Ocenjevanje teoretične in empirične napake meritev razdalj na ravnini s pametnimi telefoni

Fučka, Matic (author), Skočaj, Danijel (mentor)

Brezkontaktno optično merjenje razdalj na ravnini je eden izmed problemov računalniškega vida. Osredotočili smo se na merjenje razdalj v ravnini s pomočjo referenčnega lista. Poznane mere lista formata A4 nam omogočajo izračun homografije preslikave s slikovne ravnine v svetovne koordinate. Pogosto zaradi napačno izmerjenih parametrov kamere pride do napake v tej preslikavi in posledično do napake v meritvi razdalj. Zanimalo nas je, ali je mogoče to napako teoretično določiti. Napako smo najprej izpeljali analitično. Nato smo obravnavali vpliv napak posamičnih parametrov na končno napako ter si ogledali njihov vpliv na izračunano pozicijo in orientacijo kamere. Po obravnavi napak smo naše teoretične napovedi primerjali z empiričnimi podatki, ki so bili pridobljeni s procesiranjem slik kalibracijskega vzorca, zajetimi s pametnimi telefoni. Ugotovili smo, da naš model ustrezno napoveduje lokacijo preslikanega kalibracijskega vzorca. Ravno tako je izračunana lega kamere zelo blizu empirično izračunani poziciji kamere, ki pa se v precej primerih ne najbolj ujema z referenčno pozicijo. Izračunana orientacija kamere pa je zelo blizu tako referenčni kot tudi empirično izračunani orientaciji.

• Language: Slovenian
• Keywords: računalniški vid, kamera, homografija, optično merjenje razdalj, pametni telefon
• Work type: Bachelor thesis/paper
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science ; FMF - Faculty of Mathematics and Physics
• Year: 2020
• PID: 20.500.12556/RUL-120061
• COBISS.SI-ID: 31851267
• Publication date in RUL: 15.09.2020

FUČKA, Matic, 2020, Ocenjevanje teoretične in empirične napake meritev razdalj na ravnini s pametnimi telefoni [online]. Bachelor’s thesis. [Accessed 8 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=120061

Secondary language

• Language: English
• Title: Estimation of theoretical and empirical error in planar distance measurements with smartphones

Abstract

Non-contact distance measurement is one of the problems in computer vision. Our main focus of attention was distance measuring with a reference paper. Known size of an A4 paper enable us to calculate the homography matrix of the mapping from the image plane to the real world coordinate system. Frequently, the camera parameters are inaccurately estimated and this inaccuracy consequently contributes to the overall error in the measured distance. We decided to model this error rigorously. First we derived the error analytically. Then we looked into each parameter individually and discussed its contribution to the overall error to distance measuring and the contribution to the error in camera pose estimation. After the theoretical analysis we compared theoretical estimations with empirical data. Empirical data was gathered from several smartphones, which we calibrated using a known calibration pattern. We found out, that our model correctly estimates the location of the calibration pattern mapped to the real world coordinate system. Estimated camera pose does not accurately match the reference pose. The orientation of the camera is very close both to the empirical and the reference orientation.

• Keywords: computer vision, camera, homography, optical distance measurement, smart phone