not significantly differ (Z= -2,716, p = 0,157) and the number of correctly determine problematic positions is significant (p=0,007). Conclusion: Based on the obtained results and statistical analysis we proved the ability, usability and acceptable accuracy of the Kinect device for automatic assessment of ergonomic positions according to the RULA method at the workplace.
Keywords:ergonomics, RULA method, software, information system, image processing


Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica