臺灣博碩士論文加值系統

本論文提出了一套在P2P 網路上，針對影音串流進行SVC 影片的切割與
Torrent 的組合方式來完成傳輸速率的動態調整，我們在傳送端將SVC 影片切割
成大小不同的Segments，再將每一個Segment 依據SVC 的三種Scalability
(Temporal, Quality, Spatial)切割成更細小的Torrents，我們稱之為3D-Torrent，在
接收端我們提出三種不同的Torrents 抓取方式 (Temporal-First、Quality-First、
Interleave)，用這三種方式來驗證不同的Torrents 組合以因應不同網路的可用頻
寬與不同的硬體設備，其目的是避免影像停格。
為了驗證3D-Torrent 動態組合對P2P 影音串流速率改變的影響，我們以實作
的方式，在Linux 平台上完成Torrents 的切割、抓取與重組，藉由Hadoop 平台
作為實驗環境以建立P2P 網路，我們比較了不同的Torrents 抓取順序與不同的
Torrents 分佈對影片品質好壞的影響，而為了能比較所接收到的影片品質好壞，
我們修改了傳統的PSNR 公式，加入Temporal 與Spatial 的變化以提出全新的公
式，用來計算傳送端與接收端的畫面差異與影片品質的好壞，我們使用兩種不同
類型的影片來比較不同的Torrent 抓取順序與分佈對影片品質好壞的影響，另外
我們也實測有使用3D-Torrent 與沒有使用3D-Torrent時對Freeze-up時間的影響，
從Freeze-up 時間的幾近於零，我們可以驗證此3D-Torrent 的動態組合機制是可
以根據網路可用頻寬來調整影片的Bit Rates。

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.

第一章 導論............................................................................................................ 1
1.1 研究動機 ............................................................................................................................... 1
1.2 研究方法 ............................................................................................................................... 2
1.3 章節介紹 ............................................................................................................................... 5
第二章 P2P 網路中的SVC 影音串流 .................................................................. 6
2.1 P2P 網路 ............................................................................................................................... 6
2.1.1 Hadoop 與MapReduce ................................................................................................... 6
2.1.2 HDFS ............................................................................................................................... 7
2.2 SVC ...................................................................................................................................... 8
2.3 TRANSCODING .................................................................................................................... 11
2.4 P2P 影音串流相關研究 ..................................................................................................... 11
2.4.1 P2P 上的影音串流 ........................................................................................................ 12
2.4.2 調整SVC 影音串流的層級 ........................................................................................... 12
第三章 3D-TORRENT 的動態組合 ................................................................... 15
3.1 SEGMENTS 與3D-TORRENT ............................................................................................... 15
3.1.1 Video 切割成3D-Torrent .............................................................................................. 16
3.1.2 VS 的即時性判斷 .......................................................................................................... 17
3.2 TORRENTS 的抓取與重新組合 .......................................................................................... 18
第四章 LINUX 上實作與結果分析 .................................................................... 25
4.1 實驗拓樸與TORRENTS 分佈 ............................................................................................. 25
4.1.1 使用HDFS 的拓樸架構 ............................................................................................... 25
4.1.2 Torrents 分佈 ................................................................................................................. 27
4.2 LINUX 平台上3D-TORRENT 的實作 ................................................................................. 28
4.2.1 切割模組 ........................................................................................................................ 28
4.2.2 抓取與重組模組 ............................................................................................................ 29
4.3 效能評估 ............................................................................................................................. 30
4.3.1 PSNR3D的Temporal 變化 ............................................................................................. 31
4.3.2 PSNR3D的Spatial 變化 ................................................................................................. 33
4.3.3 PSNR3D ........................................................................................................................... 36
4.4 量測結果與分析 ................................................................................................................. 37
4.4.1 層級調整與畫面順暢度比較 ........................................................................................ 37
4.4.2 PSNR3D的量測 .............................................................................................................. 39
4.4.3 Spatial Scalability .......................................................................................................... 44
第五章 結論與未來工作 ..................................................................................... 45
5.1 結論 .................................................................................................................................... 45
5.2 未來工作 ............................................................................................................................. 47
參考資料(REFERENCES) ........................................................................................ 49
ACRONYMS .............................................................................................................. 53
索引.............................................................................................................................. 54

[1] Apache Hadoop, http://hadoop.apache.org/.
[2] J. Dean and S. Ghemawat, “MapReduce: Simplified Data Processing on Large
Clusters,” Sixth Symposium on Operating System Design and Implementation,
December, 2004.
[3] S. Konstantin, K. Hairong, R. Sanjay, and C. Robert, “The Hadoop Distributed
File System,” IEEE 26th Symposium on Mass Storage Systems and
Technologies (MSST), May, 2010.
[4] S. Ghemawat, H. Gobioff, and S. T. Leung, “The Google File System,” 19th
ACM Symposium on Operating Systems Principles, October, 2003.
[5] T. Wiegand, G. J. Sullivan, G. Bjøntegaard, and A. Luthra, “Overview of the
H.264/AVC Video Coding Standard,” IEEE Transactions on Circuits and
Systems for Video Technology, vol. 13, no. 7, pp. 560-576, July, 2003.
[6] H. Schwarz and M. Wien, “The Scalable Video Coding Extension of the
H.264/AVC Standard [Standards in a Nutshell],” IEEE Signal Processing
Magazine, vol. 25, no. 2, pp. 135-141, March, 2008.
[7] “Advanced Video Coding for Generic Audiovisual Services,” ITU-T, ITU-T
Recommendation H.264, March, 2010.
[8] Y. K. Wang, M. M. Hannuksela, S. Pateux, A. Eleftheriadis, and S. Wenger,
“System and Transport Interface of SVC,” IEEE Transactions on Circuits and
Systems for Video Technology, vol. 17, no. 9, pp. 1149-1163, September, 2007.
[9] A. Vetro, C. Christopoulos, and H. Sun, “An Overview of Video Transcoding
Architectures and Techniques,” IEEE Signal Processing Magazine, vol. 20, no.
2, pp. 18-29, March, 2003.
[10] P. Amon, Li. Haoyu, A. Hutter, D. Renzi, and S. Battista, “Scalable Video
Coding and Transcoding,” IEEE International Conference on Automation,
Quality and Testing, Robotics, May, 2008.
[11] Y. He, I. Lee, and L. Guan, “Distributed Throughput Maximization in P2P VoD
Applications,” IEEE Transactions on Multimedia, vol. 11, no. 3, pp. 509-522,
April, 2009.
[12] X. Y. Zhang, Q. Zhang, Z. Zhang, G. Song, and W. Zhu, “A Construction of
Locality-aware Overlay Network: mOverlay and its Performance,” IEEE
Journal on Selected Areas in Communications, vol. 22, no. 1, pp. 18-28, January,
2004.
[13] W. Zhang, Q. Zheng, and Y. Lian, “Tree-aware Selective Frame Discard for P2P
IPTV System on Set-top Boxes,” IEEE Transactions on Consumer Electronics,
vol. 55, no. 4, pp. 1982-1987, November, 2009.
[14] D. Kim, J. Lee, Y. Lee, and H. Kim, “AVS: An Adaptive P2P Video Streaming
Scheme with Frame Type Aware Scheduling,” The 9th International Conference
on Advanced Communication Technology, February, 2007.
[15] C. M. Lin, J. K. Zao, W. H. Peng, C. C. Hu, H. M. Chen, and C. K. Yang,
“Bandwidth Efficient Video Streaming Based Upon Multipath SVC
Multicasting,” International Wireless Communications and Mobile Computing
Conference, August, 2008.
[16] J. Wu, Y. Peng, and F. Liu, “Transmission Scheduling in Data-Driven
Peer-to-Peer Streaming towards Optimal Throughput,” IEEE International
Conference on Networking, Architecture, and Storage, July, 2009.
[17] T. C. Lee, P. C. Liu, W. L. Shyu, and C. Y. Wu, “Live Video Streaming Using
P2P and SVC,” 11th IFIP/IEEE International Conference on Management of
Multimedia and Mobile Networks and Services, September, 2008.
18] H. L. Chen, P. C. Lee, and S. H. Hu, “Improving Scalable Video Transmission
over IEEE 802.11e through a Cross-Layer Architecture,” The Fourth
International Conference on Wireless and Mobile Communications, July, 2008.
19] P. Chen, J. Lim, B. Lee, M. Kim, S. Hahm, B. Kim, K. Lee, and K. Park, “A
Network-adaptive SVC Streaming Architecture,” The 9th International
Conference on Advanced Communication Technology, February, 2007.
20] H. Lee, Y. Lee, J. Lee, D. Lee, and H. Shin, “Design of a Mobile Video
Streaming System using Adaptive Spatial Resolution Control,” IEEE
Transactions on Consumer Electronics, vol. 55, no. 3, pp. 1682-1689, August,
2009.
21] H. Choi, J. W. Kang, and J. G. Kim, “Dynamic and Interoperable Adaptation of
SVC for QoS-Enabled Streaming,” IEEE Transactions on Consumer
Electronics, vol. 53, no. 2, pp. 384-389, May, 2007.
22] W. H. J. Chen and J. N. Hwang, “Ordered Statistics Decoding of Linear Block
Codes for Robust H.263 Video Transmission in AWGN Channel,” IEEE Second
Workshop on Multimedia Signal Processing, December, 1998.
23] G. M. Su, Z. Han, M. Wu, and K. J. Ray Liu, “Joint Uplink and Downlink
Optimization for Real-Time Multiuser Video Streaming Over WLANs,” IEEE
Journal of Selected Topics in Signal Processing, vol. 1, no. 2, pp. 280-294,
August, 2007.
24] S. R. Kang and D. Loguinov, “Modeling Best-Effort and FEC Streaming of
Scalable Video in Lossy Network Channels,” IEEE/ACM Transactions on
Networking, vol. 15, no. 1, pp. 187-200, February, 2007.
[25] J. N. Hwang, “Multimedia Networking,” Cambridge University Press, 2009