面向精密制造与检测的机器视觉及智能算法研究
|
摘要
机器视觉以其检测精度高、快速、高效与非接触等的特点，在精密制造与检测领域发挥着重要作用，是提升装备制造业水平的重要途径。基于机器视觉的实时检测系统为智能制造提供了技术上的支持，以及物质上的准备。
根据我国装备制造业的内在需求，以及目前具备的研究基础、条件和优势，阐述了机器视觉与计算智能的研究背景与意义。论文从机器视觉的标定、微钻头的刃面检测、机器人手眼系统标定几个方面进行研究，为精密制造与检测水平的提高提供了理论与技术上的支撑，本文主要研究内容如下：
1．对机器视觉系统的物理模型进行了分析与研究，采用嵌入旋转矩阵的神经网络以及遗传算法对非线性模型的摄像机进行标定；当神经网络达到全局最优平衡位置时，使网络的前向计算与摄像机的物理模型相对应，即可根据神经网络的权值直接得到摄像机的内、外参数。
2．采用基于侧向抑制的正交学习的神经网络算法，以抽取自相关矩阵的最小特征值所对应的特征向量的方法，来获得机器视觉系统的空间3D信息与图像2D信息之间的变换关系，完成双目视觉系统的标定，以及与之相关的三维重建。
3．构建一个用于微钻头检测的神经网络，使其达到全局最优平衡位置的时候与需要拟合的微钻头棱边投影的椭圆方程或者主切削刃的直线方程等相一致。对神经网络的每一次训练所得到的权值进行归一化处理，得到单位权值矢量，该操作相当于遗传算法中变异操作。并引入改进的粒子群算法，以获得全局最优解。
4．通过引入进化速度因子与聚集度因子两个指标，对粒子群优化算法的粒子个体的运动轨迹从纵向以及横向进行分析，根据粒子群优化算法中的惯性因子的特性，以及专家经验与推理，得到系统的惯性权重因子变化量的动态调整的模糊控制规则表；并采用模糊逻辑对其进行自适应地调整，使得优化算法更准确与更快速地找到全局最优解。在粒子群算法的每一次迭代完成之后，同样对粒子个体的位置进行归一化处理，获得权值的单位矢量。最后得到微钻头特征曲线的拟合方程。
5．在对机器人的手眼系统进行标定时，采用混合神经网络与交叉变异粒子群优化算法，使得所设计的神经网络包括手眼系统旋转部分的信息，当求解系统达到全局最优平衡位置时，由神经网络的权值获得机械臂末端执行器相对于安装于机器人机械臂的摄像机之间的位姿关系。精度分析显示，所提出的方法能够确保手眼关系中的旋转矩阵各矢量之间的正交关系。
在上述关键技术研究的基础上，完成了基于计算智能的机器视觉系统的标定，研发了PCB板微钻头的自动化检测系统，实现对机器人的手眼系统的定标，得到摄像机与机器人末端执行器之间的变换关系，最后通过标定、测试等实验，验证上述研究结果的正确性和可行性。这些研究有利于提高精密制造与检测技术的水平，也为推进我国机器视觉研究的发展及其应用提供一个新的维度。
Machine vision plays an important role in the field of precision manufacturing andtesting due to its characteristics of high precision, rapidity, efficiency, non-contact and so onwhich is an important approach to enhance the level of equipment manufacturing industry.Real-time measurement system based on machine vision provides the technical support andmaterial preparation for intelligent manufacturing.
The research background and significance of machine vision and computationalintelligence are expounded according to requirements of improving the equipmentmanufacturing industry in our country, and the current research foundation, conditions andadvantages. Research is mainly done on machine vision calibration, the flank inspection ofmicro drill, and eye-hand calibration for robot system, which provides theoretical andtechnical support for precision manufacturing and testing. The main research of the paperincludes as follows:
1. The analysis and research on the physical model of the machine vision system havebeen carried out, and a neural network embedded rotational matrix and genetic algorithm isadopted to achieve the calibration of camera with non-linear model, where the forwardcalculation of the network is corresponding with the camera’s physical model so that theintrinsic and extrinsic parameters of camera are gotten from the stable weights of the networkwhen the network comes to the global optimal equilibrium position.
2. By extracting the eigen-vector of the self-relative matrix corresponding to the smallesteigenvalue, the orthogonal-learning neural network with lateral inhibition is adopted to obtainthe transform relation of3D space information and2D image information for the machinevision system, which results in the binocular vision system calibration, as well as the3Dreconstruction.
3. The neural network for testing micro drill is designed which is consistent with thefitting ellipse equation of margin projection, or linear equations of the main cutting edgeswhen the network comes to the global optimization position. The network‘s weights arenormalized to unit weight vector in every training, which is equal to the mutation operation ofgenetic algorithm. And an improved particle swarm algorithm is introduced in order to obtainthe global optimal solution.
4. The particles motion trajectories of the particle swarm optimization algorithm areanalyzed from the longitudinal direction and transverse direction by introducing the evolution speed factor and aggregation degree factor. According to the features of the inertia factor ofparticle swarm optimization algorithm, and the fuzzy control rule table obtained from expertexperiences and inference is used to adjust the system s inertia weighting factor dynamically,which makes optimization algorithm to find the global optimal solution more accurately andquickly. In every iteration of particle swarm optimization algorithm, the position of theindividual particle is normalized to unit weight vector. Finally micro-drill feature curves fitting equations are gotten.
5. When the robot s hand-eye system is calibrated, a hybrid neural network and particleswarm optimization algorithm with crossover and mutation operation is adopted, where theneural network including the information of hand-eye system rotating component is designed.When the solving system comes to the global optimal equilibrium position, hand-eye relationsbetween the end-effector and the camera installed in robot are obtained from the networkweights. Precision analysis shows that the proposed approach can ensure the orthogonality ofthe vectors in the rotational matrix of the hand-eye relations.
On the basis of the above key technologies, machine vision system is calibrated withcomputational intelligence, the PCB micro-drill’s automated detection system is developed,and the relations between camera and robot’s end-effector are gotten by calibrating the robothand-eye system. Finally calibration and testing experiment are carried out to demonstrate theabove research being correct and practicable.
The research will help to improve technology level of precision manufacturing andtesting, and provide another dimension for promoting the development and applications ofmachine vision research in our country.
根据我国装备制造业的内在需求，以及目前具备的研究基础、条件和优势，阐述了机器视觉与计算智能的研究背景与意义。论文从机器视觉的标定、微钻头的刃面检测、机器人手眼系统标定几个方面进行研究，为精密制造与检测水平的提高提供了理论与技术上的支撑，本文主要研究内容如下：
1．对机器视觉系统的物理模型进行了分析与研究，采用嵌入旋转矩阵的神经网络以及遗传算法对非线性模型的摄像机进行标定；当神经网络达到全局最优平衡位置时，使网络的前向计算与摄像机的物理模型相对应，即可根据神经网络的权值直接得到摄像机的内、外参数。
2．采用基于侧向抑制的正交学习的神经网络算法，以抽取自相关矩阵的最小特征值所对应的特征向量的方法，来获得机器视觉系统的空间3D信息与图像2D信息之间的变换关系，完成双目视觉系统的标定，以及与之相关的三维重建。
3．构建一个用于微钻头检测的神经网络，使其达到全局最优平衡位置的时候与需要拟合的微钻头棱边投影的椭圆方程或者主切削刃的直线方程等相一致。对神经网络的每一次训练所得到的权值进行归一化处理，得到单位权值矢量，该操作相当于遗传算法中变异操作。并引入改进的粒子群算法，以获得全局最优解。
4．通过引入进化速度因子与聚集度因子两个指标，对粒子群优化算法的粒子个体的运动轨迹从纵向以及横向进行分析，根据粒子群优化算法中的惯性因子的特性，以及专家经验与推理，得到系统的惯性权重因子变化量的动态调整的模糊控制规则表；并采用模糊逻辑对其进行自适应地调整，使得优化算法更准确与更快速地找到全局最优解。在粒子群算法的每一次迭代完成之后，同样对粒子个体的位置进行归一化处理，获得权值的单位矢量。最后得到微钻头特征曲线的拟合方程。
5．在对机器人的手眼系统进行标定时，采用混合神经网络与交叉变异粒子群优化算法，使得所设计的神经网络包括手眼系统旋转部分的信息，当求解系统达到全局最优平衡位置时，由神经网络的权值获得机械臂末端执行器相对于安装于机器人机械臂的摄像机之间的位姿关系。精度分析显示，所提出的方法能够确保手眼关系中的旋转矩阵各矢量之间的正交关系。
在上述关键技术研究的基础上，完成了基于计算智能的机器视觉系统的标定，研发了PCB板微钻头的自动化检测系统，实现对机器人的手眼系统的定标，得到摄像机与机器人末端执行器之间的变换关系，最后通过标定、测试等实验，验证上述研究结果的正确性和可行性。这些研究有利于提高精密制造与检测技术的水平，也为推进我国机器视觉研究的发展及其应用提供一个新的维度。
Machine vision plays an important role in the field of precision manufacturing andtesting due to its characteristics of high precision, rapidity, efficiency, non-contact and so onwhich is an important approach to enhance the level of equipment manufacturing industry.Real-time measurement system based on machine vision provides the technical support andmaterial preparation for intelligent manufacturing.
