可见光与红外侦察图像融合技术研究
|
摘要
目前，在航空侦察领域，常用的成像传感器主要有可见光与红外两种异源成像传感器，其中可见光传感器成像分辨率较高，场景中的地面目标的边缘纹理等细节信息比较清晰，抗干扰能力强，但容易受到天气等自然条件的影响；红外传感器成像系统具有可穿透烟雾，主体目标比较清晰，能够昼夜工作等特点，因此在航空侦察成像中采用可见光与红外侦察图像融合的方法，可以提高对目标的探测、侦察、识别、跟踪等任务的可靠性，同时也对可见光与红外侦察图像配准与融合的稳定性、有效性及实时性提出更严格的要求。
本文首先优化了先验知识的粒子群算法，并以其为搜索策略，在搜索过程中以对齐度为判优依据，实现了可见光与红外侦察图像的快速、高精度、高可靠性配准。
然后，在piella的多尺度图像融合理论框架的基础上进行拓展，得到更加完善的图像融合框架，使可见光与红外融合图像具有更丰富的融合细节信息和更佳的视觉效果。可见光与红外传感器采集到同一场景的图像其高频细节部分存在着较大差异，针对这一特点，本文首先对已经配准的可见光和红外图像进行小波变换，再对两幅图像进行多尺度边缘提取，然后以局部模方为活性测度，局部模方的比值为匹配测度，并且利用图像的边缘特征指导融合策略，经过合成模块和多尺度逆变换得到融合图像，最后对融合后的图像进行图像增强，并对其进行客观评价。本文采用小波变换，将图像边缘检测、图像增强、图像融合有机的结合起来，最终使可见光与红外融合图像在图像融合的客观评价标准中取得比较理想的结果。
最后，依据目前美国的国家导弹防御系统正在着手研制一种能够获取弹道导弹在助推阶段精确数据和观测飞机机动性能、隐身性能的视频数据，能够装备在无人机上的，具有多传感器图像融合系统吊舱的发展趋势，建立了可见光与红外高帧频侦察图像融合系统，可以实现对飞机校飞或导弹的离梁、下滑及飞行姿态等关键阶段进行观测，并且对该系统如何来减少高帧频的图像配准与融合在算法上的耗时，并能够满足高实时性要求（100帧）进行了研究。首先采用可见光与红外共光路方式，保证可见光与红外同视轴，采用光学标校配准法来进行图像配准，可以大幅减少可见光与红外侦察图像配准的耗时，并提出能够提高配准精度的处理方法，对光学标校配准法特点进行总结。然后比较分析了在时域内能达到实时性的几种图像融合方法及效果。最后对大小不同异源图像的融合后图像边缘痕迹消除进行了探讨，采用窗函数法既可以保留融合的效果又可以消除融合的边缘痕迹。
Now, there are two commonly used imaging sensors in aerial reconnaissance.The two heterogeneous source sensors are respectively visible and infrared sensors.The imaging resolution of visible sensor is superior and the detail of the edges andtexture of objects are clear. Also, it has strong anti interference capability. It’s a pitythat it is easily influenced by natural conditions, for example weather. Imagingsystem of infrared sensor can penetrate through surface features such as smog andforest. Its subject goal is comparatively clear. It is more important that it can workperfectly at day and night. So in the processing of aerial reconnaissance imaging, thefusion of visible and infrared images can improve reliability of objects detection,reconnaissance, recognition, tracking and put forward more strict requirements forstability, validity and real-time of the registration and fusion.
Firstly, optimized particle swarm optimization based on prior knowledge assearch strategy and alignment metric as basis for judgment priority, the paper bringsforward fast, high precise, high reliable heterogeneous source image registration ofvisible and infrared images.
Then, based on Piella's theoretical framework of multi-scale image fusion, thispaper constructs a more comprehensive fusion framework that fusion of visual andinfrared images has richer fusion detail and better visual effects. Images of the samescene, obtained from visible and infrared sensors respectively, have a big difference in the high-frequency detail. For this characteristic, first take Wavelet Transform ofinfrared and visible light registration images, and take edge extraction of two imagesunder the multi-scale. Then take local module square as activity measure, use theimage edge feature to guide fusion decision, and get fused images throughcombination module and multi-scale inversion. Finally, take image Enhancement tothe fused image and take objective assessment of the image quality. Under thewavelet domain, this paper combines image edge detection with image enhancementand image fusion and gets very perfect results of fused image of visible and infraredimages under the objective assessment criteria without standard reference image.
Finally, in order to observe every key stages which include flight correction ofairplane or launch and flight attitude of missile, the paper establishes airborne highframe rate heterogeneous source fusion system and have a research on the systemadopting common optical path arrangement to decrease algorithm consumed time ofhigh frame rate heterogeneous source image registration and fusion and satisfyreal-time request (100frames). In optical design, common path of visible light andinfrared is adopted so as to make their visual axis same. We make a summary of thecharacteristic of optical alignment calibration registration, use it for calibratingimage registration and propose a method of improving calibration precision. Then,we compare with some image fusion method that satisfy real-time in time domainand analyze their results. Finally, we have a research on trace elimination of edges ofimage which is obtained by fusion of two heterogeneous source images withdifferent size. The usage of window function method not only preserves fusioneffects and also eliminates trace of fusion edges.
本文首先优化了先验知识的粒子群算法，并以其为搜索策略，在搜索过程中以对齐度为判优依据，实现了可见光与红外侦察图像的快速、高精度、高可靠性配准。
然后，在piella的多尺度图像融合理论框架的基础上进行拓展，得到更加完善的图像融合框架，使可见光与红外融合图像具有更丰富的融合细节信息和更佳的视觉效果。可见光与红外传感器采集到同一场景的图像其高频细节部分存在着较大差异，针对这一特点，本文首先对已经配准的可见光和红外图像进行小波变换，再对两幅图像进行多尺度边缘提取，然后以局部模方为活性测度，局部模方的比值为匹配测度，并且利用图像的边缘特征指导融合策略，经过合成模块和多尺度逆变换得到融合图像，最后对融合后的图像进行图像增强，并对其进行客观评价。本文采用小波变换，将图像边缘检测、图像增强、图像融合有机的结合起来，最终使可见光与红外融合图像在图像融合的客观评价标准中取得比较理想的结果。
最后，依据目前美国的国家导弹防御系统正在着手研制一种能够获取弹道导弹在助推阶段精确数据和观测飞机机动性能、隐身性能的视频数据，能够装备在无人机上的，具有多传感器图像融合系统吊舱的发展趋势，建立了可见光与红外高帧频侦察图像融合系统，可以实现对飞机校飞或导弹的离梁、下滑及飞行姿态等关键阶段进行观测，并且对该系统如何来减少高帧频的图像配准与融合在算法上的耗时，并能够满足高实时性要求（100帧）进行了研究。首先采用可见光与红外共光路方式，保证可见光与红外同视轴，采用光学标校配准法来进行图像配准，可以大幅减少可见光与红外侦察图像配准的耗时，并提出能够提高配准精度的处理方法，对光学标校配准法特点进行总结。然后比较分析了在时域内能达到实时性的几种图像融合方法及效果。最后对大小不同异源图像的融合后图像边缘痕迹消除进行了探讨，采用窗函数法既可以保留融合的效果又可以消除融合的边缘痕迹。
Now, there are two commonly used imaging sensors in aerial reconnaissance.The two heterogeneous source sensors are respectively visible and infrared sensors.The imaging resolution of visible sensor is superior and the detail of the edges andtexture of objects are clear. Also, it has strong anti interference capability. It’s a pitythat it is easily influenced by natural conditions, for example weather. Imagingsystem of infrared sensor can penetrate through surface features such as smog andforest. Its subject goal is comparatively clear. It is more important that it can workperfectly at day and night. So in the processing of aerial reconnaissance imaging, thefusion of visible and infrared images can improve reliability of objects detection,reconnaissance, recognition, tracking and put forward more strict requirements forstability, validity and real-time of the registration and fusion.
Firstly, optimized particle swarm optimization based on prior knowledge assearch strategy and alignment metric as basis for judgment priority, the paper bringsforward fast, high precise, high reliable heterogeneous source image registration ofvisible and infrared images.
Then, based on Piella's theoretical framework of multi-scale image fusion, thispaper constructs a more comprehensive fusion framework that fusion of visual andinfrared images has richer fusion detail and better visual effects. Images of the samescene, obtained from visible and infrared sensors respectively, have a big difference in the high-frequency detail. For this characteristic, first take Wavelet Transform ofinfrared and visible light registration images, and take edge extraction of two imagesunder the multi-scale. Then take local module square as activity measure, use theimage edge feature to guide fusion decision, and get fused images throughcombination module and multi-scale inversion. Finally, take image Enhancement tothe fused image and take objective assessment of the image quality. Under thewavelet domain, this paper combines image edge detection with image enhancementand image fusion and gets very perfect results of fused image of visible and infraredimages under the objective assessment criteria without standard reference image.
