標題: VIDEO OBJECT INPAINTING USING MANIFOLD-BASED ACTION PREDICTION
作者: Ling, Chih-Hung
Liang, Yu-Ming
Lin, Chia-Wen
Chen, Yong-Sheng
Liao, Hong-Yuan Mark
資訊工程學系
Department of Computer Science
關鍵字: video inpainting;object completion;action prediction;synthetic posture;motion animation
公開日期: 2010
摘要: This paper presents a novel scheme for object completion in a video. The framework includes three steps: posture synthesis, graphical model construction, and action prediction. In the very beginning, a posture synthesis method is adopted to enrich the number of postures. Then, all postures are used to build a graphical model of object action which can provide possible motion tendency. We define two constraints to confine the motion continuity property. With the two constraints, possible candidates between every two consecutive postures are significantly reduced. Finally, we apply the Markov Random Field model to perform global matching. The proposed approach can effectively maintain the temporal continuity of the reconstructed motion. The advantage of this action prediction strategy is that it can handle the cases such as non-periodic motion or complete occlusion.
URI: http://hdl.handle.net/11536/26199
http://dx.doi.org/10.1109/ICIP.2010.5648911
ISBN: 978-1-4244-7994-8
ISSN: 1522-4880
DOI: 10.1109/ICIP.2010.5648911
期刊: 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
起始頁: 425
結束頁: 428
顯示於類別:會議論文


文件中的檔案:

  1. 000287728000105.pdf