集控式足球机器人视觉系统的研究
|
摘要
足球机器人是目前机器人研究领域的一个热点课题,它涉及了诸多领域的前沿研究,是一个极富挑战性的高技术密集型研究平台。视觉系统作为足球机器人四大子系统之一,是足球机器人的重要组成部分,其主要任务是通过视频设备采集场地图像,并对获取的图像进行适当处理,最终获得各目标体在场地中的位置和角度信息,从而为决策系统提供初始状态信息。衡量视觉系统的性能优劣主要体现在对目标识别的精度和速度。因此,本文的研究重点就在于如何提高系统的实时性和辨识精度。
本课题在硬件方面采用三星公司的SCC-331摄像头获取图像,并通过CA-CPE-3000型图像采集卡将模拟图像转换为数字图像,该视觉系统具有采集速率较高、图像画面优越等特点,不仅便于后期的图像处理,而且可以提高系统的实时性。
本文在分析了足球机器人视觉系统目前常用的几种颜色模型后,根据选择的硬件的特点,选用最为简单的RGB颜色模型进行图像处理,大大减小了系统的计算量。在分析了几种常用色标的基础上,提出了队标+队员标志+形状判别的色标设计方案,队标和队员标志用于获取位姿信息,利用形状判别进一步的确认所获取的小车车号。这种方法减少了颜色的使用种类,避免了某些颜色间的相互干扰,并根据色标的设计,给出了获取目标体位姿信息以及机器人车号的算法。由于广角成像的视觉系统获取的图像存在一定程度的几何畸变,文中在分析了典型的畸变校正模型的基础上,根据足球机器人比赛的要求,提出了适合足球机器人系统的几何畸变校正算法。为了快速、准确识别目标体,本文采用K-均值聚类的图像分割方法和重心法相结合获取目标的中心,以及基于图像获取和目标运动连续性的动态窗口局部搜索算法进行目标辨识。另外,通过编程调试很好地实现了上述所有算法,并且能够满足系统的实时性和精度要求。
论文最后介绍了视觉系统软件的各组成模块功能和程序流程,给出了系统运行时的人机交互界面及其具体组成部分介绍,并最终给出了调试结果。另外,文中还指出一些不足之处,为以后的改进提供了一些思路。
Soccer robot has become one of the hot subjects in the field of robot researching, it has referred to many kinds of advanced research from different fields, actually it is a research platform which is full of high technologies as challenges. The vision system is an important part in soccer robot system as one of four subsystems, its main task is to capture images through video equipments, and obtain the position and angle information of objects through proper image process, which can provide original information for decision-making system. The speed and precision of recognition are important factors to evaluate the performance of vision system, so the emphasis in this paper is how to improve the recognizing precision and real time of vision system.
The SCC-331 camera of SAMSUNG and the image grab card CA-CPE-3000 is adopted firstly to capture images as far as domestic researches. The vision system can obtain superior images with high speed, which is not only easy for later image process, but also can greatly improve the real time of the system.
According to the characteristics of new camera selected in this paper, RGB color model is used to process image after analyzing the several color models normally used in vision system, which can reduce the calculation in the system. A new design of color patch is introduced after analyzing the traditional color patch, which can decrease the total kinds of color used in the color patch and avoid the mutual disturbance between some kinds of colors. A set of algorithm is presented to obtain the position and angle information according to the new design of color patch. Because of the characteristics of wide-angle imaging system, geometrical distortion exists in actual images to some extent, a new kind of distortion correction model is built based on the classic model which is fit for the robot soccer competition. To recognize the objects quickly and accurately, image segmentation based on K-means Clustering and center of gravity method, as well as searching in a dynamic window based on the continuity of image capturing and object moving, are adopted to realize the recognition. All the algorithms above are realized well through programming and debugging, it is proved that the algorithms can meet the need of real time and precision greatly for the vision system.
In the last, the function of modules in the software and the program flow are presented, man-machine interface is introduce as well as its components and running result of vision system software is provided. In addition, some shortcomings are pointed out and some thoughts are given for the next development.
本课题在硬件方面采用三星公司的SCC-331摄像头获取图像,并通过CA-CPE-3000型图像采集卡将模拟图像转换为数字图像,该视觉系统具有采集速率较高、图像画面优越等特点,不仅便于后期的图像处理,而且可以提高系统的实时性。
本文在分析了足球机器人视觉系统目前常用的几种颜色模型后,根据选择的硬件的特点,选用最为简单的RGB颜色模型进行图像处理,大大减小了系统的计算量。在分析了几种常用色标的基础上,提出了队标+队员标志+形状判别的色标设计方案,队标和队员标志用于获取位姿信息,利用形状判别进一步的确认所获取的小车车号。这种方法减少了颜色的使用种类,避免了某些颜色间的相互干扰,并根据色标的设计,给出了获取目标体位姿信息以及机器人车号的算法。由于广角成像的视觉系统获取的图像存在一定程度的几何畸变,文中在分析了典型的畸变校正模型的基础上,根据足球机器人比赛的要求,提出了适合足球机器人系统的几何畸变校正算法。为了快速、准确识别目标体,本文采用K-均值聚类的图像分割方法和重心法相结合获取目标的中心,以及基于图像获取和目标运动连续性的动态窗口局部搜索算法进行目标辨识。另外,通过编程调试很好地实现了上述所有算法,并且能够满足系统的实时性和精度要求。
论文最后介绍了视觉系统软件的各组成模块功能和程序流程,给出了系统运行时的人机交互界面及其具体组成部分介绍,并最终给出了调试结果。另外,文中还指出一些不足之处,为以后的改进提供了一些思路。
Soccer robot has become one of the hot subjects in the field of robot researching, it has referred to many kinds of advanced research from different fields, actually it is a research platform which is full of high technologies as challenges. The vision system is an important part in soccer robot system as one of four subsystems, its main task is to capture images through video equipments, and obtain the position and angle information of objects through proper image process, which can provide original information for decision-making system. The speed and precision of recognition are important factors to evaluate the performance of vision system, so the emphasis in this paper is how to improve the recognizing precision and real time of vision system.
The SCC-331 camera of SAMSUNG and the image grab card CA-CPE-3000 is adopted firstly to capture images as far as domestic researches. The vision system can obtain superior images with high speed, which is not only easy for later image process, but also can greatly improve the real time of the system.
According to the characteristics of new camera selected in this paper, RGB color model is used to process image after analyzing the several color models normally used in vision system, which can reduce the calculation in the system. A new design of color patch is introduced after analyzing the traditional color patch, which can decrease the total kinds of color used in the color patch and avoid the mutual disturbance between some kinds of colors. A set of algorithm is presented to obtain the position and angle information according to the new design of color patch. Because of the characteristics of wide-angle imaging system, geometrical distortion exists in actual images to some extent, a new kind of distortion correction model is built based on the classic model which is fit for the robot soccer competition. To recognize the objects quickly and accurately, image segmentation based on K-means Clustering and center of gravity method, as well as searching in a dynamic window based on the continuity of image capturing and object moving, are adopted to realize the recognition. All the algorithms above are realized well through programming and debugging, it is proved that the algorithms can meet the need of real time and precision greatly for the vision system.
In the last, the function of modules in the software and the program flow are presented, man-machine interface is introduce as well as its components and running result of vision system software is provided. In addition, some shortcomings are pointed out and some thoughts are given for the next development.
