Efficient object-based video inpainting

Sen Ching S. Cheung; Jian Zhao; M. Vijay Venkatesh

doi:10.1109/ICIP.2006.312432

Efficient object-based video inpainting

Sen Ching S. Cheung, Jian Zhao, M. Vijay Venkatesh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

51 Scopus citations

Abstract

Video inpainting describes the process of removing a portion of a video and filling in the missing part (hole) in a visually consistent manner. Most existing video in-painting techniques are computationally intensive and cannot handle large holes. In this paper, we propose a complete and efficient video inpainting system. Our system applies different strategies to handle static and dynamic portions of the hole. To inpaint the static portion, our system uses background replacement and image inpainting techniques. To inpaint moving objects in the hole, we utilizes background subtraction and object segmentation to extract a set of object templates and perform optimal object interpolation using dynamic programming. We evaluate the performance of our system based on a set of indoor surveillance sequences with different types of occlusions.

Original language	English
Title of host publication	2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings
Pages	705-708
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2006.312432
State	Published - 2006
Event	2006 IEEE International Conference on Image Processing, ICIP 2006 - Atlanta, GA, United States Duration: Oct 8 2006 → Oct 11 2006

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
ISSN (Print)	1522-4880

Conference

Conference	2006 IEEE International Conference on Image Processing, ICIP 2006
Country/Territory	United States
City	Atlanta, GA
Period	10/8/06 → 10/11/06

Bibliographical note

Funding Information:
The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.

Keywords

Dynamic programming
Image segmentation
Interpolation
Tracking
Video signal processing

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2006.312432

Cite this

@inproceedings{595b257619df421aa51808de974bfb5c,

title = "Efficient object-based video inpainting",

abstract = "Video inpainting describes the process of removing a portion of a video and filling in the missing part (hole) in a visually consistent manner. Most existing video in-painting techniques are computationally intensive and cannot handle large holes. In this paper, we propose a complete and efficient video inpainting system. Our system applies different strategies to handle static and dynamic portions of the hole. To inpaint the static portion, our system uses background replacement and image inpainting techniques. To inpaint moving objects in the hole, we utilizes background subtraction and object segmentation to extract a set of object templates and perform optimal object interpolation using dynamic programming. We evaluate the performance of our system based on a set of indoor surveillance sequences with different types of occlusions.",

keywords = "Dynamic programming, Image segmentation, Interpolation, Tracking, Video signal processing",

author = "Cheung, {Sen Ching S.} and Jian Zhao and Venkatesh, {M. Vijay}",

note = "Funding Information: The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.; 2006 IEEE International Conference on Image Processing, ICIP 2006 ; Conference date: 08-10-2006 Through 11-10-2006",

year = "2006",

doi = "10.1109/ICIP.2006.312432",

language = "English",

isbn = "1424404819",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "705--708",

booktitle = "2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings",

}

Cheung, SCS, Zhao, J & Venkatesh, MV 2006, Efficient object-based video inpainting. in 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings., 4106627, Proceedings - International Conference on Image Processing, ICIP, pp. 705-708, 2006 IEEE International Conference on Image Processing, ICIP 2006, Atlanta, GA, United States, 10/8/06. https://doi.org/10.1109/ICIP.2006.312432

Efficient object-based video inpainting. / Cheung, Sen Ching S.; Zhao, Jian; Venkatesh, M. Vijay.
2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings. 2006. p. 705-708 4106627 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Efficient object-based video inpainting

AU - Cheung, Sen Ching S.

AU - Zhao, Jian

AU - Venkatesh, M. Vijay

N1 - Funding Information: The authors would like to acknowledge the support of Department of Justice under the Grant 2004-IJ-CK-K055.

PY - 2006

Y1 - 2006

N2 - Video inpainting describes the process of removing a portion of a video and filling in the missing part (hole) in a visually consistent manner. Most existing video in-painting techniques are computationally intensive and cannot handle large holes. In this paper, we propose a complete and efficient video inpainting system. Our system applies different strategies to handle static and dynamic portions of the hole. To inpaint the static portion, our system uses background replacement and image inpainting techniques. To inpaint moving objects in the hole, we utilizes background subtraction and object segmentation to extract a set of object templates and perform optimal object interpolation using dynamic programming. We evaluate the performance of our system based on a set of indoor surveillance sequences with different types of occlusions.

AB - Video inpainting describes the process of removing a portion of a video and filling in the missing part (hole) in a visually consistent manner. Most existing video in-painting techniques are computationally intensive and cannot handle large holes. In this paper, we propose a complete and efficient video inpainting system. Our system applies different strategies to handle static and dynamic portions of the hole. To inpaint the static portion, our system uses background replacement and image inpainting techniques. To inpaint moving objects in the hole, we utilizes background subtraction and object segmentation to extract a set of object templates and perform optimal object interpolation using dynamic programming. We evaluate the performance of our system based on a set of indoor surveillance sequences with different types of occlusions.

KW - Dynamic programming

KW - Image segmentation

KW - Interpolation

KW - Tracking

KW - Video signal processing

UR - http://www.scopus.com/inward/record.url?scp=78649807632&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649807632&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2006.312432

DO - 10.1109/ICIP.2006.312432

M3 - Conference contribution

AN - SCOPUS:78649807632

SN - 1424404819

SN - 9781424404810

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 705

EP - 708

BT - 2006 IEEE International Conference on Image Processing, ICIP 2006 - Proceedings

T2 - 2006 IEEE International Conference on Image Processing, ICIP 2006

Y2 - 8 October 2006 through 11 October 2006

ER -

Efficient object-based video inpainting

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this