Document Type
Article
Publication Date
January 2005
Publication Title
Signal Processing: Image Communication
Volume
20
Issue Number
1
First Page
21
Last Page
37
DOI
10.1016/j.image.2004.09.001
Abstract
Images or videos are generally coded before transmission, and they can be either non-scalable coded or scalable coded, which can be further classified into fine-scalable coded and coarse-scalable coded. In this paper, we focus on delivery of fine-scalable coded content. The objective of our work is to design algorithms to optimize the quality of fine-scalable coded images or videos on peer-to-peer networks when a requesting peer is delay-sensitive and has to display content within a certain delay bound. Fine-scalable coding has two properties: (1) it embeds lower bit-rate bitstreams into higher bit-rate bitstreams; and (2) its coding quality increases with every additional bit in the coded bitstream. These imply that for a given requesting peer, there may exist a dynamic set of supplying peers that have the same content coded in different bit-rates, have different outgoing bandwidth and may finish transmission at different times. In this paper, we first illustrate the importance of peer assignment problem using an example. Then we formally define and formulate the problem as two integer programming problems, from which we derive an optimal peer assignment solution. Finally, we carry out extensive experiments to verify the excellent performance of the proposed peer assignment algorithms by comparing with other heuristic schemes.
Recommended Citation
Xiao Su, Yi Shang, Tao Wang, and Yuqing Mai. "Delay-Constrained Transmission of Fine Scalable Coded Content over P2P Networks" Signal Processing: Image Communication (2005): 21-37. https://doi.org/10.1016/j.image.2004.09.001
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Comments
This is the Author's Accepted Manuscript of an article originally published in Signal Processing: Image Communication Vol. 20, Iss. 1, by Elsevier on January 2005, DOI: 10.1016/j.image.2004.09.001. This work is licensed under a Creative Commons CC_BY-NC-ND International License.The Version of Record is available online at this link.