成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	林威丞 Lin, Wei-Cheng
論文名稱：	用於低耗電MPEG/H.264影像編解碼器之降低記憶體存取機制 Memory Access Reduction for Low Power MPEG/H.264 Video Codec
指導教授：	陳中和 Chen, Chung-Ho
學位類別：	博士 Doctor
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2008
畢業學年度：	96
語文別：	英文
論文頁數：	97
中文關鍵詞：	記憶體存取、記憶體節能、多媒體系統、動態影像編解碼、靜態宏塊
外文關鍵詞：	reusable data, stationary macroblock, MPEG, H.264, frame memory, memory access
相關次數：	點閱：142 下載：1
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

對於具有動態影像編解碼能力的可移動式多媒體系統，如何有效降低電源消耗以延長電池壽命是一重要的議題。動態影像編解碼器需要存取大量未壓縮的影像資料以執行動態向量搜尋與影像重建，這不但使記憶體成為系統效能的瓶頸，並且成為系統的主要耗能元件。在此篇論文中我們提出降低記憶體存取的方法。首先我們利用靜態宏塊的特性去偵測MPEG-4影像解碼器記憶體中可重複使用的宏塊資料，再利用可重複使用的資料去避免不需要的記憶體存取。根據實驗的結果，約四分之一的記憶體耗能可以被減少並且不會影響影像品質。此記憶體節能方案對於低動態影像特別有效，記憶體耗能可以被減少約二分之一，若應用在行動電話等可移動式多媒體系統上，當播放新聞或視訊會議時，使用時間可以更有效延長，且其所需額外增加的硬體具有低成本與低耗能的特性，所以此節能方案非常適合於手持式裝置的使用。H.264相較MPEG-4屬於一種較新的規格，其允許多幅參考圖像被搜尋以求得最佳的影像品質，此特性加重系統對於記憶體存取的需求，我們提出“單一宏塊儲存”策略 (對於多個相同資料的宏塊只儲存一個在記憶體內作為代表)，此策略能降低約三分之一的記憶體存取量並且能維持原本的影像品質與編碼效能；適合應用於較高階的可移動式多媒體影像系統。

Power consumption has become a major concern in the design of mobile multimedia systems using MPEG video compression technology. An MPEG video decoder/encoder involves intensive memory accesses which make the memory subsystem a system performance bottleneck as well as the primary consumer of overall system energy. This dissertation presents several techniques to reduce the number of memory accesses to alleviate the impact caused by the memory subsystem. First, a reusable macroblock detector that exploits the stationary macroblock characteristic to identify the reusable data stored in a frame memory is proposed for both an MPEG-4 simple profile video decoder and an MPEG-4 advanced simple profile video decoder. The experimental results show that reusing these already existing data can eliminate about 25% of memory traffic without any sacrifice in image quality. Next, we present two data-reuse policies to remove redundant memory accesses and avoid the unnecessary operations of motion estimation for H.264 baseline profile video decoder/encoder. The proposed approaches reduce 30% (37%) of memory accesses in the encoder (decoder) and 23% of motion estimation computation without impact on coding efficiency.

摘要	                                               IV
ABSTRACT	                                                V
ACKNOWLEDGMENTS	                                      VI
CONTENTS	                                               VII
LIST OF TABLES	                                       X
LIST OF FIGURES	                                       XI
CHAPTER 1 INTRODUCTION	                              1
1 MOTIVATION	                                       1
2 CONTRIBUTIONS	                                       4
3 ORGANIZATION OF THIS DISSERTATION	           4
CHAPTER 2 BACKGROUND AND RELATED WORK	            6
1 OVERVIEW OF MPEG-4 AND H.264	                     6
1.1 MPEG-4	                                       7
1.2 H.264	                                       9
2 RELATED WORK	                                      12
2.1 Frame Memory Performance Improvement for MPEG Video Codec	                                               12
2.2 Reduction of Memory Accesses and Motion Estimation Computation for H.264	                             13
CHAPTER 3 FRAME MEMORY ACCESS REDUCTION FOR MPEG-4 SP VIDEO DECODER	                                      16
1 INTRODUCTION	                                      16
2 STATIONARY MACROBLOCK AND FRAME MEMORY MANAGEMENT IN MPEG-4 SP	                                               19
2.1 Stationary Macroblock	                             19
2.2 Frame Memory Management	                    22
3 REUSABLE MACROBLOCK DETECTOR FOR MPEG-4 SP	  23
3.1 Methodology	                                      23
3.2 Maximum Percentage of Reducible Frame Memory Accesses	                                               26
3.3 Architecture and Implementation	           27
4 SIMULATION ENVIRONMENT	                             31
5 SIMULATION RESULTS	                             34
5.1 Percentage of Reduced Frame Memory Accesses in Different QP Values	                             34
5.2 Zero-Residuals and Zero-16×16 Motion Vectors	  35
5.3 Effect of Number of Frame Memories (NFM)	  36
5.4 Percentage of Reduced Frame Memory Accesses at Different Bit Rates	                             37
5.5 Evaluation of SDRAM Performance	           38
6 SUMMARY	                                      39
CHAPTER 4 FRAME MEMORY ACCESS REDUCTION FOR MPEG-4 ASP VIDEO DECODER	                                      40
1 INTRODUCTION	                                      40
2 STATIONARY MACROBLOCK AND FRAME MEMORY REQUIREMENT IN MPEG-4 ASP	                                      42
3.1 Stationary Macroblock	                             42
3.2 Frame Memory Requirement	                    42
3 REUSABLE MACROBLOCK DETECTOR FOR MPEG-4 ASP	  43
3.1 Main Idea	                                      43
3.2 Macroblock State Tables and Frame State Tables	  45
3.3 RMD Algorithm	                             46
3.4 Example of Decoding a Video Sequence with RMD	  55
3.5 Hardware Implementation	                    57
4 SIMULATION RESULTS	                             59
4.1 Percentage of Reduced Frame Memory Accesses for Different QP Values	                             60
4.2 Impact of Video Feature on Amount of Reusable Data	                                                62
4.3 Percentage of Reduced Frame memory Accesses at Different Bit Rates	                             63
4.4 Evaluation of SDRAM Performance	           64
5 SUMMARY	                                      65
CHAPTER 5 FRAME MEMORY ACCESS REDUCTION FOR H.264 BP VIDEO CODEC	                                               66
1 INTRODUCTION	                                      66
2 STATIONARY MACROBLOCK IN H.264 BP	          67
3 DATA BLOCK BUFFERING STRATEGIES	                   70
3.1 Neighboring Data Buffer Used by Deblocking Filter	                                               70
3.2 Search Window Buffer Used by Motion Estimation	 71
4 PROPOSED METHODOLOGY	                             72
4.1 One-Valid- Macroblock Policy	                    72
4.2 One- Macroblock -Transfer Policy	           81
5 SIMULATION RESULTS	                             84
4.1 Percentage of Stationary Macroblocks for Different QP Values	                                               84
4.2 Impact of Deblocking Filter on Stationary Macroblocks for Different QP Values	                    85
4.3 Percentage of Search Windows Full of Stationary Macroblocks for Different Search Ranges	           87
4.4 Performance Evaluation	                    88
6 SUMMARY	                                      89
CHAPTER 6 CONCLUSIONS	                             90
REFERENCES	                                      93
                                    

[1] I. Richardson, “H.264 and MPEG-4 Video Compression,” John Wiley & Sons Ltd, 2003.
[2] ISO/IEC JTC1/SC29/WG11, “MPEG4 Video Verification Model Version 18.0,” January 2001.
[3] ISO/IEC 14496-2, Amendment 1, Information technology – coding of audio-visual objects, 2001.
