基于不变特征的图像拼接及软同步直写硬盘记录技术研究
|
摘要
遥感图像拼接与记录技术是获取高分辨率、大视野的战场图像侦察信息的有效手段，是现代信息化侦察装备研究领域的关键技术之一。但现有图像拼接方法存在稳定性不好、速度慢、自动化程度不高、适应性不强和特征描述符构建复杂、描述向量维数过高等弱点，以及现有数据记录方法持续记录速率不够高的问题，直接影响到空天侦察能力的持续提升。
课题“基于不变特征的图像拼接及软同步直写硬盘记录技术研究”的目的是：对高分辨率成像传感器获取的图像实施全自动拼接、实时持续记录等技术进行深入的研究，探讨一种适用于大幅面遥感图像的全自动拼接方法、在恶劣环境下可靠工作的高速长时持续记录系统的设计和实现方法，为我国遥感侦察系统性能的进一步提高奠定理论和技术基础。本课题的研究，在空间探测、航天遥感数据处理、雷达成像数据处理、SAR对抗研究等领域也有广泛的应用前景。
本文首先基于光学成像的基本原理，全面总结了图像拼接系统的基本结构，推导了图像变换的数学模型，系统地阐述了图像匹配、图像校正、图像变换和图像融合等关键技术，为展开大幅面图像拼接技术的研究奠定理论基础。
在深入研究常规的图像特征提取技术的基础上，引入尺度不变特征变换（Scale Invariant Feature Transform，SIFT）技术，用于大幅面遥感图像的特征提取。针对SIFT描述符的不变性不够完善和描述向量维数过高的问题，提出了一种基于扇形区域分割的SIFT描述符构建方法，取消了构建描述符时对区域的旋转操作，把128维的描述向量降低到48维。针对SIFT描述符对低对比度图像适应能力差的弱点，提出了一种自适应对比度阈值控制提取关键点的方法，增强了SIFT算法对遥感图像的适应能力，扩展了其应用范围。
根据SIFT特征多量性和遥感图像幅面大的特点，提出了基于统计、变换模型和改进的RANSAC等三种自动匹配策略，能依据输入图像自动计算匹配过程所需的各种阈值；提出了一种大幅面遥感图像自动快速拼接方法，在下采样图像中提取特征和参数优化，把优化后的匹配对坐标直接传递到原始图像进行配准和拼接，并对常规的拼接缝消除方法进行了改进，提高了图像拼接质量，实现了遥感图像的全自动拼接，缩短了拼接时间，提升了图像拼接的自动化水平。
为了解决常规的记录系统速率低与图像数据持续传输速率高之间的矛盾，在深入研究各种大容量数据记录系统优缺点的基础上，提出一种多通道软同步高速直写硬盘的数据记录方法，设计了自启动同步直写控制器，优化了SCSI硬盘的记录时序，有效地提高了硬盘的启动速度和数据持续记录速率，为实现每秒200兆字节高速大容量遥感图像数据的实时记录提供了技术支持。
最后，对课题所研究的特征描述符构建方法、自动匹配策略、大幅面遥感图像拼接模型和多通道软同步高速数据记录系统进行了编程实现、设备制作和性能测试，实验结果显示：本文提出的基于扇型区域分割的特征描述符，在匹配性能与原SIFT算法相当的情况下，综合匹配时间得到了显著提高；自适应对比度阈值控制的方法有效增加了特征提取算法对遥感图像的适应能力，并且提取到的特征点分布均匀；基于改进的RANSAC自动匹配策略性能稳定，所用实验图像的平均查全率达到98.3%；大幅面遥感图像自动拼接方法得到的融合图像质量满足实际要求，拼接区平滑过渡，大幅度缩短了拼接处理时间。本文提出的多通道软同步高速数据记录技术，实现了每秒200兆字节高速大容量遥感图像数据的实时无损记录，比同类记录系统的速率提高了2倍以上，且体积小、使用方便，具有良好的可扩展性。
Remote sensing image mosaic and recording technique is a key technique usedin the field of information-based reconnaissance equipment research anddevelopment to obtain high-resolution and large-scale battlefield images. It includesimage mosaic technique based on invariant feature and hard-disk direct writingrecording technique based on soft synchronization. However, the existing imagemosaic methods have such weak points as poor stability and adaptability, lowrecording speed, not highly automated operation, and very complicated structureand excessively high dimensions of feature descriptors. And none of the existingrecording techniques has a high enough continuous recording rate, which has adirect influence on further improvement of remote sensing reconnaissanceperformance. Therefore, this thesis intends to study fully automatic mosaic andreal-time continuous recording technique for images obtained using high resolutionimaging sensors, and to formulate a fully automatic mosaic technique for large scaleremote sensing images, and to find a high-speed recording system with a longcontinuous recording time suitable for reliable operation under asperityenvironments, thereby providing theoretical and technical bases for furtherimprovement of China’s remote reconnaissance system performance. This researchalso benefits space exploration, space remote sensing data processing, radarimaging data processing, radar imaging data processing and anti-SAR.
This thesis starts with a summary presentation of the basic structure of aremote sensing image mosaic system, and the derivation of image transportmathematic model based on the basic principle of optical imaging, and a systematicexposition of key techniques, such as matching, transform, correction and fusion ofimages used for large scale image mosaic.
Scale invariant feature transform (SIFT) is introduced though the in-depthstudy of conventional image feature extraction techniques for the extraction of largescale remote sensing image features. In light of the imperfect invariance andexcessively high dimensions of SIFT descriptors, a new way of constructing SIFTdescriptors based on sectorial segmentation is proposed to avoid the rotationaloperation during the construction of descriptor, and the number of dimensions is reduced from128to48while the invariance of descriptor is holden. In light of thepoor adaptability of SIFT descriptor with respect to an image with low contrast, aself-adaptive contrast threshold is proposed for the extraction of key points, therebyenhancing the adaptability of SIFT algorithm to a remote sensing image, i.e.expanding its scope of applicability.
In light of the large numbers of SIFT features and large-scale remote sensingimages, three automatic matching strategies based on statistics, transform modeland improved RANSAC are proposed for the automatic calculation of thresholdsneeded for input images in the matching process. A fast automatic remote sensingimage mosaic process is proposed so that the optimization matching coordinate canbe transferred immediately after feature extraction in the sub-sampled images andparameter optimization to the original images for matching and mosaic, and theconventional mosaic seams are eliminated in the process as well. The new methodreduces the processing time and increases the automation level of remote sensingimage mosaic.
In order to solve the conflict between the low recording speed of aconventional recording system and the high continuous transfer speed of image data,a hard-disk high-speed direct rating recording method based on multi-channel softsynchronization is proposed through a comparative study of different large capacitydata recording systems. The self-starting speed and the continuous recording speedof hard-disks are effectively increased by re-designing the self-startingsynchronization direct writing controller and optimizing the recording sequence ofSCSI hard-disks. A technical support is thus provided for the realization of real-timerecording of remote sensing image data at200MB/s.
With programs developed and equipment produced, experiments are made withfeature descriptors, made in a new way automatic matching strategies, a large-scaleremote sensing image mosaic model, and the multi-channel soft synchronizationhigh-speed data recording system proposed in this thesis for performance evaluation.Experimental results indicate that the overall matching time has been improvedobviously by using the feature descriptors proposed while the matchingperformance is equivalent to that of original SIFT algorithm; the self-adaptivecontrast threshold control method has been used to effectively improve theadaptability of feature extraction algorithm to remote sensing images, and to make the distribution of feature points extracted even; the automatic matching strategybased on improved RANSAC has a stable performance, and the average reeall ratioof experimental images used goes up to98.3%; the quality of fused images realizedusing large scale remote sensing image mosaic method satisfied the actual needs,the transition between mosaic regions is smooth, and the stitching time is greatlyreduced. The multi-channel soft synchronization high-speed recording techniqueproposed in this thesis is used to realize the real-time nondestructive recording oflarge scale remote sensing images at200MB/s, more than double the speed ofsimilar recording systems, and it is small in size, easy to use, and has very goodexpandability as well.
