Računalni vid u antropometrijskim mjerenjima

undergraduate thesis

• Title (english): Computer Vision in Anthropometric Measurements
• Author: Una Ikić
• Mentor: Tomislav Petković (mentor)
• Committee member: Tomislav Petković (predsjednik povjerenstva)
• Committee member: Kristijan Bartol (član povjerenstva)
• Committee member: Luka Posilović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-06-30, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Antropometrijska mjerenja imaju mnogobrojne primjene u ergonomiji, arhitekturi, dizajnu odjeće i industrijskom dizajnu. Korištenje računalnog vida u antropometrijskim mjerenjima olakšava mjerenje te može zamijeniti tradicionalno ručno mjerenje antropometrijskim instrumentima, pogotovo u slučajevima kada ima puno ispitanika. U ovome radu korišten je OpenPose, slobodno dostupan sustav jednostavan za korištenje koji detektira ključne točke ljudskog tijela na slici. Korištenjem OpenPose-a i ručnim mjerenjem izmjerena je duljina desne ruke za osam subjekata. Bland-Altmanovom analizom rezultata ručnog mjerenja i rezultata dobivenih OpenPoseom pokazano jest da OpenPose daje rezultate sukladne ručnom mjerenju amaterskih mjeritelja. No obzirom na ostvarenu preciznost mjerenja OpenPose nije prikladan za mjerenja koja zahtijevaju visoku preciznost.

Abstract (english)

Anthropometric measurements have many applications in ergonomics, architecture, clothing and industrial design. The use of computer vision in anthropometric measurements simplifies the measurements and it may replace the traditional manual measurement which use anthropometric instruments, especially in cases where there are many subjects to measure. In this bachelor thesis OpenPose is used. It is a freely available and easy to use system for real-time multi-person pose tracking which detects human body keypoints in an image. Using OpenPose and using manual measurement the length of the right arm was measured for eight subjects. The Bland-Altman analysis of the manual measurements and of the OpenPose measurements shows that OpenPose approach is consistent with manual measurements of amateur measurers. However, given the achieved measurement precision OpenPose is not suitable for measurements which require high precision.

• Keywords: antropometrija; OpenPose; ključne točke; Bland-Altmanova analiza
• Keywords (english): anthropometry; OpenPose; keypoints; Bland-Altman analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:891921
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 08:55:31