基于集成互补不变特征的多源遥感影像配准方法研究
|
摘要
遥感图像配准不仅是图像镶嵌、变化检测、信息融合、目标识别和跟踪的关键技术，而且也是天气预报及地图更新等在内的各种遥感图像分析目的的关键步骤之一，它的主要任务是实现同一目标在不同时相、不同角度或不同传感器获得的图像数据在空间位置上的一致。目前，对该技术研究的热点之一就是基于特征的配准方法。论文在全面总结和分析已有的基于特征的图像配准技术的基础上，主要研究了集成多种特征的多源遥感图像配准问题。
论文全面分析了已有的局部不变特征提取和描述算法，匹配搜索策略以及匹配优化提取算法等影响图像配准的各种因素，提出了两种分别适应光学遥感图像和SAR图像配准的集成特征配准算法，并采用大量的实际遥感图像进行实验以验证所提方法的正确性。论文主要包括如下研究成果：
(1)在讨论局部不变特征提取和描述过程中，针对目前主流的特征提取算法即SIFT算法比较耗时且仿射不变性弱的缺陷，提出首先降低SIFT描述符的维数，以降低运算时间，然后结合仿射不变矩的仿射不变性，从而增强描述符的仿射不变性。
(2)由于单一特征的局限性，论文通过全面分析和讨论各种特征属性对特征配准算法的影响过程，提出一种基于集成MSER和SIFT-AIM (Scale InvariantFeature Transform and Affine Invariant Moment,SIFT-AIM)互补不变特征的配准算法。该配准算法采用由粗到精两步匹配过程，首先，采用MSER特征进行粗匹配，以此初步校正图像对的空间几何畸变；然后，采用SIFT-AMI特征进行精确匹配，以此增强图像的仿射不变性和节省图像配准时间，最终达到提高图像配准精度的目的。这样能够消除或减弱由单一特征的局限性引起的配准误差。
(3)论文通过全面分析各种特征属性后，针对光学影像配准较成功的算法用于SAR影像配准却失败的问题，提出一种集成Canny边缘和SIFT互补不变特征配准方法。首先，该配准算法通过采用Canny边缘进行区域分割，利用分割的区域进行区域粗匹配，从而达到初步校正SAR影像空间形变的目的；然后，通过提取Canny边缘上稳定的SIFT特征点进行精确匹配。
论文成果丰富了遥感图像特征提取与配准的相关理论和方法，同时为后续的多源遥感图像融合奠定了良好的基础。
Remote sensing image registration is not only the key technology using in thefield of imaging mosaic, changing detection, information fusion, target recognitionand tracking, but also one of the critical steps for a variety of remote sensing imageanalysis purposes including weather forecast, map updates, and so on, whose maintask is to achieve the aligned position in space of the image data from one objectwhich obtained in different time phase, at different angles or from different sensors.Currently, feature-based registration method is one of the registration technologyresearch focuses. This thesis surveys and analyses the existing feature-based imageregistration techniques, and emphasis is given to study the integrating multiplefeatures multi-source remote sensing image registration problems.
This thesis comprehensively analyzes various factors of affecting imageregistration which includes the existing local invariant feature extraction anddescription algorithm, matching and searching strategy as well as matchingoptimization extraction algorithm, then two integration feature registration algorithmswhich respectively adapt the optical remote sensing image and SAR image areproposed, and a number of actual remote sensing images are used to experiments inorder to verify the correctness of the proposed methods. The research achievementsare as follows:
(1)In the process of studying local invariant feature extraction and descriptionalgorithm, the thesis found that popular SIFT algorithm consumes too long time andit’s worse in terms of its affine invariance, in order to resolve this problem, the thesispropose a new method to save time, enhance affine invariance and improve theregistration accuracy, which reduce the dimension of SIFT descriptor firstly to savethe time of constructing descriptor, then combined the affine invariance of affineinvariant moment to improve the affine invariance of descriptor, finally achieved theexcepted result.
(2) Due to the limitations of the single feature, the thesis propose a newregistration algorithm based on integrating MSER and SIFT-AIM complementaryinvariant feature through comprehensive analysis and discussion of the affectingprocess between various feature properties and feature registration algorithm. Thenew registration algorithm can be used to eliminate or reduce the registration errorcaused by the limitation of single feature through two steps from coarse registration to fine registration. Firstly, the method take coarse registration using MSER feature, andthe spatial geometric deformation was corrected; then image affine invariance wasimproved and image registration time was saved through further fine registrationusing SIFT-AIM feature, finally, enhanced image registration was achieved.
(3)After comprehensive analysis of various feature properties, thesis find it’salways failed when the algorithm that is successful in optical image registration wasused to deal with SAR image registration. To address this problem, thesis proposed aregistration method integrating Canny edge and SIFT complementary invariantfeature. To begin with, the registration algorithm split segment using canny edge, andcoarse registration was done utilizing split segment, so the spatial deformation of SARimage was corrected initially. Lastly, the fine registration was achieved through thestable SIFT feature points extracted from canny edge.
The achievement in this thesis can enrich the relative theories and methods of theremote sensing image feature extraction and registration, and establishes a goodfoundation for the follow-up of multi-source remote sensing image fusion.
论文全面分析了已有的局部不变特征提取和描述算法，匹配搜索策略以及匹配优化提取算法等影响图像配准的各种因素，提出了两种分别适应光学遥感图像和SAR图像配准的集成特征配准算法，并采用大量的实际遥感图像进行实验以验证所提方法的正确性。论文主要包括如下研究成果：
(1)在讨论局部不变特征提取和描述过程中，针对目前主流的特征提取算法即SIFT算法比较耗时且仿射不变性弱的缺陷，提出首先降低SIFT描述符的维数，以降低运算时间，然后结合仿射不变矩的仿射不变性，从而增强描述符的仿射不变性。
(2)由于单一特征的局限性，论文通过全面分析和讨论各种特征属性对特征配准算法的影响过程，提出一种基于集成MSER和SIFT-AIM (Scale InvariantFeature Transform and Affine Invariant Moment,SIFT-AIM)互补不变特征的配准算法。该配准算法采用由粗到精两步匹配过程，首先，采用MSER特征进行粗匹配，以此初步校正图像对的空间几何畸变；然后，采用SIFT-AMI特征进行精确匹配，以此增强图像的仿射不变性和节省图像配准时间，最终达到提高图像配准精度的目的。这样能够消除或减弱由单一特征的局限性引起的配准误差。
(3)论文通过全面分析各种特征属性后，针对光学影像配准较成功的算法用于SAR影像配准却失败的问题，提出一种集成Canny边缘和SIFT互补不变特征配准方法。首先，该配准算法通过采用Canny边缘进行区域分割，利用分割的区域进行区域粗匹配，从而达到初步校正SAR影像空间形变的目的；然后，通过提取Canny边缘上稳定的SIFT特征点进行精确匹配。
论文成果丰富了遥感图像特征提取与配准的相关理论和方法，同时为后续的多源遥感图像融合奠定了良好的基础。
Remote sensing image registration is not only the key technology using in thefield of imaging mosaic, changing detection, information fusion, target recognitionand tracking, but also one of the critical steps for a variety of remote sensing imageanalysis purposes including weather forecast, map updates, and so on, whose maintask is to achieve the aligned position in space of the image data from one objectwhich obtained in different time phase, at different angles or from different sensors.Currently, feature-based registration method is one of the registration technologyresearch focuses. This thesis surveys and analyses the existing feature-based imageregistration techniques, and emphasis is given to study the integrating multiplefeatures multi-source remote sensing image registration problems.
This thesis comprehensively analyzes various factors of affecting imageregistration which includes the existing local invariant feature extraction anddescription algorithm, matching and searching strategy as well as matchingoptimization extraction algorithm, then two integration feature registration algorithmswhich respectively adapt the optical remote sensing image and SAR image areproposed, and a number of actual remote sensing images are used to experiments inorder to verify the correctness of the proposed methods. The research achievementsare as follows:
(1)In the process of studying local invariant feature extraction and descriptionalgorithm, the thesis found that popular SIFT algorithm consumes too long time andit’s worse in terms of its affine invariance, in order to resolve this problem, the thesispropose a new method to save time, enhance affine invariance and improve theregistration accuracy, which reduce the dimension of SIFT descriptor firstly to savethe time of constructing descriptor, then combined the affine invariance of affineinvariant moment to improve the affine invariance of descriptor, finally achieved theexcepted result.
(2) Due to the limitations of the single feature, the thesis propose a newregistration algorithm based on integrating MSER and SIFT-AIM complementaryinvariant feature through comprehensive analysis and discussion of the affectingprocess between various feature properties and feature registration algorithm. Thenew registration algorithm can be used to eliminate or reduce the registration errorcaused by the limitation of single feature through two steps from coarse registration to fine registration. Firstly, the method take coarse registration using MSER feature, andthe spatial geometric deformation was corrected; then image affine invariance wasimproved and image registration time was saved through further fine registrationusing SIFT-AIM feature, finally, enhanced image registration was achieved.
(3)After comprehensive analysis of various feature properties, thesis find it’salways failed when the algorithm that is successful in optical image registration wasused to deal with SAR image registration. To address this problem, thesis proposed aregistration method integrating Canny edge and SIFT complementary invariantfeature. To begin with, the registration algorithm split segment using canny edge, andcoarse registration was done utilizing split segment, so the spatial deformation of SARimage was corrected initially. Lastly, the fine registration was achieved through thestable SIFT feature points extracted from canny edge.
The achievement in this thesis can enrich the relative theories and methods of theremote sensing image feature extraction and registration, and establishes a goodfoundation for the follow-up of multi-source remote sensing image fusion.
引文
[1]吕金建.基于特征的多源遥感图像配准技术研究[D].长沙:国防科学技术大学,2008.
[2]朱述龙,朱宝山,王红卫等.遥感图像处理原理与应用[M].北京:科学出版社,2006.
[3]L. G. Roberts. Machine Perception of3-D Solids [D]: Ph.D. Thesis. America: MIT,1963.
[4]P. E. Anuta. Registration of multispectral video imagery [J]. Society Photo-Optical Instrum. Eng. J.,1969,7:168-175.
[5]P. E. Anuta. Spatial registration of multispectral and multtemporal digital imagery using fast Fouriertransform techniques [J]. IEEE Transactions on Geoscience Electronics,1970,8(4):353-368.
[6]K. I. Mori, M. Kidode and H. Asada. An iterative prediction and correction method for automatic stereocomparison [J]. Computer Graphics and Image Processing,1973,2:393-401.
[7]M. D. Levine, D. O.O Handley and G. M. Yagi. Computer determination of depth maps [J]. ComputerGraphics and Image Processing,1973,2(4):131-150.
[8]R. Nevatia. Depth measurement by motion stereo[J]. Computer Graphics and Image Processing,1976,5:203-214.
[9]M. Singh, W. Frei, T. Shibata and G. C. Huth. A digital technique for accurate change detection in nuclearmedical images with application to myocardial perfusion studies using Thallium-201[J]. IEEETransactions on Nuclear Science,1979,26(1):565-575.
[10]Pluim J W and Fitzpatrick J M. Image registration[J]. IEEE Transactions on Medical Imaging,2003,22(11):1341-1343.
[11]刘松涛,杨绍清.图像配准技术研究进展[J].电光与控制,2007,14(6):99-105.
[12]罗小慧,基于特征和灰度的影像配准方法[D]:学位论文.北京:中国科学院遥感应用研究所,1993.
[13]Attneave F. Some informational aspects of visual perception[J]. Psychological Review1954,61:183-193.
[14]Moravec H. Towards automatic visual obstacle avoidance[C]. In: Proceedings of the International JointConference on Artificial Intelligence.1977.
[15]Johnson A, Hebert M. Using spin images for efficient object recognition in cluttered3D scenes[J]. IEEEComputer Vision and Pattern Recognition1999,21(5):433-449.
[16]C.Harris, M.Stephens. A combined corner and edge detector. In: the Alvey Vision Conference,1988,147-151.
[17]Linderberg T. Feature detection with automatic scale selection[J]. International Journal of ComputerVision1998,30(2):79-116.
[18]Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors[J]. International Journal ofComputer Vision2004,60(1):63-86.
[19]Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions onPattern Analysis and Machine Intelligence2005,27(10):1615-1630.
[20]邓宝松.基于点线特征的大基线图像序列三维重建技术研究[D].长沙:国防科学技术大学研究生院,2006.
[21]Mokhtarian F, Suomela R. Robust image corner detection through curvature scale space[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381.
[22]Mokhtarian F, Mackworth A. Scale-based description and recognition of planar curves andtwo-dimensional shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(1):34-43.
[23]Abbasi S, Mokhtarian F, Kitter J. Enhancing CSS-based shape retrieval for objects with shadowconcavities[J]. Image Vision Computing,2000,18:199-211.
[24]Rohr K. Recognizing corners by fitting parametric models[J]. International Journal of Computer Vision,1992,9(3):213-230.
[25]周拥军.基于未检校CCD相机的三维测量方法及其在结构变形监测中的应用[D].上海:上海交通大学船舶海洋与建筑工程学院,2007.
[26]Harris C, Stephens M. A combined corner and edge detector [C]//Proceedings of Alvey VisionConference. New York, USA: ACM Press,1988:147-151.
[27]Smith S M, Brady J M. SUSAN-a new approach to low level image processing [J]. International Journalof Computer Vision,1997,23(1):45-78.
[28]Lowe D G. Distinctive image features from Scale-invariant Key points[J]. International Journal ofComputer Vision,2004,60(2):91-110
[29]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features [C]//Proceedings ofInternational Conference on Computer Vision and Pattern Recognition. Cambridge, MA, USA: MITPress,2001:511-518.
[30]Lee CH, Varshney A, Jacobs DW. Mesh saliency [J]. ACMTransactions on Graphics,2005,24(3):659-666.
[31]Matas J, Chum O, and Urban M, et al. Robust wide-baseline stereo from maximally stable extremalregions [J]. Image Vision Computing,2004,22(10):761-767.
[32]Schlattmann M. Intrinsic features on surfaces [C]//Proceedings of the10th Central European Seminaron Computer Graphics, Vienna,2006:1692176.
[33]Koenderink J, Doorn Av. Representation of local geometry in the visual system[J].BiologicalCvbernetics archive1987,55(6):367-375.
[34]Florack LMJ, Romeny BMTH, Koenderink JJ, Viergever MA. General intensity transformations anddifferential invariants[J]. Journal of Mathematical Imaging and Vision1994,4(2):171-187.
[35]Freeman W, Adelson E. The design and use of steerable filters[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence1991,13(9):891-906.
[36]Daugman JG. Uncertainty relations for resolution in space, spatial frequency, and orientation optimizedby two-dimensional visual cortical filters[J]. Journal of the Optical Society of America1985,2:1160-1169.
[37]Marcelja S. Mathematical description of the responses of simple cortical cells[J]. Journal of the OpticalSociety of America1980,70(11):1297-1300.
[38]Zabih R, Woodfill J. Non-parametric Local Transforms for Computing Visual Correspondence[C]. In:Proceedings of the Third European Conference on Computer Vision.1994. Stockholm.
[39]G. Lowe D. Object recognition from local scale-Invariant features [C]. In: Proceeding of theInternational Conference on Computer Vision(ICCV’1999).1999.
[40]Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors[C]. In:2004IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2004.
[41]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEETransactions on Pattern Analysis and Machine Intelligence2002.24(4):509-522.
[42]Hu M K. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory,1962,8(1):179-187.
[43]Suk T, Flusser J. Combined blurred and affine moment invariants and their use in pattern recognition[J].Pattern Recognition Letters2003.36(12):2895-2907.
[44]刘萍萍.图像的局部不变性特征方法研究[D].吉林大学,2009.
[45]Florack L, Romeny BTH, Koenderink J, Viergever M. General intensity transformations and secondorder invariants[C]. In: the7thScandinavian Conference on Image Analysis.1991. Aalborg,Denmark.
[46]Baumberg. Reliable feature matching across widely separated views[C]. In: Conference on ComputerVision and Pattern Recognition.2000. Hilton Head Island, South Carolina, USA.
[47]Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets[C]. In: the7th EuropeanConference on Computer Vision.2002. Copenhagen, Denmark.
[48]Mikolajczyk K, Tuytelaars T, Schmid C. A Comparison of affine region detectors[J]. InternationalJournal of Computer Vision,2005,60(1):163-186.
[49]李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006，10(6):885-892.
[50]李芳芳,肖本林,贾永红,等. SIFT算法优化及其用于遥感影像自动配准[J].武汉大学学报(信息科学版),2009,34(10):1245-1249.
[51]陈方,熊智,许允喜,等.惯性组合导航系统中的快速影像匹配算法研究[J].宇航学报,2009,30(6):2308-2316.
[52]李玲玲,李翠华,曾晓明,等.基于Harris-Affine和SIFT特征匹配的图像自动配准[J].华中科技大学学报(自然科学版),2008,36(8):13-16.
[53]葛永新,杨丹,雷明.基于良分布的亚像素定位角点的图像配准[J].电子与信息学报,2010,32(2):427-432.
[54]Yu L, Zhang D R, Holden E J. A fast and fully automatic registration approach based on point featuresfor multi-source remote-sensing images[J]. Computers&Geosciences,2008,34:838-848.
[55]程亮,龚健雅,韩鹏,等.遥感影像仿射不变特征匹配的自动优化[J].武汉大学学报(信息科学版),2009,34(4):417-421.
[56]Wang H, Brady M. Real-time corner detection algorithm for motion estimation[J]. Image and VisionComputing1995,13(9):695-703.
[57]Rutkowski WS, Rosenfeld A. A comparison of corner detection techniques for chain coded curves:Maryland University,1978.
[58]Beaudet PR. Rotationally invariant image operators[C].In: Proceedings of the International JointConference on Pattern Recognition.1978.
[59]Nagel HH. Displacement vectors derived from second-order intensity variations in image sequences[J].Computer Vision Graphics and Image Processing1983,21:85-117.
[60]Kitchen L, Rosenfeld A. Gray-level corner detection[J]. Pattern Recognition Letters,1982,1:95-102.
[61]Schmid C, Mohr R. Combining gray-value invariants with local constraints for object recognition[C]. In:Proceedings of the Conference on Computer Vision and Pattern Recognition.1996.
[62]Rosten E, Drummond T. Fusing points and lines for high performance tracking[C]. In: Proceedings ofthe International Conference on Computer Vision.2005.
[63]Smith SM, Brady JM. SUSAN-a new approach to low level image processing[J]. International Journalof Computer Vision1997,23(1):45-78.
[64]E.Snyder W, Qi H.机器视觉教程[M].北京:机械工业出版社.2005.
[65]T. Lee. Image representation using2-D Gabor Wavelets[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence1996,18(10):959-971.
[66] http://b2museum.cdstm.cn/identification/sztxcl-relative.htm
[67]贾惠珍,王同罕.基于自适应微调因子的改进frost滤波[J].计算机工程与设计,2011,32(11):3793-3843.
[68]岳春宇,江万涛.一种利用级联滤波和松弛法的SAR图像配准方法[J].武汉大学学报·信息科学版,2012,37(1):43-62.
[69]C.A.Deledalle, L.Denis, F.Tupin. Iterative weighted maximum likelihood denoising with probabilisticpatch-based weights[J].IEEE Transactions on Image Processing,2009,18(12):2661-2672.
[70]周建民,何秀凤.星载SAR图像的斑点噪声抑制与滤波研究[J].河海大学学报(自然科学版),2006,34(2):189-192.
[71]徐新,廖明生,卜方玲.一种基于相对标准差的SAR图像Speckle滤波方法[J].遥感学报,2000,4(3):214-218.
[72]Witkin A P. Scale-space filtering[C]. Proc.8th Int. Joint Conf. Art. Intell. Karlsruhe, Germany,1983.
[73]Koenderink J J. Jan. The structure of images, Biological Cybernetics,1984(50).
[74]张洁玉.图像局部不变特征提取与匹配及应用研究[D].南京：南京理工大学，2010.
[74]Lindeberg T. Scale-space theory in computer vision. Kluwer Academic Publishers,1994.
[75]Florack L M J. ter Haar Romeny B M, Koenderink J J, et al. Scale and the differential structure ofimages[J]. Image and Vision Computer,1992,10(6).
[76]孙浩,王程,王润生.局部不变特征综述[J].中国图像图形学报,2011,16(2):141-151.
[77]H. Moravec. Rover visual obstacle avoidance[C]. Proceedings of the7thInternational Joints Conferenceon Artificial Intelligence, Vancouver,1981:785-790.
[78]陈志方,张艳宁,杨将林等.一种改进的SUSAN算法[J].微电子学与计算机,2007,24(11):142-144.
[79]张迁,刘政凯,庞彦伟等.一种遥感影像的自动配准方法[J].小型微型计算机系统,2004,25(7):1129-1131.
[80]V. Etienne, L. Robert. Detecting and matching feature points[J]. Journal of Visual Communication andImage Representation,2005,16(1):38-54.
[81]K. Y. Chae, W. P. Dong, C. S. Jeong. SUSAN window based cost calculation for fast stereo matching[C].Proceedings of the International Conference on Computational Intelligence and Security,2005,3802:947-952.
[82]顾华,苏光大,杜成等.人脸关键特征点的自动定位[J].光电子·激光,2004,15(8):975-979.
[83]王荣本,余天洪,顾柏园.基于边界的车道标识线识别和跟踪方法研究[J].计算机工程,2006,32(18):195-196.
[84]H. Mauricio, M. Geovanni. Facial feature extraction based on the smallest univalue segment assimilatingnucleus (SUSAN) algorithm[C]. Proceedings of the International Conference on Picture CodingSymposiump,2004,261-266.
[85]C. Harris, M. Stephens. A combined corner and edge detector[C]. Proceedings of the4thAlvey VisionConference, Mancheste,1988:147-151.
[86]C. Schmid, R. Mohr, C. Bauckhage. Evaluation of interest point detectors[J]. International Journal ofComputer Vision,2000,37(2):151-172.
[87]王阿妮,马彩文,刘爽等.基于角点的红外与可见光图像自动配准方法[J].光子学报,2009,38(12):3328-3332.
[88]仵建宁,郭宝龙,冯宗哲.一种基于兴趣点匹配的图像拼接方法[J].计算机应用,2006,26(3):610-612.
[89]X. Wang, B. Yang. Automatic image registration based on natural characteristic points and globalhomography[C]. Proceedings of the International Conference on Computer Science and SoftwareEngineering,2008,2:1365-1370.
[90]冯宇平,戴明,张威等.一种用于图像序列拼接的角点检测算法[J].计算机科学,2009,36(12):270-271.
[91]郭辉.基于视频的车辆检测和车型识别研究[D](硕士论文)。华东交通大学硕士论文,2009.
[92]张美多,郭宝龙.车牌识别系统关键技术研究[J].计算机工程,2007,33(16):186-188.
[93]孙敏,李德玉,俞梦孙.基于Harris算子和K-means聚类的红外图像脸部特征自动定位.航天医学与医学工程,2007,20(4):285-288.
[94]陈宇波,许海柱,黄婷婷等.在人脸图像中确定嘴巴位置的方法[J].电子科技大学学报,2007,36(6):1308-1310.
[95]谭园园,李俊山,杨威.新的近距离红外目标跟踪算法[J].电光与控制,2007,14(3):8-11.
[96]刘闯,龚声蓉,崔志明等.基于角点采样的多目标跟踪方法[J].中国图像图形学报,2008,13(10):1873-1877.
[97]黄祖伟.基于双目立体视觉的目标跟踪算法研究[D].山东大学硕士论文,2007.
[98]K. Mikolajczyk, C. Schmid. Indexing based on scale invariant interest points[C]. Proceedings of the8thInternational Conference on Computer Vision, Vancouver, Canada,2001,525-531.
[99]K. Mikolajczyk, C. Schmid. An affine invariant interest point detector[C]. Proceedings of the7thEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,128-142.
[100]K. Mikolajczyk. Detection of local features invariant to affine transformations[D]. Ph.D.thesis, InstituteNational Polytechnique de Grenoble, France,2002.
[101]T. Lindeberg. Feature detection with automatic scale selection[J]. International Journal of ComputerVision,1998,30(2):79-116.
[102]李伟生,王卫星,罗代建.用Harris-Laplace特征进行遥感图像配准[J].四川大学学报(工程科学版),2011,43(4):89-94.
[103]D. Marr, E. Hildreth. Theory of edge detection[C]. Proceedings of the Royal Society of London (SeriesB), Biological Sciences,1980,207(1167):187-217.
[104]Tuytelaars T, Mikolajczyk K. Local invariant feature detectors: a survey [J]. Foundations and Trends inComputer Graphics and Vision,2007,3(3):177-280.
[105]B. M. Romeny, L. M. J. Florack, A. H. Salden, et al. Higher order differential structure of images[J].Image and Vision Computing,1994,12(6):317-325.
[106]C. Schmid, R. Mohr. Local grayvalue invariants for image retrieval [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1997,19(5):530-534.
[107]T. Lindeberg. Scale-space theory: A basic tool for analyzing structures at different scales[J]. Journal ofApplied Statistics,1994,21(2):224-270.
[108]Heymann S, Mller K, Smolic A, et.al. SIFT implementation and optimization for General-Purpose GPU[C]. In Proceedings of the15thInternational Conference in Central Europe on Computer Graphics,Visualization and Computer Vision,2007.
[109]Se S, Lowe D G, Little J. Vision-based mobile robot localization and mapping using scale-invariantfeatures [C]. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)2,2001.
[110]Se S, Ng H, Jasiobedzki P, et al. Vision based modeling and localization for planetary explorationrovers[C]. Proceedings of International Astronautical Congress,23. Viola, P., Jones, M.,2004.
[111]Kristensen F, Maclean W J. Real-time Extraction of Maximally Stable Extremal Regions on an FPGA[].International Symposium on Circuits and Systems,2007.
[112]K. Mikolajczyk, C. Schmid. Comparison of affine-invariant local detectors and descriptors[C].Proceedings of12thEuropean Signal Processing Conference, Vienna, Austria,2004.
[113]Tuytelaars T, Gool L V. Matching widely separated views based on affine invariant regions [J].International Journal of Computer Vision,2004,59(1):61-85.
[114]Harris C,Stephens M. A Combined Corner and Edge Detector [C]. Proc. Alvey Vision Conf., Univ.Manchester,1988.
[115]Canny J. A computational approach to edge detection [J]. IEEE Transactionson Pattern Analysis andMachine Intelligence,1986, PAMZ-8(6).
[116]Kadir T, Brady M. Scale, Saliency and image description [J]. International Journal of Computer Vision,2001,45(2).
[117]Kadir T, Zisserman A, Brady M. An affine invariant salient region detector [C]//Proceedings of the8thEuropean Conference on Computer Vision. New York, USA:ACM Press,2004:345-457.
[118]Enriquec, Santanmariaj and Miravetc. Segment-based registration technique for visual-infrared images[J]. Optical Engineering,2000,39(1):282-289.
[119]Taylor C. R. Line triangulation for image registration [C]. Proceedings of SPIE, Orlando, FL, USA,2002,364-373.
[120]康欣,韩崇昭,杨艺.基于结构的SAR图像配准[J].系统仿真学报,2006,18(5):1307-1310.
[121]张继贤,李国胜,曾钰.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77.
[122]H. S. Alhichri and M. Kamel. Virtual circles: a new set of features for fast image registration [J].Pattern Recognition Letters,2003,24(5):1181-1190.
[123]Lindeberg T. Detecting salient blob-Like image structures and their scales with a scale-space primalsketch: A method for focus-of-attention, International Journal of Computer Vision,1993,11(3).
[124]王永明,王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社,2010.
[125]Bay H, Tuytelaars T, Van Gool L. SURF: Speeded up robust features. In ECCV,2006.
[126] Bay H, Tuytelaars T, Van Gool L. Speeded-up robust features (SURF)[J]. Computer Vision and ImageUnderstanding,2008,110.
[127]廉蔺,李国辉,王海涛,田昊,徐树奎.基于MSER的红外与可见光图像关联特征提取算法[J].电子与信息学报,2011,33(7):1625-1631.
[128]Vincent L, Soille P. Watersheds in digital spaces: An effiecient algorithm based on immersionsimulations. TPAMI,1991.
[129]Murphy C E, Trivedi M. N-tree disjoint-set foreset for maximally stable extremal regions[C].BMVC,2006.
[130]Michael Reed Teague. Image analysis via the general theory of moments[].Optical Society of America,1980.
[131]Teague M. Image analysis via the general theory of moments [J]. Journal of the Optical Society ofAmerica,1980,70(8).
[132]PEI S C,LIN C N. Image normalization for pattern recognition[J]. Image and Vision Computing,1995,13(10):711-723.
[133]LEU J G. Shape normalization through compacting[J]. Pattern Recognition Letters,1989,10(4):243-250.
[134]K. Mikolajczyk, C. Schmid. Comparison of affine invariant local detectors and descriptors [C].Proceedings of12thEuropean Signal Processing Conference, Vienna, Austria,2004.
[135]S. Belongie, J. Malik, J. Puzicha, Shape context: A new descriptor for shape matching and objectrecognition[C]. Proceedings of the Neural Information Processing Systems,2000,831-837.
[136]W. Freeman, E. Adelson. The design and use of steerable filters [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1991,13(9):891-906.
[137]P. Montesinos, V. Gouet, R. Deriche. Differential invariants for color images [C]. Proceedings of14thInternational Conference on Pattern Recognition, Brisbane, Australia,1998.
[138]L. Van Gool, T. Moons, D. Ungureanu. Affine/photometric invariants for planar intensity patterns [C].Proceedings of the4thEuropean Conference on Computer Vision, Cambridge, UK,1996,642-651.
[139]F. Schaffalitzky, A. Zisserman. Multi-view matching for unordered image sets [C]. Proceedings of the7thEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,414-431.
[140]曾万梅,吴庆宪,姜长生.基于组合不变矩特征的空中目标识别方法[J].电光与控制,2009,6(7):21-24.
[141]付波,周建中,彭兵,等.基于仿射不变矩的轴心轨迹自动识别方法[J].华中科技大学学报(自然科学版),2007,35(3):119-122.
[142] Flusser J, SUK T. Pattern recognition by affine moment invariants[J]. Pattern Recognition,1993,26(1):167-174.
[143]Li J, M N, Allinson. A comprehensive review of current local features for computer vision[J].Neurocomputing,2008,71(10-12):1771-1787.
[144]袁修孝,钟灿.一种改进的正射影像镶嵌线性最小化最大搜索算法[J].测绘学报,2012,41(2):199-204.
[145]胡正平,王玲丽.基于L1范数凸包数据描述的多观测样本分类算法[J].电子与信息学报,2012,34(1):194-199.
[146]刘晴,唐林波,赵保军等.基于自适应多特征融合的均值迁移红外目标跟踪[J].电子与信息学报,2012,34(5):1137-1142.
[147]陈冰,赵亦工,李欣.一种新的宽基线图像匹配方法[J].西安电子科技大学学报(自然科学版),2011,38(2):116-123.
[148]董道国,薛向阳,罗航哉.多维数据索引结构回顾[J].计算机科学,2002,29(3).
[149]刘芳洁,董道国,薛向阳.度量空间中高维索引结构回顾[J].计算机科学,2003,30(7).
[150]Bentley J L. Multidimensional binary search trees used for associative searching. Communications ofthe ACM,1975,18(9).
[151]Guttman A, R-trees: A Dynamic index structure for spatial searching [C]. In Proc. ACM SIGMODInternational Conference on Management of Data,1984.
[152]Lee D T, Wibg C K. Worst-Case analysis for region and partial region searches in multidimensionalbinary search trees and balanced quad trees. Acta Informatica,1976,9(23).
[153]Liu T, Moore A, Gray A, et al. An investigation of practical approximate nearest neighbor algorithms.In NIPS,2004.
[154]杨秋菊,肖雪梅.基于改进Canny特征点的SIFT算法[J].计算机工程与设计,2011,32(7):2428-2431. Improved SIFT algorithm based on Canny feature points, Computer Engineer andDesign.
[157]刘黎宁,侯榆青,高士瑞.一种改进的综合纹理和形状特征的图像检索方法[J].小型微型计算机系统,2012,33(5):1141-1144.
[158]刘黎宁,侯榆青,高士瑞.一种改进的综合纹理和形状特征的图像检索方法[J].小型微型计算机系统,2012,33(5):1141-1144.
[159]Long Xiang, Wu Xiaoqing. Motion segmentation based on fusion of MSRF segmentation and Cannyoperator[J]. Procedia Engineering,2011,15:1637-1641.
[160]杨秋菊,肖雪梅.基于改进Canny特征点的SIFT算法[J].计算机工程与设计,2011,32(7):2428-2431.
[161]李昆仑,曹铮,曹丽萍,等.半监督聚类的若干新进展[J].模式识别与人工智能,2009,22(5):735-742.
[162]吕金建,文贡坚,王继阳,等.一种改进的基于不变描述子的图像自动配准方法[J].信号处理,2009,216-222.
[163]Chang Yulin, Zhou Zhimin, Chang Wenge,et al. A new registration method for multi-spectral SARimages[C]. IEEE International on Geoscience and Remote Sensing Symposium,2005:1704-1708.
[164]王大伟,基于特征级图像融合的目标识别技术研究[D].长春：长春光学精密机械与物理研究所,2010.
[165]甘甫平,刘圣伟,周强.德兴铜矿矿山污染高光谱遥感直接识别研究[J].地球科学,2004,(01):78-83.
[166]TIMOTHY M K, TALALAAT M R. Structural controls on neoprotero zoic mineralization in the southeastern desert, Egypt: AnIntegrated Field, LandsatTM, and SIR-C/X SAR Approach[J].JournalofAfrican Earth Sciences,2002,35(1):107-121.
[167]杨波,吴德文,赖健清.矿化信息提取定量遥感模型的建立[J].遥感学报,2005(6):717-724.
[2]朱述龙,朱宝山,王红卫等.遥感图像处理原理与应用[M].北京:科学出版社,2006.
[3]L. G. Roberts. Machine Perception of3-D Solids [D]: Ph.D. Thesis. America: MIT,1963.
[4]P. E. Anuta. Registration of multispectral video imagery [J]. Society Photo-Optical Instrum. Eng. J.,1969,7:168-175.
[5]P. E. Anuta. Spatial registration of multispectral and multtemporal digital imagery using fast Fouriertransform techniques [J]. IEEE Transactions on Geoscience Electronics,1970,8(4):353-368.
[6]K. I. Mori, M. Kidode and H. Asada. An iterative prediction and correction method for automatic stereocomparison [J]. Computer Graphics and Image Processing,1973,2:393-401.
[7]M. D. Levine, D. O.O Handley and G. M. Yagi. Computer determination of depth maps [J]. ComputerGraphics and Image Processing,1973,2(4):131-150.
[8]R. Nevatia. Depth measurement by motion stereo[J]. Computer Graphics and Image Processing,1976,5:203-214.
[9]M. Singh, W. Frei, T. Shibata and G. C. Huth. A digital technique for accurate change detection in nuclearmedical images with application to myocardial perfusion studies using Thallium-201[J]. IEEETransactions on Nuclear Science,1979,26(1):565-575.
[10]Pluim J W and Fitzpatrick J M. Image registration[J]. IEEE Transactions on Medical Imaging,2003,22(11):1341-1343.
[11]刘松涛,杨绍清.图像配准技术研究进展[J].电光与控制,2007,14(6):99-105.
[12]罗小慧,基于特征和灰度的影像配准方法[D]:学位论文.北京:中国科学院遥感应用研究所,1993.
[13]Attneave F. Some informational aspects of visual perception[J]. Psychological Review1954,61:183-193.
[14]Moravec H. Towards automatic visual obstacle avoidance[C]. In: Proceedings of the International JointConference on Artificial Intelligence.1977.
[15]Johnson A, Hebert M. Using spin images for efficient object recognition in cluttered3D scenes[J]. IEEEComputer Vision and Pattern Recognition1999,21(5):433-449.
[16]C.Harris, M.Stephens. A combined corner and edge detector. In: the Alvey Vision Conference,1988,147-151.
[17]Linderberg T. Feature detection with automatic scale selection[J]. International Journal of ComputerVision1998,30(2):79-116.
[18]Mikolajczyk K, Schmid C. Scale&affine invariant interest point detectors[J]. International Journal ofComputer Vision2004,60(1):63-86.
[19]Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions onPattern Analysis and Machine Intelligence2005,27(10):1615-1630.
[20]邓宝松.基于点线特征的大基线图像序列三维重建技术研究[D].长沙:国防科学技术大学研究生院,2006.
[21]Mokhtarian F, Suomela R. Robust image corner detection through curvature scale space[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1998,20(12):1376-1381.
