臺灣博碩士論文加值系統

隨著2010年 3D電影與 3D 電視的崛起，越來越多人注意到3D 視訊的相關技術。在未來，3D 視訊必會成為熱門焦點。然而，相比於傳統的 2D 視訊，3D 視訊的資料量更為龐大。在網路傳輸頻寬有限的情形下，勢必得藉由編碼技術達到資料減量，但卻也會因此造成3D 的品質降低。如何在頻寬有限的條件下，依然保持不錯的 3D 品質就顯得格外重要。本論文提出一種基於 3D 品質最佳化的位元率控制技術。我們假設 3D 視訊係以包含彩色與深度序列的格式來進行傳輸，編碼時可對該兩種不同性質序列進行聯合位元率控制。本系統先以 3D 品質評估演算法對訓練視訊 (training sequence) 進行評估，找出能夠得到最佳 3D 品質的彩色/深度位元率分配比例，以此當作訓練資料建立支持向量迴歸模型 (Support Vector Regression, SVR)。實際編碼時，透過分析彩色畫面與深度畫面的特性，並利用所建立的支持向量迴歸模型來預測彩色與深度間的位元分配比例，藉此達到控制位元率以達 3D 品質最佳化的目的。經由實驗結果發現，本文技術比起分開進行位元率控制可以擁有更精確的位元率 (平均增加精確度達 0.4%~2.3%)，而同時保有在解碼端較佳的 3D 視訊品質。

致謝 i
摘要 ii
目錄 iii
圖目錄 iv
表目錄 v
第一章 緒論 1
1.1 研究動機與背景 1
1.2 相關文獻介紹 1
1.2.1 3D 視訊品質評估相關文獻 1
1.2.2 H.264/SVC 位元率控制技術相關文獻 4
1.3 本論文架構 8
第二章 支持向量迴歸技術 12
2.1 基本原理 12
2.2 交叉驗證技術 14
2.3 本論文訓練資料集設計 15
2.3.1目標輸出值 15
2.3.2輸入特徵向量 17
第三章 H.264/SVC位元率控制技術 21
3.1 基本原理 21
3.2 位元率控制技術 23
3.2.1 GOP 階層位元率控制 23
3.2.2畫面階層位元率控制 24
3.2.3基本單位階層位元率控制 27
3.3 本論文聯合位元率控制技術 30
第四章 實驗結果與分析 33
4.1實驗設定 33
4.2實驗結果分析 55
第五章 結論與未來工作 53
5.1 結論 53
5.2 未來工作 53
參考文獻 54

