计算机视觉中的相机标定相关问题研究与应用
|
摘要
计算机视觉的基本任务之一是从摄像机获取的二维图像信息出发来计算三维空间中物体的几何信息,由此来重建或识别物体,并进一步指导机器认知现实世界。在上述过程中,摄像机标定是一个无法回避的步骤。在传统的摄像机标定领域内,研究者们在相关方面开展了广泛的工作,取得了丰富的理论和实践应用成果,包括摄像机模型的建立,摄像机标定物的构建,标定物的识别定位,标定物上特征点的提取,标定算法模型的构建,摄像机姿态判断以及基于标定技术的各种具体应用等。本文在国家自然基金等科研项目的资助下,针对上述部分领域内存在的一些问题开展了相关研究,主要的研究内容包括以下几个方面：
1)提出了一种针对棋盘格标定物上特征点的自动提取方法。首先采用基于Gaussian平滑算子的改进型Wellner动态阈值算法实现了标定图像的二值化,然后采用Canny算子提取棋盘格的边缘信息,最后采用多次Radon变换与子图像划分相结合的方法,基于逐步推进,迭代求精的思路,实现了棋盘格上黑白相交处角点的自动提取,从而提高了摄像机的标定效率,并有助于实现一种全自动化的摄像机标定方法。角点提取过程中,采用图像分割与子图像处理的方法,在一定程度上纠正了由于镜头畸变带来的角点提取偏差。该算法提取的角点精度可以达到亚像素级,在存在遮挡的情况下仍然有能力预测到遮挡处的棋盘格角点坐标。实验表明,将采用本文方法提取到的角点信息应用于摄像机标定过程中后,最终得到的相机标定结果与采用现有成熟的人工交互方式的方法得到的结果精度相同。
2)提出了一种基于角点分类的多棋盘定位方法。详细分析了非极大邻域、高斯方差和窗口、角点阈值以及权重系数等初始参数对Harris算子提取角点的影响,给出了针对棋盘格角点提取时的参数选取准则。构建了一种自适应旋转尺度和规模尺度的用于稀释棋盘格伪角点密度的二值化模板。综合运用密度聚类算法(DBSCAN)和模糊C均值(FCM)聚类算法完成了棋盘格伪角点过滤与多棋盘定位,并采用Radon变换算法对各棋盘边缘位置进行了精确提取。实验表明该方法对于具有复杂大背景的多棋盘定位具有良好的效果,为利用单张图片进行摄像机标定提供了一种行之有效的途径。
3)采用摄像机标定技术实现了一种基于单目视频的低成本头部三维运动姿态跟踪与提取方法。该方法能够有效的提取头部姿态的6自由度(Degree of Freedom, DOF)运动参数。这些参数包括：分别沿X轴、Y轴、Z轴方向的平移运动参数Tx、Ty、Tz和分别绕X轴、Y轴、Z轴的旋转运动参数γ、β、α。在数据的后期处理中,采用了基于扩展卡尔曼滤波(Extanded Kalman flter, EKF)的算法对数据曲线进行了平滑和去噪,同时解决了由于缺帧等原因造成的祯间姿态跳跃问题。在实验中将采用本文方法提取到的数据与同步采用运动捕捉系统提取到的数据进行了比对,验证了本文方法的有效性和所得结果的准确性。
4)提出了一种基于三维眼部几何模型的人眼瞳孔中心点定位方法。本文中首先基于人眼的生理信息和二维眼部图像,构造了人眼的三维几何模型。在此基础上,将提取到的瞳孔边缘信息从二维空间转换到三维空间,然后采用边缘拟合的方法完成了瞳孔中心点的提取工作。具体过程中,基于人眼瞳孔边缘点属于同一空间平面这一属性,本文采用最小二乘法拟合出该空间平面,然后利用该平面将椭圆拟合问题转化为简单的圆形拟合问题,从而减少了拟合瞳孔时边缘信息的需求量,降低了边缘拟合时的复杂度。实验表明,当瞳孔的遮挡面积达到75%时,采用该方法仍然能够准确的提取出瞳孔中心点的位置坐标。
One of the basic tasks of computer vision is recognition and reconstruction of the 3D world by using the 2D image information which was acquired form the camera or any other image ac-quisition devices, and further guiding the machine to cognise the real world. Camera calibration is prerequisite to complete the task above. In the area of traditional camera calibration, researchers carried out extensive work and achieved rich theoretical results and applications, which including building the camera model, design and selection of the camera calibration targets, estimation of the camera pose, extraction of the feature points, build the camera calibration algorithm and achieved variety of specif c applications. Face to the existing problems in the above areas, and under the sup-port of the National Nature Science Foundation of China, this dissertation carried out systematic and in-depth studies. More details are as follows:
(1). Automatic extracting the feature points from the chessboard targets. We f rstly used the Wellner adaptive threshold with a Gaussian smoothing operator to f nish the image binarization, and then used the Canny operator to acquire the edge information. In the end, we comprehensively used the multi Radon Transform and sub-image partition methods to f nish the whole automatic corner extraction process based on the route of coarse to f ne. Our work helps to realize a totally automatic camera calibration process, and will improve the efficiency of the camera calibration. We also used an image segmentation and sub-image processing method to reduce the corner location errors, and the results show that we achieved sub-pixel location accuracy. In the f nal, the experiments show that the calibration results which used our corners are equal to the results achieved by the existed mature approaches.
(2). A multi-chessboards localization method was mentioned, which was based on the corner classif cation technique. First, we thoroughly analysis the function of the initial parameters belong to the Harris corner detection operator, respectively, and then the criterion of the parameter selec-tion were def ned. We constructed an adaptive rotation scale and size scale binary template, which used for diluting the density of the false corners. We comprehensively used the DBSCAN and FCM clustering algorithm to f nally f nish the false corners f ltering. In the end, the multi-chessboards border was extracted accurately by using the Radon Transform algorithm, respectively. The exper-iments showed that our approach especially suitable for locating multi-chessboards which have a wide and complex background, and also showed that our approach provided an effective way to calibrate a camera just by using a single image.
(3). A low-cost and monocular video based 3D head pose tracking and extraction method by using the camera calibration technique was presented. The method can effectively extract the 6 DOF motion parameters which include three translation parameters:Tx, Ty and Tz following the axis X, Y and Z, respectively, and three rotation parameters:y,β, a surrounding the axis X, Y and Z, respectively. In the end, the Extended Kalman Filter (EKF) algorithm was used to solved the problem of data jitter, and some missing-data also could be repaired. We contrasted our method with the motion capture system, the results showed that the method is effective and has the capability of extracting the 3D head pose accurately.
(4). Present a new human pupil center location method. We build a three-dimensional geo-metric model of the human eye by using the physiological parameters and 2D eye images. And then, the information of pupil edge was transform form 2D space to 3D space. Edge f tting method was used to acquire the pupil center. In detail, based on the 3D edge points of the pupil, we f rstly calculated the space plane by using the least square algorithm, and then we transform the ellipse f tting into circle f tting which could obviously reduce the demand of the edge information and the complexity of the f tting algorithm. The experiments showed that our method could still accurately extract the center coordinate of the pupil, when the block area arrived at 75%.
