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 conferenceObject |
URI: | http://wscg.zcu.cz/WSCG2006/Papers_2006/Short/!WSCG2006_Short_Proceedings_Final.pdf http://hdl.handle.net/11025/6605 |
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 | Size | Format | |
---|---|---|---|---|
Li_Zhang.pdf | Plný text | 456,26 kB | Adobe PDF | View/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.