基于DM642网络通信的运动检测研究
摘要
随着计算机技术、数字图象处理技术及相关理论的发展,计算机视觉的技术水平不断提高,应用领域迅速拓宽,在国防航天、工业自动化生产、交通监管等领域获得了越来越多的应用。在计算机视觉领域中,运动目标检测与跟踪研究的最多,而且应用水平也最高,是运动图像分析、智能监控、可视人机交互中的重要处理步骤。通过运动检测可以得到图像中的运动信息,提取图像中的运动目标,然后进行定位跟踪,广泛的应用于银行、交通和机场等安防领域。
本设计“基于DM642网络传输的运动检测的研究”的主要内容就是在DSP技术基础上,实现一种基于嵌入式网络传输的运动目标检测系统,完成系统的软硬件设计,同时寻找一种实用的运动目标检测算法。
本文的主要工作如下:
1.基于DSP网络传输的嵌入式视频系统的软硬件设计:介绍了基于TI公司多媒体处理芯片TMS320DM642的视频监控系统的设计和实现,讨论了系统软硬件的构成,分析了在TI的软件参考框架RF5架构下的操作系统任务调度,和基于TI NDK的TCP/IP协议栈在DM642上的实现。实验结果表明该系统能实时对由摄像机捕获的图像运行运算,并将处理结果通过以太网传送给客户端。该系统不仅为各种视频处理算法提供了有效的软硬件平台,还可以实现远程监控、本地播放和本地存储等功能。
2.运动目标检测算法研究:本文采用背景差分法进行目标检测,提出了一种背景模型选择及其自适应更新的方法。该方法尤其适用于场景中有物体启停的场合。利用该方法在VC++平台下对一段交通视频进行处理,实验结果证明该算法能够一定程度上避免动态变化和干扰,具有良好的稳健性和通用性。
With the development of computer technology, digital image processing technologies and some other related theory, Computer vision technology has improved continuously, applications fields are rapidly widening, and is used in defense aerospace, industrial automation, traffic surveillance and so on. In the field of computer vision, motion detection and tracking are researched most and the application level is the highest. It is the important process of motion image analysis, intelligent surveillance and visualized human-machine interactive. One can gain motion information and extracting the motion object from the image through motion detection, and then locating and tracking, and motion detection is widely used in the security field of bank, transport and airport.
The main content of this design Motion Detection Research Based on DM642 Networking Communication is based on the DSP technologies, and then a motion detecting system based on embedded networking communication is realized. The hardware and software design of this system is completed, and seeking a practical algorithm of motion detecting at the same time.
The major work of this paper is as follows:
1. Software and hardware design of embedded video system based on DSP networking transmission: a video surveillance system design and realization based on TI's TMS320DM642 is introduced, the hardware and software composition of the system is discussed, and analyzed the task scheduling of the operating system in TI's reference framework RF5 and also realization of TCP/IP protocol based on TI's NDK. Results show that the system can compute the real-time images captured by the camera, and the results can be transmitted via Ethernet to the client. This system can not only provides a hardware and software platform for various video processing algorithms, but also achieve remote monitoring, local display, local storage, and some other functions.
2. Research of the motion detection algorithms: Background difference method for motion detection is used in this paper, a background model selection and adaptive updating method are also proposed, and applies particularly in the scenes of objects starting to move and stop. This method is used to dealing with a transport video in VC++ platform and the results show that the algorithm can avoid certain dynamic change and interference to some extent, and has a good stability and versatility.