1)提出了一种针对棋盘格标定物上特征点的自动提取方法。首先采用基于Gaussian平滑算子的改进型Wellner动态阈值算法实现了标定图像的二值化,然后采用Canny算子提取棋盘格的边缘信息,最后采用多次Radon变换与子图像划分相结合的方法,基于逐步推进,迭代求精的思路,实现了棋盘格上黑白相交处角点的自动提取,从而提高了摄像机的标定效率,并有助于实现一种全自动化的摄像机标定方法。角点提取过程中,采用图像分割与子图像处理的方法,在一定程度上纠正了由于镜头畸变带来的角点提取偏差。该算法提取的角点精度可以达到亚像素级,在存在遮挡的情况下仍然有能力预测到遮挡处的棋盘格角点坐标。实验表明,将采用本文方法提取到的角点信息应用于摄像机标定过程中后,最终得到的相机标定结果与采用现有成熟的人工交互方式的方法得到的结果精度相同。
2)提出了一种基于角点分类的多棋盘定位方法。详细分析了非极大邻域、高斯方差和窗口、角点阈值以及权重系数等初始参数对Harris算子提取角点的影响,给出了针对棋盘格角点提取时的参数选取准则。构建了一种自适应旋转尺度和规模尺度的用于稀释棋盘格伪角点密度的二值化模板。综合运用密度聚类算法(DBSCAN)和模糊C均值(FCM)聚类算法完成了棋盘格伪角点过滤与多棋盘定位,并采用Radon变换算法对各棋盘边缘位置进行了精确提取。实验表明该方法对于具有复杂大背景的多棋盘定位具有良好的效果,为利用单张图片进行摄像机标定提供了一种行之有效的途径。
3)采用摄像机标定技术实现了一种基于单目视频的低成本头部三维运动姿态跟踪与提取方法。该方法能够有效的提取头部姿态的6自由度(Degree of Freedom, DOF)运动参数。这些参数包括：分别沿X轴、Y轴、Z轴方向的平移运动参数Tx、Ty、Tz和分别绕X轴、Y轴、Z轴的旋转运动参数γ、β、α。在数据的后期处理中,采用了基于扩展卡尔曼滤波(Extanded Kalman flter, EKF)的算法对数据曲线进行了平滑和去噪,同时解决了由于缺帧等原因造成的祯间姿态跳跃问题。在实验中将采用本文方法提取到的数据与同步采用运动捕捉系统提取到的数据进行了比对,验证了本文方法的有效性和所得结果的准确性。
4)提出了一种基于三维眼部几何模型的人眼瞳孔中心点定位方法。本文中首先基于人眼的生理信息和二维眼部图像,构造了人眼的三维几何模型。在此基础上,将提取到的瞳孔边缘信息从二维空间转换到三维空间,然后采用边缘拟合的方法完成了瞳孔中心点的提取工作。具体过程中,基于人眼瞳孔边缘点属于同一空间平面这一属性,本文采用最小二乘法拟合出该空间平面,然后利用该平面将椭圆拟合问题转化为简单的圆形拟合问题,从而减少了拟合瞳孔时边缘信息的需求量,降低了边缘拟合时的复杂度。实验表明,当瞳孔的遮挡面积达到75%时,采用该方法仍然能够准确的提取出瞳孔中心点的位置坐标。
One of the basic tasks of computer vision is recognition and reconstruction of the 3D world by using the 2D image information which was acquired form the camera or any other image ac-quisition devices, and further guiding the machine to cognise the real world. Camera calibration is prerequisite to complete the task above. In the area of traditional camera calibration, researchers carried out extensive work and achieved rich theoretical results and applications, which including building the camera model, design and selection of the camera calibration targets, estimation of the camera pose, extraction of the feature points, build the camera calibration algorithm and achieved variety of specif c applications. Face to the existing problems in the above areas, and under the sup-port of the National Nature Science Foundation of China, this dissertation carried out systematic and in-depth studies. More details are as follows:
(1). Automatic extracting the feature points from the chessboard targets. We f rstly used the Wellner adaptive threshold with a Gaussian smoothing operator to f nish the image binarization, and then used the Canny operator to acquire the edge information. In the end, we comprehensively used the multi Radon Transform and sub-image partition methods to f nish the whole automatic corner extraction process based on the route of coarse to f ne. Our work helps to realize a totally automatic camera calibration process, and will improve the efficiency of the camera calibration. We also used an image segmentation and sub-image processing method to reduce the corner location errors, and the results show that we achieved sub-pixel location accuracy. In the f nal, the experiments show that the calibration results which used our corners are equal to the results achieved by the existed mature approaches.
(2). A multi-chessboards localization method was mentioned, which was based on the corner classif cation technique. First, we thoroughly analysis the function of the initial parameters belong to the Harris corner detection operator, respectively, and then the criterion of the parameter selec-tion were def ned. We constructed an adaptive rotation scale and size scale binary template, which used for diluting the density of the false corners. We comprehensively used the DBSCAN and FCM clustering algorithm to f nally f nish the false corners f ltering. In the end, the multi-chessboards border was extracted accurately by using the Radon Transform algorithm, respectively. The exper-iments showed that our approach especially suitable for locating multi-chessboards which have a wide and complex background, and also showed that our approach provided an effective way to calibrate a camera just by using a single image.
(3). A low-cost and monocular video based 3D head pose tracking and extraction method by using the camera calibration technique was presented. The method can effectively extract the 6 DOF motion parameters which include three translation parameters:Tx, Ty and Tz following the axis X, Y and Z, respectively, and three rotation parameters:y,β, a surrounding the axis X, Y and Z, respectively. In the end, the Extended Kalman Filter (EKF) algorithm was used to solved the problem of data jitter, and some missing-data also could be repaired. We contrasted our method with the motion capture system, the results showed that the method is effective and has the capability of extracting the 3D head pose accurately.
(4). Present a new human pupil center location method. We build a three-dimensional geo-metric model of the human eye by using the physiological parameters and 2D eye images. And then, the information of pupil edge was transform form 2D space to 3D space. Edge f tting method was used to acquire the pupil center. In detail, based on the 3D edge points of the pupil, we f rstly calculated the space plane by using the least square algorithm, and then we transform the ellipse f tting into circle f tting which could obviously reduce the demand of the edge information and the complexity of the f tting algorithm. The experiments showed that our method could still accurately extract the center coordinate of the pupil, when the block area arrived at 75%.
引文
[1]马颂德,张正友.计算机视觉—理论与算法基础[M].北京：科学出版社,1998.
[2]徐光佑.计算机视觉[M].北京：清华大学出版社,1999.
[3]贾云得.机器视觉[M].北京：科学出版社,2003.
[4]艾海舟,武勃等译.图像处理分析与机器视觉(第二版)[M].北京：人民邮电出版社,2003.
[5]张广军.视觉测量[M].北京：科学出版社,2008.
[6]肖伯祥.运动捕捉数据处理、检索与重构方法研究[D].大连：大连理工大学,2009.
[7]Wei X P, Xiao B X, Zhang Q, Zhou C J. A Semantic Joint-Based NURBS Human Body Model for Motion Capture Data [J]. International Journal of Innovative Computing, Information and Control,2009,5(5):1351-1358.
[8]Zhang Z Y. A Flexible New Technique for Camera Calibration [J]. IEEE Transactions on pattern analysis and machine intelligence,2000,22(11):1330-1334.
[9]杨年峰,王季军,黄昌华等.直接线性变换法中标定对三维重构精度的影响[J].清华大学学报(自然科学版),2000,40(4)：24-27.
[10]Wang G H, Tsui H T, Hu Z Y, etc. Camera calibration and 3D reconstruction from a single view based on scene constraints [J]. Image and Vision Computing,2005,23(3):311-323.
[11]东方新锐运动捕捉相机标定系统www.dorealsoft.com.
[12]肖伯祥,魏小鹏,张强,周昌军.光学运动捕捉散乱数据处理的一种方法.系统仿真学报,2008,20(2)：382-385.
[13]Yu C S and Peng Q J. Robust recognition of checkerboard pattern for camera calibration [J]. Optical Engineering,2006,45(9):093201.
[14]Kato H and Billinghurst M. Marker tracking and HMD calibration for a video-based augmented reality conferencing system [C]. Proceedings of the 2nd International Workshop on Augmented Reality,1999:85-94.
[15]Zhang X, Fronz S and Navab N. Visual marker detectionand decoding in AR systems:a comparative study [C]. Proceedings of the International Symposium on Mixed and Augmented Reality,2002:97-106.
