Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras

Y. Mukaigawa, D. Genda, Ryo Yamane, Takeshi Shakunaga

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

1 Citation (Scopus)

Abstract

A color blending method for generating a high quality image of human motion is presented. The 3D (three-dimensional) human shape is reconstructed by volume intersection and expressed as a set of voxels. As each voxel is observed as different colors from different cameras, voxel color needs to be assigned appropriately from several colors. We present a color blending method, which calculates voxel color from a linear combination of the colors observed by multiple cameras. The weightings in the linear combination are calculated based on both viewpoint and surface normal. As surface normal is taken into account, the images with clear texture can be generated. Moreover, since viewpoint is also taken into account, high quality images free of unnatural warping can be generated. To examine the effectiveness of the algorithm, a traditional dance motion was captured and new images were generated from arbitrary viewpoints. Compared to existing methods, quality at the boundaries was confirmed to improve.

Original languageEnglish
Title of host publicationIEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages95-100
Number of pages6
Volume2003-January
ISBN (Print)078037987X
DOIs
Publication statusPublished - 2003
EventIEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2003 - Tokyo, Japan
Duration: Jul 30 2003Aug 1 2003

Other

OtherIEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2003
CountryJapan
CityTokyo
Period7/30/038/1/03

Fingerprint

Cameras
Color
Image quality
Textures

Keywords

  • Biological system modeling
  • Cameras
  • Cultural differences
  • Humans
  • Image generation
  • Image reconstruction
  • Motion measurement
  • Position measurement
  • Shape
  • Surface texture

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Science Applications

Cite this

Mukaigawa, Y., Genda, D., Yamane, R., & Shakunaga, T. (2003). Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras. In IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (Vol. 2003-January, pp. 95-100). [1232639] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MFI-2003.2003.1232639

Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras. / Mukaigawa, Y.; Genda, D.; Yamane, Ryo; Shakunaga, Takeshi.

IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2003-January Institute of Electrical and Electronics Engineers Inc., 2003. p. 95-100 1232639.

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

Mukaigawa, Y, Genda, D, Yamane, R & Shakunaga, T 2003, Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras. in IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. vol. 2003-January, 1232639, Institute of Electrical and Electronics Engineers Inc., pp. 95-100, IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, MFI 2003, Tokyo, Japan, 7/30/03. https://doi.org/10.1109/MFI-2003.2003.1232639
Mukaigawa Y, Genda D, Yamane R, Shakunaga T. Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras. In IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2003-January. Institute of Electrical and Electronics Engineers Inc. 2003. p. 95-100. 1232639 https://doi.org/10.1109/MFI-2003.2003.1232639
Mukaigawa, Y. ; Genda, D. ; Yamane, Ryo ; Shakunaga, Takeshi. / Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras. IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems. Vol. 2003-January Institute of Electrical and Electronics Engineers Inc., 2003. pp. 95-100
@inproceedings{45ca8651f5874944bd1cdc0138f77610,
title = "Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras",
abstract = "A color blending method for generating a high quality image of human motion is presented. The 3D (three-dimensional) human shape is reconstructed by volume intersection and expressed as a set of voxels. As each voxel is observed as different colors from different cameras, voxel color needs to be assigned appropriately from several colors. We present a color blending method, which calculates voxel color from a linear combination of the colors observed by multiple cameras. The weightings in the linear combination are calculated based on both viewpoint and surface normal. As surface normal is taken into account, the images with clear texture can be generated. Moreover, since viewpoint is also taken into account, high quality images free of unnatural warping can be generated. To examine the effectiveness of the algorithm, a traditional dance motion was captured and new images were generated from arbitrary viewpoints. Compared to existing methods, quality at the boundaries was confirmed to improve.",
keywords = "Biological system modeling, Cameras, Cultural differences, Humans, Image generation, Image reconstruction, Motion measurement, Position measurement, Shape, Surface texture",
author = "Y. Mukaigawa and D. Genda and Ryo Yamane and Takeshi Shakunaga",
year = "2003",
doi = "10.1109/MFI-2003.2003.1232639",
language = "English",
isbn = "078037987X",
volume = "2003-January",
pages = "95--100",
booktitle = "IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Color blending based on viewpoint and surface normal for generating images from any viewpoint using multiple cameras

AU - Mukaigawa, Y.

AU - Genda, D.

AU - Yamane, Ryo

AU - Shakunaga, Takeshi

PY - 2003

Y1 - 2003

N2 - A color blending method for generating a high quality image of human motion is presented. The 3D (three-dimensional) human shape is reconstructed by volume intersection and expressed as a set of voxels. As each voxel is observed as different colors from different cameras, voxel color needs to be assigned appropriately from several colors. We present a color blending method, which calculates voxel color from a linear combination of the colors observed by multiple cameras. The weightings in the linear combination are calculated based on both viewpoint and surface normal. As surface normal is taken into account, the images with clear texture can be generated. Moreover, since viewpoint is also taken into account, high quality images free of unnatural warping can be generated. To examine the effectiveness of the algorithm, a traditional dance motion was captured and new images were generated from arbitrary viewpoints. Compared to existing methods, quality at the boundaries was confirmed to improve.

AB - A color blending method for generating a high quality image of human motion is presented. The 3D (three-dimensional) human shape is reconstructed by volume intersection and expressed as a set of voxels. As each voxel is observed as different colors from different cameras, voxel color needs to be assigned appropriately from several colors. We present a color blending method, which calculates voxel color from a linear combination of the colors observed by multiple cameras. The weightings in the linear combination are calculated based on both viewpoint and surface normal. As surface normal is taken into account, the images with clear texture can be generated. Moreover, since viewpoint is also taken into account, high quality images free of unnatural warping can be generated. To examine the effectiveness of the algorithm, a traditional dance motion was captured and new images were generated from arbitrary viewpoints. Compared to existing methods, quality at the boundaries was confirmed to improve.

KW - Biological system modeling

KW - Cameras

KW - Cultural differences

KW - Humans

KW - Image generation

KW - Image reconstruction

KW - Motion measurement

KW - Position measurement

KW - Shape

KW - Surface texture

UR - http://www.scopus.com/inward/record.url?scp=84858990786&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858990786&partnerID=8YFLogxK

U2 - 10.1109/MFI-2003.2003.1232639

DO - 10.1109/MFI-2003.2003.1232639

M3 - Conference contribution

AN - SCOPUS:84858990786

SN - 078037987X

VL - 2003-January

SP - 95

EP - 100

BT - IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -