Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/63973
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Inter-frame error concealment using graph cut technique for video transmission |
Author: | Wu, X. Shen, H. |
Citation: | Proceedings of the 3rd International Congress on Image and Signal Processing (CISP 2010), held in Yantai, China 16-18 October 2010: pp.253-257 |
Publisher: | IEEE |
Publisher Place: | USA |
Issue Date: | 2010 |
ISBN: | 9781424465163 |
Conference Name: | International Congress on Image and Signal Processing (3rd : 2010 : Yantai, China) |
Statement of Responsibility: | Xuanguo Wu and Hong Shen |
Abstract: | Due to channel noise and congestion, video data packets can be lost during transmission in error-prone networks, which severely affects the quality of received video sequences. The conventional inter-frame error concealment (EC) methods estimate a motion vector (MV) for a corrupted block or reconstruct the corrupted pixel values using spatial and temporal weighted interpolation, which may result in boundary discontinuity and blurring artifacts of the reconstructed region. In this paper, we reconstruct corrupted macroblock (MB) by predicting sub-partitions and synthesizing the corrupted MB to reduce boundary discontinuity and avoid blurring artifacts. First, we select the optimal MV for each neighboring boundary using minimum side match distortion from a candidate MV set, and then we calculate the optimal cut path between the overlapping regions to synthesize the corrupted MB. The simulation results show that our proposed method is able to achieve significantly higher PSNR as well as better visual quality than using the H.264/AVC reference software. |
Keywords: | Error concealment Side match distortion Graph cut Image synthesis H.264/AVC |
Rights: | ©2010 IEEE |
DOI: | 10.1109/CISP.2010.5648292 |
Published version: | http://dx.doi.org/10.1109/cisp.2010.5648292 |
Appears in Collections: | Aurora harvest 5 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.