Content-aware video retargeting using object-preserving warping

Shih Syun Lin, Chao Hung Lin, I. Cheng Yeh, Shu Huai Chang, Chih Kuo Yeh, Tong Yee Lee

Research output: Contribution to journalArticlepeer-review

23 Citations (Scopus)

Abstract

A novel content-aware warping approach is introduced for video retargeting. The key to this technique is adapting videos to fit displays with various aspect ratios and sizes while preserving both visually salient content and temporal coherence. Most previous studies solve this spatiotemporal problem by consistently resizing content in frames. This strategy significantly improves the retargeting results, but does not fully consider object preservation, sometimes causing apparent distortions on visually salient objects. We propose an object-preserving warping scheme with object-based significance estimation to reduce this unpleasant distortion. In the proposed scheme, visually salient objects in 3D space-time space are forced to undergo as-rigid-as-possible warping, while low-significance contents are warped as close as possible to linear rescaling. These strategies enable our method to consistently preserve both the spatial shapes and temporal motions of visually salient objects and avoid overdeformations on low-significance objects, yielding a pleasing motion-aware video retargeting. Qualitative and quantitative analyses, including a user study and experiments on complex videos containing diverse cameras and dynamic motions, show a clear superiority of our method over related video retargeting methods.

Original languageEnglish
Article number6506841
Pages (from-to)1677-1686
Number of pages10
JournalIEEE Transactions on Visualization and Computer Graphics
Volume19
Issue number10
DOIs
Publication statusPublished - 2013 Sep 2

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Content-aware video retargeting using object-preserving warping'. Together they form a unique fingerprint.

Cite this