Finally, in order to observe every key stages which include flight correction ofairplane or launch and flight attitude of missile, the paper establishes airborne highframe rate heterogeneous source fusion system and have a research on the systemadopting common optical path arrangement to decrease algorithm consumed time ofhigh frame rate heterogeneous source image registration and fusion and satisfyreal-time request (100frames). In optical design, common path of visible light andinfrared is adopted so as to make their visual axis same. We make a summary of thecharacteristic of optical alignment calibration registration, use it for calibratingimage registration and propose a method of improving calibration precision. Then,we compare with some image fusion method that satisfy real-time in time domainand analyze their results. Finally, we have a research on trace elimination of edges ofimage which is obtained by fusion of two heterogeneous source images withdifferent size. The usage of window function method not only preserves fusioneffects and also eliminates trace of fusion edges.
引文
[1]何友，王国宏，陆大金，等．多传感器信息融合及应用[M]．北京：电子工业出版社，2007．
[2]阮秋奇，阮宇智，等译．数字图像处理（第二版）[M]．北京：电子工业出版社，2004．
[3]郑南宁．计算机视觉与模式识别[M]．北京：国防工业出版社，1998．
[4]康耀红．数据融合理论与应用[M]．西安：西安电子科技大学出版社，1997．
[5]文成林，周东华．多尺度估计理论及其应用[M]．北京：清华大学出版社，2002．
[6]李光鑫．红外和可见光图像融合技术的研究[D]：[博士学位论文]．长春：吉林大学，2008．
[7]何友，王国宏，陆大紟．多传感器数据融合模型综述[J]．清华大学学报，1996，36(9)：14-20．
[8]Basseville M, Benveniste A, Willsky A. S. Multiscale autoregressive process, PartsI: Schur-Levinson Parametrization [J]. IEEE Trans. on Signal Processing,1992,40(8):1915-1934.
[9]徐毓．雷达网数据融合问题研究[D]：[博士学位论文]．北京：清华大学，2003．
[10]Bertero M, Poggio T. A. III-posed problems in early vision [J]. Proceedings of theIEEE,1998,76(8):869-889.
[11]Cheng Y. Mean Shift, mode seeking, and clustering [J]. IEEE Trans. PatternAnalysis and Machine Intelligence,1995,17(8):790-799.
[12]Comaniciu D, Meer P. Mean Shift analysis and applications [C]. Proc, Int1Conf,Computer Vision,1999:1197-1203.
[13]Rucklidge W J. Efficiently Locating Objects Using Hausdorff Distance [J].International Journal of Computer Vision,1997,24(3):251-270.
[14]Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for LocalImage Descriptors [C]. Computer Vision and Pattern Recognition,2004:511-517.
[15]Mikolajczyk K, Schmid C. Scale and Affine invariant interest point detectors [J].Int1Computer Vision,2004,60(1):63-86.
[16]管云峰，胡勇，李介谷．基于Fourier-Mellin变换的对称相匹配滤波算法[J]．红外与毫米波学报，1999,18(6)：465-471．
[17]强赞霞，彭加雄，王洪群．基于傅里叶变换的遥感图像配准算法[J]．红外与激光工程，2004，33(4)：385-387．
[18]Philippe Thevenaz, Urs E. Ruttimann, Michael Unser. A pyramid approach tosubpixel registration based on intensity [C]. IEEE Trans. on Image Processing,1998,7(1),27-41.
[19]Josien P. W. Pluim, J. B. Antoine, Max A. Viergever. Image registration bymaximization of combined mutual information and gradient information [C]. IEEETrans. on Medical Imaging,2000,19(8):809-814.
[20]Philippe Thevenaz, Michael Unse. Optimization of mutual information formultiresolution image registration [C]. IEEE Trans. on Image Processing,2000,9(12):2083-2098.
[21]L. G. Brown. A survey of image registration techniques [J]. ACM ComputingSurveys,1992,24(4):325-376.
[22]刘斌，彭嘉雄．图像配准的小波分解方法[J]．计算机辅助设计与图形学学报，2003，15(9)：1070-1073．
[23]Sadjadi F. A model-based technique for recognizing targets by using millimeterwave radar signature [J]. International Journal of Infrared and Millimeter Waves,1987,10(3):337-342.
[24]Chein-I Chang, Shao-Shan Chiang. Anomaly detection and classification forhyperspectral imagery [C]. IEEE Transactions on Geoscience,2002,40(6):1314-1325.
[25]Zelnio E G. Importance of sensor models to model-based vision application [J].SPIE Institute Series,1990(7):112-121.
[26]Verly J G. A model-based system for automatic target recognition [J]. SPIE,1991(1471):266-282.
[27]Tu T M, Su S C, Shyu H C, et al. A New Look at HIS Like Image Fusion Methods[J]. Information Fusion,2001,(2):177-186．
[28]Rockinger O. Image Sequence Fusion Using a Shift-Invariant Wavelet Transform[J]. In: Proc of Int1Conf on Image Processing,1997,(3):288-291.
[29]Rockinger O. Pixel-Level Fusion of Image Sequences Using Wavelet Frames [J].In: Proceedings in Image Fusion and Shape Varicability Techniques, Leeds, UK,1996,149-154.
[30]Rockinger O, Fechner T. Pixel-Level Image Fusion: The Case of ImageSequences [J]. In: Proceedings of SPIE, Signal Processing, Sensor Fusion, and TargetRecognition Ⅶ, Orlando, Florido,1998,3374:378-388.
[31]余小游，卢焕章，常青．多传感器目标识别系统中的数据融合方法与系统结构的研究[J]．国防科技参考，1998，19(1)：11-16．
[32]张莉，周伟达，李成焦．用于一维图像识别的支撑向量机方法[J]．红外与毫米波学报，2002，21(2)：119-123．
[33]夏明革，何友，唐小明．多传感器图像融合综述[J]．电光与控制，2002，4(9)：1-7．
[34]陈虎虎，钟方平，许学忠，等．基于支持向量机的低空飞行目标识别[J]．系统工程与电子技术，2005，27(l)：46-48．
[35]党宏社，韩崇昭，段战胜．一种基于模糊量相似度测量的模糊数据关联方法[J]．武汉理工大学学报(交通科学与工程版)，2003，27(7)：11—14．
[36]邰滢滢，陈小惠．基于模糊聚类的数据关联融合算法[J]．华东船舶工业学院学报(自然科学版)，2003，17(6)：58-62．
[37]王俊林，张剑云．应用D—S证据理论进行多传感器雷达体制识别[J]．现代防御技术，2006，34(6)：89-92．
[38]Blum R S. On multisensor image fusion performance limits from and estimationtheory perspective [J]. Information Fusion,2006,7(3):250-263.
[39]Smith M I, Heather J P. Review of Image Fusion Technology in2005[C].Proceedings of SPIE,2005,5782:29-45.
[40]刘哲，郝重阳，刘晓翔，等．多光谱图像与全色图像的像素级融合研究[J]．数据采集与处理，2003，18(3)：296-301．
[41]唐健，朱继红，孙增圻．基于智能优化策略的图像自动配准方法[J]．清华大学学报(自然科学版)，2004，44(9)：1252-1255．
[42]Roche A, Pennec X, Malandain G, et al. Rigid registration of3-Dultrasound withMR images: a new approach combining intensity and gradient information [J]. IEEETransaction on Medical Imaging,2001,20(10):1038-1049.
[43]Pluim J. P. W, Maintz J. B. N, Viergver M. A. Image registration by maximizationof combined mutual information and gradient information [J]. IEEE Transactions onMedical Imaging,2000,19(8):809-814.
[44]Hsieh Jun wei. Image registration using a new edge based approach [J]. ComputerVision and Image understanding,1997,67(2):112-130.
[45]李震，范湘涛，施建成．基于分窗口相关的遥感图象配准方法[J]．中国图象图形学报，2001，6(2)：129-132．
[46]Xia Y S, Leung H, Bosse E. Neural data fusion algorithms based on a linearlyconstrained least square method [J]. IEEE Transactions on Neural Networks,2002,13(2):320-329.
[47]Chibani Y, Houacine A. Redundant versus orthogonal wavelet decomposition formultisensor image fusion [J]. Pattern Recognition,2003,36(4):879-887.
[48]Santos M, Pajares G, Portela M, et al. A new wavelets image fusion strategy [C].Proceedings of Parttern Recognition and Image Analysis in Lecture Notes inComputer Science. Mallorca, Spain,2003,2652:919-926.
[49]I.Koren, A.Laine, F.Taylor. Image fusion using steerable dyadic wavelettransforms [J]. The International Conference on Image Processing,1995,3:232-235.
[50]V.S.Petrovic, C.S.Xydeas. Cross-band pixel selection in multiresolution imagefusion [J]. Proc.SPIE,1999,3719:319-326.
[51]O.Rockinger. Image sequence fusion using a shift-invariant wavelet transforms [J].The International Conference on Image Processing,1997,3:288-291.
[52]付华，李博，薛永存．基于D-S证据理论的数据融合井下监测方法分析[J]．传感器与微系统，2007，26(1)：27-29．
[53]闫志鹏，唐祯敏．基于Bayes估计和加权数据融合算法的交通量检测方法[J]．郑州轻工业学院学报(自然科学版)，2006，21(4)：44-46．
[54]刘严岩，吴秀清．基于广义相对信息熵的数据融合系统性能评估[J]．系统仿真学报，2006，28(5)：1283-1285．
[55]吴琼玉，蔡宣平，刘云辉．一种基于多分类器融合的双色红外成像目标识别方法[J]．信号处理，2008，28(2)：62-66．
[56]卢大威，马君国，赵宏钟，等．基于轮廓特征的空间目标识别算法[J]．火力与指挥控制，2007，12(5)：53-56．
[57]蒋晓瑜，高稚允．小波变换在特征级多重图像融合与目标分类中的应用[J]．红外技术，2004，8(2)：1-4．
[58]秦其明，陆荣建．分形与神经网络方法在卫星数字图像分类中的应用[J]．北京大学学报(自然科学版)，2000(36)：858-864．
[59]苏冬雪，吴小俊．基于多特征模糊聚类的图像融合方法[J]．计算机辅助设计与图形学学报，2006，15(6)：838-843．
[60]张池平．多传感器信息融合方法及其在空间目标识别中的应用[D]．[博士学位论文]．哈尔滨：哈尔滨工业大学，2006．
[61]F.R. Castella. Multisensor, multisite tracking filter. IEEE Proc, Radar, Sonar andNavigation,1994,141(2):75-83.
[62]L. Y. Bao. Centralized multisensor fusion algorithm for tracking application [J].Control Engineering Practice,1994,2(5):875-998.
[63]胡文龙等．多传感器多目标跟踪中的概率数据互联[J]．电子学报，1996，24(9)：30-35．
[64]Zhang Z, Blum R S. A Hybrid Image Registration Technique for A DigitalCamera Image Fusion Application [J]. Information Fusion,2001,(2):135-149.
[65]Achalakul T, Lee J, Taylor S. Resilient Image Fusion. In: Proceedings of theInternational Conference on Parallel Processing Workshops, Toronto, Canada,2000,8:291-296．
[66]Tseng D C, Chen Y L, Liu M S. Wavelet-Based Multispectral Image Fusion [J]. In:Proc of IEEE Int1Conf on Geo science and Remote Sensing (IGARSS),2001,(4):1956-1958.
[67]Tu T M, Su S C, Shyu H C, ed al. A New Look at HIS Like Image FusionMethods [J]. Information Fusion,2001,(2):177-186．
[68]Llinas. J, Hall. D. L. An Introduetion to Multisensor Data Fusion [J]. Proc.IEEE,1998,85(1):537-540.
[69]Pohl C, Genderen J L Van, Multisensor image fusion in remote sensing: Concepts,methods and applications [J]. Int J Remote Sensing,1998,19(5):823-854.
[70]Costantiti M, Farina A, ZirilliF. The fusion of different resolution SAR image [C].In: Proeeeding of the IEEE.1997,85(1):139-146.
[71]何国金，李克鲁，胡德永，等．多卫星遥感数据的信息融合：理论、方法和实践[J]．中国图像图形学报．1999，4A(9)：744-750．
[72]Chavez P S, Sides S C, Anderson J A. Comparison of three different methods tomerge multi-resolution and multi-spectral data: Landsat TM and SPOT Panehromatic[J]. PE&RS.1991,57(3):295-303.
[73]G.Simone, A.Farina. Image Fusion Techniques for Remote Sensing Application[J]. Information Fusion,2003,(3):3-15.
[74]李伟．像素级图像融合算法及应用研究[D]：［博士学位论文］．广州：华南理工大学，2006．
[75]A.Gholipour, N.Kehtarnavaz, R.Briggs, et al. Brain functional localization: Asurvey of image registration techniques [J]. IEEE Transactions on Medical Imaging,2007,26(4):427-451.
[76]B.Zitova, J.Flusser. Image registration methods: A survey [J]. Image and VisionComputing,2003,21:977-1000.
[77]J.Pluim, J.Maintz, M.Viergever. Mutual-information-based registration of medicalimages: A Survey [J]. IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
[78]H.Lester, S.R.Arridge. A survey of hierarchical non-linear medical imageregistration [J]. Pattern Recognition,1999,32:129-149.
[79]L.G.Brown. A survey of image registration techniques [J]. ACM ComputingSurveys,1992,24(4):325-376.
[80]J.P.Heather, M.I.Smith. Multimodal image registration with applications to imagefusion [J]. The8th International Conference of Information Fusion,2005,1:372-379.
[81]毛士艺，赵巍．多传感器图像融合技术综述[J]．北京航空航天大学学报，2002，28(5)：512-518．
[82] Newman E A, Hartline P H. The infrared vision of snakes [J]. ScientificAmerican,1982,46(3):116-127.
[83]Fechner T, Godlewski G. Optimal fusion of TV and infrared images usingartificial neural networks [C]. Proc of SPIE.Orlando, FL:[s.n.],1995:919-925.
[84]Broussard R P, Roges S K, Oxley M E, et al. Physiologically motivated imagefusion for object detection using a pulse coupled neural network [J]. IEEE Trans onNeural Networks,1999,10(3):554-563.
[85]Toet A. Hierarchical image fusion [J]. Machine Vision and Applications,1990,3(1):1-11.
[86]王洁，韩崇昭，李晓榕．异步多传感器数据融合[J]．控制与决策，2001，16(6)：877-881．
[87]姜万录，李冲祥，刘继刚．多传感器数据融合技术及展望[J]．机床与液压，2003，03(6)：16-18．
[88]曲晓慧，安钢．数据融合方法综述及展望[J]．舰船电子工程，2003(02)：33-35．
[89]夏明革，何友，唐小明，等．图像融合的发展现状与展望[J]．船舶电子工程，2002，(6)：2-12．
[90]杨杰，陆正刚，黄欣．基于多传感器数据融合的目标识别和跟踪[J]．上海交通大学学报，1999，33(9)：1107-1110．
[91]刘严岩，吴秀清．基于广义相对信息熵的数据融合系统性能评估[J]．系统仿真学报，2006，28(5)：1283-1285．
[92]刘同明．数据融合技术及其应用[M]．北京：国防工业出版社，2000．
[93]孟继成，杨万麟．基于核函数的雷达一维距离像目标识别[J]．电子与信息学报，2005，27(3)：462-466．
[94]O.Rockinger, T.Fechner. Pixel-level image fusion: The case of image sequences[J]. Proc.SPIE,1998,374:378-388.
[95]P.J.Burt, E.H.Adelson. Merging images through pattern decomposition.Applications of Digital Image Processing VIII [J]. Proc.SPIE,1985,575:173-181.
[96]P.J.Burt, R.J.Kolczynski. Enhanced image capture through fusion [J]. The4thInternational Conference on Computer Vision,1993:173-182.
[97]A.Toet. Image fusion by a ration of low-pass pyramid [J]. Pattern RecognitionLetters,1989,9(4):245-253.
[98]A.Toet, J.J.van Ruyven, J.M.Valeton. Merging thermal and visual images by acontrast pyramid [J]. Optical Engineering,1989,28(7):789-792.
[99]A.Toet. Multi-scale contrast enhancement with applications to image fusion [J].Optical Engineering,1992,31(5):1026-1031.
[100]G.K.Matsopoulos, S.Marshall. Application of morphological pyramids: Fusionof MR and CT phantoms [J].Journal of Visual Communication and ImageRepresentation,1995,6(2):196-207.
[101]C.Lejeune. Wavelet transform for infrared application [J]. Proc.SPIE,1995,2552:313-324.
[102]刘贵喜，杨万海．一种像素级多算子红外与可见光图像融合方法[J]．红外与毫米学报，2001，20(3)：207-210．
[103]M.K.Uner, L.C.Ramac, P.K.Varshney, et al. Concealed weapon detection: Animage fusion approach [J]. Proc.SPIE,1997,2942:123-132.
[104]H.Li, B.S.Manjunath, S.K.Mitra. Multisensor image fusion using the wavelettransforms [J]. Graphical Models and Image Processing,1995,57(3):235-245.
[105]高海波．多源传感器最优配准技术和算法研究[D]：[硕士学位论文]．西安：西安电子科技大学，2009．
[106]L. Brown. A survey of image registration techniques [J]. ACM, ComputingSurveys,1992,24(4):325-376.
[107]P. A. Van den Elsen, E. J. D. Pol, M. A. Viergever. Medical image matching-Areview with classication [C]. IEEE Eng. Med. Biol. Mag.,1993,12:26-39.
[108]P. A. Viola, W. M. Wells III. Alignment by maximization of mutual information.[J]. International Journal of Computer Vision,1997,24(2):137-154.
[109]A.Goshtasby, G. C. Stockman, C. V. Page. A region-based approach to digitalimage registration with subpixel accuracy [C]. IEEE Trans. on Geoscience andRemote Sensing,1986, GE-24(3):390-399.
