基于DSP的视频监控系统设计及相关算法研究
|
摘要
视频监控作为一种重要的安防手段已经有了一段很长的发展历史。在社会信息化日益发展的今天,数字化视频监控已经成为视频监控的重点发展领域,监控录像系统的产品正向着网络化、高清晰化、智能化的方向发展。此外,嵌入式系统在监控系统中的使用也很有潜力。
基于上述现状与趋势,本文试图从安防与监控应用背景出发,作了如下的相关研究与设计:
首先,搭建了以TMS320DM642为核心的视频处理硬件平台,其中分别从DSP模块、外部存储器模块、视频解码器模块及电压管理模块与EMIF总线、I2C总线、VP总线及PCI总线两个层面进行了设计。
随后,基于该平台完成了具有良好移植性的软件设计,其中包括DSP端系统软件设计与PC端应用软件设计两部分,并重点介绍了RF5结构及使用与WinDriver工具及使用。
然后,在总结智能视频监控中动目标检测与跟踪理论的基础上,研究了目前适于DSP的实用算法并给出了其流程,其中具体分析并归纳了阈值的选取、阴影的抑制、连通性的分析和不变矩与最小外接矩形的使用。
最后,给出了目前的测试与实验结果及相关分析,并对目前工作进展情况作了总结。
智能视频监控系统的研究成果可以提高传统视频监控系统的自动化程度,必将对社会经济发展、国防建设与社会治安产生重要的意义。
Video surveillance has been developed for a long time as a security method. Nowadays, with the development of the information technology, digital video surveillance has become an important domain. Products for surveillance recording system are required to be networked and intelligent, with high resolution and low bit rate. Meanwhile, embedding technology is much potential in surveillance systems. Based on actuality and tendency above, much related research and design about security and surveillance are introduced in this thesis as follows:
At first hardware platform based on TMS320DM642 about video processing is designed and finished, which consists of DSP module, external memory module, video decoder module and power module that interact through EMIF bus, I2C bus, VP bus and PCI bus.
Corresponding to hardware platform above, transplantable software is designed and programed, including system software on DSP and application software on PC. Especially, the architecture of RF5 and WinDriver software are introduced and in use.
Then motion detection and object tracking around intelligent video surveillance technology are summarized. Its algorithms customized on DSP and flow chart are given, in which selection of threshold, detection of shadow, analysis of continuity, use of invariant moment and utility of bounding box are mainly discussed.
Finally the present results about testing the above system and simulating the above algorithms are provided. It is concluded that some components need improving and upgrading.
Advanced intelligent video surveillance technology will improve the degree of automation of traditional video surveillance system. It will have more significance for economy, national defense and public security.
基于上述现状与趋势,本文试图从安防与监控应用背景出发,作了如下的相关研究与设计:
首先,搭建了以TMS320DM642为核心的视频处理硬件平台,其中分别从DSP模块、外部存储器模块、视频解码器模块及电压管理模块与EMIF总线、I2C总线、VP总线及PCI总线两个层面进行了设计。
随后,基于该平台完成了具有良好移植性的软件设计,其中包括DSP端系统软件设计与PC端应用软件设计两部分,并重点介绍了RF5结构及使用与WinDriver工具及使用。
然后,在总结智能视频监控中动目标检测与跟踪理论的基础上,研究了目前适于DSP的实用算法并给出了其流程,其中具体分析并归纳了阈值的选取、阴影的抑制、连通性的分析和不变矩与最小外接矩形的使用。
最后,给出了目前的测试与实验结果及相关分析,并对目前工作进展情况作了总结。
智能视频监控系统的研究成果可以提高传统视频监控系统的自动化程度,必将对社会经济发展、国防建设与社会治安产生重要的意义。
Video surveillance has been developed for a long time as a security method. Nowadays, with the development of the information technology, digital video surveillance has become an important domain. Products for surveillance recording system are required to be networked and intelligent, with high resolution and low bit rate. Meanwhile, embedding technology is much potential in surveillance systems. Based on actuality and tendency above, much related research and design about security and surveillance are introduced in this thesis as follows:
At first hardware platform based on TMS320DM642 about video processing is designed and finished, which consists of DSP module, external memory module, video decoder module and power module that interact through EMIF bus, I2C bus, VP bus and PCI bus.
Corresponding to hardware platform above, transplantable software is designed and programed, including system software on DSP and application software on PC. Especially, the architecture of RF5 and WinDriver software are introduced and in use.
Then motion detection and object tracking around intelligent video surveillance technology are summarized. Its algorithms customized on DSP and flow chart are given, in which selection of threshold, detection of shadow, analysis of continuity, use of invariant moment and utility of bounding box are mainly discussed.
Finally the present results about testing the above system and simulating the above algorithms are provided. It is concluded that some components need improving and upgrading.
Advanced intelligent video surveillance technology will improve the degree of automation of traditional video surveillance system. It will have more significance for economy, national defense and public security.
引文
[1] 白木,周洁. 数字视频监控系统. 有线电视技术,2002,(18):39-43
[2] I.Haritaoglu, D.Harwood, L.S.Davis. "W4: Real-time surveillance of people and their activities". IEEE Trans. Pattern Anal. Machine Intell., Vol.22, pp.809-830, Aug. 2000
[3] www.cs.cmu.edu/~vsam
[4] Weiming Hu, Tieniu Tan, Liang Wang, Steve Maybank. "A Survey on Visual Surveillance of Object Motion and Behaviors". IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews, Vol.34, No.3, August 2004
[5] J.Barron, D.Fleet, S.Beauchemin. "Performance of Optical Flow Techniques". International Journal of Computer Vision, Vol.12, No.1, pp.42-77, 1994
[6] A.J.Lipton, H.Fujiyoshi, R.S.Patil. "Moving target classification and tracking from real-time video". IEEE Workshop Applications of Computer Vision, pp.8-14, 1998
[7] C.Stauffer, W.Grimson. "Adaptive background mixture models for real-time tracking". IEEE Conf. Computer Vision and Pattern Recognition, Vol.2, pp.246-252, 1999
[8] Alan Bovik. Handbook of Image and Video Processing, Second Edition. Peking: Publishing House of Electronics Industry, 2006
[9] 冈萨雷斯等著,阮秋琦等译. 数字图像处理(第二版). 电子工业出版社,2003
[10] Texas Instruments. TMS320DM642 Video/Imaging Fixed-Point Digital Signal Processor. www.ti.com, SPRS200J
[11] Texas Instruments. TMS320C6000 DSP External Memory Interface (EMIF) Reference Guide. www.ti.com, SPRU266E
[12] Texas Instruments. TVP5150APBS. www.ti.com, SLES087
[13] Texas Instruments. TMS320C6000 DSP Inter-Integrated Circuit (I2C) Module Reference Guide. www.ti.com, SPRU175C
[14] Texas Instruments. TMS320C64x DSP Video Port / VCXO Interpolated Control (VIC) Port Reference Guide. www.ti.com, SPRU629E
[15] Texas Instruments. TMS320C6000 DSP Enhanced Direct Memory Access (EDMA) Controller Reference Guide. www.ti.com, SPRU234B
[16] Texas Instruments. TMS320C6000 DSP Peripheral Component Interconnect (PCI)Reference Guide. www.ti.com, SPRU581B
[17] Texas Instruments. TPS54310. www.ti.com, SLVS412B
[18] Texas Instruments. TMS320C6000 DSP/BIOS 5.20 Application Programming Interface (API) Reference Guide. www.ti.com, SPRU403J
[19] Texas Instruments. TMS320C6000 Chip Support Library API Reference Guide. www.ti.com, SPRU401J
[20] Texas Instruments. TMS320C64x DSP Two-Level Internal Memory Reference Guide. www.ti.com, SPRU610C
[21] Texas Instruments. Reference Frameworks for eXpressDSP Software: RF5, An Extensive, High-Density System. www.ti.com, SPRA795A
[22] Texas Instruments. Reference Frameworks for eXpressDSP Software: API Reference. www.ti.com, SPRA147C
[23] Jungo Ltd. WinDriver PCI/PCMCIA/ISA v8.01 Low-Level API Reference
[24] 冈萨雷斯等著,阮秋琦等译. 数字图像处理(MATLAB 版). 电子工业出版社,2005
[25] 韩思奇,王蕾. 图像分割的阈值法概述. 系统工程与电子技术,2002,(6):91-94
[26] N.Ostu. "Threshold Selection Method from Gray - Level Histograms". IEEE Trans. on System, Man, and Cybernetics, 1979, 9(1):62-66