[4] M. A. Viredaz, L. S. Brakmo, and W. R. Hamburgen, “Energy Management on Handheld Devices,” ACM Queue, Vol. 1, No. 7, pp. 44-52, October 2003.
[5] T. Hashimoto, M. Ohashi, M. Matsuo, and et al., “A 27-MHz/54-MHz 11-mW MPEG-4 Video Decoder LSI for Mobile Applications,” IEEE Journal of Solid-State Circuits, Vol. 37, No. 11, pp. 1574-1581, November 2002.
[6] M. Takahashi, et al., “A 60-MHz 240-mW MPEG-4 Videophone LSI with 16-Mb Embedded DRAM,” IEEE Journal of Solid-State Circuits, Vol. 35, No. 11, pp. 1713-1721, November 2000.
[7] C.-W. Yoon, R. Woo, J. Kook, S.-J. Lee, K. Lee, and H.-J. Yeo, “An 80/20-MHz, 160-mW Multimedia Processor Integrated With Embedded DRAM, MPEG-4 Accelerator, and 3D-Rendering Engine For Mobile Applications,” IEEE Journal of Solid-State Circuits, Vol. 36, No. 11, pp. 1758-1767, November 2001.
[8] Joint Video Team Reference Software JM8.5, September 2004.
[9] 3GPP TS 26.110, Codec for Circuit-Switched Multimedia Telephony Service (General Description), http://www.3gpp.org/.
[10] P. List, A. Joch, J. Lainema, G. Bjøntegaard, and M. Karczewicz, “Adaptive Deblocking Filter,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 7, pp. 614-619, July 2003.
[11] H. Malvar, A. Hallapuro, M. Karczewicz, and L. Kerofsky, “Low-Complexity Transform and Quantization in H.264/AVC,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 7, pp. 598-603, July 2003.
[12] N. Ahmed, T. Natarajan, and R. Rao, “Discrete Cosine Transform,” IEEE Transactions on Computers, Vol. C-23, pp. 90-93, January 1974.
[13] T. Wiegand, X. Zhang, and B. Girod, “Long-Term Memory Motion-Compensated Prediction,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 1, pp.70-84, February 1999.
[14] M. Flierl and B. Girod, “Generalized B Pictures and the Draft H.264/AVC Video Compression Standard,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 7, pp.587-597, July 2003.
[15] T. Wedi and H. G. Musmann, “Motion- and Aliasing-Compensated Prediction for Hybrid Video Coding,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 7, pp. 577-587, July 2003.
[16] D. Marpe, H. Schwarz, and T. Wiegand, “Context-Based Adaptive Binary Arithmetic Coding in the H.264/AVC Video Compression Standard,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 7, pp. 620-636, July 2003.
[17] V. G. Moshnyaga, “Reducing Energy Dissipation of Frame Memory by Adaptive Bit-Width Compression,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 8, pp. 713-718, August 2002.
[18] C.-H. Lin, C.-M. Chen, and C.-W. Jen, “Low Power Design for MPEG-2 Video Decoder,” IEEE Transactions on Consumer Electronics, Vol. 42, No. 3, pp. 513-521, August 1996.
[19] P. R. Panda and N. D. Dutt, “Low Power Memory Mapping through Reducing Address Bus Activity,” IEEE. Transactions on VLSI Systems, Vol. 7, No. 3, pp. 309-320, September 1999.
[20] C.-W. J. Shih, N. Ling, and T. Ogunfunmi, “Memory Reduction by Haar Wavelet Transform for MPEG Decoder,” IEEE Transactions on Consumer Electronics, Vol. 45, No. 3, pp. 867-873, August 1999.
[21] P. H. N. de With, P. H. Frencken, and M. V. D. Schaar-Mittera, “An MPEG Decoder with Embedded Compression for Memory Reduction,” IEEE Transactions on Consumer Electronics, Vol. 44, No. 3, pp. 545-555, August 1998.
[22] E. Brockmeyer, L. Nachtergaele, F. V. M. Catthoor, J. Bormans, and H. J. D. Man, “Low Power Memory Storage and Transfer Organization for the MPEG-4 Full Pel Motion Estimation on a Multimedia Processor,” IEEE Transactions on Multimedia, Vol. 1, No. 2, pp. 202-216, June 1999.
[23] Z. Xu, S. Sohoni, R. Min, and Y. Hu, “An Analysis of Cache Performance of Multimedia Applications,” IEEE Transactions on Computers, Vol. 53, No.1, pp. 20-38, January 2004.
[24] P. Pakdeepaiboonpol and S. Kittitornkun, “Energy Optimization for Mobile MPEG-4 Video Decoder,” International Conference on Mobile Technology, Applications and Systems, pp. 1-6, November 2005.
[25] A. Ramachandran and M. F. Jacome, “Energy-Delay Efficient Data Memory Subsystems,” IEEE Signal Processing Magazine, pp. 23-37, May 2005.
[26] M. Kandemir, J. Ramanujam, M. J. Irwin, V. Narayanan, I. Kadayif, and A. Parikh, “A Compiler-Based Approach for Dynamically Managing Scratch-Pad Memories in Embedded Systems,” IEEE Transactions on Computer-Aided Design, Vol. 23, No. 2, pp. 243-260, February 2004.
[27] Samsung SDRAM 16Mb H-die (x16) data sheet, Part number: K4S161622H, August 2004.
[28] H. Kim and I.-C. Park, “High Performance and Low-Power Memory-Interface Architecture for Video Processing Applications,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 11, pp. 1160-1170, November 2001.
[29] E. G. T. Jaspers and P. H. N. de With, “Bandwidth Reduction for Video Processing in Consumer Systems,” IEEE Transactions on Consumer Electronics, Vol. 47, No. 4, pp. 885-894, November 2001.
[30] S. Rixner, W. J. Dally, U. J. Kapasi, P. Mattson, and J. D. Owens, “Memory Access Scheduling,” Proceedings of 27th Annual International Symposium Computer Architecture (ISCA), pp. 128-138, June 2000.
[31] S.-E. Kim, J.-K. Han, and J.-G. Kim, “An Efficient Scheme for Motion Estimation Using Multireference Frames in H.264/AVC,” IEEE Transactions on Multimedia, Vol. 8, No. 3, pp. 457-466, June 2006.
[32] M.-J. Chen, G.-L. Li, Y.-Y. Chiang, and C.-T. Hsu, “Fast Multiframe Motion Estimation Algorithms by Motion Vector Composition for the MPEG-4/AVC/H.264 Standard,” IEEE Transactions on Multimedia, Vol. 8, No. 3, pp. 478-487, June 2006.
[33] G. N. Rao and P. S. S. B. K. Gupta, “Temporal Motion Prediction for Fast Motion Estimation in Multiple Reference Frames,” IEEE International Symposium on Signal Processing and Information Technology, pp. 817-820, August 27-30, 2006.
[34] Y. Su and M. T. Sun, “Fast Multiple Reference Frame Motion Estimation for H.264/AVC,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 16, No. 3, pp. 447-452, March 2006.
[35] A. K. Mahajan, S. Kondayya, and X. Su, “Exploiting Reference Frame History in H.264/AVC Motion Estimation,” IEEE Asia Pacific Conference on Circuits and Systems, pp. 410-413, December 4-7, 2006.
[36] S.-F. Lin, M.-T. Lu, H. Chen, and C.-H. Pan, “Fast Multi-Frame Motion Estimation for H.264 and Its Applications to Complexity-Aware Streaming,” IEEE International Symposium on Circuits and Systems, pp. 1505-1508, May 23-26, 2005.
[37] Y.-W. Huang, B.-Y. Hsieh, S.-Y. Chien, S.-Y. Ma, and L.-G. Chen, “Analysis and Complexity Reduction of Multiple Reference Frames Motion Estimation in H.264/AVC,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 16, No. 4, pp. 507-522, April 2006.
