Surface reconstruction using the rapid segmentation and optimization method

Eungyeol Song, Sang Youn Lee, Sunjin Yu

Research output: Contribution to journalArticle

Abstract

We present a system for accurate reconstruction of a complex face model using only a moving low-cost depth camera and optimization algorithm. In this paper, we introduce a method to minimize the error of the depth images on the signed distance function (SDF). As the signed distance function contains the distances to the surface for each voxel, the camera coordinate estimation can be carried out rapidly with Levenberg–Marquardt that uses the camera pose and the preprocess data in the voxel grid. With this proposed method, a detailed reconstruction of an object can be achieved.

Original languageEnglish
Pages (from-to)3422-3425
Number of pages4
JournalAdvanced Science Letters
Volume22
Issue number11
DOIs
Publication statusPublished - 2016 Nov 1

Fingerprint

Surface Reconstruction
Surface reconstruction
segmentation
Optimization Methods
reconstruction
Segmentation
Camera
Cameras
Voxel
Distance Function
Signed
Costs and Cost Analysis
Optimization Algorithm
costs
cost
Face
Grid
Minimise
method
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Health(social science)
  • Mathematics(all)
  • Education
  • Environmental Science(all)
  • Engineering(all)
  • Energy(all)

Cite this

@article{9af48d025f6a4c258fce299d25d2fd2a,
title = "Surface reconstruction using the rapid segmentation and optimization method",
abstract = "We present a system for accurate reconstruction of a complex face model using only a moving low-cost depth camera and optimization algorithm. In this paper, we introduce a method to minimize the error of the depth images on the signed distance function (SDF). As the signed distance function contains the distances to the surface for each voxel, the camera coordinate estimation can be carried out rapidly with Levenberg–Marquardt that uses the camera pose and the preprocess data in the voxel grid. With this proposed method, a detailed reconstruction of an object can be achieved.",
author = "Eungyeol Song and Lee, {Sang Youn} and Sunjin Yu",
year = "2016",
month = "11",
day = "1",
doi = "10.1166/asl.2016.7894",
language = "English",
volume = "22",
pages = "3422--3425",
journal = "Advanced Science Letters",
issn = "1936-6612",
publisher = "American Scientific Publishers",
number = "11",

}

Surface reconstruction using the rapid segmentation and optimization method. / Song, Eungyeol; Lee, Sang Youn; Yu, Sunjin.

In: Advanced Science Letters, Vol. 22, No. 11, 01.11.2016, p. 3422-3425.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Surface reconstruction using the rapid segmentation and optimization method

AU - Song, Eungyeol

AU - Lee, Sang Youn

AU - Yu, Sunjin

PY - 2016/11/1

Y1 - 2016/11/1

N2 - We present a system for accurate reconstruction of a complex face model using only a moving low-cost depth camera and optimization algorithm. In this paper, we introduce a method to minimize the error of the depth images on the signed distance function (SDF). As the signed distance function contains the distances to the surface for each voxel, the camera coordinate estimation can be carried out rapidly with Levenberg–Marquardt that uses the camera pose and the preprocess data in the voxel grid. With this proposed method, a detailed reconstruction of an object can be achieved.

AB - We present a system for accurate reconstruction of a complex face model using only a moving low-cost depth camera and optimization algorithm. In this paper, we introduce a method to minimize the error of the depth images on the signed distance function (SDF). As the signed distance function contains the distances to the surface for each voxel, the camera coordinate estimation can be carried out rapidly with Levenberg–Marquardt that uses the camera pose and the preprocess data in the voxel grid. With this proposed method, a detailed reconstruction of an object can be achieved.

UR - http://www.scopus.com/inward/record.url?scp=85013414573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013414573&partnerID=8YFLogxK

U2 - 10.1166/asl.2016.7894

DO - 10.1166/asl.2016.7894

M3 - Article

AN - SCOPUS:85013414573

VL - 22

SP - 3422

EP - 3425

JO - Advanced Science Letters

JF - Advanced Science Letters

SN - 1936-6612

IS - 11

ER -