Video inpainting for largely occluded moving human

Haomian Wang, Houqiang Li, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, a video inpainting approach is proposed, which targets at repairing a video containing moving humans that are largely or completely occluded or missing for some of the frames. The proposed approach first categorizes typically periodic human motion in a video into a set of temporal states (called motion states), and then estimates the motion states for the frames with missing humans so as to repair the missing parts using other undamaged frames with the same motion states. This deviates from common approaches that directly repair the pixels of the damaged parts. Experiments demonstrate that the proposed method can well repair the damaged video sequences without introducing strong artifacts that exist in many existing techniques.

Original languageEnglish (US)
Title of host publicationProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Pages1719-1722
Number of pages4
StatePublished - 2007
EventIEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China
Duration: Jul 2 2007Jul 5 2007

Other

OtherIEEE International Conference onMultimedia and Expo, ICME 2007
CountryChina
CityBeijing
Period7/2/077/5/07

Fingerprint

Repair
Pixels
Experiments

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Wang, H., Li, H., & Li, B. (2007). Video inpainting for largely occluded moving human. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007 (pp. 1719-1722). [4285001]

Video inpainting for largely occluded moving human. / Wang, Haomian; Li, Houqiang; Li, Baoxin.

Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 1719-1722 4285001.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, H, Li, H & Li, B 2007, Video inpainting for largely occluded moving human. in Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007., 4285001, pp. 1719-1722, IEEE International Conference onMultimedia and Expo, ICME 2007, Beijing, China, 7/2/07.
Wang H, Li H, Li B. Video inpainting for largely occluded moving human. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 1719-1722. 4285001
Wang, Haomian ; Li, Houqiang ; Li, Baoxin. / Video inpainting for largely occluded moving human. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. pp. 1719-1722
@inproceedings{aed8ab1ac6324a8d9008a536b502ddea,
title = "Video inpainting for largely occluded moving human",
abstract = "In this paper, a video inpainting approach is proposed, which targets at repairing a video containing moving humans that are largely or completely occluded or missing for some of the frames. The proposed approach first categorizes typically periodic human motion in a video into a set of temporal states (called motion states), and then estimates the motion states for the frames with missing humans so as to repair the missing parts using other undamaged frames with the same motion states. This deviates from common approaches that directly repair the pixels of the damaged parts. Experiments demonstrate that the proposed method can well repair the damaged video sequences without introducing strong artifacts that exist in many existing techniques.",
author = "Haomian Wang and Houqiang Li and Baoxin Li",
year = "2007",
language = "English (US)",
isbn = "1424410177",
pages = "1719--1722",
booktitle = "Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007",

}

TY - GEN

T1 - Video inpainting for largely occluded moving human

AU - Wang, Haomian

AU - Li, Houqiang

AU - Li, Baoxin

PY - 2007

Y1 - 2007

N2 - In this paper, a video inpainting approach is proposed, which targets at repairing a video containing moving humans that are largely or completely occluded or missing for some of the frames. The proposed approach first categorizes typically periodic human motion in a video into a set of temporal states (called motion states), and then estimates the motion states for the frames with missing humans so as to repair the missing parts using other undamaged frames with the same motion states. This deviates from common approaches that directly repair the pixels of the damaged parts. Experiments demonstrate that the proposed method can well repair the damaged video sequences without introducing strong artifacts that exist in many existing techniques.

AB - In this paper, a video inpainting approach is proposed, which targets at repairing a video containing moving humans that are largely or completely occluded or missing for some of the frames. The proposed approach first categorizes typically periodic human motion in a video into a set of temporal states (called motion states), and then estimates the motion states for the frames with missing humans so as to repair the missing parts using other undamaged frames with the same motion states. This deviates from common approaches that directly repair the pixels of the damaged parts. Experiments demonstrate that the proposed method can well repair the damaged video sequences without introducing strong artifacts that exist in many existing techniques.

UR - http://www.scopus.com/inward/record.url?scp=46449110043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46449110043&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1424410177

SN - 9781424410170

SP - 1719

EP - 1722

BT - Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

ER -