The research background and significance of machine vision and computationalintelligence are expounded according to requirements of improving the equipmentmanufacturing industry in our country, and the current research foundation, conditions andadvantages. Research is mainly done on machine vision calibration, the flank inspection ofmicro drill, and eye-hand calibration for robot system, which provides theoretical andtechnical support for precision manufacturing and testing. The main research of the paperincludes as follows:
1. The analysis and research on the physical model of the machine vision system havebeen carried out, and a neural network embedded rotational matrix and genetic algorithm isadopted to achieve the calibration of camera with non-linear model, where the forwardcalculation of the network is corresponding with the camera’s physical model so that theintrinsic and extrinsic parameters of camera are gotten from the stable weights of the networkwhen the network comes to the global optimal equilibrium position.
2. By extracting the eigen-vector of the self-relative matrix corresponding to the smallesteigenvalue, the orthogonal-learning neural network with lateral inhibition is adopted to obtainthe transform relation of3D space information and2D image information for the machinevision system, which results in the binocular vision system calibration, as well as the3Dreconstruction.
3. The neural network for testing micro drill is designed which is consistent with thefitting ellipse equation of margin projection, or linear equations of the main cutting edgeswhen the network comes to the global optimization position. The network‘s weights arenormalized to unit weight vector in every training, which is equal to the mutation operation ofgenetic algorithm. And an improved particle swarm algorithm is introduced in order to obtainthe global optimal solution.
4. The particles motion trajectories of the particle swarm optimization algorithm areanalyzed from the longitudinal direction and transverse direction by introducing the evolution speed factor and aggregation degree factor. According to the features of the inertia factor ofparticle swarm optimization algorithm, and the fuzzy control rule table obtained from expertexperiences and inference is used to adjust the system s inertia weighting factor dynamically,which makes optimization algorithm to find the global optimal solution more accurately andquickly. In every iteration of particle swarm optimization algorithm, the position of theindividual particle is normalized to unit weight vector. Finally micro-drill feature curves fitting equations are gotten.
5. When the robot s hand-eye system is calibrated, a hybrid neural network and particleswarm optimization algorithm with crossover and mutation operation is adopted, where theneural network including the information of hand-eye system rotating component is designed.When the solving system comes to the global optimal equilibrium position, hand-eye relationsbetween the end-effector and the camera installed in robot are obtained from the networkweights. Precision analysis shows that the proposed approach can ensure the orthogonality ofthe vectors in the rotational matrix of the hand-eye relations.
On the basis of the above key technologies, machine vision system is calibrated withcomputational intelligence, the PCB micro-drill’s automated detection system is developed,and the relations between camera and robot’s end-effector are gotten by calibrating the robothand-eye system. Finally calibration and testing experiment are carried out to demonstrate theabove research being correct and practicable.
The research will help to improve technology level of precision manufacturing andtesting, and provide another dimension for promoting the development and applications ofmachine vision research in our country.
引文
[1]吴福培,邝泳聪,张宪民,等.基于模式匹配及其参数自适应的PCB焊点检测[J].光学精密工程,2009,17(10):2586-2593
[2]谢宏威,张宪民,邝泳聪.基于图像特征统计分析的PCB焊点检测方法[J].仪器仪表学报,2011,32(2):401-407.
[3] Chen J-Y, Lee B-Y, Lee K-C, et al. Development and Implementation of a Simplified ToolMeasuring System[J]. Measurement Science Review,2010,10(4):142-146.
[4] Tien F C, Yeh C H, Hsieh K H. Automated visual inspection for micro-drills in printedcircuit board production[J]. International Journal of Production Research,2004,2(12):2477-2495.
[5]中国图像网.微操作机器人系统的研究开发[EB/OL].[2013-4-11]. http://www.china-image.cn/lunwen/3200602231459351526356474.html.
[6]东莞科视自动化科技有限公司网.机器视觉技术在精密制造行业中的地位越来越重要[EB/OL].[2013.1.24].http://www.cstmv.com/news/industry/201301241473.html.
[7] Szeliski R. Computer Vision: Algorithms and Applications[M]. Springer,2010.8,237-292.
[8]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998:1-80,277-373.
[9]马颂德，张正友.计算机视觉—计算理论与算法基础[M].北京：科学出版社，1998：1-116.
[10]吴立德.计算机视觉[M].上海:复旦大学出版社,1993.119-208.
[11] Faugeras O D, Toscani G. The calibration problem for stereo[A]. IEEE Computer SocietyConference on Computer Vision and Pattern Recognition[C], Minmi Beach, Florida,June22-26,1986:15-20.
[12] Tsai R Y. A versatile camera calibration technique for high accuracy3D machine visionmetrology using off-the-shelf cameras and lens[J]. IEEE Transactions on Robotics andAutomation,1987,3(4):323-344.
[13]葛动元,姚锡凡,李凯南.双目立体视觉系统的标定[J].机械设计与制造,2010年第6期.188-189.
[14]葛动元,姚锡凡.向文江.构造性方法在摄像机标定中的应用研究[J].机床与液压,2010,(1):11-13.
[15]侯俊捷,魏新国,孙军华.基于同心圆合成图像匹配的双目视觉标定[J].光学学报,2012,32(3):0315003.
[16] Zhou F Q, Wang Y X, Cui Y, et al. Camera calibration approach usingcircle-square-combined target[J]. Chinese Optics Letters,2012,10(2):021003.
[17] Kim J S, Kim H W, Kweon I S. A camera calibration method using concentric circles forvision applications[A]. The5thAsia Conference on Computer Vision[C],2002:515-520.
[18] Zhang Z. A flexible new technique for camera calibration[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[19] Basu A. Active calibration: alternative strategy and analysis[A]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition[C],1993:495-500.
[20] Du F, Brady M. Self-calibration of the intrinsic parameters of camera for active visionsystem[A]. Proceedings of IEEE Conference on Computer Vision and PatternRecognition [C],1993:477-482.
[21] Ma S D. A Self-calibration technique for active vision system[J]. IEEE Trans. Roboticsand Automation.1996,12(1):114-120.
[22]吴福朝,李华,胡占义.基于主动视觉系统的摄像机自标定方法研究[J].自动化学报,2001,27(6):752-762.
[23]胡占义,雷成,吴福朝.关于共面P4P问题的一点讨论[J].自动化学报,2001,27(6):770-776.
[24] Hartley R. Self-calibration of stationary cameras[J]. International Journal of ComputerVision,1997,229(1):2-5.
[25] Benalla M, Meunier J. Camera calibration with simple geometry[J]. Proceedings of2003International Conference on Image and Signal,2003,10(3):292-297
[26] Carvalho P C P, Szenberg F, Gattass M. Image-based modeling using a two-step camerascalibration method[A]. Proceedings of International Symposium on Computer Graphics,Image Processing and Vision[C],1998:388-395.
[27] Wu Y H, Zhu H J, Hu Z Y, Wu F C. Camera calibration from the quasi-affine invarianceof two parallel circles[A]. The8thEuropean Conference on Computer Vision[C],2004:190-202.
[28] Wu Y H, Hu Z Y. The invariant representations of a quadric cone and a twisted cubic [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(10):1329-1332.
[29] Yang A Y, Hong W, Ma Y. Structure and pose from single images of symmetric objectswith applications to robot navigation[A]. Proceedings of IEEE International Conferenceon Robotics and Automation [C], Taipei2003:1013-1020.
[30]霍炬,杨卫,杨明.基于消隐点几何特性的摄像机自标定方法[J].光学学报,2010,30(2):465-472.
[31]陈爱华,高诚辉,何炳蔚.基于正交消失点对的摄像机标定方法[J].仪器仪表学报,2012,33(1):161-166.
[32]许海霞,王耀南,袁小芳,等.基于矢量差分的未标定摄像机P5P问题的求解[J].自动化学报,2009,35(8):1140-1144.
[33]姚锡凡,李旻.人工智能技术与应用[M].北京:中国电力出版社,2008,126~155.
[34]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,101-161.
[35]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2007,55-76.
[36] Cho S.-B. Neural Network Classifiers for Recognizing Totally UnconstrainedHandwritten Neumeral[J]. IEEE Transaction on Neural Network.1997,8:43-53.
[37]吕朝辉,张兆杨,安平.基于神经网络的立体视觉摄像机标定[J].机械工程学报,2003,39(9):93-96.
[38]崔彦平,林玉池,张晓玲.基于神经网络的双目视觉摄像机标定方法的研究[J].光电子.激光.2005,16(9):1097-1110.
[39] Zong X P, Xu Y, Hao L, e al. Camera Calibration Based on the RBF Neural Networkwith Tunable Nodes forVisual Servoing in Robotics[A]. Proceedings of The2006IEEE/RSJ International Conference on Intelligent Robots and System[C],2006:5708-5712.
[40]蔡盛,李清安,乔彦峰.基于BP神经网络的姿态测量系统摄像机标定[J].光电子.激光,2007,18(7):832-834.
[41]葛动元,姚锡凡,黄英杰,张庆.基于模糊神经网络的双目视觉系统的研究与准确度[J].计量学报,2009,30(4):307-311.
[42]王社阳,强文义,陈兴林,张炳通.基于遗传算法的非线性摄像机标定[J].宇航计测技术,2004,24(4):33-38.
[43]郭秋艳,刘鹏飞,安平,张兆杨.基于遗传算法的摄像机自标定方法[J].中国图象图形学报,2006,11(11):1712-1715.
[44] Bouchouicha M, Khelifa M B, Puech W. A non-linear camera calibration with geneticalgorithm[A]. Proceedings of Seventh International Symposium on Signal Processingand Its Applications [C],2003:189-192.
[45] Ge D-Y, Yao X-F, Yu M-Q. Research on Hopfield Network&Simulated Annealing inCamera Calibration[J]. ICIC Express Letters,2010,4(4):1257-1262.
[46]葛动元,姚锡凡.有侧向连接的Sanger算子在摄像机标定中的应用[J].光电子.激光.2010,21(11):1720-1724.
[47]葛动元,姚锡凡,向文江.嵌入正交权值神经网络在摄像机内外参数标定中的应用[J].光学精密工程,2011,19(11):2782-2790.
[48] Ahmed M T, Hemayed E E, Farag A A. Neurocalibration: A neural network That can tellcamera calibration parameters[A]. The Proceedings of the Seventh IEEE InternationalConference on Computer Vision[C],1999,463-468.
[49] Ahmed M T, Farag A A. A neural optimization framework for zoom lens cameracalibration[A], Proceedings of IEEE Conference on Computer Vision and PatternRecognition[C],2000:403-409.
[50] Jun J H, Kim W. Robust camera calibration using neural network[C]. Proceedings of theIEEE Region10Conference1999:694–697.
[51] Mohamed R, Ahmed A, Eid A, Farag A. Support vector machines for camera calibrationproblem [A]. IEEE International Conference on Image Processing[C],2006:1029-1032.
[52]吴俊芳.小尺寸视觉二维精密检测理论与方法[D].华南理工大学,2011:63~81.
[53] Foo Y S, Takefuji Y.[A]. In: IEEE Int Conf on NNS [C], San Diego,1998.34~45.
[54]黄赞.基于计算机微视觉的微运动测量关键技术研究[D].广州:华南理工大学,2011:108-118.
[55]张长水，阎平凡.基于机器视觉的谷物外观品质检测技术研究[J].自动化学报,1995,21(6):706~712.
[56]王克如,李少昆,王崇桃等.用机器视觉技术获取棉花叶片叶绿素浓度[J].作物学报,2006,32(1):34-40.
[57]陆尚平,文友先,葛维等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.
[58]赵杰文,刘少鹏,邹小波等.基于支持向量机的缺陷红枣机器视觉识别[J].农业机械学报,2008,39(3):113-115.
[59]柯薇.羊绒与羊毛纤维的计算机图像识别方法的研究[D].武汉:武汉纺织大学，2011,21~58.
[60]刘曙光,屈萍鸽,费佩燕.机器视觉在纺织检测中的应用[J].纺织学报,2005,24(6):597-599.
[61]陈振学,汪国有,刘成云.基于计算机视觉的汽车流量检测统计[J].华中科技大学学报(自然科学版),2006,34(5):46-49.
[62]苟挺,沈春林,张金林.基于字符特征的车牌英文和数字字符自联想识别[J].模式识别与人工智能,2004,17(4):467-471.
[63]王晓东,宋洪侠,刘超等.基于机器视觉的微小型零件测量与装配控制[J].哈尔滨工程大学学报,2011,32(9):1117-1122.
[64] Park T H, Kim H J. Path planning of automatic optical inspection machines for PCBassembly systems[A]. Proceedings2005IEEE International Symposium onComputational Intelligence in Robotics and Automation [C].2005:249-354.
[65]吴福培,张宪民,邝泳聪. SMT炉后晶体管类元件无铅焊点的自动光学检测算法[J].焊接学报,2009,30(7):5-8.
[66] Sanguino T J M, Rodriguez M S. Computer-aided system for defect inspection in thePCB manufacturing process[A]. IEEE16thInternational Conference on IntelligentEngineering Systems [C].2012:151-156.
[67]苏雷,张广明,魏晓冬.基于机器视觉的印刷电路板缺陷检测系统的设计与研究[J].机床与液压,2009,37(8):294-296.
[68]熊光洁,马树元,聂学俊等.基于机器视觉的高密度电路板缺陷检测系统[J].计算机测量与控制,2011,19(8):1824-1826.
[69]卢盛林,张宪民,邝泳聪.基于神经网络的PCB焊点检测方法[J].华南理工大学学报(自然科学版),2008,36(5):135-139.
[70] Liang Y-T, Chiou Y-C. Vision-based automatic tool wear monitoring system[A].Proceedings of the7th World Congress on Intelligent Control and Automation[C],2008:6031-6035.
[71]胡松立,许黎明,许开州等.微钻刃面图像边缘角点自适应提取方法[J].上海交通大学学报,2009,43(5):825-829.
[72]胡松立.基于机器视觉的PCB微钻几何参数精密检测技术研究[D].上海:上海交通大学,2009:27-54.
[73]张舞杰,李迪,叶峰.基于计算机视觉技术的微钻刃面自动光学检测[J].华南理工大学学报(自然科学版),2006,34(11):55-59.
[74]张舞杰,杨义禄,李迪等.自动影像测量系统关键算法[J].光学精密工程,2007,15(2):294-301.
[75]罗颖.基于机器视觉的PCB微钻端面缺陷检测研究[D].成都:电子科技大学,2009:5-52.
[76]葛动元,姚锡凡,向文江.有侧向连接的Sanger算法在微钻头棱边投影拟合中的应用[J].光学精密工程,2011,19(3):567-572.
[77] Ge D-Y, Yao X-F, Xiang W-J. Application of BP Neural Network and Genetic Algorithmin Testing of Micro-drill’s Rounded Corner[J]. Sensor Letters,2011,9(5):1943-1947.
[78]徐德,谭民,李原.机器人视觉测量与控制[M].北京：国防工业出版社,2008:39-195.
[79]王社阳.机器人视觉伺服系统的若干问题研究[D].哈尔滨:哈尔滨工业大学,2006:30-60.
[80] Lu U-C, Chou J C K. Eight-Space Quaternion Approach for Robotic Hand-eyeCalibration[A]. IEEE International Conference on Systems, Man and Cybernetics [C],1995:3316-3321.
[81] Andreff N, Horaud R, Espiau B. On-line Hand-Eye Calibration[A]. Proceedings ofSecond International Conference on3-D Digital Imaging and Modeling[C],1999.:430-436.
[82] Strobl K H, Hirzinger G. Optimal Hand-Eye Calibration [A]. Proceedings of the2006IEEE/RSJ International Conference on Intelligent Robots and Systems[C],2006:4647-4653.
[83] Heller J, Havlena M, Sugimoto A, Pajdla T. Structure-from-Motion Based Hand-EyeCalibration Using L∞Minimization[A]. IEEE Conference on Computer Vision andPattern Recognition (CVPR)[C],2011:3497-3503.
[84]袁野,仲崇权,欧宗瑛.基于BP网络的足球机器人视觉系统的标定[J].机器人,2001,23(7):752-755.
[85]周汉新,余小舫,李富荣,等.遥控宙斯机器人胆囊切除术的临床应用[J].中华医学杂志,2005,85(3):154-157.
[86]赵军,赵继,张雷.焊缝结构光图像处理与特征提取方法[J].西安交通大学学报,2013,47(1): y1-y6.
[87]徐德,赵晓光,涂志国等.基于结构光立体视觉的焊缝测量[J].焊接学报,2004,25(5):45-48.
[88]张广军,冷孝宇,吴林.弧焊机器人结构光视觉传感焊缝跟踪[J].焊接学报,2008,29(9):8-10.
[89]吴福朝.计算机视觉中的数学方法[M]，北京:科学出版社，2008,3-149.
[90] Tsai R Y. A versatile camera calibration technique for high accuracy3D machine visionmetrology using off-the-shelf TV cameras and lenses[J], IEEE Journal of Robotics andAutomation,1987,3(4):323-344.
[91] Chen T-P, Chen H, Liu R-W. Approximation capability in C(R-n) by multilayerfeedforward networks and related problems[J]. IEEE Transactions on Neural Networks,1995,6(1):25-30.
[92] Holland J H. Adaptation in Natural and Artificial Systems[M]. Michigan: The Univ. ofMichigon Press,1975,10-56.
[93] Bagley J D. The Behavior of Adaptive System Which Employ Genetic and CorrelationAlgorithms[D]. Dissertation Abstracts International.1976,28(12):1231-1240.
[94] Kennedy J, Eberhart C. Particle swarm optimization [A]. Proc. of IEEE InternationalConference on Neural Network[C], USA: IEEE Press,1995,(4):1942-1948.
[95] Shi Y, Eberhart R. Modified particle swarm optimizer[A]. The IEEE InternationalConference on Evolutionary Computation Proceedings[C], Anchorage, Alaska: IEEEPress,1998:69-73.
[96] Zadeh L A. Fuzzy sets[J]. Information and Control,1965,8(2):338-353.
[97] Zadeh, A Lotfi. Outline of a new approach to the analysis of complex systems anddecision processes[J]. IEEE Trans. On Systems, Man and Cybernetics,1973,3(1):28-44.
[98] Chandraker M, Agarwal S, Kriegman D, et al. Globally Optimal Affine and MetricUpgrades in Stratified Auto-calibration[A]. IEEE International Conference on ComputerVision[C],2007,1-8.
[99] Migita T, Shakunaga T. Evaluation of Epipole Estimation Methods with/without Rank-2Constraint across Algebraic/Geometric Error Functions[A], Proc. of IEEE Conference ofComputer Vision and Pattern Recognition[C],2007,1-7.
[100] Yao X F, Lian Z T, Ge D Y, et al. Approaches to Model and Control Non-linear Systemsby RBF Neural Network[J]. International Journal of Innovative Computing, Informationand Control,2011,7(2):941-954.
[101] Zhang S-C, Wei C-F, Shang H, and Shao J-A. Coupling of rural road network's spatialpattern and landform morphological factors by multilayer perception neural network[J].Sensor Letters,2012,10(1-2):168-176.
[102] Lin C-J, Wang J-G, Chen S-M.2D/3D face recognition using neural network based onhybrid Taguchi-particle swarm optimization[J]. International Journal of InnovativeComputing, Information and Control,2011,7(2):537-553.
[103] Song X-D, and Liu X-B. ETL tasks matching and scheduling based on geneticalgorithm[J]. ICIC Express Letters,2010,4(4):1245-1250.
[104] Yahya B N, H. Bae, Bae J, Kim D. Generating Valid Reference Business Process ModelUsing Genetic Algorithm[J]. International Journal of Innovative Computing, Informationand Control,2012,8(2):1463-1478.
[105]汪禹喆,雷英杰.基于最优评价的改进自适应粒子群算法[J].系统工程与电子技术,2008,30(12):2497-2501.
[106]常文平,罗先觉.梯级水电站优化调度的模糊自适应粒子群算法[J].西安交通大学学报,2009,43(6):93-98.
[107] Wang Y-Q, Gao H, Liang Y. Parametric Detection of Rice Kernel Shape Using MachineVision[J]. Sensor Letters,2011,9(3):1212-1219.
[108] Canny J. A Computational Approach to Edge Detection[J]. IEEE. Transactions onAnalysis and Machine Intelligence,1986,8(6):679-698.
[109]孙军华,刘震,张广军,等.基于柔性立体靶标的摄像机标定[J].光学学报,2009,29(12):3433-3439.
[110] Chatterjee C, et al. A Nonlinear Gauss-Seidel Algorithm for Noncoplanar and CoplanarCamera Calibration with Convergence Analysis[J]. Computer Vision and ImagineUnderstanding,1997,67(1):58-80.
[111] Jaros aw Protasiewicz, Piotr Szczepaniak. Neural Models of Demands for Electricity-Prediction and Risk Assessment[J], Przeglad Elektrotechniczny (Electrical Review),2012,88(6):272-279.
[112]苑云,朱肇昆,张小虎,等.基于无穷单应的大视场摄像机标定方法[J].光学学报,2012,32(7):59-79.
[113] Seyedtabaii S. Performance Evaluation of Neural Network Based Pulse-Echo WeldDefect Classifiers[J]. Measurement Science Review,2012,12(5):168-174.
[114] Wu C-F, Lin C-J. Digital image stabilization using a functional neural fuzzy network[J].International Journal of Innovative Computing, Information and Control,2013,9(1):99-109.
[115]蔡良伟,李霞.基于距离测度的改进自适应遗传退火算法[J].模式识别与人工智能,2005,18(3):380-384.
[116] Pan C S, Zhang Y, Yang L, Qiu S M. The Multi-Target Fire Distribution StrategyResearch of the Anti-Air Fire Based on the Genetic Algorithm[J]. International Journalof Innovative Computing, Information and Control,2012,8(4):2803-2810.
[117] Wong Y C, Leung K S, Wong K. Simulated annealing-based algorithms for the studiesof the thermoelastic scaling behavior[J]. IEEE Transactions on Systems, Man, andCybernetics, Part C: Applications and Reviews,2000,30(4):506-516.
[118]唐正宗,梁晋,肖振中,等.用于三维变形测量的数字图像相关系统[J].光学精密工程,2010,18(10):2244-2253.
[119]葛动元,姚锡凡.基于瑞利原理摄像机标定的精度研究[J].计量学报,2009,30(1):11-15.
[120] Kung S Y, Diamautaras K I, A Neural Network Learning Algorithm for AdaptivePrinciple Components Extraction(APEX)[A]. Proc of International Conference onAcoustics, Speech, and Signal Processing [C],1990,2:861-864.
[121] Palmieri F, Zhu J, Chang C H, Anti-Hebbian learning in topologically constrained linearnetworks a tutorial[J]. IEEE Transactions on Neural Networks,1993,5(4):748-761.
[122] Zhou J M, Zhou Q X, Shu L L, Xu D D, Research on Thermal Image Enhancement forDetecting Early Mechanical Damage in Apple[J]. Sensor letters,2011,9(3):1031-1036.
[123]胡峰,胡春生,王省书,等.成像激光雷达与摄像机外部位置关系的标定[J].光学精密工程,2011,19(4):938-943.
[124]玛嘎拉.高速微孔钻床主轴系统及钻头的动态特性研究[D].吉林:吉林大学,2005,1-9.
[125] GB/T28248-2012.印制板用硬质合金钻头国标[S].北京:中国标准出版社,2012.
[126]倪志福,陈璧光.群钻—倪志福钻头[M].上海:上海科技技术出版社,1999,1-87.
[127]周志雄.一种新型钻头及其刃磨技术的研究[D].长沙:湖南大学,2000,19-94.
[128]葛动元,姚锡凡,蒋寿生.基于神经网络的麻花钻圆度误差的检测[J].中北大学学报(自然科学版),2011,32(3):286-290.
[129] Ilhan I, Goktepe Y E, Kahramanli S. A Genetic Algorithm-Support Vector MachineMethod for Selecting Tag Single Nucleotide Polymorphisms[J]. International Journal ofInnovative Computing, Information and Control,2013,9(2):525-541.
[130] Ordaz J, Salazar S, MondiéS, et al. Predictor-based Position Control of a Quad-rotorwith Delays in GPS and Vision Measurements[J]. Journal of Intelligent&RoboticSystems,2013,70(1-4):13-26.
[131] Shao Y E, Lee W H. A Comparative Study between Box-Jenkins and Artificial NeuralNetworks Modeling Schemes in Predictions of Taiwan's Currency[J]. ICIC ExpressLetters,2013,7(2):349-353.
[132] Shi Y, Eberhart R C. A modified swarm optimizer[A], IEEE International Conference ofEvolutionary Computation[C], Anchorage, Alska: IEEE Press, May,1998:69-73.
[133] Izadi M, Ab Kadir M Z, Gomes C, et al. Evaluation of lightning return strokeparameters using measured magnetic flux density and PSO algorithm[J]. PrzegladElektrotechniczny (Electrical Review),2012,88(10a):201-204.
[134] Ma C X, Li Y Z, He R C, et al. Bus-Priority Intersection Signal Control System Basedon Wireless Sensor Network and Improved Particle Swarm Optimization Algorithm[J].Sensor Letters,2012,10(8):1823-1829.
[135]熊有伦,丁汉,刘恩沧.机器人学[M],北京:机械工业出版社,1993,15-93.
[136]蔡自兴.机器人学[M].北京:清华大学出版社.2000,29-130.
[137]谢存禧,张铁.机器人技术及其应用[M].北京:机械工业出版社,1993,35-57.
[138] Ding H. Computer-aided off-line planning of robot motion[J]. Robotics andAutonomous System,1991,7(1):67-72.
[139]申铁龙.机器人鲁棒控制基础[M].北京:清华大学出版社.2000,19-111.
[140]于靖军,刘辛军,丁希仑,等.机器人机构学的数学基础[M].北京:机械工业出版社,1993,82-130.
[141] Ganapathy S, Decomposition of transformation matrices for robot vision[C], Int. Conf.on Robotics[A], Atlanta. GA. Mar,1984:130-139.
[142] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography[J]. Commun. ACM,1981,24(6):381-395.
[143] Gennery D B. Stereo-camera calibration[A], in Proc. Image Understanding Workshop[C],1979:101-107.
[144] Barnard S T, Fischler M A. Computational stereo from an IU perspective[A], in Proc.Image Understanding Workshop[C],1981:157-167.
[145] Duda R O, Nitzan D, Barrett P. Use of range and reflectance data to find planar surfaceregions, IEEE Transactions on Pattern Analysis and Machine Intelligence[J].1979, vol.PAMI-1, no.3,259–271.
[146] Horaud P, Bolles R C.3DPO’s strategy to matching three-dimensional objects in rangedate[A], Proc. Int. Conf. on Robotics [C]. Atlanta. GA. Mar,1984:78-85.
[147] Nitzan D, Brain A E, Duda R O, The measurement and use of Registered reflectanceand range data in sense analysis[C], Proc. IEEE. Vol.65,1977:206-220.
[148] Brown M K. Feature extraction techniques for recognizing solid objects with anultrasonic range sensor[J]. IEEE Journal of Robotics and Automation,,1985, vol.RA-1,no.4,191-205.
[149] Grimson W E L. Disambiguating sensory interpretation using minimal sets of sensorydata [A]. in Proc. IEEE Int. Conf. on Robotics and Automation (San. Francisco. CA. Apr.1986).286-292.
[150] Grimson W E L, Lozano-Perez T. Model-based recognition and localization from sparserange or tactile data[J]. Int. J. Robotics Res.,1984,3(3):248-255.
[151] Shiu Y C, Paul R P, and Ahmad S. Using visual servoing in robotis tasks, Tech. Rep.TR-ERC86-10, Purdue University, W. Lafayette, IN,1986.
[152] Shiu Y C, Ahmad S. Calibration of wrist-mounted robotic sensors by solvinghomogenous Transform Equations of the form AX=XB[J]. IEEE Trans. on Robotics andAutomation,1989,5(1):16-29.
[153] Park F, Martin B. Robot sensor calibration: Solving AX=XB on the Euclidean group[J].IEEE Transactions on Robotics and Automation,1994,10(5):717-721.
[154]杨广林,孔令富,王洁.一种新的机器人手眼关系标定方法[J].机器人,2006,28(4):400-405.
[155] Motai Y, Kosaka A. Hand-eye calibration applied to viewpoint selection for roboticvision[J]. IEEE Transactions on Industrial Electronics,2008,55(10):3731-3741.
[156]张旭,李爱国,马孜,胡英.机器人手眼关系-基坐标系和世界坐标系关系的同时标定[J].控制与决策,2009,24(10):1531-1534.
[157] Li M X. Kinematic Calibration of an Active Head-Eye System[J]. IEEE Transactions onRobotics and Automation,1998,14(1):153-158.
[158] Dornaika F, Horaud R. Simultaneous Robot-World and Hand-Eye Calibration[J]. IEEETransactions on Robotics and Automation,1998,14(4):617-622.
[159] Ge D Y, Yao X F, Jiang S S, Gu Y Z. On Hand-Eye Calibration of Manipulator withOrthogonal Neural Network and Genetic Algorithm[J]. ICIC Express Letters Part B:Applications,2011,2(4):899-904.
[160] Fisher W D. The kinematic control of redundant manipulator, Ph. D. dissertation, W.Lafayette: Purdue University,1984.
[161] Zhao Z X, Wen G J, Zhang X, et al. Model-based Estimation for Pose, Velocity ofProjectile from Stereo Linear Array Image[J]. Measurement Science Review,2012,12(3):104-110.
[162]储珺,郭卢安政,赵贵花.采用环形模板的棋盘格角点检测[J].光学精密工程,2013,21(1):189-196.
[163] Ngaopitakkul A, Jettanasen C. Selection of Proper Activation Functions inBack-Propagation Neural Networks Algorithm for Identifying the Phase with FaultAppearance in Transformer Windings[J]. International Journal of Innovative Computing,Information and control,2012,8(6):4299-4318,
[164] Jaros aw Protasiewicz, Piotr Szczepaniak, Neural Models of Demands forElectricity-Prediction and Risk Assessment[J]. Przeglad Elektrotechniczny (ElectricalReview),2012,88(6):272-279.
[165] Chen S, Hong X, Harris C J. Particle Swarm Optimization Aided Orthogonal ForwardRegression for Unified Data Modeling[J]. IEEE Trans. On Evolutionary Computation,2010,14(4):477-499.
[166] Liu L L, Yang S X, Wang D W. Particle Swarm Optimization with Composite Particlesin Dynamic Environment[J]. IEEE Trans. on Systems, Man, and Cybernetics-Part B:Cybernetics,2010,40(6):1634-1648.
[167] Ma L-H, Zhang Y, Li H, Lu Z-M. A New Kind of Particle Filter Algorithm Based onImmune Particle Swarm Optimization in Objective Tracking[J]. ICIC Express Letters,2013,7(1):41-46.
[168] Mohamad M S, Omatu S, Deris S,et al. Selecting a Small Subset of Informative Genesfrom Gene Expression Data by Using a Modified Binary Particle Swarm Optimization[J].International Journal of Innovative Computing, Information and control,2012,8(6):4285-4297.
[169] Liu T G, Chen Q N, Ding Z Y, et al. A Polarization Control Method Based on ChaoticParticle Swarm Optimization Algorithm in Distributed Fiber-Optic Sensor[J]. SensorLetters,2012,10(7):1507-1510.
[2]谢宏威,张宪民,邝泳聪.基于图像特征统计分析的PCB焊点检测方法[J].仪器仪表学报,2011,32(2):401-407.
[3] Chen J-Y, Lee B-Y, Lee K-C, et al. Development and Implementation of a Simplified ToolMeasuring System[J]. Measurement Science Review,2010,10(4):142-146.
[4] Tien F C, Yeh C H, Hsieh K H. Automated visual inspection for micro-drills in printedcircuit board production[J]. International Journal of Production Research,2004,2(12):2477-2495.
[5]中国图像网.微操作机器人系统的研究开发[EB/OL].[2013-4-11]. http://www.china-image.cn/lunwen/3200602231459351526356474.html.
[6]东莞科视自动化科技有限公司网.机器视觉技术在精密制造行业中的地位越来越重要[EB/OL].[2013.1.24].http://www.cstmv.com/news/industry/201301241473.html.
[7] Szeliski R. Computer Vision: Algorithms and Applications[M]. Springer,2010.8,237-292.
[8]郑南宁.计算机视觉与模式识别[M].北京:国防工业出版社,1998:1-80,277-373.
[9]马颂德，张正友.计算机视觉—计算理论与算法基础[M].北京：科学出版社，1998：1-116.
[10]吴立德.计算机视觉[M].上海:复旦大学出版社,1993.119-208.
[11] Faugeras O D, Toscani G. The calibration problem for stereo[A]. IEEE Computer SocietyConference on Computer Vision and Pattern Recognition[C], Minmi Beach, Florida,June22-26,1986:15-20.
[12] Tsai R Y. A versatile camera calibration technique for high accuracy3D machine visionmetrology using off-the-shelf cameras and lens[J]. IEEE Transactions on Robotics andAutomation,1987,3(4):323-344.
[13]葛动元,姚锡凡,李凯南.双目立体视觉系统的标定[J].机械设计与制造,2010年第6期.188-189.
[14]葛动元,姚锡凡.向文江.构造性方法在摄像机标定中的应用研究[J].机床与液压,2010,(1):11-13.
[15]侯俊捷,魏新国,孙军华.基于同心圆合成图像匹配的双目视觉标定[J].光学学报,2012,32(3):0315003.
[16] Zhou F Q, Wang Y X, Cui Y, et al. Camera calibration approach usingcircle-square-combined target[J]. Chinese Optics Letters,2012,10(2):021003.
[17] Kim J S, Kim H W, Kweon I S. A camera calibration method using concentric circles forvision applications[A]. The5thAsia Conference on Computer Vision[C],2002:515-520.
[18] Zhang Z. A flexible new technique for camera calibration[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[19] Basu A. Active calibration: alternative strategy and analysis[A]. Proceedings of IEEEConference on Computer Vision and Pattern Recognition[C],1993:495-500.