[16]Soh L M, Kittler J and Matas J. Empirical evaluation of a calibration chart detector [J]. Machine Vision and Applications,2001,12(6):305-325.
[17]Shi J and Tomasi C. Good feathures to track [C]. IEEE Conference on Computer Vision and Pattern Recon-gnition,1994.
[18]John M, and Whelan P F. Which Pattern? Biasing Aspects of Planar Calibration Patterns and Detection Methods [J]. Pattern Recognition Letters,2007,28(8):921-930.
[19]Heikkila J. Geometric camera calibration using circular control points [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1066-1077.
[20]Bouguet J Y. Camera Calibration Toolbox for Matlab. http://www.vision.caltech.edu/bouguetj /calib_doc/index.html.
[21]Bouguet J Y. Camera Calibration Toolbox for Matlab. http://www.vision.caltech.edu/bouguetj /calib_doc/download/index.html.
[22]陈胜勇,刘盛等.基于OpenCV的计算机视觉技术实现[M].北京：科学出版社,2008.
[23]Open Source Computer Vision Library. Cv照相机定标和三维重建. http://www.opencv.org.cn/
[24]Vladimir V and Alexander V. GML camera calibration toolbox. Laboratory of computer graphics at dep. of CS MSU, http://graphics.cs.msu.ru/en/science/research/calibration/matlab.
[25]Ha J. Automatic detection of calibration markers on a chessboard [J]. Optical Engineering,2007, 46(10):107203.
[26]Ha J. Automatic detection of chessboard and its applications [J]. Optical Engineering,2009,48(6):067205.
[27]Paulo J. Tavares D S and Vaz M A. Accurate subpixel corner detection on planar camera calibration targets [J]. Optical Engineering,2007,46(10):107205.
[28]Chen D and Zhang G. A new sub-pixel detector for X-corners in camera calibration targets [C]. The 13th International Conference in Center Europe on Computer Graphics, Visualization and Computer Vision 2005:97-100.
[29]刘阳成,朱枫.一种新的棋盘格图像角点检测算法[J].中国图象图形学报,2006,11(5)：656-660.
[30]王忠石,徐心和.棋盘格模板角点的自动识别与定位[J].中国图象图形学报,2007,12(4)：618-622.
[31]Wang Z, Wu W, Xu X and Xue D. Recognition and location of the internal corners of planar checkerboard calibration pattern image [J]. Applied Mathematics and Computation,2007(185)2:894-906.
[32]梁志敏,高洪明,王志江,吴林.摄像机标定中亚像素级角点检测算法[J].焊接学报,2006,27(2)：102-104.
[33]熊会元,宗志坚,余志,陈承鹤.基于凸包的棋盘格角点自动识别与定位方法[J].中山大学学报(自然科学版),2009,48(1)：1-5.
[34]袁萍,袁正鹏.一种应用于视觉测量标定的亚像素级特征点提取算法[J].现代机械,2003,4：14-15.
[35]胡海峰,侯晓微.一种自动检测棋盘角点的新算法[J].计算机工程,2007,30(14)：19-21.
[36]侯建辉,林意.自适应的Harris棋盘格角点检测算法[J].计算机工程与设计,2009,30(20)：4741-4743.
[37]Soh L M, Matas J and Kittlee J. Robust recgnition of calibration charts [C].6th International Conference on Image Processing and Its Applications,1997,2:487-491.
[38]Soh L M, Matas J and Kittlee J. Model acquisition and matching in tagged object recognition (TOR) [C]. European signal processing conference on theories and applications,1998:8-11.
[39]Gunilla B. Hierarchical chamfer matching:a parametric edge matching algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(6):849-865.
[40]Bunke H and Messmer B T. Efficient attributed graph matching and its applications to image analysis [C]. ICIAP,1995:45-55.
[41]Martin R, Davide S and Roland S. Automatic Detection of Checkerboards on Blurred and Distorted Images [C]. IEEE/RSJ International Conference on Intelligent Robots and Systems,2008:22-26.
[42]OCamCalib Toolbox. http://asl.epf.ch/scaramuz/research/Davide_Scaramuzza_fles/Research/Ocam Calib_Tutorial.htm
[43]Shu C,Alan B and Mark F. Automatic Grid Finding in Calibration Patterns Using Delaunay Triangulation. Technical Report, NRC-46497/ERB-1104.
[44]郑志刚.高精度摄像机标定和鲁棒立体匹配[D].中国科技大学,2008.
[45]Zhang X and Navab N. Tracking and pose estimation for computer assisted localization inindustrial envi-ronments [C]. Fifth IEEE Workshop on Applications of Computer Vision,2000:214-221.
[46]Bencina R, Kaltenbrunner M and Jorda S. Improved Topological Fiducial Tracking in the reacTIVision System [C]. Proceedings of The IEEE Computer Society Conference on Computer Vision and Pattern Recog-nition,2005:99-106.
[47]Shi J and Tomasi C. Good features to track [C]. IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR'94),1994:593-600.
[48]David C and Andrew W F. Reliable f ducial detection in natural scenes [C]. Proceedings of the 8th European Conference on Computer Vision,2004:469-480.
[49]Kou X, wang Z, Chen M and Ye S. Fully automatic algorithm for region of interest location in camera calibration [J]. Optical Engineering,2002,41(6):1220-1226.
[50]闫焱,刘允才.复杂背景下的角点检测[J].微型电脑应用,2009,25(1)：51-53.
[51]林国余,张为公.一种大场景下的棋盘靶标角点自动定位算法.信息与控制[J],2008,36(6)：740-746.
[52]Zhang X, Fronz S and Navab N. Visual Marker Detection and Decoding in AR Systems:A Comparative Study [C].Proceedings of the International Symposium on Mixed and Augmented Reality,2002:97-106.
[53]ARtoolkit. http://www.hitl.washington.edu/artoolkit/
[54]ARtag system. http://www.artag.net/
[55]Koller D, Klinker G, Rose E, Breen D, Whitaker R, and Tuceryan M. Real-time vision-based camera track-ing for augmented reality application [C]. ACM Symposium on Virtual Reality Software and Technology, Switzerland,1997:87-94.
[56]Zhang X and Navab N. Tracking and Pose Estimation for Computer Assisted Localization in Industrial Environments [C]. The Fifth IEEE Workshop on Applications of Computer Vision,2000:214-221.
[57]Maidi M and Didier J. A performance study for camera pose estimation using visual marker based tracking [J]. Machine Vision and Applications,2010,21:365-376.
[58]Animazoo mechanical motion capture system. http://www.animazoo.com
[59]Polhemus electromagnetic motion tracking system. http://www.polhemus.com
[60]Xsens 3D motion tracking system based on miniature MEMS inertial sensor (IMU) technology. http://www.xsens.com
[61]Innalabs 3DSuit motion capture system. http://www.3dsuit.com
[62]VICON motion capture system. http://www.vicon.com
[63]MotionAnalysis 3D passive optical motion capture system. http://www.motionanalysis.com
[64]东方新锐DVMC-8820光学运动捕捉系统.大连东锐软件有限公司,http://www.dorealsoft.com/product/
[65]Project Natal by Microsoft. http://www.xbox.com/en-us/live/projectnatal/
[66]TrackIR headpose tracking systemy by NaturalPoint. http://www.naturalpoint.com/trackir/
[67]Optitrack motion capture system. http://www.optitrack.com
[68]北京迪生DS-T160动作捕捉技术http://www.disontech.com.cn
[69]PhaseSpace optical motion capture systems. http://www.phasespace.com/
[70]Worldviz PPT motion tracking system.http：//www.worldviz.com/products/ppt/index.html
[71]Chen X. Design of Many-camera Tracking System for Scalability and Efficient Resource Allocation [D]. Stanford University,2002.
[72]Hoff W A, Nguyen K and Lyon T. Computer vision-based registration techniques for augmented reality [C]. Proceedings of Intelligent Robots and Computer Vision XV, SPIE,1996,2904:538-548.