本设计“基于DM642网络传输的运动检测的研究”的主要内容就是在DSP技术基础上,实现一种基于嵌入式网络传输的运动目标检测系统,完成系统的软硬件设计,同时寻找一种实用的运动目标检测算法。
本文的主要工作如下:
1.基于DSP网络传输的嵌入式视频系统的软硬件设计:介绍了基于TI公司多媒体处理芯片TMS320DM642的视频监控系统的设计和实现,讨论了系统软硬件的构成,分析了在TI的软件参考框架RF5架构下的操作系统任务调度,和基于TI NDK的TCP/IP协议栈在DM642上的实现。实验结果表明该系统能实时对由摄像机捕获的图像运行运算,并将处理结果通过以太网传送给客户端。该系统不仅为各种视频处理算法提供了有效的软硬件平台,还可以实现远程监控、本地播放和本地存储等功能。
2.运动目标检测算法研究:本文采用背景差分法进行目标检测,提出了一种背景模型选择及其自适应更新的方法。该方法尤其适用于场景中有物体启停的场合。利用该方法在VC++平台下对一段交通视频进行处理,实验结果证明该算法能够一定程度上避免动态变化和干扰,具有良好的稳健性和通用性。
With the development of computer technology, digital image processing technologies and some other related theory, Computer vision technology has improved continuously, applications fields are rapidly widening, and is used in defense aerospace, industrial automation, traffic surveillance and so on. In the field of computer vision, motion detection and tracking are researched most and the application level is the highest. It is the important process of motion image analysis, intelligent surveillance and visualized human-machine interactive. One can gain motion information and extracting the motion object from the image through motion detection, and then locating and tracking, and motion detection is widely used in the security field of bank, transport and airport.
The main content of this design Motion Detection Research Based on DM642 Networking Communication is based on the DSP technologies, and then a motion detecting system based on embedded networking communication is realized. The hardware and software design of this system is completed, and seeking a practical algorithm of motion detecting at the same time.
The major work of this paper is as follows:
1. Software and hardware design of embedded video system based on DSP networking transmission: a video surveillance system design and realization based on TI's TMS320DM642 is introduced, the hardware and software composition of the system is discussed, and analyzed the task scheduling of the operating system in TI's reference framework RF5 and also realization of TCP/IP protocol based on TI's NDK. Results show that the system can compute the real-time images captured by the camera, and the results can be transmitted via Ethernet to the client. This system can not only provides a hardware and software platform for various video processing algorithms, but also achieve remote monitoring, local display, local storage, and some other functions.
2. Research of the motion detection algorithms: Background difference method for motion detection is used in this paper, a background model selection and adaptive updating method are also proposed, and applies particularly in the scenes of objects starting to move and stop. This method is used to dealing with a transport video in VC++ platform and the results show that the algorithm can avoid certain dynamic change and interference to some extent, and has a good stability and versatility.
引文
[1]李华,宋晓虹,张宁.背景模型的建立及保持方法比较.电脑与信息技术[J],2004,12(1):5-8.
[2]Friedman.N,Russell.S.Image segmentation in video sequences:A probabilistic approach.Presented at the 13th Conf.Uncertainty in Artificial Intelligence,Providence ,RI,1997.
[3]Stauffer.C,Grimson.W,E.L.Learning patterns of activity using real-time tracking.IEEE Trans.Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[4]Elagammal.A,Harwood.D,Davis.L.Non-parametric model for background subtraction[A].In:Proceedings of International Conference on Computer Vision[C],Kerkyra,Greece,1999,pp.751-767.
[5]Rittscher.J,Kato.J,Joga.S,BIake.A.A probabilistic background model for tracking.Proc.European Conf.Computer Vision,2000,2:336-350.
[6]Toyama.K,Krumm.J,Brumitt.B,Meyers.B.Wallflower.Principles and practice of background maintenance.Proceedings of IEEE International Conference on Computer Vision,1(20-27):255-261.
[7]Rosin.P.Thresholding for Change Detection.Proceedings of IEEE,International Conference on Computer Vision,1998,pp.274-279.
[8]Liyuan Li,Weimin Huang,Irene Y,H.Gu,Qi Tian.Foreground Object Detection in Changing Background Based on Color Co-Occurrence Statistics.Proceedings of the Sixth IEEE Workshop on Application of Computer Vision,2002,pp.369-274.
[9]NOBUYUKI OTSU.A Threshold Selection Method from Gray-Level Histograms [J].IEEE Transactions on Systems,Man and Cybernetics,1979,9(1):62-66.
[10]冈萨雷斯.数字图象处理(第二版)(阮秋琦,阮宇智等译)[M].北京:电子工业出版社,2006.
[11]彭启琮,管庆等.DSP集成开发环境-CCS及DSP/BIOS的原理与应用[M].北京:电子工业出版社,2005.
[12]章毓晋.图象分割[M].科学出版社,2001.
[13]Texas Instruments.TMS320 DSP/BIOS User's Guide[Z],2002.