课题“基于不变特征的图像拼接及软同步直写硬盘记录技术研究”的目的是：对高分辨率成像传感器获取的图像实施全自动拼接、实时持续记录等技术进行深入的研究，探讨一种适用于大幅面遥感图像的全自动拼接方法、在恶劣环境下可靠工作的高速长时持续记录系统的设计和实现方法，为我国遥感侦察系统性能的进一步提高奠定理论和技术基础。本课题的研究，在空间探测、航天遥感数据处理、雷达成像数据处理、SAR对抗研究等领域也有广泛的应用前景。
本文首先基于光学成像的基本原理，全面总结了图像拼接系统的基本结构，推导了图像变换的数学模型，系统地阐述了图像匹配、图像校正、图像变换和图像融合等关键技术，为展开大幅面图像拼接技术的研究奠定理论基础。
在深入研究常规的图像特征提取技术的基础上，引入尺度不变特征变换（Scale Invariant Feature Transform，SIFT）技术，用于大幅面遥感图像的特征提取。针对SIFT描述符的不变性不够完善和描述向量维数过高的问题，提出了一种基于扇形区域分割的SIFT描述符构建方法，取消了构建描述符时对区域的旋转操作，把128维的描述向量降低到48维。针对SIFT描述符对低对比度图像适应能力差的弱点，提出了一种自适应对比度阈值控制提取关键点的方法，增强了SIFT算法对遥感图像的适应能力，扩展了其应用范围。
根据SIFT特征多量性和遥感图像幅面大的特点，提出了基于统计、变换模型和改进的RANSAC等三种自动匹配策略，能依据输入图像自动计算匹配过程所需的各种阈值；提出了一种大幅面遥感图像自动快速拼接方法，在下采样图像中提取特征和参数优化，把优化后的匹配对坐标直接传递到原始图像进行配准和拼接，并对常规的拼接缝消除方法进行了改进，提高了图像拼接质量，实现了遥感图像的全自动拼接，缩短了拼接时间，提升了图像拼接的自动化水平。
为了解决常规的记录系统速率低与图像数据持续传输速率高之间的矛盾，在深入研究各种大容量数据记录系统优缺点的基础上，提出一种多通道软同步高速直写硬盘的数据记录方法，设计了自启动同步直写控制器，优化了SCSI硬盘的记录时序，有效地提高了硬盘的启动速度和数据持续记录速率，为实现每秒200兆字节高速大容量遥感图像数据的实时记录提供了技术支持。
最后，对课题所研究的特征描述符构建方法、自动匹配策略、大幅面遥感图像拼接模型和多通道软同步高速数据记录系统进行了编程实现、设备制作和性能测试，实验结果显示：本文提出的基于扇型区域分割的特征描述符，在匹配性能与原SIFT算法相当的情况下，综合匹配时间得到了显著提高；自适应对比度阈值控制的方法有效增加了特征提取算法对遥感图像的适应能力，并且提取到的特征点分布均匀；基于改进的RANSAC自动匹配策略性能稳定，所用实验图像的平均查全率达到98.3%；大幅面遥感图像自动拼接方法得到的融合图像质量满足实际要求，拼接区平滑过渡，大幅度缩短了拼接处理时间。本文提出的多通道软同步高速数据记录技术，实现了每秒200兆字节高速大容量遥感图像数据的实时无损记录，比同类记录系统的速率提高了2倍以上，且体积小、使用方便，具有良好的可扩展性。
Remote sensing image mosaic and recording technique is a key technique usedin the field of information-based reconnaissance equipment research anddevelopment to obtain high-resolution and large-scale battlefield images. It includesimage mosaic technique based on invariant feature and hard-disk direct writingrecording technique based on soft synchronization. However, the existing imagemosaic methods have such weak points as poor stability and adaptability, lowrecording speed, not highly automated operation, and very complicated structureand excessively high dimensions of feature descriptors. And none of the existingrecording techniques has a high enough continuous recording rate, which has adirect influence on further improvement of remote sensing reconnaissanceperformance. Therefore, this thesis intends to study fully automatic mosaic andreal-time continuous recording technique for images obtained using high resolutionimaging sensors, and to formulate a fully automatic mosaic technique for large scaleremote sensing images, and to find a high-speed recording system with a longcontinuous recording time suitable for reliable operation under asperityenvironments, thereby providing theoretical and technical bases for furtherimprovement of China’s remote reconnaissance system performance. This researchalso benefits space exploration, space remote sensing data processing, radarimaging data processing, radar imaging data processing and anti-SAR.
This thesis starts with a summary presentation of the basic structure of aremote sensing image mosaic system, and the derivation of image transportmathematic model based on the basic principle of optical imaging, and a systematicexposition of key techniques, such as matching, transform, correction and fusion ofimages used for large scale image mosaic.
Scale invariant feature transform (SIFT) is introduced though the in-depthstudy of conventional image feature extraction techniques for the extraction of largescale remote sensing image features. In light of the imperfect invariance andexcessively high dimensions of SIFT descriptors, a new way of constructing SIFTdescriptors based on sectorial segmentation is proposed to avoid the rotationaloperation during the construction of descriptor, and the number of dimensions is reduced from128to48while the invariance of descriptor is holden. In light of thepoor adaptability of SIFT descriptor with respect to an image with low contrast, aself-adaptive contrast threshold is proposed for the extraction of key points, therebyenhancing the adaptability of SIFT algorithm to a remote sensing image, i.e.expanding its scope of applicability.
In light of the large numbers of SIFT features and large-scale remote sensingimages, three automatic matching strategies based on statistics, transform modeland improved RANSAC are proposed for the automatic calculation of thresholdsneeded for input images in the matching process. A fast automatic remote sensingimage mosaic process is proposed so that the optimization matching coordinate canbe transferred immediately after feature extraction in the sub-sampled images andparameter optimization to the original images for matching and mosaic, and theconventional mosaic seams are eliminated in the process as well. The new methodreduces the processing time and increases the automation level of remote sensingimage mosaic.
In order to solve the conflict between the low recording speed of aconventional recording system and the high continuous transfer speed of image data,a hard-disk high-speed direct rating recording method based on multi-channel softsynchronization is proposed through a comparative study of different large capacitydata recording systems. The self-starting speed and the continuous recording speedof hard-disks are effectively increased by re-designing the self-startingsynchronization direct writing controller and optimizing the recording sequence ofSCSI hard-disks. A technical support is thus provided for the realization of real-timerecording of remote sensing image data at200MB/s.
With programs developed and equipment produced, experiments are made withfeature descriptors, made in a new way automatic matching strategies, a large-scaleremote sensing image mosaic model, and the multi-channel soft synchronizationhigh-speed data recording system proposed in this thesis for performance evaluation.Experimental results indicate that the overall matching time has been improvedobviously by using the feature descriptors proposed while the matchingperformance is equivalent to that of original SIFT algorithm; the self-adaptivecontrast threshold control method has been used to effectively improve theadaptability of feature extraction algorithm to remote sensing images, and to make the distribution of feature points extracted even; the automatic matching strategybased on improved RANSAC has a stable performance, and the average reeall ratioof experimental images used goes up to98.3%; the quality of fused images realizedusing large scale remote sensing image mosaic method satisfied the actual needs,the transition between mosaic regions is smooth, and the stitching time is greatlyreduced. The multi-channel soft synchronization high-speed recording techniqueproposed in this thesis is used to realize the real-time nondestructive recording oflarge scale remote sensing images at200MB/s, more than double the speed ofsimilar recording systems, and it is small in size, easy to use, and has very goodexpandability as well.
引文
[1]戴军.21世纪现代国内外军事侦察技术百科全书（一）[M].北京：军事文献出版社，2008：3-4.
[2] Booz Allen Hamilton. A Statement of Operational Needs on The OperationalConcept and Capabilities of The Ballistic Missile Defense System[M]. USStrategic Command,2006:6-7.
[3]傅全友，梁光烈等.中国大百科全书·军事[M].第二版.北京：中国大百科全书出版社，2007：232.
[4]郭冬梅.美国航空侦察中信息的获取及传输[J].中国科技信息.2005,(20):28-38.
[5]赵育良，许兆林，李开端.航空CCD光电侦察系统的发展现状与展望.光电子技术.2001，21(4)：290-293.
[6] Brownie D D. Introduction into service of mature pushbroom electro-opticsensors[J]. Proc. SPIE.2000,(4127)：12-23.
[7] Sturz R A. CCD video camera and airborne applications[J]. Proc. SPIE.2000，(4127)：139-147.
[8] Laresu A G. Dual-band framing cameras：technology and status[J]. Proc. SPIE.2000,(4127):148-156.
[9] Matthews B. Flight test results from the ultrahigh-resolution electro-opticalframing camera containing a9216×9216pixel wafer scale focal plane array[J].Proc. SPIE.1999,(3751):133-144.
[10]高士英.空军航空侦察装备发展需求[J].应用光学.2000，21(z1)：1-4
[11]荆新利，齐泽强，韩鹏.美军航空侦察设备探析[J].国防科技.2006，(6)：12-16.
[12]朱耘，韩根甲.无人机光电探测技术的现状及发展趋势[J].舰船科学技术.2004，26(6)：1-6.
[13]沈荣骏，李学军.自动制图—月球遥感数据处理的新方向[J].装备指挥技术学院学报.2010，21(1):1-5.
[14]徐正光，田清，张利欣.图像拼接方法探讨[J].微计算机信息(管控一体化).2006，22(10-3)：255-256.
