Metode antropometrijskih mjerenja

master's thesis

• Title (english): Methods of Anthropometric Measurements
• Author: Martin Vrpoljac
• Mentor: Tomislav Pribanić (mentor)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-02-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovome radu opisali smo metode pronalaska antropometrijskih mjera pomoću sustava baziranih na računalnom vidu i dubokom učenju. Rezultati tih sustava moguće je primijeniti na različitim područjima, kao što su odjevna industrija, medicina i u proizvodnji anatomskog namještaja (kao što su uredske stolice i stolovi). Sustavi se automatiziraju kako bi se ubrzala i olakšala mjerenja, jer za sami proces ručnog mjerenja mjeritelj mora biti osposobljen locirati antropometrijske lokacije. Implementirani sustav omogućava pronalazak antropometrijskih mjera promatrane osobe iz njene fotografije, te se znatno ubrzava i olakšava način pronalaska istih, što je kasnije moguće implementirati u daljnje sustave.

Abstract (english)

In this work, we describe methods for finding anthropometric measurements using systems based on computer vision and deep learning. The results of those systems can be applied in various fields, such as clothing industry, medicine and in production of anatomical furniture (such as office chairs and desks). The systems are automated to speed up and facilitate anthropometric measurements, because for getting manual measurements, measurer must have knowledge to be able to locate anthropometric locations correctly, which takes time and experience. The implemented system enables easier discovery of anthropometric measures of observed person from her photograph, and significantly speeds up process of finding them, which can later be implemented in larger systems.

• Keywords: antropometrija; antropometrijske mjere; antropometrijske lokacije; antropometrijske točke; računalni vid; duboko učenje; strojno učenje; Python; OpenCV
• Keywords (english): anthropometry; anthropometric measures; anthropometric landmarks; computer vision; deep learning; machine learning; Python; OpenCV
• Language: croatian
• URN:NBN: urn:nbn:hr:168:181437
• 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: 2023-01-13 10:52:39