Virtual contour guided video object inpainting using posture mapping and retrieval

Chih Hung Ling*, Chia Wen Lin, Chih Wen Su, Yong-Sheng Chen, Hong Yuan Mark Liao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

27 Scopus citations

Abstract

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 inpainting 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.

Original languageEnglish
Article number5643929
Pages (from-to)292-302
Number of pages11
JournalIEEE Transactions on Multimedia
Volume13
Issue number2
DOIs
StatePublished - 1 Apr 2011

Keywords

  • Object completion
  • posture mapping
  • posture sequence retrieval
  • synthetic posture
  • video inpainting

Fingerprint

Dive into the research topics of 'Virtual contour guided video object inpainting using posture mapping and retrieval'. Together they form a unique fingerprint.

Cite this