[110]A. D. Ventura, A. Rampini, R. Schettini. Image registration by recognition ofcorresponding structures [C]. IEEE Trans. on Geoscience and Remote Sensing,1990,28(3):305-314.
[111]B. S. Reddy, B. N. Chatterji. An FFT-based technique for translation, rotation,and scale-invariant image registration [C]. IEEE Trans. on Image Processing,1996,5(8):1266-1271.
[112]田阿灵．基于SIFT的红外与可见光图像配准方法研究[D]：[硕士学位论文]．北京：华北电力大学，2008．
[113]张浩．多信息融合图像边缘特征提取及图像配准研究与应用[D]：[博士学位论文]．杭州：浙江大学，2008．
[114]J. Ton and A. K. Jain. Registering Landsat images by point matching [J]. IEEETrans. on Geoscience and Remote Sensing,1989,27:642-651.
[115]J. Flusser, T. Suk. A moment-based approach to registration of images withaffine geometric distortion [J]. IEEE Trans. on Geoscience and Remote Sensing,1994,32(2):382-387.
[116]H. Li, B. S. Manjunath, S. K. Mitra. A contour-based approach to multisensorimage registration [J]. IEEE Trans. on Image Processing,1995,4(3):320-334.
[117]Mark Holden, Derek L. G. Hill, Erika R. E. Denton. Voxel similarity measuresfor3-D serial MR bain image registration [J]. IEEE Transaction on Medical Image,2000,19(2):94-102.
[118]Kwon O. K, Sim D. G, Park R. H. Robust Hausdorff Distance MatchingAlgorithms Using Pyramidal structures [J]. Pattern Recognition,2001,34(7):2005-2013.
[119]Harold S Stone, Robert Wolpov. Blind cross-spectral image registration usingprefiltering and Fourier based translation detection [J]. IEEE Transaction onGeoscience and Remote Sensing,2002,40(3):637-650.
[120]Harold S Stone, Michael T Orchard, Ee Chien Chang, et al. A fast direct Fourierbased algorithm for subpixel registration of images [J]. IEEE Transactions onGeoscience and Remote Sensing,2001,39(10):2235-2243.
[121]Wen-Hao Wang, Yung-Chang Chen. Image registration by control points pairingusing the invariant properties of line segments [J]. Pattern recognition letters,1997,18(3):269-274.
[122]Hui Li, B. S. Manjunath, S. K. Mitra. A contour-based approach to multisensorimage registration [J]. IEEE Trans. on Image Processing,1995,4(3):320-334.
[123]Xiaolong Dai and Siamak Khorram. A feature-Based image registrationalgorithm using improved chain-code representation combined with invariantmoments [J]. IEEE Trans. on Geoscience and Remote Sensing,1999,37(5):2351-2362.
[124]陈煜，田裕鹏．图像融合中的图像配准方法研究[J]．激光与红外，2004，34(1)：34-36．
[125]王东峰．多模态和大型图像配准技术研究[D]：[博士学位论文]．北京：中国科学院，2002．
[126]杨凤芹．基于粒子群的优化方法研究[D]：[博士学位论文]．长春：吉林大学，2009．
[127]袁亚湘，孙文瑜．最优化理论与方法[M]．北京：科学出版社，1997．
[128]施光燕，钱伟懿，庞丽萍．最优化方法（第二版）[M]．北京：高等教育出版社，2007．
[129]闫允一．粒子群优化及其在图像处理中的应用研究[D]：[博士学位论文]．西安：西安电子科技大学，2008．
[130]P. A. Viola, W. M. Wells III. Alignment by maximization of mutual information[J]. International Journal of Computer Vision,1997,24(2):137-154.
[131]Van de Bergh F, A P Engelbrecht. A study of particle swarm optimizationtrajectories [J]. Information Sciences,2006,17(6):937-971.
[132]Kennedy J, Eberhart R. C. Particle Swarm Optimization [C]. Neural Networks,1995, Proceeding. IEEE International Conference. Piscataway, NJ, USA,1995:1942-1948.
[133]彭喜元，彭宇，戴毓丰．群智能理论及应用[J]．电子学报，2003，31（12A）：1982-1988．
[134]Sidhartha Panda, Narayana Prasad Padhy. Optimal location and controller designof STATCOM for power system stability improvement using PSO [J]. Journal of theFranklin Institute,2008,345(2):166-181.
[135]Ali Allahverdi, Fawaz S, Al-Anzi. A PSO and a Tabu search heuristics for theassembly scheduling problem of the two-stage distributed database application [J].Computers&Operations Research,2006,33(4):1056-1080.
[136]Li-Yeh Chuang, Hsueh-Wei Chang, Chung-Jui Tu, et al. Improved binary PSOfor feature selection using gene expression data [J]. Computational Biology andChemistry,2008,32(1):29-38.
[137]B. Samanta, C. Nataraj. Use of particle swarm optimization for machinery faultdetection [J]. Engineering Applications of Artificial Intelligence,2009,22(2):308-316.
[138]Leonard E. Baum and Ted Petrie. Statistical Inference for Probabilistic Functionsof Finite State Markov Chains[J].The Annals of Mathematical Statistics,1966,37(6):1554-1563.
[139]Young-Sun Yun, Yung-Hwan Oh. A segmental-feature HMM for continuousspeech recognition based on a parametric trajectory model [J]. SpeechCommunication,2002,38(1-2):115-130.
[140]Alexander Seward. A fast HMM match algorithm for very large vocabularyspeech recognition [J]. Speech Communication,2004,42(2):191-206.
[141]Suphattharachai Chomphan, Takao Kobayashi. Tone correctness improvement inspeaker dependent HMM-based Thai speech synthesis [J]. Speech Communication,2008,50(5):392-404.
[142]Randy Gomez, Tomoki Toda, Hiroshi Saruwatari, et al. Techniques in rapidunsupervised speaker adaptation based on HMM-Sufficient Statistics [J]. SpeechCommunication Speech Communication,2009,51(1):42-57.
[143]Longbiao Wang, Norihide Kitaoka, Seiichi Nakagawa. Robust distant speakerrecognition based on position-dependent CMN by combining speaker-specific GMMwith speaker-adapted HMM [J]. Speech Communication,2007,49(6):501-513.
[144]Tianming Hu, Liyanage C. De Silva, Kuntal Sengupta. A hybrid approach of NNand HMM for facial emotion classification [J].Pattern Recognition Letters,2002,23(11):1303-1310.
[145]Hongyu Liu, Jeannette Janssen, Evangelos Milios. Using HMM to learn userbrowsing patterns for focused Web crawling [J]. Data&Knowledge Engineering,2006,59(2):270-291.
[146]Qi Liu, Yi-Sheng Zhu, Bao-Hua Wang, et al. A HMM-based method to predictthe transmembrane regions of β-barrel membrane proteins [J]. Computational Biologyand Chemistry,2003,27(1):69-76.
[147]高尚，杨静宇．群智能算法及其应用[M]．北京：中国水利水电出版社，2006．
[148]陈华，叶东，陈刚，等．遗传算法的数字图像相关搜索法[J]．光学精密工程，2007，15(10)：1633-1637．
[149]Mingchao Sun, Bao Zhang, Jinghong Liu, et.al. The Registration of AerialInfrared and Visible Images[C].2010International Conference on Educational andInformation Technology (ICEIT2010),2010:428-439.
[150]杨煊，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法[J]．电子学报，2001，29(6)：846-848．
[151]Swain M I, Ballard D H. Color indexing [J]. International Journal of ComputerVision,1991,7(1):11-32．
[152]Rockinger O. Image Sequence Fusion Using a Shift-Invariant WaveletTransform [J]. In: Proc of Int1Conf on Image Processing,1997,(3):288-291．
[153]Rockinger O. Pixel-Level Fusion of Image Sequences Using Wavelet Frames [J].In: Proceedings in Image Fusion and Shape Varicability Techniques, Leeds, UK,1996，149-154．
[154]Rockinger O, Fechner T. Pixel-Level Image Fusion: The Case of ImageSequences [J]. In: Proceedings of SPIE, Signal Processing, Sensor Fusion, and TargetRecognition VII, Orlando, Florido,1998,3374:378-388.
[155]Scheunders P. Multiscale Edge Representation Applied to Image Fusion [J]. In:Proceedings of SPIE, Wavelet Application in Signal and Image Processing VII,2000,4119:894-901.
[156]敬忠良，肖刚，李振华．图像融合理论与应用[M]．北京：高等教育出版社，2007．
[157]Piella G. Adaptive wavelets and their applications to image fusion andcompression [D]:[Doctor Degree]. Amsterdam, Netherlands：Korteweg-de Vriesinstitute for mathematics, University of Amsterdam,2003.
[158]Piella G. A general framework for multiresolution image fusion: From pixels toregions [J]. Elsevier Science, Information fusion,2003,4(4):259-280.
[159]秦前清，杨宗凯．实用小波分析[M]．西安：西安电子科技出版社，1994．
[160]催锦泰．小波分析导论[M]．西安：西安交通大学出版社，1997．
[161]马维祯，段瑞祥．小波变换理论及在信号处理中的应用[J]．数据采集与处理，1994，9(2)：121一129．
[162]刘汉，莫玉龙．基于二维自适应小波基小波变换的规则纹理缺陷检测[J]．中国图象图形学报，1999，(4)：349一352．
[163]程正兴．小波分析算法及应用[M]．西安：西安交通大学出版社，1998．
[164]Q. T. Jinag. On the design of multifilter bank and orthonorml multi-waveletbases [J]. IEEE Trans on Signal Processing,1998,46(12):3292-3302.
[165]V. Streal, P. H. Helle. The Application of multiwavelet filter banks to imageproeessing [J]. IEEE Trans on image Porcessing,1999,8(4):548-563.
[166]X. G. Xia, D. P. Hadrin. Design of prefilter for discrete multiwavelet transforms[J]. IEEE Tarns on Singal Processing,1996,29(2):481-510.
[167]蒲恬，倪国强．基于对比度的多分辨图像融合[J]．电子学报，2000，28(12)：116-181．
[168]Burt P J, Adelson E H. The Laplacian Pyamid a compact image code [J]. IEEETrans on Commun,1998,31:532-540.
[169]李树涛，王耀南．基于树状小波分解的多传感器图像融合[J]．红外与毫米波学报，2001，20(3)：119-202．
[170]蒋晓瑜，高稚允，周立伟．基于小波变换的多分辨图像融合[J]．北京理工大学学报，1997，7(4)：458-461．
[171]张贤达，保铮．非平稳信号分析与处理[M]．北京：国防工业出版社，1998．
[172]Maes F, Collignon A. Multimodality image registration by maximization ofmutual information [J]. IEEE Trans on Medical imageing,1997,16(2):187-199.
[173]陈勇，皮德富，周士源．基于小波变换的红外图像融合技术研究[J]．红外与激光工程，2001，30(1)：15-17．
[174]Pluim P W, Maintz J. B. Mutual-information based registration of medicalimages: A suvery [J]. IEEE Trans on Medical Imageing,2003,22(8):986-1003.
[175]杨恒，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法[J]．电子学报，2001，29(6)：846-848．
[176]Srinivas B, Redd. An FFT based technique of Translation Rotation and ScaleInvariant Image Registration [J]. IEEE Trans on Image Processing,1996,5(8):1266-1270.
[177]Amar Mitiche, Aggarwal J. K. Cnotour registration by shape specific points forshape matching [J]. Computer Vision, Graphics, and Image Processing,1983,22(3):396-408.
[178]王丽荣．基于小波变换的目标检测方法研究[D]：[博士学位论文]．长春：吉林大学，2006．
[179]王宏，敬忠良，李建勋．多分辨率图像融合的研究与进展[J]．控制理论与应用，2004，21(1)：145-151．
[180]Goodman TNT. Wavelet of multiplicity [J]. Tarns, Amer Math Soc,1994,38(2):639-652.
[181]Geronimo J, Hardin D. Fractal functions and wavelet expansions based onseveral functions [J]. J Approx Theory,1994,78:373-401.
[182]蒋晓瑜，高雅允，周立伟．小波变换在多光谱图像融合中的应用[J]．电子学报，1997，25(8)：105-108．
[183]Mallat S. A theory for multiresolution signal decomposition: The waveletrepresentation [J]. IEEE Trans on PAMI,1989,11(7):674-693.
[184]David G. V. A wavelet-based analysis of fractal image compression [J]. IEEETrans. On Image Prorcessing,1998,7(2):140-153.
[185]李瑛．多元小波的构造及其应用[D]：[博士学位论文]．长春：吉林大学，2004．
[186]刘贵喜，杨万海．基于小波分解的图像融合方法及性能评价[J]．自动化学报，2002，28(6)：927-934．
[187]孙明超，张崇，刘晶红.多尺度图像增强可见光与红外图像融合[J].吉林大学学报（工学版），2012，42(3)：738-742.
[188]孙明超，张葆，刘晶红.高帧频图像融合光学测量吊舱的设计[J].光学精密工程.（已录用，EI收录）
[189]曲锋，刘英，王建，等．红外双波段图像实时融合系统[J]．光学精密工程，2010，18(7)：1684-1690．
[190]Dov Freiman. Dichroic Beamsplitter for a Dual-wavelength Canera in aLong-range Airborne Reconnaissance System [J]. Proc. Of SPIE2005,5783:827-834.
[191]董科研，潘玉龙，王学进，等．谐衍射红外双波段双焦光学系统设计[J]．光学精密工程，2008，16(5)：764-770．
[192]郝松傲，秦军．热红外图像与可见光图像的配准与融合[J]．四川测绘，2008，31(3)：131-133．
[193]刘卫光，郭师红，周利华．红外与可见光图像实时配准融合系统[J]．红外技术，2004，26(5)：66-71．
[2]阮秋奇，阮宇智，等译．数字图像处理（第二版）[M]．北京：电子工业出版社，2004．
[3]郑南宁．计算机视觉与模式识别[M]．北京：国防工业出版社，1998．
[4]康耀红．数据融合理论与应用[M]．西安：西安电子科技大学出版社，1997．
[5]文成林，周东华．多尺度估计理论及其应用[M]．北京：清华大学出版社，2002．
[6]李光鑫．红外和可见光图像融合技术的研究[D]：[博士学位论文]．长春：吉林大学，2008．
[7]何友，王国宏，陆大紟．多传感器数据融合模型综述[J]．清华大学学报，1996，36(9)：14-20．
[8]Basseville M, Benveniste A, Willsky A. S. Multiscale autoregressive process, PartsI: Schur-Levinson Parametrization [J]. IEEE Trans. on Signal Processing,1992,40(8):1915-1934.
[9]徐毓．雷达网数据融合问题研究[D]：[博士学位论文]．北京：清华大学，2003．
[10]Bertero M, Poggio T. A. III-posed problems in early vision [J]. Proceedings of theIEEE,1998,76(8):869-889.
[11]Cheng Y. Mean Shift, mode seeking, and clustering [J]. IEEE Trans. PatternAnalysis and Machine Intelligence,1995,17(8):790-799.
[12]Comaniciu D, Meer P. Mean Shift analysis and applications [C]. Proc, Int1Conf,Computer Vision,1999:1197-1203.
[13]Rucklidge W J. Efficiently Locating Objects Using Hausdorff Distance [J].International Journal of Computer Vision,1997,24(3):251-270.
[14]Ke Y, Sukthankar R. PCA-SIFT: A More Distinctive Representation for LocalImage Descriptors [C]. Computer Vision and Pattern Recognition,2004:511-517.
[15]Mikolajczyk K, Schmid C. Scale and Affine invariant interest point detectors [J].Int1Computer Vision,2004,60(1):63-86.
[16]管云峰，胡勇，李介谷．基于Fourier-Mellin变换的对称相匹配滤波算法[J]．红外与毫米波学报，1999,18(6)：465-471．
[17]强赞霞，彭加雄，王洪群．基于傅里叶变换的遥感图像配准算法[J]．红外与激光工程，2004，33(4)：385-387．
[18]Philippe Thevenaz, Urs E. Ruttimann, Michael Unser. A pyramid approach tosubpixel registration based on intensity [C]. IEEE Trans. on Image Processing,1998,7(1),27-41.
[19]Josien P. W. Pluim, J. B. Antoine, Max A. Viergever. Image registration bymaximization of combined mutual information and gradient information [C]. IEEETrans. on Medical Imaging,2000,19(8):809-814.
[20]Philippe Thevenaz, Michael Unse. Optimization of mutual information formultiresolution image registration [C]. IEEE Trans. on Image Processing,2000,9(12):2083-2098.
[21]L. G. Brown. A survey of image registration techniques [J]. ACM ComputingSurveys,1992,24(4):325-376.
[22]刘斌，彭嘉雄．图像配准的小波分解方法[J]．计算机辅助设计与图形学学报，2003，15(9)：1070-1073．
[23]Sadjadi F. A model-based technique for recognizing targets by using millimeterwave radar signature [J]. International Journal of Infrared and Millimeter Waves,1987,10(3):337-342.
[24]Chein-I Chang, Shao-Shan Chiang. Anomaly detection and classification forhyperspectral imagery [C]. IEEE Transactions on Geoscience,2002,40(6):1314-1325.
[25]Zelnio E G. Importance of sensor models to model-based vision application [J].SPIE Institute Series,1990(7):112-121.
[26]Verly J G. A model-based system for automatic target recognition [J]. SPIE,1991(1471):266-282.
[27]Tu T M, Su S C, Shyu H C, et al. A New Look at HIS Like Image Fusion Methods[J]. Information Fusion,2001,(2):177-186．
[28]Rockinger O. Image Sequence Fusion Using a Shift-Invariant Wavelet Transform[J]. In: Proc of Int1Conf on Image Processing,1997,(3):288-291.