[14]Texas Instruments.TMS320DM642 Data Sheet[Z],2004.
[15]Texas Instruments.TMS320C6000 Optimizing Compiler User's Guide[Z],2004.
[16]Antoine Monnet,Anurag Mittal,Nikos Paragios,Visvanathan Ramesh.Background Modeling and Subtraction of Dynamic Scenes.Proceedings of the Ninth IEEE International Conference on Computer Vision.2003,2:1305-1312.
[17]Gupte.S,Masoud.O,R.EK,Martin,and Papanikolopoulos NP.Detection and Classification of Vehicles.IEEE transactions on intellingent transportation systems,2002,3(1):37-47.
[18]Texas Instruments.JPEG with Motion Detection on the DM642 EVM.Application Report[Z],2004.
[19]Tao Yang,Stan Z.Li,Quan Pan,Jing Li.Real-Time and Accurate Segmentation of Moving Objects in Dynamic Scene.International Multimedia Conference,2004,New York,USA,pp.136-143.
[20]Texas Instruments.TMS320C6000 Network Developer's Kit(NDK)[Z].
[21]李亦非,吴裕斌,曹丹华,李非一.基于DSP/BIOS的设备驱动程序开发.计算机与数字工程[J],2005,33(3):69-72.
[22]MAO Yan-fen,SHI Peng-fei.Diversity Sampling Based Kernel Density Estimation for Back ground Modeling.Journal of Shanghai University(English Edition)[J],2005,9(6):506-509.
[23]Robert T.Collins,Alan J.Lipton,Takeo Kanade.A system for video Surveillance and Monitoring[R].Carnegie Mellon,Carnegie Mellon University,2000,pp.54-67.
[24]Haritaoglu.I,Harwood.D,Davis.L.W4:Real-time surveillance of people and their activities[J].IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[25]John D.Prahge.Detecting,Recognizing and Understanding Video Events in Surveillance Video[A].Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance[C].Miami:AVSS'03,2003:48-57.
[26]Tai J,Tsang S,Lin C,Song K.Real-time image tracking for automatic Traffic monitoring and enforcement application.Image and Vision- Computing[J],2004,22(6):485-501.
[27]孟凤,视频监控系统中运动目标检测与跟踪算法的研究[硕士学位论文],燕山大学,2007.
[28]赵荣椿等.数字图象处理导论[M].西北工业大学出版社.1996.
[29]刘康,基于DM642的网络多媒体开发平台的设计与实现[硕士学位论文],天津大学,2005.
[30]何宇,郭建明.基于TMS320DM642单芯片的网络接入系统研究与实现[J],2005,29(5):770-773.
[31]Guo Jing,Rajan.D,Chng Eng Siong.Motion Detection with Adaptive Background and Dynamic Thresholds.Information,Communications and Signal Processing,2005 Fifth International Conference,2005,pp.41-45.
[32]TMS320C6000 Chip Support Library API Reference Guide,2003.
[33]TMS320C6000 Peripherals Reference Guide,2003.
[34]TMS320C6000 DSP/BIOS Application Programming Interface(API) Reference Guide,http://www.ti.com,2003.
[35]TMS320 DSP/BIOS User's Guide,http://www.ti.com,2003.
[33]TMS320C64x Image/Video Processing Library Programmer's Reference,http://www.ti.com,2003.
[36]Reference Frameworks foreXpressDSPSoftware:RF5,An Extensive,High Density System,http://www.ti.com,2003.
[37]The TMS320DM642 Video Port Mini-Driver,http://www.ti.com,2003.
[38]DSP/BIOS Device Driver Developer's Guide,http://www.ti.com,2002.
[39]TMS320 DSP Algorithm Standard Rules and Guidelines,http://www.ti.com,2002.
[40]Andrew R.Webb.Statistical Pattern Recognition[M].Second Edition,2002.
[41]张莎莎,图像分割与运动目标跟踪算法研究[硕士学位论文],哈尔滨工业大学,2006.
[42]王玮等,DM642在网络视频传输系统中的应用,自动化仪表[J],2007,28(2):19-25.
[43]T.A.Brown and J.Koplowitz.The weighted nearest neighbor rule for class dependent sample sizes.IEEE Transactions on Information Theory,1979,25(5):617-619.
