Moving object completion is a process of completing moving object's missing information based on local structures. Over the past few years, a number of computable algorithms of video completion have been developed, however most of these algorithms are based on the pixel domain. Little theoretical and computational work in video completion is based on the compressed domain. In this paper, a moving object completion method on the compressed domain is proposed. It is composed of three steps: motion field transferring, thin plate spline interpolation and combination. Missing space-time blocks will be completed by placing new motion vectors on them so that the resulting video sequence will have as much global visual coherence with the video portions outside the hole. The experimental results are presented to demonstrate the efficiency and accuracy of the proposed algorithm.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Jiang YIWEI, Xu DE, Liu NA, Lang CONGYAN, "Moving Object Completion on the Compressed Domain" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 7, pp. 1496-1499, July 2009, doi: 10.1587/transinf.E92.D.1496.
Abstract: Moving object completion is a process of completing moving object's missing information based on local structures. Over the past few years, a number of computable algorithms of video completion have been developed, however most of these algorithms are based on the pixel domain. Little theoretical and computational work in video completion is based on the compressed domain. In this paper, a moving object completion method on the compressed domain is proposed. It is composed of three steps: motion field transferring, thin plate spline interpolation and combination. Missing space-time blocks will be completed by placing new motion vectors on them so that the resulting video sequence will have as much global visual coherence with the video portions outside the hole. The experimental results are presented to demonstrate the efficiency and accuracy of the proposed algorithm.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.1496/_p
Copy
@ARTICLE{e92-d_7_1496,
author={Jiang YIWEI, Xu DE, Liu NA, Lang CONGYAN, },
journal={IEICE TRANSACTIONS on Information},
title={Moving Object Completion on the Compressed Domain},
year={2009},
volume={E92-D},
number={7},
pages={1496-1499},
abstract={Moving object completion is a process of completing moving object's missing information based on local structures. Over the past few years, a number of computable algorithms of video completion have been developed, however most of these algorithms are based on the pixel domain. Little theoretical and computational work in video completion is based on the compressed domain. In this paper, a moving object completion method on the compressed domain is proposed. It is composed of three steps: motion field transferring, thin plate spline interpolation and combination. Missing space-time blocks will be completed by placing new motion vectors on them so that the resulting video sequence will have as much global visual coherence with the video portions outside the hole. The experimental results are presented to demonstrate the efficiency and accuracy of the proposed algorithm.},
keywords={},
doi={10.1587/transinf.E92.D.1496},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Moving Object Completion on the Compressed Domain
T2 - IEICE TRANSACTIONS on Information
SP - 1496
EP - 1499
AU - Jiang YIWEI
AU - Xu DE
AU - Liu NA
AU - Lang CONGYAN
PY - 2009
DO - 10.1587/transinf.E92.D.1496
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2009
AB - Moving object completion is a process of completing moving object's missing information based on local structures. Over the past few years, a number of computable algorithms of video completion have been developed, however most of these algorithms are based on the pixel domain. Little theoretical and computational work in video completion is based on the compressed domain. In this paper, a moving object completion method on the compressed domain is proposed. It is composed of three steps: motion field transferring, thin plate spline interpolation and combination. Missing space-time blocks will be completed by placing new motion vectors on them so that the resulting video sequence will have as much global visual coherence with the video portions outside the hole. The experimental results are presented to demonstrate the efficiency and accuracy of the proposed algorithm.
ER -