[15]王伟，陆佩忠．数字图像拼接技术[J]．小型微型计算机系统．2006，27(6)：1347-1351.
[16]王成儒，赵娜，张丽丽.基于三角形几何相似性的图像配准与拼接[J].光电工程.2007，34(8)：87-92.
[17] Bossert，Oliver．A Java software for creation of image mosaics[J]．ComputerMethods and Programs in Biomedicine．2004,75(2)：159-161
[18] Guo-Sheng Yang，Huan-Long Zhang．Optimal Image Mosaic Wavelet MethodBased on Fuzzy Integral[J]．Machine Learning and Cybernetics．2006，8：3738-3744.
[19]张显全，唐振军，卢江涛.基于线匹配的图像拼接[J].计算机科学.2005，32(1)：221-223.
[20]王诚，李琳．基于模板匹配的全景图像拼接[J]．福建电脑．2008，(4)：104-105.
[21]钟力，胡晓峰.重叠图像拼接算法[J].中国图像图形学报.1998，3(5)：367-370.
[22]李志刚.边界重叠图像的一种快速拼接算法[J].计算机工程.2000，26(5)：37-38.
[23] Tian Guuiyun，Gledhill D，Taylor D．Comprehensive Interest Points BasedImaging Mosaic[J]．Pattern Recognition Leters，2003，24(9／l0)：l171-1179.
[24] Szeliski R, Kang S B. Direct Methods for Visual Scene Reconstruction
[C]．Proc．of IEEE Workshop on Presentation of Visual Scenes，1995:26-33.
[25] Fishchler MA, Bolles RC．Random Sample Consensus: A Paradigm for ModelFitting with Application to Image Analysis and Automated Cartography[J].Communication Association Machine,1981,24(6):381-395.
[26] Kim T，Im Y J．Automatic satellite image registration by combination ofmatching and random sample consensus[C]．IEEE Trans on Geoscience andRemote Sensing，2003，41(5)：1111-1117.
[27] Lingjia Gu．An Automatic Target Image Mosaic Algorithm[C]．IEEE．TheInternational Conference on "Computer as a Tool"．2007，(9)：369-374.
[28] Wang Wei, Hong Jun, Tang Yiping. Image Matching for GeomorphicMeasurement Based on SIFT and RANSAC Methods[C]. Proceedings of theIEEE on Computer Science and Software Engineering,2008:317-320.
[29] Shu Z L，Ruan Q Q．Image registration based on KLT feature tracker in imagemosaicing application[C]．Proceedings of ICSP2000．2000：1143-1146.
[30] Hsu S C，Sawhney H S，Kumar R．Automated Mosaics via TopologyInference[J]．IEEE Computer Graphics and Applications，2002，22(2)：44-54
[31] Davis J.Mosaics of Scenes with Moving Objects[C]. Proc. of IEEE Comp. Soc.Conf. on Computer Vision and Pattern Recognition，1998:354-360.
[32] Bartoli N，Dalai B，Bose R et a1．From Video Sequences to Motion Panoramas[C]．Proceedings of the IEEE Workshop on Motion and Video Computing，Orlando，Florida，USA，2002,12：201-207.
[33]庄志国，孙惠军，董继扬等．基于角点检测的图像匹配算法及其在图像拼接中的应用[J]．厦门大学学报(自然科学版)．2007，46(4)：501-505.
[34] LOWE D G. Object recognition from local scale-invariant features[C].Proceeding of ICCV. Piscataway, NJ,USA: Institute of Electrical andElectronics Engineers Inc,1999,2:1150-1157.
[35] LOWE D G. Distinctive image features from scale-invariant keypoints[J]．International Journal of Computer Vision，2004,60(2)：91-l10.
[36]张洁玉.图像局部不变特征提取与匹配及应用研究[D].南京理工大学.博士.2010.06，3-13.
[37]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.
[38] Vural M F, Yardimci Y, Temizel A. Multi modal satellite image registrationusing SIFT[C]. Proceedings of the IEEE on Signal Processing andCommunications Applications Conference,2009:428-431.
[39]杨恒，王庆.一种新的局部不变特征检测和描述算法[J].计算机学报.2010,33(5):935-944.
[40] Zhu Qidan, Li Ke. Image stitching using simplified SIFT[C]. Proceedings ofthe IEEE on Information and Automation,2010:1134-1137.
[41] Su Junying, Ai Mingyao. Unmanned Airship Based Multiple Spectrum ImageMosaic with SIFT Feature Matching[C]. Proceedings of the IEEE onMulti-Platform/Multi-Sensor Remote Sensing and Mapping,2011:1-5.
[42] Yang Ping, Mao Zheng, Gao Anjie et al. Video Image Mosaics in Real-TimeBased on SIFT[C]. Proceedings of the IEEE on Pervasive Computing SignalProcessing and Applications,2010:879-882.
[43] Hua Zhen, Li Yewei, Li Jinjiang. Image stitch algorithm based on SIFT andMVSC[C]. Proceedings of the IEEE on Fuzzy Systems and KnowledgeDiscovery,2010,6:2628-2632.
[44] Zhu Daixian, Wang Xiaohua. A Method of Improving SIFT AlgorithmMatching Efficiency[C]. Proceedings of the IEEE on Image and SignalProcessing,2009:1-5.
[45] Wang Yu-quan, Xia Gui-hua, Zhu Qi-dan el al. Monte Carlo Localization ofMobile Robot with Modified SIFT[C]. Proceedings of the IEEE on MeasuringTechnology and Mechatronics Automation,2009,3:400-403.
[46] Wang Xiaohua, Fu Weiping, Daixian Zhu. Research on recognition ofwork-piece based on improved SIFT algorithm[C]. Proceedings of the IEEE onElectronic Measurement&Instruments,2009,1:417-421.
[47] Wang Yan, Fu Weiping, Zhu Hong et al. A Method for Recognition ofWork-Pieces Based on Improved SIFT Characteristics Matching[C].Proceedings of the IEEE on Software Engineering,2009,3:29-33.
[48] Li Lingjun, Long Xiang. LSIFT-An improved SIFT algorithm with a newmatching method[C]. Proceedings of the IEEE on Computer Application andSystem Modeling,2010,4:643-646.
[49] Hua Yuning, Lin Jing, Lin Chao. An improved SIFT feature matchingalgorithm[C]. Proceedings of the IEEE on Intelligent Control and Automation,2010:6109-6113.
[50] Wang Lizhong, Ma Shuoshi, Xue Heru. An improved SIFT algorithm forfeature points matching of dairy cow images[C]. Proceedings of the IEEE onWorld Automation Congress,2010:87-90.
[51] Yang Yang, Song Yixu, Zhai Fangwen et al. A High-Precision LocalizationAlgorithm by Improved SIFT Key-Points[C]. Proceedings of the IEEE onImage and Signal Processing,2009:1-6.
[52] Hou Zhenjie, Zhao Lei, Gu Liguo et al. An Improved Image RegistrationMethod Based on SIFT[C]. Proceedings of the IEEE on Intelligent Interactionand Affective Computing,2009:87-90.
[53]柯杉，王博亮，黄晓阳.一种改进的SIFT算法及其在医学图像配准中的应用[J].厦门大学学报.2010,49(3)：354-358.
[54]刘焕敏，王华，段慧芬.一种改进的SIFT双向匹配算法[J].兵工自动化.2009,28(6):89-91.
[55]杨晓敏，吴炜，卿粼波等.图像特征点提取及匹配技术[J].光学精密工程.2009，17（9）:2276-2282.
[56]纪华，吴元昊，孙宏海等.结合全局信息的SIFT特征匹配算法[J].光学精密工程.2009，17（2）：439-444.
[57]刘立，彭复员，赵坤等.采用简化SIFT算法实现快速图像匹配[J].红外与激光工程.2008,37(1):181-184.
[58]吕冀，高洪民，汪渤，等.图像制导中的SIFT快速算法[J].系统工程与电子技术.2009,31(5):1147-1151.
[59] Ke Y, Sukthankar R. PCA-SIFT:a more distinctive representation for localimage descriptors[C]. Proceedings of IEEE Conference on Computer Visionand Pattern Recognition, Washington D C,2004,2:506-513.
[60] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[61] Huang Chun-Rong, Chen Chu-Song, Chung Pau-Choo. Contrast contexthistogram–An efficient discriminating local descriptor for object recognitionand image matching[J]. Pattern Recognition.2008,41(10):3071-3077
[62]刘萍萍,赵宏伟,臧雪柏,戴金波.一种快速局部特征描述算法.自动化学报,2010,36(1):40-45.
[63] Tola Engin, Lepetit Vincent, Fua Pascal. DAISY: An Efficient Dense DescriptorApplied to Wide-Baseline Stereo[J]. IEEE TRANSACTIONS ON PATTERNANALYSIS AND MACHINE INTELLIGENCE.2010,32(5):815-830.
