隨著智慧型手機和平板電腦等手持裝置的興起，使用者對於網路串流影片和即時串流的需求也日益增加，這樣的趨勢也間接地促進許多即時串流技術的發展，如Adobe’s RTMP、Microsoft’s Smooth Streaming以及Apple’s HTTP Live Streaming等，而傳輸方式也逐漸以通用性高的HTTP-based Streaming為主流。
而在串流影片時期，網路頻寬發生變化往往可能會導致播放不順暢或影片延遲的現象，造成不好的使用者體驗，為了改善這種現象，自適性串流機制是一種常被用在用戶端串流時的決策方式，讓用戶端的裝置可以依據當前的網路狀況選擇不同的影片品質，不過若伺服器端提供的影片品質選擇過少，所能改善的空間就會因此受到限制。
本文基於HTTP即時串流協定提出了一套頻寬評估機制，並且在TI PandaBoard開發版移植Google Android 4.0 Ice Crream Sandwich作業系統作為HTTP即時串流用戶端，而在伺服器端則是定義一模式轉移狀態機和三種評估失誤型態，根據頻寬評估的結果來觀察當前網路變化的情況，在不同的模式下分別採取不同的轉換編碼策略，計算合適的媒體片段位元率，將媒體片段轉換編碼為符合當前連線品質的片段，經過HTTP重新導向技術，讓HTTP即時串流用戶端能觀賞到較適切的影片品質，最後則以PNSR和頻寬使用率分析作為影片品質提升的參考指標。據實驗結果顯示，本研究於一般的網路行為可提升PSNR約2.8dB並於串流期間維持在80%以上的頻寬使用率。

Due to the rising popularity of smart phones and tablets, the need for multimedia streaming and live video streaming increases daily on these handheld devices, causing the rapid development of live streaming protocols such as Adobe’s RTMP, Microsoft’s Smooth Streaming and Apple’s HTTP Live Streaming.
The variations of bandwidth due to environmental or external reasons may result in unsmooth playback or interruptions of video during video playing. In order to improve quality of video streaming, adaptive streaming is proposed to be a solution for client end devices. The streaming client can choose the suitable quality of media segment when there are different qualities of video pre-encoded and stored at server. However the less the choice of quality selections provided for clients, the more limited the improvement can be made.
In this paper, we propose a bandwidth evaluation mechanism based on HTTP Live Streaming, and port Google Android 4.0 Ice Cream Sandwich operating system on TI PandaBoard. On server side, we define a mode-transition finite state machine as well as three estimated error types. According to the result of bandwidth evaluation, we can determine the current state of network, and compute the suitable bitrate of media segment by different methods in different modes. Then the client of HTTP Live Streaming can receive a segment with the more suitable bitrate than that of the original mechanism of HTTP Live Streaming via the technique of HTTP redirecting after transrating. Finally, we analyze the PSNR and bandwidth usage as the performance metrics of quality of video streaming, and the result shows that the video quality of HTTP live streaming is improved by using our approach.

[1] M. Barr, and A. J. Massa, “Programming embedded systems: with C and GNU development tools”, O’Reilly Media, Inc., pp.1-2., 2006.
[2] K. J. Ma, R. Bartoˇs, S. Bhatia, and R. Nair, “Mobile video delivery with HTTP,” IEEE Communications Magazine, vol. 49, no. 4, pp. 166–175, Apr. 2011.
[3] V. Swaminathan, and S. Wei, “Low latency live video streaming using HTTP chunked encoding,” in Proc. of IEEE 13th International Workshop on Multimedia Signal Processing, pp. 1-6, Oct 2011.
[4] A. Goel, C. Krasic, and J. Walpole, “Low-latency adaptive streaming over TCP,” ACM Trans. Multimedia Computing Commun. and Applications, vol. 4, no. 3, Aug. 2008, article 20.
[5] P.Frossard, J. C. de Martin, and M Reha Civanlar, “Media Streaming With Network Diversity,” Proceedings of the IEEE, vol. 96, no. 1, Jan. 2008.
[6] H. S. Lee, H. Y. Youn, and H. D. Jung, “Packet control mechanism for seamless multimedia streaming service in wireless network,” in Proc. of ICACT 2006 Advanced Communication Technology, vol. 3, pp. 1833-1838, Feb. 2006.
[7] J. Guo, and L. N. Bhuyan, “Load Balancing in a Cluster-Based Web Server for Multimedia Applications,” IEEE Trans. Parallel and Distributed Systems, vol. 17, no. 11, pp. 1321-1334, Nov. 2006.