[29]Rockinger O. Pixel-Level Fusion of Image Sequences Using Wavelet Frames [J].In: Proceedings in Image Fusion and Shape Varicability Techniques, Leeds, UK,1996,149-154.
[30]Rockinger O, Fechner T. Pixel-Level Image Fusion: The Case of ImageSequences [J]. In: Proceedings of SPIE, Signal Processing, Sensor Fusion, and TargetRecognition Ⅶ, Orlando, Florido,1998,3374:378-388.
[31]余小游，卢焕章，常青．多传感器目标识别系统中的数据融合方法与系统结构的研究[J]．国防科技参考，1998，19(1)：11-16．
[32]张莉，周伟达，李成焦．用于一维图像识别的支撑向量机方法[J]．红外与毫米波学报，2002，21(2)：119-123．
[33]夏明革，何友，唐小明．多传感器图像融合综述[J]．电光与控制，2002，4(9)：1-7．
[34]陈虎虎，钟方平，许学忠，等．基于支持向量机的低空飞行目标识别[J]．系统工程与电子技术，2005，27(l)：46-48．
[35]党宏社，韩崇昭，段战胜．一种基于模糊量相似度测量的模糊数据关联方法[J]．武汉理工大学学报(交通科学与工程版)，2003，27(7)：11—14．
[36]邰滢滢，陈小惠．基于模糊聚类的数据关联融合算法[J]．华东船舶工业学院学报(自然科学版)，2003，17(6)：58-62．
[37]王俊林，张剑云．应用D—S证据理论进行多传感器雷达体制识别[J]．现代防御技术，2006，34(6)：89-92．
[38]Blum R S. On multisensor image fusion performance limits from and estimationtheory perspective [J]. Information Fusion,2006,7(3):250-263.
[39]Smith M I, Heather J P. Review of Image Fusion Technology in2005[C].Proceedings of SPIE,2005,5782:29-45.
[40]刘哲，郝重阳，刘晓翔，等．多光谱图像与全色图像的像素级融合研究[J]．数据采集与处理，2003，18(3)：296-301．
[41]唐健，朱继红，孙增圻．基于智能优化策略的图像自动配准方法[J]．清华大学学报(自然科学版)，2004，44(9)：1252-1255．
[42]Roche A, Pennec X, Malandain G, et al. Rigid registration of3-Dultrasound withMR images: a new approach combining intensity and gradient information [J]. IEEETransaction on Medical Imaging,2001,20(10):1038-1049.
[43]Pluim J. P. W, Maintz J. B. N, Viergver M. A. Image registration by maximizationof combined mutual information and gradient information [J]. IEEE Transactions onMedical Imaging,2000,19(8):809-814.
[44]Hsieh Jun wei. Image registration using a new edge based approach [J]. ComputerVision and Image understanding,1997,67(2):112-130.
[45]李震，范湘涛，施建成．基于分窗口相关的遥感图象配准方法[J]．中国图象图形学报，2001，6(2)：129-132．
[46]Xia Y S, Leung H, Bosse E. Neural data fusion algorithms based on a linearlyconstrained least square method [J]. IEEE Transactions on Neural Networks,2002,13(2):320-329.
[47]Chibani Y, Houacine A. Redundant versus orthogonal wavelet decomposition formultisensor image fusion [J]. Pattern Recognition,2003,36(4):879-887.
[48]Santos M, Pajares G, Portela M, et al. A new wavelets image fusion strategy [C].Proceedings of Parttern Recognition and Image Analysis in Lecture Notes inComputer Science. Mallorca, Spain,2003,2652:919-926.
[49]I.Koren, A.Laine, F.Taylor. Image fusion using steerable dyadic wavelettransforms [J]. The International Conference on Image Processing,1995,3:232-235.
[50]V.S.Petrovic, C.S.Xydeas. Cross-band pixel selection in multiresolution imagefusion [J]. Proc.SPIE,1999,3719:319-326.
[51]O.Rockinger. Image sequence fusion using a shift-invariant wavelet transforms [J].The International Conference on Image Processing,1997,3:288-291.
[52]付华，李博，薛永存．基于D-S证据理论的数据融合井下监测方法分析[J]．传感器与微系统，2007，26(1)：27-29．
[53]闫志鹏，唐祯敏．基于Bayes估计和加权数据融合算法的交通量检测方法[J]．郑州轻工业学院学报(自然科学版)，2006，21(4)：44-46．
[54]刘严岩，吴秀清．基于广义相对信息熵的数据融合系统性能评估[J]．系统仿真学报，2006，28(5)：1283-1285．
[55]吴琼玉，蔡宣平，刘云辉．一种基于多分类器融合的双色红外成像目标识别方法[J]．信号处理，2008，28(2)：62-66．
[56]卢大威，马君国，赵宏钟，等．基于轮廓特征的空间目标识别算法[J]．火力与指挥控制，2007，12(5)：53-56．
[57]蒋晓瑜，高稚允．小波变换在特征级多重图像融合与目标分类中的应用[J]．红外技术，2004，8(2)：1-4．
[58]秦其明，陆荣建．分形与神经网络方法在卫星数字图像分类中的应用[J]．北京大学学报(自然科学版)，2000(36)：858-864．
[59]苏冬雪，吴小俊．基于多特征模糊聚类的图像融合方法[J]．计算机辅助设计与图形学学报，2006，15(6)：838-843．
[60]张池平．多传感器信息融合方法及其在空间目标识别中的应用[D]．[博士学位论文]．哈尔滨：哈尔滨工业大学，2006．
[61]F.R. Castella. Multisensor, multisite tracking filter. IEEE Proc, Radar, Sonar andNavigation,1994,141(2):75-83.
[62]L. Y. Bao. Centralized multisensor fusion algorithm for tracking application [J].Control Engineering Practice,1994,2(5):875-998.
[63]胡文龙等．多传感器多目标跟踪中的概率数据互联[J]．电子学报，1996，24(9)：30-35．
[64]Zhang Z, Blum R S. A Hybrid Image Registration Technique for A DigitalCamera Image Fusion Application [J]. Information Fusion,2001,(2):135-149.
[65]Achalakul T, Lee J, Taylor S. Resilient Image Fusion. In: Proceedings of theInternational Conference on Parallel Processing Workshops, Toronto, Canada,2000,8:291-296．
[66]Tseng D C, Chen Y L, Liu M S. Wavelet-Based Multispectral Image Fusion [J]. In:Proc of IEEE Int1Conf on Geo science and Remote Sensing (IGARSS),2001,(4):1956-1958.
[67]Tu T M, Su S C, Shyu H C, ed al. A New Look at HIS Like Image FusionMethods [J]. Information Fusion,2001,(2):177-186．
[68]Llinas. J, Hall. D. L. An Introduetion to Multisensor Data Fusion [J]. Proc.IEEE,1998,85(1):537-540.
[69]Pohl C, Genderen J L Van, Multisensor image fusion in remote sensing: Concepts,methods and applications [J]. Int J Remote Sensing,1998,19(5):823-854.
[70]Costantiti M, Farina A, ZirilliF. The fusion of different resolution SAR image [C].In: Proeeeding of the IEEE.1997,85(1):139-146.
[71]何国金，李克鲁，胡德永，等．多卫星遥感数据的信息融合：理论、方法和实践[J]．中国图像图形学报．1999，4A(9)：744-750．
[72]Chavez P S, Sides S C, Anderson J A. Comparison of three different methods tomerge multi-resolution and multi-spectral data: Landsat TM and SPOT Panehromatic[J]. PE&RS.1991,57(3):295-303.
[73]G.Simone, A.Farina. Image Fusion Techniques for Remote Sensing Application[J]. Information Fusion,2003,(3):3-15.
[74]李伟．像素级图像融合算法及应用研究[D]：［博士学位论文］．广州：华南理工大学，2006．
[75]A.Gholipour, N.Kehtarnavaz, R.Briggs, et al. Brain functional localization: Asurvey of image registration techniques [J]. IEEE Transactions on Medical Imaging,2007,26(4):427-451.
[76]B.Zitova, J.Flusser. Image registration methods: A survey [J]. Image and VisionComputing,2003,21:977-1000.
[77]J.Pluim, J.Maintz, M.Viergever. Mutual-information-based registration of medicalimages: A Survey [J]. IEEE Transactions on Medical Imaging,2003,22(8):986-1004.
[78]H.Lester, S.R.Arridge. A survey of hierarchical non-linear medical imageregistration [J]. Pattern Recognition,1999,32:129-149.
[79]L.G.Brown. A survey of image registration techniques [J]. ACM ComputingSurveys,1992,24(4):325-376.
[80]J.P.Heather, M.I.Smith. Multimodal image registration with applications to imagefusion [J]. The8th International Conference of Information Fusion,2005,1:372-379.
[81]毛士艺，赵巍．多传感器图像融合技术综述[J]．北京航空航天大学学报，2002，28(5)：512-518．
[82] Newman E A, Hartline P H. The infrared vision of snakes [J]. ScientificAmerican,1982,46(3):116-127.
[83]Fechner T, Godlewski G. Optimal fusion of TV and infrared images usingartificial neural networks [C]. Proc of SPIE.Orlando, FL:[s.n.],1995:919-925.
[84]Broussard R P, Roges S K, Oxley M E, et al. Physiologically motivated imagefusion for object detection using a pulse coupled neural network [J]. IEEE Trans onNeural Networks,1999,10(3):554-563.
[85]Toet A. Hierarchical image fusion [J]. Machine Vision and Applications,1990,3(1):1-11.
[86]王洁，韩崇昭，李晓榕．异步多传感器数据融合[J]．控制与决策，2001，16(6)：877-881．
[87]姜万录，李冲祥，刘继刚．多传感器数据融合技术及展望[J]．机床与液压，2003，03(6)：16-18．
[88]曲晓慧，安钢．数据融合方法综述及展望[J]．舰船电子工程，2003(02)：33-35．
[89]夏明革，何友，唐小明，等．图像融合的发展现状与展望[J]．船舶电子工程，2002，(6)：2-12．
[90]杨杰，陆正刚，黄欣．基于多传感器数据融合的目标识别和跟踪[J]．上海交通大学学报，1999，33(9)：1107-1110．
[91]刘严岩，吴秀清．基于广义相对信息熵的数据融合系统性能评估[J]．系统仿真学报，2006，28(5)：1283-1285．
[92]刘同明．数据融合技术及其应用[M]．北京：国防工业出版社，2000．
[93]孟继成，杨万麟．基于核函数的雷达一维距离像目标识别[J]．电子与信息学报，2005，27(3)：462-466．
[94]O.Rockinger, T.Fechner. Pixel-level image fusion: The case of image sequences[J]. Proc.SPIE,1998,374:378-388.
[95]P.J.Burt, E.H.Adelson. Merging images through pattern decomposition.Applications of Digital Image Processing VIII [J]. Proc.SPIE,1985,575:173-181.
[96]P.J.Burt, R.J.Kolczynski. Enhanced image capture through fusion [J]. The4thInternational Conference on Computer Vision,1993:173-182.
[97]A.Toet. Image fusion by a ration of low-pass pyramid [J]. Pattern RecognitionLetters,1989,9(4):245-253.
[98]A.Toet, J.J.van Ruyven, J.M.Valeton. Merging thermal and visual images by acontrast pyramid [J]. Optical Engineering,1989,28(7):789-792.
[99]A.Toet. Multi-scale contrast enhancement with applications to image fusion [J].Optical Engineering,1992,31(5):1026-1031.
[100]G.K.Matsopoulos, S.Marshall. Application of morphological pyramids: Fusionof MR and CT phantoms [J].Journal of Visual Communication and ImageRepresentation,1995,6(2):196-207.
[101]C.Lejeune. Wavelet transform for infrared application [J]. Proc.SPIE,1995,2552:313-324.
[102]刘贵喜，杨万海．一种像素级多算子红外与可见光图像融合方法[J]．红外与毫米学报，2001，20(3)：207-210．
[103]M.K.Uner, L.C.Ramac, P.K.Varshney, et al. Concealed weapon detection: Animage fusion approach [J]. Proc.SPIE,1997,2942:123-132.
[104]H.Li, B.S.Manjunath, S.K.Mitra. Multisensor image fusion using the wavelettransforms [J]. Graphical Models and Image Processing,1995,57(3):235-245.
[105]高海波．多源传感器最优配准技术和算法研究[D]：[硕士学位论文]．西安：西安电子科技大学，2009．
[106]L. Brown. A survey of image registration techniques [J]. ACM, ComputingSurveys,1992,24(4):325-376.
[107]P. A. Van den Elsen, E. J. D. Pol, M. A. Viergever. Medical image matching-Areview with classication [C]. IEEE Eng. Med. Biol. Mag.,1993,12:26-39.
[108]P. A. Viola, W. M. Wells III. Alignment by maximization of mutual information.[J]. International Journal of Computer Vision,1997,24(2):137-154.
[109]A.Goshtasby, G. C. Stockman, C. V. Page. A region-based approach to digitalimage registration with subpixel accuracy [C]. IEEE Trans. on Geoscience andRemote Sensing,1986, GE-24(3):390-399.
[110]A. D. Ventura, A. Rampini, R. Schettini. Image registration by recognition ofcorresponding structures [C]. IEEE Trans. on Geoscience and Remote Sensing,1990,28(3):305-314.
[111]B. S. Reddy, B. N. Chatterji. An FFT-based technique for translation, rotation,and scale-invariant image registration [C]. IEEE Trans. on Image Processing,1996,5(8):1266-1271.
[112]田阿灵．基于SIFT的红外与可见光图像配准方法研究[D]：[硕士学位论文]．北京：华北电力大学，2008．
[113]张浩．多信息融合图像边缘特征提取及图像配准研究与应用[D]：[博士学位论文]．杭州：浙江大学，2008．
[114]J. Ton and A. K. Jain. Registering Landsat images by point matching [J]. IEEETrans. on Geoscience and Remote Sensing,1989,27:642-651.
[115]J. Flusser, T. Suk. A moment-based approach to registration of images withaffine geometric distortion [J]. IEEE Trans. on Geoscience and Remote Sensing,1994,32(2):382-387.
[116]H. Li, B. S. Manjunath, S. K. Mitra. A contour-based approach to multisensorimage registration [J]. IEEE Trans. on Image Processing,1995,4(3):320-334.
[117]Mark Holden, Derek L. G. Hill, Erika R. E. Denton. Voxel similarity measuresfor3-D serial MR bain image registration [J]. IEEE Transaction on Medical Image,2000,19(2):94-102.
[118]Kwon O. K, Sim D. G, Park R. H. Robust Hausdorff Distance MatchingAlgorithms Using Pyramidal structures [J]. Pattern Recognition,2001,34(7):2005-2013.
[119]Harold S Stone, Robert Wolpov. Blind cross-spectral image registration usingprefiltering and Fourier based translation detection [J]. IEEE Transaction onGeoscience and Remote Sensing,2002,40(3):637-650.
[120]Harold S Stone, Michael T Orchard, Ee Chien Chang, et al. A fast direct Fourierbased algorithm for subpixel registration of images [J]. IEEE Transactions onGeoscience and Remote Sensing,2001,39(10):2235-2243.
[121]Wen-Hao Wang, Yung-Chang Chen. Image registration by control points pairingusing the invariant properties of line segments [J]. Pattern recognition letters,1997,18(3):269-274.
[122]Hui Li, B. S. Manjunath, S. K. Mitra. A contour-based approach to multisensorimage registration [J]. IEEE Trans. on Image Processing,1995,4(3):320-334.
[123]Xiaolong Dai and Siamak Khorram. A feature-Based image registrationalgorithm using improved chain-code representation combined with invariantmoments [J]. IEEE Trans. on Geoscience and Remote Sensing,1999,37(5):2351-2362.
[124]陈煜，田裕鹏．图像融合中的图像配准方法研究[J]．激光与红外，2004，34(1)：34-36．
[125]王东峰．多模态和大型图像配准技术研究[D]：[博士学位论文]．北京：中国科学院，2002．
[126]杨凤芹．基于粒子群的优化方法研究[D]：[博士学位论文]．长春：吉林大学，2009．
[127]袁亚湘，孙文瑜．最优化理论与方法[M]．北京：科学出版社，1997．
[128]施光燕，钱伟懿，庞丽萍．最优化方法（第二版）[M]．北京：高等教育出版社，2007．
[129]闫允一．粒子群优化及其在图像处理中的应用研究[D]：[博士学位论文]．西安：西安电子科技大学，2008．
[130]P. A. Viola, W. M. Wells III. Alignment by maximization of mutual information[J]. International Journal of Computer Vision,1997,24(2):137-154.
[131]Van de Bergh F, A P Engelbrecht. A study of particle swarm optimizationtrajectories [J]. Information Sciences,2006,17(6):937-971.
[132]Kennedy J, Eberhart R. C. Particle Swarm Optimization [C]. Neural Networks,1995, Proceeding. IEEE International Conference. Piscataway, NJ, USA,1995:1942-1948.
[133]彭喜元，彭宇，戴毓丰．群智能理论及应用[J]．电子学报，2003，31（12A）：1982-1988．
[134]Sidhartha Panda, Narayana Prasad Padhy. Optimal location and controller designof STATCOM for power system stability improvement using PSO [J]. Journal of theFranklin Institute,2008,345(2):166-181.
[135]Ali Allahverdi, Fawaz S, Al-Anzi. A PSO and a Tabu search heuristics for theassembly scheduling problem of the two-stage distributed database application [J].Computers&Operations Research,2006,33(4):1056-1080.
[136]Li-Yeh Chuang, Hsueh-Wei Chang, Chung-Jui Tu, et al. Improved binary PSOfor feature selection using gene expression data [J]. Computational Biology andChemistry,2008,32(1):29-38.
[137]B. Samanta, C. Nataraj. Use of particle swarm optimization for machinery faultdetection [J]. Engineering Applications of Artificial Intelligence,2009,22(2):308-316.
[138]Leonard E. Baum and Ted Petrie. Statistical Inference for Probabilistic Functionsof Finite State Markov Chains[J].The Annals of Mathematical Statistics,1966,37(6):1554-1563.
[139]Young-Sun Yun, Yung-Hwan Oh. A segmental-feature HMM for continuousspeech recognition based on a parametric trajectory model [J]. SpeechCommunication,2002,38(1-2):115-130.
[140]Alexander Seward. A fast HMM match algorithm for very large vocabularyspeech recognition [J]. Speech Communication,2004,42(2):191-206.
[141]Suphattharachai Chomphan, Takao Kobayashi. Tone correctness improvement inspeaker dependent HMM-based Thai speech synthesis [J]. Speech Communication,2008,50(5):392-404.
[142]Randy Gomez, Tomoki Toda, Hiroshi Saruwatari, et al. Techniques in rapidunsupervised speaker adaptation based on HMM-Sufficient Statistics [J]. SpeechCommunication Speech Communication,2009,51(1):42-57.
[143]Longbiao Wang, Norihide Kitaoka, Seiichi Nakagawa. Robust distant speakerrecognition based on position-dependent CMN by combining speaker-specific GMMwith speaker-adapted HMM [J]. Speech Communication,2007,49(6):501-513.
[144]Tianming Hu, Liyanage C. De Silva, Kuntal Sengupta. A hybrid approach of NNand HMM for facial emotion classification [J].Pattern Recognition Letters,2002,23(11):1303-1310.
[145]Hongyu Liu, Jeannette Janssen, Evangelos Milios. Using HMM to learn userbrowsing patterns for focused Web crawling [J]. Data&Knowledge Engineering,2006,59(2):270-291.
[146]Qi Liu, Yi-Sheng Zhu, Bao-Hua Wang, et al. A HMM-based method to predictthe transmembrane regions of β-barrel membrane proteins [J]. Computational Biologyand Chemistry,2003,27(1):69-76.
[147]高尚，杨静宇．群智能算法及其应用[M]．北京：中国水利水电出版社，2006．
[148]陈华，叶东，陈刚，等．遗传算法的数字图像相关搜索法[J]．光学精密工程，2007，15(10)：1633-1637．
[149]Mingchao Sun, Bao Zhang, Jinghong Liu, et.al. The Registration of AerialInfrared and Visible Images[C].2010International Conference on Educational andInformation Technology (ICEIT2010),2010:428-439.
[150]杨煊，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法[J]．电子学报，2001，29(6)：846-848．
[151]Swain M I, Ballard D H. Color indexing [J]. International Journal of ComputerVision,1991,7(1):11-32．
[152]Rockinger O. Image Sequence Fusion Using a Shift-Invariant WaveletTransform [J]. In: Proc of Int1Conf on Image Processing,1997,(3):288-291．
[153]Rockinger O. Pixel-Level Fusion of Image Sequences Using Wavelet Frames [J].In: Proceedings in Image Fusion and Shape Varicability Techniques, Leeds, UK,1996，149-154．
[154]Rockinger O, Fechner T. Pixel-Level Image Fusion: The Case of ImageSequences [J]. In: Proceedings of SPIE, Signal Processing, Sensor Fusion, and TargetRecognition VII, Orlando, Florido,1998,3374:378-388.
[155]Scheunders P. Multiscale Edge Representation Applied to Image Fusion [J]. In:Proceedings of SPIE, Wavelet Application in Signal and Image Processing VII,2000,4119:894-901.
[156]敬忠良，肖刚，李振华．图像融合理论与应用[M]．北京：高等教育出版社，2007．
[157]Piella G. Adaptive wavelets and their applications to image fusion andcompression [D]:[Doctor Degree]. Amsterdam, Netherlands：Korteweg-de Vriesinstitute for mathematics, University of Amsterdam,2003.
[158]Piella G. A general framework for multiresolution image fusion: From pixels toregions [J]. Elsevier Science, Information fusion,2003,4(4):259-280.
[159]秦前清，杨宗凯．实用小波分析[M]．西安：西安电子科技出版社，1994．
[160]催锦泰．小波分析导论[M]．西安：西安交通大学出版社，1997．
[161]马维祯，段瑞祥．小波变换理论及在信号处理中的应用[J]．数据采集与处理，1994，9(2)：121一129．
[162]刘汉，莫玉龙．基于二维自适应小波基小波变换的规则纹理缺陷检测[J]．中国图象图形学报，1999，(4)：349一352．
[163]程正兴．小波分析算法及应用[M]．西安：西安交通大学出版社，1998．
[164]Q. T. Jinag. On the design of multifilter bank and orthonorml multi-waveletbases [J]. IEEE Trans on Signal Processing,1998,46(12):3292-3302.
[165]V. Streal, P. H. Helle. The Application of multiwavelet filter banks to imageproeessing [J]. IEEE Trans on image Porcessing,1999,8(4):548-563.
[166]X. G. Xia, D. P. Hadrin. Design of prefilter for discrete multiwavelet transforms[J]. IEEE Tarns on Singal Processing,1996,29(2):481-510.
[167]蒲恬，倪国强．基于对比度的多分辨图像融合[J]．电子学报，2000，28(12)：116-181．
[168]Burt P J, Adelson E H. The Laplacian Pyamid a compact image code [J]. IEEETrans on Commun,1998,31:532-540.
[169]李树涛，王耀南．基于树状小波分解的多传感器图像融合[J]．红外与毫米波学报，2001，20(3)：119-202．
[170]蒋晓瑜，高稚允，周立伟．基于小波变换的多分辨图像融合[J]．北京理工大学学报，1997，7(4)：458-461．
[171]张贤达，保铮．非平稳信号分析与处理[M]．北京：国防工业出版社，1998．
[172]Maes F, Collignon A. Multimodality image registration by maximization ofmutual information [J]. IEEE Trans on Medical imageing,1997,16(2):187-199.
[173]陈勇，皮德富，周士源．基于小波变换的红外图像融合技术研究[J]．红外与激光工程，2001，30(1)：15-17．
[174]Pluim P W, Maintz J. B. Mutual-information based registration of medicalimages: A suvery [J]. IEEE Trans on Medical Imageing,2003,22(8):986-1003.
[175]杨恒，杨万海，裴继红．基于小波分解的不同聚焦点图像融合方法[J]．电子学报，2001，29(6)：846-848．
[176]Srinivas B, Redd. An FFT based technique of Translation Rotation and ScaleInvariant Image Registration [J]. IEEE Trans on Image Processing,1996,5(8):1266-1270.
[177]Amar Mitiche, Aggarwal J. K. Cnotour registration by shape specific points forshape matching [J]. Computer Vision, Graphics, and Image Processing,1983,22(3):396-408.
[178]王丽荣．基于小波变换的目标检测方法研究[D]：[博士学位论文]．长春：吉林大学，2006．
[179]王宏，敬忠良，李建勋．多分辨率图像融合的研究与进展[J]．控制理论与应用，2004，21(1)：145-151．
[180]Goodman TNT. Wavelet of multiplicity [J]. Tarns, Amer Math Soc,1994,38(2):639-652.
[181]Geronimo J, Hardin D. Fractal functions and wavelet expansions based onseveral functions [J]. J Approx Theory,1994,78:373-401.
[182]蒋晓瑜，高雅允，周立伟．小波变换在多光谱图像融合中的应用[J]．电子学报，1997，25(8)：105-108．
[183]Mallat S. A theory for multiresolution signal decomposition: The waveletrepresentation [J]. IEEE Trans on PAMI,1989,11(7):674-693.
[184]David G. V. A wavelet-based analysis of fractal image compression [J]. IEEETrans. On Image Prorcessing,1998,7(2):140-153.
[185]李瑛．多元小波的构造及其应用[D]：[博士学位论文]．长春：吉林大学，2004．
[186]刘贵喜，杨万海．基于小波分解的图像融合方法及性能评价[J]．自动化学报，2002，28(6)：927-934．
[187]孙明超，张崇，刘晶红.多尺度图像增强可见光与红外图像融合[J].吉林大学学报（工学版），2012，42(3)：738-742.
[188]孙明超，张葆，刘晶红.高帧频图像融合光学测量吊舱的设计[J].光学精密工程.（已录用，EI收录）
[189]曲锋，刘英，王建，等．红外双波段图像实时融合系统[J]．光学精密工程，2010，18(7)：1684-1690．
[190]Dov Freiman. Dichroic Beamsplitter for a Dual-wavelength Canera in aLong-range Airborne Reconnaissance System [J]. Proc. Of SPIE2005,5783:827-834.
[191]董科研，潘玉龙，王学进，等．谐衍射红外双波段双焦光学系统设计[J]．光学精密工程，2008，16(5)：764-770．
[192]郝松傲，秦军．热红外图像与可见光图像的配准与融合[J]．四川测绘，2008，31(3)：131-133．
[193]刘卫光，郭师红，周利华．红外与可见光图像实时配准融合系统[J]．红外技术，2004，26(5)：66-71．
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |