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

研究成果: Article

20 引文 (Scopus)

摘要

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.

原文English
文章編號6506841
頁(從 - 到)1677-1686
頁數10
期刊IEEE Transactions on Visualization and Computer Graphics
19
發行號10
DOIs
出版狀態Published - 2013 九月 2

指紋

Aspect ratio
Cameras
Display devices
Experiments

All Science Journal Classification (ASJC) codes

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

引用此文

Lin, Shih Syun ; Lin, Chao Hung ; Yeh, I. Cheng ; Chang, Shu Huai ; Yeh, Chih Kuo ; Lee, Tong Yee. / Content-aware video retargeting using object-preserving warping. 於: IEEE Transactions on Visualization and Computer Graphics. 2013 ; 卷 19, 編號 10. 頁 1677-1686.
@article{bd035fb469c844e6b3019ac805a31af0,
title = "Content-aware video retargeting using object-preserving warping",
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.",
author = "Lin, {Shih Syun} and Lin, {Chao Hung} and Yeh, {I. Cheng} and Chang, {Shu Huai} and Yeh, {Chih Kuo} and Lee, {Tong Yee}",
year = "2013",
month = "9",
day = "2",
doi = "10.1109/TVCG.2013.75",
language = "English",
volume = "19",
pages = "1677--1686",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "10",

}

Content-aware video retargeting using object-preserving warping. / Lin, Shih Syun; Lin, Chao Hung; Yeh, I. Cheng; Chang, Shu Huai; Yeh, Chih Kuo; Lee, Tong Yee.

於: IEEE Transactions on Visualization and Computer Graphics, 卷 19, 編號 10, 6506841, 02.09.2013, p. 1677-1686.

研究成果: Article

TY - JOUR

T1 - Content-aware video retargeting using object-preserving warping

AU - Lin, Shih Syun

AU - Lin, Chao Hung

AU - Yeh, I. Cheng

AU - Chang, Shu Huai

AU - Yeh, Chih Kuo

AU - Lee, Tong Yee

PY - 2013/9/2

Y1 - 2013/9/2

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84883109745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883109745&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2013.75

DO - 10.1109/TVCG.2013.75

M3 - Article

C2 - 23929847

AN - SCOPUS:84883109745

VL - 19

SP - 1677

EP - 1686

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 10

M1 - 6506841

ER -