引文
[1]洪炳熔,韩学东,孟伟.机器人足球比赛研究.机器人.2003,25(4):373-374
[2]宁春林,田国会,尹建芹,路飞,李晓磊.机器人足球比赛及其发展.山东大学学报(工学版),2002,32(5):480-482
[3]徐心和,高大志.足球机器人与国际机器人足联的发展[C].见:机器人足球研讨班论文集.沈阳:东北大学,1998,7-101
[4]高大志,张春晖,徐心和.机器人足球--智能机器人的新领域.机器人.1998,20(4):309-310
[5]陈小平.国际机器人足球(Robocup)最新发展[J].机器人技术与应用.2001,(1):25-28
[6]李实,徐旭明,叶榛等.国际机器人足球比赛及其相关技术[J].机器人.2000,22(5):420-426
[7]http://www.fira.net/
[8]单泽永,徐心和.机器人足球发展势不可挡.机器人技术与应用.1998,(4):4-5
[9]王文学,徐心和.机器人足球:高科技的对抗.百科知识,2000,(10):16-17
[10]彭志刚,杨艳丽.机器人足球与足球机器人:机器人技术与应用,1999,(5):29-31
[11]http://www.robocup.org/
[12]王文学,赵姝颖.多智能足球机器人系统的关键技术.东北大学学报:自然科学版.2001,22(2):192-195
[13]苗夺谦,李顺勇.基于多智能体的对抗平台--微型足球机器人系统.微计算机应用.2002,23(3):154-157
[14]J.Liu,J.Wu.Multi-agent Robotic Systems,CRC Press,Boca Raton,Florida,2001.
[15]Subramanyam S,Vadakkepat p,Kim K C,Kim J H.Multi-agent Centralized Control in Soccer Robot.Proc MIROSOT'97.1997:49-58
[16]D.Matko,G.Klancar,M.Lepetic.A tool for the analysis of robot soccer game,International Journal of Control Automation and Systems,2003,Vol.1,No.2:222-228.
[17]T.Chinapirom,T.Kaulmann,U.Witkowski,and U.Ruckert.VISUAL OBJECT RECOGNITION BY 2D-COLOR CAMERA AND ON-BOARD INFORMATION PROCESSING FOR MINIROBOTS.2004 FIRA Robot World Congress.
[18]Gregor Klancar,Marko Lepetic,Omar Orqueda,Drage Matko,Rihard Karba,VISION SYSTEM DESIGN FOR MOBILE ROBOTS TRACKING,2004 FIRA Robot World Congress.
[19]赵姝颖,佟国峰.机器人视觉子系统,机器人技术与应用,2000(2):26-28
[20]王庆有.CCD应用技术,天津:天津大学出版社,2000
[21]吴文田,冯文书.CCD尺寸测量光学系统设计原理,应用光学,1994,(15):20-24
[22]蔡文贵.CCD技术及应用.北京:电子工业出版社,1992.
[23]http://www.canalalarm.com
[24]田宏强,蒋建国,李小红.基于PCI总线的图像采集卡的开发与应用.微计算机信息,2000,16(3):28-30
[25]http://www.hygdz.com
[26]张毓晋.图像工程(上册)--图像处理和分析[M].北京:清华大学出版社,1999.
[27]贾永红.计算机图像处理与分析[M].武汉:武汉大学出版社,2001.
[28]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001.
[29]杨枝灵,王开.Visual C++数字图像获取处理及实践应用[M].北京:人民邮电出版社,2003.
[30]刘禾.数字图像处理及应用[M].北京:中国电力出版社.2006.
[31]韩博,徐枫.数字图像处理基础[M].北京:清华大学出版社.2006.
[32]艾海舟,武勃等译。图像处理分析与机器视觉[M].北京:人民邮电出版社.2003.
[33]K.P.Castleman.Digital Image Processing[M].北京,电子工业出版社,2002.
[34]Kenneth R.Castleman.Digital image Processing[M].New Jersey:Prentice Hall.1996.
[35]聂飞,冯宗哲,郭宝龙等.嵌入式视频采集系统的实现方法研究.电视技术,2003,(8):46-49
[36]鄂丰凯.自主式足球机器人的控制系统研究.东北大学硕士学位论文,2004
[37]张广军.机器视觉[M].北京:科学精神出版社,2005.
[38]田梦倩.机器人视觉系统标定问题研究综述[J].工业仪表与自动化装置,2006,(2):14-17.
[39]张全法,何金田.提高广角成像系统几何畸变数字校正精度的方法.光学技术,2001, 27(3):242-246
[40]王伟,钟堰利,吴建坤.广角镜头图像畸变校正系统的研究.光学技术,2004,30(4):489-491
[41]Mclean G.Image warping for calibration and removal of lens distortion.IEEE Pacific Rim Conference on Communications,Computers and Signal Processing.1993,Vol.1:170-173
[42]姜大志,孙俊兰,郁倩等.标准图像法求解相机镜头非线性畸变的研究.东南大学学报:自然科学版,2001,31(4):111-116
[43]张华达.大视场短焦距CCD成像系统畸变校正研究.红外,2004,1:1-6
[44]梁亮,张定华,赵歆波,毛海鹏,王凯.一种基于网络图像的几何畸变修正方法.计算机工程与应用.2004,2:4-6
[45]魏天滨,孟庆春,庄晓东.一种足球机器人视觉系统非线性畸变的数宁校正方法.机器人技术与应用.2004,2:37-40
[46]李春雨,邱道尹等.计算机图像学理论与实践.北京航空大学出版社.167-171
[47]Goh Pit Khiam,Ruan ZhiLong,Leong Kum Cheong,REAL-TIME COLOR VISION TRACKING SYSTEM,2004 FIRA Robot World Congress
[48]徐大宏,吴敏等.一种新的实时彩色目标分割方法.计算机工程与应用.2003,22:75-77
[49]何超,熊蓉,戴连奎.足球机器人视觉图像的快速识别.中国图像图形学报,2003,8(3):271-274
[50]赵姝颖,佟国峰.数字彩色图像样本HIS全息分析的研究与实现.控制与决策,1999(14):593-596
[51]P.Kopacek,M.W.Han,B.Putz,E.Schierer and M.Wurzl.An industrial image processing system for fast moving objects,2005 International Conference on Computational Intelligence,Robotics and Autonomous Systems
[52]佟国峰,赵姝颖,徐心和.提高足球机器人彩色视觉系统实时性的若干图像识别关键技术的研究.东北大学控制与仿真研究中心
[53]胡英,赵姝颖,徐心和.色标设计与辨识算法.中国图像图形学报.2002,7(12):1291-1295
[54]关慧贞,魏永,刘赞等.足球机器人视觉系统的快速识别与跟踪技术.控制与检测,2005,2:55-57
[55]Donghun Lee,DoEun Kim,KyungHun Hwang,ChaeWook Chung and TaeYong Kuc,A Novel Color patch System for the Large League MIROSOT,2005 International Conference on Computational Intelligence,Robotics and Autonomous Systems
[56]周军,李奎,张伟.基于角度补偿的色标辨识算法的设计,哈尔滨工业大学学报,2004,7(12):969-971
[57]李春雨,邱道尹等.计算机图像学理论与实践.北京航空航天大学出版社.186-188
[58]章毓晋.图像分割,北京:科学出版社,2001
[59]黄麟.粗糙理论及其应用[M].重庆大学出版社,1998
[60]郑南宁,计算机视觉与模式识别[M].国防工业出版社,1998
[61]刘岩,李言俊,张科.基于粗糙集的K-均值聚类图象分割方法[J].计算机工程与应用,2003,29(1):17-19.
