Robust approach to reconstructing transparent objects using a time-of-flight depth camera

Kyungmin Kim, Hyunjung Shim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This study presents a robust approach to reconstructing a three dimensional (3-D) translucent object using a single time-of-flight depth camera with simple user marks. Because the appearance of translucent objects depends on the light interaction with the surrounding environment, the measurement using depth cameras is considerably biased or invalid. Although several existing methods attempt to model the depth error of translucent objects, their model remains partial because of object assumptions and its sensitivity to noise. In this study, we introduce a ground plane and piece-wise linear surface model as priors and construct a robust 3-D reconstruction framework for translucent objects. These two depth priors are combined with the depth error model built on the time-of-flight principle. Extensive evaluation of various real data reveals that the proposed method substantially improves the accuracy and reliability of 3-D reconstruction for translucent objects.

Original languageEnglish
Pages (from-to)2666-2676
Number of pages11
JournalOptics Express
Volume25
Issue number3
DOIs
Publication statusPublished - 2017 Feb 6

Fingerprint

cameras
depth measurement
evaluation
sensitivity
interactions

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics

Cite this

@article{d7d31c9d0c1b4e64b450e03c944d308e,
title = "Robust approach to reconstructing transparent objects using a time-of-flight depth camera",
abstract = "This study presents a robust approach to reconstructing a three dimensional (3-D) translucent object using a single time-of-flight depth camera with simple user marks. Because the appearance of translucent objects depends on the light interaction with the surrounding environment, the measurement using depth cameras is considerably biased or invalid. Although several existing methods attempt to model the depth error of translucent objects, their model remains partial because of object assumptions and its sensitivity to noise. In this study, we introduce a ground plane and piece-wise linear surface model as priors and construct a robust 3-D reconstruction framework for translucent objects. These two depth priors are combined with the depth error model built on the time-of-flight principle. Extensive evaluation of various real data reveals that the proposed method substantially improves the accuracy and reliability of 3-D reconstruction for translucent objects.",
author = "Kyungmin Kim and Hyunjung Shim",
year = "2017",
month = "2",
day = "6",
doi = "10.1364/OE.25.002666",
language = "English",
volume = "25",
pages = "2666--2676",
journal = "Optics Express",
issn = "1094-4087",
publisher = "The Optical Society",
number = "3",

}

Robust approach to reconstructing transparent objects using a time-of-flight depth camera. / Kim, Kyungmin; Shim, Hyunjung.

In: Optics Express, Vol. 25, No. 3, 06.02.2017, p. 2666-2676.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust approach to reconstructing transparent objects using a time-of-flight depth camera

AU - Kim, Kyungmin

AU - Shim, Hyunjung

PY - 2017/2/6

Y1 - 2017/2/6

N2 - This study presents a robust approach to reconstructing a three dimensional (3-D) translucent object using a single time-of-flight depth camera with simple user marks. Because the appearance of translucent objects depends on the light interaction with the surrounding environment, the measurement using depth cameras is considerably biased or invalid. Although several existing methods attempt to model the depth error of translucent objects, their model remains partial because of object assumptions and its sensitivity to noise. In this study, we introduce a ground plane and piece-wise linear surface model as priors and construct a robust 3-D reconstruction framework for translucent objects. These two depth priors are combined with the depth error model built on the time-of-flight principle. Extensive evaluation of various real data reveals that the proposed method substantially improves the accuracy and reliability of 3-D reconstruction for translucent objects.

AB - This study presents a robust approach to reconstructing a three dimensional (3-D) translucent object using a single time-of-flight depth camera with simple user marks. Because the appearance of translucent objects depends on the light interaction with the surrounding environment, the measurement using depth cameras is considerably biased or invalid. Although several existing methods attempt to model the depth error of translucent objects, their model remains partial because of object assumptions and its sensitivity to noise. In this study, we introduce a ground plane and piece-wise linear surface model as priors and construct a robust 3-D reconstruction framework for translucent objects. These two depth priors are combined with the depth error model built on the time-of-flight principle. Extensive evaluation of various real data reveals that the proposed method substantially improves the accuracy and reliability of 3-D reconstruction for translucent objects.

UR - http://www.scopus.com/inward/record.url?scp=85011664814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011664814&partnerID=8YFLogxK

U2 - 10.1364/OE.25.002666

DO - 10.1364/OE.25.002666

M3 - Article

AN - SCOPUS:85011664814

VL - 25

SP - 2666

EP - 2676

JO - Optics Express

JF - Optics Express

SN - 1094-4087

IS - 3

ER -