[44] Bruce.J, Balch.T, Veloso.M. Fast and inexpensive color image segmentation for interactive robots[A]. In: Proc. IEEE / RSJ International Conference on Intelligent Robots and System [C], 2000,3:2061-2066.
[45] B.Espiau, F.Chaumette, F.Rives. A new approach to visual servoing in robotics [J]. IEEE Trans on Robotics and Automation, 1992, 8(3):313-326.
[46] GD.Hager. A modular system for robust positioning using feedback from stereo vision[J]. IEEE Transon Robotics and Automation, 1997,13(4):582-595.
[47] K.Hashimoto, T.Kimoto, T.Ebineetal. Manipulator control with image-based visual servo[A].IEEE Confront Robotics and Automation[C]. California, 1991, pp.2267-2272.
[48] S.Hutchinson, G.Hager, P.Corke. Atutorial introduction to visual servo control [J]. IEEE Trans on Robotics and Automation, 1996,12(5):651-670.
[49] W.Jang, Z.B.jen. Feature based visual servoing of an eye-in-hand robot with improved tracking performance [A]. IEEE Confront Robotics and Automation[C].California, 1991, pp.2254-2260.
[50] M.Jagersand.On-line estimation of visual motor models for robot control and visual simulation [D].USA: University of Rochester, 1998.
[51] R。Jain, R.Kasturi, and B.GSchunck. Machine Vision.McGraw-Hill,1995.
[52] H.Kitano, Y.Kuniyoshi, I.Noda, M.Asada, H.Matsubara, and E.Osawa.RoboCup:A challenge problem for AI.Magazine, 1997,18(l):73-85.
[53] M.C.Ngugen. Situation reined behavior-based stereovision to gain robustness adaptation in manipulator control[A]. Proc of SPIE[C]. Massachusetts, 1999,38(37):90-97.
[54] J.Pauli. Learning to recognize and grasp objects[J] .Machine Learning, 1998,31(1-3):239-258.
[55] N.P.Papaniko lopoulos, P.K.Khosla, T.Kanade. Visual tracking of a moving target by a camera mounted on a robot: A combination of vision and control [J].IEEE Trans on Robotics and Automation, 1993, 9(1): 14-35.
[56]H.Sutanto,R.Sharma,V.Varma.The role of exploratory movement in visual servoing without calibration[J].Robotics and Autonomous Systems,1998,23(3):153-169.
[57]M.Vargas,F.R.Rubio,A.R.Malpesa.Pose-estimation and control in a 3D visual servoing system[A].Proc of the 14th IFA[C].Beijing,1999,pp.317-323.
[58]P.Viola,M.Jones.Rapid object detection using a Boosted cascade of simple features[C].In:Proc IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2001,pp.511-518.
[59]D.B.Westmore,W.J.Wilson.Direct dynamic control of a robot using an end-point mounted camera and Kalman filter position estimation[A].IEEE Conf on Robotics and Automation[C].California,1991,3:2376-2384.
[60]L.E.Weiss,A.C.Sanderson,C.P.Neuman.Dynamic sensor-based control of robots with visual feedback[J].IEEE Robot Automation,1987,3(5):404-417.
[61]S.Wijesoma,D.Wolfe,R.Richards.Eye-to2hand coordination for vision-guided robot control applications[J].In Robotics Research,1993,12(1):65-78.
[62]W.J.Wilson,C.C.Hulls,G.S.Bell.Relative end-effect to control using Cartesian position-based visual servoing[J].IEEE Trans on Robotics and Automation,199612(5):684-696.
[63]崔屹.图象处理与分析:数学形态学方法及应用[M].科学出版社.2000.
[64]陈祖爵,陈潇君,何鸿.基于改进的混合高斯模型的运动目标检测.中国图象图像学报[J],2007,12(9):1581-1589.
[65]郑世友,费树岷,刘怀,龙飞.动态场景图象序列中运动目标检测新方法.中国图象图形学报[J],2007,12(9):1590-1597.
[66]付安新,基于DSP的嵌入式机器人视觉系统的设计与研究[硕士学位论文],浙江大学,2006.
[67]刘宏,李锦涛,刘群,钱跃良,李豪杰.融合颜色和梯度特征的运动阴影消除方法.计算机辅助设计与图形学学报[J],2007,19(10):1279-1285.
