用于实时牌照识别的DSP系统的设计
摘要
随着经济的发展和道路交通事业的发展，以计算机图像处理技术，通信技术和信息管理技术为核心的智能化道路交通监控和管理系统在道路交通安全管理领域和小区的智能化管理得到了广泛的运用。车辆牌照的自动识别是计算机视觉与模式识别技术在智能交通领域应用的重要研究课题之一，是实现交通管理智能化的重要环节。
车牌识别车牌自动识别是一个难度很大的课题。目前的牌照识别系统不仅实现价格的比较高、机动性能差，还存在着识别速度慢，识别率和稳定性差的问题，而且，因为整个系统都是基于通用计算机地软件，不利于软件知识产权的保护。
牌照识别是我们实验室的一个重要研究课题，为了增强系统的实时性能，最大可能的降低成本，并且加强系统的知识产权保护功能。经过详细的分析牌照识别算法的特点和DSP的芯片以及DSP系统的特点。我们得出用DSP实现牌照识别无论在性能上，成本上，机动性上还是知识产权保护上都有着巨大的优越性。
本论文设计了两个DSP系统，用来实现牌照的实时识别。一个是基于PCI总线的DSP通用信号处理系统。另外一个是专门用于实时牌照识别的DSP系统。通过该课题的开发，熟悉了DSP的结构及其开发流程，设计制作了基于PCI总线的DSP通用信号处理系统的硬件平台，并编写了该系统的驱动程序，通过FFT测试，验证了该系统的功能。在设计专门用于实时牌照识别的DSP的硬件系统中，解决了视频采集的同步，16位RGB到24位RGB的转换，DSP跟SDRAM、FLASH、视频采集芯片以及主机的接口等多个问题。本文对这两个系统的设计制作进行了详细的介绍。
下面是具体的章节安排。第一章是绪论，介绍了车辆牌照识别的应用价值、存在问题，提出了用DSP实现牌照实时识别的课题，及本论文的主要内容。第二章分析了牌照识别算法的特点，DSP芯片以及DSP系统的特定。得出用DSP实现牌照自动识别有着巨大得优越性。第三章介绍了DSP系统的设计及开发的流程、工具以及算法标准。第四章介绍了基于PCI总线的DSP通用信号处理系统的硬件设计，包括PCI接口，存储器扩展，和DSP与主机的通信等。第五章介绍了基于PCI总线的DSP通用信号处理系统的软件设计，主要包括系统自举和PCI驱动程序的编写，也论述了在牌照识别时DSP算法的改进。第六章介绍了专门用于实时牌照识别的DSP系统的设计，包括硬件接口和软件驱动。最后，在第七章总结了本论文所做的主要工作，并对以后用DSP实现牌照识别的问题作了展望。
With the development of transportation system,more and more roads are constructed and more and more vehicles are used,there are more and more demands on the management of transportation system,Intelligent Transport System(ITS) provides a scientific method for it. License Plate Recognition(LPR) is the key of ITS. With the development of LPR technology,LPR is widely used in toll station,parking lot traffic management,automatic payment of highway toll fee,and so on.
LPR is a very hard research area. The license plate automatic recognition systems of now-days still have some shortage:It is too expensive,the recognition speed is not fast enough,and the ratio of recognition is not high enough. After all,because the whole LPR system is based on PC software it is hard to protect the right of the LPR system.
Digital Signal Processors(DSP)are the powerful tools for digital signal processing. It is widely used in digital communication,signal processing,industry controlling and so on.
LPR is an important research area of our laboratory. In order to control the cost of the LRP system,improve its performance and protect the right,based on analysis the characters of the algorithm of LPR and the characters of DSP chips and DSP systems,We draw a conclusion,that the LPR system based on DSP can resolve those shortage.
We have developed two LPR systems based on DSP:one is a general DSP signal processing system based on PCI bus. The other is a special License Plate recognition system based on DSP. Though the research,I get the knowledge of the structure of the DSP,the knowledge of DSP system development flow. Designed and made a general DSP signal processing system based on PCI bus,and write the driver of this system,and at the end,I validate the function of the system through FFT. During design the special License Plate recognition system based on DSP,I resolved many problems such as video capture synchronization,the conversion from 16 bits RGB to 24 bits RGB,the interface between DSP and SDRAM,FLASH video capture and host PC and so on. This paper gives a detail introduction about these two systems.
In chapter two,I analysis the characters of the algorithm of LPR and
the characters of DSP chips and DSP systems. We draw a conclusion,that the LPR system realization though DSP have some advantages. In chapter three,I introduce the flow chart of DSP system development,tools of DSP development and eXpressDSP Algorithm Standard. In chapter four,I designed a general DSP signal processing system based on PCI bus. In this chapter,I introduce the hardware design of this system,include:PCI interface,memory expand and the communication between the DSP and the host PC. In chapter five,I introduce the design of the software of the general DSP signal processing system based on PCI bus. Include BOOTLOAD and PCI driver. In chapter six,I designed a special LPR system based on DSP.I introduce the interface and the drivers of DMA and PCI bus. In chapter sever,I conclude the work what I had done and analysis the work still need to been.
车牌识别车牌自动识别是一个难度很大的课题。目前的牌照识别系统不仅实现价格的比较高、机动性能差，还存在着识别速度慢，识别率和稳定性差的问题，而且，因为整个系统都是基于通用计算机地软件，不利于软件知识产权的保护。
牌照识别是我们实验室的一个重要研究课题，为了增强系统的实时性能，最大可能的降低成本，并且加强系统的知识产权保护功能。经过详细的分析牌照识别算法的特点和DSP的芯片以及DSP系统的特点。我们得出用DSP实现牌照识别无论在性能上，成本上，机动性上还是知识产权保护上都有着巨大的优越性。
本论文设计了两个DSP系统，用来实现牌照的实时识别。一个是基于PCI总线的DSP通用信号处理系统。另外一个是专门用于实时牌照识别的DSP系统。通过该课题的开发，熟悉了DSP的结构及其开发流程，设计制作了基于PCI总线的DSP通用信号处理系统的硬件平台，并编写了该系统的驱动程序，通过FFT测试，验证了该系统的功能。在设计专门用于实时牌照识别的DSP的硬件系统中，解决了视频采集的同步，16位RGB到24位RGB的转换，DSP跟SDRAM、FLASH、视频采集芯片以及主机的接口等多个问题。本文对这两个系统的设计制作进行了详细的介绍。
下面是具体的章节安排。第一章是绪论，介绍了车辆牌照识别的应用价值、存在问题，提出了用DSP实现牌照实时识别的课题，及本论文的主要内容。第二章分析了牌照识别算法的特点，DSP芯片以及DSP系统的特定。得出用DSP实现牌照自动识别有着巨大得优越性。第三章介绍了DSP系统的设计及开发的流程、工具以及算法标准。第四章介绍了基于PCI总线的DSP通用信号处理系统的硬件设计，包括PCI接口，存储器扩展，和DSP与主机的通信等。第五章介绍了基于PCI总线的DSP通用信号处理系统的软件设计，主要包括系统自举和PCI驱动程序的编写，也论述了在牌照识别时DSP算法的改进。第六章介绍了专门用于实时牌照识别的DSP系统的设计，包括硬件接口和软件驱动。最后，在第七章总结了本论文所做的主要工作，并对以后用DSP实现牌照识别的问题作了展望。
With the development of transportation system,more and more roads are constructed and more and more vehicles are used,there are more and more demands on the management of transportation system,Intelligent Transport System(ITS) provides a scientific method for it. License Plate Recognition(LPR) is the key of ITS. With the development of LPR technology,LPR is widely used in toll station,parking lot traffic management,automatic payment of highway toll fee,and so on.
LPR is a very hard research area. The license plate automatic recognition systems of now-days still have some shortage:It is too expensive,the recognition speed is not fast enough,and the ratio of recognition is not high enough. After all,because the whole LPR system is based on PC software it is hard to protect the right of the LPR system.
Digital Signal Processors(DSP)are the powerful tools for digital signal processing. It is widely used in digital communication,signal processing,industry controlling and so on.
LPR is an important research area of our laboratory. In order to control the cost of the LRP system,improve its performance and protect the right,based on analysis the characters of the algorithm of LPR and the characters of DSP chips and DSP systems,We draw a conclusion,that the LPR system based on DSP can resolve those shortage.