[20] Du F, Brady M. Self-calibration of the intrinsic parameters of camera for active visionsystem[A]. Proceedings of IEEE Conference on Computer Vision and PatternRecognition [C],1993:477-482.
[21] Ma S D. A Self-calibration technique for active vision system[J]. IEEE Trans. Roboticsand Automation.1996,12(1):114-120.
[22]吴福朝,李华,胡占义.基于主动视觉系统的摄像机自标定方法研究[J].自动化学报,2001,27(6):752-762.
[23]胡占义,雷成,吴福朝.关于共面P4P问题的一点讨论[J].自动化学报,2001,27(6):770-776.
[24] Hartley R. Self-calibration of stationary cameras[J]. International Journal of ComputerVision,1997,229(1):2-5.
[25] Benalla M, Meunier J. Camera calibration with simple geometry[J]. Proceedings of2003International Conference on Image and Signal,2003,10(3):292-297
[26] Carvalho P C P, Szenberg F, Gattass M. Image-based modeling using a two-step camerascalibration method[A]. Proceedings of International Symposium on Computer Graphics,Image Processing and Vision[C],1998:388-395.
[27] Wu Y H, Zhu H J, Hu Z Y, Wu F C. Camera calibration from the quasi-affine invarianceof two parallel circles[A]. The8thEuropean Conference on Computer Vision[C],2004:190-202.
[28] Wu Y H, Hu Z Y. The invariant representations of a quadric cone and a twisted cubic [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(10):1329-1332.
[29] Yang A Y, Hong W, Ma Y. Structure and pose from single images of symmetric objectswith applications to robot navigation[A]. Proceedings of IEEE International Conferenceon Robotics and Automation [C], Taipei2003:1013-1020.
[30]霍炬,杨卫,杨明.基于消隐点几何特性的摄像机自标定方法[J].光学学报,2010,30(2):465-472.
[31]陈爱华,高诚辉,何炳蔚.基于正交消失点对的摄像机标定方法[J].仪器仪表学报,2012,33(1):161-166.
[32]许海霞,王耀南,袁小芳,等.基于矢量差分的未标定摄像机P5P问题的求解[J].自动化学报,2009,35(8):1140-1144.
[33]姚锡凡,李旻.人工智能技术与应用[M].北京:中国电力出版社,2008,126~155.
[34]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,101-161.
[35]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2007,55-76.
[36] Cho S.-B. Neural Network Classifiers for Recognizing Totally UnconstrainedHandwritten Neumeral[J]. IEEE Transaction on Neural Network.1997,8:43-53.
[37]吕朝辉,张兆杨,安平.基于神经网络的立体视觉摄像机标定[J].机械工程学报,2003,39(9):93-96.
[38]崔彦平,林玉池,张晓玲.基于神经网络的双目视觉摄像机标定方法的研究[J].光电子.激光.2005,16(9):1097-1110.
[39] Zong X P, Xu Y, Hao L, e al. Camera Calibration Based on the RBF Neural Networkwith Tunable Nodes forVisual Servoing in Robotics[A]. Proceedings of The2006IEEE/RSJ International Conference on Intelligent Robots and System[C],2006:5708-5712.
[40]蔡盛,李清安,乔彦峰.基于BP神经网络的姿态测量系统摄像机标定[J].光电子.激光,2007,18(7):832-834.
[41]葛动元,姚锡凡,黄英杰,张庆.基于模糊神经网络的双目视觉系统的研究与准确度[J].计量学报,2009,30(4):307-311.
[42]王社阳,强文义,陈兴林,张炳通.基于遗传算法的非线性摄像机标定[J].宇航计测技术,2004,24(4):33-38.
[43]郭秋艳,刘鹏飞,安平,张兆杨.基于遗传算法的摄像机自标定方法[J].中国图象图形学报,2006,11(11):1712-1715.
[44] Bouchouicha M, Khelifa M B, Puech W. A non-linear camera calibration with geneticalgorithm[A]. Proceedings of Seventh International Symposium on Signal Processingand Its Applications [C],2003:189-192.
[45] Ge D-Y, Yao X-F, Yu M-Q. Research on Hopfield Network&Simulated Annealing inCamera Calibration[J]. ICIC Express Letters,2010,4(4):1257-1262.
[46]葛动元,姚锡凡.有侧向连接的Sanger算子在摄像机标定中的应用[J].光电子.激光.2010,21(11):1720-1724.
[47]葛动元,姚锡凡,向文江.嵌入正交权值神经网络在摄像机内外参数标定中的应用[J].光学精密工程,2011,19(11):2782-2790.
[48] Ahmed M T, Hemayed E E, Farag A A. Neurocalibration: A neural network That can tellcamera calibration parameters[A]. The Proceedings of the Seventh IEEE InternationalConference on Computer Vision[C],1999,463-468.
[49] Ahmed M T, Farag A A. A neural optimization framework for zoom lens cameracalibration[A], Proceedings of IEEE Conference on Computer Vision and PatternRecognition[C],2000:403-409.
[50] Jun J H, Kim W. Robust camera calibration using neural network[C]. Proceedings of theIEEE Region10Conference1999:694–697.
[51] Mohamed R, Ahmed A, Eid A, Farag A. Support vector machines for camera calibrationproblem [A]. IEEE International Conference on Image Processing[C],2006:1029-1032.
[52]吴俊芳.小尺寸视觉二维精密检测理论与方法[D].华南理工大学,2011:63~81.
[53] Foo Y S, Takefuji Y.[A]. In: IEEE Int Conf on NNS [C], San Diego,1998.34~45.
[54]黄赞.基于计算机微视觉的微运动测量关键技术研究[D].广州:华南理工大学,2011:108-118.
[55]张长水，阎平凡.基于机器视觉的谷物外观品质检测技术研究[J].自动化学报,1995,21(6):706~712.
[56]王克如,李少昆,王崇桃等.用机器视觉技术获取棉花叶片叶绿素浓度[J].作物学报,2006,32(1):34-40.
[57]陆尚平,文友先,葛维等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10):190-194.
[58]赵杰文,刘少鹏,邹小波等.基于支持向量机的缺陷红枣机器视觉识别[J].农业机械学报,2008,39(3):113-115.
[59]柯薇.羊绒与羊毛纤维的计算机图像识别方法的研究[D].武汉:武汉纺织大学，2011,21~58.
[60]刘曙光,屈萍鸽,费佩燕.机器视觉在纺织检测中的应用[J].纺织学报,2005,24(6):597-599.
[61]陈振学,汪国有,刘成云.基于计算机视觉的汽车流量检测统计[J].华中科技大学学报(自然科学版),2006,34(5):46-49.
[62]苟挺,沈春林,张金林.基于字符特征的车牌英文和数字字符自联想识别[J].模式识别与人工智能,2004,17(4):467-471.
[63]王晓东,宋洪侠,刘超等.基于机器视觉的微小型零件测量与装配控制[J].哈尔滨工程大学学报,2011,32(9):1117-1122.
[64] Park T H, Kim H J. Path planning of automatic optical inspection machines for PCBassembly systems[A]. Proceedings2005IEEE International Symposium onComputational Intelligence in Robotics and Automation [C].2005:249-354.
[65]吴福培,张宪民,邝泳聪. SMT炉后晶体管类元件无铅焊点的自动光学检测算法[J].焊接学报,2009,30(7):5-8.
[66] Sanguino T J M, Rodriguez M S. Computer-aided system for defect inspection in thePCB manufacturing process[A]. IEEE16thInternational Conference on IntelligentEngineering Systems [C].2012:151-156.
[67]苏雷,张广明,魏晓冬.基于机器视觉的印刷电路板缺陷检测系统的设计与研究[J].机床与液压,2009,37(8):294-296.
[68]熊光洁,马树元,聂学俊等.基于机器视觉的高密度电路板缺陷检测系统[J].计算机测量与控制,2011,19(8):1824-1826.
[69]卢盛林,张宪民,邝泳聪.基于神经网络的PCB焊点检测方法[J].华南理工大学学报(自然科学版),2008,36(5):135-139.
[70] Liang Y-T, Chiou Y-C. Vision-based automatic tool wear monitoring system[A].Proceedings of the7th World Congress on Intelligent Control and Automation[C],2008:6031-6035.
[71]胡松立,许黎明,许开州等.微钻刃面图像边缘角点自适应提取方法[J].上海交通大学学报,2009,43(5):825-829.
[72]胡松立.基于机器视觉的PCB微钻几何参数精密检测技术研究[D].上海:上海交通大学,2009:27-54.
[73]张舞杰,李迪,叶峰.基于计算机视觉技术的微钻刃面自动光学检测[J].华南理工大学学报(自然科学版),2006,34(11):55-59.
[74]张舞杰,杨义禄,李迪等.自动影像测量系统关键算法[J].光学精密工程,2007,15(2):294-301.
[75]罗颖.基于机器视觉的PCB微钻端面缺陷检测研究[D].成都:电子科技大学,2009:5-52.
[76]葛动元,姚锡凡,向文江.有侧向连接的Sanger算法在微钻头棱边投影拟合中的应用[J].光学精密工程,2011,19(3):567-572.
[77] Ge D-Y, Yao X-F, Xiang W-J. Application of BP Neural Network and Genetic Algorithmin Testing of Micro-drill’s Rounded Corner[J]. Sensor Letters,2011,9(5):1943-1947.
[78]徐德,谭民,李原.机器人视觉测量与控制[M].北京：国防工业出版社,2008:39-195.
[79]王社阳.机器人视觉伺服系统的若干问题研究[D].哈尔滨:哈尔滨工业大学,2006:30-60.
[80] Lu U-C, Chou J C K. Eight-Space Quaternion Approach for Robotic Hand-eyeCalibration[A]. IEEE International Conference on Systems, Man and Cybernetics [C],1995:3316-3321.
[81] Andreff N, Horaud R, Espiau B. On-line Hand-Eye Calibration[A]. Proceedings ofSecond International Conference on3-D Digital Imaging and Modeling[C],1999.:430-436.
[82] Strobl K H, Hirzinger G. Optimal Hand-Eye Calibration [A]. Proceedings of the2006IEEE/RSJ International Conference on Intelligent Robots and Systems[C],2006:4647-4653.
[83] Heller J, Havlena M, Sugimoto A, Pajdla T. Structure-from-Motion Based Hand-EyeCalibration Using L∞Minimization[A]. IEEE Conference on Computer Vision andPattern Recognition (CVPR)[C],2011:3497-3503.
[84]袁野,仲崇权,欧宗瑛.基于BP网络的足球机器人视觉系统的标定[J].机器人,2001,23(7):752-755.
[85]周汉新,余小舫,李富荣,等.遥控宙斯机器人胆囊切除术的临床应用[J].中华医学杂志,2005,85(3):154-157.
[86]赵军,赵继,张雷.焊缝结构光图像处理与特征提取方法[J].西安交通大学学报,2013,47(1): y1-y6.
[87]徐德,赵晓光,涂志国等.基于结构光立体视觉的焊缝测量[J].焊接学报,2004,25(5):45-48.
[88]张广军,冷孝宇,吴林.弧焊机器人结构光视觉传感焊缝跟踪[J].焊接学报,2008,29(9):8-10.
[89]吴福朝.计算机视觉中的数学方法[M]，北京:科学出版社，2008,3-149.
[90] Tsai R Y. A versatile camera calibration technique for high accuracy3D machine visionmetrology using off-the-shelf TV cameras and lenses[J], IEEE Journal of Robotics andAutomation,1987,3(4):323-344.
[91] Chen T-P, Chen H, Liu R-W. Approximation capability in C(R-n) by multilayerfeedforward networks and related problems[J]. IEEE Transactions on Neural Networks,1995,6(1):25-30.
[92] Holland J H. Adaptation in Natural and Artificial Systems[M]. Michigan: The Univ. ofMichigon Press,1975,10-56.
[93] Bagley J D. The Behavior of Adaptive System Which Employ Genetic and CorrelationAlgorithms[D]. Dissertation Abstracts International.1976,28(12):1231-1240.
[94] Kennedy J, Eberhart C. Particle swarm optimization [A]. Proc. of IEEE InternationalConference on Neural Network[C], USA: IEEE Press,1995,(4):1942-1948.
[95] Shi Y, Eberhart R. Modified particle swarm optimizer[A]. The IEEE InternationalConference on Evolutionary Computation Proceedings[C], Anchorage, Alaska: IEEEPress,1998:69-73.
[96] Zadeh L A. Fuzzy sets[J]. Information and Control,1965,8(2):338-353.
[97] Zadeh, A Lotfi. Outline of a new approach to the analysis of complex systems anddecision processes[J]. IEEE Trans. On Systems, Man and Cybernetics,1973,3(1):28-44.
[98] Chandraker M, Agarwal S, Kriegman D, et al. Globally Optimal Affine and MetricUpgrades in Stratified Auto-calibration[A]. IEEE International Conference on ComputerVision[C],2007,1-8.
[99] Migita T, Shakunaga T. Evaluation of Epipole Estimation Methods with/without Rank-2Constraint across Algebraic/Geometric Error Functions[A], Proc. of IEEE Conference ofComputer Vision and Pattern Recognition[C],2007,1-7.
[100] Yao X F, Lian Z T, Ge D Y, et al. Approaches to Model and Control Non-linear Systemsby RBF Neural Network[J]. International Journal of Innovative Computing, Informationand Control,2011,7(2):941-954.
[101] Zhang S-C, Wei C-F, Shang H, and Shao J-A. Coupling of rural road network's spatialpattern and landform morphological factors by multilayer perception neural network[J].Sensor Letters,2012,10(1-2):168-176.
[102] Lin C-J, Wang J-G, Chen S-M.2D/3D face recognition using neural network based onhybrid Taguchi-particle swarm optimization[J]. International Journal of InnovativeComputing, Information and Control,2011,7(2):537-553.
[103] Song X-D, and Liu X-B. ETL tasks matching and scheduling based on geneticalgorithm[J]. ICIC Express Letters,2010,4(4):1245-1250.
[104] Yahya B N, H. Bae, Bae J, Kim D. Generating Valid Reference Business Process ModelUsing Genetic Algorithm[J]. International Journal of Innovative Computing, Informationand Control,2012,8(2):1463-1478.
[105]汪禹喆,雷英杰.基于最优评价的改进自适应粒子群算法[J].系统工程与电子技术,2008,30(12):2497-2501.
[106]常文平,罗先觉.梯级水电站优化调度的模糊自适应粒子群算法[J].西安交通大学学报,2009,43(6):93-98.
[107] Wang Y-Q, Gao H, Liang Y. Parametric Detection of Rice Kernel Shape Using MachineVision[J]. Sensor Letters,2011,9(3):1212-1219.
[108] Canny J. A Computational Approach to Edge Detection[J]. IEEE. Transactions onAnalysis and Machine Intelligence,1986,8(6):679-698.
[109]孙军华,刘震,张广军,等.基于柔性立体靶标的摄像机标定[J].光学学报,2009,29(12):3433-3439.
[110] Chatterjee C, et al. A Nonlinear Gauss-Seidel Algorithm for Noncoplanar and CoplanarCamera Calibration with Convergence Analysis[J]. Computer Vision and ImagineUnderstanding,1997,67(1):58-80.
[111] Jaros aw Protasiewicz, Piotr Szczepaniak. Neural Models of Demands for Electricity-Prediction and Risk Assessment[J], Przeglad Elektrotechniczny (Electrical Review),2012,88(6):272-279.
[112]苑云,朱肇昆,张小虎,等.基于无穷单应的大视场摄像机标定方法[J].光学学报,2012,32(7):59-79.
[113] Seyedtabaii S. Performance Evaluation of Neural Network Based Pulse-Echo WeldDefect Classifiers[J]. Measurement Science Review,2012,12(5):168-174.
[114] Wu C-F, Lin C-J. Digital image stabilization using a functional neural fuzzy network[J].International Journal of Innovative Computing, Information and Control,2013,9(1):99-109.
[115]蔡良伟,李霞.基于距离测度的改进自适应遗传退火算法[J].模式识别与人工智能,2005,18(3):380-384.
[116] Pan C S, Zhang Y, Yang L, Qiu S M. The Multi-Target Fire Distribution StrategyResearch of the Anti-Air Fire Based on the Genetic Algorithm[J]. International Journalof Innovative Computing, Information and Control,2012,8(4):2803-2810.
[117] Wong Y C, Leung K S, Wong K. Simulated annealing-based algorithms for the studiesof the thermoelastic scaling behavior[J]. IEEE Transactions on Systems, Man, andCybernetics, Part C: Applications and Reviews,2000,30(4):506-516.
[118]唐正宗,梁晋,肖振中,等.用于三维变形测量的数字图像相关系统[J].光学精密工程,2010,18(10):2244-2253.
[119]葛动元,姚锡凡.基于瑞利原理摄像机标定的精度研究[J].计量学报,2009,30(1):11-15.
[120] Kung S Y, Diamautaras K I, A Neural Network Learning Algorithm for AdaptivePrinciple Components Extraction(APEX)[A]. Proc of International Conference onAcoustics, Speech, and Signal Processing [C],1990,2:861-864.
[121] Palmieri F, Zhu J, Chang C H, Anti-Hebbian learning in topologically constrained linearnetworks a tutorial[J]. IEEE Transactions on Neural Networks,1993,5(4):748-761.