[62]周明明,赵臣,阴炳皓.基于序列图像相关性的足球机器人目标搜索.微型机与应用,2003,9:55-57
[63]张彦铎,鲁统伟.基于航迹关联的足球机器人视觉系统的改进.哈尔滨工业大学学报.2004,36(7):908-910
[64]郑阿奇,丁有和,郑进等.Visual C++使用教程(第2版),电子工业出版社
[65]王新成.多媒体使用技术(图像分册).电子科技大学出版社
[66]周长发.精通Visual C++图像编程.电子工业出版社
[67]黄维通.Visual C++面向对象与可视化程序设计.清华大学
[2]宁春林,田国会,尹建芹,路飞,李晓磊.机器人足球比赛及其发展.山东大学学报(工学版),2002,32(5):480-482
[3]徐心和,高大志.足球机器人与国际机器人足联的发展[C].见:机器人足球研讨班论文集.沈阳:东北大学,1998,7-101
[4]高大志,张春晖,徐心和.机器人足球--智能机器人的新领域.机器人.1998,20(4):309-310
[5]陈小平.国际机器人足球(Robocup)最新发展[J].机器人技术与应用.2001,(1):25-28
[6]李实,徐旭明,叶榛等.国际机器人足球比赛及其相关技术[J].机器人.2000,22(5):420-426
[7]http://www.fira.net/
[8]单泽永,徐心和.机器人足球发展势不可挡.机器人技术与应用.1998,(4):4-5
[9]王文学,徐心和.机器人足球:高科技的对抗.百科知识,2000,(10):16-17
[10]彭志刚,杨艳丽.机器人足球与足球机器人:机器人技术与应用,1999,(5):29-31
[11]http://www.robocup.org/
[12]王文学,赵姝颖.多智能足球机器人系统的关键技术.东北大学学报:自然科学版.2001,22(2):192-195
[13]苗夺谦,李顺勇.基于多智能体的对抗平台--微型足球机器人系统.微计算机应用.2002,23(3):154-157
[14]J.Liu,J.Wu.Multi-agent Robotic Systems,CRC Press,Boca Raton,Florida,2001.
[15]Subramanyam S,Vadakkepat p,Kim K C,Kim J H.Multi-agent Centralized Control in Soccer Robot.Proc MIROSOT'97.1997:49-58
[16]D.Matko,G.Klancar,M.Lepetic.A tool for the analysis of robot soccer game,International Journal of Control Automation and Systems,2003,Vol.1,No.2:222-228.
[17]T.Chinapirom,T.Kaulmann,U.Witkowski,and U.Ruckert.VISUAL OBJECT RECOGNITION BY 2D-COLOR CAMERA AND ON-BOARD INFORMATION PROCESSING FOR MINIROBOTS.2004 FIRA Robot World Congress.
[18]Gregor Klancar,Marko Lepetic,Omar Orqueda,Drage Matko,Rihard Karba,VISION SYSTEM DESIGN FOR MOBILE ROBOTS TRACKING,2004 FIRA Robot World Congress.
[19]赵姝颖,佟国峰.机器人视觉子系统,机器人技术与应用,2000(2):26-28
[20]王庆有.CCD应用技术,天津:天津大学出版社,2000
[21]吴文田,冯文书.CCD尺寸测量光学系统设计原理,应用光学,1994,(15):20-24
[22]蔡文贵.CCD技术及应用.北京:电子工业出版社,1992.
[23]http://www.canalalarm.com
[24]田宏强,蒋建国,李小红.基于PCI总线的图像采集卡的开发与应用.微计算机信息,2000,16(3):28-30
[25]http://www.hygdz.com
[26]张毓晋.图像工程(上册)--图像处理和分析[M].北京:清华大学出版社,1999.
[27]贾永红.计算机图像处理与分析[M].武汉:武汉大学出版社,2001.
[28]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001.
[29]杨枝灵,王开.Visual C++数字图像获取处理及实践应用[M].北京:人民邮电出版社,2003.
[30]刘禾.数字图像处理及应用[M].北京:中国电力出版社.2006.
[31]韩博,徐枫.数字图像处理基础[M].北京:清华大学出版社.2006.
[32]艾海舟,武勃等译。图像处理分析与机器视觉[M].北京:人民邮电出版社.2003.
[33]K.P.Castleman.Digital Image Processing[M].北京,电子工业出版社,2002.
[34]Kenneth R.Castleman.Digital image Processing[M].New Jersey:Prentice Hall.1996.
[35]聂飞,冯宗哲,郭宝龙等.嵌入式视频采集系统的实现方法研究.电视技术,2003,(8):46-49
[36]鄂丰凯.自主式足球机器人的控制系统研究.东北大学硕士学位论文,2004
[37]张广军.机器视觉[M].北京:科学精神出版社,2005.