We have developed two LPR systems based on DSP:one is a general DSP signal processing system based on PCI bus. The other is a special License Plate recognition system based on DSP. Though the research,I get the knowledge of the structure of the DSP,the knowledge of DSP system development flow. Designed and made a general DSP signal processing system based on PCI bus,and write the driver of this system,and at the end,I validate the function of the system through FFT. During design the special License Plate recognition system based on DSP,I resolved many problems such as video capture synchronization,the conversion from 16 bits RGB to 24 bits RGB,the interface between DSP and SDRAM,FLASH video capture and host PC and so on. This paper gives a detail introduction about these two systems.
In chapter two,I analysis the characters of the algorithm of LPR and
the characters of DSP chips and DSP systems. We draw a conclusion,that the LPR system realization though DSP have some advantages. In chapter three,I introduce the flow chart of DSP system development,tools of DSP development and eXpressDSP Algorithm Standard. In chapter four,I designed a general DSP signal processing system based on PCI bus. In this chapter,I introduce the hardware design of this system,include:PCI interface,memory expand and the communication between the DSP and the host PC. In chapter five,I introduce the design of the software of the general DSP signal processing system based on PCI bus. Include BOOTLOAD and PCI driver. In chapter six,I designed a special LPR system based on DSP.I introduce the interface and the drivers of DMA and PCI bus. In chapter sever,I conclude the work what I had done and analysis the work still need to been.
引文
1．照识别中关键技术研究 俞伦峰毕业论文 浙江大学 2001
2．2000上海国际智能交通及管理技术研讨会发言汇编，2000
3. Paolo Castello, Christopher Coelhho, Enrico Eel Ninno, Ennio Ottaviani, Michele Zanini," Traffic Monitoring in Motorways by Real-time Number Plate Recognition", IEEE, 0-7695-0040-4, 1999
