摘要
具有物体识别能力是机器人具有智能性的一个重要标志。智能机器人通过感知目标物体的位置和形状,才能实现抓取或跟踪等任务。形状信息是一种高层视觉特征,通过形状信息特征可以让机器人实现对物体形状的理解。如何让机器人将目标图像从自然图像中抽象并表示出来,是计算机视觉的一个核心。关于纯形状的分析研究虽然取得了大量成果,但是受噪声、形状建模等因素影响,实际应用却很少。
本文对服务于数控机床群协同加工的上下料机器人所抓取的工件、卡盘等目标物体的识别、定位进行了研究,受到格式塔心理认知机制的启发,采用了自底向上的特征提取和自顶向下的形状指导相结合混合策略,解决了工件和卡盘识别定位中的关键问题。
论文的研究工作及取得的成果如下：
(1)针对目标物体和背景混合在一起的自然图像,提出了一种基于格式塔心理感知理论的高层视觉引导下的不连续轮廓段的识别方法。该算法提出了局部形状片段描述子,并建立了形状片段相似度评价函数,确定片段与模型间的从属概率,增强了局部形状片段对模型的作用,提高了拟合过程的收敛速度。对不连续轮廓链,在图模型基础上对不连续轮廓链进行“完形”操作,以寻找虚实交错的最小代价的简单环将高次问题转化为优化问题,并将计算复杂度降低到多项式级。通过邻域投票机制,对背景噪声边缘进行剔除和抑制,剔除异值轮廓后,减少了数据计算量,提高了定位精度。通过对物体轮廓的曲线拟合,准确的得到了上下料的空间位置信息。
(2)为了对毛坯工件进行准确选择,保证最小的加工余量,提出了基于修正的贝塞尔点扩散函数的亚像素边缘检测方法。根据初步定位边缘的灰度分布特征,采用最小二乘法拟合原理进行亚像素定位。拟合函数采用了修正贝塞尔点扩散函数。修正后的贝塞尔点扩散函数吸取了高斯点扩散函数的优点,引入可变参数对贝塞尔点扩散函数进行一次修正和二次修正,提高了的贝塞尔点扩散函数灵活性和精确性,其实验结果表明修正后的贝塞尔拟合比高斯拟合具有更高的精度,而且一次修正速度较快,满足了对于边缘检测的实时性要求。
(3)研究了摄像机标定的主要方法,分析摄像机标定产生误差的主要原因,进行了误差纠正。在实验数据分析的基础上,总结了基线距、焦距、物距与标定精度的非线性关系,绘制了标定误差变化的曲线图。通过摄像机标定的内外参数和基线距的选择优化,使双目视觉标定的精度和稳定性得到提高。
(4)在图像的降噪处理方面,提出了一种保留图像边缘细节特征的平滑滤波方法。该方法构造了基于九邻域的由五边形和六边形组成的窗口掩模,该掩模设计具有一个优势,当像素点位于一个形状复杂邻域的锐角处,该掩模也能找一个与边缘形状基本相符的均匀的邻域,这样在去除噪声的同时也尽可能的保留了边缘细节。
上述研究工作为面向数控机床群的上下料机器人的工程实践奠定了理论基础,并且对提高加工制造业的自动化水平,增强计算机视觉技术在工业领域的适用性具有重要意义。
The robot with object recognition is an important symbol of intelligence. Intelligent robot can realize the capture or tracking task through the position and shape of object perception. The shape information is a kind of high-level visual features, analysis on the characteristics of shape information can make robot realize the understanding of the object shape. How to make robots represent and abstract shape information of the aim object from natural images is a core of computer vision. A lot of achievements have been made in analysis and research on pure shape, but a few are rarely used in practice, influenced by the noise and shape model.
In this paper, mainly research on positioning and objects recognition such as robot grapping workpiece, chuck, is about the robot special used in the service of NC Machine Group. Enlightened by Gestalt psychology cognitive theory, the paper puts forward the hybrid strategy, which combines the feature extraction of bottom-up and top-down the shape of the guidance, and solve the key problems in the workpiece and chuck identification and location.
(1) According to the target object and the background are blended in the natural images, this paper proposes a high-level vision based on the theory of the Gestalt perception under the guide of discrete contour recognition method. The algorithm presents local shape fragment descriptors, and establishes the shape similarity evaluation function to determine the segment between the model and subordinate probability, enhances the role of local shape fragments on the model, improves the convergence speed of the fitting process. For the discontinuous contour chain,"Gestalt" operation on the discontinuous contour in figure on the basis of the model, finds a minimum cost simple ring. The high order problem can be converted to optimization problems, and the computational complexity is reduced to polynomial level. Through the neighborhood voting mechanism, the background noise is eliminated and inhibited. After excluding abnormal value profile reduced the data computation, the positioning precision is improved. The accurate space location information about feeding NC machine is got by the curve fitting of the contour of the object.
(2) In order to select the blank workpiece accurately, and ensure the minimum machining allowance, this paper puts forward the sub-pixel edge detection methods based on modified Bezier point spread function. According to the gray level distribution of the initial edge localization, the subpixel is located by the quafric curve. The quafric curve uses the modified Bezier point spread function. Revised Bezier point spread function takes the advantages of Gauss point spread function. The introduction of variable parameters on the Bezier point spread function for a correction and the second amendment, improves the flexibility and accuracy of Bezier point spread function, the experimental results show that the revised Bezier fitting has a higher accuracy than Gauss fitting, and a correction is faster, to meet the real-time requirements for edge detection.
(3) Research on the methods of camera calibration, and analyze the main cause of the camera calibration error and complete the error correction. Based on the analysis of experimental data, summarizes nonlinear relation between calibration accuracy and the baseline distance, focal length, distance; then draw the curve of calibration error change. Through the internal and external parameters of camera calibration and optimization choice of baseline distance, binocular calibration precision and stability is improved.
(4) In the denoising image, this paper proposes a smooth filtering method of retention characteristics of image edge details. This method constructs window mask based on nine neighborhoods with pentagons and hexagons. Because pentagons and hexagons in the mask neighborhood all have acute Angle, this design has the advantage that the pixels are in acute angle of a complex shape field, the mask can also find a homogeneous neighborhood consistent with edge shape basically. The edge details are retained while removing the noise.
The research works above laid a theoretical foundation for the engineering practice of the up-down material robot serving for numerical control machine tool group, and those are of great significance not only to improve the level of automation of manufacturing industry,but also to enhance the applicability of computer vision technology in the industrial field.
引文
[1]张广军.机器视觉[M].北京：科学出版社,2005.
[2]Chellappa, Rama. Mathematical statistics and computer vision[J]. Image and Vision Computing,2012,30(8):467-468.
[3]Gnanasekera, Manaram. Computer vision based hand movement capturing system[C]//Proceedings of the 8th International Conference on Computer Science and Education(ICCSE),2013:416-421.
[4]Szczypinski, Piotr M. Computer vision algorithm for barley kernel identification, orientation estimation and surface structure assessmen[J]. Computers and Electronics in Agriculture, 2012,87:32-38.
[5]Wangtong, Theerayod. Computer vision framework for object monitoring[C]//2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2012.
[6]Horst Bunke, Kaspar RiesenTowards.The unification of structural and statistical pattern recognition[J].Pattern Recognition Letters,2012,33(7):811-825.
[7]邵宇,刘莹,孙富春.张量值图像插值方法综述[J].中国图象图形学报,2012,17(10)：1197-1205.
[8]龙云,李小明,向建化,吴青凤.基于Lab VIEW的视觉检测系统软件框架设计[J].机电工程技术,2012,6：141-143.
[9]杨福增,刘珊,陈丽萍.基于立体视觉技术的多种农田障碍物检测方法[J].农业机械学报,2012,43(5)：169-172.
[10]王耀南,吴成中,张辉,葛继,周博文.医药输液视觉检测机器人关键技术综述[J].机械工程学报,2013,36(4)：114-117.
[11][12]唐湘娜,王耀南.铁轨表面缺陷的视觉检测与识别算法[J].计算机工程,2013,(05)：129-132.
[12]鹿文浩,李亚利,王生进,丁晓青.基于部件的三维目标检测算法新进展[J].自动化学报,2012,36(04)：497-506.
[13]Lulio, Luciano C. Cognitive-merged statistical pattern recognition method for image processing in mobile robot navigation[C]//Proceedings-2012 Brazilian Robotics Symposium and Latin American Robotics Symposium, SBR-LARS 2012,2012:279-283.
