fulltext.pdf 645 KB
Mukaigawa, Yasuhiro University of Tsukuba
Genda, Daisuke Okayama University
Yamane, Ryo Okayama University
Shakunaga, Takeshi Okayama University
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.
image colour analysis
image motion analysis
Digital Object Identifier: 10.1109/MFI-2003.2003.1232639
Published with permission from the copyright holder. This is the institute's copy, as published in Multisensor Fusion and Integration for Intelligent Systems, MFI2003. Proceedings of IEEE International Conference on, 30 July-1 Aug. 2003, Pages 95-100.
Copyright © 2003 IEEE. All rights reserved.
Multisensor Fusion and Integration for Intelligent Systems