[64] Cui Yan, Hasler Nils, Thorm hlen Thorsten et al. Scale Invariant FeatureTransform with Irregular Orientation Histogram Binning [C].6th InternationalConference on Image Analysis and Recognition (ICIAR2009):258-267.
[65] Wong Yuk-Man. Invariant Local Feature for Image Matching [D]. Hong Kong:The Chinese University of Hong Kong,2006:38-43.
[66] Chen Jie, Shan Shiguang, He Chu et al. WLD: A Robust Local ImageDescriptor[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS ANDMACHINE INTELLIGENCE.2010,32(9):1705-1720.
[67] Heikkil Marko, Pietik inen Matti, Schmid Cordelia. Description of InterestRegions with Local Binary Patterns[J]. IEEE TRANS-ACTIONS ON PatternRecognition2009,42(3):425-436.
[68] Bay Herbert, Ess Andreas, Tuytelaarset Tinne al. SURF: Speeded Up RobustFeatures[J]. Computer Vision and Image Understanding (CVIU).2008,110(3):346-359.
[69]张锐娟，张建奇，杨翠.基于SURF的图像配准方法研究[J].红外与激光工程.2009,38(1):165-165.
[70]侯舒维，郭宝龙.一种图像自动拼接的快速算法[J].计算机工程.2005,31(15):70-72.
[71]米兰，许海波.基于边缘提取的图像拼接[J].计算机应用研究.2007,24(5):318-320.
[72]樊庆文，王小龙，侯力等.基于等距序列图像的快速拼接技术[J].四川大学学报(工程科学版).2005,37(1):139-142.
[73]李佳佳，何小海，吴晓红.基于网格模板的最小欧式距离准则图像自动拼接技术[J].成都信息工程学院学报.2007,22(1):80-83.
[74] SZELISKI R. Video mosaics for virtual environments [J]. IEEE ComputerGraphics and Applications.1996,16(2):22-30.
[75]仵建宁，郭宝龙，冯宗哲.一种基于兴趣点匹配的像拼接方法[J].计算机应用.2006,26(3):610-612.
[76]朱福珍,李金宗,李冬冬等. IHS变换与小波变换相结合的图像融合新方法[J].计算机应用研究.2009，26(2):784-786.
[77]张跃进，谢昕.基于IHS和小波变换的遥感图像融合方法研究[J].华东交通大学学报.2008,25(1):49-52.
[78]潘建平，明飞雄，左志进.一种改进的小波变换图像融合方法[J].测绘.2009,32(2):82-86.
[79] Li H，Manjunath B S，Mitra S K．Multisensor image fusion using the wavelettransform[J]. Graphical Models and Image Processing.1995,57(3):235-245
[80] Quesu A Y. Large-capacity airborne data recorders for reconnaissanceapplications[J]. Proc. SPIE.1999,(3751):192-200.
[81] Sohail Ejaz, Kim Bum Seok, Chae Woong Lim. A novel model of imageacquisition and processing for holistic quantification of angiogenesis disruptedby application of mainstream and sidestream cigarette smoke solutions[J].Environmental Toxicology and Pharmacology.2006,(21):22-33.
[82] Gang Li, Wei Shao, Kaijie Wu et al. The DSP-based Data Acquisition andProcessing System for OCT[C]. SPIE2002,4916:536-542.
[83] Dongming Lu, Qian Chen, Guohua Gu. High resolution X-ray medicalsequential image acquisition and processing system based on PCI interface
[C]. SPIE2003,5203:683-690.
[84] Hidehiko Nakaya. Data Acquisition System for the Instruments of SubaruTelescope [C]. SPIE2004,5492:852-858.
[85] Binhua Li, Keliang Hu, Chunrong Wang et al. Data acquisition system based onthe Nios II for a CCD camera[C]. SPIE2006,6274(62741C):1-8.
[86] Bruce E. Pirger, Justin Schoenwald, Terry L. Herter et al. High Speed, HighlyFlexible Reconfigurable Data Acquisition System for Astronomy[C]. SPIE2006,6276(62760X):1-12.
[87] Hisashi Fujiwara, Masayuki Mori，Takashi Ishiwata. Continuous acquisitionand storage of uncompressed image data based on a personal computerequipped with a CCD camera and an external hard disk drive[J].MEASUREMENT SCIENCE AND TECHNOLOGY.2007,(18):952-958.
[88] Fei Liu, Jian Zhang, Yihua Yan et al. Design of PCI-based data acquisition,antenna control, and real-time web-based database for a solar radioobservational system[C]. SPIE2004,5496:419-425.
[89]徐江丰,张涌,汤心溢等.基于Wishbone-PCI Bridge核的红外图像高速采集系统[J].红外与激光工程.2006,35(6):713-716.
[90]郄玉双,刘广荣等.高速实时长时无压缩数字视频记录分析系统[J].光学技术.2005,31(3):476-478.
[91] Liua B J，Caob F，Zhou M Z et al. Trends in PACS image storage and archive[J].Computerized Medical Imaging and Graphics.2003,(27):165-174.
[92] Reetz J, Heimann P, Heinzel S et al. Image data acquisition in the scope of longduration discharges[J]. Fusion Engineering and Design.2004,(71):231-237.
[93]王红.磁盘阵列的RAID技术.信息化技术与信息化.2005,(3):134-136.
[94]刘伟周,张文栋.空载固态记录器中控制模块的设计[J].弹箭与制导学报.2005，25(1):190-191.
[95] Wise R J. Design for a modular nonvolatile5.0+Gb/sec solid state datarecorder[C]. Proc. SPIE.2000,4127:182-189.
[96]刘宇.机载合成孔径雷达实时信号处理及实时存储技术的研究与实现[D].中国科学院研究生院.博士.2003.07，2-3.
[97]张耀，栾志超，欧阳益明等.采用图像格式的IDE硬盘直写记录[J].光电工程.2004,31(5):68-72.
[98]黄进，郭立红，李岩等.高速CCD数字视频采集和并行存储技术[J].长春理工大学学报.2004,27(3):104-106.
[99]蒋昌龙.柔性并行高速数据记录系统的研究与实现[D].清华大学.博士.2003.07，60-70.
[100]吴立德.计算机视觉[M].上海:复旦大学出版社，1993:119-128.
[101]钟玉琢，乔秉新，李树青.机器人视觉技术[M].北京:国防工业出版社，1994:132-145.
[102]李忠新.图像镶嵌理论及若干算法研究[D].南京理工大学.博士.2004.05,13-16.
[103]马颂德，张正友.计算机视觉—计算理论与算法基础[M].北京:科学出版社，1998:199-202.
[104]Brown L G. A survey of image registration techniques [J].ACM ComputingSurveys.1992,24(4):325-376.
[105]韩崇昭，朱洪艳，段战胜等.多源信息融合[M].北京:清华大学出版社，2006:377-383,416-418.
[106]Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images usingthe Hausdorff distance[J]．IEEE Transactions on Pattern Analysis and MachineIntelligence，1993，15(9)：850-863.
[107]刘琼.多源图像配准若干关键技术研究[D].北京理工大学.博士.2006.07，10-30.
[108]Barnea D I, Silverman H F. A class of algorithms for fast digital imageregistration [J]. IEEE Transactions on Computing,1972,21(2):179-186.
[109]Zhiqiang Hou, Chongzhao Han, Lin Zheng. A fast Visual Tracking AlgorithmBased on Circle Pixels Matching[C]. Proceedings of the Sixth InternationalConference on Information Fusion.2003:291-295.
[110]邓敏，徐凯，赵彬彬等.基于结构化空间关系信息的结点层次匹配方法[J].武汉大学学报·信息科学版.2010,35(8):913-916.
[111]Bentley J L．K-d trees for semi-dynamic point sets[C]. Proceedings of the SixthAnnual Symposium on Computational Geometry，San Francisco，USA，1990：187-197.
[112] Zitova B, Flusser J. Image registration methods: A survey[J]. Image andVision Computing,2003,21:977-1000.
[113]吕金建.基于特征的多源遥感图像配准技术研究[D].国防科学技术大学.博士.2008.10,8-9.
[114]葛宝臻，李晓洁，邱实.基于共面点直接线性变换的摄像机畸变校正[J].中国激光.2010，37(2):488-493.
[115]田杨.精确直方图规定化[D].山东大学.硕士.2008.10:8,16-20.
[116]童晓冲，吴云东，王慧等.大面阵CCD影像多通道不一致性消除算法[J].测绘学报,2006,35(3):234-239.
[117]刘卫光.图像信息融合与识别[M].北京:电子工业出版社.2008:19-32.
[118]何友，彭应宁.多传感器数据融合模型综述[J].清华大学学报(自然科学版).1996,36(9):14-20.
[119]He Chu, Xia Guisong, Peng Wenmin et al. Pixel-level SAR image fusion basedon turbo iterative[C]. SPIE.2005,6043(60432X):1-8.
[120]陆欢.像素级多源图像配准及融合研究[D].南京航空航天大学.硕士.2007.01,8-9.
[121]Xiao Zhongyong, Jiang Hong, Zhou Huiping et al. Remote sensing imagefusion based on fuzzy theory in pixel level and assessing the quality ofresulting images[C]. SPIE.2007,6752(67520P):1-9.
[122]Edward J Bender, Colin E Reese, Gooitzen S Van Der Wal. Comparison ofadditive image fusion versus feature-level image fusion techniques forenhanced night driving[C]. SPIE.2003,4796:140-151.
[123]Fan Zhigang, Fu Songling, Li Runshun et al. Feature-level image fusiontechnique based on wavelet transform[C]. SPIE.2002,4919:289-292.
[124]Chen Shao-hui, Zeng Zhi-yuan, Wang Cheng. Decision-level fusion systemrealization of multisensor images[C]. SPIE.2005,6044(604406):1-6.
[125]Wang Yi,Chen Wei, Mao Shiyi. Multi-sensor decision level image fusion basedon fuzzy theory and unsupervised FCM[C]. SPIE.2006,6200(62000J):1-7.
[126]Aed El-Saba, Tadele Bezuayehu. Fusion of Stokes vector imagery using simplelogical operators:application to the problem of surface land mine detection[C].SPIE.2008,6972(69720Q):1-13.
[127]ZHAO Long, WANG Guangfang. Study on adaptation of SAR/CCD imagefusion algorithm[C]. SPIE.2008,6623(66230P):1-8.
[128] Mohd Shahida, Sumana Guptab. Fusion of multisensor, multispectral anddefocused images[C]. SPIE.2005,6043(604308):1-7.
[129] Lei Zhang, Peng Liu, Yuling Liu et al.3D reconstruction based on waveletpyramid image fusion algorithm for digital microscope[C]. SPIE.2009,7513(751312):1-8.
[130]WANG Haihui, ZHANG Jian, WANG Jun et al. A novel method based ondiscrete multiple wavelet transform to multispectral image fusion[C]. SPIE.2005,6044(60440T):1-8.
[131]Li Jianlin, Yu Jiancheng, Sun Shengli. An Image Fusion Method Based onBiorthogonal Wavelet[C]. SPIE.2007,66833(683330):1-9.
[132] WANG Xin, YAN Feng, SUI Yong-xin et al. Multiwavelet based multispectralimage fusion for corona detection[C]. SPIE.2006,6027(60272R):1-6.
[133]Germain M, Voorons M, Boucher J M et al. Fuzzy statistical classificationmethod for multiband image fusion[C]. Proceedings of the Fifth InternationalConference on Information Fusion,2002,1:178-184.
[134]Sharma B, Pavel M. Adaptive and statistical image fusion[C]. Proceedings ofthe Forth International Conference on Information Fusion,2001,1:125-131
[135]Sun Jifeng, Jiang Yuanjiao, Zeng Shaoyong. A study of PCA image fusiontechniques on remote sensing[C]. SPIE.2005,5985(59853X):1-6
[136]S Senthil Kumar, S Muttan. PCA-based image fusion[C]. SPIE.2006,6233(62331T):1-8.
[137] Cheng Sansheng, Yang Yingbao, Li Yanwen. Image fusion based on improvedHIS and curvelet transform integrated method[C]. SPIE.2007,6752(67520S):1-10.
[138] Zhang Xiaodong, Yan Zhiyan, Pan Delu et al. An image fusion method basedon EMD decomposition[C]. SPIE.2009,7494(74941R):1-9.
[139] Liu Yueyan, Jia Yonghong, Zou Cui et al. Comparison of Laplace pyramid anda trous wavelet transformation techniques for fusion of Ikonos images[C].SPIE.2005,6044(60442A):1-6.
[140] Yajun Song, Kun Gao, Guoqiang Ni. Implementation of real-time Laplacianpyramid image fusion processing based on FPGA[C]. SPIE.2007,6833(683316):1-8.
[141]Chunling Zhao, Quanxin Ding, Jianxun Li. The performance analysis of imagefusion algorithm[C]. IEEE, International Symposium on ComputationalIntelligence and Design,2008,1:83-86.
[142]Toet A. Image fusion by a ratio of low-pass pyramid[J]. Pattern RecognitionLetters,1989,9(4):245-253.
[143]Shao Guifang,Li Zushu,Huang Tongyuan et al. An evaluation method forfusion image quality based on HVS[C]. SPIE.2005,6041(604103):1-6.
[144]Daubechies I. Ten lectures on wavelets[M]. Philadelphia: SIAM Publ,1992:10-50.
[145]Harris C, Stephens M. A Combined Corner and Edge Detector. In: ProceedingsFourth Alvey Vision Conference, Manchester, UK,1988:147-151.
[146]廖斌.基于特征点的图像配准技术研究[D].国防科学技术大学.博士.2008.06，19-21.
[147]Stephen M S，Brady J M. SUSAN-a new approach to low Level imageprocessing [J]．International Journal of Computer Vision，1997，23(1)：45-78.
[148] Zhou Dongxiang，Liu Yunhui，Cai Xuanping．An efficient and robust cornerdetection algorithm [C]．Proceedings of the5th World Congress on IntelligentControl and Automation，2004,5:4020-4024.
[149]Kenney C S，Zuliani M，Manjunath B S. An axiomatic approach to cornerdetection[C]. Proceedings of IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2005，1:191-197.
[150]沈项军，李峰，陈金华.一种基于特征跟踪的彩色序列图像拼接方法[J].微电脑应用.2003,19(3):39-41.
[151]Koenderink J J. The structure of images[J]. Biological Cybernetics,1984，50:363-396.
[152]Lindeberg Tony. Scale-space theory: A basic tool for analysing structures atdifferent scales[J]. Journal of Applied Statistics.1994,21(2):224-270.
[153]Lindeberg Tony. Detecting salient blob-like image structures and their scaleswith a scale-space primal sketch: a method for focus-of-attention[J].International Journal of Computer Vision.1993,11(3):283-318.
[154]Mikolajczyk K, Schmid C. An affine invariant interest point detector[C]. InEuropean Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:128-142.
[155]Li Canlin, Ma Lizhuang. A new framework for feature descriptor based onSIFT[J]. Pattern Recognition Letters.2009,30(5):544-557.
[156]赵向阳，杜利民.一种全自动稳健的图像拼接融合算法[J].中国图象图形学报，2004，9(4)：417-422.
[157]苏伍各，陶忠祥，董博.一种基于提升小波的图像融合技术研究[J].光学与光电技术，2010，8(4):56-59.
[158]牛晓晖，贾克斌.基于PCA和自适应区域方差的图像融合方法[J].计算机应用研究，2010，27(8):3179-3181.
[159]张永梅，田越，李波.基于小波变换的自适应图像融合算法[J].高技术通讯，2010，20(2):111-116.
[160]王小艳，吴迁，赵薇.基于小波变换的相关邻域非线性迭代图像融合[J].计算机工程与设计，2010，31(16):3628-3631.
[161]王仲妮，余先川，张立保.一种基于整数小波变换的遥感影像融合算法[J].光电子·激光，2008，19(11):1542-1545.
[162]何同弟，汪西莉.基于小波-Contourlet变换的遥感图像融合[J].计算机工程与设计，2008，29(24):6302-6304.
[163]史榕，许惠平，陈华根.遥感影像数据融合技术及融合质量评价研究[J].鲁东大学学报(自然科学版)，2008，24(2):130-134.
[164]李伟.多源图像融合质量的综合评价体系研究[J].深圳信息职业技术学院学报，2008，6(2):83-88.
[165]宋宝森，付永庆，宋海亮.一种消除图像拼接痕迹的新方法[J].计算机科学，2011，38(2):260-263.
[166]汪志云，黄梦为.基于直方图的图像增强及其MATLAB实现[J].计算机工程与科学,2006(28):55-58.
[167]王国美，陈孝威. SIFT特征匹配算法研究[J].盐城工学院学报(自然科学版)，2007，20(2):1-5.
[2] Booz Allen Hamilton. A Statement of Operational Needs on The OperationalConcept and Capabilities of The Ballistic Missile Defense System[M]. USStrategic Command,2006:6-7.
[3]傅全友，梁光烈等.中国大百科全书·军事[M].第二版.北京：中国大百科全书出版社，2007：232.
[4]郭冬梅.美国航空侦察中信息的获取及传输[J].中国科技信息.2005,(20):28-38.
[5]赵育良，许兆林，李开端.航空CCD光电侦察系统的发展现状与展望.光电子技术.2001，21(4)：290-293.
