用于全方位视觉导航的图像校正技术研究
|
摘要
全方位视觉系统能一次性获取180度立体角内的场景图像。由于该系统具有大视野的显著特征,使其在军事和民用等领域的应用日益广泛。但是全方位视觉设备由于其特殊的光学成像机制,系统获取的图像存在严重的扭曲。因此,在将全方位视觉投入到真正的应用之前,需要从全方位图像中恢复出所拍摄的景物信息。本文研究了使用鱼眼镜头获取的全方位视觉图像的校正问题。
图像的几何畸变校正就是以特定变换方式将一幅图像变换为理想图像的操作,该技术在全方位视觉导航系统中具有重要作用,为本系统中的目标识别、跟踪和定位奠定了良好基础。全方位视觉导航系统中的几何畸变校正拓宽了识别系统的适用性,优化了系统的性能,增加了系统的可靠性。鱼眼镜头主要的畸变误差分为三类:径向畸变、偏心畸变和薄棱镜畸变。在假定镜头中心和附近为零畸变或小畸变的前提下,用制做标准的标定板对摄像机进行标定来求取标定点像素坐标的理想值和实际值,同时把支持向量机引入图像处理领域对径向距离进行回归生成坐标映射表,把坐标映射表用于图像校正程序对畸变图像进行校正,得到无畸变图像。
本文首先介绍了全方位视觉技术、该技术的研究现状以及具体应用现状,然后介绍摄像机的成像理论、摄像机的标定理论,在分析鱼眼镜头成像的畸变模型的基础上对鱼眼镜头进行标定;文章阐述了图像处理的相关理论方法,特别是图像产生几何畸变后的校正方法。本文设计并实现了一个应用软件,该软件可以对全方位视觉系统采集的图像进行实时校正,所处理的图像可以分别为采集的单帧或连续的图像帧,为全方位视觉导航的目标定位和识别奠定了基础。
Omni-directional vision system can one-time obtain the 180 degree image of the scene in the three-dimensional angle. As with the notable features of large visual perspective, the application of omni-direction vision system to military and civilian areas increasingly widespread. But due to its special optical imaging system, images generated by omni-directional vision equipments exist serious distortion. Therefore, if we want to put omni-directional vision into the real application, restoration of the scene information from the omni-directional image is needed. This paper studies the distortion correction problem of omni-directional vision image taken by fisheye lens.
The geometric distortion correction of an image is an operation to transform an image to an ideal image by the means of special transformation. This technology plays an important role in the omni-directional vision system. It lays a good foundation for target identification, tracking and positioning in the system. The omni-directional vision system broadens the applicability of the recognition system, optimize the performance of the system and increase the system's real-time performance and reliability. The major distortion error of fisheye lens is divided into three categories: radial distortion, eccentric distortion and thin prism distortion. Under the premise of assuming that there is no or small distortion in the lens centre and near the centre , we make standard calibration board to get the ideal and the actual value of the calibration reference points pixel coordinates. At the same time, we apply the Support Vector Machine to image processing area, which is used to generate coordinate mapping table by the means of the radial distance regression. We use coordinate mapping table in the correction procedure to correct image distortion, so we can get distortion-free images.
This paper firstly introduces the omni-directional vision technology, the current research status and the specific application status of this technology. Then it introduces camera imaging theory and camera calibration theory. It gives the method of the calibration for fisheye lens on the basis of the analysis of the fisheye lens imaging distortion model. This paper describes the related theory of image processing, especially the correction method for the geometric distortion produced in the images. This paper designs and implements an application software. This software achieves the effective and real-time correction for the distortion images and the handled images can be a single frame or Continuous frames. It lays the foundation for omni-directional vision navigation objective positioning and identification.