[73]Hoff W A and Lyon T. Analysis of head pose accuracy in augmented reality [J]. IEEE Transactions on Visualization and Computers,2000,6(4):1-16.
[74]State A, Hirota G, Chen D, Garrett W, etc. Superior augmented reality registration by integrating landmark tracking and magnetic tracking [C]. Computer Graphics, SIGGRAPH Proceedings,1996:429-438.
[75]Cho Y, Lee W and Neumann U. A multi-ring color f ducial system and intensity-invariant detection method for scalable f ducial-tracking augmented reality [C]. International Workshop on Augmented Reality,1998:1-15.
[76]Yoon J, Park J and Kim C. Increasing Camera Pose Estimation Accuracy Using Multiple Markers [C]. Lecture Notes in Computer Science:Advances in Artif cial Reality and Tele-Existence,2006,4282:239-248.
[77]Hirokazu K and Mark B. Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System [C]. Proceedings of the 2nd IEEE and ACM International Workshop on Augmented Reality,1999:85-94.
[78]Wagner D and Schmalsteig I. First steps towards handheld augmented reality [C]. Proceedings of the 7th International Conference on Wearable Computers,2003:127-135.
[79]Park K S and Lim C J. An efficient camera calibration method for vision-based head tracking [J]. Int. J. Human-Computer Studies,2000,52:879-898.
[80]Ulrich W, Georg L, Pierre B and Heiko N. Detection of Head Pose and Gaze Direction for Human-Computer Interaction [C]. Lecture Notes in Computer Science:Perception and Interactive Technologies, 2006,4021:9-19.
[81]Beymer D J. Face recognition under varying pose [C]. IEEE Conference on Computer Vision and Pattern Recognition,1994:756-761.
[82]Niyogi S and Freeman W. Example-based head tracking [C].2nd International Conference on Automatic Face and Gesture Recognition,1996:374-378.
[83]陈华杰,韦巍.基于关联子区域映射的多姿态人脸识别[J].中国图形图像学报,2007,12(7)：1254-1260.
[84]Lee H and Kim D. Pose invariant face recognition using linear pose transformation in feature space [C]. Lecture Notes in Computer Science:Computer Vision in Human-Computer Interaction,2004,3058:211-220.
[85]Okada K and Malsburg C. Pose-invariant face recognition with parametric linear subspaces [C]. Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002:64-69.
[86]朱长仁.复杂背景下的多姿态人脸识别技术研究[D].国防科学技术大学,2001.
[87]Zhou C J, Wei X P and Zhang Q. Facial Expression Recognition Based on Features Fusion [C]. INFOR-MATION TECHNOLOGY FOR MANUFACTURING SYSTEMS, PTS 1 AND 2,2010:1253-1259.
[88]Erik M and Mohan M T. Head Pose Estimation in Computer Vision:A Survey [J]. IEEE Transactions on circuits and systems for video technology,2009,19(2):261-272.
[89]Wu J and Mohan M T. A two-stage head pose estimation framework and evaluation [J]. Pattern Recognition, 2008,41(3):1138-1158.
[90]Andrew G and Roberto C. Determining the gaze of faces in images [J]. Image and Vision Computing,1994, 12(10):639-647.
[91]Heinzmann J and Zelinsky A.3-D facial pose and gaze point estimation using a robust real-time tracking paradigm [C]. Third IEEE International Conference on Automatic Face and Gesture Recognition,1998:142-147.
[92]Wang J and Sung E. EM enhancement of 3D head pose estimated by point at inf nity [J]. Image and Vision Computing,2007,25(12):1864-1874.
[93]Cordea M, Petriu E, Georganas N, Petriu D, and Whalen T. Real-time 2(1/2)-D head pose recovery for model-based video-coding [J]. IEEE Trans. Instrum. Meas.,2001,50(4):1007-1013.
[94]Ji Q and Hu R.3D Face pose estimation and tracking from a monocular camera [J]. Image and Vision Computing,2002,20(7):499-511.
[95]Hirotake Y, Akira U, Kenichi H and Masahiko Y. A body-mounted camera system for head-pose estimation and user-view image synthesis [J]. Image and Vision Computing,2007,25(12):1848-1855.
[96]Canton-Ferrer C, Casas J R, Pardas M. Head Orientation Estimation Using Particle Filtering in Multiview Scenarios [C]. Lecture Notes in Computer Science:Multimodal Technologies for Perception of Humans, 2008,4625:317-327.
[97]Yip B and Jin J S.3D Reconstruction of a Human Face with Monocular Camera Based on Head Movement [C]. Proceedings of the Pan-Sydney area workshop on Visual information processing,2004:99-103.
[98]Choi K N, Worthington P L and Hancock E R. Estimating facial pose using shape-from-shading [J]. Pattern Recognition Letters,2002,23(5):533-548.
[99]Zhu Y and Fujimura K.3D Head Pose Estimation with Optical Flow and Depth Constraints [C]. Fourth International Conference on 3-D Digital Imaging and Modeling,2003,211-216.
[100]梁国远.基于三维模型的单目图像序列人脸姿态跟踪[D].北京大学,2005.
[101]Lopez R and Huang T S.3D Head pose computation from 2D images:template versus features [C]. Proceedings of IEEE International Conference on Image Processing,1995,2:599-602.
[102]Shimizu I, Zhang Z, Akamatsu S and Deguchi K. Head pose determination from one image using a generic model [C]. Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, 1998:100-105.
[103]Marco L C and Stan S. Fast, Reliable head tracking under varying illumination:an approach based on reg-istration of texture-mapped 3D models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(4):322-336.
[104]Kwon O, Chun J and Park P. Cylindrical Model-Based Head Tracking and 3D Pose Recovery from Sequen-tial Face Images [C]. Proceedings of the 2006 International Conference on Hybrid Information Technology, 2006:135-139.
[105]Chun J, Kwon O and Park P. A robust 3D face pose estimation and facial expression control for vision-based animation [C]. Lecture Notes in Computer Science:Advances in Multimedia Modeling,2007, 4351:968-977.
[106]Ryu W and Kim D. Robust 3D Head Tracking and Its Applications [C]. Lecture Notes in Computer Sci-ence:Advances in Biometrics,2007,4642:700-708
[107]尹宝才,张壮,孙艳丰,王成章.基于三维形变模型的多姿态人脸识别[J].北京工业大学学报,2007,33(3)：320-325.
[108]Yang R and Zhang Z. Model-based head pose tracking with stereo vision [C]. Proceedings of IEEE Inter-national Conference on Automatic Face and Gesture Recognition,2002:255-260.
[109]刘志镜,李夏忠,武芒.基于三维模型的多姿态人脸识别[J].西安电子科技大学学报(自然科学版),2004,31(2)：218-222.
[110]胡异丁,朱斌,甘俊英.基于三维人脸建模的多姿态人脸识别[J].计算机工程与设计,2009,30(7)：1728-1731.
[111]Huttenlocker D P and Ullman S. Recognizing solid objects by alignment with an image [J]. International Journal of Computer Vision,1990,5(2):195-212.
[112]宋杰.基于三维模型的单目图像序列头部姿态跟踪[D].浙江大学,2008.
[113]http://en.wikipedia.org/wiki/Radon_transform
[114]Tabbone S, Wendling L and Salmon J P. A new shape descriptor defned on the Radon transform [J]. Computer Vision and Image Understanding,2007,102:42-51.
[115]Vladimir V and Alexander V. Recommendations for taking calibration photos. http://graphics2.cs.msu.ru/ru/science/research/calibration/recommendations.
[116]李玉山.数字视觉视频技术[M].西安：西安电子科技大学出版社,2006.
[117]章毓晋.图像工程(上册)[M].北京：清华大学出版社,1999.
[118]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[119]冈萨雷斯.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2005.
[120]张广军.机器视觉[M].北京：科学出版社,2005.
[121]Claus D. Video-based surveying for large outdoor environments. First Year Report, University of Oxford, 2004.
[122]Harris C and Stephens M. A combined corner and edge detector [C]. Proceedings of The Fourth Alvey Vision Conference,1988:147-151.
[123]Moravec H. Obstacle avoidance and navigation in the realworld by a seeing robot rover. Technical Report CMU-RI-TR-3, Carnegie-Mellon University, Robotics Institute,1980.
[124]Parks D and Gravel J. http://www.cim.mcgill.ca/-dparks/CornerDetector/harris.htm
[125]谷萩隆嗣.语音与图像的数字信号处理[M].北京：科学出版社,2003.
[126]Parks D and Gravel J. http://www.cim.mcgill.ca/dparks/CornerDetector/mainApplet.htm
[127]Chen D and Zhang G. A new sub-pixel detector for x-corners in camera calibration targets [C]. WSCG (Short Papers),2005:97-100.
[128]刘群根.基于梯度与对称度提取棋盘格角点及角点递推定位[J].测控技术,2008,27(1)：7-9.
[129]Yu C and Peng Q. Robust recognition of checkerboard pattern for camera calibration [J]. Optical Engineer-ing,2006,45(9):093201.
[130]刘阳,王福利,常玉清,吕哲.黑白棋盘格角点检测算法[J].东北大学学报(自然科学版),2007,28(7)：1090-1093.
[131]王忠石,韩晓微,徐心和.棋盘格模板角点的自动定位[J].东北大学学报(自然科学版),2006,27(9)：949-952.
[132]张铁楠,涂亚庆,王德超.针对棋盘格角点快速检测的一种新方法[J].计算机工程与应用,2008,44(31)：236-238.
[133]Kaufman L and Rousseeuw P J. Finding groups in data:an introduction to cluster analysis [M]. San Francisco:John Wiley and Sons,1990.
[134]杨风召.高维数据挖掘技术研究[M].南京：东南大学出版社,2007.
[135]Ester M, Kriegel H, Sander J and Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise [C]. Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining,1996:226-231.
[136]Bezdek J C. Pattern recognition with fuzzy objective algorithm [M]. New York:Plenum Press,1981.
[137]Pal N R and Bezdek J C. On cluster validity for the fuzzy c-means model [J]. IEEE Transactions on Fuzzy Systems,1995,3(3):370-379.
[138]高新波,裴继红,谢维信.模糊c-均值聚类算法中加权指数m的研究[J].电子学报,2000,28(4)：80-83.
[139]王建维.制造单元构建的关键技术研究[D].大连：大连理工大学,2009.
[140]王建维,魏小鹏,李睿Evolutionary algorithms with preference for manufacturing cells formation [J]机械工程学报(英文版),2008,21(1)：111-115.
[141]Hartley R and Zisserman A. Multiple view geometry in computer vision [M]. London:Cambridge Univer-sity Press,2003.
[142]Brown D C. Close-range camera calibration [J]. Photogrammetric Engineering,1971,37(8):855-866.
[143]Wei G and Ma S. Implicit and explicit camera calibration:Theory and experiments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,16(5):469-480,1994.
[144]http://research.microsoft.com/en-us/um/people/zhang/Calib/
[145]Kahnan R E. A new approach to linear f ltering and prediction problems [J]. Transactions of the ASME-Journal of basic engineering (Series D),1960,82:35-45.
[146]Ferrario V F, Sforza C, Serrao G, Grassi G and Mossi E. Active range of motion of the head and cervical spine:a three-dimensional investigation in healthy young adults [J]. Journal of Orthopaedic Research,2002, 20(1):122-129.
[147]文成林.多尺度动态建模理论及应用[M].北京：科学出版社,2007.
[148]Young L and Sheena D. Methods & designs:survey of eye movement recording methods [J]. Behav Res Methods Instrum 1975,7(5):397-429.
[149]van der Geest JN, Frens MA. Recording eye movements with videooculography and scleral search coils:a direct comparison of two methods [J]. J Neurosci Methods,2002,114(2):185-195.
[150]Morimoto C H and Mimica MRM. Eye gaze tracking techniques for interactive applications [J]. Comput Vis Image Und,2005,98(1):4-24.
[151]Villanueva A, Cabeza R and Porta S. Eye tracking:pupil orientation geometrical modeling [J]. Image Vision Comput,2006,24(7):633-679.
[152]Kim S C, Nam K C, Lee W S, etc. A new method for accurate and fast measurement of 3D eye movements [J]. Med Eng Phys,2006,28(l):82-89.
[153]Fetter M.3D-analysis of eye movements [J]. Clin Neurophysiol,2000,3(4):247-250.
[154]Schreiber K and Haslwanter T. Improving calibration of 3-D video oculography systems [J]. IEEE Trans Biomed Eng,2004,51(4):676-679.
[155]Hatamian M and Anderson D J. Design considerations for a real-time ocular counterroll instrument[J]. IEEE Trans Biomed Eng,1983,30:278-288.
[156]Sung K and Anderson D J. Analysis of two video eye tracking algorithms [C]. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society,1991,13(5):1949-1450.
[157]Daniela I and Matteo L. Parametric characterization of the form of the human pupil from blurred noisy images [J]. Comput Methods Programs Biomed,2005,77(1):39-48.
[158]Ebisawa Y. Improved video-based eye-gaze detection method [J]. IEEE Trans Instrum Meas,1998, 47(4):948-955.
[159]Yoo D H and Chung M J. RA novel non-intrusive eye gaze estimation using cross-ratio under large head motion [J]. Comput Vision Image Und,2005,98(1):25-51.
[160]Zhu D J, Steven T M and Theodore R. Robust pupil center detection using a curvature algorithm [J]. Comput Methods Programs Biomed,1999,59(3):145-157.
[161]Moore S T, Haslwanter T, Curthoys I S, etc. A geometric basis for measurement of three-dimensional eye position using image processing [J]. Vision Res,1996,36(3):445-459.
[162]Kim J and Park K. An image processing method for improved pupil size estimation accuracy [C]. Proceed-ings of the 25th Annual Imitational Conference of the IEEE EMBS,2003,9:17-21.
[163]葛坚.眼科学[M].北京：人民卫生出版社(第二版),2002.
[164]Guestrin E D and Eizenman M. General theory of remote gaze estimation using the pupil center and corneal ref ections [J]. IEEE Trans Biomed Eng,2006,53(6):1124-1133.
[165]Zhou Z H and Geng X. Projection functions for eye detection [J]. Pattern Recogn,2004,37(5):1049-1056.
[166]Frosio I and Borghese N A. Real-time accurate circle f tting with occlusions [J]. Pattern Recognition,2008, 41(3):1041-1055.
[167]Zheng Z L, Yang J and Yang L M. A robust method for eye features extraction on color image [J]. Pattern Recognition Letters,2005,26(14):2252-2261.
[2]徐光佑.计算机视觉[M].北京：清华大学出版社,1999.
[3]贾云得.机器视觉[M].北京：科学出版社,2003.
[4]艾海舟,武勃等译.图像处理分析与机器视觉(第二版)[M].北京：人民邮电出版社,2003.
[5]张广军.视觉测量[M].北京：科学出版社,2008.
[6]肖伯祥.运动捕捉数据处理、检索与重构方法研究[D].大连：大连理工大学,2009.
[7]Wei X P, Xiao B X, Zhang Q, Zhou C J. A Semantic Joint-Based NURBS Human Body Model for Motion Capture Data [J]. International Journal of Innovative Computing, Information and Control,2009,5(5):1351-1358.
[8]Zhang Z Y. A Flexible New Technique for Camera Calibration [J]. IEEE Transactions on pattern analysis and machine intelligence,2000,22(11):1330-1334.
[9]杨年峰,王季军,黄昌华等.直接线性变换法中标定对三维重构精度的影响[J].清华大学学报(自然科学版),2000,40(4)：24-27.
[10]Wang G H, Tsui H T, Hu Z Y, etc. Camera calibration and 3D reconstruction from a single view based on scene constraints [J]. Image and Vision Computing,2005,23(3):311-323.
[11]东方新锐运动捕捉相机标定系统www.dorealsoft.com.
[12]肖伯祥,魏小鹏,张强,周昌军.光学运动捕捉散乱数据处理的一种方法.系统仿真学报,2008,20(2)：382-385.
[13]Yu C S and Peng Q J. Robust recognition of checkerboard pattern for camera calibration [J]. Optical Engineering,2006,45(9):093201.
[14]Kato H and Billinghurst M. Marker tracking and HMD calibration for a video-based augmented reality conferencing system [C]. Proceedings of the 2nd International Workshop on Augmented Reality,1999:85-94.
[15]Zhang X, Fronz S and Navab N. Visual marker detectionand decoding in AR systems:a comparative study [C]. Proceedings of the International Symposium on Mixed and Augmented Reality,2002:97-106.
[16]Soh L M, Kittler J and Matas J. Empirical evaluation of a calibration chart detector [J]. Machine Vision and Applications,2001,12(6):305-325.
[17]Shi J and Tomasi C. Good feathures to track [C]. IEEE Conference on Computer Vision and Pattern Recon-gnition,1994.
[18]John M, and Whelan P F. Which Pattern? Biasing Aspects of Planar Calibration Patterns and Detection Methods [J]. Pattern Recognition Letters,2007,28(8):921-930.
[19]Heikkila J. Geometric camera calibration using circular control points [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1066-1077.
[20]Bouguet J Y. Camera Calibration Toolbox for Matlab. http://www.vision.caltech.edu/bouguetj /calib_doc/index.html.
[21]Bouguet J Y. Camera Calibration Toolbox for Matlab. http://www.vision.caltech.edu/bouguetj /calib_doc/download/index.html.
[22]陈胜勇,刘盛等.基于OpenCV的计算机视觉技术实现[M].北京：科学出版社,2008.
[23]Open Source Computer Vision Library. Cv照相机定标和三维重建. http://www.opencv.org.cn/
[24]Vladimir V and Alexander V. GML camera calibration toolbox. Laboratory of computer graphics at dep. of CS MSU, http://graphics.cs.msu.ru/en/science/research/calibration/matlab.
[25]Ha J. Automatic detection of calibration markers on a chessboard [J]. Optical Engineering,2007, 46(10):107203.
[26]Ha J. Automatic detection of chessboard and its applications [J]. Optical Engineering,2009,48(6):067205.
[27]Paulo J. Tavares D S and Vaz M A. Accurate subpixel corner detection on planar camera calibration targets [J]. Optical Engineering,2007,46(10):107205.
[28]Chen D and Zhang G. A new sub-pixel detector for X-corners in camera calibration targets [C]. The 13th International Conference in Center Europe on Computer Graphics, Visualization and Computer Vision 2005:97-100.
[29]刘阳成,朱枫.一种新的棋盘格图像角点检测算法[J].中国图象图形学报,2006,11(5)：656-660.
[30]王忠石,徐心和.棋盘格模板角点的自动识别与定位[J].中国图象图形学报,2007,12(4)：618-622.
[31]Wang Z, Wu W, Xu X and Xue D. Recognition and location of the internal corners of planar checkerboard calibration pattern image [J]. Applied Mathematics and Computation,2007(185)2:894-906.
[32]梁志敏,高洪明,王志江,吴林.摄像机标定中亚像素级角点检测算法[J].焊接学报,2006,27(2)：102-104.
[33]熊会元,宗志坚,余志,陈承鹤.基于凸包的棋盘格角点自动识别与定位方法[J].中山大学学报(自然科学版),2009,48(1)：1-5.
[34]袁萍,袁正鹏.一种应用于视觉测量标定的亚像素级特征点提取算法[J].现代机械,2003,4：14-15.
[35]胡海峰,侯晓微.一种自动检测棋盘角点的新算法[J].计算机工程,2007,30(14)：19-21.
[36]侯建辉,林意.自适应的Harris棋盘格角点检测算法[J].计算机工程与设计,2009,30(20)：4741-4743.
[37]Soh L M, Matas J and Kittlee J. Robust recgnition of calibration charts [C].6th International Conference on Image Processing and Its Applications,1997,2:487-491.
[38]Soh L M, Matas J and Kittlee J. Model acquisition and matching in tagged object recognition (TOR) [C]. European signal processing conference on theories and applications,1998:8-11.
[39]Gunilla B. Hierarchical chamfer matching:a parametric edge matching algorithm [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1988,10(6):849-865.
[40]Bunke H and Messmer B T. Efficient attributed graph matching and its applications to image analysis [C]. ICIAP,1995:45-55.
[41]Martin R, Davide S and Roland S. Automatic Detection of Checkerboards on Blurred and Distorted Images [C]. IEEE/RSJ International Conference on Intelligent Robots and Systems,2008:22-26.
[42]OCamCalib Toolbox. http://asl.epf.ch/scaramuz/research/Davide_Scaramuzza_fles/Research/Ocam Calib_Tutorial.htm
[43]Shu C,Alan B and Mark F. Automatic Grid Finding in Calibration Patterns Using Delaunay Triangulation. Technical Report, NRC-46497/ERB-1104.
[44]郑志刚.高精度摄像机标定和鲁棒立体匹配[D].中国科技大学,2008.
[45]Zhang X and Navab N. Tracking and pose estimation for computer assisted localization inindustrial envi-ronments [C]. Fifth IEEE Workshop on Applications of Computer Vision,2000:214-221.
[46]Bencina R, Kaltenbrunner M and Jorda S. Improved Topological Fiducial Tracking in the reacTIVision System [C]. Proceedings of The IEEE Computer Society Conference on Computer Vision and Pattern Recog-nition,2005:99-106.
[47]Shi J and Tomasi C. Good features to track [C]. IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR'94),1994:593-600.
[48]David C and Andrew W F. Reliable f ducial detection in natural scenes [C]. Proceedings of the 8th European Conference on Computer Vision,2004:469-480.
[49]Kou X, wang Z, Chen M and Ye S. Fully automatic algorithm for region of interest location in camera calibration [J]. Optical Engineering,2002,41(6):1220-1226.
[50]闫焱,刘允才.复杂背景下的角点检测[J].微型电脑应用,2009,25(1)：51-53.
[51]林国余,张为公.一种大场景下的棋盘靶标角点自动定位算法.信息与控制[J],2008,36(6)：740-746.
[52]Zhang X, Fronz S and Navab N. Visual Marker Detection and Decoding in AR Systems:A Comparative Study [C].Proceedings of the International Symposium on Mixed and Augmented Reality,2002:97-106.
[53]ARtoolkit. http://www.hitl.washington.edu/artoolkit/
[54]ARtag system. http://www.artag.net/
[55]Koller D, Klinker G, Rose E, Breen D, Whitaker R, and Tuceryan M. Real-time vision-based camera track-ing for augmented reality application [C]. ACM Symposium on Virtual Reality Software and Technology, Switzerland,1997:87-94.
[56]Zhang X and Navab N. Tracking and Pose Estimation for Computer Assisted Localization in Industrial Environments [C]. The Fifth IEEE Workshop on Applications of Computer Vision,2000:214-221.
[57]Maidi M and Didier J. A performance study for camera pose estimation using visual marker based tracking [J]. Machine Vision and Applications,2010,21:365-376.
[58]Animazoo mechanical motion capture system. http://www.animazoo.com
[59]Polhemus electromagnetic motion tracking system. http://www.polhemus.com
[60]Xsens 3D motion tracking system based on miniature MEMS inertial sensor (IMU) technology. http://www.xsens.com
[61]Innalabs 3DSuit motion capture system. http://www.3dsuit.com
[62]VICON motion capture system. http://www.vicon.com
[63]MotionAnalysis 3D passive optical motion capture system. http://www.motionanalysis.com
[64]东方新锐DVMC-8820光学运动捕捉系统.大连东锐软件有限公司,http://www.dorealsoft.com/product/
[65]Project Natal by Microsoft. http://www.xbox.com/en-us/live/projectnatal/
[66]TrackIR headpose tracking systemy by NaturalPoint. http://www.naturalpoint.com/trackir/
[67]Optitrack motion capture system. http://www.optitrack.com
[68]北京迪生DS-T160动作捕捉技术http://www.disontech.com.cn
[69]PhaseSpace optical motion capture systems. http://www.phasespace.com/
[70]Worldviz PPT motion tracking system.http：//www.worldviz.com/products/ppt/index.html
[71]Chen X. Design of Many-camera Tracking System for Scalability and Efficient Resource Allocation [D]. Stanford University,2002.
[72]Hoff W A, Nguyen K and Lyon T. Computer vision-based registration techniques for augmented reality [C]. Proceedings of Intelligent Robots and Computer Vision XV, SPIE,1996,2904:538-548.
[73]Hoff W A and Lyon T. Analysis of head pose accuracy in augmented reality [J]. IEEE Transactions on Visualization and Computers,2000,6(4):1-16.
[74]State A, Hirota G, Chen D, Garrett W, etc. Superior augmented reality registration by integrating landmark tracking and magnetic tracking [C]. Computer Graphics, SIGGRAPH Proceedings,1996:429-438.
[75]Cho Y, Lee W and Neumann U. A multi-ring color f ducial system and intensity-invariant detection method for scalable f ducial-tracking augmented reality [C]. International Workshop on Augmented Reality,1998:1-15.
[76]Yoon J, Park J and Kim C. Increasing Camera Pose Estimation Accuracy Using Multiple Markers [C]. Lecture Notes in Computer Science:Advances in Artif cial Reality and Tele-Existence,2006,4282:239-248.
[77]Hirokazu K and Mark B. Marker Tracking and HMD Calibration for a Video-based Augmented Reality Conferencing System [C]. Proceedings of the 2nd IEEE and ACM International Workshop on Augmented Reality,1999:85-94.
[78]Wagner D and Schmalsteig I. First steps towards handheld augmented reality [C]. Proceedings of the 7th International Conference on Wearable Computers,2003:127-135.
[79]Park K S and Lim C J. An efficient camera calibration method for vision-based head tracking [J]. Int. J. Human-Computer Studies,2000,52:879-898.
[80]Ulrich W, Georg L, Pierre B and Heiko N. Detection of Head Pose and Gaze Direction for Human-Computer Interaction [C]. Lecture Notes in Computer Science:Perception and Interactive Technologies, 2006,4021:9-19.
[81]Beymer D J. Face recognition under varying pose [C]. IEEE Conference on Computer Vision and Pattern Recognition,1994:756-761.
[82]Niyogi S and Freeman W. Example-based head tracking [C].2nd International Conference on Automatic Face and Gesture Recognition,1996:374-378.
[83]陈华杰,韦巍.基于关联子区域映射的多姿态人脸识别[J].中国图形图像学报,2007,12(7)：1254-1260.
[84]Lee H and Kim D. Pose invariant face recognition using linear pose transformation in feature space [C]. Lecture Notes in Computer Science:Computer Vision in Human-Computer Interaction,2004,3058:211-220.
[85]Okada K and Malsburg C. Pose-invariant face recognition with parametric linear subspaces [C]. Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002:64-69.
[86]朱长仁.复杂背景下的多姿态人脸识别技术研究[D].国防科学技术大学,2001.
[87]Zhou C J, Wei X P and Zhang Q. Facial Expression Recognition Based on Features Fusion [C]. INFOR-MATION TECHNOLOGY FOR MANUFACTURING SYSTEMS, PTS 1 AND 2,2010:1253-1259.
[88]Erik M and Mohan M T. Head Pose Estimation in Computer Vision:A Survey [J]. IEEE Transactions on circuits and systems for video technology,2009,19(2):261-272.
[89]Wu J and Mohan M T. A two-stage head pose estimation framework and evaluation [J]. Pattern Recognition, 2008,41(3):1138-1158.
[90]Andrew G and Roberto C. Determining the gaze of faces in images [J]. Image and Vision Computing,1994, 12(10):639-647.
[91]Heinzmann J and Zelinsky A.3-D facial pose and gaze point estimation using a robust real-time tracking paradigm [C]. Third IEEE International Conference on Automatic Face and Gesture Recognition,1998:142-147.
[92]Wang J and Sung E. EM enhancement of 3D head pose estimated by point at inf nity [J]. Image and Vision Computing,2007,25(12):1864-1874.
[93]Cordea M, Petriu E, Georganas N, Petriu D, and Whalen T. Real-time 2(1/2)-D head pose recovery for model-based video-coding [J]. IEEE Trans. Instrum. Meas.,2001,50(4):1007-1013.
[94]Ji Q and Hu R.3D Face pose estimation and tracking from a monocular camera [J]. Image and Vision Computing,2002,20(7):499-511.
[95]Hirotake Y, Akira U, Kenichi H and Masahiko Y. A body-mounted camera system for head-pose estimation and user-view image synthesis [J]. Image and Vision Computing,2007,25(12):1848-1855.
[96]Canton-Ferrer C, Casas J R, Pardas M. Head Orientation Estimation Using Particle Filtering in Multiview Scenarios [C]. Lecture Notes in Computer Science:Multimodal Technologies for Perception of Humans, 2008,4625:317-327.
[97]Yip B and Jin J S.3D Reconstruction of a Human Face with Monocular Camera Based on Head Movement [C]. Proceedings of the Pan-Sydney area workshop on Visual information processing,2004:99-103.
[98]Choi K N, Worthington P L and Hancock E R. Estimating facial pose using shape-from-shading [J]. Pattern Recognition Letters,2002,23(5):533-548.
[99]Zhu Y and Fujimura K.3D Head Pose Estimation with Optical Flow and Depth Constraints [C]. Fourth International Conference on 3-D Digital Imaging and Modeling,2003,211-216.
[100]梁国远.基于三维模型的单目图像序列人脸姿态跟踪[D].北京大学,2005.
[101]Lopez R and Huang T S.3D Head pose computation from 2D images:template versus features [C]. Proceedings of IEEE International Conference on Image Processing,1995,2:599-602.
[102]Shimizu I, Zhang Z, Akamatsu S and Deguchi K. Head pose determination from one image using a generic model [C]. Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition, 1998:100-105.
[103]Marco L C and Stan S. Fast, Reliable head tracking under varying illumination:an approach based on reg-istration of texture-mapped 3D models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(4):322-336.
[104]Kwon O, Chun J and Park P. Cylindrical Model-Based Head Tracking and 3D Pose Recovery from Sequen-tial Face Images [C]. Proceedings of the 2006 International Conference on Hybrid Information Technology, 2006:135-139.
[105]Chun J, Kwon O and Park P. A robust 3D face pose estimation and facial expression control for vision-based animation [C]. Lecture Notes in Computer Science:Advances in Multimedia Modeling,2007, 4351:968-977.
[106]Ryu W and Kim D. Robust 3D Head Tracking and Its Applications [C]. Lecture Notes in Computer Sci-ence:Advances in Biometrics,2007,4642:700-708
[107]尹宝才,张壮,孙艳丰,王成章.基于三维形变模型的多姿态人脸识别[J].北京工业大学学报,2007,33(3)：320-325.
[108]Yang R and Zhang Z. Model-based head pose tracking with stereo vision [C]. Proceedings of IEEE Inter-national Conference on Automatic Face and Gesture Recognition,2002:255-260.
[109]刘志镜,李夏忠,武芒.基于三维模型的多姿态人脸识别[J].西安电子科技大学学报(自然科学版),2004,31(2)：218-222.
[110]胡异丁,朱斌,甘俊英.基于三维人脸建模的多姿态人脸识别[J].计算机工程与设计,2009,30(7)：1728-1731.
[111]Huttenlocker D P and Ullman S. Recognizing solid objects by alignment with an image [J]. International Journal of Computer Vision,1990,5(2):195-212.
[112]宋杰.基于三维模型的单目图像序列头部姿态跟踪[D].浙江大学,2008.
[113]http://en.wikipedia.org/wiki/Radon_transform
[114]Tabbone S, Wendling L and Salmon J P. A new shape descriptor defned on the Radon transform [J]. Computer Vision and Image Understanding,2007,102:42-51.
[115]Vladimir V and Alexander V. Recommendations for taking calibration photos. http://graphics2.cs.msu.ru/ru/science/research/calibration/recommendations.
[116]李玉山.数字视觉视频技术[M].西安：西安电子科技大学出版社,2006.
[117]章毓晋.图像工程(上册)[M].北京：清华大学出版社,1999.
[118]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[119]冈萨雷斯.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2005.
[120]张广军.机器视觉[M].北京：科学出版社,2005.
[121]Claus D. Video-based surveying for large outdoor environments. First Year Report, University of Oxford, 2004.
[122]Harris C and Stephens M. A combined corner and edge detector [C]. Proceedings of The Fourth Alvey Vision Conference,1988:147-151.
[123]Moravec H. Obstacle avoidance and navigation in the realworld by a seeing robot rover. Technical Report CMU-RI-TR-3, Carnegie-Mellon University, Robotics Institute,1980.
[124]Parks D and Gravel J. http://www.cim.mcgill.ca/-dparks/CornerDetector/harris.htm
[125]谷萩隆嗣.语音与图像的数字信号处理[M].北京：科学出版社,2003.
[126]Parks D and Gravel J. http://www.cim.mcgill.ca/dparks/CornerDetector/mainApplet.htm
[127]Chen D and Zhang G. A new sub-pixel detector for x-corners in camera calibration targets [C]. WSCG (Short Papers),2005:97-100.
[128]刘群根.基于梯度与对称度提取棋盘格角点及角点递推定位[J].测控技术,2008,27(1)：7-9.
[129]Yu C and Peng Q. Robust recognition of checkerboard pattern for camera calibration [J]. Optical Engineer-ing,2006,45(9):093201.
[130]刘阳,王福利,常玉清,吕哲.黑白棋盘格角点检测算法[J].东北大学学报(自然科学版),2007,28(7)：1090-1093.
[131]王忠石,韩晓微,徐心和.棋盘格模板角点的自动定位[J].东北大学学报(自然科学版),2006,27(9)：949-952.
[132]张铁楠,涂亚庆,王德超.针对棋盘格角点快速检测的一种新方法[J].计算机工程与应用,2008,44(31)：236-238.
[133]Kaufman L and Rousseeuw P J. Finding groups in data:an introduction to cluster analysis [M]. San Francisco:John Wiley and Sons,1990.
[134]杨风召.高维数据挖掘技术研究[M].南京：东南大学出版社,2007.
[135]Ester M, Kriegel H, Sander J and Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise [C]. Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining,1996:226-231.
[136]Bezdek J C. Pattern recognition with fuzzy objective algorithm [M]. New York:Plenum Press,1981.
[137]Pal N R and Bezdek J C. On cluster validity for the fuzzy c-means model [J]. IEEE Transactions on Fuzzy Systems,1995,3(3):370-379.
[138]高新波,裴继红,谢维信.模糊c-均值聚类算法中加权指数m的研究[J].电子学报,2000,28(4)：80-83.
[139]王建维.制造单元构建的关键技术研究[D].大连：大连理工大学,2009.
[140]王建维,魏小鹏,李睿Evolutionary algorithms with preference for manufacturing cells formation [J]机械工程学报(英文版),2008,21(1)：111-115.
[141]Hartley R and Zisserman A. Multiple view geometry in computer vision [M]. London:Cambridge Univer-sity Press,2003.
[142]Brown D C. Close-range camera calibration [J]. Photogrammetric Engineering,1971,37(8):855-866.
[143]Wei G and Ma S. Implicit and explicit camera calibration:Theory and experiments [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,16(5):469-480,1994.
[144]http://research.microsoft.com/en-us/um/people/zhang/Calib/
[145]Kahnan R E. A new approach to linear f ltering and prediction problems [J]. Transactions of the ASME-Journal of basic engineering (Series D),1960,82:35-45.
[146]Ferrario V F, Sforza C, Serrao G, Grassi G and Mossi E. Active range of motion of the head and cervical spine:a three-dimensional investigation in healthy young adults [J]. Journal of Orthopaedic Research,2002, 20(1):122-129.
[147]文成林.多尺度动态建模理论及应用[M].北京：科学出版社,2007.
[148]Young L and Sheena D. Methods & designs:survey of eye movement recording methods [J]. Behav Res Methods Instrum 1975,7(5):397-429.
[149]van der Geest JN, Frens MA. Recording eye movements with videooculography and scleral search coils:a direct comparison of two methods [J]. J Neurosci Methods,2002,114(2):185-195.
[150]Morimoto C H and Mimica MRM. Eye gaze tracking techniques for interactive applications [J]. Comput Vis Image Und,2005,98(1):4-24.
[151]Villanueva A, Cabeza R and Porta S. Eye tracking:pupil orientation geometrical modeling [J]. Image Vision Comput,2006,24(7):633-679.
[152]Kim S C, Nam K C, Lee W S, etc. A new method for accurate and fast measurement of 3D eye movements [J]. Med Eng Phys,2006,28(l):82-89.
[153]Fetter M.3D-analysis of eye movements [J]. Clin Neurophysiol,2000,3(4):247-250.
[154]Schreiber K and Haslwanter T. Improving calibration of 3-D video oculography systems [J]. IEEE Trans Biomed Eng,2004,51(4):676-679.
[155]Hatamian M and Anderson D J. Design considerations for a real-time ocular counterroll instrument[J]. IEEE Trans Biomed Eng,1983,30:278-288.
[156]Sung K and Anderson D J. Analysis of two video eye tracking algorithms [C]. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society,1991,13(5):1949-1450.
[157]Daniela I and Matteo L. Parametric characterization of the form of the human pupil from blurred noisy images [J]. Comput Methods Programs Biomed,2005,77(1):39-48.
[158]Ebisawa Y. Improved video-based eye-gaze detection method [J]. IEEE Trans Instrum Meas,1998, 47(4):948-955.
[159]Yoo D H and Chung M J. RA novel non-intrusive eye gaze estimation using cross-ratio under large head motion [J]. Comput Vision Image Und,2005,98(1):25-51.
[160]Zhu D J, Steven T M and Theodore R. Robust pupil center detection using a curvature algorithm [J]. Comput Methods Programs Biomed,1999,59(3):145-157.
[161]Moore S T, Haslwanter T, Curthoys I S, etc. A geometric basis for measurement of three-dimensional eye position using image processing [J]. Vision Res,1996,36(3):445-459.
[162]Kim J and Park K. An image processing method for improved pupil size estimation accuracy [C]. Proceed-ings of the 25th Annual Imitational Conference of the IEEE EMBS,2003,9:17-21.
[163]葛坚.眼科学[M].北京：人民卫生出版社(第二版),2002.
[164]Guestrin E D and Eizenman M. General theory of remote gaze estimation using the pupil center and corneal ref ections [J]. IEEE Trans Biomed Eng,2006,53(6):1124-1133.
[165]Zhou Z H and Geng X. Projection functions for eye detection [J]. Pattern Recogn,2004,37(5):1049-1056.
[166]Frosio I and Borghese N A. Real-time accurate circle f tting with occlusions [J]. Pattern Recognition,2008, 41(3):1041-1055.
[167]Zheng Z L, Yang J and Yang L M. A robust method for eye features extraction on color image [J]. Pattern Recognition Letters,2005,26(14):2252-2261.