[14]Boaz Zion, The use of computer vision technologies in agriculture-A review[J]. Computers and Electronics in Agriculture,2012,88:125-132.
[15]Voosen K. Machine vision-It's all in the software[J]. Manufacturing Engineer,2007, 86(1):43-45.
[16]Nagendra, Pavan. Vehicle position estimation for driving pattern recognition using a monocular vision system[C]//2012 International Conference on Computer Communication and Informatics,2012:751-759.
[17]Wang Zhi. Mobile positioning in blind environments (Ⅰ):Pattern recognition algorithms for coded sequence pattern signposts[J]. Dongbei Daxue Xuebao/Journal of Northeastern University,2011,32(5):72-73.
[18]Raducanu. Online pattern recognition and machine learning techniques for computer-vision: Theory and applications[J]. Image and Vision Computing,2010,28(7):1063-1064.
[19]Bhuvanesh Abhinesh, Ratnam Mani Maran. Automatic detection of stamping defects in leadframes using machine vision:Overcoming translational and rotational misalignment [J].International Journal of Advanced Manufacturing Technology,2007,32(11):1201-1210.
[20]Gamage P, Xie S Q.A real-time vision system for defect inspection in cast extrusion manufacturing process [J].International Journal of Advanced Manufacturing Technology, 2009,40(2):144-156.
[21]Cheng Yuan, Jafari Mohsen A. Vision-based online process control in manufacturing applications [J]. IEEE Transactions on Automation Science and Engineering,2008,5(1): 140-153.
[22]Bui Trong Tuyen, Pham Thuong Cat. Neural Network Based Visual Control[C]//In Proceeding of:Control, Automation, Robotics and Vision,2002:39-44.
[23]Mark B Lynch, Cihan H Dagli, Mahesh Vallenki. The use of feed forward neural networks for machine vision calibration [J]. International Journal of Production Economies,2009, 60/61:479-89.
[24]Lyndon N Smith, Melvyn L Smith.Automatic machine vision calibration using statistical and neural network methods [J]. Image and Vision Computing,2009,23(10):887-899.
[25]Palani S. Prediction of surface roughness in CNC end milling by machine vision system using artificial neural network based on 2D Fourier transform [J]. International Journal of Advanced Manufacturing Technology,2010,54(9-12):1033-1042.
[26]Lahajnar F, Bernard R. Machine vision system for inspecting electric plates[J].Computer in Industry,2010,47(1):113-122.
[27]Perng D B, Chou C C, Lee S M. Design and development of a new machine vision wire bonding inspection system[J].The International Journal of Advanced Manufacturing Technology,2011,34(3-4):323-334.
[28]Shahdi A, Sirouspour S. Adaptive/robust control for time-delay teleoperation [J]. IEEE Transactions on Robotics,2012,25(1):196-205.
[29]Lu Y, Chen Tie Qi, Chen Jie, et al. Machine vision systems using machine learning for industrial product inspection[C]//Proceedings of SPIE-The International Society for Optical Engineering,2012:161-170.
[30]Hong Deokhwal, Lee Hyunkil, Kim Minyoung, et al. A 3D inspection system for PCB board by Fusing Moire Technique and stereo vision algorithm [C]//Proceedings of the SICE Annual Conference,2012:2473-2479.
[31]邓勇军,吴明辉,陈锦云,陈善本.移动焊接机器人的工作识别及焊缝起始位置定位[J].上海交通大学学报：自科版,2012,(07)：1054-1058
[32]Cong Jason, Huang Hui. A generalized control-flow-aware pattern recognition algorithm for behavioral synthesis[C]//Proceedings -Design, Automation and Test in Europe, DATE, 2012:1255-1260.
[33]Zhao Ping, Li Yongkui. Composite measurement method based on computer vision technology[J].Advanced Materials Research,418-420,2012,2118-2121
[34]Vincze M. Integrated vision system for the semantic interpretation of activities where a person handles objects [J]. CVIU,2009,113(6):682-692.
[35]陶霖密,于亚鹏,邸慧军.摄像机几何约束及人体定位[J].中国图象图形学报2012,(09)：105-112
[36]胡刚,刘侍刚,吴清亮,王刚.基于扩散距离的SIFT特征匹配算法[J].计算机系统应用,2012,(09)：94-98.
[37]仇阿根,熊利荣,赵阳阳.基于BP神经网络的花生外衣完整性识别方法[J].农机化研究2013,(02)：54-56.
[38]陈英,廖涛,林初靠,万虎,李伟.基于计算机视觉的葡萄检测分级系统[J].农业机械学报.2010,(03)：175-178.
[39]黄琛,丁晓青,方驰.一种鲁棒高效的人脸特征点跟踪方法[J].自动化学报,2012,(05)：119-127.
[40]Lin Kaiyan, Chen Jie.A review on computer vision technologies applied in greenhouse plant stress detection[J]. Communications in Computer and Information Science,2013,363: 192-200.
[41]Beardsley P A, Torr P H S, Zisserman. A 3D Model Acquisition from x-tended Image Sequences[C]//Proc 4th European Conference on Computer Vision,1996:683-695.
[42]张兴华.基于机器视觉的目标识别与测量算法的研究[D].山东济南：山东大学,2012.
[43]伍雪冬.计算机视觉中摄像机定标及位姿和运动估计方法的研究[D].湖南长沙：湖南大学,2004.
[44]陈国栋,孙立宁,杜志江,纪军红.一种利用形状片段的物体检测方法[J].自动化学报,2011,39(04)：41-53
[45]于乃功,马春燕,林佳.基于双目视觉的关键点的检测方法及定位研究[J].计算机测量与控制.2011,26(07)：47-50.
[46]Perng Der-Baau, Chou Cheng-Chuan, Lee Shu-Ming. Design and development of a new machine vision wire bonding inspection system [J]. International Journal of Advanced Manufacturing Technology,2007,34(3-4):323-334.
[47]Lu Chi-Jie, Tsai Du-Ming. Independent component analysis-based defect detection in patterned liquid crystal display surfaces [J]. Image and Vision Computing,2008, 26(7):955-970.
[48]Chang Chuan-Yu, Li Chun-Hsi, Chang Jia-Wei, et al. An unsupervised neural network approach for automatic semiconductor wafer defect inspection [J]. Expert Systems with Applications,2009,36(1):950-958.
[49]Feng Zhongwei, Xu Chunguang, Xiao Dingguo, et al. In-pipe profile detection using circular structured light and its calibration technique[C]//Proceedings of the 2008 IEEE International Conference on Information and Automation, ICIA 2008,2008:1437-1441.
[50]Domae Y, Takauji H, Kaneko S, et al.3D measurement of flexible objects byrobust motion stereo[C]//Proceedings of the SICE Annual Conference,2007:740-743.
[51]刘巍,刘双军,贾振元,等.大型锻件尺寸在线测量系统研究[J].压电与声光.2011,33(5)：831-836.
[52]Yoshihiko N, Michihiro S, Hiroshi N, et al. Simple calibration algorithm for high-distortion-lens camera[J].IEEE Transactionson Pattern Analysis and Machine Intelligence,2012,14(11):1095-1099.
[53]钟球盛,胡广华,李静蓉.光学薄膜表面微细缺陷在线检测方法研究[J].机械设计与制造,2011,(10)：102-104..
[54]Zhang Zhe. A computer vision based sea search method using Kalman filter and CAMSHIFT[C]//The International Conference on Technological Advances in Electrical, Electronics and Computer Engineering, TAEECE 2013,2013,188-193.
[55]Pollefeys, Marc (Leuven K U), Koch Reinhard, et al. Self-calibration and metric reconstruction in spite of varying and unknown intrinsic camera parameters[J]. International Journal of Computer Vision,2010,32(1):7-25.
[56]唐启敬,田行斌,耿明超,周游,赵铁石.CCD视觉检测系统的整体标定[J].光学精密工程2011,08：1903-1910.
[57]魏振忠,张博,张广军.双机器人系统的快速手眼标定方法[J].计算机学报,2011,23(2)：1895-1902.
[58]张艳珍,欧宗瑛,薛斌党.一种基于斜率的摄像机畸变校正方法[J]小型微型计算机系统,2002,23(5)：625-627.
[59]贺科学,李树涛.基于两垂直相交线段的摄像机快速标定算法[J].仪器仪表学报,2013,34(8)：1696-1702.
[60]Zille, Pascal.Optimal control theory for multi-resolution problems in computer vision: Application to optical-flow estimation[C]//VISAPP 2012-Proceedings of the International Conference on Computer Vision Theory and Applications,2012,2:134-143.
[61]Hartley R. Lines and points in three views and the trifocal tensor [J].International Journal of Computer Vision,2007,22(2):125-140.
[62]Sturm P, Triggs B. A factorization based algorithm for multi-image projective structure and motion[C]//Proceedings of 4th European Conference on Computer Vision,2009:709-720.
[63]刘金颂,原思聪,张庆阳,刘道华.双目立体视觉中的摄像机标定技术研究[[J]].计算机工程与应用,2008,44(6)：237-239.
[64]王勇,吕征宇.一种基于空间矢量调制的矩阵变换器死区补偿方法[J].中国电机工程学报.2005,25(11)：42-45.
[65]高品,吴育峰,吴昆,孙继银.基于角点检测的图像匹配算法[J].仪器仪表学报,2013.34(8)：1717-1725.
[66]拜颖乾,赫东锋,刘波,等.表面贴装LED全自动编带机视觉检测系统研制[J].机械设计与制造,2013,08：104-109.
[67]张辉,张丽艳,陈江,赵转萍.基于平面模板自由拍摄的双目立体测量系统的现场标定[J].航空学报,2007,28(3)：695-701.
[68]胡辉,谭小群.基于视觉检测技术的机器人自动贴片系统设计[J].机械制造2013,02：141-146.
[69]Roger Y, Tsai. A versatile camera Calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV camera and lenses [J].IEEE Journal of Robotics and Automation.1987,3(4):323-344.
[70]Hermosilla T, Bermejo E, Balaguer A, et al. Non-linear fourth-order image interpolation for subpixel edge detection and localization [J]. Image and Vision Computing,2008,26(9): 1240-1248.
[71]Devernay F, Faugeras O. Straight lines have to be straight:automatic calibration and removal of distortion from scenes of structured environments [J]. Machine Vision and Applications, 2011,13(1):14-24.
[72]Hartley R, Zisserman A计算机视觉中的多视图几何[M].韦穗,译.安徽合肥：安徽大学出版社,2002：130-132.
[73]Cheng Songlin, Zhou Zude, Hu Wenjuan. Research of vision detection system on PCB [J].武汉理工大学学报：英文版,2006,28(S2)：714-717.
[74]李志敏,林越伟,黄俊,等.PCB走线检测的预处理算法[J].光学精密工程,2007,15(2)：272-276.
[75]叶亭,吴开华,马莉,等.一种基于线阵CCD技术印刷电路板胶片的尺寸及缺陷在线检测方法[J].光学与光电技术,2008,6(2)：74-77.
[76]解杨敏,刘强.高精度自动贴片机视觉系统定位算法研究[J].光学技术,2008,34(3)：449-451+454.
[77]张宏伟,张国雄,刘书桂,等.零件轮廓测量机安全监测系统的设计[J].机械工程学报, 2009,42(2)：212-215.
[78]Yuan Qiaoling, Ji Shiming, Xie Yi, et al. Auto detecting flaws in continuous punching by image analysis [J]. WSEAS Transactions on Information Science and Applications,2006, 13(7):1208-1213.
[79]邾继贵,郭磊,刘常杰,等.基于机器人的柔性电子检具测量系统[J].光学精密工程,2013,34(8)：1787-1793
[80]谭磊,王耀南,沈春生.输电线路除冰机器人障碍视觉检测识别算法[J].仪器仪表学报,2013.34(8).1656-1661.
[81]侯玉伟,李雷,赵彦伟,等.非接触式自动定尺切割系统[J].自动化应用,2011,(4)：19-20.
[82]Min C Shin. Comparison of edge detector performance through use in an object recognition task [J]. Computer Vision and Image Understanding,2011,(84):160-178.
[83]Mike Heath, Sudeep Sarkar, Thomas Sanocki. Comparison of edge detectors[J]. Computer Vision and Image Understanding,2008,69(1):38-54.
[84]Hermosilla T, Bermejo E, Balaguer A, Ruiz L A. Non-linear fourth-order image interpolation for subpixel edge detection and localization [J]. Image and Vision Computing, In Press, Accepted Manuscript, Available online,2008:1302-1308.
[85]田原嫄,谭庆昌.高斯型点扩散函数边缘拟合模型的研究[J].武汉理工大学学报,2011,33(11)：154-157
[86]Perna A, Morrone M C. The lowest spatial frequency channel determines brightness perception [J]. Vision Research,2007,47(10):1282-1291.
[87]Ye Jian, Fu Gongkang, Upendra P. Poudel. High-accuracy edge detection with Blurred Edge Model [J]. Image and Vision Computing,2005,23(5):453-467.
[88]田原嫄.基于数字图像的三维尺寸测量[D].吉林长春：吉林大学,2008.
[89]T. Hermosilla. E. Bermejo.Non-linear fourth-order image interpolation for subpixel edge detection and localization. Image and Vision Computing,2008,26,1240-1248
[90]Schindler K, Suter D. Object detection by global contour shape [J]. Pattern Recognition,2008, 41:3736-3748.
[91]Shotton J, Blake A, Cipolla. Multiscale categorical object recognition using contour fragments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30:1270-1281.
[92]库尔特·考夫卡著,李维译.格式塔心理学原理[M].北京：北京大学出版社,2010.12
[93]Lu C, Adluru N, Ling H, Zhu G, Latecki L J. Contour based object detection using part bundles[J]. Computer Vision and Image Understanding,2010,114:827-834.
[94]Sala P, Dickinson S J. Contour grouping and abstraction using simple part models[C]//In European Conference on Computer Vision,2010:603-616.
[95]Toshev A, Taskar B, Daniilidis K. Object detection via boundary structure segmentation[C]//In Computer Vision and Pattern Recognition,2010:950-957
[96]Martin D R, Fowlkes C, Malik J. Learning to detect natural image boundaries using brightness and texture[C]//In Neural Information Processing Systems,2012:1255-1262.
[97]陈国栋,孙立宁,杜志江.一种利用形状片段的物体检测方法[J].自动化学报,2011(04)：427-436
[98]郭强.基于轮廓编组和形状指导的目标检测算法研究[D].湖南长沙：国防科学技术大学,2011.
[99]Toshiro Kubota. Massively parallel networks for edge localization and contour integration-adaptable relaxation approach [J]. Neural Networks,2010,17(3):411-425.
[100]Scott Konishi, Alan L Yuille, James M Coughlan, Song Chun Zhu. Statistical edge detection: learning and evaluating edge cues [J]. IEEE Transactions on Pattern Analysis and Machineintelligence,2008,25(1):433-438.
[101]Wei Xu, Michael Jenkin, Yves Lesperance. A multi-channel algorithm for edge detection under varying lighting conditions[J].IEEE Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06),2010:1203-1209.
[102]Vidya Venkatachalam, Richard M Wasserman. Comprehensive investigation of Sub-pixel edge detection schemes in metrology [C]//Proceedings of SPIE-IS&T Electronic Imaging, SPIE 2011,65(11):200-211.
[103]李燕.视觉感知中的闭合轮廓提取方法研究[D].北京：北京交通大学,2011.
[104]温佩芝,黄锦芳,宁如花,吴晓军.基于张量投票的主动轮廓边缘提取[J].计算机工程2012,38(6)：216-219.
[105]孙秋成.基于机器视觉的轴径测量[D].吉林长春：吉林大学,2010.
[106]余洪山,王耀南.一种改进型Canny边缘检测算法[J].计算机工程与应用,2004,(20)：27-29.
[107]于忠党.基于支持向量机的机械零件计算机视觉检测若干关键技术的研究[D].吉林长春：吉林大学,2009.
[108]余忠贵,华学明,肖笑,李芳.铝合金变极性TIG焊熔池与阴极清理区视觉检测系统[J].上海交通大学学报：自科版,2012,(07)：1084-1087.
[109]张丽丽,罗斌,汤进.一种基于加权投票的图像匹配改进方法[J].计算机工程,2013(06)：34-37.
[110]谢孟龙,傅其凤,朱庆芹,等.承压零件气密性视觉检测系统的研发[J].现代制造工程2013,(01)：104-108.
[111]王煜.基于支持向量机的规则零件机器视觉检测技术研究[D].上海：东华大学,2011.
[112]张秀芝.基于计算机视觉的机械零件几何量精密测量技术研究[D].吉林长春：吉林大学,2009.
[113]姚立健.茄子收获机器人视觉系统和机械臂避障规划研究[D].江苏南京：南京农业大学,2008.
[114]张辉.医药输液的可见异物的视觉检测机器人技术研究[D].湖南长沙：湖南大学,2012.