图像的几何畸变校正就是以特定变换方式将一幅图像变换为理想图像的操作,该技术在全方位视觉导航系统中具有重要作用,为本系统中的目标识别、跟踪和定位奠定了良好基础。全方位视觉导航系统中的几何畸变校正拓宽了识别系统的适用性,优化了系统的性能,增加了系统的可靠性。鱼眼镜头主要的畸变误差分为三类:径向畸变、偏心畸变和薄棱镜畸变。在假定镜头中心和附近为零畸变或小畸变的前提下,用制做标准的标定板对摄像机进行标定来求取标定点像素坐标的理想值和实际值,同时把支持向量机引入图像处理领域对径向距离进行回归生成坐标映射表,把坐标映射表用于图像校正程序对畸变图像进行校正,得到无畸变图像。
本文首先介绍了全方位视觉技术、该技术的研究现状以及具体应用现状,然后介绍摄像机的成像理论、摄像机的标定理论,在分析鱼眼镜头成像的畸变模型的基础上对鱼眼镜头进行标定;文章阐述了图像处理的相关理论方法,特别是图像产生几何畸变后的校正方法。本文设计并实现了一个应用软件,该软件可以对全方位视觉系统采集的图像进行实时校正,所处理的图像可以分别为采集的单帧或连续的图像帧,为全方位视觉导航的目标定位和识别奠定了基础。
Omni-directional vision system can one-time obtain the 180 degree image of the scene in the three-dimensional angle. As with the notable features of large visual perspective, the application of omni-direction vision system to military and civilian areas increasingly widespread. But due to its special optical imaging system, images generated by omni-directional vision equipments exist serious distortion. Therefore, if we want to put omni-directional vision into the real application, restoration of the scene information from the omni-directional image is needed. This paper studies the distortion correction problem of omni-directional vision image taken by fisheye lens.
The geometric distortion correction of an image is an operation to transform an image to an ideal image by the means of special transformation. This technology plays an important role in the omni-directional vision system. It lays a good foundation for target identification, tracking and positioning in the system. The omni-directional vision system broadens the applicability of the recognition system, optimize the performance of the system and increase the system's real-time performance and reliability. The major distortion error of fisheye lens is divided into three categories: radial distortion, eccentric distortion and thin prism distortion. Under the premise of assuming that there is no or small distortion in the lens centre and near the centre , we make standard calibration board to get the ideal and the actual value of the calibration reference points pixel coordinates. At the same time, we apply the Support Vector Machine to image processing area, which is used to generate coordinate mapping table by the means of the radial distance regression. We use coordinate mapping table in the correction procedure to correct image distortion, so we can get distortion-free images.
This paper firstly introduces the omni-directional vision technology, the current research status and the specific application status of this technology. Then it introduces camera imaging theory and camera calibration theory. It gives the method of the calibration for fisheye lens on the basis of the analysis of the fisheye lens imaging distortion model. This paper describes the related theory of image processing, especially the correction method for the geometric distortion produced in the images. This paper designs and implements an application software. This software achieves the effective and real-time correction for the distortion images and the handled images can be a single frame or Continuous frames. It lays the foundation for omni-directional vision navigation objective positioning and identification.
引文
[1]Rees D W.Panoramic tele-vison viewing system[P].1970.4:350-465
[2]J.S.Chahl and M.V.Srinivasan.Reflective surfaces for panoramic imaging.Applied Optics(Optical Society of America),1997.36(31):8275-8285,
[3]CHR ISTENSEN O.Localization and navigation of a mobile robot using.natural point landmarks extracted from data[J].Robotics and Autonomous Systems,2000,33(3):131-142.
[4]YANG G S,TANM,HOU Z G.Doorp late Image Quantization Based on Peer Group Filtering for a Mobile Robot[J].Chinese Journal of Electronics,2004,13(4):660-664.
[5]K.Yamazawa,Y.Yagi,and M.Yachida.Omnidirectional Imaging with Hyperboloidal Projection[J].Proc.Int.Conf.on Intelligent Robots and Systems,1993,7(2):1029-1034.
[6]ZHONG Z,YI J,ZHAO D,et al.Novel app roach formobile robot localization using monocular vision[J].Proceedings of SPIE-The International Society for Op tical Engineering,2003,5286(1):159-162.
[7]Tomas svoboda,Tomas Pajdla and Vaclav hlavac.Motion estimation using central panoramic cameras[J].In Stefan Hahn,editor,IEEE international Conference onlntelligent Vehicles,Stuttgart,Germany,1998.10:335-340.
[8]T.Svoboda.Central Panoramic Cameras Design,Geometry,Egomotion[D].PhD thesis,Czech Technical University,1999.
[9]Tomas Svoboda,Tomas Pajdla.Epipolar Geometry for Central Catadioptric Cameras[J].Czech technical University,2001.3.
[10]北京理工大学媒体计算与智能系统实验室.http://www.mcislab.org.cn/direction/research/pqm /omnidirectional%20camera.htm.2006.
[11]XiangHua Ying,Zhanyi hu.Catadioptric Camera Calibration Using Geometric Invariants[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2004.10:102-104.
[12]Y.Onoe,K.Yamazawa.N.Yokoya,and H.Takemura,Visual surveillance and monitoring system using an omnidirectional video camera[J],Proc.IEEE Intl.Conf.on Pattern Recognition,1998:588-592.
[13]Noboru Babaguchi,Yoshihiko fujimoto,Kazumasa Yamazawa,Naokazu Yokoya.A system for visualization and summarization of omnidirectional surveillance video[J].Proc 8th International Workshop on Multimedia Inforamtion System,2002.9:18-27.
[14]皮文凯.基于全方位视觉的人体运动检测与跟踪[C].北京:北京大学智能科学系2001级硕士论文.2004:28-32.
[15]Yu Ohara,Ryusuke Sagawa,Tomio Echigo,Yasushi Yagi.Gait Volum:Spatio-temporal Analysis of Walking[J].Omnivis 2004.
[16]Yong Rui,Anoop Gupta JJCadiz.Viewing Meeting Captured by an Omni-Directional Camera[J].Human Factors in Computing Systems CHI 2001,Seattle Washington,2001:450-457.
[17]Frank Wallhoff,Martin Zobl,Gerhard Rigoll and Igor Potucek.Face Tracking in Meeting Room Scenarios Using Omni-directional Views In IEEE Int.Proceedings on International Conference on Pattern Recognition(1CPR),Cambridge,UK,2004.8
[18]Rainer Stiefelhagen,Xilin Chen,Jie Yang.Capturing Interactions in Meetings with Omnidirectional Cameras[J].Womtec-ICCV workshop 2003.
[19]Yagi Y,kawato S,Tsuji S.Collision avoidance using omni-directional images sensor(COPIS)[J].Proc IEEE ICRA,1991.
[20]Yagi Y,kawato S,Tsuji S.Real-time omni-directional image sensor(COPIS) for vision-guided navi gat -ion[J].IEEE Trans Robotics and Automation,1994.2(1):56-63.
[21]Yagi Y,Okumara H,Yachida M.Multiple visual sensing system for mobile robot[J].Proc ICRA 1994.
[22]M.A.Fischler and R.C.Bolles.Random sample consensus:a paradigm for model fitting with applicati -ons to image analysisand automated cartography.Communications of ACM,1981.24(6):381-395.
[23]Stefan Harbar,Gaurav S.Sukhatme.Omnidirectional Vision for an Autonous Helicopter[J].In proceedings of the IEEE International Conference on Roboticsand Automation 2004.4:3602-3609.
[24]Heung Yeung Shum,Sing Bing Kang.A Review of Image-based Rendering Techniques[J].IEEE/SPIE Visual Communications and Image Processing(VCIP) 2000.6:2-13.
[25]Daniel G.Aliaga,Ingrid Carlbom.Plenoptic Stitching:A scalable method for reconstruction 3D interactive walkthroughs[J].In Proceedings of ACM SIGGRAPH 2001.8:443-450.
[26]D.Aliaga,T.Funkhouser,D.Yanovsky,I.Carlbom,Sea of Images[J],Proceedings of IEEE Visualization.2001:331-338.
[27]Hiroshi Ishiguro,Kim C,Ng,Richard Capella,Mohan M.Trivedi.Omnidirectional image-based modelingahree approaches to approximated plenoptic representations[J].Machine Vision and Applications.2003.
[28]Jose Gaspar,Etienne Grosslnann,Jose Sntos-Victor.Interactive Reconstruction from an Omni-directional Image 9th International Symposium on Intelligent Robotic Systems,2001.
[29]Petr Doubek,Tomas Svoboda.Reliable 3D reconstruction from a few catadioptric images[J].IEEE workshop on Omni-directional vision.2002:71-78.
[30]Petri Doubek,Tomas Svoboda.What space can be reconstructed from multiple catadioptric images[J].In Horst Witdenauer and Walter Kropatsch,editors,Proceedings of the Computer Vision Winter Workshop.PRIP TU Vienna,2002.2:198-207.
[31]Roland Bunschoten,Ben krose.Robust Scene Reconstruction from and Omnidirectional Vision System[J].IEEE transactions on robotics and automation.2002.
[32]D.马尔.视觉计算理论,姚国正,刘磊等译.北京:科学出版社,1998.
[33]罗志增,蒋静坪.机器人感觉与多信息融合.北京:机械工业出版社.2002.