[8] A. Mahmood, T. Jinnah, Y. Asfia, and G. A. Shah, “A hybrid adaptive compression scheme for Multimedia Streaming over wireless networks,” in Proc. of ICET 2008. 4th International Emerging Technologies, pp. 187-192, Oct. 2008.
[9] S. Y. Wu, and C. E. He, “QoS-Aware Dynamic Adaptation for Cooperative Media Streaming in Mobile Environments,” IEEE Trans. Parallel and Distributed Systems, vol. 22, no. 3, pp. 439-450, Mar. 2011.
[10] A. Begen, T. Akgul, and M. Baugher, “Watching Video over the Web: Part 1: Streaming Protocols,” IEEE Internet Computing, vol. 15, no. 2, pp. 54-63, Mar.-Apr 2011.
[11] “The Next Big Thing in Video: Adaptive Bitrate Streaming,” http://pro.gigaom.com/2009/06/how-to-deliver-as-much-video-as-users-can-take/, retrieved on June 2012.
[12] W. Wu, A. Arefin, R. Rivas, K. Nahrstedt, R. Sheppard, and Z. Yang, “Quality of Experience in Distributed Interactive Multimedia Environments: Toward a Theoretical Framework,” in Proc. of ACM 17th International Conference on Multimedia, pp. 481-490, 2009.
[13] M. Medagama, D. Dias, S. Fernado, “Transcoding based optimum quality video streaming under limited bandwidth,” in Proc. of 2009 International Conference on ICIIS, pp. 62-67, Dec. 2009.
[14] H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson, “RTP: a transport protocol for real-time applications,” Internet Engineering Task Force (IETF), RFC 3550, July 2003.
[15] R. Pantos, “HTTP Live Streaming,” Internet Engineering Task Force (IETF), Internet-Draft Version 8 (draft-pantos-http-live-streaming-08), Mar. 2012.
[16] ITU-T, “H.222.0 : Information technology – Generic coding of moving pictures and associated audio information: Systems,” http://www.itu.int/rec/T-REC-H.222.0, retrieved on June 2012.
[17] “TCPDUMP”, http://www.tcpdump.org/, retrieved on June 2012.
[18] “PandaBoard”, http://pandaboard.org/, retrieved on June 2012.
[19] Khronos, “OpenMAX – The Standard for Media Library Portability”, http://www.khronos.org/openmax/, retrieved on June 2012.
[20] “Android@Mobile World Congress: It’s all about the ecosystem. ” , http://googlemobile.blogspot.fr/2012/02/androidmobile-world-congress-its-all.html, retrieved on June 2012.
[21] “Google unveils Android@Home”, http://www.zdnetasia.com/videos/google-unveils-androidhome-62300298.htm, retrieved on June 2012.
[22] Y. Shi, K. Casey, M. A. Ertl, D. Gregg, “Virtual machine showdown: Stack versus registers,” ACM Transactions on Architecture and Code Optimization, vol. 4, no. 4, article 2, Jan. 2008.
[23] “Android Supported Media Formats”, http://developer.android.com/guide/appendix/media-formats.html, retrieved on June 2012.
[24] D. Vatolin, D. Kulikov, A. Parshin, M. Arsaev, and A. Voronov, “MPEG-4 AVC/H.264 Video Codecs Comparison”, http://www.compression.ru/video/codec_comparison/h264_2011/mpeg-4_avc_h264_video_codecs_comparison.pdf , retrieved on June 2012.
[25] PacketVideo, “PacketVideo – powering interactive media experiences for mobile and consumer electronics service providers”, retrieved on June 2012.
[26] J. Z. Chen, “Design and Integration of DVB-T Playback into Android OpenCORE on Heterogeneous Multicore Platform”, Taiwan: NCKU, July 2010.
[27] C. Y. Liu, “Android Stagefright Performance Enhancement and Dynamic Streaming Adjustment Mechanism on Heterogeneous Multicore Platform”, Taiwan: NCKU, July 2011.
[28] “Initializing a Build Environment”, http://source.android.com/source/initializing.html, retrieved on June 2012.
[29] Q. Tang, H. Mansour, P. Nasiopoulos, and R. Ward, “Bit-rate estimation for bit-rate reduction H.264/AVC video transcoding in wireless networks,” in Proc. of ISWPC 2008 3rd International Symposium on Wireless Pervasive Computing, pp. 464-467, May 2008.