標題: Virtual Contour Guided Video Object Inpainting Using Posture Mapping and Retrieval
作者: Ling, Chih-Hung
Lin, Chia-Wen
Su, Chih-Wen
Chen, Yong-Sheng
Liao, Hong-Yuan Mark
資訊工程學系
Department of Computer Science
關鍵字: Object completion;posture mapping;posture sequence retrieval;synthetic posture;video inpainting
公開日期: 1-四月-2011
摘要: This paper presents a novel framework for object completion in a video. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and performs patch-based image in-painting to complete the partially damaged object trajectories in the 2-D slices. The completed slices are then combined to obtain a sequence of virtual contours of the damaged object. Next, a posture sequence retrieval technique is applied to the virtual contours to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are used to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of postures so as to reduce the effect of insufficient postures. Our experiment results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously.
URI: http://dx.doi.org/10.1109/TMM.2010.2095000
http://hdl.handle.net/11536/9094
ISSN: 1520-9210
DOI: 10.1109/TMM.2010.2095000
期刊: IEEE TRANSACTIONS ON MULTIMEDIA
Volume: 13
Issue: 2
起始頁: 292
結束頁: 302
顯示於類別:期刊論文


文件中的檔案:

  1. 000288661800011.pdf