[38] C.-W. Ting, L.-M. Po, and C.-H. Cheung, “Center-Biased Frame Selection Algorithms for Fast Multi-Frame Motion Estimation in H.264,” IEEE International Conference on Neural Networks and Signal Processing, pp. 1258-1261, December 2003.
[39] A. Chang, O. C. Au, and Y.-M. Yeung, “A Novel Approach to Fast Multi-Frame Selection for H.264 Video Coding,” IEEE International Symposium on Circuits and Systems, Vol. 2, pp. 704-707, May 25-28, 2003.
[40] Y. Liang, I. Ahmad, J. Luo, Y. Sun, and V. Swaminathan, “On Using Hierarchical Motion History for Motion Estimation in H.264/AVC,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 15, No. 12, pp. 1594-1603, December 2005.
[41] H.-J. Li, C.-T. Hsu, and M.-J. Chen, “Fast Multiple Reference Frame Selection Method for Motion Estimation in JVT/H.264,” IEEE Asia-Pacific Conference on Circuit and System, pp. 605-608, December 6-9, 2004.
[42] T.-C. Chen, C.-Y. Tsai, Y.-W. Huang, and L.-G. Chen, “Single Reference Frame Multiple Current Macroblocks Scheme for Multiple Reference Frame Motion Estimation in H.264/AVC,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 17, No. 2, pp. 242-247, February 2007.
[43] H. Shim and C.-M. Kyung, “Data Reuse Algorithm for Multiple Reference Frame Motion Estimation,” Electronics Letters, Vol. 43, No. 7, pp. 382-383, March 2007.
[44] J.-C. Tuan, T.-S. Chang, and C.-W. Jen, “On the Data Reuse and Memory Bandwidth Analysis for Full Search Block Matching VLSI Architecture,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 12, No. 1, pp.61-72, January 2002.
[45] T.-M. Liu, et al., “An 865μW H.264/AVC Video Decoder for Mobile Applications,” IEEE Asia Solid-State Circuits Conference (A-SSCC), pp. 301-304, November 2005.
[46] J.-H. Li and N. Ling, “Architecture and Bus-Arbitration Schemes for MPEG-2 Video Decoder,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 5, pp. 727-736, August 1999.
[47] D. Isovic, G. Fohler, and L. Steffens, “Real-Time Issues of MPEG-2 Playout in Resource Constrained Systems,” Journal of Embedded Computing, Vol. 1, No. 2, pp.239-256, December 2005.
[48] A. R. A. Elenien, L. S. Ismail, and H. S. Bedor, “Quality of Service Handler for MPEG Video in Best Effort Environment,” International Conference on Electrical, Electronic and Computer Engineering (ICEEC), pp. 393-398, September 2004.
[49] Y. Lu and K. J. Christensen, “Using Selective Discard to Improve Real-Time Video Quality on an Ethernet Local Area Network,” International Journal of Network Management, Vol. 9, pp. 106-117, 1999.
[50] P. Cuenca, A. Garrido, F. Quiles, and L. Orozco-Barbosa, “Performance Evaluation of Cell Discarding Mechanisms for the Distribution of VBR MPEG-2 Video over ATM Networks,” IEEE Transactions on Broadcasting, Vol. 44, No. 2, pp. 206-215, June 1998.
[51] A. Awad, R. Sivakumar, and M. W. McKinnon, “MPFD: A Lookahead Based Buffer Management Scheme for MPEG-2 Video Traffic,” International Symposium on Computers and Communication (ISCC), pp. 893-898, June 2003.
[52] Y. Shen, C. Huang, L. Yu, D. Zhang, and J. Li, “Fast Multiframe Motion Estimation Algorithm in H.264,” Proceedings of International Conference on Signal Processing, Vol. 2, pp.1187-1190, 31 August-4 September, 2004.

校內：立即公開
校外：2008-08-04公開

簡易檢索 / 詳目顯示

相關論文