Praćenje zdravstvenog stanja starijih osoba putem računalnog vida

master's thesis

• Title (english): Computer Vision for Health Monitoring of Senior Citizens
• Author: Nikola Vrbanić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Slobodan Ribarić (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-19, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Demografske projekcije predviđaju znatan porast starije populacije u sljedećih 50 godina. Poznata je činjenica da se u zdravstvu troši značajno više na stariju populaciju. Potrebno je uložiti napore u povećanje kvalitete života starijih ljudi te prevenciju mogućih oboljenja i ozljeda. U okviru ovog rada proučeni su mogući načini praćenja zdravlja starijih osoba putem računalnog vida. Opisan je korišten model i sve njegove komponente. Ručno je sakupljen skup podataka za treniranje i evaluaciju modela te napravljeni eksperimenti. Dobiveni rezultati prikazani su i diskutirani.

Abstract (english)

Demographic projections predict a significant increase in the older population over the next 50 years. It is well-known that the elderly spend significantly more on healthcare than the average population. Efforts should be made to increase the quality of life of older people and to prevent possible illness and injury. Within this paper, possible ways of monitoring the health of the elderly through computer vision are studied. The model and all its components are described. A set of training and evaluation data sets and experiments were collected manually. The results obtained are presented and discussed.

• Keywords: računalni vid; strojno učenje; stroj potpornih vektora; konvolucijske neuronske mreže; duboko učenje; estimacija poze
• Keywords (english): Computer vision; machine learning; svm; convolutional neural networks; deep learning; pose estimation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:954376
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 22:57:32