Return to search

Dynamic 3D-Torrent Assembly for Bit-Rate Adjustments in P2P Video Streaming

In this Thesis, we propose a mechanism to dynamically adjust the video bit rates
through the segmentation and the reassembly of SVC (Scalable Video Coding)
segments in a P2P network. At the transmitter, an SVC film is segmented into a
number of segments with different sizes. Each segment is further chopped into
Torrents according to three scalabilities of SVC (Temporal, Quality, and Spatial). The
Torrents with three scalabilities are referred to as 3D-Torrents. At the receiver, we
present three approaches of grabbing Torrents (Temporal-First, Quality-First and
Interleaving) form P2P networks to validate that the proposed 3D-Torrent reassembly
can adapt to different bandwidths and to fit different hardware equipments so that any
possible video freeze-up time can be avoided.
To demonstrate how the proposed 3D-Torrent reassembly affect video bit rates in
the P2P video streaming environment, we implement the segmentation, grabbing, and
reassembly of Torrents on a Linux platform. In the P2P network built by Hadoop, we
study (i) the video freeze-up time with/without adopting 3D-Torrent reassembly, (ii)
video quality under different grabbing approaches using two different types of video,
static and active background. To compare the video quality at the transmitter to that at
the receiver, we modify the conventional PSNR equation. Two new dimensions,
Temporal and Spatial, are included in the new PSNR3D equation to compare the video
quality between the transmitter and the receiver. From the experimental results, we
observe that the freeze-up time approaches zero using the 3D-Torrent reassembly and
video bit rates can be dynamically adjusted according to the available bandwidth.

Identiferoai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0827110-153308
Date27 August 2010
CreatorsLin, Ching-Chen
ContributorsCe-Kuen Shieh, Tsang-Ling Sheu, Ren-hung Hwang, Sheng-Tzong Cheng, Cheng-Shong Wu
PublisherNSYSU
Source SetsNSYSU Electronic Thesis and Dissertation Archive
LanguageCholon
Detected LanguageEnglish
Typetext
Formatapplication/pdf
Sourcehttp://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0827110-153308
Rightswithheld, Copyright information available at source archive

Page generated in 0.0011 seconds