Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2010, Vol. 11 Issue (4): 270-277    DOI: 10.1631/jzus.C0910308
    
Exemplar-based video inpainting with large patches
Abbas Koochari, Mohsen Soryani
Department of Computer Engineering, Iran University of Science and Technology, Tehran 16846-13114, Iran
Exemplar-based video inpainting with large patches
Abbas Koochari, Mohsen Soryani
Department of Computer Engineering, Iran University of Science and Technology, Tehran 16846-13114, Iran
 全文: PDF(516 KB)  
摘要： Inpainting is the process of reconstructing damaged regions of images and video frames. This study deals with weaknesses of the current video inpainting techniques, when an object is totally damaged, and a framework for video inpainting is proposed. Using this framework, the moving object is separated from the background. A large mosaic image is constructed using the moving object and then a patch-based method with large patches is used to fill holes. In each frame, the inpainted foreground is obtained by placing the object in its location. Missing areas of the stationary background are also filled separately and the final video is produced by composing the inpainted background and object frames. Results for three video sequences with an occluded object show that this approach represents the object in the missing region better than other approaches.
关键词： Video inpainting;  Patch;  Background modeling;  Mosaic    
Abstract: Inpainting is the process of reconstructing damaged regions of images and video frames. This study deals with weaknesses of the current video inpainting techniques, when an object is totally damaged, and a framework for video inpainting is proposed. Using this framework, the moving object is separated from the background. A large mosaic image is constructed using the moving object and then a patch-based method with large patches is used to fill holes. In each frame, the inpainted foreground is obtained by placing the object in its location. Missing areas of the stationary background are also filled separately and the final video is produced by composing the inpainted background and object frames. Results for three video sequences with an occluded object show that this approach represents the object in the missing region better than other approaches.
Key words: Video inpainting    Patch    Background modeling    Mosaic
收稿日期: 2009-05-24 出版日期: 2010-03-22
CLC:  TP391.41  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Abbas Koochari
Mohsen Soryani

引用本文:

Abbas Koochari, Mohsen Soryani. Exemplar-based video inpainting with large patches. Front. Inform. Technol. Electron. Eng., 2010, 11(4): 270-277.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.C0910308    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2010/V11/I4/270

[1] Kai ZHU, Gang LIU , Long ZHAO , Wan ZHANG. Label fusion for segmentation via patch based on local weighted voting[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(5): 680-688.
[2] Hong-chao Ma, Jie Sun. Intelligent optimization of seam-line finding for orthophoto mosaicking with LiDAR point clouds[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(5): 417-429.