[68]Shahinfard.E,Sid-Ahmed.M,Ahmadi.M.An Improved Motion Adaptive Deinterlacing Method Using Variable Block-Size Motion Detection.Signal Processing and Information Technology,2007 IEEE International Symposium,2007,pp.122-126.
[69]梁迅,熊水东.DM642嵌入式网络接口开发设计.计算机工程[J],2007,33(16):277-279.
[70]Wenming Yang,Wang Lu,Naitong Zhang.Object Extraction Combining Image Partition with Motion Detection.Image Processing,IEEE International Conference,2007,3:Ⅲ-337-Ⅲ-340.
[71]Aksoy.E,Adar.N,Canbek.S,Seke.E,Gurel.U.Real-time Motion Region Detection and Contouring System.Signal Processing and Communications Applications,2007,SIU.IEEE 15th 11-13,2007,pp.1-4.
[72]潘秦华,车辆目标检测与交通流量检测系统的研究,西安电子科技大学[硕士学位论文],2005年.
[2]Friedman.N,Russell.S.Image segmentation in video sequences:A probabilistic approach.Presented at the 13th Conf.Uncertainty in Artificial Intelligence,Providence ,RI,1997.
[3]Stauffer.C,Grimson.W,E.L.Learning patterns of activity using real-time tracking.IEEE Trans.Pattern Analysis and Machine Intelligence,2000,22(8):747-757.
[4]Elagammal.A,Harwood.D,Davis.L.Non-parametric model for background subtraction[A].In:Proceedings of International Conference on Computer Vision[C],Kerkyra,Greece,1999,pp.751-767.
[5]Rittscher.J,Kato.J,Joga.S,BIake.A.A probabilistic background model for tracking.Proc.European Conf.Computer Vision,2000,2:336-350.
[6]Toyama.K,Krumm.J,Brumitt.B,Meyers.B.Wallflower.Principles and practice of background maintenance.Proceedings of IEEE International Conference on Computer Vision,1(20-27):255-261.
[7]Rosin.P.Thresholding for Change Detection.Proceedings of IEEE,International Conference on Computer Vision,1998,pp.274-279.
[8]Liyuan Li,Weimin Huang,Irene Y,H.Gu,Qi Tian.Foreground Object Detection in Changing Background Based on Color Co-Occurrence Statistics.Proceedings of the Sixth IEEE Workshop on Application of Computer Vision,2002,pp.369-274.
[9]NOBUYUKI OTSU.A Threshold Selection Method from Gray-Level Histograms [J].IEEE Transactions on Systems,Man and Cybernetics,1979,9(1):62-66.
[10]冈萨雷斯.数字图象处理(第二版)(阮秋琦,阮宇智等译)[M].北京:电子工业出版社,2006.
[11]彭启琮,管庆等.DSP集成开发环境-CCS及DSP/BIOS的原理与应用[M].北京:电子工业出版社,2005.
[12]章毓晋.图象分割[M].科学出版社,2001.
[13]Texas Instruments.TMS320 DSP/BIOS User's Guide[Z],2002.
[14]Texas Instruments.TMS320DM642 Data Sheet[Z],2004.
[15]Texas Instruments.TMS320C6000 Optimizing Compiler User's Guide[Z],2004.
[16]Antoine Monnet,Anurag Mittal,Nikos Paragios,Visvanathan Ramesh.Background Modeling and Subtraction of Dynamic Scenes.Proceedings of the Ninth IEEE International Conference on Computer Vision.2003,2:1305-1312.
[17]Gupte.S,Masoud.O,R.EK,Martin,and Papanikolopoulos NP.Detection and Classification of Vehicles.IEEE transactions on intellingent transportation systems,2002,3(1):37-47.
[18]Texas Instruments.JPEG with Motion Detection on the DM642 EVM.Application Report[Z],2004.
[19]Tao Yang,Stan Z.Li,Quan Pan,Jing Li.Real-Time and Accurate Segmentation of Moving Objects in Dynamic Scene.International Multimedia Conference,2004,New York,USA,pp.136-143.
[20]Texas Instruments.TMS320C6000 Network Developer's Kit(NDK)[Z].