[38]田梦倩.机器人视觉系统标定问题研究综述[J].工业仪表与自动化装置,2006,(2):14-17.
[39]张全法,何金田.提高广角成像系统几何畸变数字校正精度的方法.光学技术,2001, 27(3):242-246
[40]王伟,钟堰利,吴建坤.广角镜头图像畸变校正系统的研究.光学技术,2004,30(4):489-491
[41]Mclean G.Image warping for calibration and removal of lens distortion.IEEE Pacific Rim Conference on Communications,Computers and Signal Processing.1993,Vol.1:170-173
[42]姜大志,孙俊兰,郁倩等.标准图像法求解相机镜头非线性畸变的研究.东南大学学报:自然科学版,2001,31(4):111-116
[43]张华达.大视场短焦距CCD成像系统畸变校正研究.红外,2004,1:1-6
[44]梁亮,张定华,赵歆波,毛海鹏,王凯.一种基于网络图像的几何畸变修正方法.计算机工程与应用.2004,2:4-6
[45]魏天滨,孟庆春,庄晓东.一种足球机器人视觉系统非线性畸变的数宁校正方法.机器人技术与应用.2004,2:37-40
[46]李春雨,邱道尹等.计算机图像学理论与实践.北京航空大学出版社.167-171
[47]Goh Pit Khiam,Ruan ZhiLong,Leong Kum Cheong,REAL-TIME COLOR VISION TRACKING SYSTEM,2004 FIRA Robot World Congress
[48]徐大宏,吴敏等.一种新的实时彩色目标分割方法.计算机工程与应用.2003,22:75-77
[49]何超,熊蓉,戴连奎.足球机器人视觉图像的快速识别.中国图像图形学报,2003,8(3):271-274
[50]赵姝颖,佟国峰.数字彩色图像样本HIS全息分析的研究与实现.控制与决策,1999(14):593-596
[51]P.Kopacek,M.W.Han,B.Putz,E.Schierer and M.Wurzl.An industrial image processing system for fast moving objects,2005 International Conference on Computational Intelligence,Robotics and Autonomous Systems
[52]佟国峰,赵姝颖,徐心和.提高足球机器人彩色视觉系统实时性的若干图像识别关键技术的研究.东北大学控制与仿真研究中心
[53]胡英,赵姝颖,徐心和.色标设计与辨识算法.中国图像图形学报.2002,7(12):1291-1295
[54]关慧贞,魏永,刘赞等.足球机器人视觉系统的快速识别与跟踪技术.控制与检测,2005,2:55-57
[55]Donghun Lee,DoEun Kim,KyungHun Hwang,ChaeWook Chung and TaeYong Kuc,A Novel Color patch System for the Large League MIROSOT,2005 International Conference on Computational Intelligence,Robotics and Autonomous Systems
[56]周军,李奎,张伟.基于角度补偿的色标辨识算法的设计,哈尔滨工业大学学报,2004,7(12):969-971
[57]李春雨,邱道尹等.计算机图像学理论与实践.北京航空航天大学出版社.186-188
[58]章毓晋.图像分割,北京:科学出版社,2001
[59]黄麟.粗糙理论及其应用[M].重庆大学出版社,1998
[60]郑南宁,计算机视觉与模式识别[M].国防工业出版社,1998
[61]刘岩,李言俊,张科.基于粗糙集的K-均值聚类图象分割方法[J].计算机工程与应用,2003,29(1):17-19.
[62]周明明,赵臣,阴炳皓.基于序列图像相关性的足球机器人目标搜索.微型机与应用,2003,9:55-57
[63]张彦铎,鲁统伟.基于航迹关联的足球机器人视觉系统的改进.哈尔滨工业大学学报.2004,36(7):908-910
[64]郑阿奇,丁有和,郑进等.Visual C++使用教程(第2版),电子工业出版社
[65]王新成.多媒体使用技术(图像分册).电子科技大学出版社
[66]周长发.精通Visual C++图像编程.电子工业出版社
[67]黄维通.Visual C++面向对象与可视化程序设计.清华大学
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |