计算机视觉技术在低空突防与精确打击中的应用研究
|
摘要
本文从应用需求出发,分别对计算机视觉中的立体视觉与图像配准技术进行仔细分析,着重对两项技术中均涉及的最基本、也是最困难的部分— —匹配问题展开深入研究,提出两种新颖的基于遗传算法的匹配方法,从而在技术上寻求把计算机视觉技术应用于低空突防与精确打击战术的解决途径。
二十世纪九十年代的海湾战争,本世纪初的美伊战争等,使世人目睹了现代高科技武器的强大威力,也使人们充分认识到将高新科学技术应用于现代国防中的必要性和紧迫性。目前,低空突防与精确打击是现代局部战争中发展起来的能有效完成空中进攻任务的两种实用战术,随着防空力量的日益强大,为与之抗衡,迫切需要在保障自身安全的同时尽可能地提高空中进攻的效率,因此需要对一些新兴技术进行探究,以使其在低空突防与精确打击中充分发挥效力。
计算机视觉是近几十年迅速发展起来的一项新兴技术,已经在众多领域中应用、实践,并逐渐为人们所共识。笼统地说,它是一项利用计算机处理视觉信息的技术,因而可视其为一项遥感技术,应用于工程实践中,可以提高系统的自动化和智能化程度,以及其它方面的性能。实际上,将计算机视觉技术应用于低空突防与精确打击已不再是一种新的想法,但在技术上解决其应用问题却存在着诸多难点,因此本文尝试对其中的两项技术:立体视觉技术与图像配准技术的应用问题进行研究。应用这两项技术所共同面临的任务是两幅图像间的匹配问题,是实现这两项技术本身自动化所无法回避的必经历程,也是它们中最难解决的任务。本文将其视为工程优化问题进行解决,但由于上面两种战术各有不同的应用要求,比如低空突防战术中需要数字地形图及距离(深度)信息,而在精确打击中则需要目标点的精确位置(或方位)信息,因此两种情况下对匹配问题的要求就不同,匹配问题所涉及的难点、解决方法也各有不同,必须区别对待,本文针对这两种情况进行了具体深入的研究。针对低空突防战术需要详尽数字地形图和深度信息的要求,本文采用立体视觉技术,为其研究开发基于区域的匹配方法,不需要预先进行特征提取,也不需要进行后续插值,就可以直接获得高密度的视差图(进而可以转化为深度信息图);针对精确打击中需要进行目标点自动定位的要求,本文在分析了多种可能方案之后,采用基于点映射的图像配准技术,为其研究开发基于特征的匹配方法,从而实现快速、准确、自动的图像空间对准和信息综合。
Based on the requirements of practical applications, the dissertation anatomizes StereoVision and Image Registration techniques in Computer Vision field and put the emphasis on theessential and most difficult part involved in both of them, i.e. the correspondence problem. Thedissertation proposes two novel approaches to solve the problem so as to technically find howto apply computer vision techniques into low penetration and precision strike.
During the Persian Gulf War in 1990s and the US-Iraq War in 2003, television viewersaround the world have witnessed the new effectiveness of modern high-tech weapons. It showsthat modern national defense is in urgent need of new science and high technology. At present,low penetration and precision strike are the two practical tactics developed in modern warfarethat can effectively fulfill an air attack mission. With the growing of air defense power, it ismore necessary to exert all the power of new technologies on air strike power so as to improvetheir effectiveness as possible, meanwhile assuring the safety of attackers.
Computer Vision is a new technique developed rapidly in recent years, which has beenapplied in a variety of domains and is gradually accepted by more and more researchers.Generally speaking, it is the technique to process visual information taking advantage ofcomputers and can thus be regarded as a remote sensing technique, with which engineeringsystems can improve their automation, intelligence, and other performance. In fact, it is not anew idea to apply computer vision techniques into low penetration and precision strike, butthere exist many technical problems to solve. The dissertation intends to study two of them, oneis Stereo Vision, and the other is Image Registration. In both of them, there is the commoncrucial part, i.e. the correspondence problem, which is also the most difficult task to solve. Inthe dissertation, it is cast as an engineering optimization problem, but has to be solved in twoways according to different application requirements. For example, a detailed digital terrainmap is needed in low penetration while the position of the target point needs to be locatedautomatically in precision strike. Thus, the difficulties involved and/or the methods employedmay be various in different applications. In the case of low penetration, Stereo Vision techniqueis employed and an area-based matching method is developed in the dissertation, with which a
dense disparity map can be obtained directly without the need of the feature extraction and thepost-interpolation processes. In the case of precision strike, after analyzing several candidateschemes Point Mapping Based Image Registration technique is employed and a feature-basedmatching method is developed, with which images are aligned and their spatial information iscombined correctly, quickly, and automatically.
Genetic Algorithms are well known as the optimization technique that can be search forglobal optimal solutions. As an optimization task, the correspondence problem can be solvedmaking use of them. In the dissertation, two novel matching methods are proposed for the twoapplications, respectively. One is used to estimate a dense disparity map and the other is used tofind the matches quickly and correctly. In their implementations, for the first case, a feasibledisparity map is viewed as an individual and the disparity value at each of its pixel sites isviewed as a chromosome, which is represented by a binary string. Therefore, one individualcontains a lot of chromosomes, which is very different from the classical GAs. Accordingly,two types of guided crossover and one type of guided mutation are designed for the encoding,and four matching constraints are formulated into the evaluation function. Hence, the proposedalgorithm can obtain a dense disparity map with efficiency. For the second case, first a newchromosomal encoding scheme is proposed, so called the partial permutation, then for thoseencoding chromosomes five matching constraints are considered, five seclection methods andthree replacem
二十世纪九十年代的海湾战争,本世纪初的美伊战争等,使世人目睹了现代高科技武器的强大威力,也使人们充分认识到将高新科学技术应用于现代国防中的必要性和紧迫性。目前,低空突防与精确打击是现代局部战争中发展起来的能有效完成空中进攻任务的两种实用战术,随着防空力量的日益强大,为与之抗衡,迫切需要在保障自身安全的同时尽可能地提高空中进攻的效率,因此需要对一些新兴技术进行探究,以使其在低空突防与精确打击中充分发挥效力。
计算机视觉是近几十年迅速发展起来的一项新兴技术,已经在众多领域中应用、实践,并逐渐为人们所共识。笼统地说,它是一项利用计算机处理视觉信息的技术,因而可视其为一项遥感技术,应用于工程实践中,可以提高系统的自动化和智能化程度,以及其它方面的性能。实际上,将计算机视觉技术应用于低空突防与精确打击已不再是一种新的想法,但在技术上解决其应用问题却存在着诸多难点,因此本文尝试对其中的两项技术:立体视觉技术与图像配准技术的应用问题进行研究。应用这两项技术所共同面临的任务是两幅图像间的匹配问题,是实现这两项技术本身自动化所无法回避的必经历程,也是它们中最难解决的任务。本文将其视为工程优化问题进行解决,但由于上面两种战术各有不同的应用要求,比如低空突防战术中需要数字地形图及距离(深度)信息,而在精确打击中则需要目标点的精确位置(或方位)信息,因此两种情况下对匹配问题的要求就不同,匹配问题所涉及的难点、解决方法也各有不同,必须区别对待,本文针对这两种情况进行了具体深入的研究。针对低空突防战术需要详尽数字地形图和深度信息的要求,本文采用立体视觉技术,为其研究开发基于区域的匹配方法,不需要预先进行特征提取,也不需要进行后续插值,就可以直接获得高密度的视差图(进而可以转化为深度信息图);针对精确打击中需要进行目标点自动定位的要求,本文在分析了多种可能方案之后,采用基于点映射的图像配准技术,为其研究开发基于特征的匹配方法,从而实现快速、准确、自动的图像空间对准和信息综合。
Based on the requirements of practical applications, the dissertation anatomizes StereoVision and Image Registration techniques in Computer Vision field and put the emphasis on theessential and most difficult part involved in both of them, i.e. the correspondence problem. Thedissertation proposes two novel approaches to solve the problem so as to technically find howto apply computer vision techniques into low penetration and precision strike.
During the Persian Gulf War in 1990s and the US-Iraq War in 2003, television viewersaround the world have witnessed the new effectiveness of modern high-tech weapons. It showsthat modern national defense is in urgent need of new science and high technology. At present,low penetration and precision strike are the two practical tactics developed in modern warfarethat can effectively fulfill an air attack mission. With the growing of air defense power, it ismore necessary to exert all the power of new technologies on air strike power so as to improvetheir effectiveness as possible, meanwhile assuring the safety of attackers.
Computer Vision is a new technique developed rapidly in recent years, which has beenapplied in a variety of domains and is gradually accepted by more and more researchers.Generally speaking, it is the technique to process visual information taking advantage ofcomputers and can thus be regarded as a remote sensing technique, with which engineeringsystems can improve their automation, intelligence, and other performance. In fact, it is not anew idea to apply computer vision techniques into low penetration and precision strike, butthere exist many technical problems to solve. The dissertation intends to study two of them, oneis Stereo Vision, and the other is Image Registration. In both of them, there is the commoncrucial part, i.e. the correspondence problem, which is also the most difficult task to solve. Inthe dissertation, it is cast as an engineering optimization problem, but has to be solved in twoways according to different application requirements. For example, a detailed digital terrainmap is needed in low penetration while the position of the target point needs to be locatedautomatically in precision strike. Thus, the difficulties involved and/or the methods employedmay be various in different applications. In the case of low penetration, Stereo Vision techniqueis employed and an area-based matching method is developed in the dissertation, with which a
dense disparity map can be obtained directly without the need of the feature extraction and thepost-interpolation processes. In the case of precision strike, after analyzing several candidateschemes Point Mapping Based Image Registration technique is employed and a feature-basedmatching method is developed, with which images are aligned and their spatial information iscombined correctly, quickly, and automatically.
Genetic Algorithms are well known as the optimization technique that can be search forglobal optimal solutions. As an optimization task, the correspondence problem can be solvedmaking use of them. In the dissertation, two novel matching methods are proposed for the twoapplications, respectively. One is used to estimate a dense disparity map and the other is used tofind the matches quickly and correctly. In their implementations, for the first case, a feasibledisparity map is viewed as an individual and the disparity value at each of its pixel sites isviewed as a chromosome, which is represented by a binary string. Therefore, one individualcontains a lot of chromosomes, which is very different from the classical GAs. Accordingly,two types of guided crossover and one type of guided mutation are designed for the encoding,and four matching constraints are formulated into the evaluation function. Hence, the proposedalgorithm can obtain a dense disparity map with efficiency. For the second case, first a newchromosomal encoding scheme is proposed, so called the partial permutation, then for thoseencoding chromosomes five matching constraints are considered, five seclection methods andthree replacem
引文
[1] Ballard D H and Brown C M. Computer Vision [M]. Prentice-Hall, 1982.
[2] Shapiro L G and Stockman G. Computer Vision [M]. Prentice-Hall, 2001.
[3] Shashua A. Geometry and Photometry in 3D Visual Recognition. Technique Report, AI-TR 1401, MIT, 1992.
[4] Forsyth D A and Ponce J. Computer Vision: A Modern Approach [M], Prentice-Hall, 2003.
[5] Zhang R, Tsai P-S, Cryer J E, et al. Shape from Shading: A Survey [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, 1999, 21(8): 690~706.
[6] Faugeras O D. Three-Dimensional Computer Vision: A Geometric Viewpoint [M], The MIT Press, Cambridge, Massachusetts, 1993.
[7] Xu G and Zhang Z. Epipolar Geometry in Stereo, Motion and Object Recognition: A UnifiedApproach [M]. KluwerAcademic Publishers, 1996.
[8] Poggio T and Koch C. Ill-posed Problems in Early Vision: from Computational Theory to Analogue Networks [A]. In Proc of Royal Society London B 226 [C]. 1985. 303~323.
[9] Poggio T, Torre V, and Koch C. Computational Vision and Regularization Theory [J]. Nature, Sep 26, 1985, 317: 314~319.
[10] Brady M. Computational Approaches to Image Understanding [J]. Computing Surveys, March 1982, 14(1): 3~71.
[11] Koch C, Marroquin J, and Yuille A, Analog “Neuronal”Networks in Early Vision [A]. In Proc of NationalAcademic Science USA[C], June 1986. 83: 4263~4267.
[12] Mohr R and Triggs B. Projective Geometry for Image Analysis, A Tutorial given at ISPRS (International Society for Photogrammetry and Remote Sensing) [C]. Vienna, July 1996.
[13] Gros P, Mohr R, Quan L, et al. How Useful is Projective Geometry [J]. Computer Vision and Image Understanding, Mar 1997. 3(65): 442~446.
[14] Collins S H. Stereoscopic Depth Perception [J]. Photogrammetric Engineering and Remote Sensing, Jan 1981. 47(1): 45~52.
[15] Muddy J L and Zisserman A. Geometric Invariance in Computer Vision [M], Chapter 23: Appendix –Projective Geometry for Machine Vision, The MIT Press, Cambridge, MA,
1992. 463~534.
[16] Faugeras D. Stratification of 3-D Vision: Projective, Affine and Metric Representations [J]. Journal of the Optical Society of America A, Mar 1995. 12(3): 465~484.
[17] Birchfield S. An Introduction to Projective Geometry (for computer vision) [OL]. http://robotics.stanford.edu/~birch/projective/, 1998.
[18] Barnard S T and Fischler M A. Computational Stereo [J]. Computing Surveys, Dec 1982. 14(4): 553~572.
[19] Hartley R and Zisserman A. Multiple View Geometry in Computer Vision [M], Cambridge University Press, 2000.
[20] Elias R and Laganière R. Projective Geometry for Three-Dimensional Computer Vision, Technical Report, TR-2001-08, School of Information Technology and Eng., University of Ottawa, Canada, 2001.
[21] Cochran S D and Medioni G. 3D Surface Description from Binocular Stereo [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, Oct 1992. 14(10): 981~994.
[22] Zitnick C L and Kanade T. A Cooperative Algorithm for Stereo Matching and Occlusion Detection, Technical Report CMU-RI-TR-99-35, Carnegie Mellon University, 1999.
[23] Kumar K S and Desai U B. New Algorithms for 3D Surface Description from Binocular Stereo Using Integration [J]. Journal of Franklin Institute, 1994. 331B(5): 531~554.
[24] Marr D and Poggio T. A Computational theory of Human Stereo Vision [A]. In Porc of Royal Society London B 204 [C]. 1979. 301~328.
[25] Zhang Z, Deriche R, Faugeras O D, et al. A Robust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry, Research Report 2273, INRIA, Sophia-Antipolis, France, May 1994.
[26] Jones G A. Constraint, Optimization, and Hierarchy: Reviewing Stereoscopic Correspon- dence of Complex Features [J]. Computer Vision and Image Understanding, Jan 1997. 65(1): 57~78.
[27] Brown L G. A Survey of Image Registration Techniques [J]. ACM Computing Surveys, Dec 1992. 24(4): 325~376.
[28] Cass T A. Polynomial-Time Geometric Matching for Object Recognition [J]. Interna- tional Journal of Computer Vision, 1997. 21(1/2): 37~61.
[29] Sivazlian B D and Stanfel L E. Optimization Techniques in Operations Research [M]. Prentice-Hall Inc, Englewood Cliffs, New Jersey, 1975.
[30] Wolfe M A. Numerical Methods for Unconstrained Optimization [M]. Van Nostrand Reinhold Company Ltd, Molly Millars Lane, Workingham, Berkshire, England, 1978.
[31] Rao S S. Optimization: Theory andApplications [M]. Wiley Eastern Limited, 1979.
[32] Gill P E, Murray W, Wright M H. Practical Optimization [M].Academic Press, 1981.
[33] Luenberger D G. Linear and Nonlinear Programming [M]. 2nd Edition, Addison-Wesley Publishing Company, 1984.
[34] Gr?tschel M and Lovász L. Combinatorial Optimization: A Survey, DIMACS Technical Report 93-29, May 1993.
[35] Deb K. Genetic Algorithms for Function Optimization [A]. In Genetic algorithms and soft computing [M]. Herrera F, Verdegay J (ed.), Heidelberg: Physica-Verl, 1996.
[36] Gimel'farb G. Stereo Terrain Reconstruction by Dynamic Programming, Technical Report CITR-TR-21, The University ofAuckland, June 1998.
[37] Kirkpatrick S, Gelatt C D, Jr, et al. Optimization by Simulated Annealing [J]. Science, May 13, 1983. 220(4598): 671~680.
[38] Locatelli M. Simulated Annealing Algorithms for Global Continuous Optimization [A]. In Handbook of Global Optimization: Vol. 2 [M]. Edited by Pardalos P M and Romeijn H E. KluwerAcademic Publishers, May 2002.
[39] Johnson D S, Aragon C R, Mcgeoch L A, et al. Optimization by Simulated Annealing: an Experimental Evaluation; Part II, Graph Coloring and Number Partitioning [J]. Operations Research, May-June 1991. 39(3): 378~406.
[40] Ingber L. Simulated Annealing: Practice versus Theory [J]. Journal of Mathematical and Computer Modeling, 1993. 18(11): 29~57.
[41] Ingber L. Adaptive Simulated Annealing (ASA): Lessons Learned [J]. Journal of Control and Cybernetics, 1996. 25(1): 33~54.
[42] Chandler B, Rekeczky C, Nishio Y, et al. Adaptive Simulated Annealing in CNN Template Learning [J]. IEICE Trans Fundamentals, Feb 1999. E82-A(2): 398~402.
[43] Ingber L and Rosen B. Genetic Algorithms and Very Fast Simulated Reannealing: a Comparison [J]. Journal of Mathematical and Computer Modeling, 1992. 16(11): 87~100.
[44] Davis L. Handbook of Genetic Algorithms [M]. New York: Van Nostrand Reinhold, 1991.
[45] Michalewicz Z. Genetic Algorithms + Data Structures = Evolution Programs [M]. Springer-Verlag, Berlin, 1996.
[46] Whitley D.AGenetic Algorithm Tutorial [J]. Statistics and Computing, 1994. 4: 65~85.
[47] Salomon R. Short Notes on the Schema Theorem and the Building Block Hypothesis in Genetic Algorithms [J]. Evolutionary Programming VII, Springer, Berlin, V. W. Porto, N. Saravanan, D. Waagen, andA. E. Eiben, 1998. 113~122.
[48] Deb K. Genetic Algorithm in Search and Optimization: The Technique and Applications [A]. In Proc of International Workshop on Soft Comput and Intel System [C]. Calcutta, India: Machine Intelligence Unit, Indian Statistical Institute, 1998. 58~87.
[49] Fogel D B. An Introduction to Simulated Evolutionary Optimization [J]. IEEE Trans on Neural Networks, Jan 1994. 5(1): 3~14.
[50] Goldberg D E and Deb K. A Comparative Analysis of Selection Schemes Used in Genetic Algorithms [A]. In Foundations of Genetic Algorithms [M]. Rawlins G J (ed.), San Mateo, CA, 1991. 69~93.
[51] Blickle T and Thiele L. A Comparison of Selection Schemes Used in Genetic Algorithms, TIK-Report Ver. 2, Swiss Federal Institute of Technology, Dec. 1995.
[52] Zhang B-T and Kim J-J. Comparison of Selection Methods for Evolutionary Optimization [J]. Evolutionary Optimization, An International Journal on the Internet, 2000. 2(1): 55~70.
[53] Wieczorek W and Czech Z J. Selection Schemes in Evolutionary Algorithms [A]. XI International Symposium on Intelligent Information systems [C]. Sopot, June 3-6, 2002.
[54] De Jong K A. An Analysis of the Behavior of a Class of Genetic Adaptive Systems [D]. Doctoral Dissertation, Computer and Communication Sciences, University of Michigan, 1975.
[55] Barnard S T and Thompson W B. Disparity Analysis of Images [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, July 1980. 2(4): 333~340.
[56] Kim Y S, Han K P, Lee E J, et al. Robust 3-D Depth Estimation Using Genetic Algorithm in Stereo Image Pairs [A]. In Proc of IEEE Asia Pacific Conference on Circuits and Systems [C]. Seoul, Korea, Nov 18~21, 1996. 357~360.
[57] Jahn H. Parallel Epipolar Stereo Matching [A]. In Proceedings of the 15th International Conference on Pattern Recognition [C]. Barcelona, Spain, Sep 03-08, 2000. 1: 402~405.
[58] Aguado A S and Montiel E. Progressive Linear Search for Stereo Matching and Its Application to Interframe Interpolation [J]. Computer Vision and Image Understanding 2001. 81: 46~71.
[59] Ho P-K and Chung R. Stereo-Motion with Stereo and Motion in Complement [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, Feb 2000. 22(2): 215~220.
[60] Dornaika F and Chung R. Cooperative Stereo-Motion: Matching and Reconstruction [J]. Computer Vision and Image Understanding, 2000, 79: 408~427.
[61] Tai J M. Incremental 3D Reconstruction Using Stereo Image Sequences [D]. Master‘s Dissertation, Systems Design Engineering, University of Waterloo, Canada, 2000.
[62] Dhond U R and Aggarwal J K. Structure from Stereo— A Review [J]. IEEE Trans on Systems, Man, and Cybernetics, Nov./Dec. 1989. 19(6): 1489~1510.
[63] Gennery D B. Visual Terrain Matching for a Mars Rover [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. San Diego, California, 1989. 483~491.
[64] Kanade T and Okutomi M. A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment [A]. In Proceedings of IEEE Conference on Robotics and Automation [C]. Sacramento, California, April 1991. 1088~1095.
[65] Henkel R D. Fast Stereovision by Coherence Detection [A]. In Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns [C]. Kiel, Germany, Sep 10-12, 1997. 291~304.
[66] Gong M and Yang Y-H. Genetic-Based Stereo Algorithm and Disparity Map Evaluation [J]. International Journal of Computer Vision, 2002. 47(1/2/3): 73~77.
[67] Agrawal M and Davis L. Window-based, Discontinuity Preserving Stereo [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. 2003.
[68] Hoff W and Ahuja N. Surfaces from Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Feb 1989. 11(2): 121~136.
[69] Nagar V and Dudgeon J E. Stereo Image Databases for Flight Simulators [A]. In IEEE Proceedings of the 23th Southeastern Symposium on System Theory [C]. Columbia, SC, USA, March 10-12, 1991. 80~83.
[70] Raskar R. Edge-based Correspondence Using the Viterbi Algorithm [D]. Master Thesis, The University of Iowa,August 1995.
[71] Veksler O. Dense Features for Semi-Dense Stereo Correspondence [J]. International Journal of Computer Vision, 2002. 47(1/2/3): 247~260.
[72] Lhuillier M. Efficient Dense Matching for Textured Scenes Using Region Growing [A]. In Proc of the 9th British Machine Vision Conference [C]. UK, 1998. 700~709.
[73] Boult T E and Chen L-H. Analysis of Two New Stereo Algorithms [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. 1988. 177~182.
[74] Smith P, Sinclair D, Cipolla R, et al. Effective Corner Matching [A]. In Proc of the 9th British Machine Vision Conference [C]. Southampton, Sep 1998. 2: 545~556.
[75] Bhandarkar S M, Zhang Y, Potter W D. An Edge Detection Technique Using Genetic Algorithm-Based Optimization [J]. Pattern Recognition, 1994. 27(9): 1159~1180.
[76] Da Silva J D S, Simoni P O, and Bharadwaj K K. Multiple Correspondences in Stereo Vision under a Genetic Algorithm Approach [A]. In Proceedings of the 13th Brazilian Symposium on Computer Graphics and Image Processing [C]. Oct 17-20, 2000. 52~59.
[77] Luo L J, Clewer D R, Bull D R, et al. A Hierarchical Genetic Disparity Estimation Algorithm for Multiview Image Synthesis [A]. In Proc of International Conference on Image Processing [C]. Vancouver, BC, Canada, Sep 10-13, 2000. 768~771.
[78] Chai J and Ma S. An Evolutionary Framework for Stereo Correspondence [A]. In Proc of the 14th International Conference on Pattern Recognition [C]. Brisbane, Australia, Aug 1998. 16~20.
[79] Ruichek Y, Issa H, and Postaire J-G. Genetic Approach for Obstacle Detection using Linear Stereo Vision [A]. In Proceedings of the IEEE Intelligent Vehicles Symposium 2000 [C]. Dearborn (MI), USA, Oct 3-5, 2000.
[80] Zhang Y and Kambhamettu C. Stereo Matching with Segmentation-Based Cooperation [A]. In Proc of the 7th European Conference on Computer Vision [C]. Copenhagen, Denmark, May 2002. 2: 556~571.
[81] Fusiello A, Trucco E, and Verri A. Rectification with Unconstrained Stereo Geometry [A]. In Proc of British Machine Vision Conference [C]. Essex, 1997. 400~409.
[82] Fusiello A, Trucco E, and Verri A. A Compact Algorithm for Rectification of Stereo Pairs [J]. Machine Vision andApplications, 2000. 12(1): 16~22.
[83] Im J-H, Yoon Y-I, Kim J-H, et al. Plane Rectification Using Bilinear Forms on Projective Spaces [A]. In Proc of the 7th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2001) [C]. 2001. 19~24.
[84] Loop C and Zhang Z. Computing Rectifying Homographies for Stereo Vision [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. 1999. 1: 125~131.
[85] Bhat D N and Nayar S K. Ordinal Measures for Image Correspondence [J]. IEEE Trans on PatternAnalysis and Machine Intelligence,April 1998. 20(4): 415~423.
[86] Konecny G and Pape D. Correlation Techniques and Devices [J]. Photogrammetric Engineering and Remote Sensing, March 1981. 47(3): 323~333.
[87] Faugeras O D, Hotz B, Mathieu H, et al. Real Time Correlation-based Stereo: Algorithm, Implementations and Applications, Research Report 2013, INRIA, Sophia-Antipolis, France,August 1993.
[88] Pollard S B, Mayhew J E W, and Frisby J P. PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient Limit [J]. Perception, 1985. 14: 449~470.
[89] Trivedi H P and Lloyd S A. The Role of Disparity Gradient in Stereo Vision [J]. Perception, 1985. 14: 685~690.
[90] Scharstein D and Szeliski R. Stereo Matching with Non-Linear Diffusion [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. San Francisco, June 1996. 343~350.
[91] Scharstein D and Szeliski R. A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms [J]. International Journal of Computer Vision, April-June, 2002. 47(1/2/3): 7~42.
[92] Weiss I and Ray M. Model-Based Recognition of 3D Objects from Single Images [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, Feb 2001. 23(2): 116~128.
[93] Shashua A. Projective Structure from Uncalibrated Images: Structure from Motion and Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, August 1994. 16(8): 778~790.
[94] Shashua A. Algebraic Functions for Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,August 1995. 17(8): 779~789.
[95] Rohr K. Elastic Registration of Multimodal Medical Images: A Survey [J]. Auszug aus: Künstliche Intelligenz, 2000. 3: 11~17.
[96] Goshtasby A A. Transformation Functions, 2D and 3D Image Registration and Warping: ATutorial, Course 2 on SIGGRAPH'99, LosAngeles, CA,August 8, 1999.
[97] Lucas B D and Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision [A]. In Proc of Imaging Understanding Workshop [C]. 1981. 121~130.
[98] Stone H S, Orchard M T, Chang E-C, et al. A Fast Direct Fourier-Based Algorithm for Subpixel Registration of Images [J]. IEEE Transactions on Geoscience and Remote Sensing, Oct 2001. 39(10): 2235~2243.
[99] Zheng Q and Chellappa R. A Computational Vision Approach to Image Registration [J]. IEEE Transactions on Image Processing, July 1993. 2(3): 311~326.
[100] Hsieh J-W, Liao H-Y M, Fan K-C, et al. Image Registration Using a New Edge-Based Approach [J]. Computer Vision and Image Understanding,Aug 1997. 67(2): 112~130.
[101] Li H, Manjunath B S, and Mitra S K. A Contour-Based Approach to Multisensor Image Registration [J]. IEEE Trans on Image Processing, Mar 1995. 4(3): 320~334.
[102] Coiras E, Santamaria J, and Miravet C. A Segment-based Registration Technique for Visual-IR Images [J]. Optical Engineering, 2000. 39: 282~289.
[103] Liang Z-P, Pan H, Magin R L, et al. Automated Image Registration by Maximization of a Region Similarity Metric [J]. International Journal of Imaging System Technology, 1997. 8(6): 513~518.
[104] Ventura A D, Rampini A, and Schettini R. Image Registration by Recognition of Corresponding Structures [J]. IEEE Transactions on Geoscience and Remote Sensing, May 1990. 28(3): 305~314.
[105] Maintz J B A and Viergever M A. A Survey of Medical Image Registration [J]. Medical ImageAnalysis, 1998. 2(1): 1~37.
[106] Guest E, Berry E, Baldock R A, et al. Robust Point Correspondence Applied to Two- and Three-Dimensional Image Registration [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Feb 2001. 23(2): 165~179.
[107] He Y, Hamza A B, and Krim H. A Generalized Divergence Measure for Robust Image Registration [J]. IEEE Trans on Signal Processing, May 2003. 51(5): 1211~1220.
[108] Kaczmarek K, Walczak B, De Jong S, et al. Comparison of Image-Transformation Methods Used in Matching 2D GEL Electrophoresis Images [J]. ACTA Chromato-
graphica, 2003. 13: 7~21.
[109] Heyden A and Rohr K. Evaluation of Corner Extraction Schemes Using Invariance Methods [A]. In Proc of the 13th International Conference on Pattern Recognition [C]. Vienna,Austria,Aug 25-29, 1996. 895~899.
[110] Schmid C, Mohr R, and Bauckhage C. Comparing and Evaluating Interest Points [A]. In Proceedings of the 6th International Conference on Computer Vision [C]. Bombay, India, 1998. 230~235.
[111] Schmid C, Mohr R, and Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000. 37(2): 151~172.
[112] Mohanna F and Mokhtarian F. Performance Evaluation of Corner Detection Algorithms under Similarity and Affine Transforms [A]. In Proceedings of British Machine Vision Conference [C]. University of Manchester, Sep 10-13, 2001.
[113] Asada H and Brady M. The Curvature Primal Sketch [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Jan 1986. 8(1): 2~14.
[114] Rattarangsi A and Chin R T. Scale-Based Detection of Corners of Planar Curves [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, April 1992. 14(4): 430~449.
[115] Mokhtarian F and Suomela R. Robust Image Corner Detection through Curvature Scale Space [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Dec 1998. 20(12): 1376~1381.
[116] Tsai D-M, Hou H-T, and Su H-J. Boundary-based Corner Detection Using Eigenvalues of Covariance Matrices [J]. Pattern Recognition Letters, Jan 1999. 20(1): 31~40.
[117] Moravec H P. Towards Automatic Visual Obstacle Avoidance [A]. In Proceedings of International Conference onArtificial Intelligence [C]. 1977. 584.
[118] Harris C and Stephens M. A Combined Corner and Edge Detector [A]. Fourth Alvey Vision Conference [C]. 1988. 147~151.
[119] Cooper J, Venkatesh S, and Kitchen L. Early Jump-Out Corner Detectors [J]. IEEE Trans on Pattern Recognition and Machine Intelligence,Aug 1993. 15(8): 823~828.
[120] F?rstner W. A Framework for Low Level Feature Extraction [A]. In Proc of the 3rd European Conference on Computer Vision [C]. Stockholm, Sweden, 1994. 383~394.
[121] Smith S M and Brady J M. SUSAN— A New Approach to Low Level Image Processing [J]. International Journal of Computer Vision, May 1997. 23(1): 45~78.
[122] Trajkovic M and Hedley M. Fast Corner Detection [J]. Image and Vision Computing, Feb 20, 1998. 16(2): 75~87.
[123] Stammberger T, Michaelis M, Reiser M, et al. AHierarchical Filter Scheme for Efficient Corner Detection [J]. Pattern Recognition Letters, 1998. 19(8): 680~700.
[124] Blaszka T and Deriche R. Recovering and Characterizing Image Features Using an Efficient Model Based Approach, Research Report 2422, INRIA, Sophia-Antipolis, France, Nov. 1994.
[125] Baker S, Nayar S K, and Murase H, Parametric Feature Detection [J]. International Journal of Computer Vision, 1998. 27(1): 27~50.
[126] Shen F and Wang H. Real Time Gray Level Corner Detector [A]. In Proceedings of the 6th International Conference on Control, Automation, Robotics and Vision [C]. Singapore, Dec 5-8, 2000.
[127] Rohr K. On the Precision in Estimating the Location of Edges and Corners [J]. Journal of Mathematical Imaging and Vision, 1997. 7: 7~22.
[128] Sung H J. Queen-bee Evolution for Genetic Algorithms [J]. Electronics Letters, March 20, 2003. 39(6): 575~576.
[129] Bierwirh C, Mattfeld D C, and Kopfer H. On Permutation Representations for Scheduling Problems [A]. In Proc of Parallel Problem Solving from Nature [C]. Lecture Notes on Computer Science, Springer-Verlag, Berlin Heidelberg, New York, 1996. 1141: 310~318.
[130] Chai J and Ma S. Robust Epipolar Geometry Estimation Using Genetic Algorithm [J]. Pattern Recognition Letters, 1998. 19: 829~838.
[131] Luong Q-T, Deriche R, Faugeras O D, et al. On Determining the Fundamental Matrix: Analysis of Different Methods and Experimental Results, Research Report 2273, INRIA, Sophia-Antipolis, France,April 1993.
[132] Zhang Z. Determining the Epipolar Geometry and its Uncertainty: A Review [J]. International Journal of Computer Vision, 1998. 27(2): 161~195.
[133] Zhang Z and Loop C. Estimating the Fundamental Matrix by Transforming Image Points in Projective Space [J]. Computer Vision and Image Understanding, May 2001. 82(2): 174~180.
[134] Torr P H S and Murray D W. The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix [J]. International Journal of Computer Vision, 1997. 24(3): 271~300.
[135] Boufama B S and Mohr R. A Stable and Accurate Algorithm for Computing Epipolar Geometry [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1998. 12(6): 817~840.
[136] Ponce J and Genc Y. Epipolar Geometry and Linear Subspace Methods: A New Approach to Weak Calibration [J]. International Journal of Computer Vision, 1998. 28(3): 223~243.
[137] Hartley R I. In Defence of the 8-point Algorithm [A]. In Proc. of the 5th International Conference on Computer Vision [C]. June 20-23, 1995.
[138] Starkweather T, McDaniel S, Mathias K, et al. A Comparison of Genetic Sequencing Operators [A]. In Proc. of the 4th International Conference on Genetic Algorithms [C]. Morgan Kaufmann, 1991. 69~76.
[139] Brizuela C A and Aceves R. Experimental Genetic Operators Analysis for the Multi- objective Permutation Flowshop [J]. EMO 2003. Lecture Notes on Computer Science, 2003. 2632: 578~592.
[2] Shapiro L G and Stockman G. Computer Vision [M]. Prentice-Hall, 2001.
[3] Shashua A. Geometry and Photometry in 3D Visual Recognition. Technique Report, AI-TR 1401, MIT, 1992.
[4] Forsyth D A and Ponce J. Computer Vision: A Modern Approach [M], Prentice-Hall, 2003.
[5] Zhang R, Tsai P-S, Cryer J E, et al. Shape from Shading: A Survey [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, 1999, 21(8): 690~706.
[6] Faugeras O D. Three-Dimensional Computer Vision: A Geometric Viewpoint [M], The MIT Press, Cambridge, Massachusetts, 1993.
[7] Xu G and Zhang Z. Epipolar Geometry in Stereo, Motion and Object Recognition: A UnifiedApproach [M]. KluwerAcademic Publishers, 1996.
[8] Poggio T and Koch C. Ill-posed Problems in Early Vision: from Computational Theory to Analogue Networks [A]. In Proc of Royal Society London B 226 [C]. 1985. 303~323.
[9] Poggio T, Torre V, and Koch C. Computational Vision and Regularization Theory [J]. Nature, Sep 26, 1985, 317: 314~319.
[10] Brady M. Computational Approaches to Image Understanding [J]. Computing Surveys, March 1982, 14(1): 3~71.
[11] Koch C, Marroquin J, and Yuille A, Analog “Neuronal”Networks in Early Vision [A]. In Proc of NationalAcademic Science USA[C], June 1986. 83: 4263~4267.
[12] Mohr R and Triggs B. Projective Geometry for Image Analysis, A Tutorial given at ISPRS (International Society for Photogrammetry and Remote Sensing) [C]. Vienna, July 1996.
[13] Gros P, Mohr R, Quan L, et al. How Useful is Projective Geometry [J]. Computer Vision and Image Understanding, Mar 1997. 3(65): 442~446.
[14] Collins S H. Stereoscopic Depth Perception [J]. Photogrammetric Engineering and Remote Sensing, Jan 1981. 47(1): 45~52.
[15] Muddy J L and Zisserman A. Geometric Invariance in Computer Vision [M], Chapter 23: Appendix –Projective Geometry for Machine Vision, The MIT Press, Cambridge, MA,
1992. 463~534.
[16] Faugeras D. Stratification of 3-D Vision: Projective, Affine and Metric Representations [J]. Journal of the Optical Society of America A, Mar 1995. 12(3): 465~484.
[17] Birchfield S. An Introduction to Projective Geometry (for computer vision) [OL]. http://robotics.stanford.edu/~birch/projective/, 1998.
[18] Barnard S T and Fischler M A. Computational Stereo [J]. Computing Surveys, Dec 1982. 14(4): 553~572.
[19] Hartley R and Zisserman A. Multiple View Geometry in Computer Vision [M], Cambridge University Press, 2000.
[20] Elias R and Laganière R. Projective Geometry for Three-Dimensional Computer Vision, Technical Report, TR-2001-08, School of Information Technology and Eng., University of Ottawa, Canada, 2001.
[21] Cochran S D and Medioni G. 3D Surface Description from Binocular Stereo [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, Oct 1992. 14(10): 981~994.
[22] Zitnick C L and Kanade T. A Cooperative Algorithm for Stereo Matching and Occlusion Detection, Technical Report CMU-RI-TR-99-35, Carnegie Mellon University, 1999.
[23] Kumar K S and Desai U B. New Algorithms for 3D Surface Description from Binocular Stereo Using Integration [J]. Journal of Franklin Institute, 1994. 331B(5): 531~554.
[24] Marr D and Poggio T. A Computational theory of Human Stereo Vision [A]. In Porc of Royal Society London B 204 [C]. 1979. 301~328.
[25] Zhang Z, Deriche R, Faugeras O D, et al. A Robust Technique for Matching Two Uncalibrated Images through the Recovery of the Unknown Epipolar Geometry, Research Report 2273, INRIA, Sophia-Antipolis, France, May 1994.
[26] Jones G A. Constraint, Optimization, and Hierarchy: Reviewing Stereoscopic Correspon- dence of Complex Features [J]. Computer Vision and Image Understanding, Jan 1997. 65(1): 57~78.
[27] Brown L G. A Survey of Image Registration Techniques [J]. ACM Computing Surveys, Dec 1992. 24(4): 325~376.
[28] Cass T A. Polynomial-Time Geometric Matching for Object Recognition [J]. Interna- tional Journal of Computer Vision, 1997. 21(1/2): 37~61.
[29] Sivazlian B D and Stanfel L E. Optimization Techniques in Operations Research [M]. Prentice-Hall Inc, Englewood Cliffs, New Jersey, 1975.
[30] Wolfe M A. Numerical Methods for Unconstrained Optimization [M]. Van Nostrand Reinhold Company Ltd, Molly Millars Lane, Workingham, Berkshire, England, 1978.
[31] Rao S S. Optimization: Theory andApplications [M]. Wiley Eastern Limited, 1979.
[32] Gill P E, Murray W, Wright M H. Practical Optimization [M].Academic Press, 1981.
[33] Luenberger D G. Linear and Nonlinear Programming [M]. 2nd Edition, Addison-Wesley Publishing Company, 1984.
[34] Gr?tschel M and Lovász L. Combinatorial Optimization: A Survey, DIMACS Technical Report 93-29, May 1993.
[35] Deb K. Genetic Algorithms for Function Optimization [A]. In Genetic algorithms and soft computing [M]. Herrera F, Verdegay J (ed.), Heidelberg: Physica-Verl, 1996.
[36] Gimel'farb G. Stereo Terrain Reconstruction by Dynamic Programming, Technical Report CITR-TR-21, The University ofAuckland, June 1998.
[37] Kirkpatrick S, Gelatt C D, Jr, et al. Optimization by Simulated Annealing [J]. Science, May 13, 1983. 220(4598): 671~680.
[38] Locatelli M. Simulated Annealing Algorithms for Global Continuous Optimization [A]. In Handbook of Global Optimization: Vol. 2 [M]. Edited by Pardalos P M and Romeijn H E. KluwerAcademic Publishers, May 2002.
[39] Johnson D S, Aragon C R, Mcgeoch L A, et al. Optimization by Simulated Annealing: an Experimental Evaluation; Part II, Graph Coloring and Number Partitioning [J]. Operations Research, May-June 1991. 39(3): 378~406.
[40] Ingber L. Simulated Annealing: Practice versus Theory [J]. Journal of Mathematical and Computer Modeling, 1993. 18(11): 29~57.
[41] Ingber L. Adaptive Simulated Annealing (ASA): Lessons Learned [J]. Journal of Control and Cybernetics, 1996. 25(1): 33~54.
[42] Chandler B, Rekeczky C, Nishio Y, et al. Adaptive Simulated Annealing in CNN Template Learning [J]. IEICE Trans Fundamentals, Feb 1999. E82-A(2): 398~402.
[43] Ingber L and Rosen B. Genetic Algorithms and Very Fast Simulated Reannealing: a Comparison [J]. Journal of Mathematical and Computer Modeling, 1992. 16(11): 87~100.
[44] Davis L. Handbook of Genetic Algorithms [M]. New York: Van Nostrand Reinhold, 1991.
[45] Michalewicz Z. Genetic Algorithms + Data Structures = Evolution Programs [M]. Springer-Verlag, Berlin, 1996.
[46] Whitley D.AGenetic Algorithm Tutorial [J]. Statistics and Computing, 1994. 4: 65~85.
[47] Salomon R. Short Notes on the Schema Theorem and the Building Block Hypothesis in Genetic Algorithms [J]. Evolutionary Programming VII, Springer, Berlin, V. W. Porto, N. Saravanan, D. Waagen, andA. E. Eiben, 1998. 113~122.
[48] Deb K. Genetic Algorithm in Search and Optimization: The Technique and Applications [A]. In Proc of International Workshop on Soft Comput and Intel System [C]. Calcutta, India: Machine Intelligence Unit, Indian Statistical Institute, 1998. 58~87.
[49] Fogel D B. An Introduction to Simulated Evolutionary Optimization [J]. IEEE Trans on Neural Networks, Jan 1994. 5(1): 3~14.
[50] Goldberg D E and Deb K. A Comparative Analysis of Selection Schemes Used in Genetic Algorithms [A]. In Foundations of Genetic Algorithms [M]. Rawlins G J (ed.), San Mateo, CA, 1991. 69~93.
[51] Blickle T and Thiele L. A Comparison of Selection Schemes Used in Genetic Algorithms, TIK-Report Ver. 2, Swiss Federal Institute of Technology, Dec. 1995.
[52] Zhang B-T and Kim J-J. Comparison of Selection Methods for Evolutionary Optimization [J]. Evolutionary Optimization, An International Journal on the Internet, 2000. 2(1): 55~70.
[53] Wieczorek W and Czech Z J. Selection Schemes in Evolutionary Algorithms [A]. XI International Symposium on Intelligent Information systems [C]. Sopot, June 3-6, 2002.
[54] De Jong K A. An Analysis of the Behavior of a Class of Genetic Adaptive Systems [D]. Doctoral Dissertation, Computer and Communication Sciences, University of Michigan, 1975.
[55] Barnard S T and Thompson W B. Disparity Analysis of Images [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, July 1980. 2(4): 333~340.
[56] Kim Y S, Han K P, Lee E J, et al. Robust 3-D Depth Estimation Using Genetic Algorithm in Stereo Image Pairs [A]. In Proc of IEEE Asia Pacific Conference on Circuits and Systems [C]. Seoul, Korea, Nov 18~21, 1996. 357~360.
[57] Jahn H. Parallel Epipolar Stereo Matching [A]. In Proceedings of the 15th International Conference on Pattern Recognition [C]. Barcelona, Spain, Sep 03-08, 2000. 1: 402~405.
[58] Aguado A S and Montiel E. Progressive Linear Search for Stereo Matching and Its Application to Interframe Interpolation [J]. Computer Vision and Image Understanding 2001. 81: 46~71.
[59] Ho P-K and Chung R. Stereo-Motion with Stereo and Motion in Complement [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, Feb 2000. 22(2): 215~220.
[60] Dornaika F and Chung R. Cooperative Stereo-Motion: Matching and Reconstruction [J]. Computer Vision and Image Understanding, 2000, 79: 408~427.
[61] Tai J M. Incremental 3D Reconstruction Using Stereo Image Sequences [D]. Master‘s Dissertation, Systems Design Engineering, University of Waterloo, Canada, 2000.
[62] Dhond U R and Aggarwal J K. Structure from Stereo— A Review [J]. IEEE Trans on Systems, Man, and Cybernetics, Nov./Dec. 1989. 19(6): 1489~1510.
[63] Gennery D B. Visual Terrain Matching for a Mars Rover [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. San Diego, California, 1989. 483~491.
[64] Kanade T and Okutomi M. A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment [A]. In Proceedings of IEEE Conference on Robotics and Automation [C]. Sacramento, California, April 1991. 1088~1095.
[65] Henkel R D. Fast Stereovision by Coherence Detection [A]. In Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns [C]. Kiel, Germany, Sep 10-12, 1997. 291~304.
[66] Gong M and Yang Y-H. Genetic-Based Stereo Algorithm and Disparity Map Evaluation [J]. International Journal of Computer Vision, 2002. 47(1/2/3): 73~77.
[67] Agrawal M and Davis L. Window-based, Discontinuity Preserving Stereo [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. 2003.
[68] Hoff W and Ahuja N. Surfaces from Stereo: Integrating Feature Matching, Disparity Estimation, and Contour Detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Feb 1989. 11(2): 121~136.
[69] Nagar V and Dudgeon J E. Stereo Image Databases for Flight Simulators [A]. In IEEE Proceedings of the 23th Southeastern Symposium on System Theory [C]. Columbia, SC, USA, March 10-12, 1991. 80~83.
[70] Raskar R. Edge-based Correspondence Using the Viterbi Algorithm [D]. Master Thesis, The University of Iowa,August 1995.
[71] Veksler O. Dense Features for Semi-Dense Stereo Correspondence [J]. International Journal of Computer Vision, 2002. 47(1/2/3): 247~260.
[72] Lhuillier M. Efficient Dense Matching for Textured Scenes Using Region Growing [A]. In Proc of the 9th British Machine Vision Conference [C]. UK, 1998. 700~709.
[73] Boult T E and Chen L-H. Analysis of Two New Stereo Algorithms [A]. IEEE Conference on Computer Vision and Pattern Recognition [C]. 1988. 177~182.
[74] Smith P, Sinclair D, Cipolla R, et al. Effective Corner Matching [A]. In Proc of the 9th British Machine Vision Conference [C]. Southampton, Sep 1998. 2: 545~556.
[75] Bhandarkar S M, Zhang Y, Potter W D. An Edge Detection Technique Using Genetic Algorithm-Based Optimization [J]. Pattern Recognition, 1994. 27(9): 1159~1180.
[76] Da Silva J D S, Simoni P O, and Bharadwaj K K. Multiple Correspondences in Stereo Vision under a Genetic Algorithm Approach [A]. In Proceedings of the 13th Brazilian Symposium on Computer Graphics and Image Processing [C]. Oct 17-20, 2000. 52~59.
[77] Luo L J, Clewer D R, Bull D R, et al. A Hierarchical Genetic Disparity Estimation Algorithm for Multiview Image Synthesis [A]. In Proc of International Conference on Image Processing [C]. Vancouver, BC, Canada, Sep 10-13, 2000. 768~771.
[78] Chai J and Ma S. An Evolutionary Framework for Stereo Correspondence [A]. In Proc of the 14th International Conference on Pattern Recognition [C]. Brisbane, Australia, Aug 1998. 16~20.
[79] Ruichek Y, Issa H, and Postaire J-G. Genetic Approach for Obstacle Detection using Linear Stereo Vision [A]. In Proceedings of the IEEE Intelligent Vehicles Symposium 2000 [C]. Dearborn (MI), USA, Oct 3-5, 2000.
[80] Zhang Y and Kambhamettu C. Stereo Matching with Segmentation-Based Cooperation [A]. In Proc of the 7th European Conference on Computer Vision [C]. Copenhagen, Denmark, May 2002. 2: 556~571.
[81] Fusiello A, Trucco E, and Verri A. Rectification with Unconstrained Stereo Geometry [A]. In Proc of British Machine Vision Conference [C]. Essex, 1997. 400~409.
[82] Fusiello A, Trucco E, and Verri A. A Compact Algorithm for Rectification of Stereo Pairs [J]. Machine Vision andApplications, 2000. 12(1): 16~22.
[83] Im J-H, Yoon Y-I, Kim J-H, et al. Plane Rectification Using Bilinear Forms on Projective Spaces [A]. In Proc of the 7th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2001) [C]. 2001. 19~24.
[84] Loop C and Zhang Z. Computing Rectifying Homographies for Stereo Vision [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. 1999. 1: 125~131.
[85] Bhat D N and Nayar S K. Ordinal Measures for Image Correspondence [J]. IEEE Trans on PatternAnalysis and Machine Intelligence,April 1998. 20(4): 415~423.
[86] Konecny G and Pape D. Correlation Techniques and Devices [J]. Photogrammetric Engineering and Remote Sensing, March 1981. 47(3): 323~333.
[87] Faugeras O D, Hotz B, Mathieu H, et al. Real Time Correlation-based Stereo: Algorithm, Implementations and Applications, Research Report 2013, INRIA, Sophia-Antipolis, France,August 1993.
[88] Pollard S B, Mayhew J E W, and Frisby J P. PMF: A Stereo Correspondence Algorithm Using a Disparity Gradient Limit [J]. Perception, 1985. 14: 449~470.
[89] Trivedi H P and Lloyd S A. The Role of Disparity Gradient in Stereo Vision [J]. Perception, 1985. 14: 685~690.
[90] Scharstein D and Szeliski R. Stereo Matching with Non-Linear Diffusion [A]. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition [C]. San Francisco, June 1996. 343~350.
[91] Scharstein D and Szeliski R. A Taxonomy and Evaluation of Dense Two-frame Stereo Correspondence Algorithms [J]. International Journal of Computer Vision, April-June, 2002. 47(1/2/3): 7~42.
[92] Weiss I and Ray M. Model-Based Recognition of 3D Objects from Single Images [J]. IEEE Trans on PatternAnalysis and Machine Intelligence, Feb 2001. 23(2): 116~128.
[93] Shashua A. Projective Structure from Uncalibrated Images: Structure from Motion and Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, August 1994. 16(8): 778~790.
[94] Shashua A. Algebraic Functions for Recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,August 1995. 17(8): 779~789.
[95] Rohr K. Elastic Registration of Multimodal Medical Images: A Survey [J]. Auszug aus: Künstliche Intelligenz, 2000. 3: 11~17.
[96] Goshtasby A A. Transformation Functions, 2D and 3D Image Registration and Warping: ATutorial, Course 2 on SIGGRAPH'99, LosAngeles, CA,August 8, 1999.
[97] Lucas B D and Kanade T. An Iterative Image Registration Technique with an Application to Stereo Vision [A]. In Proc of Imaging Understanding Workshop [C]. 1981. 121~130.
[98] Stone H S, Orchard M T, Chang E-C, et al. A Fast Direct Fourier-Based Algorithm for Subpixel Registration of Images [J]. IEEE Transactions on Geoscience and Remote Sensing, Oct 2001. 39(10): 2235~2243.