[21]李亦非,吴裕斌,曹丹华,李非一.基于DSP/BIOS的设备驱动程序开发.计算机与数字工程[J],2005,33(3):69-72.
[22]MAO Yan-fen,SHI Peng-fei.Diversity Sampling Based Kernel Density Estimation for Back ground Modeling.Journal of Shanghai University(English Edition)[J],2005,9(6):506-509.
[23]Robert T.Collins,Alan J.Lipton,Takeo Kanade.A system for video Surveillance and Monitoring[R].Carnegie Mellon,Carnegie Mellon University,2000,pp.54-67.
[24]Haritaoglu.I,Harwood.D,Davis.L.W4:Real-time surveillance of people and their activities[J].IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[25]John D.Prahge.Detecting,Recognizing and Understanding Video Events in Surveillance Video[A].Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance[C].Miami:AVSS'03,2003:48-57.
[26]Tai J,Tsang S,Lin C,Song K.Real-time image tracking for automatic Traffic monitoring and enforcement application.Image and Vision- Computing[J],2004,22(6):485-501.
[27]孟凤,视频监控系统中运动目标检测与跟踪算法的研究[硕士学位论文],燕山大学,2007.
[28]赵荣椿等.数字图象处理导论[M].西北工业大学出版社.1996.
[29]刘康,基于DM642的网络多媒体开发平台的设计与实现[硕士学位论文],天津大学,2005.
[30]何宇,郭建明.基于TMS320DM642单芯片的网络接入系统研究与实现[J],2005,29(5):770-773.
[31]Guo Jing,Rajan.D,Chng Eng Siong.Motion Detection with Adaptive Background and Dynamic Thresholds.Information,Communications and Signal Processing,2005 Fifth International Conference,2005,pp.41-45.
[32]TMS320C6000 Chip Support Library API Reference Guide,2003.
[33]TMS320C6000 Peripherals Reference Guide,2003.
[34]TMS320C6000 DSP/BIOS Application Programming Interface(API) Reference Guide,http://www.ti.com,2003.
[35]TMS320 DSP/BIOS User's Guide,http://www.ti.com,2003.
[33]TMS320C64x Image/Video Processing Library Programmer's Reference,http://www.ti.com,2003.
[36]Reference Frameworks foreXpressDSPSoftware:RF5,An Extensive,High Density System,http://www.ti.com,2003.
[37]The TMS320DM642 Video Port Mini-Driver,http://www.ti.com,2003.
[38]DSP/BIOS Device Driver Developer's Guide,http://www.ti.com,2002.
[39]TMS320 DSP Algorithm Standard Rules and Guidelines,http://www.ti.com,2002.
[40]Andrew R.Webb.Statistical Pattern Recognition[M].Second Edition,2002.
[41]张莎莎,图像分割与运动目标跟踪算法研究[硕士学位论文],哈尔滨工业大学,2006.
[42]王玮等,DM642在网络视频传输系统中的应用,自动化仪表[J],2007,28(2):19-25.
[43]T.A.Brown and J.Koplowitz.The weighted nearest neighbor rule for class dependent sample sizes.IEEE Transactions on Information Theory,1979,25(5):617-619.
[44] Bruce.J, Balch.T, Veloso.M. Fast and inexpensive color image segmentation for interactive robots[A]. In: Proc. IEEE / RSJ International Conference on Intelligent Robots and System [C], 2000,3:2061-2066.
[45] B.Espiau, F.Chaumette, F.Rives. A new approach to visual servoing in robotics [J]. IEEE Trans on Robotics and Automation, 1992, 8(3):313-326.
[46] GD.Hager. A modular system for robust positioning using feedback from stereo vision[J]. IEEE Transon Robotics and Automation, 1997,13(4):582-595.
[47] K.Hashimoto, T.Kimoto, T.Ebineetal. Manipulator control with image-based visual servo[A].IEEE Confront Robotics and Automation[C]. California, 1991, pp.2267-2272.
[48] S.Hutchinson, G.Hager, P.Corke. Atutorial introduction to visual servo control [J]. IEEE Trans on Robotics and Automation, 1996,12(5):651-670.
[49] W.Jang, Z.B.jen. Feature based visual servoing of an eye-in-hand robot with improved tracking performance [A]. IEEE Confront Robotics and Automation[C].California, 1991, pp.2254-2260.
[50] M.Jagersand.On-line estimation of visual motor models for robot control and visual simulation [D].USA: University of Rochester, 1998.
[51] R。Jain, R.Kasturi, and B.GSchunck. Machine Vision.McGraw-Hill,1995.
[52] H.Kitano, Y.Kuniyoshi, I.Noda, M.Asada, H.Matsubara, and E.Osawa.RoboCup:A challenge problem for AI.Magazine, 1997,18(l):73-85.
[53] M.C.Ngugen. Situation reined behavior-based stereovision to gain robustness adaptation in manipulator control[A]. Proc of SPIE[C]. Massachusetts, 1999,38(37):90-97.
[54] J.Pauli. Learning to recognize and grasp objects[J] .Machine Learning, 1998,31(1-3):239-258.
[55] N.P.Papaniko lopoulos, P.K.Khosla, T.Kanade. Visual tracking of a moving target by a camera mounted on a robot: A combination of vision and control [J].IEEE Trans on Robotics and Automation, 1993, 9(1): 14-35.
[56]H.Sutanto,R.Sharma,V.Varma.The role of exploratory movement in visual servoing without calibration[J].Robotics and Autonomous Systems,1998,23(3):153-169.
[57]M.Vargas,F.R.Rubio,A.R.Malpesa.Pose-estimation and control in a 3D visual servoing system[A].Proc of the 14th IFA[C].Beijing,1999,pp.317-323.
[58]P.Viola,M.Jones.Rapid object detection using a Boosted cascade of simple features[C].In:Proc IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2001,pp.511-518.
[59]D.B.Westmore,W.J.Wilson.Direct dynamic control of a robot using an end-point mounted camera and Kalman filter position estimation[A].IEEE Conf on Robotics and Automation[C].California,1991,3:2376-2384.
[60]L.E.Weiss,A.C.Sanderson,C.P.Neuman.Dynamic sensor-based control of robots with visual feedback[J].IEEE Robot Automation,1987,3(5):404-417.
[61]S.Wijesoma,D.Wolfe,R.Richards.Eye-to2hand coordination for vision-guided robot control applications[J].In Robotics Research,1993,12(1):65-78.
[62]W.J.Wilson,C.C.Hulls,G.S.Bell.Relative end-effect to control using Cartesian position-based visual servoing[J].IEEE Trans on Robotics and Automation,199612(5):684-696.
[63]崔屹.图象处理与分析:数学形态学方法及应用[M].科学出版社.2000.
[64]陈祖爵,陈潇君,何鸿.基于改进的混合高斯模型的运动目标检测.中国图象图像学报[J],2007,12(9):1581-1589.
[65]郑世友,费树岷,刘怀,龙飞.动态场景图象序列中运动目标检测新方法.中国图象图形学报[J],2007,12(9):1590-1597.
[66]付安新,基于DSP的嵌入式机器人视觉系统的设计与研究[硕士学位论文],浙江大学,2006.
[67]刘宏,李锦涛,刘群,钱跃良,李豪杰.融合颜色和梯度特征的运动阴影消除方法.计算机辅助设计与图形学学报[J],2007,19(10):1279-1285.
[68]Shahinfard.E,Sid-Ahmed.M,Ahmadi.M.An Improved Motion Adaptive Deinterlacing Method Using Variable Block-Size Motion Detection.Signal Processing and Information Technology,2007 IEEE International Symposium,2007,pp.122-126.
[69]梁迅,熊水东.DM642嵌入式网络接口开发设计.计算机工程[J],2007,33(16):277-279.
[70]Wenming Yang,Wang Lu,Naitong Zhang.Object Extraction Combining Image Partition with Motion Detection.Image Processing,IEEE International Conference,2007,3:Ⅲ-337-Ⅲ-340.
[71]Aksoy.E,Adar.N,Canbek.S,Seke.E,Gurel.U.Real-time Motion Region Detection and Contouring System.Signal Processing and Communications Applications,2007,SIU.IEEE 15th 11-13,2007,pp.1-4.
[72]潘秦华,车辆目标检测与交通流量检测系统的研究,西安电子科技大学[硕士学位论文],2005年.