Video Inpainting for Largely Occluded Moving Human
Haomian Wang
Houqiang Li
Baoxin Li
Univ. of Sci. & Technol., Hefei;
This paper appears in: Multimedia and Expo, 2007 IEEE International Conference on
Publication Date: 2-5 July 2007
On page(s): 1719-1722
Location: Beijing,
ISBN: 1-4244-1016-9
INSPEC Accession Number: 9804607
Digital Object Identifier: 10.1109/ICME.2007.4285001
Current Version Published: 2007-08-08
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.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
