Title: 3D Human Animation from 2D Monocular Data Based on Motion Trend Prediction
Authors: Zhang, Li
Li, Ling
Citation: WSCG '2006: Short Papers Proceedings: The 14-th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2006: University of West Bohemia, Plzen, Czech Republic, January 31 - February 2, 2006, p. 117-124.
Issue Date: 2006
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: http://wscg.zcu.cz/WSCG2006/Papers_2006/Short/!WSCG2006_Short_Proceedings_Final.pdf
ISBN: 80-86943-05-4
Keywords: animace člověka;3D rekonstrukce pohybu
Keywords in different language: human animation;3D motion reconstruction
Abstract: A model-based method is proposed in this paper for 3-dimensional human motion recovery, taking un-calibrated monocular data as input. The proposed method is able to generate smooth human motions that resemble the original motion from the same viewpoint the sequence was taken, and look continuous from any other viewpoint. The core of the proposed system is the motion trend prediction for reconstruction. To focus the research effort on motion reconstruction, “synthesized” input is first employed to ensure that the reconstruction algorithm is developed and evaluated accurately. Experiment results on real video data indicate that the proposed method is able to recover human motion from un-calibrated 2D monocular images with very high accuracy.
Rights: © Václav Skala - UNION Agency
Appears in Collections:WSCG '2006: Short Papers Proceedings

Files in This Item:
File Description SizeFormat 
Li_Zhang.pdfPlný text456,26 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/6605

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.