多媒体处理库（MML）在BF53x上的优化研究
|
摘要
随着多媒体技术的发展,实时实现各种视音频标准的系统得到了广泛应用。数字处理器(DSP)由于其丰富灵活的指令集、特殊的内部结构、超强的数据吞吐能力及运算速度,使得以DSP处理器为核心的实现方法成为了一种有效的媒体处理途径。
Blackfin DSP处理器是ADI公司率先推出的新一代16/32 bit嵌入式处理器,它们特别适合满足当今嵌入式音频、视频和通信应用对计算能力和功耗的严格要求。考虑到软件开发中的三个事实:(1)针对相同类型的处理器,可以建立一套比较通用并且计算能力很强大的函数库;(2)软件开发者为了得到一定的性能要求必须认真仔细的利用处理器的结构和指令来优化这些函数库;(3)函数的优化是复杂且花时间的。为此我们打算建立一套基于Blackfin系列处理器的高度优化的多媒体处理库(MML),为音视频编码、图像处理、信号处理、语音压缩等提供大量的库函数,方便用户的调用和缩短多媒体系统开发时间。
本文首先对多媒体处理库中的视频和图像部分进行分层封装,并分析了各层主要函数,不同层次的函数可以满足不同应用系统的要求;其次介绍了多媒体处理库的实现平台Blackfin处理器和软件开发平台Visual DSP,这些是媒体处理库优化的基础;然后重点阐述了视频处理库中的H.264/MPEG-4部分的优化,主要从算法结构、存储器结构以及汇编代码优化三个部分来详细叙述了各个模块的优化方法,并给出了实验结果;接着利用该媒体处理库构建了一个具有实际应用价值的数字视频图像监控系统,并详细说明了各个模块(如采集模块、存储模块、GPRS通信模块)的软硬件的实现过程;最后对本文的工作进行了总结,并提出今后工作的方向。
With the development of multimedia technology, real-time system of various video and audio coding standards has been widly applied. Digital signal processor, which is rich in instruction, has special core structure, powerful in throughput and computing, is widely used in the multimedia processing, and this solution is considered to be the most effective approach.Blackfin Processors embody a new breed of 16/32-bit embedded processor designed specifically to meet the computational demands and power constraints of today's embedded audio, video, and communications applications. Considering three facts in software development:(1)we could build a set of common computationally intensive functions needed on the similar processor;(2)Developers would have to optimization the functions carefully to get adequate performance;(3)This optimization process was complicated and time-consuming. So we began to build a set of optimized multimedia processing libraries, consisted of Video/Audio CODEC, Image Processing, Signal Processing, Speech compression, and so on. Also the libraries are convenient for call and ensure that product developing time is minimized.In this paper, first, the video and image processing libraries in multimedia processing library were encapsulated in several level functions, and we analyzed the different level functions. Different level functions are suitable for different systems. Second, we introduced the hardware platform -Blackfin processor and the software platform-Visual DSP, they are both the basis of the optimization. Third, the optimization of multimedia processing library based on the BF53x series DSP, this part is the emphases of the paper, the optimization methods cover three aspects: the algorithm of the Video CODEC, the structure of memory and the assemble code for DSP. Then, we use the multimedia processing library to construct an application system: Digital Video Surveillance. Finally, there are conclusion and tasks in the future.