[22]Mokhtarian F, Mackworth A. Scale-based description and recognition of planar curves andtwo-dimensional shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(1):34-43.
[23]Abbasi S, Mokhtarian F, Kitter J. Enhancing CSS-based shape retrieval for objects with shadowconcavities[J]. Image Vision Computing,2000,18:199-211.
[24]Rohr K. Recognizing corners by fitting parametric models[J]. International Journal of Computer Vision,1992,9(3):213-230.
[25]周拥军.基于未检校CCD相机的三维测量方法及其在结构变形监测中的应用[D].上海:上海交通大学船舶海洋与建筑工程学院,2007.
[26]Harris C, Stephens M. A combined corner and edge detector [C]//Proceedings of Alvey VisionConference. New York, USA: ACM Press,1988:147-151.
[27]Smith S M, Brady J M. SUSAN-a new approach to low level image processing [J]. International Journalof Computer Vision,1997,23(1):45-78.
[28]Lowe D G. Distinctive image features from Scale-invariant Key points[J]. International Journal ofComputer Vision,2004,60(2):91-110
[29]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features [C]//Proceedings ofInternational Conference on Computer Vision and Pattern Recognition. Cambridge, MA, USA: MITPress,2001:511-518.
[30]Lee CH, Varshney A, Jacobs DW. Mesh saliency [J]. ACMTransactions on Graphics,2005,24(3):659-666.
[31]Matas J, Chum O, and Urban M, et al. Robust wide-baseline stereo from maximally stable extremalregions [J]. Image Vision Computing,2004,22(10):761-767.
[32]Schlattmann M. Intrinsic features on surfaces [C]//Proceedings of the10th Central European Seminaron Computer Graphics, Vienna,2006:1692176.
[33]Koenderink J, Doorn Av. Representation of local geometry in the visual system[J].BiologicalCvbernetics archive1987,55(6):367-375.
[34]Florack LMJ, Romeny BMTH, Koenderink JJ, Viergever MA. General intensity transformations anddifferential invariants[J]. Journal of Mathematical Imaging and Vision1994,4(2):171-187.
[35]Freeman W, Adelson E. The design and use of steerable filters[J]. IEEE Transactions on Pattern Analysisand Machine Intelligence1991,13(9):891-906.
[36]Daugman JG. Uncertainty relations for resolution in space, spatial frequency, and orientation optimizedby two-dimensional visual cortical filters[J]. Journal of the Optical Society of America1985,2:1160-1169.
[37]Marcelja S. Mathematical description of the responses of simple cortical cells[J]. Journal of the OpticalSociety of America1980,70(11):1297-1300.
[38]Zabih R, Woodfill J. Non-parametric Local Transforms for Computing Visual Correspondence[C]. In:Proceedings of the Third European Conference on Computer Vision.1994. Stockholm.
[39]G. Lowe D. Object recognition from local scale-Invariant features [C]. In: Proceeding of theInternational Conference on Computer Vision(ICCV’1999).1999.
[40]Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors[C]. In:2004IEEE Computer Society Conference on Computer Vision and Pattern Recognition.2004.
[41]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts[J]. IEEETransactions on Pattern Analysis and Machine Intelligence2002.24(4):509-522.
[42]Hu M K. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory,1962,8(1):179-187.
[43]Suk T, Flusser J. Combined blurred and affine moment invariants and their use in pattern recognition[J].Pattern Recognition Letters2003.36(12):2895-2907.
[44]刘萍萍.图像的局部不变性特征方法研究[D].吉林大学,2009.
[45]Florack L, Romeny BTH, Koenderink J, Viergever M. General intensity transformations and secondorder invariants[C]. In: the7thScandinavian Conference on Image Analysis.1991. Aalborg,Denmark.
[46]Baumberg. Reliable feature matching across widely separated views[C]. In: Conference on ComputerVision and Pattern Recognition.2000. Hilton Head Island, South Carolina, USA.
[47]Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets[C]. In: the7th EuropeanConference on Computer Vision.2002. Copenhagen, Denmark.
[48]Mikolajczyk K, Tuytelaars T, Schmid C. A Comparison of affine region detectors[J]. InternationalJournal of Computer Vision,2005,60(1):163-186.
[49]李晓明,郑链,胡占义.基于SIFT特征的遥感影像自动配准[J].遥感学报,2006，10(6):885-892.
[50]李芳芳,肖本林,贾永红,等. SIFT算法优化及其用于遥感影像自动配准[J].武汉大学学报(信息科学版),2009,34(10):1245-1249.
[51]陈方,熊智,许允喜,等.惯性组合导航系统中的快速影像匹配算法研究[J].宇航学报,2009,30(6):2308-2316.
[52]李玲玲,李翠华,曾晓明,等.基于Harris-Affine和SIFT特征匹配的图像自动配准[J].华中科技大学学报(自然科学版),2008,36(8):13-16.
[53]葛永新,杨丹,雷明.基于良分布的亚像素定位角点的图像配准[J].电子与信息学报,2010,32(2):427-432.
[54]Yu L, Zhang D R, Holden E J. A fast and fully automatic registration approach based on point featuresfor multi-source remote-sensing images[J]. Computers&Geosciences,2008,34:838-848.
[55]程亮,龚健雅,韩鹏,等.遥感影像仿射不变特征匹配的自动优化[J].武汉大学学报(信息科学版),2009,34(4):417-421.
[56]Wang H, Brady M. Real-time corner detection algorithm for motion estimation[J]. Image and VisionComputing1995,13(9):695-703.
[57]Rutkowski WS, Rosenfeld A. A comparison of corner detection techniques for chain coded curves:Maryland University,1978.
[58]Beaudet PR. Rotationally invariant image operators[C].In: Proceedings of the International JointConference on Pattern Recognition.1978.
[59]Nagel HH. Displacement vectors derived from second-order intensity variations in image sequences[J].Computer Vision Graphics and Image Processing1983,21:85-117.
[60]Kitchen L, Rosenfeld A. Gray-level corner detection[J]. Pattern Recognition Letters,1982,1:95-102.
[61]Schmid C, Mohr R. Combining gray-value invariants with local constraints for object recognition[C]. In:Proceedings of the Conference on Computer Vision and Pattern Recognition.1996.
[62]Rosten E, Drummond T. Fusing points and lines for high performance tracking[C]. In: Proceedings ofthe International Conference on Computer Vision.2005.
[63]Smith SM, Brady JM. SUSAN-a new approach to low level image processing[J]. International Journalof Computer Vision1997,23(1):45-78.
[64]E.Snyder W, Qi H.机器视觉教程[M].北京:机械工业出版社.2005.
[65]T. Lee. Image representation using2-D Gabor Wavelets[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence1996,18(10):959-971.
[66] http://b2museum.cdstm.cn/identification/sztxcl-relative.htm
[67]贾惠珍,王同罕.基于自适应微调因子的改进frost滤波[J].计算机工程与设计,2011,32(11):3793-3843.
[68]岳春宇,江万涛.一种利用级联滤波和松弛法的SAR图像配准方法[J].武汉大学学报·信息科学版,2012,37(1):43-62.
[69]C.A.Deledalle, L.Denis, F.Tupin. Iterative weighted maximum likelihood denoising with probabilisticpatch-based weights[J].IEEE Transactions on Image Processing,2009,18(12):2661-2672.
[70]周建民,何秀凤.星载SAR图像的斑点噪声抑制与滤波研究[J].河海大学学报(自然科学版),2006,34(2):189-192.
[71]徐新,廖明生,卜方玲.一种基于相对标准差的SAR图像Speckle滤波方法[J].遥感学报,2000,4(3):214-218.
[72]Witkin A P. Scale-space filtering[C]. Proc.8th Int. Joint Conf. Art. Intell. Karlsruhe, Germany,1983.
[73]Koenderink J J. Jan. The structure of images, Biological Cybernetics,1984(50).
[74]张洁玉.图像局部不变特征提取与匹配及应用研究[D].南京：南京理工大学，2010.
[74]Lindeberg T. Scale-space theory in computer vision. Kluwer Academic Publishers,1994.
[75]Florack L M J. ter Haar Romeny B M, Koenderink J J, et al. Scale and the differential structure ofimages[J]. Image and Vision Computer,1992,10(6).
[76]孙浩,王程,王润生.局部不变特征综述[J].中国图像图形学报,2011,16(2):141-151.
[77]H. Moravec. Rover visual obstacle avoidance[C]. Proceedings of the7thInternational Joints Conferenceon Artificial Intelligence, Vancouver,1981:785-790.
[78]陈志方,张艳宁,杨将林等.一种改进的SUSAN算法[J].微电子学与计算机,2007,24(11):142-144.
[79]张迁,刘政凯,庞彦伟等.一种遥感影像的自动配准方法[J].小型微型计算机系统,2004,25(7):1129-1131.
[80]V. Etienne, L. Robert. Detecting and matching feature points[J]. Journal of Visual Communication andImage Representation,2005,16(1):38-54.
[81]K. Y. Chae, W. P. Dong, C. S. Jeong. SUSAN window based cost calculation for fast stereo matching[C].Proceedings of the International Conference on Computational Intelligence and Security,2005,3802:947-952.
[82]顾华,苏光大,杜成等.人脸关键特征点的自动定位[J].光电子·激光,2004,15(8):975-979.
[83]王荣本,余天洪,顾柏园.基于边界的车道标识线识别和跟踪方法研究[J].计算机工程,2006,32(18):195-196.
[84]H. Mauricio, M. Geovanni. Facial feature extraction based on the smallest univalue segment assimilatingnucleus (SUSAN) algorithm[C]. Proceedings of the International Conference on Picture CodingSymposiump,2004,261-266.
[85]C. Harris, M. Stephens. A combined corner and edge detector[C]. Proceedings of the4thAlvey VisionConference, Mancheste,1988:147-151.
[86]C. Schmid, R. Mohr, C. Bauckhage. Evaluation of interest point detectors[J]. International Journal ofComputer Vision,2000,37(2):151-172.
[87]王阿妮,马彩文,刘爽等.基于角点的红外与可见光图像自动配准方法[J].光子学报,2009,38(12):3328-3332.
[88]仵建宁,郭宝龙,冯宗哲.一种基于兴趣点匹配的图像拼接方法[J].计算机应用,2006,26(3):610-612.
[89]X. Wang, B. Yang. Automatic image registration based on natural characteristic points and globalhomography[C]. Proceedings of the International Conference on Computer Science and SoftwareEngineering,2008,2:1365-1370.
[90]冯宇平,戴明,张威等.一种用于图像序列拼接的角点检测算法[J].计算机科学,2009,36(12):270-271.
[91]郭辉.基于视频的车辆检测和车型识别研究[D](硕士论文)。华东交通大学硕士论文,2009.
[92]张美多,郭宝龙.车牌识别系统关键技术研究[J].计算机工程,2007,33(16):186-188.
[93]孙敏,李德玉,俞梦孙.基于Harris算子和K-means聚类的红外图像脸部特征自动定位.航天医学与医学工程,2007,20(4):285-288.
[94]陈宇波,许海柱,黄婷婷等.在人脸图像中确定嘴巴位置的方法[J].电子科技大学学报,2007,36(6):1308-1310.
[95]谭园园,李俊山,杨威.新的近距离红外目标跟踪算法[J].电光与控制,2007,14(3):8-11.
[96]刘闯,龚声蓉,崔志明等.基于角点采样的多目标跟踪方法[J].中国图像图形学报,2008,13(10):1873-1877.
[97]黄祖伟.基于双目立体视觉的目标跟踪算法研究[D].山东大学硕士论文,2007.
[98]K. Mikolajczyk, C. Schmid. Indexing based on scale invariant interest points[C]. Proceedings of the8thInternational Conference on Computer Vision, Vancouver, Canada,2001,525-531.
[99]K. Mikolajczyk, C. Schmid. An affine invariant interest point detector[C]. Proceedings of the7thEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,128-142.
[100]K. Mikolajczyk. Detection of local features invariant to affine transformations[D]. Ph.D.thesis, InstituteNational Polytechnique de Grenoble, France,2002.
[101]T. Lindeberg. Feature detection with automatic scale selection[J]. International Journal of ComputerVision,1998,30(2):79-116.
[102]李伟生,王卫星,罗代建.用Harris-Laplace特征进行遥感图像配准[J].四川大学学报(工程科学版),2011,43(4):89-94.
[103]D. Marr, E. Hildreth. Theory of edge detection[C]. Proceedings of the Royal Society of London (SeriesB), Biological Sciences,1980,207(1167):187-217.
[104]Tuytelaars T, Mikolajczyk K. Local invariant feature detectors: a survey [J]. Foundations and Trends inComputer Graphics and Vision,2007,3(3):177-280.
[105]B. M. Romeny, L. M. J. Florack, A. H. Salden, et al. Higher order differential structure of images[J].Image and Vision Computing,1994,12(6):317-325.
[106]C. Schmid, R. Mohr. Local grayvalue invariants for image retrieval [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1997,19(5):530-534.
[107]T. Lindeberg. Scale-space theory: A basic tool for analyzing structures at different scales[J]. Journal ofApplied Statistics,1994,21(2):224-270.
[108]Heymann S, Mller K, Smolic A, et.al. SIFT implementation and optimization for General-Purpose GPU[C]. In Proceedings of the15thInternational Conference in Central Europe on Computer Graphics,Visualization and Computer Vision,2007.
[109]Se S, Lowe D G, Little J. Vision-based mobile robot localization and mapping using scale-invariantfeatures [C]. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)2,2001.
[110]Se S, Ng H, Jasiobedzki P, et al. Vision based modeling and localization for planetary explorationrovers[C]. Proceedings of International Astronautical Congress,23. Viola, P., Jones, M.,2004.
[111]Kristensen F, Maclean W J. Real-time Extraction of Maximally Stable Extremal Regions on an FPGA[].International Symposium on Circuits and Systems,2007.
[112]K. Mikolajczyk, C. Schmid. Comparison of affine-invariant local detectors and descriptors[C].Proceedings of12thEuropean Signal Processing Conference, Vienna, Austria,2004.
[113]Tuytelaars T, Gool L V. Matching widely separated views based on affine invariant regions [J].International Journal of Computer Vision,2004,59(1):61-85.
[114]Harris C,Stephens M. A Combined Corner and Edge Detector [C]. Proc. Alvey Vision Conf., Univ.Manchester,1988.
[115]Canny J. A computational approach to edge detection [J]. IEEE Transactionson Pattern Analysis andMachine Intelligence,1986, PAMZ-8(6).
[116]Kadir T, Brady M. Scale, Saliency and image description [J]. International Journal of Computer Vision,2001,45(2).
[117]Kadir T, Zisserman A, Brady M. An affine invariant salient region detector [C]//Proceedings of the8thEuropean Conference on Computer Vision. New York, USA:ACM Press,2004:345-457.
[118]Enriquec, Santanmariaj and Miravetc. Segment-based registration technique for visual-infrared images[J]. Optical Engineering,2000,39(1):282-289.
[119]Taylor C. R. Line triangulation for image registration [C]. Proceedings of SPIE, Orlando, FL, USA,2002,364-373.
[120]康欣,韩崇昭,杨艺.基于结构的SAR图像配准[J].系统仿真学报,2006,18(5):1307-1310.
[121]张继贤,李国胜,曾钰.多源遥感影像高精度自动配准的方法研究[J].遥感学报,2005,9(1):73-77.
[122]H. S. Alhichri and M. Kamel. Virtual circles: a new set of features for fast image registration [J].Pattern Recognition Letters,2003,24(5):1181-1190.
[123]Lindeberg T. Detecting salient blob-Like image structures and their scales with a scale-space primalsketch: A method for focus-of-attention, International Journal of Computer Vision,1993,11(3).
[124]王永明,王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社,2010.
[125]Bay H, Tuytelaars T, Van Gool L. SURF: Speeded up robust features. In ECCV,2006.
[126] Bay H, Tuytelaars T, Van Gool L. Speeded-up robust features (SURF)[J]. Computer Vision and ImageUnderstanding,2008,110.
[127]廉蔺,李国辉,王海涛,田昊,徐树奎.基于MSER的红外与可见光图像关联特征提取算法[J].电子与信息学报,2011,33(7):1625-1631.
[128]Vincent L, Soille P. Watersheds in digital spaces: An effiecient algorithm based on immersionsimulations. TPAMI,1991.
[129]Murphy C E, Trivedi M. N-tree disjoint-set foreset for maximally stable extremal regions[C].BMVC,2006.
[130]Michael Reed Teague. Image analysis via the general theory of moments[].Optical Society of America,1980.
[131]Teague M. Image analysis via the general theory of moments [J]. Journal of the Optical Society ofAmerica,1980,70(8).
[132]PEI S C,LIN C N. Image normalization for pattern recognition[J]. Image and Vision Computing,1995,13(10):711-723.
[133]LEU J G. Shape normalization through compacting[J]. Pattern Recognition Letters,1989,10(4):243-250.
[134]K. Mikolajczyk, C. Schmid. Comparison of affine invariant local detectors and descriptors [C].Proceedings of12thEuropean Signal Processing Conference, Vienna, Austria,2004.
[135]S. Belongie, J. Malik, J. Puzicha, Shape context: A new descriptor for shape matching and objectrecognition[C]. Proceedings of the Neural Information Processing Systems,2000,831-837.
[136]W. Freeman, E. Adelson. The design and use of steerable filters [J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1991,13(9):891-906.
[137]P. Montesinos, V. Gouet, R. Deriche. Differential invariants for color images [C]. Proceedings of14thInternational Conference on Pattern Recognition, Brisbane, Australia,1998.
[138]L. Van Gool, T. Moons, D. Ungureanu. Affine/photometric invariants for planar intensity patterns [C].Proceedings of the4thEuropean Conference on Computer Vision, Cambridge, UK,1996,642-651.
[139]F. Schaffalitzky, A. Zisserman. Multi-view matching for unordered image sets [C]. Proceedings of the7thEuropean Conference on Computer Vision, Copenhagen, Denmark,2002,414-431.
[140]曾万梅,吴庆宪,姜长生.基于组合不变矩特征的空中目标识别方法[J].电光与控制,2009,6(7):21-24.
[141]付波,周建中,彭兵,等.基于仿射不变矩的轴心轨迹自动识别方法[J].华中科技大学学报(自然科学版),2007,35(3):119-122.
[142] Flusser J, SUK T. Pattern recognition by affine moment invariants[J]. Pattern Recognition,1993,26(1):167-174.
[143]Li J, M N, Allinson. A comprehensive review of current local features for computer vision[J].Neurocomputing,2008,71(10-12):1771-1787.
[144]袁修孝,钟灿.一种改进的正射影像镶嵌线性最小化最大搜索算法[J].测绘学报,2012,41(2):199-204.
[145]胡正平,王玲丽.基于L1范数凸包数据描述的多观测样本分类算法[J].电子与信息学报,2012,34(1):194-199.
[146]刘晴,唐林波,赵保军等.基于自适应多特征融合的均值迁移红外目标跟踪[J].电子与信息学报,2012,34(5):1137-1142.
[147]陈冰,赵亦工,李欣.一种新的宽基线图像匹配方法[J].西安电子科技大学学报(自然科学版),2011,38(2):116-123.
[148]董道国,薛向阳,罗航哉.多维数据索引结构回顾[J].计算机科学,2002,29(3).
[149]刘芳洁,董道国,薛向阳.度量空间中高维索引结构回顾[J].计算机科学,2003,30(7).
[150]Bentley J L. Multidimensional binary search trees used for associative searching. Communications ofthe ACM,1975,18(9).
[151]Guttman A, R-trees: A Dynamic index structure for spatial searching [C]. In Proc. ACM SIGMODInternational Conference on Management of Data,1984.
[152]Lee D T, Wibg C K. Worst-Case analysis for region and partial region searches in multidimensionalbinary search trees and balanced quad trees. Acta Informatica,1976,9(23).
[153]Liu T, Moore A, Gray A, et al. An investigation of practical approximate nearest neighbor algorithms.In NIPS,2004.
[154]杨秋菊,肖雪梅.基于改进Canny特征点的SIFT算法[J].计算机工程与设计,2011,32(7):2428-2431. Improved SIFT algorithm based on Canny feature points, Computer Engineer andDesign.
[157]刘黎宁,侯榆青,高士瑞.一种改进的综合纹理和形状特征的图像检索方法[J].小型微型计算机系统,2012,33(5):1141-1144.
[158]刘黎宁,侯榆青,高士瑞.一种改进的综合纹理和形状特征的图像检索方法[J].小型微型计算机系统,2012,33(5):1141-1144.
[159]Long Xiang, Wu Xiaoqing. Motion segmentation based on fusion of MSRF segmentation and Cannyoperator[J]. Procedia Engineering,2011,15:1637-1641.
[160]杨秋菊,肖雪梅.基于改进Canny特征点的SIFT算法[J].计算机工程与设计,2011,32(7):2428-2431.
[161]李昆仑,曹铮,曹丽萍,等.半监督聚类的若干新进展[J].模式识别与人工智能,2009,22(5):735-742.
[162]吕金建,文贡坚,王继阳,等.一种改进的基于不变描述子的图像自动配准方法[J].信号处理,2009,216-222.
[163]Chang Yulin, Zhou Zhimin, Chang Wenge,et al. A new registration method for multi-spectral SARimages[C]. IEEE International on Geoscience and Remote Sensing Symposium,2005:1704-1708.
[164]王大伟,基于特征级图像融合的目标识别技术研究[D].长春：长春光学精密机械与物理研究所,2010.
[165]甘甫平,刘圣伟,周强.德兴铜矿矿山污染高光谱遥感直接识别研究[J].地球科学,2004,(01):78-83.
[166]TIMOTHY M K, TALALAAT M R. Structural controls on neoprotero zoic mineralization in the southeastern desert, Egypt: AnIntegrated Field, LandsatTM, and SIR-C/X SAR Approach[J].JournalofAfrican Earth Sciences,2002,35(1):107-121.
[167]杨波,吴德文,赖健清.矿化信息提取定量遥感模型的建立[J].遥感学报,2005(6):717-724.