[1]Z. G. Li, F. Pan, and K. P. Lim, Adaptive Basic Unit Layer Rate Control for JVT, JVT-G012, 7th Meeting, Thailand, 2003.
[2]MPEG-4 Video Verofication Model 18.0, ISO/IEC JTC1/SC29/WG11, Doc. MPEG-N3908, Apr. 2001.
[3]J. Ribas-Corbera, and S. Lei, “Rate Control in DCT Video Coding for Low-delay Communications,” IEEE Trans. on Circuits Systems for Video Technology, Vol. 9, No.1, pp. 172~185, Feb. 1999.
[4]A. Leontaris, and A. M. Tourapis, “Rate Control Reorganization in the Joint Model (JM) Reference Software,” Doc. JVT-W042, California, Apr. 2007.
[5]A. Leontaris, and A. M. Tourapis, “Rate Control for the Joint Scalable Video model (JSVM),” Doc. JVT-W043, California, Apr. 2007.
[6]Donghyun Kim, Seungchul Ryu, and Kwanghoon Sohn, “Depth Perception and Motion Cue Based 3D Video Quality Assessment,” IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB-2012), Seoul, June 2012.
[7]Chaminda T.E.R. Hewage, and Maria G. Martini, “Quality Evaluation for Real-time 3D Video Services,” Proc. of IEEE Int’l Conf. on Multimedia and Expo (ICME-2011), Barcelona, Spain, July 2011.
[8]Chaminda T.E.R. Hewage, and Maria G. Martini, “Edge-based Reduced-Reference Quality Metric for 3-D Video Compression and Transmission,” IEEE Journal of Selected Topics in Signal Processing, Vol. 6, No.5, pp.471~482, Apr. 2012.
[9]Chaminda T.E.R. Hewage, and Maria G. Martini, “Reduced-reference Quality Evaluation for Compressed Depth Maps Associated With Colour Plus Depth 3D Video,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2010), pp.4017~4020, Hong Kong, Oct. 2010.
[10]Chaminda T.E.R. Hewage, and Maria G. Martini, “Reduced-reference Quality Metric for 3D Depth Map Transmission,” 3DTV-Conference:The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), pp. 1~4, Tampere, Finland, June 2010.
[11]Kwangsung Ha, and Munchurl Kim, “A Perceptual Quality Assessment Metric Using Temporal Complexity and Disparity Information for Stereoscopic Video,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2011), pp. 2525~2528 , Brussels, Sep. 2011.
[12]A. Benoit, P. Le Callet, P. Campisi, and R. Cousseau,“Using Disparity for Quality Assessment of Stereoscopic Images,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2008), pp. 389~392, Brussels, San Diego, USA, Sep. 2008.
[13]Meng Liu, Yi Guo, Houqiang Li, and Chang-Wen Chen “Low-complexity Rate Control Based on ρ-Domain Model for Scalable Video Coding,” Proc. of IEEE Int’l Conf. on Image Processing (ICIP-2010), pp.1277~1280, Hong Kong, Oct. 2010.
[14]Jin Yang, Yu Sun, Yimin Zhou, and Shixin Sun, “Incremental Rate Control for H.264 Scalable Video Coding,” IEEE Global Telecommunications Conference (GLOBECOM 2010), pp.1~5, Miami, USA, Dec. 2010.
[15]O. Chapelle, V. vapnik, O. Bousquet, and S. Mukherjee, “Choosing Multiple Parameters for Support Vector Machines,” Machine Learning, Vol. 46, No. 1~3, pp.131~159, Jan. 2002.
[16]A. J. Smola, and B. Scholkopf, “A Tutorial on Support Vector Regression,” Statistics and Computing, pp.199~222, Aug. 2004.
[17]N. Cristianini, and J. Shawe-Taylor, “An Introduction to Support Vector Machines and Other Kernel-based Learning Methods”, Cambridge University Press, Cambridge, UK, 2000.
[18]Chih-Chung Chang, and Chih-Jen Lin, LIBSVM: A Library for Support Vector Machines, 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/
[19]R. C. Gonzalez, and R. E. Woods, “Digital Image Processing,” 2nd Edition, Prentice Hall, Upper Saddle River, NJ, 2002.
[20]Y. Morvan, D. Farin, and Peter H. N. de, “Joint Depth/Texture Bit-allocation for Multiview Video Compression,” Proc. of Picture Coding Symposium (PCS), Nov. 2007.
[21]Heiko Schwarz, and Dmytro Rusanovskyy, “Common Test Conditions for 3DV Experimentation,” ISO/IEC JTC1/SC29/WG11, Doc. MPEG-N12745, Geneva, Switzerland, May 2012.
[22]H. Schwarz, D. Marpe, and T. Wiegand, “Overview of the Scalable Video Coding Extension of the H.264/AVC Standard,” IEEE Trans. on Circuits Systems for Video Technology, Vol. 17, No.9, pp. 1103~1120, Sep. 2007.
[23]Tao Zhu, Xiong-wei Zhang, “Rate Control Scheme for Spatial Scalability of H.264/SVC,” Przegląd Elektrotechniczny, 2011.
[24]L. Xu, W. Gao, X. Ji , D. Zhao and S. Ma , “Rate Control for Spatial Scalable Coding in SVC,” Proc. of Picture Coding Symposium (PCS), 2007.