Blackfin DSP处理器是ADI公司率先推出的新一代16/32 bit嵌入式处理器,它们特别适合满足当今嵌入式音频、视频和通信应用对计算能力和功耗的严格要求。考虑到软件开发中的三个事实:(1)针对相同类型的处理器,可以建立一套比较通用并且计算能力很强大的函数库;(2)软件开发者为了得到一定的性能要求必须认真仔细的利用处理器的结构和指令来优化这些函数库;(3)函数的优化是复杂且花时间的。为此我们打算建立一套基于Blackfin系列处理器的高度优化的多媒体处理库(MML),为音视频编码、图像处理、信号处理、语音压缩等提供大量的库函数,方便用户的调用和缩短多媒体系统开发时间。
本文首先对多媒体处理库中的视频和图像部分进行分层封装,并分析了各层主要函数,不同层次的函数可以满足不同应用系统的要求;其次介绍了多媒体处理库的实现平台Blackfin处理器和软件开发平台Visual DSP,这些是媒体处理库优化的基础;然后重点阐述了视频处理库中的H.264/MPEG-4部分的优化,主要从算法结构、存储器结构以及汇编代码优化三个部分来详细叙述了各个模块的优化方法,并给出了实验结果;接着利用该媒体处理库构建了一个具有实际应用价值的数字视频图像监控系统,并详细说明了各个模块(如采集模块、存储模块、GPRS通信模块)的软硬件的实现过程;最后对本文的工作进行了总结,并提出今后工作的方向。
With the development of multimedia technology, real-time system of various video and audio coding standards has been widly applied. Digital signal processor, which is rich in instruction, has special core structure, powerful in throughput and computing, is widely used in the multimedia processing, and this solution is considered to be the most effective approach.Blackfin Processors embody a new breed of 16/32-bit embedded processor designed specifically to meet the computational demands and power constraints of today's embedded audio, video, and communications applications. Considering three facts in software development:(1)we could build a set of common computationally intensive functions needed on the similar processor;(2)Developers would have to optimization the functions carefully to get adequate performance;(3)This optimization process was complicated and time-consuming. So we began to build a set of optimized multimedia processing libraries, consisted of Video/Audio CODEC, Image Processing, Signal Processing, Speech compression, and so on. Also the libraries are convenient for call and ensure that product developing time is minimized.In this paper, first, the video and image processing libraries in multimedia processing library were encapsulated in several level functions, and we analyzed the different level functions. Different level functions are suitable for different systems. Second, we introduced the hardware platform -Blackfin processor and the software platform-Visual DSP, they are both the basis of the optimization. Third, the optimization of multimedia processing library based on the BF53x series DSP, this part is the emphases of the paper, the optimization methods cover three aspects: the algorithm of the Video CODEC, the structure of memory and the assemble code for DSP. Then, we use the multimedia processing library to construct an application system: Digital Video Surveillance. Finally, there are conclusion and tasks in the future.
引文
[1] CCITT Recommendation H.261, "Video Codec for Audiovisual Services at p~*64kb/s", 1990
[2] ITU-T Recommendation H.263, "Video Coding for Low Bit Rate Communication", 1996
[3] ITU-T Draft for "H.263++" Annexes U,V, and W to recommendation H.263
[4] Thomas Wiegand, Gary J. Sullivan, Gisle Bjntegaard, Ajay Luthra., "Overview of the H.264/AVC video coding standard", Circuits and Systems for Video Technology, IEEE Transactions, Volume 13, Issue 7, July 2003, P560-576
[5] 钟玉琢等,“MPEG-2运动图像压缩编码国际标准及MPEG的新进展”,北京:清华大学出版社,2002
[6] ISO/IEC International Standard 11172-2. Information Technology-Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to about 1.5Mbit/s: Video, 1993.
[7] ISO/IEC International Standard 13818-2. Information Technology-Generic Coding of Moving Pictures and Associated Audio Information: Video, 1994
[8] ISO/IEC JTC1/SC29/WG11 Document N3342, Overview of the MPEG-4 standard.Mar.2000
[9] 钟玉琢等,“基于对象的多么体数据压缩编码国际标准-MPEG-4及其校验模型”,科学出版社,2000
[10] T. Sikora, "MPEG digital video coding standards," IEEE Signal Processing Magazine, Sept. 1997, P82-100
[11] T. Sikora, "MPEG Digital Audio-and Video-Coding Standards", Signal Processing Magazine, IEEE Volume 14, Issue 5, Sept. 1997, P58-58
[12] ISO/IEC FDIS 14496-2, "Information Technology-Generic Coding of Audio-visual Objects Part2: Visual", Oct. 1998.
[13] Erol, B.;Gallant, M.;Cote, G.;Kossentini, F, "The H.263+ video coding standard: complexity and performance", Data Compression Conference, 1998, Page(s):259-268
[14] 《AVS视频(报批稿)》信息技术,先进音视频编码,第2部分:视频
[15] 胡兴军,AVS:数字电视音视频解码技术,有线电视技术,2004年第10期(总第154期)
[16] 崔海燕,AVS推动中国标准产业化,IT时代周刊.2004(06X),P51-52
[17] ISO/IEC 10918-1 Information technology, Digital compression and coding of continuous tone still images: Requirements and guidelines[S], ISO/IEC. 1994, P10-21
[18] G.K. Wallace, The JPEG still picture compression standard [J],Communications of the ACM, 1991 (4), P30-44
[19] Stewart Taylor, Intel Integrated Performance Primitives How to Optimize Software Applications Using Intel IPP,2004
[20] 俞国军,“基于DSPs的媒体处理系统芯片设计研究”,浙江大学博士学位论文,2006
[21] 徐慧,“基于DSP的多媒体处理库”,浙江大学硕士学位论文,2006
[22] 陈峰,“Blackfin系列DSP原理与系统设计”,电子工业出版社,2004
[23] Analog Devices, Inc. ADSP-BF531/532/533 Biackfin Processor Hardware Reference,http://www.analog.com,2003
[24] Analog Devices,Inc. Visual DSP++ 4.0 C/C++ Compiler and Library Manual for Blackfin Processors,http://www.analog.com,2004
[25] Analog Devices,Inc. Visual DSP++ 4.0 Linker and Utilities Manual for Blackfin DSPs,http://www.analog.com,2004
[26] Analog Devices,Inc. Visual DSP++ 4.0 User's Guide for Blackfin Processors, http://www.analog.com,2004
[27] Analog Devices,Inc. Visual DSP++ 4.0 Getting Started Guide for Blackfin Processors, http://www.analog.com,2004
[28] 石磊,“AVS-M视频解码系统在嵌入式系统上的实现和应用研究”,浙江大学硕士学位论文,2006
[29] 王嵩,“H.264/AVC视频编码标准研究及其编码器的优化”,浙江大学硕士学位论文,2004
[30] Intel Corporation, "Intel(?) Integrated Performance Primitives for Intel(?) Architecture Reference Manual,Volume 2: Image and Video Processing",2003
[31] H.264/MPEG-4 Part 10 White Paper: Transform and quantization
[32] H.264/MPEG-4 Part 10 White Paper: Intra Prediction
[33] H.264/MPEG-4 Part 10 White Paper: Inter Prediction
[34] H.264/MPEG-4 Part 10 White Paper: Context-Based Adaptive Arithmetic Coding (CABAC)
[35] 施建强,虞露.“在TM1300上实现的MPEG4-ASP单目标编码器”,计算机工程,2003,29(13):P155-156
[36] Kunal Singh, "Using Cache Memory on Blackfin(?) Processors,Analog Devices", Inc.http://www.analog.com,2005
[37] Iain E.G.Richardson, "Video Codec Design-Developing Image and Video Compression Systems", The Robert Gordon University, Aberdeen,UK,2002
[38] 姚庆栋,徐孟侠等,“图像编码基础”(修订版),浙江大学出版社
[39] 操勇,“基于Blackfin的MPEG-4编码器的设计与实现”,武汉大学硕士学位论文,2003
[40] Analog Devices,Inc. ADSP-BF531/532/533 Blackfin Processor Instruction Set Reference,http://www.analog.com,2003
[41] Analog Devices,Inc. ADSP-BF535 Blackfin rocessor Multi-cycle Instructions and Latencies, http://www.analog.com,2003
[42] 薛全,“H.264/AVC中运动估计、变换与解码器优化”,浙江大学博士学位论文,2004
[43] Borko Furht, Joshua Greenberg, Raymond Westwater, "Motion Estimation Algorithms for Video Compression",Kluwer Academic,2000
[44] 苏珊,“适应更多应用的增强型Blackfin DSP”,电子设计应用.2003(5),P102-10
[45] 龚剑明,“MPEG-4标准视频编码器在Blackfin 21535上的实现”,电视技术,2003(11):P82-83,91
[46] 黄晓伟,张莹,陈峰,“基于Blackfin533的H.264编码”,电子技术应用,2005,31(8):P41-43
[47] 杨波,邢克飞,“ADSP-21535 Blackfin的Mem DMA高速通信”,电子技术应用,2003,29(8):P50-53
[48] J.Koga, K. Iiunuma, A. Hirani and et al., "Motion compensated interframe coding for video conferencing", in Porc. National Telecommunications Conference,1981, PG5.3.1-5.3.5
[49] R. Li, B. Zeng and M.L. Lion, "A new three-step search algorithm for block motion estimation",IEEE Trans Circuits Syst. Video TechnoL., vol.4(4), Aug. 1994,P438-442
[50] J. Jain and A. Jain, "Displacement Measurement and its Application in interframe Image Coding", IEEE Trans. Communications. vol. 29(12), Dec. 1981, P 1799-1808
[51] R. Srinivasan, K. Rao, "Predictive Coding Based on Eficient Motion Estimation", IEEE Trans. Communications, vol.33(8), Aug 1985, P888-896
[52] B. Furth, J. Greeberg, R. Westwater, "Motion estimation algorithms for video compression", Kluwer Academic Publishers, 1997
[53] Xiaoquan Yi, Nam Ling, "Rapid Block-Matching Motion Estimation Using Modified Diamond Search Algorithm", IEEE Trans. Circuits Syst. VOL.6,May 2005, P5489-5492
[54] Chun-Ho Cheung, Lai-Man Po, "Novel Cross-Diamond-Hexagonal Search Algorithms for Fast Block Motion Estimation", IEEE Transactions on Multimedia.VOL.7, NO. 1, Feb 2005
[55] C.W. Lam, L. M. Po, and C. H. Cheung, "A new cross-diamond search algorithm for fast block matching motion estimation," IEEE International Conference on Neural Networks and Signal Processing, P1262-1265,Nanjing, China, Dec. 2003.
[56] Y. Nie and K.-K. Ma, "Adaptive rood pattern search for fast block-matching motion estimation," IEEE Trans. Image Processing, vol. 11, pp. 1442-1449,Dec. 2002.
[57] A. Tourapis, O. C. Au, and M. L. Liou, "Highly efficient predictive zonal algorithm for fast block-matching motion estimation," IEEE Trans. Circuits Syst. Video Technol., vol. 12, pp. 934-947, Oct. 2002.
[58] X. Zhou, Z. Yu, and S. Yu, "Method for Detecting All-Zero DCT Coefficients Ahead of Discrete Cosine Transformation and Quantization", Electro. Lett., vol. 34, no. 19, P1839-1840, Sept. 1998.
[59] L.A. Sousa, "General Method for Eleminating Redundant Computations in Video Coding", Electron. Lett., vol. 36, no. 4, P306-307, Feb. 2000.
[60] I.M. Pao and M. T. Sun, "Modeling DCT Coefficients for Fast Video Encoding", IEEE Trans. Circuits Syst. Video Technol., vol. 9, no. 4, P608-616, Jun. 1999.
[61] G.Y. Kim, Y. H. Moon, and J. H. Kim, "An Early Detection of All-Zero DCT Blocks in H.264", in Proc. IEEE ICIP'04, P453-456, Oct. 2004.
[62] Hanli Wang, Sam Kwnong, Chi-Wah Kok, "Efficient Prediction Algorithm of Integer DCT Coefficients for H.264/AVC Optimization", Circuits and Systems for Video Technology, IEEE Transactions on Vol. 16, NO. 4, P547-552, April 2005.
[63] 吕鸿波,“多媒体处理库在DM642上的优化研究”,浙江大学硕士学位论文,2006.
[64] 王念旭,“DSP基础与应用系统设计”,北京航空航天大学出版社,2001.
[65] 张雄伟,“DSP芯片的原理与开发应用”,电子工业出版社,2003.
[2] ITU-T Recommendation H.263, "Video Coding for Low Bit Rate Communication", 1996
[3] ITU-T Draft for "H.263++" Annexes U,V, and W to recommendation H.263
[4] Thomas Wiegand, Gary J. Sullivan, Gisle Bjntegaard, Ajay Luthra., "Overview of the H.264/AVC video coding standard", Circuits and Systems for Video Technology, IEEE Transactions, Volume 13, Issue 7, July 2003, P560-576
[5] 钟玉琢等,“MPEG-2运动图像压缩编码国际标准及MPEG的新进展”,北京:清华大学出版社,2002
[6] ISO/IEC International Standard 11172-2. Information Technology-Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to about 1.5Mbit/s: Video, 1993.
[7] ISO/IEC International Standard 13818-2. Information Technology-Generic Coding of Moving Pictures and Associated Audio Information: Video, 1994
[8] ISO/IEC JTC1/SC29/WG11 Document N3342, Overview of the MPEG-4 standard.Mar.2000
[9] 钟玉琢等,“基于对象的多么体数据压缩编码国际标准-MPEG-4及其校验模型”,科学出版社,2000
[10] T. Sikora, "MPEG digital video coding standards," IEEE Signal Processing Magazine, Sept. 1997, P82-100
[11] T. Sikora, "MPEG Digital Audio-and Video-Coding Standards", Signal Processing Magazine, IEEE Volume 14, Issue 5, Sept. 1997, P58-58
[12] ISO/IEC FDIS 14496-2, "Information Technology-Generic Coding of Audio-visual Objects Part2: Visual", Oct. 1998.
[13] Erol, B.;Gallant, M.;Cote, G.;Kossentini, F, "The H.263+ video coding standard: complexity and performance", Data Compression Conference, 1998, Page(s):259-268
[14] 《AVS视频(报批稿)》信息技术,先进音视频编码,第2部分:视频
[15] 胡兴军,AVS:数字电视音视频解码技术,有线电视技术,2004年第10期(总第154期)
[16] 崔海燕,AVS推动中国标准产业化,IT时代周刊.2004(06X),P51-52
[17] ISO/IEC 10918-1 Information technology, Digital compression and coding of continuous tone still images: Requirements and guidelines[S], ISO/IEC. 1994, P10-21
[18] G.K. Wallace, The JPEG still picture compression standard [J],Communications of the ACM, 1991 (4), P30-44
[19] Stewart Taylor, Intel Integrated Performance Primitives How to Optimize Software Applications Using Intel IPP,2004
[20] 俞国军,“基于DSPs的媒体处理系统芯片设计研究”,浙江大学博士学位论文,2006
[21] 徐慧,“基于DSP的多媒体处理库”,浙江大学硕士学位论文,2006
[22] 陈峰,“Blackfin系列DSP原理与系统设计”,电子工业出版社,2004
[23] Analog Devices, Inc. ADSP-BF531/532/533 Biackfin Processor Hardware Reference,http://www.analog.com,2003
[24] Analog Devices,Inc. Visual DSP++ 4.0 C/C++ Compiler and Library Manual for Blackfin Processors,http://www.analog.com,2004
[25] Analog Devices,Inc. Visual DSP++ 4.0 Linker and Utilities Manual for Blackfin DSPs,http://www.analog.com,2004
[26] Analog Devices,Inc. Visual DSP++ 4.0 User's Guide for Blackfin Processors, http://www.analog.com,2004
[27] Analog Devices,Inc. Visual DSP++ 4.0 Getting Started Guide for Blackfin Processors, http://www.analog.com,2004
[28] 石磊,“AVS-M视频解码系统在嵌入式系统上的实现和应用研究”,浙江大学硕士学位论文,2006
[29] 王嵩,“H.264/AVC视频编码标准研究及其编码器的优化”,浙江大学硕士学位论文,2004
[30] Intel Corporation, "Intel(?) Integrated Performance Primitives for Intel(?) Architecture Reference Manual,Volume 2: Image and Video Processing",2003
[31] H.264/MPEG-4 Part 10 White Paper: Transform and quantization
[32] H.264/MPEG-4 Part 10 White Paper: Intra Prediction
[33] H.264/MPEG-4 Part 10 White Paper: Inter Prediction
[34] H.264/MPEG-4 Part 10 White Paper: Context-Based Adaptive Arithmetic Coding (CABAC)
[35] 施建强,虞露.“在TM1300上实现的MPEG4-ASP单目标编码器”,计算机工程,2003,29(13):P155-156
[36] Kunal Singh, "Using Cache Memory on Blackfin(?) Processors,Analog Devices", Inc.http://www.analog.com,2005
[37] Iain E.G.Richardson, "Video Codec Design-Developing Image and Video Compression Systems", The Robert Gordon University, Aberdeen,UK,2002
[38] 姚庆栋,徐孟侠等,“图像编码基础”(修订版),浙江大学出版社
[39] 操勇,“基于Blackfin的MPEG-4编码器的设计与实现”,武汉大学硕士学位论文,2003
[40] Analog Devices,Inc. ADSP-BF531/532/533 Blackfin Processor Instruction Set Reference,http://www.analog.com,2003
[41] Analog Devices,Inc. ADSP-BF535 Blackfin rocessor Multi-cycle Instructions and Latencies, http://www.analog.com,2003