[27] J.Stauder, R.Mech, J.Ostermann. "Detection of moving cast shadows for object segmentation". IEEE Transactions on Multimedia, Vol.1, No.1, pp.65-76, Mar. 1999
[28] Hu M K. "Visual pattern recognition by moment invarients". IRE Trans. on Information Theory, 1962, (8):179-187
[29] Texas Instruments. TMS320DM648 Digital Media Processor. www.ti.com, SPRS372
[30] 王长军. 基于视频的目标检测与跟踪技术研究:[博士学位论文]. 浙江:浙江大学 2006
[2] I.Haritaoglu, D.Harwood, L.S.Davis. "W4: Real-time surveillance of people and their activities". IEEE Trans. Pattern Anal. Machine Intell., Vol.22, pp.809-830, Aug. 2000
[3] www.cs.cmu.edu/~vsam
[4] Weiming Hu, Tieniu Tan, Liang Wang, Steve Maybank. "A Survey on Visual Surveillance of Object Motion and Behaviors". IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews, Vol.34, No.3, August 2004
[5] J.Barron, D.Fleet, S.Beauchemin. "Performance of Optical Flow Techniques". International Journal of Computer Vision, Vol.12, No.1, pp.42-77, 1994
[6] A.J.Lipton, H.Fujiyoshi, R.S.Patil. "Moving target classification and tracking from real-time video". IEEE Workshop Applications of Computer Vision, pp.8-14, 1998
[7] C.Stauffer, W.Grimson. "Adaptive background mixture models for real-time tracking". IEEE Conf. Computer Vision and Pattern Recognition, Vol.2, pp.246-252, 1999
[8] Alan Bovik. Handbook of Image and Video Processing, Second Edition. Peking: Publishing House of Electronics Industry, 2006
[9] 冈萨雷斯等著,阮秋琦等译. 数字图像处理(第二版). 电子工业出版社,2003
[10] Texas Instruments. TMS320DM642 Video/Imaging Fixed-Point Digital Signal Processor. www.ti.com, SPRS200J
[11] Texas Instruments. TMS320C6000 DSP External Memory Interface (EMIF) Reference Guide. www.ti.com, SPRU266E
[12] Texas Instruments. TVP5150APBS. www.ti.com, SLES087
[13] Texas Instruments. TMS320C6000 DSP Inter-Integrated Circuit (I2C) Module Reference Guide. www.ti.com, SPRU175C
[14] Texas Instruments. TMS320C64x DSP Video Port / VCXO Interpolated Control (VIC) Port Reference Guide. www.ti.com, SPRU629E
[15] Texas Instruments. TMS320C6000 DSP Enhanced Direct Memory Access (EDMA) Controller Reference Guide. www.ti.com, SPRU234B
[16] Texas Instruments. TMS320C6000 DSP Peripheral Component Interconnect (PCI)Reference Guide. www.ti.com, SPRU581B
[17] Texas Instruments. TPS54310. www.ti.com, SLVS412B
[18] Texas Instruments. TMS320C6000 DSP/BIOS 5.20 Application Programming Interface (API) Reference Guide. www.ti.com, SPRU403J
[19] Texas Instruments. TMS320C6000 Chip Support Library API Reference Guide. www.ti.com, SPRU401J
[20] Texas Instruments. TMS320C64x DSP Two-Level Internal Memory Reference Guide. www.ti.com, SPRU610C
[21] Texas Instruments. Reference Frameworks for eXpressDSP Software: RF5, An Extensive, High-Density System. www.ti.com, SPRA795A
[22] Texas Instruments. Reference Frameworks for eXpressDSP Software: API Reference. www.ti.com, SPRA147C
[23] Jungo Ltd. WinDriver PCI/PCMCIA/ISA v8.01 Low-Level API Reference
[24] 冈萨雷斯等著,阮秋琦等译. 数字图像处理(MATLAB 版). 电子工业出版社,2005
[25] 韩思奇,王蕾. 图像分割的阈值法概述. 系统工程与电子技术,2002,(6):91-94
[26] N.Ostu. "Threshold Selection Method from Gray - Level Histograms". IEEE Trans. on System, Man, and Cybernetics, 1979, 9(1):62-66
[27] J.Stauder, R.Mech, J.Ostermann. "Detection of moving cast shadows for object segmentation". IEEE Transactions on Multimedia, Vol.1, No.1, pp.65-76, Mar. 1999
[28] Hu M K. "Visual pattern recognition by moment invarients". IRE Trans. on Information Theory, 1962, (8):179-187
[29] Texas Instruments. TMS320DM648 Digital Media Processor. www.ti.com, SPRS372
[30] 王长军. 基于视频的目标检测与跟踪技术研究:[博士学位论文]. 浙江:浙江大学 2006