[122] Zhou J M, Zhou Q X, Shu L L, Xu D D, Research on Thermal Image Enhancement forDetecting Early Mechanical Damage in Apple[J]. Sensor letters,2011,9(3):1031-1036.
[123]胡峰,胡春生,王省书,等.成像激光雷达与摄像机外部位置关系的标定[J].光学精密工程,2011,19(4):938-943.
[124]玛嘎拉.高速微孔钻床主轴系统及钻头的动态特性研究[D].吉林:吉林大学,2005,1-9.
[125] GB/T28248-2012.印制板用硬质合金钻头国标[S].北京:中国标准出版社,2012.
[126]倪志福,陈璧光.群钻—倪志福钻头[M].上海:上海科技技术出版社,1999,1-87.
[127]周志雄.一种新型钻头及其刃磨技术的研究[D].长沙:湖南大学,2000,19-94.
[128]葛动元,姚锡凡,蒋寿生.基于神经网络的麻花钻圆度误差的检测[J].中北大学学报(自然科学版),2011,32(3):286-290.
[129] Ilhan I, Goktepe Y E, Kahramanli S. A Genetic Algorithm-Support Vector MachineMethod for Selecting Tag Single Nucleotide Polymorphisms[J]. International Journal ofInnovative Computing, Information and Control,2013,9(2):525-541.
[130] Ordaz J, Salazar S, MondiéS, et al. Predictor-based Position Control of a Quad-rotorwith Delays in GPS and Vision Measurements[J]. Journal of Intelligent&RoboticSystems,2013,70(1-4):13-26.
[131] Shao Y E, Lee W H. A Comparative Study between Box-Jenkins and Artificial NeuralNetworks Modeling Schemes in Predictions of Taiwan's Currency[J]. ICIC ExpressLetters,2013,7(2):349-353.
[132] Shi Y, Eberhart R C. A modified swarm optimizer[A], IEEE International Conference ofEvolutionary Computation[C], Anchorage, Alska: IEEE Press, May,1998:69-73.
[133] Izadi M, Ab Kadir M Z, Gomes C, et al. Evaluation of lightning return strokeparameters using measured magnetic flux density and PSO algorithm[J]. PrzegladElektrotechniczny (Electrical Review),2012,88(10a):201-204.
[134] Ma C X, Li Y Z, He R C, et al. Bus-Priority Intersection Signal Control System Basedon Wireless Sensor Network and Improved Particle Swarm Optimization Algorithm[J].Sensor Letters,2012,10(8):1823-1829.
[135]熊有伦,丁汉,刘恩沧.机器人学[M],北京:机械工业出版社,1993,15-93.
[136]蔡自兴.机器人学[M].北京:清华大学出版社.2000,29-130.
[137]谢存禧,张铁.机器人技术及其应用[M].北京:机械工业出版社,1993,35-57.
[138] Ding H. Computer-aided off-line planning of robot motion[J]. Robotics andAutonomous System,1991,7(1):67-72.
[139]申铁龙.机器人鲁棒控制基础[M].北京:清华大学出版社.2000,19-111.
[140]于靖军,刘辛军,丁希仑,等.机器人机构学的数学基础[M].北京:机械工业出版社,1993,82-130.
[141] Ganapathy S, Decomposition of transformation matrices for robot vision[C], Int. Conf.on Robotics[A], Atlanta. GA. Mar,1984:130-139.
[142] Fischler M A, Bolles R C. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography[J]. Commun. ACM,1981,24(6):381-395.
[143] Gennery D B. Stereo-camera calibration[A], in Proc. Image Understanding Workshop[C],1979:101-107.
[144] Barnard S T, Fischler M A. Computational stereo from an IU perspective[A], in Proc.Image Understanding Workshop[C],1981:157-167.
[145] Duda R O, Nitzan D, Barrett P. Use of range and reflectance data to find planar surfaceregions, IEEE Transactions on Pattern Analysis and Machine Intelligence[J].1979, vol.PAMI-1, no.3,259–271.
[146] Horaud P, Bolles R C.3DPO’s strategy to matching three-dimensional objects in rangedate[A], Proc. Int. Conf. on Robotics [C]. Atlanta. GA. Mar,1984:78-85.
[147] Nitzan D, Brain A E, Duda R O, The measurement and use of Registered reflectanceand range data in sense analysis[C], Proc. IEEE. Vol.65,1977:206-220.
[148] Brown M K. Feature extraction techniques for recognizing solid objects with anultrasonic range sensor[J]. IEEE Journal of Robotics and Automation,,1985, vol.RA-1,no.4,191-205.
[149] Grimson W E L. Disambiguating sensory interpretation using minimal sets of sensorydata [A]. in Proc. IEEE Int. Conf. on Robotics and Automation (San. Francisco. CA. Apr.1986).286-292.
[150] Grimson W E L, Lozano-Perez T. Model-based recognition and localization from sparserange or tactile data[J]. Int. J. Robotics Res.,1984,3(3):248-255.
[151] Shiu Y C, Paul R P, and Ahmad S. Using visual servoing in robotis tasks, Tech. Rep.TR-ERC86-10, Purdue University, W. Lafayette, IN,1986.
[152] Shiu Y C, Ahmad S. Calibration of wrist-mounted robotic sensors by solvinghomogenous Transform Equations of the form AX=XB[J]. IEEE Trans. on Robotics andAutomation,1989,5(1):16-29.
[153] Park F, Martin B. Robot sensor calibration: Solving AX=XB on the Euclidean group[J].IEEE Transactions on Robotics and Automation,1994,10(5):717-721.
[154]杨广林,孔令富,王洁.一种新的机器人手眼关系标定方法[J].机器人,2006,28(4):400-405.
[155] Motai Y, Kosaka A. Hand-eye calibration applied to viewpoint selection for roboticvision[J]. IEEE Transactions on Industrial Electronics,2008,55(10):3731-3741.
[156]张旭,李爱国,马孜,胡英.机器人手眼关系-基坐标系和世界坐标系关系的同时标定[J].控制与决策,2009,24(10):1531-1534.
[157] Li M X. Kinematic Calibration of an Active Head-Eye System[J]. IEEE Transactions onRobotics and Automation,1998,14(1):153-158.
[158] Dornaika F, Horaud R. Simultaneous Robot-World and Hand-Eye Calibration[J]. IEEETransactions on Robotics and Automation,1998,14(4):617-622.
[159] Ge D Y, Yao X F, Jiang S S, Gu Y Z. On Hand-Eye Calibration of Manipulator withOrthogonal Neural Network and Genetic Algorithm[J]. ICIC Express Letters Part B:Applications,2011,2(4):899-904.
[160] Fisher W D. The kinematic control of redundant manipulator, Ph. D. dissertation, W.Lafayette: Purdue University,1984.
[161] Zhao Z X, Wen G J, Zhang X, et al. Model-based Estimation for Pose, Velocity ofProjectile from Stereo Linear Array Image[J]. Measurement Science Review,2012,12(3):104-110.
[162]储珺,郭卢安政,赵贵花.采用环形模板的棋盘格角点检测[J].光学精密工程,2013,21(1):189-196.
[163] Ngaopitakkul A, Jettanasen C. Selection of Proper Activation Functions inBack-Propagation Neural Networks Algorithm for Identifying the Phase with FaultAppearance in Transformer Windings[J]. International Journal of Innovative Computing,Information and control,2012,8(6):4299-4318,
[164] Jaros aw Protasiewicz, Piotr Szczepaniak, Neural Models of Demands forElectricity-Prediction and Risk Assessment[J]. Przeglad Elektrotechniczny (ElectricalReview),2012,88(6):272-279.
[165] Chen S, Hong X, Harris C J. Particle Swarm Optimization Aided Orthogonal ForwardRegression for Unified Data Modeling[J]. IEEE Trans. On Evolutionary Computation,2010,14(4):477-499.
[166] Liu L L, Yang S X, Wang D W. Particle Swarm Optimization with Composite Particlesin Dynamic Environment[J]. IEEE Trans. on Systems, Man, and Cybernetics-Part B:Cybernetics,2010,40(6):1634-1648.
[167] Ma L-H, Zhang Y, Li H, Lu Z-M. A New Kind of Particle Filter Algorithm Based onImmune Particle Swarm Optimization in Objective Tracking[J]. ICIC Express Letters,2013,7(1):41-46.
[168] Mohamad M S, Omatu S, Deris S,et al. Selecting a Small Subset of Informative Genesfrom Gene Expression Data by Using a Modified Binary Particle Swarm Optimization[J].International Journal of Innovative Computing, Information and control,2012,8(6):4285-4297.
[169] Liu T G, Chen Q N, Ding Z Y, et al. A Polarization Control Method Based on ChaoticParticle Swarm Optimization Algorithm in Distributed Fiber-Optic Sensor[J]. SensorLetters,2012,10(7):1507-1510.