[99] Zheng Q and Chellappa R. A Computational Vision Approach to Image Registration [J]. IEEE Transactions on Image Processing, July 1993. 2(3): 311~326.
[100] Hsieh J-W, Liao H-Y M, Fan K-C, et al. Image Registration Using a New Edge-Based Approach [J]. Computer Vision and Image Understanding,Aug 1997. 67(2): 112~130.
[101] Li H, Manjunath B S, and Mitra S K. A Contour-Based Approach to Multisensor Image Registration [J]. IEEE Trans on Image Processing, Mar 1995. 4(3): 320~334.
[102] Coiras E, Santamaria J, and Miravet C. A Segment-based Registration Technique for Visual-IR Images [J]. Optical Engineering, 2000. 39: 282~289.
[103] Liang Z-P, Pan H, Magin R L, et al. Automated Image Registration by Maximization of a Region Similarity Metric [J]. International Journal of Imaging System Technology, 1997. 8(6): 513~518.
[104] Ventura A D, Rampini A, and Schettini R. Image Registration by Recognition of Corresponding Structures [J]. IEEE Transactions on Geoscience and Remote Sensing, May 1990. 28(3): 305~314.
[105] Maintz J B A and Viergever M A. A Survey of Medical Image Registration [J]. Medical ImageAnalysis, 1998. 2(1): 1~37.
[106] Guest E, Berry E, Baldock R A, et al. Robust Point Correspondence Applied to Two- and Three-Dimensional Image Registration [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Feb 2001. 23(2): 165~179.
[107] He Y, Hamza A B, and Krim H. A Generalized Divergence Measure for Robust Image Registration [J]. IEEE Trans on Signal Processing, May 2003. 51(5): 1211~1220.
[108] Kaczmarek K, Walczak B, De Jong S, et al. Comparison of Image-Transformation Methods Used in Matching 2D GEL Electrophoresis Images [J]. ACTA Chromato-
graphica, 2003. 13: 7~21.
[109] Heyden A and Rohr K. Evaluation of Corner Extraction Schemes Using Invariance Methods [A]. In Proc of the 13th International Conference on Pattern Recognition [C]. Vienna,Austria,Aug 25-29, 1996. 895~899.
[110] Schmid C, Mohr R, and Bauckhage C. Comparing and Evaluating Interest Points [A]. In Proceedings of the 6th International Conference on Computer Vision [C]. Bombay, India, 1998. 230~235.
[111] Schmid C, Mohr R, and Bauckhage C. Evaluation of Interest Point Detectors [J]. International Journal of Computer Vision, 2000. 37(2): 151~172.
[112] Mohanna F and Mokhtarian F. Performance Evaluation of Corner Detection Algorithms under Similarity and Affine Transforms [A]. In Proceedings of British Machine Vision Conference [C]. University of Manchester, Sep 10-13, 2001.
[113] Asada H and Brady M. The Curvature Primal Sketch [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Jan 1986. 8(1): 2~14.
[114] Rattarangsi A and Chin R T. Scale-Based Detection of Corners of Planar Curves [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, April 1992. 14(4): 430~449.
[115] Mokhtarian F and Suomela R. Robust Image Corner Detection through Curvature Scale Space [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Dec 1998. 20(12): 1376~1381.
[116] Tsai D-M, Hou H-T, and Su H-J. Boundary-based Corner Detection Using Eigenvalues of Covariance Matrices [J]. Pattern Recognition Letters, Jan 1999. 20(1): 31~40.
[117] Moravec H P. Towards Automatic Visual Obstacle Avoidance [A]. In Proceedings of International Conference onArtificial Intelligence [C]. 1977. 584.
[118] Harris C and Stephens M. A Combined Corner and Edge Detector [A]. Fourth Alvey Vision Conference [C]. 1988. 147~151.
[119] Cooper J, Venkatesh S, and Kitchen L. Early Jump-Out Corner Detectors [J]. IEEE Trans on Pattern Recognition and Machine Intelligence,Aug 1993. 15(8): 823~828.
[120] F?rstner W. A Framework for Low Level Feature Extraction [A]. In Proc of the 3rd European Conference on Computer Vision [C]. Stockholm, Sweden, 1994. 383~394.
[121] Smith S M and Brady J M. SUSAN— A New Approach to Low Level Image Processing [J]. International Journal of Computer Vision, May 1997. 23(1): 45~78.
[122] Trajkovic M and Hedley M. Fast Corner Detection [J]. Image and Vision Computing, Feb 20, 1998. 16(2): 75~87.
[123] Stammberger T, Michaelis M, Reiser M, et al. AHierarchical Filter Scheme for Efficient Corner Detection [J]. Pattern Recognition Letters, 1998. 19(8): 680~700.
[124] Blaszka T and Deriche R. Recovering and Characterizing Image Features Using an Efficient Model Based Approach, Research Report 2422, INRIA, Sophia-Antipolis, France, Nov. 1994.
[125] Baker S, Nayar S K, and Murase H, Parametric Feature Detection [J]. International Journal of Computer Vision, 1998. 27(1): 27~50.
[126] Shen F and Wang H. Real Time Gray Level Corner Detector [A]. In Proceedings of the 6th International Conference on Control, Automation, Robotics and Vision [C]. Singapore, Dec 5-8, 2000.
[127] Rohr K. On the Precision in Estimating the Location of Edges and Corners [J]. Journal of Mathematical Imaging and Vision, 1997. 7: 7~22.
[128] Sung H J. Queen-bee Evolution for Genetic Algorithms [J]. Electronics Letters, March 20, 2003. 39(6): 575~576.
[129] Bierwirh C, Mattfeld D C, and Kopfer H. On Permutation Representations for Scheduling Problems [A]. In Proc of Parallel Problem Solving from Nature [C]. Lecture Notes on Computer Science, Springer-Verlag, Berlin Heidelberg, New York, 1996. 1141: 310~318.
[130] Chai J and Ma S. Robust Epipolar Geometry Estimation Using Genetic Algorithm [J]. Pattern Recognition Letters, 1998. 19: 829~838.
[131] Luong Q-T, Deriche R, Faugeras O D, et al. On Determining the Fundamental Matrix: Analysis of Different Methods and Experimental Results, Research Report 2273, INRIA, Sophia-Antipolis, France,April 1993.
[132] Zhang Z. Determining the Epipolar Geometry and its Uncertainty: A Review [J]. International Journal of Computer Vision, 1998. 27(2): 161~195.
[133] Zhang Z and Loop C. Estimating the Fundamental Matrix by Transforming Image Points in Projective Space [J]. Computer Vision and Image Understanding, May 2001. 82(2): 174~180.
[134] Torr P H S and Murray D W. The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix [J]. International Journal of Computer Vision, 1997. 24(3): 271~300.
[135] Boufama B S and Mohr R. A Stable and Accurate Algorithm for Computing Epipolar Geometry [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1998. 12(6): 817~840.
[136] Ponce J and Genc Y. Epipolar Geometry and Linear Subspace Methods: A New Approach to Weak Calibration [J]. International Journal of Computer Vision, 1998. 28(3): 223~243.
[137] Hartley R I. In Defence of the 8-point Algorithm [A]. In Proc. of the 5th International Conference on Computer Vision [C]. June 20-23, 1995.
[138] Starkweather T, McDaniel S, Mathias K, et al. A Comparison of Genetic Sequencing Operators [A]. In Proc. of the 4th International Conference on Genetic Algorithms [C]. Morgan Kaufmann, 1991. 69~76.
[139] Brizuela C A and Aceves R. Experimental Genetic Operators Analysis for the Multi- objective Permutation Flowshop [J]. EMO 2003. Lecture Notes on Computer Science, 2003. 2632: 578~592.