基于网格标记的视觉坐标测量技术
|
摘要
本论文对视觉坐标测量技术进行了系统的研究，建立了一个基于网格标记的四目视觉坐标测量系统的模型，并基于这一模型研制了一台四目视觉坐标测量仪，这一仪器用于金属板料变形过程的应变测量，得到了较好的效果。
本论文提出的基于网格标记的四目视觉坐标测量系统的模型首先需要在被测量物体上覆盖一层特殊的网格，把网格点作为测量特征点来处理，通过对带有网格标记的图象对的处理、计算，得到网格点的三维坐标。本论文着重研究了针对带有网格标记的图象这个特殊的处理对象进行图象处理、立体匹配等算法的优化的问题，提出或者改进了一些可行的算法。同时该系统采用四个摄象机作为图象采集源，本论文从理论上对这种特殊的测量模型进行了分析，设计了坐标计算的算法。具体来说研究结果包括以下几个部分：
1．摄象机标定以及空间点三维坐标计算。根据系统的精度要求，摄象机模型的选择的是线性模型。论文提出了基于网格标记的线性摄象机的标定方法，建立了基于线性摄象机模型的立体视觉模型，并设计了四台摄象机匹配进行空间点三维坐标计算的算法。
2．图象采集与处理。设计了硬件独立的图象采集接口。基于网格标记图象，设计了一系列的合理的图象处理步骤，包括图象分割并二值化、二值图象闭运算、细化以及基于B样条插值的亚象素图象处理技术。系统的图象处理算法都是根据网格标记这个特殊的处理对象进行重新设计或者优化设计的。其中独立设计了自适应的移动窗口灰度阈值图象分割法，优化设计了并行模板匹配细化算法，独立提出了基于三次均匀B样条插值放大局部图象的亚象素图象处理算法，并都取得了较好的处理效果。
3．网格点提取以及匹配。基于以前研究者的工作，提出了从细化网格图象中提取网格点的算法。独立的提出了基于网格点相邻关系建立二维表格的网格点匹配算法。
4．坐标数据的后处理。设计了通用的三维显示模块以及后处理数据接口，方便了系统功能的扩展。
After systematic researches on computer vision coordinate measurement techniques, this paper proposed a Four-eyed Vision Coordinate Measurement Model (FVCMM) based on Rectangular Grid Mark. A Four-eyed Vision Coordinate Measurement System (FVCMS) was constructed based on this model. It was firstly applied to strain measurement during the process of metal plate deformation and gained some success.
In the FVCMM proposed in this paper, a special designed rectangular grid mark is required to be attached to the surface of the object. The grid nodes on the surface are treated as measurement marks. The 3-Dimensional coordinates of these grid nodes are calculated through processing the grid images which captured by four cameras.
This paper paid most efforts on the algorithms of image processing and stereo corresponding of the grid nodes concerning the special objects - grid images. Some applicable algorithms are proposed or improved. The FVCMS employed four cameras as image acquisition source. This paper built a theoretical model of this kind of measuring method and designed coordinate calculation algorithm.
In summary, the research result described in this paper includes four parts.
1. Camera calibration and 3-Dimensional coordinates' calculation. Regarding the precision requirement of the system, a simple linear camera model is selected and a calibration method based on grid image is proposed. Based on linear camera model, this paper constructed a stereo vision model and designed an algorithm for 3-Dimensional coordinates' calculation through four cameras.
2. Image acquisition and processing. A hardware independent image acquisition interface is designed. Aimed at grid images, a reasonable image processing procedure is employed, including segmentation, binarization, close, thinning and sub-pixel image processing technique based on B-spline interpolation. The algorithms employed in this paper are redesigned or improved for grid images. For example, an adaptable moving window gray scale threshold image segmentation method is proposed originally, a parallel template matching thinning algorithm is improved greatly, a sub-pixel image processing algorithm based on B-spline interpolation is present independently.
3. Grid nodes extraction and corresponding. Based on former researcher's works, an algorithm for grid nodes extraction from thinned grid image is present. A brand new method of grid nodes corresponding is proposed based on 2-Dimensional Neighbor Node Table.
4. Coordinate data visualization. A general 3-Dimensional coordinate data visualization model and a general post-processing data interface are designed for extension of the system's function.
本论文提出的基于网格标记的四目视觉坐标测量系统的模型首先需要在被测量物体上覆盖一层特殊的网格，把网格点作为测量特征点来处理，通过对带有网格标记的图象对的处理、计算，得到网格点的三维坐标。本论文着重研究了针对带有网格标记的图象这个特殊的处理对象进行图象处理、立体匹配等算法的优化的问题，提出或者改进了一些可行的算法。同时该系统采用四个摄象机作为图象采集源，本论文从理论上对这种特殊的测量模型进行了分析，设计了坐标计算的算法。具体来说研究结果包括以下几个部分：
1．摄象机标定以及空间点三维坐标计算。根据系统的精度要求，摄象机模型的选择的是线性模型。论文提出了基于网格标记的线性摄象机的标定方法，建立了基于线性摄象机模型的立体视觉模型，并设计了四台摄象机匹配进行空间点三维坐标计算的算法。
2．图象采集与处理。设计了硬件独立的图象采集接口。基于网格标记图象，设计了一系列的合理的图象处理步骤，包括图象分割并二值化、二值图象闭运算、细化以及基于B样条插值的亚象素图象处理技术。系统的图象处理算法都是根据网格标记这个特殊的处理对象进行重新设计或者优化设计的。其中独立设计了自适应的移动窗口灰度阈值图象分割法，优化设计了并行模板匹配细化算法，独立提出了基于三次均匀B样条插值放大局部图象的亚象素图象处理算法，并都取得了较好的处理效果。
3．网格点提取以及匹配。基于以前研究者的工作，提出了从细化网格图象中提取网格点的算法。独立的提出了基于网格点相邻关系建立二维表格的网格点匹配算法。
4．坐标数据的后处理。设计了通用的三维显示模块以及后处理数据接口，方便了系统功能的扩展。
After systematic researches on computer vision coordinate measurement techniques, this paper proposed a Four-eyed Vision Coordinate Measurement Model (FVCMM) based on Rectangular Grid Mark. A Four-eyed Vision Coordinate Measurement System (FVCMS) was constructed based on this model. It was firstly applied to strain measurement during the process of metal plate deformation and gained some success.
In the FVCMM proposed in this paper, a special designed rectangular grid mark is required to be attached to the surface of the object. The grid nodes on the surface are treated as measurement marks. The 3-Dimensional coordinates of these grid nodes are calculated through processing the grid images which captured by four cameras.
This paper paid most efforts on the algorithms of image processing and stereo corresponding of the grid nodes concerning the special objects - grid images. Some applicable algorithms are proposed or improved. The FVCMS employed four cameras as image acquisition source. This paper built a theoretical model of this kind of measuring method and designed coordinate calculation algorithm.
In summary, the research result described in this paper includes four parts.
1. Camera calibration and 3-Dimensional coordinates' calculation. Regarding the precision requirement of the system, a simple linear camera model is selected and a calibration method based on grid image is proposed. Based on linear camera model, this paper constructed a stereo vision model and designed an algorithm for 3-Dimensional coordinates' calculation through four cameras.
2. Image acquisition and processing. A hardware independent image acquisition interface is designed. Aimed at grid images, a reasonable image processing procedure is employed, including segmentation, binarization, close, thinning and sub-pixel image processing technique based on B-spline interpolation. The algorithms employed in this paper are redesigned or improved for grid images. For example, an adaptable moving window gray scale threshold image segmentation method is proposed originally, a parallel template matching thinning algorithm is improved greatly, a sub-pixel image processing algorithm based on B-spline interpolation is present independently.
3. Grid nodes extraction and corresponding. Based on former researcher's works, an algorithm for grid nodes extraction from thinned grid image is present. A brand new method of grid nodes corresponding is proposed based on 2-Dimensional Neighbor Node Table.
4. Coordinate data visualization. A general 3-Dimensional coordinate data visualization model and a general post-processing data interface are designed for extension of the system's function.
引文
[1] 祝世平，申功勋等．工件特征点三维坐标非视觉测量方法综述．光学精密工程，1999，7(5)：22-29．
[2] 张之江，车仁生等．仿生计量学的新领域—视觉坐标测量机．字航计测技术，1998，18(4)：13-17．
[3] 祝世平，强锡富．工件特征点三维坐标视觉测量方法综述．光学精密工程，2000，8(2)：192-197．
[4] 张吉华等．激光三角法轮廓测量．天津大学学报，1995，28(2)：265-269．
[5] 王晓尔．空间机器人激光测距传感器系统的研制．哈尔滨：哈尔滨工业大学博士学位论文：1995．
[6]唐朝伟等．三维曲面激光精密测量技术．计量学报．1994，15(2)：99-103．
[7] Yoshida K, et al. Laser Triangulation Range Finder Available Under Direct Sunlight. Proc. of the 1988 IEEE International Conf. on Robotics and Automation. 1988:1702-1708.
[8] Bakos G C, et al. Long distance non-contact high precision measurements. International Journal of Electronics. 1993,75(6): 1269-1279.
[9] Tamura S, et al. Error correction in laser scanner three-dimensional measurement by two-axis model and coarse-fine parameter search. Pattern Recogniton. 1994,27(3):331-338.
[10] 陈伟民等．双光源光切法三维轮廓测量的误差分析．仪器仪表学报．1996，17(2)：149-153．
[11] Greer D. Online machine vision sensor measurnments ina coordinate systm. Proc. Of SME Robots 12 and Vision'88. 1988,1(5):43-50.
[12] Dewar R. Self-generated targets for spatial calibration of structured-light optical sectioning sensors with respect td an external coordinate system. Proc. Of SME Robots 12 and Vision'88. 1988,1(5): 13-21.
[13] Maruyama T, et al. Hand-eye system with three-dimensional vision and microgripper for handing flexiable wire. Machine Vision and Applications. 1990,3(4): 189-199.
[14] Araki K, et al. A high-speed and continuous 3D measurement system. Machine Vision and Applications. 1995,8(2):79-84.
[15] Dewitt T D, et al. Range-finding method using diffraction gratings. Applied Optics. 1995,34(14):2501-2521.
[16] Bhatnagar D, et al. Static scene analysis using structured light. Image and Vision Computing. 1991,9(2):82-87.
[17] Maruyama M, et al. Range sensing by projecting multiple sites with random cuts. IEEE Trans on Pattern Analysis and Machine Intelligence. 1993,15(6):647-651.
[18] Yee S R, et al. Three-dimensional imaging system. Optical Engineering. 1994,33(6):2070-2075.
[19] Commean P K, et al. Geometric design of a multisensor structerd light range digitizer. Optical
Engineering. 1994,33(4) :1349-1358．
[20] Godhwanl A, et al. Calibration of a multisensor structured lighrrange scanner. Optical Engineering. 1994,33(4) : 1359-1367．
[21] Chen Z, et al. Measuring 3D location and shape parameters of cylinders by a spatial encoding technique. IEEE Trans. On Robotis and Automation. 1994,10(5) :632-647．
[22] Ho M, et al. A three-level checkerboard pattern(TCP) projection method for curved surface measurement. Pattern Recognition. 1995,28(1) :27-40．
[23] Zou D H, et al. Structured-lighting surface sensor and its calibration. Optical Engineering. 1995,34(10) :3040-3043,
[24] Boyer K L, et al. Color-encoded structured light for rapid active ranging. IEEE Trans. on Pattern Analysis and Machine Intelligence. 1987,9(1) :14-28．
[25] Akuta T, et al. Development of an automatic 3D shape measuring system using a new auto-focusing method. Measurement. 1991,9(3) :98-103．
[26] 吴晓峰．激光自动聚焦三维形状测量系统的研究．仪器仪表学报．1996． 17(2) ：129-131．
[27] Shan Y C, et al. Anew technique to extract range information from stereo image. IEEE Trans on Pattern Analysis and Machine Intelligence. 1989,11(7) :768-773．
[28] 吴立德．计算机视觉．上海：复且大学出版社，1993．
[29] Herman M. Matching three-dimensional symbolic descriptions obtained from multiple view of a scene. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 1985:585-590．
[30] Weng J Y. A theory of image matching. IEEE Computer Society Conf. Compuer Vision and Pattern Recognition, 1990:200-209．
[31] Weng J Y, et al. Matching two perspective views. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1992,14(8) :806-825．
[32] Zhang YN. Integration of segmentation and stereo matching. Proc. SPIE, 1993,2094:848-857．
[33] Marapane S B, et al. Multi-primitive hierarchical(MPH) stereo analysis. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1994,16(3) :227-240．
[34] Cochran S D, et al. 3-D surface description from binocular stereo. IEEE Trans. on.Pattern Analysis and Machine Intelligence,1992,14(10) :981-994．
[35] Kanade T, et al. A stereo matching algorithm with an adaptive window:Theory and Experiment. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1994,16(9) :920-932．
[36] Kim Y C, et al. Positioning three-dimensional objects using stereo images. IEEE Journal of Robotics and Automation, 1987,3(4) :361-373．
[37] EL-Hakim S F, et al. The VCM automated 3-D measurement system, theory, application and performance evaluation. Proc. SPIE, 1992,1708:460-482．
[38] 林宗坚等．由双目序列影象解求运动参数的非立体匹配方法．武汉测绘科技大学学报，1994，19(1)：1-6．
[39] 杨敬安．由双目图象流无对应地估计3-D运动参数．计算机学报，1995，18(11)：849-857．
[40] Dhond U R, et al. A Cost-benefit analysis of a third camera for stereo correspondence. International Journal of Computer Vision, 1991,6(1):39-58.
[41] Ayache N, et al. Trinocular stereo vision for robotics. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1991,13(1):73-85.
[42] Subbarao M, et al. Depth recovery from blurred edge. IEEE Computer Society Conf. Computer Vision and Pattern Recognition,1988:498-503.
[43] Ens J, et al. An investigation of methods for determining depth from focus. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1993,15(2):97-108.
[44] 张业鹏，何涛等．机器视觉在工业测量中的应用与研究．光学精密工程，2001，9(4)：324-329．
[45] 金隼，曹立波等．汽车车身模型立体视觉测量系统工程设计，1992，2：28-31．
[46] 解则晓，徐玉春等．四轴自由曲面非接触测量系统．航空精密制造技术，2002，38(1)：31-33．
[47] 阳道善，陈吉红等．线结构激光—机器视觉三角测量光路设计．光学技术，2001，27(2)：120-122．
[48] 刘维一，于德月等．用彩色二维编码测量动态物体三维轮廓的方法．光电子激光，2002，13(2)：169-172．
[49] 吕乃光，桑新柱等．用于微波天线的三维面形测量技术．华中科技大学学报(自然科学版)，2002，30(5)：16-18．
[50] 张之江，车仁生等．测头成象视觉坐标测量系统组成、建模及求解．哈尔滨工业大学学报，1999，31(4)：69-73．
[51] 吕乃光，冯迪等．用BP神经网络构成三维视觉测量系统的新方法．华中科技大学学报(自然科学版)，2002，30(5)：19-21．
[52] 章毓晋．图象工程(上)—图象处理和分析．北京：清华大学出版社，2000．1-46，81-106．
[53] 章毓晋．图象工程(下)—图象理解与计算机视觉．北京：清华大学出版社，2000．179-215，254-277．
[54] 马颂德，张正友．计算机视觉(计算理论与算法基础)．北京：科学出版社，1998．1-65．
[55] K．R．Castleman，朱志刚等译．数字图象处理．北京：电子工业出版社，1998．60-120，387-442．
[56] 吴健康．数字图象分析．北京：人民邮电出版社，1989．79-155．
[57] 邱茂林，马颂德，李毅．计算机视觉中摄象机定标综述．自动化学报，2000，26(1)：43-55．
[58] 田思，袁占亭．计算机视觉系统框架的新构思．计算机工程与应用，2000，36(6)：57-59．
[59] 黄海，戚飞虎．利用遗传锋法精确标定摄象机参数．上海交通大学学报，2000，34(7)：948-951．
[60] L.Guisser, R.Payrissat, S. Castan. PGSD: an accurate 3D vision system using a projected grid for
surface descriptions. Image and Vision Computing, 2000, 18: 463-491.