[42] 薛全,“H.264/AVC中运动估计、变换与解码器优化”,浙江大学博士学位论文,2004
[43] Borko Furht, Joshua Greenberg, Raymond Westwater, "Motion Estimation Algorithms for Video Compression",Kluwer Academic,2000
[44] 苏珊,“适应更多应用的增强型Blackfin DSP”,电子设计应用.2003(5),P102-10
[45] 龚剑明,“MPEG-4标准视频编码器在Blackfin 21535上的实现”,电视技术,2003(11):P82-83,91
[46] 黄晓伟,张莹,陈峰,“基于Blackfin533的H.264编码”,电子技术应用,2005,31(8):P41-43
[47] 杨波,邢克飞,“ADSP-21535 Blackfin的Mem DMA高速通信”,电子技术应用,2003,29(8):P50-53
[48] J.Koga, K. Iiunuma, A. Hirani and et al., "Motion compensated interframe coding for video conferencing", in Porc. National Telecommunications Conference,1981, PG5.3.1-5.3.5
[49] R. Li, B. Zeng and M.L. Lion, "A new three-step search algorithm for block motion estimation",IEEE Trans Circuits Syst. Video TechnoL., vol.4(4), Aug. 1994,P438-442
[50] J. Jain and A. Jain, "Displacement Measurement and its Application in interframe Image Coding", IEEE Trans. Communications. vol. 29(12), Dec. 1981, P 1799-1808
[51] R. Srinivasan, K. Rao, "Predictive Coding Based on Eficient Motion Estimation", IEEE Trans. Communications, vol.33(8), Aug 1985, P888-896
[52] B. Furth, J. Greeberg, R. Westwater, "Motion estimation algorithms for video compression", Kluwer Academic Publishers, 1997
[53] Xiaoquan Yi, Nam Ling, "Rapid Block-Matching Motion Estimation Using Modified Diamond Search Algorithm", IEEE Trans. Circuits Syst. VOL.6,May 2005, P5489-5492
[54] Chun-Ho Cheung, Lai-Man Po, "Novel Cross-Diamond-Hexagonal Search Algorithms for Fast Block Motion Estimation", IEEE Transactions on Multimedia.VOL.7, NO. 1, Feb 2005
[55] C.W. Lam, L. M. Po, and C. H. Cheung, "A new cross-diamond search algorithm for fast block matching motion estimation," IEEE International Conference on Neural Networks and Signal Processing, P1262-1265,Nanjing, China, Dec. 2003.
[56] Y. Nie and K.-K. Ma, "Adaptive rood pattern search for fast block-matching motion estimation," IEEE Trans. Image Processing, vol. 11, pp. 1442-1449,Dec. 2002.
[57] A. Tourapis, O. C. Au, and M. L. Liou, "Highly efficient predictive zonal algorithm for fast block-matching motion estimation," IEEE Trans. Circuits Syst. Video Technol., vol. 12, pp. 934-947, Oct. 2002.
[58] X. Zhou, Z. Yu, and S. Yu, "Method for Detecting All-Zero DCT Coefficients Ahead of Discrete Cosine Transformation and Quantization", Electro. Lett., vol. 34, no. 19, P1839-1840, Sept. 1998.
[59] L.A. Sousa, "General Method for Eleminating Redundant Computations in Video Coding", Electron. Lett., vol. 36, no. 4, P306-307, Feb. 2000.
[60] I.M. Pao and M. T. Sun, "Modeling DCT Coefficients for Fast Video Encoding", IEEE Trans. Circuits Syst. Video Technol., vol. 9, no. 4, P608-616, Jun. 1999.
[61] G.Y. Kim, Y. H. Moon, and J. H. Kim, "An Early Detection of All-Zero DCT Blocks in H.264", in Proc. IEEE ICIP'04, P453-456, Oct. 2004.
[62] Hanli Wang, Sam Kwnong, Chi-Wah Kok, "Efficient Prediction Algorithm of Integer DCT Coefficients for H.264/AVC Optimization", Circuits and Systems for Video Technology, IEEE Transactions on Vol. 16, NO. 4, P547-552, April 2005.
[63] 吕鸿波,“多媒体处理库在DM642上的优化研究”,浙江大学硕士学位论文,2006.
[64] 王念旭,“DSP基础与应用系统设计”,北京航空航天大学出版社,2001.
[65] 张雄伟,“DSP芯片的原理与开发应用”,电子工业出版社,2003.