4．牌识别技术在交通工具和城市安全中的作用及应用前景，赵明生，包丛笑，电子与金系列工程信息，1999年，第9期
5．MS320C6000系列DSPs的原理与应用 任丽香等 电子工业出版社
6．数字信号处理——理论、算法、与实现 吴广书编 清华大学出版社 1997
7．DSP芯片的原理与开发应用 张雄伟等 电子工业出版社
8. Oppenheim A V, Schafer R.Discrete-Time Signal Processing. Englewood Cliffs,NJ:Prentice-Hall.1989
9．DSP基础与应用系统设计 王念旭等编 北京航空航天大学出版社．2001
10．TMS320C54X DSP结构，原理及应用 戴明桢 北京航空航天大学出版社 2001
11．计算机图像处理 容观奥编 清华大学出版社 2000
12．图像处理和分析 章毓普编 清华大学出版社 1999
13. Kenneth R. Castleman, Digital Image Processing, Printice-Hall International, Inc., 1998
14．数字信号处理教程 程佩青 清华大学出版社
15．Code Composer Studio教程 中国人民解放军信息工程大学与中泰康通信技术有限责任 ADSP系列教材编写组。
16．DSP解决之道 北京瑞泰创新科技有限公司
17．神经网络的应用与实现 西安电子科技大学出版社
18. TMS320 DSP Algorithm Standard Rules and Guidelines, spru352.
19. eXpressDSP Algorithm Standard Rules and Guideline. Texas Instruments Incorporated 1999
20. eXpressDSP Algorithm Standard API Reference, Texas Instruments Incorporated 1999
21.The eXpressDSP Algorithm Standard. Texas Instruments Incorporated, 1999
22.TMS320数字信号处理器算法标准及参考构架 丁刚，
23.TMS320C54X DSP Reference Set, volumel, CPU and Peripheral (literature number SPRU131),Texas Instruments
24.TMS320C54x实用教程 电子科技大学出版社
25．刘晖等译 PCI系统结构(第四版) 电子工业出版社 2000
26．PCI总线与多媒体计算机 曾繁泰等 电子工业出版社 199718．TMS320C54X
27. TPS767318 DUAL-OUTPUT LOW-DROPOUT VOLTAGE REGULATORS, slvs209, Texas Instruments
28. pci2040 implementation guide Texas Instruments
29. the tms320c54x dsp-hpi and pc parallel port interface spra151
30. pci2040 implementation guide scpu004
31. A Practical Application of the TMS320C54x Host Port Interface (HPI) spra574
32. TMS320vc5402 fixed point digital signal processor sprs079 Texas Instruments
33. IDT71016s HIGH SPEED STATIC SRAM. Integrated Device Technology. Inc
34．微波与光导波技术教程 陈抗生 浙江大学出版社 2000
35. TMS320VC5402 and TMS320UC5402 Bootloader spra616 Texas Instruments
36. DSP Reference Set, volume4, Application Guide(literature number SPRU173), Texas Instruments
37. TMS320C54X DSP Reference Set, volume2,Mnemonic Instruction Set(literature number SPRU172),Texas Instruments
38. WinDrive Developer's Guide Jungo公司
39．Windows核心编程 Jeffrey Richter著，王建华译，机械工业出版社
40．Windows98下硬件中断驱动程序的开发，杭州浙江大学，李博 鲍超
41. Markel J D. FFT pruning. IEEE Trans. Audio Electroacoust. 1971,19(4)
42. Duhamel P, Holtmann H. Split-radix FFT algorithm. Electronics Letters. 1984, 20(1): 14-16
43. Skinner D P.Pruning the decimation-in-time FFT algorithm. IEEE Trans.on ASSP, 1976,24(Apr): 193-292
44. Heideman M T.Kultiplicative Complexity,Concolution,and the DFT.New York:Springer-Verlag NewYorklne, 1988
45. TMS320C6000 Peripherals Reference Guide Texas Instruments
46. TMS320C6205 Fixed-Point Digital Signal Processor Texas Instruments
47. TMS320C6000 CPU and Instruction Set reference Guide(literature number SPRZ189f) Texas Instruments
48. Manual Update Sheet (literature number SPRU168b)Texas Instruments
49. Manual Update Sheet (literature number SPRU122b)Texas Instruments
50. TMS320C62X Image/Video processing library Programmer's reference (literature number SPRU400a) Texas Instruments
51. TMS320C62X Peripheral support library Programmer's reference (literature number SPRU273b) Texas Instruments
52. TPS70148 DUAL-OUTPUT LOW-DROPOUT VOLTAGE REGULATORS, with power up sequencing for split voltage DSP system, slvs222b, Texas Instruments
53. DATASHEET for SAA7111 Enhanced Video Input Processor. PHILIPS Semiconductors. 1998.
54. SN74ACT7808 Strobed First-In First-Out Memory, Texas Instruments. 2001
55. SN74LVTH162245 Bus Switchers with level shifting. Texas Instruments. 2000
56. HY57V643220C Synchronous DRAM. Hynix Inc. 2002.
57. MBM29LV160T Flash Memory. FUJITSU SEMICONDUCTOR.
2．2000上海国际智能交通及管理技术研讨会发言汇编，2000
3. Paolo Castello, Christopher Coelhho, Enrico Eel Ninno, Ennio Ottaviani, Michele Zanini," Traffic Monitoring in Motorways by Real-time Number Plate Recognition", IEEE, 0-7695-0040-4, 1999
4．牌识别技术在交通工具和城市安全中的作用及应用前景，赵明生，包丛笑，电子与金系列工程信息，1999年，第9期
5．MS320C6000系列DSPs的原理与应用 任丽香等 电子工业出版社
6．数字信号处理——理论、算法、与实现 吴广书编 清华大学出版社 1997
7．DSP芯片的原理与开发应用 张雄伟等 电子工业出版社
8. Oppenheim A V, Schafer R.Discrete-Time Signal Processing. Englewood Cliffs,NJ:Prentice-Hall.1989
9．DSP基础与应用系统设计 王念旭等编 北京航空航天大学出版社．2001
10．TMS320C54X DSP结构，原理及应用 戴明桢 北京航空航天大学出版社 2001
11．计算机图像处理 容观奥编 清华大学出版社 2000
12．图像处理和分析 章毓普编 清华大学出版社 1999
13. Kenneth R. Castleman, Digital Image Processing, Printice-Hall International, Inc., 1998
14．数字信号处理教程 程佩青 清华大学出版社
15．Code Composer Studio教程 中国人民解放军信息工程大学与中泰康通信技术有限责任 ADSP系列教材编写组。
16．DSP解决之道 北京瑞泰创新科技有限公司
17．神经网络的应用与实现 西安电子科技大学出版社
18. TMS320 DSP Algorithm Standard Rules and Guidelines, spru352.
19. eXpressDSP Algorithm Standard Rules and Guideline. Texas Instruments Incorporated 1999
20. eXpressDSP Algorithm Standard API Reference, Texas Instruments Incorporated 1999
21.The eXpressDSP Algorithm Standard. Texas Instruments Incorporated, 1999
22.TMS320数字信号处理器算法标准及参考构架 丁刚，
23.TMS320C54X DSP Reference Set, volumel, CPU and Peripheral (literature number SPRU131),Texas Instruments
24.TMS320C54x实用教程 电子科技大学出版社
25．刘晖等译 PCI系统结构(第四版) 电子工业出版社 2000
26．PCI总线与多媒体计算机 曾繁泰等 电子工业出版社 199718．TMS320C54X
27. TPS767318 DUAL-OUTPUT LOW-DROPOUT VOLTAGE REGULATORS, slvs209, Texas Instruments
28. pci2040 implementation guide Texas Instruments
29. the tms320c54x dsp-hpi and pc parallel port interface spra151
30. pci2040 implementation guide scpu004
31. A Practical Application of the TMS320C54x Host Port Interface (HPI) spra574
32. TMS320vc5402 fixed point digital signal processor sprs079 Texas Instruments
33. IDT71016s HIGH SPEED STATIC SRAM. Integrated Device Technology. Inc
34．微波与光导波技术教程 陈抗生 浙江大学出版社 2000
35. TMS320VC5402 and TMS320UC5402 Bootloader spra616 Texas Instruments
36. DSP Reference Set, volume4, Application Guide(literature number SPRU173), Texas Instruments
37. TMS320C54X DSP Reference Set, volume2,Mnemonic Instruction Set(literature number SPRU172),Texas Instruments
38. WinDrive Developer's Guide Jungo公司
39．Windows核心编程 Jeffrey Richter著，王建华译，机械工业出版社
40．Windows98下硬件中断驱动程序的开发，杭州浙江大学，李博 鲍超
41. Markel J D. FFT pruning. IEEE Trans. Audio Electroacoust. 1971,19(4)
42. Duhamel P, Holtmann H. Split-radix FFT algorithm. Electronics Letters. 1984, 20(1): 14-16
43. Skinner D P.Pruning the decimation-in-time FFT algorithm. IEEE Trans.on ASSP, 1976,24(Apr): 193-292
44. Heideman M T.Kultiplicative Complexity,Concolution,and the DFT.New York:Springer-Verlag NewYorklne, 1988
45. TMS320C6000 Peripherals Reference Guide Texas Instruments
46. TMS320C6205 Fixed-Point Digital Signal Processor Texas Instruments
47. TMS320C6000 CPU and Instruction Set reference Guide(literature number SPRZ189f) Texas Instruments
48. Manual Update Sheet (literature number SPRU168b)Texas Instruments
49. Manual Update Sheet (literature number SPRU122b)Texas Instruments
50. TMS320C62X Image/Video processing library Programmer's reference (literature number SPRU400a) Texas Instruments
51. TMS320C62X Peripheral support library Programmer's reference (literature number SPRU273b) Texas Instruments
52. TPS70148 DUAL-OUTPUT LOW-DROPOUT VOLTAGE REGULATORS, with power up sequencing for split voltage DSP system, slvs222b, Texas Instruments
53. DATASHEET for SAA7111 Enhanced Video Input Processor. PHILIPS Semiconductors. 1998.
54. SN74ACT7808 Strobed First-In First-Out Memory, Texas Instruments. 2001
55. SN74LVTH162245 Bus Switchers with level shifting. Texas Instruments. 2000
56. HY57V643220C Synchronous DRAM. Hynix Inc. 2002.
57. MBM29LV160T Flash Memory. FUJITSU SEMICONDUCTOR.