[61] 周新伦，韦剑，李锋．一种并行细化算法及其硬件实现方案．模式识别与人工智能，1994，7(1)：1-6．
[62] 张毓晋．图象分割．北京：科学出版社，2001．
[63] 崔屹．图象处理与分析—数学形态学方法及应用．北京：科学出版社，2000．
[64] 邱慧敏，杨济安．B样条函数与图象边缘检测．四川通信技术，2000，30(3)：5-8．
[65] 李艳，彭嘉雄．基于D_2样样条插值和LOG算子的亚象素边缘检测．华中理工大学学报，2000，28(3)：77-79．
[66] 候成刚，赵明涛，屈梁生．基于二次曲面拟合的亚象素图象匹配算法．计量学报，1997，18(3)：227-230．
[67] 董汉莉，王洪林，李东君．利用样条函数的图象边缘精确定位算法研究．信息工程学院学报，1997，16(4)：10-13．
[68] 李永忠．B样条小波在图象边缘检测中的应用研究．西北民族学院学报，1999，20(3)：10-13．
[69] 许志祥．二阶导数型边缘检测算子边缘定位误差的研究．自动化学报，1992，18(4)：448-455
[70] 吴焕明，方漪．基于计算机立体视觉的图象测量技术．第一届全国几何设计与计算学术会议(2002)，2002年6月：312-318
[71] 吴焕明，方漪．基于计算机立体视觉的图象测量技术．工程图学学报，2002，23(4)：60-67
[2] 张之江，车仁生等．仿生计量学的新领域—视觉坐标测量机．字航计测技术，1998，18(4)：13-17．
[3] 祝世平，强锡富．工件特征点三维坐标视觉测量方法综述．光学精密工程，2000，8(2)：192-197．
[4] 张吉华等．激光三角法轮廓测量．天津大学学报，1995，28(2)：265-269．
[5] 王晓尔．空间机器人激光测距传感器系统的研制．哈尔滨：哈尔滨工业大学博士学位论文：1995．
[6]唐朝伟等．三维曲面激光精密测量技术．计量学报．1994，15(2)：99-103．
[7] Yoshida K, et al. Laser Triangulation Range Finder Available Under Direct Sunlight. Proc. of the 1988 IEEE International Conf. on Robotics and Automation. 1988:1702-1708.
[8] Bakos G C, et al. Long distance non-contact high precision measurements. International Journal of Electronics. 1993,75(6): 1269-1279.
[9] Tamura S, et al. Error correction in laser scanner three-dimensional measurement by two-axis model and coarse-fine parameter search. Pattern Recogniton. 1994,27(3):331-338.
[10] 陈伟民等．双光源光切法三维轮廓测量的误差分析．仪器仪表学报．1996，17(2)：149-153．
[11] Greer D. Online machine vision sensor measurnments ina coordinate systm. Proc. Of SME Robots 12 and Vision'88. 1988,1(5):43-50.
[12] Dewar R. Self-generated targets for spatial calibration of structured-light optical sectioning sensors with respect td an external coordinate system. Proc. Of SME Robots 12 and Vision'88. 1988,1(5): 13-21.
[13] Maruyama T, et al. Hand-eye system with three-dimensional vision and microgripper for handing flexiable wire. Machine Vision and Applications. 1990,3(4): 189-199.
[14] Araki K, et al. A high-speed and continuous 3D measurement system. Machine Vision and Applications. 1995,8(2):79-84.
[15] Dewitt T D, et al. Range-finding method using diffraction gratings. Applied Optics. 1995,34(14):2501-2521.
[16] Bhatnagar D, et al. Static scene analysis using structured light. Image and Vision Computing. 1991,9(2):82-87.
[17] Maruyama M, et al. Range sensing by projecting multiple sites with random cuts. IEEE Trans on Pattern Analysis and Machine Intelligence. 1993,15(6):647-651.
[18] Yee S R, et al. Three-dimensional imaging system. Optical Engineering. 1994,33(6):2070-2075.
[19] Commean P K, et al. Geometric design of a multisensor structerd light range digitizer. Optical
Engineering. 1994,33(4) :1349-1358．
[20] Godhwanl A, et al. Calibration of a multisensor structured lighrrange scanner. Optical Engineering. 1994,33(4) : 1359-1367．
[21] Chen Z, et al. Measuring 3D location and shape parameters of cylinders by a spatial encoding technique. IEEE Trans. On Robotis and Automation. 1994,10(5) :632-647．
[22] Ho M, et al. A three-level checkerboard pattern(TCP) projection method for curved surface measurement. Pattern Recognition. 1995,28(1) :27-40．
[23] Zou D H, et al. Structured-lighting surface sensor and its calibration. Optical Engineering. 1995,34(10) :3040-3043,
[24] Boyer K L, et al. Color-encoded structured light for rapid active ranging. IEEE Trans. on Pattern Analysis and Machine Intelligence. 1987,9(1) :14-28．
[25] Akuta T, et al. Development of an automatic 3D shape measuring system using a new auto-focusing method. Measurement. 1991,9(3) :98-103．
[26] 吴晓峰．激光自动聚焦三维形状测量系统的研究．仪器仪表学报．1996． 17(2) ：129-131．
[27] Shan Y C, et al. Anew technique to extract range information from stereo image. IEEE Trans on Pattern Analysis and Machine Intelligence. 1989,11(7) :768-773．
[28] 吴立德．计算机视觉．上海：复且大学出版社，1993．
[29] Herman M. Matching three-dimensional symbolic descriptions obtained from multiple view of a scene. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 1985:585-590．
[30] Weng J Y. A theory of image matching. IEEE Computer Society Conf. Compuer Vision and Pattern Recognition, 1990:200-209．
[31] Weng J Y, et al. Matching two perspective views. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1992,14(8) :806-825．
[32] Zhang YN. Integration of segmentation and stereo matching. Proc. SPIE, 1993,2094:848-857．
[33] Marapane S B, et al. Multi-primitive hierarchical(MPH) stereo analysis. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1994,16(3) :227-240．
[34] Cochran S D, et al. 3-D surface description from binocular stereo. IEEE Trans. on.Pattern Analysis and Machine Intelligence,1992,14(10) :981-994．
[35] Kanade T, et al. A stereo matching algorithm with an adaptive window:Theory and Experiment. IEEE Trans, on Pattern Analysis and Machine Intelligence, 1994,16(9) :920-932．
[36] Kim Y C, et al. Positioning three-dimensional objects using stereo images. IEEE Journal of Robotics and Automation, 1987,3(4) :361-373．
[37] EL-Hakim S F, et al. The VCM automated 3-D measurement system, theory, application and performance evaluation. Proc. SPIE, 1992,1708:460-482．
[38] 林宗坚等．由双目序列影象解求运动参数的非立体匹配方法．武汉测绘科技大学学报，1994，19(1)：1-6．
[39] 杨敬安．由双目图象流无对应地估计3-D运动参数．计算机学报，1995，18(11)：849-857．
[40] Dhond U R, et al. A Cost-benefit analysis of a third camera for stereo correspondence. International Journal of Computer Vision, 1991,6(1):39-58.
[41] Ayache N, et al. Trinocular stereo vision for robotics. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1991,13(1):73-85.
[42] Subbarao M, et al. Depth recovery from blurred edge. IEEE Computer Society Conf. Computer Vision and Pattern Recognition,1988:498-503.
[43] Ens J, et al. An investigation of methods for determining depth from focus. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1993,15(2):97-108.
[44] 张业鹏，何涛等．机器视觉在工业测量中的应用与研究．光学精密工程，2001，9(4)：324-329．
[45] 金隼，曹立波等．汽车车身模型立体视觉测量系统工程设计，1992，2：28-31．
[46] 解则晓，徐玉春等．四轴自由曲面非接触测量系统．航空精密制造技术，2002，38(1)：31-33．
[47] 阳道善，陈吉红等．线结构激光—机器视觉三角测量光路设计．光学技术，2001，27(2)：120-122．
[48] 刘维一，于德月等．用彩色二维编码测量动态物体三维轮廓的方法．光电子激光，2002，13(2)：169-172．
[49] 吕乃光，桑新柱等．用于微波天线的三维面形测量技术．华中科技大学学报(自然科学版)，2002，30(5)：16-18．
[50] 张之江，车仁生等．测头成象视觉坐标测量系统组成、建模及求解．哈尔滨工业大学学报，1999，31(4)：69-73．
[51] 吕乃光，冯迪等．用BP神经网络构成三维视觉测量系统的新方法．华中科技大学学报(自然科学版)，2002，30(5)：19-21．
[52] 章毓晋．图象工程(上)—图象处理和分析．北京：清华大学出版社，2000．1-46，81-106．
[53] 章毓晋．图象工程(下)—图象理解与计算机视觉．北京：清华大学出版社，2000．179-215，254-277．
[54] 马颂德，张正友．计算机视觉(计算理论与算法基础)．北京：科学出版社，1998．1-65．
[55] K．R．Castleman，朱志刚等译．数字图象处理．北京：电子工业出版社，1998．60-120，387-442．
[56] 吴健康．数字图象分析．北京：人民邮电出版社，1989．79-155．
[57] 邱茂林，马颂德，李毅．计算机视觉中摄象机定标综述．自动化学报，2000，26(1)：43-55．
[58] 田思，袁占亭．计算机视觉系统框架的新构思．计算机工程与应用，2000，36(6)：57-59．
[59] 黄海，戚飞虎．利用遗传锋法精确标定摄象机参数．上海交通大学学报，2000，34(7)：948-951．
[60] L.Guisser, R.Payrissat, S. Castan. PGSD: an accurate 3D vision system using a projected grid for
surface descriptions. Image and Vision Computing, 2000, 18: 463-491.
[61] 周新伦，韦剑，李锋．一种并行细化算法及其硬件实现方案．模式识别与人工智能，1994，7(1)：1-6．
[62] 张毓晋．图象分割．北京：科学出版社，2001．
[63] 崔屹．图象处理与分析—数学形态学方法及应用．北京：科学出版社，2000．
[64] 邱慧敏，杨济安．B样条函数与图象边缘检测．四川通信技术，2000，30(3)：5-8．
[65] 李艳，彭嘉雄．基于D_2样样条插值和LOG算子的亚象素边缘检测．华中理工大学学报，2000，28(3)：77-79．
[66] 候成刚，赵明涛，屈梁生．基于二次曲面拟合的亚象素图象匹配算法．计量学报，1997，18(3)：227-230．
[67] 董汉莉，王洪林，李东君．利用样条函数的图象边缘精确定位算法研究．信息工程学院学报，1997，16(4)：10-13．
[68] 李永忠．B样条小波在图象边缘检测中的应用研究．西北民族学院学报，1999，20(3)：10-13．
[69] 许志祥．二阶导数型边缘检测算子边缘定位误差的研究．自动化学报，1992，18(4)：448-455
[70] 吴焕明，方漪．基于计算机立体视觉的图象测量技术．第一届全国几何设计与计算学术会议(2002)，2002年6月：312-318
[71] 吴焕明，方漪．基于计算机立体视觉的图象测量技术．工程图学学报，2002，23(4)：60-67