Efficient object-based video inpainting

被引：31

作者：

Cheung, Sen-Ching S. ^{[1
]}

Zhao, Jian ^{[1
]}

Venkatesh, M. Vijay ^{[1
]}

机构：

[1] Univ Kentucky, Ctr Visualizat & Virtual Environm, Lexington, KY 40507 USA

来源：

2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS | 2006年

关键词：

video signal processing; interpolation; image segmentation; tracking; dynamic programming;

D O I：

10.1109/ICIP.2006.312432

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 inpainting 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.

引用

页码：705 / +

页数：2

共 8 条

[1]

[Anonymous], 1990, TIME VARYING IMAGE P

[2]

[Anonymous], P IEEE INT C IM PROC

[3]

Bertalmio M., 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, V1, pI, DOI DOI 10.1109/CVPR.2001.990497

[4] Region filling and object removal by exemplar-based image inpainting [J].

Criminisi, A ;

Pérez, P ;

Toyama, K .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (09) :1200-1212

[5]

Horprasert T., 1999, P IEEE FRAM RAT APPL

[6]

Wexler Y, 2004, PROC CVPR IEEE, P120

[7]

WICKRAMASURIYA J, 2004, ACM INT C MULT NEW Y

[8]

Zhang W., 2005, P 12 IEEE INT C IM P

← 1 →