[34]MPEG-4VideoGrot:P,MPEG—4videoverificationmodelversion10.015].150/IECJTCI/SC -19/WGII DoeunlentMPEG98/N1992.February 1998.[32]D.马尔.视觉计算理论,姚国正,刘磊等译.北京:科学出版社,1998.
[35]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.
[36]Ganapathy S.Decomposition of transformation matrices for robot vision.Proc.Int.Conference on Robotics and Automation.1984:130-139.
[37]Abdel-Aziz Y.L,Karara H.M..Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry.In U.of Illinois Symposium on Ctose-Range Photogrammetry.Urbana:Univ.of Illinois at Urbana-Champaign,1971:1-18.
[38]R.Y.Tsai.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using ofi-the-shelf TV camera and lenses.IEEE Journal of Automation,1987,3(4):323-334.
[39]高立志,方勇,林志航,陈康宁.高精度立体视觉测量中一种通用的摄像机标定技术,机械科学与技术,1998,17(5):809-811.
[40]R.K.Lenz and R.Y.Tsai.Techniques for calibration of the scale factor and image center for high accuracy 3D machine vision metrology.IEEE Trans.on PAMI,1998,10(5):713-720.
[41]高立志,方勇,林志航.立体视觉测量中摄像机标定的新技术.电子学报,1999,27(2):12-14.
[42]张艳珍,欧宗瑛.一种新的摄像机线性标定方法.中国图象图形学报,2001,6(8):727-731.
[43]马颂德,张正友.计算机视觉-计算理论与实践.北京:科学出版社,1998.
[44]贾云德.机器视觉.北京:科学出版社,2000.
[45]吴立德.计算机视觉.上海:复旦大学出版社,1993.
[46]郑南宁.计算机视觉与模式识别.北京:国防工业出版社,1998.
[47]W.Faig,Calibration of close-range Photogrammetric Eng.Remote Sensing,photogrammetry systems:Mathematical formulation.1975,41(12):1479-1486.
[48]I.Sobel.On calibrating computer controlled cameras for perceiving 3-D scenes.Artificial Intelligence,1974,5(2):185-188.
[49]Tsal R.Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off the-shelf TV camera and lenses.IEEE Journal of Automation,1987,3(4):323-334.
[50]Tsai R.Y.An efficient and accurate camera calibration technique for 3D machine vision.Proc.CVPR'86.New York:IEEE.1986:364-374.
[51]Zhang.Z.A flexible new technique for camera calibration.Microsoft Corporation:Technical Report MSR-TR-98-71,1998.
[52]高满屯,曲仕如,李西琴.计算机视觉研究中的投影理论和方法.西安:西北工业大学出版社,1998.
[53]Robert M.Haraliek.Using perspective transformation in scene analysis,Computer Graphics and Image Processing,1980,13(3):191-221.
[54]Caprile B.,Torre.V.Using vanishing points for camera calibration.Int.J.of Computer Vision,1990,4(2):127-140.
[55]Bdllault B,O.Mahony.New method for vanishing points detection.CVGIP:Image Understand -ing,1991,54(2):289-300.
[56]Fadi Dornaika,Christophe Garcia.Pose estimation using point and line correspondences.Real-Time Imaging,1999,5(5):215-230.
[57]Martins H A,Birk JR,Kelley R B.Camera models based no data from two calibration planes Computer Graphics and Imaging Processing,1981,17(2):173-180.
[58]Wei G,Ma S.Two-plane calibration:a unified model.Proc.CVPR'91.Piseataway:IEEE 1991:133-138.
[59]Wei G,Ma S.Complete two-plane camera calibration and experimental comparisons.Proc.IEEE Int.Conf On Computer Vision.Los Alamitos:IEEE.1993:439-446.
[60]Wei G,Ma S.Implicit and explicit camera calibration:theory and experiments.IEEE Trans PAMI,1994,16(5):469-480.
[61]阮秋琦,数字图像处理学,北京:电子工业出版社,2001:1-62.
[62]夏良正,数字图像处理,南京:东南大学出版社,1999:1-9.
[63]章毓晋,图像分割,北京:科学出版社,2001:1-8.
[64]Kenneth R.Castleman,Digital Image Processing(影印版),北京:清华大学出版社,1998.3:1-3.
[65]唐良端,马全明,景晓军,图像处理实用技术,北京:化学工业出版社,2001.10:73-75
[66]胡成发,印刷色彩和色度学,北京:印刷工业出版社,1993.3:1-10.
[67]Abhjit S.Pandya,Robert B.Macy,Pattern Recognition with neural networks in C++,北京:电子工业出版社,2002:30-33.
[68]Hao Pan,Yuan Jing-ling,Zhong Luo,Probing Modification of BP Neural Network Learning-Rate,Proceeding of the First International Conference on Machine Learning and Cybernetics,2002.11:307-309.
[69]周长发.精通VC++.NET图像处理编程.电子工业出版社.2002.
[70]Kenneth R.Castleman,Digital Image Processing Prentice-Hall International,lnc Pages 115-128.
[71]马卫东,李幼平,袁宏春.面向对象的网络信息空间模型与信息传播[J].计算机科学,2003,30(2):34-37.
[72]Harris D,Burges[J],Kaufman L,Smola A,Vapnik V Support Vector Regression Machines.In Michael C,et al.editors,Advances in Neural Information Processing Systems.The MIT Press,1997,9:155.
[73]Smola A,Scholkophf B.A Tutorial on Support Vector Regression.NeuroCOLT2 Technical Report NC2-TR-1998-030 1998.10.
[74]Smola A J.Regression estimation with support vector machines.Master's thesis,Technical University Munchen 1996.
[2]J.S.Chahl and M.V.Srinivasan.Reflective surfaces for panoramic imaging.Applied Optics(Optical Society of America),1997.36(31):8275-8285,
[3]CHR ISTENSEN O.Localization and navigation of a mobile robot using.natural point landmarks extracted from data[J].Robotics and Autonomous Systems,2000,33(3):131-142.
[4]YANG G S,TANM,HOU Z G.Doorp late Image Quantization Based on Peer Group Filtering for a Mobile Robot[J].Chinese Journal of Electronics,2004,13(4):660-664.
[5]K.Yamazawa,Y.Yagi,and M.Yachida.Omnidirectional Imaging with Hyperboloidal Projection[J].Proc.Int.Conf.on Intelligent Robots and Systems,1993,7(2):1029-1034.
[6]ZHONG Z,YI J,ZHAO D,et al.Novel app roach formobile robot localization using monocular vision[J].Proceedings of SPIE-The International Society for Op tical Engineering,2003,5286(1):159-162.
[7]Tomas svoboda,Tomas Pajdla and Vaclav hlavac.Motion estimation using central panoramic cameras[J].In Stefan Hahn,editor,IEEE international Conference onlntelligent Vehicles,Stuttgart,Germany,1998.10:335-340.
[8]T.Svoboda.Central Panoramic Cameras Design,Geometry,Egomotion[D].PhD thesis,Czech Technical University,1999.
[9]Tomas Svoboda,Tomas Pajdla.Epipolar Geometry for Central Catadioptric Cameras[J].Czech technical University,2001.3.
[10]北京理工大学媒体计算与智能系统实验室.http://www.mcislab.org.cn/direction/research/pqm /omnidirectional%20camera.htm.2006.
[11]XiangHua Ying,Zhanyi hu.Catadioptric Camera Calibration Using Geometric Invariants[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2004.10:102-104.
[12]Y.Onoe,K.Yamazawa.N.Yokoya,and H.Takemura,Visual surveillance and monitoring system using an omnidirectional video camera[J],Proc.IEEE Intl.Conf.on Pattern Recognition,1998:588-592.
[13]Noboru Babaguchi,Yoshihiko fujimoto,Kazumasa Yamazawa,Naokazu Yokoya.A system for visualization and summarization of omnidirectional surveillance video[J].Proc 8th International Workshop on Multimedia Inforamtion System,2002.9:18-27.
[14]皮文凯.基于全方位视觉的人体运动检测与跟踪[C].北京:北京大学智能科学系2001级硕士论文.2004:28-32.
[15]Yu Ohara,Ryusuke Sagawa,Tomio Echigo,Yasushi Yagi.Gait Volum:Spatio-temporal Analysis of Walking[J].Omnivis 2004.
[16]Yong Rui,Anoop Gupta JJCadiz.Viewing Meeting Captured by an Omni-Directional Camera[J].Human Factors in Computing Systems CHI 2001,Seattle Washington,2001:450-457.
[17]Frank Wallhoff,Martin Zobl,Gerhard Rigoll and Igor Potucek.Face Tracking in Meeting Room Scenarios Using Omni-directional Views In IEEE Int.Proceedings on International Conference on Pattern Recognition(1CPR),Cambridge,UK,2004.8
[18]Rainer Stiefelhagen,Xilin Chen,Jie Yang.Capturing Interactions in Meetings with Omnidirectional Cameras[J].Womtec-ICCV workshop 2003.
[19]Yagi Y,kawato S,Tsuji S.Collision avoidance using omni-directional images sensor(COPIS)[J].Proc IEEE ICRA,1991.
[20]Yagi Y,kawato S,Tsuji S.Real-time omni-directional image sensor(COPIS) for vision-guided navi gat -ion[J].IEEE Trans Robotics and Automation,1994.2(1):56-63.
[21]Yagi Y,Okumara H,Yachida M.Multiple visual sensing system for mobile robot[J].Proc ICRA 1994.
[22]M.A.Fischler and R.C.Bolles.Random sample consensus:a paradigm for model fitting with applicati -ons to image analysisand automated cartography.Communications of ACM,1981.24(6):381-395.
[23]Stefan Harbar,Gaurav S.Sukhatme.Omnidirectional Vision for an Autonous Helicopter[J].In proceedings of the IEEE International Conference on Roboticsand Automation 2004.4:3602-3609.
[24]Heung Yeung Shum,Sing Bing Kang.A Review of Image-based Rendering Techniques[J].IEEE/SPIE Visual Communications and Image Processing(VCIP) 2000.6:2-13.
[25]Daniel G.Aliaga,Ingrid Carlbom.Plenoptic Stitching:A scalable method for reconstruction 3D interactive walkthroughs[J].In Proceedings of ACM SIGGRAPH 2001.8:443-450.
[26]D.Aliaga,T.Funkhouser,D.Yanovsky,I.Carlbom,Sea of Images[J],Proceedings of IEEE Visualization.2001:331-338.
[27]Hiroshi Ishiguro,Kim C,Ng,Richard Capella,Mohan M.Trivedi.Omnidirectional image-based modelingahree approaches to approximated plenoptic representations[J].Machine Vision and Applications.2003.
[28]Jose Gaspar,Etienne Grosslnann,Jose Sntos-Victor.Interactive Reconstruction from an Omni-directional Image 9th International Symposium on Intelligent Robotic Systems,2001.
[29]Petr Doubek,Tomas Svoboda.Reliable 3D reconstruction from a few catadioptric images[J].IEEE workshop on Omni-directional vision.2002:71-78.
[30]Petri Doubek,Tomas Svoboda.What space can be reconstructed from multiple catadioptric images[J].In Horst Witdenauer and Walter Kropatsch,editors,Proceedings of the Computer Vision Winter Workshop.PRIP TU Vienna,2002.2:198-207.
[31]Roland Bunschoten,Ben krose.Robust Scene Reconstruction from and Omnidirectional Vision System[J].IEEE transactions on robotics and automation.2002.
[32]D.马尔.视觉计算理论,姚国正,刘磊等译.北京:科学出版社,1998.
[33]罗志增,蒋静坪.机器人感觉与多信息融合.北京:机械工业出版社.2002.
[34]MPEG-4VideoGrot:P,MPEG—4videoverificationmodelversion10.015].150/IECJTCI/SC -19/WGII DoeunlentMPEG98/N1992.February 1998.[32]D.马尔.视觉计算理论,姚国正,刘磊等译.北京:科学出版社,1998.
[35]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.
[36]Ganapathy S.Decomposition of transformation matrices for robot vision.Proc.Int.Conference on Robotics and Automation.1984:130-139.
[37]Abdel-Aziz Y.L,Karara H.M..Direct linear transformation from comparator coordinates into object space coordinates in close-range photogrammetry.In U.of Illinois Symposium on Ctose-Range Photogrammetry.Urbana:Univ.of Illinois at Urbana-Champaign,1971:1-18.
[38]R.Y.Tsai.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using ofi-the-shelf TV camera and lenses.IEEE Journal of Automation,1987,3(4):323-334.
[39]高立志,方勇,林志航,陈康宁.高精度立体视觉测量中一种通用的摄像机标定技术,机械科学与技术,1998,17(5):809-811.
[40]R.K.Lenz and R.Y.Tsai.Techniques for calibration of the scale factor and image center for high accuracy 3D machine vision metrology.IEEE Trans.on PAMI,1998,10(5):713-720.
[41]高立志,方勇,林志航.立体视觉测量中摄像机标定的新技术.电子学报,1999,27(2):12-14.
[42]张艳珍,欧宗瑛.一种新的摄像机线性标定方法.中国图象图形学报,2001,6(8):727-731.
[43]马颂德,张正友.计算机视觉-计算理论与实践.北京:科学出版社,1998.
[44]贾云德.机器视觉.北京:科学出版社,2000.
[45]吴立德.计算机视觉.上海:复旦大学出版社,1993.
[46]郑南宁.计算机视觉与模式识别.北京:国防工业出版社,1998.
[47]W.Faig,Calibration of close-range Photogrammetric Eng.Remote Sensing,photogrammetry systems:Mathematical formulation.1975,41(12):1479-1486.
[48]I.Sobel.On calibrating computer controlled cameras for perceiving 3-D scenes.Artificial Intelligence,1974,5(2):185-188.
[49]Tsal R.Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off the-shelf TV camera and lenses.IEEE Journal of Automation,1987,3(4):323-334.
[50]Tsai R.Y.An efficient and accurate camera calibration technique for 3D machine vision.Proc.CVPR'86.New York:IEEE.1986:364-374.
[51]Zhang.Z.A flexible new technique for camera calibration.Microsoft Corporation:Technical Report MSR-TR-98-71,1998.
[52]高满屯,曲仕如,李西琴.计算机视觉研究中的投影理论和方法.西安:西北工业大学出版社,1998.
[53]Robert M.Haraliek.Using perspective transformation in scene analysis,Computer Graphics and Image Processing,1980,13(3):191-221.
[54]Caprile B.,Torre.V.Using vanishing points for camera calibration.Int.J.of Computer Vision,1990,4(2):127-140.
[55]Bdllault B,O.Mahony.New method for vanishing points detection.CVGIP:Image Understand -ing,1991,54(2):289-300.
[56]Fadi Dornaika,Christophe Garcia.Pose estimation using point and line correspondences.Real-Time Imaging,1999,5(5):215-230.
[57]Martins H A,Birk JR,Kelley R B.Camera models based no data from two calibration planes Computer Graphics and Imaging Processing,1981,17(2):173-180.
[58]Wei G,Ma S.Two-plane calibration:a unified model.Proc.CVPR'91.Piseataway:IEEE 1991:133-138.
[59]Wei G,Ma S.Complete two-plane camera calibration and experimental comparisons.Proc.IEEE Int.Conf On Computer Vision.Los Alamitos:IEEE.1993:439-446.
[60]Wei G,Ma S.Implicit and explicit camera calibration:theory and experiments.IEEE Trans PAMI,1994,16(5):469-480.
[61]阮秋琦,数字图像处理学,北京:电子工业出版社,2001:1-62.
[62]夏良正,数字图像处理,南京:东南大学出版社,1999:1-9.
[63]章毓晋,图像分割,北京:科学出版社,2001:1-8.
[64]Kenneth R.Castleman,Digital Image Processing(影印版),北京:清华大学出版社,1998.3:1-3.
[65]唐良端,马全明,景晓军,图像处理实用技术,北京:化学工业出版社,2001.10:73-75
[66]胡成发,印刷色彩和色度学,北京:印刷工业出版社,1993.3:1-10.
[67]Abhjit S.Pandya,Robert B.Macy,Pattern Recognition with neural networks in C++,北京:电子工业出版社,2002:30-33.
[68]Hao Pan,Yuan Jing-ling,Zhong Luo,Probing Modification of BP Neural Network Learning-Rate,Proceeding of the First International Conference on Machine Learning and Cybernetics,2002.11:307-309.
[69]周长发.精通VC++.NET图像处理编程.电子工业出版社.2002.
[70]Kenneth R.Castleman,Digital Image Processing Prentice-Hall International,lnc Pages 115-128.
[71]马卫东,李幼平,袁宏春.面向对象的网络信息空间模型与信息传播[J].计算机科学,2003,30(2):34-37.
[72]Harris D,Burges[J],Kaufman L,Smola A,Vapnik V Support Vector Regression Machines.In Michael C,et al.editors,Advances in Neural Information Processing Systems.The MIT Press,1997,9:155.
[73]Smola A,Scholkophf B.A Tutorial on Support Vector Regression.NeuroCOLT2 Technical Report NC2-TR-1998-030 1998.10.
[74]Smola A J.Regression estimation with support vector machines.Master's thesis,Technical University Munchen 1996.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |