Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera

Takuya Ikeda, Yuji Oyamada, Maki Sugimoto, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Optical consistency between the real world and the virtual objects is one of the important issues in Augmented Reality (AR). This paper proposes a method to estimate illuminations from an object shadow and incomplete object shape information captured by an RGB-D camera. The environmental illumination can be estimated without any prior knowledge of the object shape. The radiance of each light source is computed by solving linear equations derived from color and depth images. Since a priori knowledge of object shape is not necessary, we can flexibly use/combine any objects. Thus, we can use/combine multiple objects in the target scene to increase the accuracy and flexibility. Experimental results show the characteristics of our proposed method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages165-169
Number of pages5
Publication statusPublished - 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: 2012 Nov 112012 Nov 15

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period12/11/1112/11/15

Fingerprint

Lighting
Cameras
Augmented reality
Linear equations
Light sources
Color

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ikeda, T., Oyamada, Y., Sugimoto, M., & Saito, H. (2012). Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera. In Proceedings - International Conference on Pattern Recognition (pp. 165-169). [6460098]

Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera. / Ikeda, Takuya; Oyamada, Yuji; Sugimoto, Maki; Saito, Hideo.

Proceedings - International Conference on Pattern Recognition. 2012. p. 165-169 6460098.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ikeda, T, Oyamada, Y, Sugimoto, M & Saito, H 2012, Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera. in Proceedings - International Conference on Pattern Recognition., 6460098, pp. 165-169, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 12/11/11.
Ikeda T, Oyamada Y, Sugimoto M, Saito H. Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera. In Proceedings - International Conference on Pattern Recognition. 2012. p. 165-169. 6460098
Ikeda, Takuya ; Oyamada, Yuji ; Sugimoto, Maki ; Saito, Hideo. / Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera. Proceedings - International Conference on Pattern Recognition. 2012. pp. 165-169
@inproceedings{eada99b955354845870a1450ac1da56d,
title = "Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera",
abstract = "Optical consistency between the real world and the virtual objects is one of the important issues in Augmented Reality (AR). This paper proposes a method to estimate illuminations from an object shadow and incomplete object shape information captured by an RGB-D camera. The environmental illumination can be estimated without any prior knowledge of the object shape. The radiance of each light source is computed by solving linear equations derived from color and depth images. Since a priori knowledge of object shape is not necessary, we can flexibly use/combine any objects. Thus, we can use/combine multiple objects in the target scene to increase the accuracy and flexibility. Experimental results show the characteristics of our proposed method.",
author = "Takuya Ikeda and Yuji Oyamada and Maki Sugimoto and Hideo Saito",
year = "2012",
language = "English",
isbn = "9784990644109",
pages = "165--169",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - Illumination estimation from shadow and incomplete object shape captured by an RGB-D camera

AU - Ikeda, Takuya

AU - Oyamada, Yuji

AU - Sugimoto, Maki

AU - Saito, Hideo

PY - 2012

Y1 - 2012

N2 - Optical consistency between the real world and the virtual objects is one of the important issues in Augmented Reality (AR). This paper proposes a method to estimate illuminations from an object shadow and incomplete object shape information captured by an RGB-D camera. The environmental illumination can be estimated without any prior knowledge of the object shape. The radiance of each light source is computed by solving linear equations derived from color and depth images. Since a priori knowledge of object shape is not necessary, we can flexibly use/combine any objects. Thus, we can use/combine multiple objects in the target scene to increase the accuracy and flexibility. Experimental results show the characteristics of our proposed method.

AB - Optical consistency between the real world and the virtual objects is one of the important issues in Augmented Reality (AR). This paper proposes a method to estimate illuminations from an object shadow and incomplete object shape information captured by an RGB-D camera. The environmental illumination can be estimated without any prior knowledge of the object shape. The radiance of each light source is computed by solving linear equations derived from color and depth images. Since a priori knowledge of object shape is not necessary, we can flexibly use/combine any objects. Thus, we can use/combine multiple objects in the target scene to increase the accuracy and flexibility. Experimental results show the characteristics of our proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84874568988&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874568988&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84874568988

SN - 9784990644109

SP - 165

EP - 169

BT - Proceedings - International Conference on Pattern Recognition

ER -