Robustly registering range images using local distribution of albedo

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

We propose a robust method for registering overlapping range images of a Lambertian object under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, the albedo is promising to range image registration of Lambertian objects lacking in discriminative geometric features under variable illumination. We use adaptive regions in our method to model the local distribution of albedo, which enables us to stably extract the reliable attributes of each point against illumination estimates. We use a level-set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is also defined to match points in the overlapping area. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

Original languageEnglish
Pages (from-to)649-667
Number of pages19
JournalComputer Vision and Image Understanding
Volume115
Issue number5
DOIs
Publication statusPublished - May 1 2011
Externally publishedYes

Fingerprint

Lighting
Image registration
Rigidity
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Robustly registering range images using local distribution of albedo. / Thomas, Diego Gabriel Francis; Sugimoto, Akihiro.

In: Computer Vision and Image Understanding, Vol. 115, No. 5, 01.05.2011, p. 649-667.

Research output: Contribution to journalArticle

@article{79758f0611c64bbe875416dab20d2e94,
title = "Robustly registering range images using local distribution of albedo",
abstract = "We propose a robust method for registering overlapping range images of a Lambertian object under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, the albedo is promising to range image registration of Lambertian objects lacking in discriminative geometric features under variable illumination. We use adaptive regions in our method to model the local distribution of albedo, which enables us to stably extract the reliable attributes of each point against illumination estimates. We use a level-set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is also defined to match points in the overlapping area. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.",
author = "Thomas, {Diego Gabriel Francis} and Akihiro Sugimoto",
year = "2011",
month = "5",
day = "1",
doi = "10.1016/j.cviu.2010.11.016",
language = "English",
volume = "115",
pages = "649--667",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",
number = "5",

}

TY - JOUR

T1 - Robustly registering range images using local distribution of albedo

AU - Thomas, Diego Gabriel Francis

AU - Sugimoto, Akihiro

PY - 2011/5/1

Y1 - 2011/5/1

N2 - We propose a robust method for registering overlapping range images of a Lambertian object under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, the albedo is promising to range image registration of Lambertian objects lacking in discriminative geometric features under variable illumination. We use adaptive regions in our method to model the local distribution of albedo, which enables us to stably extract the reliable attributes of each point against illumination estimates. We use a level-set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is also defined to match points in the overlapping area. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

AB - We propose a robust method for registering overlapping range images of a Lambertian object under a rough estimate of illumination. Because reflectance properties are invariant to changes in illumination, the albedo is promising to range image registration of Lambertian objects lacking in discriminative geometric features under variable illumination. We use adaptive regions in our method to model the local distribution of albedo, which enables us to stably extract the reliable attributes of each point against illumination estimates. We use a level-set method to grow robust and adaptive regions to define these attributes. A similarity metric between two attributes is also defined to match points in the overlapping area. Moreover, remaining mismatches are efficiently removed using the rigidity constraint of surfaces. Our experiments using synthetic and real data demonstrate the robustness and effectiveness of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=79952280579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952280579&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2010.11.016

DO - 10.1016/j.cviu.2010.11.016

M3 - Article

VL - 115

SP - 649

EP - 667

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 5

ER -