视觉检测系统的若干关键问题研究
|
摘要
视觉检测具有速度快、非接触、较高精度、操作简单以及自动化程度高等优点，因此视觉检测已经在许多领域内发挥巨大作用。本文对视觉检测系统的若干关键问题进行了研究，主要研究内容可以概括为以下几个方面：
1、为了克服在摄像机标定过程中需要使用者给出标定模板的附加信息，或全自动标定点识别算法在遮挡、不均匀照明、大视角和摄像机镜头畸变情况下不能检测出标定点的缺点，提出一种改进的基于基准点标记的棋盘格模板以及相应的全自动识别算法。新的摄像机标定模板以基准点标记代替传统棋盘格的黑白方块，从而使全自动识别算法识别出标记的位置。利用模板中标记按照标记ID从小到大的顺序排列的先验知识，估计丢失的标定点位置。为了提高丢失标定点在图像中初始位置的估计，算法估计径向畸变参数，从而克服了畸变对识别的影响。为了提高标定点的定位精度，利用高精度的鞍点检测器。为了检测鞍点的有效性，算法提出2种滤波准则，最终得到有效的标定点。识别算法是有效的且不需要任何参数。
2、传统摄像机标定同时计算针孔模型和透镜畸变模型，从而两种模型耦合在一起，所得到的标定结果仅对训练数据是有效的，而算法对于新数据的标定误差增加。为了克服两种模型的耦合，一种分离地标定两种模型的方法被提出。算法利用模板的射影不变量约束，即交比和直线的射影为直线，求解带有畸变的标定点的校正的坐标，然后线性地求解两种模型。该算法稳定且精度高。
3、图像传感器通常受到脉冲噪声的干扰。为了从获取的数字图像中去除脉冲噪声，且同时保留图像的边缘特征，提出基于灰度一致性的脉冲噪声滤波器。滤波器由脉冲噪声检测器和自适应开关中值滤波器组成。由于脉冲噪声是固定值脉冲噪声和随机值脉冲噪声的混合，所以检测器首先利用噪声图像直方图去除固定值脉冲噪声，然后利用方向模板检测待测点是否同任一方向的像素满足灰度一致性准则，从而找到任何可能的随机值脉冲噪声污染的像素。随后，自适应开关中值滤波器利用二进制检测图判断是否进行滤波和确定滤波窗口尺寸，采用窗口内无噪声像素的中值替换检测出的噪声像素。为了获得最优的滤波结果，提出自适应地确定迭代数目的滤波方案。提出的滤波器能够滤除脉冲噪声和具有较快的处理时间。
4、分析原始Canny边缘检测算法的不足，提出改进的Canny边缘检测算法。该算法首先利用小尺度的高斯函数平滑图像，提高边缘检测算法的定位精度，然后利用Otsu双阈值算法自适应地计算梯度幅值的双阈值，利用Otsu单阈值算法自适应地计算灰度的阈值，灰度的阈值对梯度幅值的双阈值进行更强的限制，更加准确地寻找边缘，排除无意义的边缘。改进的Canny边缘检测算法避免人为设定参数，适合工业检测的需要，具有很好的抗造性能、边缘定位精度和实时性。
5、分析伪边缘的性质，提出判断准则，排除明显错误的伪边缘，提高边缘匹配的速度和精度。利用基于弦到点距离累积技术的边缘特征点检测算法检测剩余边缘的特征点。利用各种约束限制候选匹配特征点的搜索范围，然后利用边缘描述子找到正确的匹配点。边缘描述子由灰度均值，灰度标准差和边缘方向直方图组成。边缘描述子具有优良的匹配性能，并且对遮挡、平移、旋转和线性光照具有不变性。匹配特征点所在的边缘是匹配的，利用边缘约束范围，利用外极线约束实现边缘点的快速匹配。
6、分析精度造船对船体分段视觉检测系统的要求，即快速和高精度地获取船体分段边缘的三维数据，从而提出船体分段视觉检测系统的硬件设计方案。硬件由机械伺服系统、视觉传感器、图像采集系统和计算机组成。本文给出硬件的选型，并着重分析视觉传感器的结构设计。同时给出船体分段扫描的实现方法，包括基于移动坐标的测量方法，基于位置触发的船体分段扫描方式和摄像机和图像采集卡的触发方式。高性能的硬件保证船体分段视觉检测系统的测量精度和测量速度，高精度的检测结果保证船体分段无余量对接和补偿量系统的建立。
With the advantages of fast measuring speed, non-contact, high accuracy, easy operationand automatic measuring, etc, the stereo vision inspection technique has played a significantrole in many areas. We discussed some key problems about the stereo vision inspectionpractically and theoretically. The major content is as follows:
1、In order to overcome camera calibration needs user to give additional information ofcalibration pattern, or fully-automatic identification algorithm of calibration points can’tdetect calibration points in the presence of significant occlusions, uneven illumination,observations under extremely acute angles and lens distortion, an improved checker patternbased on fiducial markers is designed, and its correspondingly fully-automatic identificationof calibration points is proposed. New camera calibration pattern replace black and whitesquares of traditional checker pattern with fiducial markers, so fully-automatic identificationalgorithm can locate markers. Using the priori knowledge that markers are arrangedsequentially into calibration pattern in accordance with markers’ ID from small to large, themissed calibration points can be located. In order to improve the estimate of initial position ofmissed points in image, radial distortion is estimated, so identification algorithm overcomethe impact of lens distortion. In order to improve location accuracy of calibration points,subpixel-accurate saddle points’ finder is used. In order to validate the potential points, twofiltering criteria is performed, finally valid calibration points is obtained. The detectionalgorithm is efficient and free of parameters.
2、A lot of traditional camera calibrations compute the pin-hole and lens distortionmodels at the same time, so two models are coupled, computed calibration results are validonly for training data, and their calibration errors increase for new data. In order to overcomethe coupling of two models, a calibration which calibrate two models separately is proposed.The algorithm uses geometric invariants of calibration template, which are cross-rationinvariability and the projection of straight line in the space to the camera is a line, to computeundistorted coordinates of distorted calibration point, and then compute two models linearly.The proposed algorithm is stable and has high calibration accuracy.
3、Vision measurement system is usually subjected to the interference of impulse noise.In order to remove impulse noise from the obtained digital images and also preserve image edge features, impulse noise filter based on gray consistency is proposed. The proposed filteris composed of an impulse noise detector and an adaptive switching median filter. Becauseimpulse noise is some mixture between the fixed-valued impulse noise and the random-valuedimpulse noise, the detector first utilizes the noise image histogram to identify the fixed-valuedimpulse noise, then utilizes direction templates to detect whether detected point meet thecriterion of gray consistency with pixels in any direction, and classifies any possiblerandom-valued impulsive noise pixels. Subsequently, adaptive switching median filter usesbinary decision map to determine whether the filter is implemented and determine thedimensions of filtering window, and replaces the detected noise pixels with the median pixelof all noise-free pixels in filtering window. In order to obtain the optimum performance, thefiltering scheme that adaptively determines the number of iterations is proposed. Theproposed filter is capable of filtering impulse noise and has the relatively fast processing time.
4、Analysis the deficiencies of original Canny edge detection algorithm, the improvedCanny edge detection algorithm is proposed. First, the algorithm use small-scall Gaussianfunction to smooth image, improve location accuracy of edge detection algorithm. Second, ituse Otsu dual-threshold algorithm to calculate the dual-threshold of gradient amplitudeadaptively, use Otsu single threshold algorithm to calculate the threshold of grayscale, whichlimits the high threshold of gradient magnitude, more accurately finds the edge, excludes themeaningless edge. The improved canny edge detection algorithm avoids set parametersartificially, meet the needs of industrial inspection, has good anti-making performance, edgelocation accuracy and real-time.
5、Analysis the nature of error edge, propose the criterions to exclude error edges,improve the speed and accuracy of edge matching. Use the corner detector based on thechord-to-point distance accumulation technique to detect the festure points of remainingedges. Use a few constraints to limit the search of candidate matching feature points, then useedge descriptor to find right matching point. Edge descriptor is composed of grayscale mean,grayscale standard deviation and edge direction histogram. Edge descriptor has excellentmatching performance, and is invariant to occlusion, translation, rotation and linearillumination. The edges including matching feature points are matched, use edge to constrainthe range, and use epipolar constraint to achieve fast matching of edge points.
6、Analylysis the requirements of accuracy shipbuilding for hull section visual inspectionsystem, that is to obtain the three-dimensional data of the edge of hull section, so thehardware design of the hull section visual inspection system is proposed. Hardware iscomposed of mechanical servo system, vision sensor, image acquisition system and computer. This paper gives the selection of hardware, and focuses on analysis of the structural design ofvision sensor. At the same time, it gives the implementation method of hull section scanning,including measuring method based on moving coordinate, hull section scanning mode basedon location trigger, trigger mode of camera and image acquisition card. High-performancehardware guarantees the measurement accuracy and speed of the hull section visual inspectionsystem. High-precision detection results guarantee the establishment of marginless dockingand compensation system about hull section.
1、为了克服在摄像机标定过程中需要使用者给出标定模板的附加信息，或全自动标定点识别算法在遮挡、不均匀照明、大视角和摄像机镜头畸变情况下不能检测出标定点的缺点，提出一种改进的基于基准点标记的棋盘格模板以及相应的全自动识别算法。新的摄像机标定模板以基准点标记代替传统棋盘格的黑白方块，从而使全自动识别算法识别出标记的位置。利用模板中标记按照标记ID从小到大的顺序排列的先验知识，估计丢失的标定点位置。为了提高丢失标定点在图像中初始位置的估计，算法估计径向畸变参数，从而克服了畸变对识别的影响。为了提高标定点的定位精度，利用高精度的鞍点检测器。为了检测鞍点的有效性，算法提出2种滤波准则，最终得到有效的标定点。识别算法是有效的且不需要任何参数。
2、传统摄像机标定同时计算针孔模型和透镜畸变模型，从而两种模型耦合在一起，所得到的标定结果仅对训练数据是有效的，而算法对于新数据的标定误差增加。为了克服两种模型的耦合，一种分离地标定两种模型的方法被提出。算法利用模板的射影不变量约束，即交比和直线的射影为直线，求解带有畸变的标定点的校正的坐标，然后线性地求解两种模型。该算法稳定且精度高。
3、图像传感器通常受到脉冲噪声的干扰。为了从获取的数字图像中去除脉冲噪声，且同时保留图像的边缘特征，提出基于灰度一致性的脉冲噪声滤波器。滤波器由脉冲噪声检测器和自适应开关中值滤波器组成。由于脉冲噪声是固定值脉冲噪声和随机值脉冲噪声的混合，所以检测器首先利用噪声图像直方图去除固定值脉冲噪声，然后利用方向模板检测待测点是否同任一方向的像素满足灰度一致性准则，从而找到任何可能的随机值脉冲噪声污染的像素。随后，自适应开关中值滤波器利用二进制检测图判断是否进行滤波和确定滤波窗口尺寸，采用窗口内无噪声像素的中值替换检测出的噪声像素。为了获得最优的滤波结果，提出自适应地确定迭代数目的滤波方案。提出的滤波器能够滤除脉冲噪声和具有较快的处理时间。
4、分析原始Canny边缘检测算法的不足，提出改进的Canny边缘检测算法。该算法首先利用小尺度的高斯函数平滑图像，提高边缘检测算法的定位精度，然后利用Otsu双阈值算法自适应地计算梯度幅值的双阈值，利用Otsu单阈值算法自适应地计算灰度的阈值，灰度的阈值对梯度幅值的双阈值进行更强的限制，更加准确地寻找边缘，排除无意义的边缘。改进的Canny边缘检测算法避免人为设定参数，适合工业检测的需要，具有很好的抗造性能、边缘定位精度和实时性。
5、分析伪边缘的性质，提出判断准则，排除明显错误的伪边缘，提高边缘匹配的速度和精度。利用基于弦到点距离累积技术的边缘特征点检测算法检测剩余边缘的特征点。利用各种约束限制候选匹配特征点的搜索范围，然后利用边缘描述子找到正确的匹配点。边缘描述子由灰度均值，灰度标准差和边缘方向直方图组成。边缘描述子具有优良的匹配性能，并且对遮挡、平移、旋转和线性光照具有不变性。匹配特征点所在的边缘是匹配的，利用边缘约束范围，利用外极线约束实现边缘点的快速匹配。
6、分析精度造船对船体分段视觉检测系统的要求，即快速和高精度地获取船体分段边缘的三维数据，从而提出船体分段视觉检测系统的硬件设计方案。硬件由机械伺服系统、视觉传感器、图像采集系统和计算机组成。本文给出硬件的选型，并着重分析视觉传感器的结构设计。同时给出船体分段扫描的实现方法，包括基于移动坐标的测量方法，基于位置触发的船体分段扫描方式和摄像机和图像采集卡的触发方式。高性能的硬件保证船体分段视觉检测系统的测量精度和测量速度，高精度的检测结果保证船体分段无余量对接和补偿量系统的建立。
With the advantages of fast measuring speed, non-contact, high accuracy, easy operationand automatic measuring, etc, the stereo vision inspection technique has played a significantrole in many areas. We discussed some key problems about the stereo vision inspectionpractically and theoretically. The major content is as follows:
1、In order to overcome camera calibration needs user to give additional information ofcalibration pattern, or fully-automatic identification algorithm of calibration points can’tdetect calibration points in the presence of significant occlusions, uneven illumination,observations under extremely acute angles and lens distortion, an improved checker patternbased on fiducial markers is designed, and its correspondingly fully-automatic identificationof calibration points is proposed. New camera calibration pattern replace black and whitesquares of traditional checker pattern with fiducial markers, so fully-automatic identificationalgorithm can locate markers. Using the priori knowledge that markers are arrangedsequentially into calibration pattern in accordance with markers’ ID from small to large, themissed calibration points can be located. In order to improve the estimate of initial position ofmissed points in image, radial distortion is estimated, so identification algorithm overcomethe impact of lens distortion. In order to improve location accuracy of calibration points,subpixel-accurate saddle points’ finder is used. In order to validate the potential points, twofiltering criteria is performed, finally valid calibration points is obtained. The detectionalgorithm is efficient and free of parameters.
2、A lot of traditional camera calibrations compute the pin-hole and lens distortionmodels at the same time, so two models are coupled, computed calibration results are validonly for training data, and their calibration errors increase for new data. In order to overcomethe coupling of two models, a calibration which calibrate two models separately is proposed.The algorithm uses geometric invariants of calibration template, which are cross-rationinvariability and the projection of straight line in the space to the camera is a line, to computeundistorted coordinates of distorted calibration point, and then compute two models linearly.The proposed algorithm is stable and has high calibration accuracy.
3、Vision measurement system is usually subjected to the interference of impulse noise.In order to remove impulse noise from the obtained digital images and also preserve image edge features, impulse noise filter based on gray consistency is proposed. The proposed filteris composed of an impulse noise detector and an adaptive switching median filter. Becauseimpulse noise is some mixture between the fixed-valued impulse noise and the random-valuedimpulse noise, the detector first utilizes the noise image histogram to identify the fixed-valuedimpulse noise, then utilizes direction templates to detect whether detected point meet thecriterion of gray consistency with pixels in any direction, and classifies any possiblerandom-valued impulsive noise pixels. Subsequently, adaptive switching median filter usesbinary decision map to determine whether the filter is implemented and determine thedimensions of filtering window, and replaces the detected noise pixels with the median pixelof all noise-free pixels in filtering window. In order to obtain the optimum performance, thefiltering scheme that adaptively determines the number of iterations is proposed. Theproposed filter is capable of filtering impulse noise and has the relatively fast processing time.
4、Analysis the deficiencies of original Canny edge detection algorithm, the improvedCanny edge detection algorithm is proposed. First, the algorithm use small-scall Gaussianfunction to smooth image, improve location accuracy of edge detection algorithm. Second, ituse Otsu dual-threshold algorithm to calculate the dual-threshold of gradient amplitudeadaptively, use Otsu single threshold algorithm to calculate the threshold of grayscale, whichlimits the high threshold of gradient magnitude, more accurately finds the edge, excludes themeaningless edge. The improved canny edge detection algorithm avoids set parametersartificially, meet the needs of industrial inspection, has good anti-making performance, edgelocation accuracy and real-time.
5、Analysis the nature of error edge, propose the criterions to exclude error edges,improve the speed and accuracy of edge matching. Use the corner detector based on thechord-to-point distance accumulation technique to detect the festure points of remainingedges. Use a few constraints to limit the search of candidate matching feature points, then useedge descriptor to find right matching point. Edge descriptor is composed of grayscale mean,grayscale standard deviation and edge direction histogram. Edge descriptor has excellentmatching performance, and is invariant to occlusion, translation, rotation and linearillumination. The edges including matching feature points are matched, use edge to constrainthe range, and use epipolar constraint to achieve fast matching of edge points.
6、Analylysis the requirements of accuracy shipbuilding for hull section visual inspectionsystem, that is to obtain the three-dimensional data of the edge of hull section, so thehardware design of the hull section visual inspection system is proposed. Hardware iscomposed of mechanical servo system, vision sensor, image acquisition system and computer. This paper gives the selection of hardware, and focuses on analysis of the structural design ofvision sensor. At the same time, it gives the implementation method of hull section scanning,including measuring method based on moving coordinate, hull section scanning mode basedon location trigger, trigger mode of camera and image acquisition card. High-performancehardware guarantees the measurement accuracy and speed of the hull section visual inspectionsystem. High-precision detection results guarantee the establishment of marginless dockingand compensation system about hull section.
引文
[1]吴斌,孙长钦,杨兵等.结构光传感器在柔性视觉测量系统中的应用研究.光电子·激光,2008,19(10):1309-1311页
[2]吕乃光,邓文怡.大型机械零部件孔同轴度测量技术研究.光电子·激光,2001,12(7):694-696页
[3] Wang W G, Hu Z Y, Shun Z Y.3D shape measurement based computer vision.International Conference on Machine Learning and Cybernetics, Beijing, China,2002:910-914P
[4] Shi Q, Xi N, Chen Y F. Development of an automatic optical measurement system forautomotive part surface inspection. International Conference on Advanced IntelligentMechatronics, CA, US,2005:1557-1562P
[5] Takechi S, Aoyama K, Nomoto T. Studies on the block positioning metries system forthe hull ereetion stage. Marine science and technology,2002,1(6):158-167P
[6] Hideki S. Evaluation of Three Dimensional Coordinate Measuring Methods forProduction of Ship Hull Blocks. Proceedings of the International Offshore and PolarEngineering Conference, Kitakyushu, Japan,2002:348-351P
[7] Mass H G, Kersten T P. Experiences with a high resolution still video camera in digitalPhotogrammetric applications on a shipyard. ISPRS Intercongress Symposium,Melbourne, Australia,1994:250-255P
[8] Li Z L, Wang Y. Research on3D reconstruction procedure of marked points for largeworkpiece measurement. International Conference on Information Assurance andSecurity, Xian, China,2009:273-276P
[9] Wang W G, Hu Z Y, Shun Z Y.3-D shape measurement based computer vision.International Conference on Machine Learning and Cybernetics, Beijing, China,2002:910-914P
[10] Kurazume R, Tobata Y, Iwashita Y, et al.3D laser measurement system for larger scalearchitectures using multiple mobile robots. International Conference on3-D DigitalImaging and Modeling, Montreal, Canada,2007:91-98P
[11] Richard K. Adaptive optical three-dimensional measurement with structured light.Optical Engineering,2000,39(l):150-158P
[12] Kurtis K, Jeremy A. Real-time structured light depth extraction. Three-DimensionalImage Capture and Applications,2000,3958:11-18P
[13]刘维一,王肇忻,母国光等.彩色编码投影光栅轮廓术中分色问题的探究.光学学报,2001,21(4):454-458页
[14]周富强,李章,张广军.基于三维测量扫描线点云的表面重建.仪器仪表学报,2006,27(6):619-623页
[15]谢凯,刘宛予,浦昭邦.结构光三维视觉检测系统的标定方法研究.光电子·激光,2007,18(3):369-371页
[16] Tsai R Y. A versatile camera calibration technique for high accuracy3D machinevision metrology using off-the-shelf TV cameras and lenses. IEEE Journal of Roboticsand Automation,1987,3(4):323-344P
[17] Melen T. Geometrical modelling and calibration of video cameras for underwaternavigation. Institut for teknisk kybernetikk, Norges tekniske hogskole, Throndheim,PhD thesis,1994:1-100P
[18] Hartley R. Self-calibration of stationary cameras. International Journal of ComputerVision,1997,22(1):5-23P
[19] Ma S D. Self-calibration technique for active vision system. IEEE Transactions onRobotics and Automation,1996,12(1):114-120P
[20] Moons T, Van G L, Proesmans M, et al. Affine reconstruction from perspective imagepairs with a relative object-camera translation in between. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(1):77-83P
[21] Maybank S J, Faugeras O D. Theory of self-calibration of a moving camera.International Journal of Computer Vision,1992,8(2):123-151P
[22] Hartley R. Projective reconstruction and invariants from multiple images. IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(10):1036-1041P
[23] Triggs B. Auto-calibration and the absolute quadric. Proceedings of Computer Visionand Pattern Recognition,1997:609-614P
[24] Pollefeys M, Van G L, Oosterlinck A. The modulus constraint: a new constraint forself-calibraion. Proceedings of the13th International Conference on PatternRecognition, Vienna,1996:349-353P
[25] Pollefeys M, Reinhard K, Van G L. Self-calibration and metric reconstruction in spiteof varying and unknown internal camera parameters. Proceedings of the IEEEInternational Conference on Computer Vision, Bombay, India,1998:90-95P
[26] Heyden A, Astrom K. Euclidean reconstruction from image sequences with varyingand unkown focal length and principal point. Proceedings of the IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1997:438-443P
[27] Wei G Q, Ma S D. Implicit and explicit camera calibration: Theory and experiments.IEEE transaction on Pattern Analysis and Machine Intelligence,1994,16(5):469-480P
[28] Heikkila J, Silven O. Four-step camera calibration procedure with implicit imagecorrection. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition, San Juan, PR, USA,1997:1106-1112P
[29]张浩鹏,王宗义,吴攀超等.摄像机标定的棋盘格模板的改进和自动识别.仪器仪表学报,2012,33(5):1102-1109页
[30] Fiala M. Designing highly reliable fiducial markers. IEEE Transactions on PatternAnalysis and Machine Intelligence,2010,32(7):1317-1324P
[31] Zhang Z. A flexible new technique for camera calibration. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330–1334P
[32] Song Z, Chung R. Use of LCD panel for calibrating structured-light-based rangesensing system. IEEE Transactions on Instrumentation and Measurement,2008,57(11):2623-2630P
[33] Sattar J, Bourque E, Giguère P, et al. Fourier tags: Smoothly degradable fiducialmarkers for use in human-robot interaction. Proceedings-Fourth CanadianConference on Computer and Robot Vision, Montreal, QC, Canada,2007:165-171P
[34]夏仁波,刘伟军,赵吉宾等.基于圆形标志点的全自动相机标定方法.仪器仪表学报,2009,30(2):368-373页
[35] Fiala M. ARTag, a fiducial marker system using digital techniques. Proceedings–2005IEEE Computer Society Conference on Computer Vision and PatternRecognition, San Diego, CA, US,2005:590–596P
[36] Yoon S R, Seo S, Huang M L, et al. Multi-processor based CRC computation schemefor high-speed wireless LAN design. Electronics Letters,2010,46(11):800-802P
[37] Marin C, Bouchireb K, Kieffer M, et al. Joint Exploitation of Residual SourceInformation and MAC Layer CRC Redundancy for Robust Video Decoding. IEEETransactions on Wireless Communications,2010,9(7):2165-2175P
[38]孙建平,苑一方.复杂过程的多模型建模方法研究.仪器仪表学报,2011,32(1):132-137页
[39] Heikkila J. Geometric camera calibration using circular control points. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(10):1066-1077P
[40]杨幸芳,黄玉美,高峰等.用于摄像机标定的棋盘图像角点检测新算法.仪器仪表学报,2011,32(5):1109-1113页
[41] Fiala M. Comparing ARTag and ARToolkit plus fiducial marker systems. IEEEInternational Workshop on Haptic Audio Visual Environments and their Applications,Ottawa, ON, Canada,2005:148-153P
[42]张浩鹏,王宗义,吴攀超等.基于LCD和改进棋盘格模板的摄像机标定.仪器仪表学报,2012,33(7):1541-1548页
[43]张浩鹏,王宗义,张智等.全景摄像机标定.哈尔滨工程大学学报,2009,30(11):1239-1245页
[44] Zhang J, Wu Y, Liu W, et al. Novel approach to position and orientation estimation invision-based UAV navigation. IEEE Transactions on Aerospace and ElectronicSystems,2010,46(2):687-700P
[45] Faugeras O D. Luong Q T, Maybank S J. Camera self-calibration: theory andexperiments. European Conference on Computer Vision,1992:321-334P
[46] Stein G P. Accurate internal camera calibration using rotation with analysis of sourcesof error. IEEE International Conference on Computer Vision,1995:230-236P
[47] Hu M C, Chang M H, Wu J L, et al. Robust camera calibration and player tracking inbroadcast basketball video. IEEE Transactions on Multimedia,2011,13(2):266-279P
[48]李勃,陈启美.基于监控视频的运动车辆行为分析算法.仪器仪表学报,2006,27(6):2118-2120页
[49] Lee S B, Shin I Y, Ho Y S. Gaze-corrected view generation using stereo camera systemfor immersive videoconferencing. IEEE Transactions on Consumer Electronics,2011,57(3):1033-1040P
[50] Tsai R. A versatile camera calibration technique for high-accuracy3D machine visionmetrology using off-the-self TV camera lenses. IEEE Journal of Robotics andAutomation.1987,3(4):323–344P
[51] Weng J Y, Cohen P, Herniou M. Camera calibration with distortion models andaccuracy evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(10):965–980P
[52] Zhang Z Y. Flexible camera calibration by viewing a plane from unknown orientations.Proceedings of the IEEE International Conference on Computer Vision, Kerkyra,Greece,1999:666-673P
[53] Zhang Z Y, Deriche R, Faugeras O, et al. Robust technique for matching twouncalibrated images through the recovery of the unknown epipolar geometry. ArtificialIntelligence,1995,78(1/2):87-119P
[54] Golub G H, Van L C F. Matrix computations.3Editions. Johns Hopkins UniversityPress, Baltimore, MaryLand,1996:1-694P
[55] Ahmed M, Farag A. Nonmetric calibration of camera lens distortion: differentialmethods and robust estimation. IEEE Transactions on image processing,2005,14(8):1215-1230P
[56]张浩鹏,王宗义.基于灰度方差和边缘密度的车牌定位算法.仪器仪表学报,2011,32(5):1095-1102页
[57] Li Y R, Shen L X, Dai D Q, et al. Framelet algorithms for de-blurring imagescorrupted by impulse plus gaussian noise. IEEE Transactions on Image Processing,2011,20(7):1822-1837P
[58]陈树越,路宏年.基于行列处理消除正向脉冲噪声非线性滤波器.仪器仪表学报,2000,21(5):458-463页
[59] Srinivasan K S, Ebenezer D. A new fast and efficient decision-based algorithm forremoval of high-density impulse noises. IEEE Signal Processing Letters,2007,14(3):189–192P
[60] Luo W B. Efficient removal of impulse noise from digital images. IEEE Transactionson Consumer Electronics,2006,52(2):523-527P
[61] Choi K S, Ko S J. New autofocusing technique using the frequency selective weightedmedian filter for video cameras. International Conference on Consumer Electronics,CA, USA,1999:160-161P
[62] Dong Y Q, Chan R H, Xu S. A detection statistic for random-valued impulse noise.IEEE Transactions on Image Processing,2007,16(4):1112-1120P
[63]王建勇,周晓光,廖启征.一种基于中值-模糊技术的混合噪声滤波器.电子与信息学报,2006,28(5):901-904页
[64] Ibrahim H, Kong N S P, Ng T F. Simple adaptive median filter for the removal ofimpulse noise from highly corrupted images. IEEE Transactions on ConsumerElectronics,2008,54(4):1920-1927P
[65] Petrovic N I, Crnojevic V. Universal impulse noise filter based on geneticprogramming. IEEE Transactions on Image Processing,2008,17(7):1109-1120P
[66] Toh K K V, Isa N A M. Noise adaptive fuzzy switching median filter forsalt-and-pepper noise reduction. IEEE Signal Processing Letters,2010,17(3):281-284P
[67] Ng P E, Ma K K. A switching median filter with boundary discriminative noisedetection for extremely corrupted images. IEEE Transactions on Image Processing,2006,15(6):1506-1516P
[68] Dong Y Q, Xu S. A new directional weighted median filter for removal ofrandom-valued impulse noise. IEEE Signal Processing Letters,2007,14(3):193-196P
[69] Luo W B. An efficient algorithm for the removal of impulse noise from corruptedimages. International Journal of Electronics Communications,2007,61(8):551-555P
[70] Zhang J J. An efficient median filter based method for removing random-valuedimpulse noise. Digital Signal Processing: A Review Journal,2010,20(4):1010-1018P
[71] Civicioglu P. Using uncorrupted neighborhoods of the pixels for impulsive noisesuppression with ANFIS. IEEE Transactions on Image Processing,2007,16(3):759-773P
[72] Civicioglu P. Removal of random-valued impulsive noise from corrupted images.IEEE Transactions on Consumer Electronics,2009,55(4):2097-2104P
[73] Russo F, Ramponi G. Fuzzy filter for images corrupted by impulse noise. IEEE SignalProcessing Letters,1996,3(6):168-170P
[74] Sun T, Neuvo Y. Detail-preserving median based filters in image processing. PatternRecognition Letters,1994,15(4):341-347P
[75] Chan R H, Ho C W, Nikolova M. Salt-and-pepper noise removal by median-type noisedetectors and detail-preserving regularization. IEEE Transactions on Image Processing,2005,14(10):1479-1485P
[76]刘伟嵬,颜云辉,孙宏伟.基于邻域评价法的带钢表面缺陷图像脉冲噪声去除.仪器仪表学报,2008,29(9):1846-1850页
[77] Chen T, Ma K K, Chen L H. Tri-state median-based filters in image denoising. IEEETransactions on Image Processing,1999,8(12):1834-1838P
[78] Chen T, Wu H R. Adaptive impulse detection using center-weighted median filters.IEEE Signal Processing Letters,2001,8(1):1-3P
[79] Wu J, Tang C. PDE-based random-valued impulse noise removal based on new classof controlling functions. IEEE Transactions on Image Processing,2011,20(9):2428-2438P
[80] Civicioglu P. Using uncorrupted neighborhoods of pixels for impulsive noisesuppression with ANFIS. IEEE Transactions on Image Processing,2007,16(3):759-773P
[81] Russo F, Ramponi G. Fuzzy filter for images corrupted by impulse noise. IEEE SignalProcessing Letters,1996,3(6):168-170P
[82]杜亚勤,洪波,郭雷等.一种曲面拟合图像边缘特征提取算法.西安电子科技大学学报(自然科学版),2011,38(3):164-168页
[83]李晖,肖鹏峰,冯学智等.基于向量场模型的多光谱遥感图像多尺度边缘检测.测绘学报,2012,41(1):100-107页
[84]黄茜,吴炜峰,董肖.基于局部尺度控制的模糊边缘检测算法.模式识别与人工智能,2011,24(6):875-881页
[85]周树道,王敏,刘志华等.基于多方向小波变换及形态学重构的SAR图像边缘检测.解放军理工大学学报(自然科学版),2011,12(5):436-439页
[86]胡晓辉,张晓颖,陈俊莲.一种融合小波变换和数学形态学的图像边缘检测算法.铁道学报,2011,33(3):45-48页
[87]黄海龙,王宏.一种基于小波变换和数学形态学的边缘检测算法.东北大学学报(自然科学版),2011,32(9):1315-1318页
[88]肖易寒,席志红,海涛等.基于非下采样contourlet变换的图像边缘检测新方法.系统工程与电子技术,2011,33(7):1668-1672页
[89]艾泽潭,石庚辰,熊鑫等.基于模糊梯度的微齿轮图像边缘检测算法.北京理工大学学报,2011,31(8):919-921页
[90]唐永鹤,卢焕章.基于多结构元素复合滤波的形态学边缘检测.武汉大学学报信息科学版,2012,37(1):50-53页
[91]何嘉懿,廖桂生,杨志伟.多目标航迹的图像域自适应检测方法.兵工学报,2011,32(6):663-667页
[92]刘勇,姚刚,肖人彬等.自适应多窗口梯度幅值边缘检测算法.华中科技大学学报(自然科学版),2011,39(1):14-18页
[93]曹传东,徐贵力,陈欣等.基于力场转换理论的图像粗大边缘检测方法.航空学报,2011,32(5):891-899页
[94]朱自强,曾思红,鲁光银.重力张量数据的目标体边缘检测方法.探讨石油地球物理勘探,2011,46(3):482-487页
[95] Canny J. A computational approach to edge detection. IEEE Transcations on PatternAnalysis and Machine Intelligence,1986,8(6):679-698P
[96] Lee S U, Chung S Y. A comparative performance study of several global thresholdingtechniques for segmentation. Computer Vision, Graphics, and Image Processing,1990,52(2):171-190P
[97] Wang H, Brady M. Real time corner detection algorithm for motion estimation. Imageand Vision Computing,1995,13(9):695-703P
[98] Trajkovic M, Hedley M. Fast corner detection. Image and Vision Computing,1998,16(2):75-87P
[99] Smith S M, Brady J M. SUSAN-a new approach to low level image Processing.International Journal of Computer Vision,1997,23(1):45-78P
[100]张浩鹏,王宗义.基于小波的多尺度SUSAN角点检测.光电工程,2009,36(11):100-105页
[101] Harris C, Stephens M. A combined corner and edge detector. Alvey Vision Conference,1988:147-151P
[102] Xu Q, Chakrabarti C, Karam L J. A distributed canny edge detector and itsimplementation on FPGA. Digital Sianal Processing and Signal Processing EducationMeeting, Sedona, AZ, US,2011:500-505P
[103] Xu Z D, Yuan K, He W H. An implementation method of Canny edge detectionalgorithm on FPGA. International Conference on Electric Information and ControlEngineering, Wuhan, China,2011:3958-3962P
[104] Awrangjeb M, Lu G J, Murshed M. An affine resilient curvature scale-space cornerdetector. IEEE International Conference on Acoustics, Speech and Signal Processing,Honolulu, HI, US,2007: I1233–I1236P
[105] Rattarangsi A, Chin R T. Scale-based detection of corners of planar curves. IEEETransactions on Pattern Analysis and Machine Intelligence,1992,14(4):430–449P
[106] Zhong B J, Liao W H. Direct curvature scale space: Theory and corner detection. IEEETransactions on Pattern Analysis and Machine Intelligence,2007,29(3):508–512P
[107] Ray B K, Pandyan R. ACORD-an adaptive corner detector for planar curves. PatternRecognition,2003,36(3):703–708P
[108] Mokhtarian F, Suomela R. Robust image corner detection through curvature scalespace. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381P
[109] Mokhtarian F, Mohanna F. Fusion of corners from multiple scales for robust tracking.Proceedings of Joint Conference on Information Sciences, Research Triange Park, NC,US,2002:765-768P
[110] Zhang X H, Lei M, Yang D, et al. Multi-scale curvature product for robust imagecorner detection in curvature scale space. Pattern Recognition Letters,2007,28(5):545–554P
[111] He X C, Yung N H C. Curvature scale space corner detector with adaptive thresholdand dynamic region of support. Proceedings-International Conference on PatternRecognition, Cambridge, UK,2004:791–794P
[112]王耀贵.图像高斯平滑滤波分析.计算机与信息技术,2008,8(1):79-90页
[113] Mokhtarian F, Abbasi S. Affine curvature scale space with affine lengthparametrisation. Pattern Analysis&Applications,2001,4(1):1-8P
[114] Awrangjeb M, Lu G F. A robust corner matching technique. Proceedings of the2007IEEE International Conference on Multimedia and Expo, Beijing, China,2007:1483-1486P
[115] Han J H, Poston T. Chord-to-point distance accumulation and planar curvature: A newapproach to discrete curvature. Pattern Recognition Letters,2001,22(10):1133–1144P
[116] Rosenfeld A, Johnston E. Angle detection on digital planar curves. IEEE Transactionson Computers.1973,22(9):875–878P
[117]曲学军,张璐,张凌云.基于新的成像模型的摄像机标定与三维重建.仪器仪表学报,2011,32(8):1830-1836页
[118]张文明,刘彬,李海滨.基于双目视觉的三维重建中特征点提取及匹配算法的研究.光学技术,2008,34(2):181-185页
[119] Tang A W K, Ng T P, Hung Y S, et al. Projective Reconstruction fromLine-Correspondences in Multiple Uncalibrated Images. Pattern Recognition,2006,39(5):889-896P
[120] Aider O A, Hoppenot P, Colle E. A Model-Based Method for Indoor Mobile RobotLocalization Using Monocular Vision and Straight-Line Correspondences. Roboticsand Autonomous Systems,2005,52(2/3):229-246P
[121] Shi F H, Wang J H, Zhang J, et al. Motion Segmentation of Multiple TranslationObjects from Line Correspondences. Pattern Recognition,2005,38(10):1775-1778P
[122] Bartoli A, Sturm P. Multiple-View Structure and Motion from Line Correspondences.Proceedings of the IEEE International Conference on Computer Vision, Nice, France,2003:207-212P
[123] Belongie S, Malik J, Puzicha J. Shape Matching and Object Recognition Using ShapeContexts. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522P
[124] Lowe D G. Distinctive Image Features from Scale-Invariant Key-points. InternationalJournal of Computer Vision,2004,60(2):91-110P
[125] Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for Local ImageDescriptors. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition. Washington, DC, US,2004:II506-II513P
[126] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630P
[127] Mikolajczyk K, Zisserman A, Schmid C. Shape Recognition with Edge-Based Features.British Machine Vision Conference. Norwich, UK,2003:779-788P
[128] Matas J, Chum O, Urban M, et al. Robust Wide Baseline Stereo from MaximallyStable Extremal Regions. Image and Vision Computing,2004,22(10):761-767P
[129] Schmid C, Zisserman A. Automatic Line Matching across Views. Proceedings of theIEEE Computer Society Conference on Computer Vision and Pattern Recognition. SanJuan, PR, USA,1997:666-671P
[130] Deng Y, Lin X Y. A Fast Line Segment Based Dense Stereo Algorithm Using TreeDynamic Programming. Proceedings of the9th European Conference on ComputerVision. Graz, Austria,2006:201-212P
[131] Kletter R, Koschan A, Schluns K. Computer vision three-dimensional data fromimages.1st. Springer-Verlag Singapore Pte,1998:67-83P
[132] Han J H, Park J S. Contour matching using epipolar geometry ligence. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(4):358-370P
[133] Yuan M L, Xie M, Yin X M. Rubust cooperative strategy for contour matching usingepipolar geometry. Asian Conference on Computer Vision,2002:1-10P
[134] Moallem P, Faez K. Effective parameters in search space reduction used in a fastedge-based stereo matching. Journal of Circuits, Systems and Computers,2005,14(2):249-266P
[135] Moallem P, Ashourian M, Mirzaeian B. A novel fast feature based stereo matchingalgorithm with low invalid matching. WSEAS Transactions on Computers,2006,5(3):469-476P
[136] Fusiello A, Trucco E, Verri A. Compact algorithm for rectification of stereo pairs.Machine Vision and Applications,2000,12(1):16-22P
[137] Oram D. Rectification for any epipolar Geometry. Proceedings of the British MachineVision Conference, Manchester, UK,2001:653-662P
[138]张淮峰, Jan C, Radim S等.三视校正的理论及鲁棒性算法.软件学报,2004,15(5):676-688页
[139] Egnal G, Wildes R P. Detecting Binocular Half-Occlusions: Empirical Comparisons ofFour Approaches. Proceedings of the IEEE Computer Society Conference onComputer Vision and Pattern Recognition. Hilton Head Island, SC, USA,2000:466-473P
[140] Weng J W, Cohen P, Herniou M. Camera calibration with distortion models andaccuracy evaluation. Transactions on Pattern Analysis and Machine Intelligence,1992,14(10):965-980P
[141] Miida T, Kawajiri K, Terakago H, et al. A1.5Mpixel imager with localizedhole-modulation method. International Solid-State Circuits Conference, CA, US,2002:42-43P
[142]张益昕.基于计算机视觉的大尺度三维几何尺寸测量方法及应用.南京大学博士学位论文.2011:11-26页
[143]王志衡,吴福朝.均值-标准差描述子与直线匹配.模式识别与人工智能,2009,22(1):32-39页
[144]周富强,邾继贵,杨学友等.双目视觉传感器的现场标定方法.仪器仪表学报,2000,21(2):142-145页
[145]李秀智,张广军.三目视觉图像的极线校正方法.光电工程,2007,34(10):50-54页
[146]侯建,齐乃明.月球车视觉系统立体匹配算法研究.南京理工大学学报(自然科学版),2008,32(2):176-180页
[2]吕乃光,邓文怡.大型机械零部件孔同轴度测量技术研究.光电子·激光,2001,12(7):694-696页
[3] Wang W G, Hu Z Y, Shun Z Y.3D shape measurement based computer vision.International Conference on Machine Learning and Cybernetics, Beijing, China,2002:910-914P
[4] Shi Q, Xi N, Chen Y F. Development of an automatic optical measurement system forautomotive part surface inspection. International Conference on Advanced IntelligentMechatronics, CA, US,2005:1557-1562P
[5] Takechi S, Aoyama K, Nomoto T. Studies on the block positioning metries system forthe hull ereetion stage. Marine science and technology,2002,1(6):158-167P
[6] Hideki S. Evaluation of Three Dimensional Coordinate Measuring Methods forProduction of Ship Hull Blocks. Proceedings of the International Offshore and PolarEngineering Conference, Kitakyushu, Japan,2002:348-351P
[7] Mass H G, Kersten T P. Experiences with a high resolution still video camera in digitalPhotogrammetric applications on a shipyard. ISPRS Intercongress Symposium,Melbourne, Australia,1994:250-255P
[8] Li Z L, Wang Y. Research on3D reconstruction procedure of marked points for largeworkpiece measurement. International Conference on Information Assurance andSecurity, Xian, China,2009:273-276P
[9] Wang W G, Hu Z Y, Shun Z Y.3-D shape measurement based computer vision.International Conference on Machine Learning and Cybernetics, Beijing, China,2002:910-914P
[10] Kurazume R, Tobata Y, Iwashita Y, et al.3D laser measurement system for larger scalearchitectures using multiple mobile robots. International Conference on3-D DigitalImaging and Modeling, Montreal, Canada,2007:91-98P
[11] Richard K. Adaptive optical three-dimensional measurement with structured light.Optical Engineering,2000,39(l):150-158P
[12] Kurtis K, Jeremy A. Real-time structured light depth extraction. Three-DimensionalImage Capture and Applications,2000,3958:11-18P
[13]刘维一,王肇忻,母国光等.彩色编码投影光栅轮廓术中分色问题的探究.光学学报,2001,21(4):454-458页
[14]周富强,李章,张广军.基于三维测量扫描线点云的表面重建.仪器仪表学报,2006,27(6):619-623页
[15]谢凯,刘宛予,浦昭邦.结构光三维视觉检测系统的标定方法研究.光电子·激光,2007,18(3):369-371页
[16] Tsai R Y. A versatile camera calibration technique for high accuracy3D machinevision metrology using off-the-shelf TV cameras and lenses. IEEE Journal of Roboticsand Automation,1987,3(4):323-344P
[17] Melen T. Geometrical modelling and calibration of video cameras for underwaternavigation. Institut for teknisk kybernetikk, Norges tekniske hogskole, Throndheim,PhD thesis,1994:1-100P
[18] Hartley R. Self-calibration of stationary cameras. International Journal of ComputerVision,1997,22(1):5-23P
[19] Ma S D. Self-calibration technique for active vision system. IEEE Transactions onRobotics and Automation,1996,12(1):114-120P
[20] Moons T, Van G L, Proesmans M, et al. Affine reconstruction from perspective imagepairs with a relative object-camera translation in between. IEEE Transactions onPattern Analysis and Machine Intelligence,1996,18(1):77-83P
[21] Maybank S J, Faugeras O D. Theory of self-calibration of a moving camera.International Journal of Computer Vision,1992,8(2):123-151P
[22] Hartley R. Projective reconstruction and invariants from multiple images. IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(10):1036-1041P
[23] Triggs B. Auto-calibration and the absolute quadric. Proceedings of Computer Visionand Pattern Recognition,1997:609-614P
[24] Pollefeys M, Van G L, Oosterlinck A. The modulus constraint: a new constraint forself-calibraion. Proceedings of the13th International Conference on PatternRecognition, Vienna,1996:349-353P
[25] Pollefeys M, Reinhard K, Van G L. Self-calibration and metric reconstruction in spiteof varying and unknown internal camera parameters. Proceedings of the IEEEInternational Conference on Computer Vision, Bombay, India,1998:90-95P
[26] Heyden A, Astrom K. Euclidean reconstruction from image sequences with varyingand unkown focal length and principal point. Proceedings of the IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1997:438-443P
[27] Wei G Q, Ma S D. Implicit and explicit camera calibration: Theory and experiments.IEEE transaction on Pattern Analysis and Machine Intelligence,1994,16(5):469-480P
[28] Heikkila J, Silven O. Four-step camera calibration procedure with implicit imagecorrection. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition, San Juan, PR, USA,1997:1106-1112P
[29]张浩鹏,王宗义,吴攀超等.摄像机标定的棋盘格模板的改进和自动识别.仪器仪表学报,2012,33(5):1102-1109页
[30] Fiala M. Designing highly reliable fiducial markers. IEEE Transactions on PatternAnalysis and Machine Intelligence,2010,32(7):1317-1324P
[31] Zhang Z. A flexible new technique for camera calibration. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330–1334P
[32] Song Z, Chung R. Use of LCD panel for calibrating structured-light-based rangesensing system. IEEE Transactions on Instrumentation and Measurement,2008,57(11):2623-2630P
[33] Sattar J, Bourque E, Giguère P, et al. Fourier tags: Smoothly degradable fiducialmarkers for use in human-robot interaction. Proceedings-Fourth CanadianConference on Computer and Robot Vision, Montreal, QC, Canada,2007:165-171P
[34]夏仁波,刘伟军,赵吉宾等.基于圆形标志点的全自动相机标定方法.仪器仪表学报,2009,30(2):368-373页
[35] Fiala M. ARTag, a fiducial marker system using digital techniques. Proceedings–2005IEEE Computer Society Conference on Computer Vision and PatternRecognition, San Diego, CA, US,2005:590–596P
[36] Yoon S R, Seo S, Huang M L, et al. Multi-processor based CRC computation schemefor high-speed wireless LAN design. Electronics Letters,2010,46(11):800-802P
[37] Marin C, Bouchireb K, Kieffer M, et al. Joint Exploitation of Residual SourceInformation and MAC Layer CRC Redundancy for Robust Video Decoding. IEEETransactions on Wireless Communications,2010,9(7):2165-2175P
[38]孙建平,苑一方.复杂过程的多模型建模方法研究.仪器仪表学报,2011,32(1):132-137页
[39] Heikkila J. Geometric camera calibration using circular control points. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(10):1066-1077P
[40]杨幸芳,黄玉美,高峰等.用于摄像机标定的棋盘图像角点检测新算法.仪器仪表学报,2011,32(5):1109-1113页
[41] Fiala M. Comparing ARTag and ARToolkit plus fiducial marker systems. IEEEInternational Workshop on Haptic Audio Visual Environments and their Applications,Ottawa, ON, Canada,2005:148-153P
[42]张浩鹏,王宗义,吴攀超等.基于LCD和改进棋盘格模板的摄像机标定.仪器仪表学报,2012,33(7):1541-1548页
[43]张浩鹏,王宗义,张智等.全景摄像机标定.哈尔滨工程大学学报,2009,30(11):1239-1245页
[44] Zhang J, Wu Y, Liu W, et al. Novel approach to position and orientation estimation invision-based UAV navigation. IEEE Transactions on Aerospace and ElectronicSystems,2010,46(2):687-700P
[45] Faugeras O D. Luong Q T, Maybank S J. Camera self-calibration: theory andexperiments. European Conference on Computer Vision,1992:321-334P
[46] Stein G P. Accurate internal camera calibration using rotation with analysis of sourcesof error. IEEE International Conference on Computer Vision,1995:230-236P
[47] Hu M C, Chang M H, Wu J L, et al. Robust camera calibration and player tracking inbroadcast basketball video. IEEE Transactions on Multimedia,2011,13(2):266-279P
[48]李勃,陈启美.基于监控视频的运动车辆行为分析算法.仪器仪表学报,2006,27(6):2118-2120页
[49] Lee S B, Shin I Y, Ho Y S. Gaze-corrected view generation using stereo camera systemfor immersive videoconferencing. IEEE Transactions on Consumer Electronics,2011,57(3):1033-1040P
[50] Tsai R. A versatile camera calibration technique for high-accuracy3D machine visionmetrology using off-the-self TV camera lenses. IEEE Journal of Robotics andAutomation.1987,3(4):323–344P
[51] Weng J Y, Cohen P, Herniou M. Camera calibration with distortion models andaccuracy evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(10):965–980P
[52] Zhang Z Y. Flexible camera calibration by viewing a plane from unknown orientations.Proceedings of the IEEE International Conference on Computer Vision, Kerkyra,Greece,1999:666-673P
[53] Zhang Z Y, Deriche R, Faugeras O, et al. Robust technique for matching twouncalibrated images through the recovery of the unknown epipolar geometry. ArtificialIntelligence,1995,78(1/2):87-119P
[54] Golub G H, Van L C F. Matrix computations.3Editions. Johns Hopkins UniversityPress, Baltimore, MaryLand,1996:1-694P
[55] Ahmed M, Farag A. Nonmetric calibration of camera lens distortion: differentialmethods and robust estimation. IEEE Transactions on image processing,2005,14(8):1215-1230P
[56]张浩鹏,王宗义.基于灰度方差和边缘密度的车牌定位算法.仪器仪表学报,2011,32(5):1095-1102页
[57] Li Y R, Shen L X, Dai D Q, et al. Framelet algorithms for de-blurring imagescorrupted by impulse plus gaussian noise. IEEE Transactions on Image Processing,2011,20(7):1822-1837P
[58]陈树越,路宏年.基于行列处理消除正向脉冲噪声非线性滤波器.仪器仪表学报,2000,21(5):458-463页
[59] Srinivasan K S, Ebenezer D. A new fast and efficient decision-based algorithm forremoval of high-density impulse noises. IEEE Signal Processing Letters,2007,14(3):189–192P
[60] Luo W B. Efficient removal of impulse noise from digital images. IEEE Transactionson Consumer Electronics,2006,52(2):523-527P
[61] Choi K S, Ko S J. New autofocusing technique using the frequency selective weightedmedian filter for video cameras. International Conference on Consumer Electronics,CA, USA,1999:160-161P
[62] Dong Y Q, Chan R H, Xu S. A detection statistic for random-valued impulse noise.IEEE Transactions on Image Processing,2007,16(4):1112-1120P
[63]王建勇,周晓光,廖启征.一种基于中值-模糊技术的混合噪声滤波器.电子与信息学报,2006,28(5):901-904页
[64] Ibrahim H, Kong N S P, Ng T F. Simple adaptive median filter for the removal ofimpulse noise from highly corrupted images. IEEE Transactions on ConsumerElectronics,2008,54(4):1920-1927P
[65] Petrovic N I, Crnojevic V. Universal impulse noise filter based on geneticprogramming. IEEE Transactions on Image Processing,2008,17(7):1109-1120P
[66] Toh K K V, Isa N A M. Noise adaptive fuzzy switching median filter forsalt-and-pepper noise reduction. IEEE Signal Processing Letters,2010,17(3):281-284P
[67] Ng P E, Ma K K. A switching median filter with boundary discriminative noisedetection for extremely corrupted images. IEEE Transactions on Image Processing,2006,15(6):1506-1516P
[68] Dong Y Q, Xu S. A new directional weighted median filter for removal ofrandom-valued impulse noise. IEEE Signal Processing Letters,2007,14(3):193-196P
[69] Luo W B. An efficient algorithm for the removal of impulse noise from corruptedimages. International Journal of Electronics Communications,2007,61(8):551-555P
[70] Zhang J J. An efficient median filter based method for removing random-valuedimpulse noise. Digital Signal Processing: A Review Journal,2010,20(4):1010-1018P
[71] Civicioglu P. Using uncorrupted neighborhoods of the pixels for impulsive noisesuppression with ANFIS. IEEE Transactions on Image Processing,2007,16(3):759-773P
[72] Civicioglu P. Removal of random-valued impulsive noise from corrupted images.IEEE Transactions on Consumer Electronics,2009,55(4):2097-2104P
[73] Russo F, Ramponi G. Fuzzy filter for images corrupted by impulse noise. IEEE SignalProcessing Letters,1996,3(6):168-170P
[74] Sun T, Neuvo Y. Detail-preserving median based filters in image processing. PatternRecognition Letters,1994,15(4):341-347P
[75] Chan R H, Ho C W, Nikolova M. Salt-and-pepper noise removal by median-type noisedetectors and detail-preserving regularization. IEEE Transactions on Image Processing,2005,14(10):1479-1485P
[76]刘伟嵬,颜云辉,孙宏伟.基于邻域评价法的带钢表面缺陷图像脉冲噪声去除.仪器仪表学报,2008,29(9):1846-1850页
[77] Chen T, Ma K K, Chen L H. Tri-state median-based filters in image denoising. IEEETransactions on Image Processing,1999,8(12):1834-1838P
[78] Chen T, Wu H R. Adaptive impulse detection using center-weighted median filters.IEEE Signal Processing Letters,2001,8(1):1-3P
[79] Wu J, Tang C. PDE-based random-valued impulse noise removal based on new classof controlling functions. IEEE Transactions on Image Processing,2011,20(9):2428-2438P
[80] Civicioglu P. Using uncorrupted neighborhoods of pixels for impulsive noisesuppression with ANFIS. IEEE Transactions on Image Processing,2007,16(3):759-773P
[81] Russo F, Ramponi G. Fuzzy filter for images corrupted by impulse noise. IEEE SignalProcessing Letters,1996,3(6):168-170P
[82]杜亚勤,洪波,郭雷等.一种曲面拟合图像边缘特征提取算法.西安电子科技大学学报(自然科学版),2011,38(3):164-168页
[83]李晖,肖鹏峰,冯学智等.基于向量场模型的多光谱遥感图像多尺度边缘检测.测绘学报,2012,41(1):100-107页
[84]黄茜,吴炜峰,董肖.基于局部尺度控制的模糊边缘检测算法.模式识别与人工智能,2011,24(6):875-881页
[85]周树道,王敏,刘志华等.基于多方向小波变换及形态学重构的SAR图像边缘检测.解放军理工大学学报(自然科学版),2011,12(5):436-439页
[86]胡晓辉,张晓颖,陈俊莲.一种融合小波变换和数学形态学的图像边缘检测算法.铁道学报,2011,33(3):45-48页
[87]黄海龙,王宏.一种基于小波变换和数学形态学的边缘检测算法.东北大学学报(自然科学版),2011,32(9):1315-1318页
[88]肖易寒,席志红,海涛等.基于非下采样contourlet变换的图像边缘检测新方法.系统工程与电子技术,2011,33(7):1668-1672页
[89]艾泽潭,石庚辰,熊鑫等.基于模糊梯度的微齿轮图像边缘检测算法.北京理工大学学报,2011,31(8):919-921页
[90]唐永鹤,卢焕章.基于多结构元素复合滤波的形态学边缘检测.武汉大学学报信息科学版,2012,37(1):50-53页
[91]何嘉懿,廖桂生,杨志伟.多目标航迹的图像域自适应检测方法.兵工学报,2011,32(6):663-667页
[92]刘勇,姚刚,肖人彬等.自适应多窗口梯度幅值边缘检测算法.华中科技大学学报(自然科学版),2011,39(1):14-18页
[93]曹传东,徐贵力,陈欣等.基于力场转换理论的图像粗大边缘检测方法.航空学报,2011,32(5):891-899页
[94]朱自强,曾思红,鲁光银.重力张量数据的目标体边缘检测方法.探讨石油地球物理勘探,2011,46(3):482-487页
[95] Canny J. A computational approach to edge detection. IEEE Transcations on PatternAnalysis and Machine Intelligence,1986,8(6):679-698P
[96] Lee S U, Chung S Y. A comparative performance study of several global thresholdingtechniques for segmentation. Computer Vision, Graphics, and Image Processing,1990,52(2):171-190P
[97] Wang H, Brady M. Real time corner detection algorithm for motion estimation. Imageand Vision Computing,1995,13(9):695-703P
[98] Trajkovic M, Hedley M. Fast corner detection. Image and Vision Computing,1998,16(2):75-87P
[99] Smith S M, Brady J M. SUSAN-a new approach to low level image Processing.International Journal of Computer Vision,1997,23(1):45-78P
[100]张浩鹏,王宗义.基于小波的多尺度SUSAN角点检测.光电工程,2009,36(11):100-105页
[101] Harris C, Stephens M. A combined corner and edge detector. Alvey Vision Conference,1988:147-151P
[102] Xu Q, Chakrabarti C, Karam L J. A distributed canny edge detector and itsimplementation on FPGA. Digital Sianal Processing and Signal Processing EducationMeeting, Sedona, AZ, US,2011:500-505P
[103] Xu Z D, Yuan K, He W H. An implementation method of Canny edge detectionalgorithm on FPGA. International Conference on Electric Information and ControlEngineering, Wuhan, China,2011:3958-3962P
[104] Awrangjeb M, Lu G J, Murshed M. An affine resilient curvature scale-space cornerdetector. IEEE International Conference on Acoustics, Speech and Signal Processing,Honolulu, HI, US,2007: I1233–I1236P
[105] Rattarangsi A, Chin R T. Scale-based detection of corners of planar curves. IEEETransactions on Pattern Analysis and Machine Intelligence,1992,14(4):430–449P
[106] Zhong B J, Liao W H. Direct curvature scale space: Theory and corner detection. IEEETransactions on Pattern Analysis and Machine Intelligence,2007,29(3):508–512P
[107] Ray B K, Pandyan R. ACORD-an adaptive corner detector for planar curves. PatternRecognition,2003,36(3):703–708P
[108] Mokhtarian F, Suomela R. Robust image corner detection through curvature scalespace. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381P
[109] Mokhtarian F, Mohanna F. Fusion of corners from multiple scales for robust tracking.Proceedings of Joint Conference on Information Sciences, Research Triange Park, NC,US,2002:765-768P
[110] Zhang X H, Lei M, Yang D, et al. Multi-scale curvature product for robust imagecorner detection in curvature scale space. Pattern Recognition Letters,2007,28(5):545–554P
[111] He X C, Yung N H C. Curvature scale space corner detector with adaptive thresholdand dynamic region of support. Proceedings-International Conference on PatternRecognition, Cambridge, UK,2004:791–794P
[112]王耀贵.图像高斯平滑滤波分析.计算机与信息技术,2008,8(1):79-90页
[113] Mokhtarian F, Abbasi S. Affine curvature scale space with affine lengthparametrisation. Pattern Analysis&Applications,2001,4(1):1-8P
[114] Awrangjeb M, Lu G F. A robust corner matching technique. Proceedings of the2007IEEE International Conference on Multimedia and Expo, Beijing, China,2007:1483-1486P
[115] Han J H, Poston T. Chord-to-point distance accumulation and planar curvature: A newapproach to discrete curvature. Pattern Recognition Letters,2001,22(10):1133–1144P
[116] Rosenfeld A, Johnston E. Angle detection on digital planar curves. IEEE Transactionson Computers.1973,22(9):875–878P
[117]曲学军,张璐,张凌云.基于新的成像模型的摄像机标定与三维重建.仪器仪表学报,2011,32(8):1830-1836页
[118]张文明,刘彬,李海滨.基于双目视觉的三维重建中特征点提取及匹配算法的研究.光学技术,2008,34(2):181-185页
[119] Tang A W K, Ng T P, Hung Y S, et al. Projective Reconstruction fromLine-Correspondences in Multiple Uncalibrated Images. Pattern Recognition,2006,39(5):889-896P
[120] Aider O A, Hoppenot P, Colle E. A Model-Based Method for Indoor Mobile RobotLocalization Using Monocular Vision and Straight-Line Correspondences. Roboticsand Autonomous Systems,2005,52(2/3):229-246P
[121] Shi F H, Wang J H, Zhang J, et al. Motion Segmentation of Multiple TranslationObjects from Line Correspondences. Pattern Recognition,2005,38(10):1775-1778P
[122] Bartoli A, Sturm P. Multiple-View Structure and Motion from Line Correspondences.Proceedings of the IEEE International Conference on Computer Vision, Nice, France,2003:207-212P
[123] Belongie S, Malik J, Puzicha J. Shape Matching and Object Recognition Using ShapeContexts. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(4):509-522P
[124] Lowe D G. Distinctive Image Features from Scale-Invariant Key-points. InternationalJournal of Computer Vision,2004,60(2):91-110P
[125] Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for Local ImageDescriptors. Proceedings of the IEEE Computer Society Conference on ComputerVision and Pattern Recognition. Washington, DC, US,2004:II506-II513P
[126] Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630P
[127] Mikolajczyk K, Zisserman A, Schmid C. Shape Recognition with Edge-Based Features.British Machine Vision Conference. Norwich, UK,2003:779-788P
[128] Matas J, Chum O, Urban M, et al. Robust Wide Baseline Stereo from MaximallyStable Extremal Regions. Image and Vision Computing,2004,22(10):761-767P
[129] Schmid C, Zisserman A. Automatic Line Matching across Views. Proceedings of theIEEE Computer Society Conference on Computer Vision and Pattern Recognition. SanJuan, PR, USA,1997:666-671P
[130] Deng Y, Lin X Y. A Fast Line Segment Based Dense Stereo Algorithm Using TreeDynamic Programming. Proceedings of the9th European Conference on ComputerVision. Graz, Austria,2006:201-212P
[131] Kletter R, Koschan A, Schluns K. Computer vision three-dimensional data fromimages.1st. Springer-Verlag Singapore Pte,1998:67-83P
[132] Han J H, Park J S. Contour matching using epipolar geometry ligence. IEEETransactions on Pattern Analysis and Machine Intelligence,2000,22(4):358-370P
[133] Yuan M L, Xie M, Yin X M. Rubust cooperative strategy for contour matching usingepipolar geometry. Asian Conference on Computer Vision,2002:1-10P
[134] Moallem P, Faez K. Effective parameters in search space reduction used in a fastedge-based stereo matching. Journal of Circuits, Systems and Computers,2005,14(2):249-266P
[135] Moallem P, Ashourian M, Mirzaeian B. A novel fast feature based stereo matchingalgorithm with low invalid matching. WSEAS Transactions on Computers,2006,5(3):469-476P
[136] Fusiello A, Trucco E, Verri A. Compact algorithm for rectification of stereo pairs.Machine Vision and Applications,2000,12(1):16-22P
[137] Oram D. Rectification for any epipolar Geometry. Proceedings of the British MachineVision Conference, Manchester, UK,2001:653-662P
[138]张淮峰, Jan C, Radim S等.三视校正的理论及鲁棒性算法.软件学报,2004,15(5):676-688页
[139] Egnal G, Wildes R P. Detecting Binocular Half-Occlusions: Empirical Comparisons ofFour Approaches. Proceedings of the IEEE Computer Society Conference onComputer Vision and Pattern Recognition. Hilton Head Island, SC, USA,2000:466-473P
[140] Weng J W, Cohen P, Herniou M. Camera calibration with distortion models andaccuracy evaluation. Transactions on Pattern Analysis and Machine Intelligence,1992,14(10):965-980P
[141] Miida T, Kawajiri K, Terakago H, et al. A1.5Mpixel imager with localizedhole-modulation method. International Solid-State Circuits Conference, CA, US,2002:42-43P
[142]张益昕.基于计算机视觉的大尺度三维几何尺寸测量方法及应用.南京大学博士学位论文.2011:11-26页
[143]王志衡,吴福朝.均值-标准差描述子与直线匹配.模式识别与人工智能,2009,22(1):32-39页
[144]周富强,邾继贵,杨学友等.双目视觉传感器的现场标定方法.仪器仪表学报,2000,21(2):142-145页
[145]李秀智,张广军.三目视觉图像的极线校正方法.光电工程,2007,34(10):50-54页
[146]侯建,齐乃明.月球车视觉系统立体匹配算法研究.南京理工大学学报(自然科学版),2008,32(2):176-180页