[6] Brownie D D. Introduction into service of mature pushbroom electro-opticsensors[J]. Proc. SPIE.2000,(4127)：12-23.
[7] Sturz R A. CCD video camera and airborne applications[J]. Proc. SPIE.2000，(4127)：139-147.
[8] Laresu A G. Dual-band framing cameras：technology and status[J]. Proc. SPIE.2000,(4127):148-156.
[9] Matthews B. Flight test results from the ultrahigh-resolution electro-opticalframing camera containing a9216×9216pixel wafer scale focal plane array[J].Proc. SPIE.1999,(3751):133-144.
[10]高士英.空军航空侦察装备发展需求[J].应用光学.2000，21(z1)：1-4
[11]荆新利，齐泽强，韩鹏.美军航空侦察设备探析[J].国防科技.2006，(6)：12-16.
[12]朱耘，韩根甲.无人机光电探测技术的现状及发展趋势[J].舰船科学技术.2004，26(6)：1-6.
[13]沈荣骏，李学军.自动制图—月球遥感数据处理的新方向[J].装备指挥技术学院学报.2010，21(1):1-5.
[14]徐正光，田清，张利欣.图像拼接方法探讨[J].微计算机信息(管控一体化).2006，22(10-3)：255-256.
[15]王伟，陆佩忠．数字图像拼接技术[J]．小型微型计算机系统．2006，27(6)：1347-1351.
[16]王成儒，赵娜，张丽丽.基于三角形几何相似性的图像配准与拼接[J].光电工程.2007，34(8)：87-92.
[17] Bossert，Oliver．A Java software for creation of image mosaics[J]．ComputerMethods and Programs in Biomedicine．2004,75(2)：159-161
[18] Guo-Sheng Yang，Huan-Long Zhang．Optimal Image Mosaic Wavelet MethodBased on Fuzzy Integral[J]．Machine Learning and Cybernetics．2006，8：3738-3744.
[19]张显全，唐振军，卢江涛.基于线匹配的图像拼接[J].计算机科学.2005，32(1)：221-223.
[20]王诚，李琳．基于模板匹配的全景图像拼接[J]．福建电脑．2008，(4)：104-105.
[21]钟力，胡晓峰.重叠图像拼接算法[J].中国图像图形学报.1998，3(5)：367-370.
[22]李志刚.边界重叠图像的一种快速拼接算法[J].计算机工程.2000，26(5)：37-38.
[23] Tian Guuiyun，Gledhill D，Taylor D．Comprehensive Interest Points BasedImaging Mosaic[J]．Pattern Recognition Leters，2003，24(9／l0)：l171-1179.
[24] Szeliski R, Kang S B. Direct Methods for Visual Scene Reconstruction
[C]．Proc．of IEEE Workshop on Presentation of Visual Scenes，1995:26-33.
[25] Fishchler MA, Bolles RC．Random Sample Consensus: A Paradigm for ModelFitting with Application to Image Analysis and Automated Cartography[J].Communication Association Machine,1981,24(6):381-395.
[26] Kim T，Im Y J．Automatic satellite image registration by combination ofmatching and random sample consensus[C]．IEEE Trans on Geoscience andRemote Sensing，2003，41(5)：1111-1117.
[27] Lingjia Gu．An Automatic Target Image Mosaic Algorithm[C]．IEEE．TheInternational Conference on "Computer as a Tool"．2007，(9)：369-374.
[28] Wang Wei, Hong Jun, Tang Yiping. Image Matching for GeomorphicMeasurement Based on SIFT and RANSAC Methods[C]. Proceedings of theIEEE on Computer Science and Software Engineering,2008:317-320.
[29] Shu Z L，Ruan Q Q．Image registration based on KLT feature tracker in imagemosaicing application[C]．Proceedings of ICSP2000．2000：1143-1146.
[30] Hsu S C，Sawhney H S，Kumar R．Automated Mosaics via TopologyInference[J]．IEEE Computer Graphics and Applications，2002，22(2)：44-54
[31] Davis J.Mosaics of Scenes with Moving Objects[C]. Proc. of IEEE Comp. Soc.Conf. on Computer Vision and Pattern Recognition，1998:354-360.
[32] Bartoli N，Dalai B，Bose R et a1．From Video Sequences to Motion Panoramas[C]．Proceedings of the IEEE Workshop on Motion and Video Computing，Orlando，Florida，USA，2002,12：201-207.
[33]庄志国，孙惠军，董继扬等．基于角点检测的图像匹配算法及其在图像拼接中的应用[J]．厦门大学学报(自然科学版)．2007，46(4)：501-505.
[34] LOWE D G. Object recognition from local scale-invariant features[C].Proceeding of ICCV. Piscataway, NJ,USA: Institute of Electrical andElectronics Engineers Inc,1999,2:1150-1157.
[35] LOWE D G. Distinctive image features from scale-invariant keypoints[J]．International Journal of Computer Vision，2004,60(2)：91-l10.
[36]张洁玉.图像局部不变特征提取与匹配及应用研究[D].南京理工大学.博士.2010.06，3-13.
[37]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.
[38] Vural M F, Yardimci Y, Temizel A. Multi modal satellite image registrationusing SIFT[C]. Proceedings of the IEEE on Signal Processing andCommunications Applications Conference,2009:428-431.
[39]杨恒，王庆.一种新的局部不变特征检测和描述算法[J].计算机学报.2010,33(5):935-944.
[40] Zhu Qidan, Li Ke. Image stitching using simplified SIFT[C]. Proceedings ofthe IEEE on Information and Automation,2010:1134-1137.
[41] Su Junying, Ai Mingyao. Unmanned Airship Based Multiple Spectrum ImageMosaic with SIFT Feature Matching[C]. Proceedings of the IEEE onMulti-Platform/Multi-Sensor Remote Sensing and Mapping,2011:1-5.
[42] Yang Ping, Mao Zheng, Gao Anjie et al. Video Image Mosaics in Real-TimeBased on SIFT[C]. Proceedings of the IEEE on Pervasive Computing SignalProcessing and Applications,2010:879-882.
[43] Hua Zhen, Li Yewei, Li Jinjiang. Image stitch algorithm based on SIFT andMVSC[C]. Proceedings of the IEEE on Fuzzy Systems and KnowledgeDiscovery,2010,6:2628-2632.
[44] Zhu Daixian, Wang Xiaohua. A Method of Improving SIFT AlgorithmMatching Efficiency[C]. Proceedings of the IEEE on Image and SignalProcessing,2009:1-5.
[45] Wang Yu-quan, Xia Gui-hua, Zhu Qi-dan el al. Monte Carlo Localization ofMobile Robot with Modified SIFT[C]. Proceedings of the IEEE on MeasuringTechnology and Mechatronics Automation,2009,3:400-403.
[46] Wang Xiaohua, Fu Weiping, Daixian Zhu. Research on recognition ofwork-piece based on improved SIFT algorithm[C]. Proceedings of the IEEE onElectronic Measurement&Instruments,2009,1:417-421.
[47] Wang Yan, Fu Weiping, Zhu Hong et al. A Method for Recognition ofWork-Pieces Based on Improved SIFT Characteristics Matching[C].Proceedings of the IEEE on Software Engineering,2009,3:29-33.
[48] Li Lingjun, Long Xiang. LSIFT-An improved SIFT algorithm with a newmatching method[C]. Proceedings of the IEEE on Computer Application andSystem Modeling,2010,4:643-646.
[49] Hua Yuning, Lin Jing, Lin Chao. An improved SIFT feature matchingalgorithm[C]. Proceedings of the IEEE on Intelligent Control and Automation,2010:6109-6113.
[50] Wang Lizhong, Ma Shuoshi, Xue Heru. An improved SIFT algorithm forfeature points matching of dairy cow images[C]. Proceedings of the IEEE onWorld Automation Congress,2010:87-90.
[51] Yang Yang, Song Yixu, Zhai Fangwen et al. A High-Precision LocalizationAlgorithm by Improved SIFT Key-Points[C]. Proceedings of the IEEE onImage and Signal Processing,2009:1-6.
[52] Hou Zhenjie, Zhao Lei, Gu Liguo et al. An Improved Image RegistrationMethod Based on SIFT[C]. Proceedings of the IEEE on Intelligent Interactionand Affective Computing,2009:87-90.
[53]柯杉，王博亮，黄晓阳.一种改进的SIFT算法及其在医学图像配准中的应用[J].厦门大学学报.2010,49(3)：354-358.
[54]刘焕敏，王华，段慧芬.一种改进的SIFT双向匹配算法[J].兵工自动化.2009,28(6):89-91.
[55]杨晓敏，吴炜，卿粼波等.图像特征点提取及匹配技术[J].光学精密工程.2009，17（9）:2276-2282.
[56]纪华，吴元昊，孙宏海等.结合全局信息的SIFT特征匹配算法[J].光学精密工程.2009，17（2）：439-444.
[57]刘立，彭复员，赵坤等.采用简化SIFT算法实现快速图像匹配[J].红外与激光工程.2008,37(1):181-184.
[58]吕冀，高洪民，汪渤，等.图像制导中的SIFT快速算法[J].系统工程与电子技术.2009,31(5):1147-1151.
[59] Ke Y, Sukthankar R. PCA-SIFT:a more distinctive representation for localimage descriptors[C]. Proceedings of IEEE Conference on Computer Visionand Pattern Recognition, Washington D C,2004,2:506-513.
[60] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[61] Huang Chun-Rong, Chen Chu-Song, Chung Pau-Choo. Contrast contexthistogram–An efficient discriminating local descriptor for object recognitionand image matching[J]. Pattern Recognition.2008,41(10):3071-3077
[62]刘萍萍,赵宏伟,臧雪柏,戴金波.一种快速局部特征描述算法.自动化学报,2010,36(1):40-45.
[63] Tola Engin, Lepetit Vincent, Fua Pascal. DAISY: An Efficient Dense DescriptorApplied to Wide-Baseline Stereo[J]. IEEE TRANSACTIONS ON PATTERNANALYSIS AND MACHINE INTELLIGENCE.2010,32(5):815-830.
[64] Cui Yan, Hasler Nils, Thorm hlen Thorsten et al. Scale Invariant FeatureTransform with Irregular Orientation Histogram Binning [C].6th InternationalConference on Image Analysis and Recognition (ICIAR2009):258-267.
[65] Wong Yuk-Man. Invariant Local Feature for Image Matching [D]. Hong Kong:The Chinese University of Hong Kong,2006:38-43.
[66] Chen Jie, Shan Shiguang, He Chu et al. WLD: A Robust Local ImageDescriptor[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS ANDMACHINE INTELLIGENCE.2010,32(9):1705-1720.
[67] Heikkil Marko, Pietik inen Matti, Schmid Cordelia. Description of InterestRegions with Local Binary Patterns[J]. IEEE TRANS-ACTIONS ON PatternRecognition2009,42(3):425-436.
[68] Bay Herbert, Ess Andreas, Tuytelaarset Tinne al. SURF: Speeded Up RobustFeatures[J]. Computer Vision and Image Understanding (CVIU).2008,110(3):346-359.
[69]张锐娟，张建奇，杨翠.基于SURF的图像配准方法研究[J].红外与激光工程.2009,38(1):165-165.
[70]侯舒维，郭宝龙.一种图像自动拼接的快速算法[J].计算机工程.2005,31(15):70-72.
[71]米兰，许海波.基于边缘提取的图像拼接[J].计算机应用研究.2007,24(5):318-320.
[72]樊庆文，王小龙，侯力等.基于等距序列图像的快速拼接技术[J].四川大学学报(工程科学版).2005,37(1):139-142.
[73]李佳佳，何小海，吴晓红.基于网格模板的最小欧式距离准则图像自动拼接技术[J].成都信息工程学院学报.2007,22(1):80-83.
[74] SZELISKI R. Video mosaics for virtual environments [J]. IEEE ComputerGraphics and Applications.1996,16(2):22-30.
[75]仵建宁，郭宝龙，冯宗哲.一种基于兴趣点匹配的像拼接方法[J].计算机应用.2006,26(3):610-612.
[76]朱福珍,李金宗,李冬冬等. IHS变换与小波变换相结合的图像融合新方法[J].计算机应用研究.2009，26(2):784-786.
[77]张跃进，谢昕.基于IHS和小波变换的遥感图像融合方法研究[J].华东交通大学学报.2008,25(1):49-52.
[78]潘建平，明飞雄，左志进.一种改进的小波变换图像融合方法[J].测绘.2009,32(2):82-86.
[79] Li H，Manjunath B S，Mitra S K．Multisensor image fusion using the wavelettransform[J]. Graphical Models and Image Processing.1995,57(3):235-245
[80] Quesu A Y. Large-capacity airborne data recorders for reconnaissanceapplications[J]. Proc. SPIE.1999,(3751):192-200.
[81] Sohail Ejaz, Kim Bum Seok, Chae Woong Lim. A novel model of imageacquisition and processing for holistic quantification of angiogenesis disruptedby application of mainstream and sidestream cigarette smoke solutions[J].Environmental Toxicology and Pharmacology.2006,(21):22-33.
[82] Gang Li, Wei Shao, Kaijie Wu et al. The DSP-based Data Acquisition andProcessing System for OCT[C]. SPIE2002,4916:536-542.
[83] Dongming Lu, Qian Chen, Guohua Gu. High resolution X-ray medicalsequential image acquisition and processing system based on PCI interface
[C]. SPIE2003,5203:683-690.
[84] Hidehiko Nakaya. Data Acquisition System for the Instruments of SubaruTelescope [C]. SPIE2004,5492:852-858.
[85] Binhua Li, Keliang Hu, Chunrong Wang et al. Data acquisition system based onthe Nios II for a CCD camera[C]. SPIE2006,6274(62741C):1-8.
[86] Bruce E. Pirger, Justin Schoenwald, Terry L. Herter et al. High Speed, HighlyFlexible Reconfigurable Data Acquisition System for Astronomy[C]. SPIE2006,6276(62760X):1-12.
[87] Hisashi Fujiwara, Masayuki Mori，Takashi Ishiwata. Continuous acquisitionand storage of uncompressed image data based on a personal computerequipped with a CCD camera and an external hard disk drive[J].MEASUREMENT SCIENCE AND TECHNOLOGY.2007,(18):952-958.
[88] Fei Liu, Jian Zhang, Yihua Yan et al. Design of PCI-based data acquisition,antenna control, and real-time web-based database for a solar radioobservational system[C]. SPIE2004,5496:419-425.
[89]徐江丰,张涌,汤心溢等.基于Wishbone-PCI Bridge核的红外图像高速采集系统[J].红外与激光工程.2006,35(6):713-716.
[90]郄玉双,刘广荣等.高速实时长时无压缩数字视频记录分析系统[J].光学技术.2005,31(3):476-478.
[91] Liua B J，Caob F，Zhou M Z et al. Trends in PACS image storage and archive[J].Computerized Medical Imaging and Graphics.2003,(27):165-174.
[92] Reetz J, Heimann P, Heinzel S et al. Image data acquisition in the scope of longduration discharges[J]. Fusion Engineering and Design.2004,(71):231-237.
[93]王红.磁盘阵列的RAID技术.信息化技术与信息化.2005,(3):134-136.
[94]刘伟周,张文栋.空载固态记录器中控制模块的设计[J].弹箭与制导学报.2005，25(1):190-191.
[95] Wise R J. Design for a modular nonvolatile5.0+Gb/sec solid state datarecorder[C]. Proc. SPIE.2000,4127:182-189.
[96]刘宇.机载合成孔径雷达实时信号处理及实时存储技术的研究与实现[D].中国科学院研究生院.博士.2003.07，2-3.
[97]张耀，栾志超，欧阳益明等.采用图像格式的IDE硬盘直写记录[J].光电工程.2004,31(5):68-72.
[98]黄进，郭立红，李岩等.高速CCD数字视频采集和并行存储技术[J].长春理工大学学报.2004,27(3):104-106.
[99]蒋昌龙.柔性并行高速数据记录系统的研究与实现[D].清华大学.博士.2003.07，60-70.
[100]吴立德.计算机视觉[M].上海:复旦大学出版社，1993:119-128.
[101]钟玉琢，乔秉新，李树青.机器人视觉技术[M].北京:国防工业出版社，1994:132-145.
[102]李忠新.图像镶嵌理论及若干算法研究[D].南京理工大学.博士.2004.05,13-16.
[103]马颂德，张正友.计算机视觉—计算理论与算法基础[M].北京:科学出版社，1998:199-202.
[104]Brown L G. A survey of image registration techniques [J].ACM ComputingSurveys.1992,24(4):325-376.
[105]韩崇昭，朱洪艳，段战胜等.多源信息融合[M].北京:清华大学出版社，2006:377-383,416-418.
[106]Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images usingthe Hausdorff distance[J]．IEEE Transactions on Pattern Analysis and MachineIntelligence，1993，15(9)：850-863.
[107]刘琼.多源图像配准若干关键技术研究[D].北京理工大学.博士.2006.07，10-30.
[108]Barnea D I, Silverman H F. A class of algorithms for fast digital imageregistration [J]. IEEE Transactions on Computing,1972,21(2):179-186.
[109]Zhiqiang Hou, Chongzhao Han, Lin Zheng. A fast Visual Tracking AlgorithmBased on Circle Pixels Matching[C]. Proceedings of the Sixth InternationalConference on Information Fusion.2003:291-295.
[110]邓敏，徐凯，赵彬彬等.基于结构化空间关系信息的结点层次匹配方法[J].武汉大学学报·信息科学版.2010,35(8):913-916.
[111]Bentley J L．K-d trees for semi-dynamic point sets[C]. Proceedings of the SixthAnnual Symposium on Computational Geometry，San Francisco，USA，1990：187-197.
[112] Zitova B, Flusser J. Image registration methods: A survey[J]. Image andVision Computing,2003,21:977-1000.
[113]吕金建.基于特征的多源遥感图像配准技术研究[D].国防科学技术大学.博士.2008.10,8-9.
[114]葛宝臻，李晓洁，邱实.基于共面点直接线性变换的摄像机畸变校正[J].中国激光.2010，37(2):488-493.
[115]田杨.精确直方图规定化[D].山东大学.硕士.2008.10:8,16-20.
[116]童晓冲，吴云东，王慧等.大面阵CCD影像多通道不一致性消除算法[J].测绘学报,2006,35(3):234-239.
[117]刘卫光.图像信息融合与识别[M].北京:电子工业出版社.2008:19-32.
[118]何友，彭应宁.多传感器数据融合模型综述[J].清华大学学报(自然科学版).1996,36(9):14-20.
[119]He Chu, Xia Guisong, Peng Wenmin et al. Pixel-level SAR image fusion basedon turbo iterative[C]. SPIE.2005,6043(60432X):1-8.
[120]陆欢.像素级多源图像配准及融合研究[D].南京航空航天大学.硕士.2007.01,8-9.
[121]Xiao Zhongyong, Jiang Hong, Zhou Huiping et al. Remote sensing imagefusion based on fuzzy theory in pixel level and assessing the quality ofresulting images[C]. SPIE.2007,6752(67520P):1-9.
[122]Edward J Bender, Colin E Reese, Gooitzen S Van Der Wal. Comparison ofadditive image fusion versus feature-level image fusion techniques forenhanced night driving[C]. SPIE.2003,4796:140-151.
[123]Fan Zhigang, Fu Songling, Li Runshun et al. Feature-level image fusiontechnique based on wavelet transform[C]. SPIE.2002,4919:289-292.
[124]Chen Shao-hui, Zeng Zhi-yuan, Wang Cheng. Decision-level fusion systemrealization of multisensor images[C]. SPIE.2005,6044(604406):1-6.
[125]Wang Yi,Chen Wei, Mao Shiyi. Multi-sensor decision level image fusion basedon fuzzy theory and unsupervised FCM[C]. SPIE.2006,6200(62000J):1-7.
[126]Aed El-Saba, Tadele Bezuayehu. Fusion of Stokes vector imagery using simplelogical operators:application to the problem of surface land mine detection[C].SPIE.2008,6972(69720Q):1-13.
[127]ZHAO Long, WANG Guangfang. Study on adaptation of SAR/CCD imagefusion algorithm[C]. SPIE.2008,6623(66230P):1-8.
[128] Mohd Shahida, Sumana Guptab. Fusion of multisensor, multispectral anddefocused images[C]. SPIE.2005,6043(604308):1-7.
[129] Lei Zhang, Peng Liu, Yuling Liu et al.3D reconstruction based on waveletpyramid image fusion algorithm for digital microscope[C]. SPIE.2009,7513(751312):1-8.
[130]WANG Haihui, ZHANG Jian, WANG Jun et al. A novel method based ondiscrete multiple wavelet transform to multispectral image fusion[C]. SPIE.2005,6044(60440T):1-8.
[131]Li Jianlin, Yu Jiancheng, Sun Shengli. An Image Fusion Method Based onBiorthogonal Wavelet[C]. SPIE.2007,66833(683330):1-9.
[132] WANG Xin, YAN Feng, SUI Yong-xin et al. Multiwavelet based multispectralimage fusion for corona detection[C]. SPIE.2006,6027(60272R):1-6.
[133]Germain M, Voorons M, Boucher J M et al. Fuzzy statistical classificationmethod for multiband image fusion[C]. Proceedings of the Fifth InternationalConference on Information Fusion,2002,1:178-184.
[134]Sharma B, Pavel M. Adaptive and statistical image fusion[C]. Proceedings ofthe Forth International Conference on Information Fusion,2001,1:125-131
[135]Sun Jifeng, Jiang Yuanjiao, Zeng Shaoyong. A study of PCA image fusiontechniques on remote sensing[C]. SPIE.2005,5985(59853X):1-6
[136]S Senthil Kumar, S Muttan. PCA-based image fusion[C]. SPIE.2006,6233(62331T):1-8.
[137] Cheng Sansheng, Yang Yingbao, Li Yanwen. Image fusion based on improvedHIS and curvelet transform integrated method[C]. SPIE.2007,6752(67520S):1-10.
[138] Zhang Xiaodong, Yan Zhiyan, Pan Delu et al. An image fusion method basedon EMD decomposition[C]. SPIE.2009,7494(74941R):1-9.
[139] Liu Yueyan, Jia Yonghong, Zou Cui et al. Comparison of Laplace pyramid anda trous wavelet transformation techniques for fusion of Ikonos images[C].SPIE.2005,6044(60442A):1-6.
[140] Yajun Song, Kun Gao, Guoqiang Ni. Implementation of real-time Laplacianpyramid image fusion processing based on FPGA[C]. SPIE.2007,6833(683316):1-8.
[141]Chunling Zhao, Quanxin Ding, Jianxun Li. The performance analysis of imagefusion algorithm[C]. IEEE, International Symposium on ComputationalIntelligence and Design,2008,1:83-86.
[142]Toet A. Image fusion by a ratio of low-pass pyramid[J]. Pattern RecognitionLetters,1989,9(4):245-253.
[143]Shao Guifang,Li Zushu,Huang Tongyuan et al. An evaluation method forfusion image quality based on HVS[C]. SPIE.2005,6041(604103):1-6.
[144]Daubechies I. Ten lectures on wavelets[M]. Philadelphia: SIAM Publ,1992:10-50.
[145]Harris C, Stephens M. A Combined Corner and Edge Detector. In: ProceedingsFourth Alvey Vision Conference, Manchester, UK,1988:147-151.
[146]廖斌.基于特征点的图像配准技术研究[D].国防科学技术大学.博士.2008.06，19-21.
[147]Stephen M S，Brady J M. SUSAN-a new approach to low Level imageprocessing [J]．International Journal of Computer Vision，1997，23(1)：45-78.
[148] Zhou Dongxiang，Liu Yunhui，Cai Xuanping．An efficient and robust cornerdetection algorithm [C]．Proceedings of the5th World Congress on IntelligentControl and Automation，2004,5:4020-4024.
[149]Kenney C S，Zuliani M，Manjunath B S. An axiomatic approach to cornerdetection[C]. Proceedings of IEEE Computer Society Conference on ComputerVision and Pattern Recognition，2005，1:191-197.
[150]沈项军，李峰，陈金华.一种基于特征跟踪的彩色序列图像拼接方法[J].微电脑应用.2003,19(3):39-41.
[151]Koenderink J J. The structure of images[J]. Biological Cybernetics,1984，50:363-396.
[152]Lindeberg Tony. Scale-space theory: A basic tool for analysing structures atdifferent scales[J]. Journal of Applied Statistics.1994,21(2):224-270.
[153]Lindeberg Tony. Detecting salient blob-like image structures and their scaleswith a scale-space primal sketch: a method for focus-of-attention[J].International Journal of Computer Vision.1993,11(3):283-318.
[154]Mikolajczyk K, Schmid C. An affine invariant interest point detector[C]. InEuropean Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:128-142.
[155]Li Canlin, Ma Lizhuang. A new framework for feature descriptor based onSIFT[J]. Pattern Recognition Letters.2009,30(5):544-557.
[156]赵向阳，杜利民.一种全自动稳健的图像拼接融合算法[J].中国图象图形学报，2004，9(4)：417-422.
[157]苏伍各，陶忠祥，董博.一种基于提升小波的图像融合技术研究[J].光学与光电技术，2010，8(4):56-59.
[158]牛晓晖，贾克斌.基于PCA和自适应区域方差的图像融合方法[J].计算机应用研究，2010，27(8):3179-3181.
[159]张永梅，田越，李波.基于小波变换的自适应图像融合算法[J].高技术通讯，2010，20(2):111-116.
[160]王小艳，吴迁，赵薇.基于小波变换的相关邻域非线性迭代图像融合[J].计算机工程与设计，2010，31(16):3628-3631.
[161]王仲妮，余先川，张立保.一种基于整数小波变换的遥感影像融合算法[J].光电子·激光，2008，19(11):1542-1545.
[162]何同弟，汪西莉.基于小波-Contourlet变换的遥感图像融合[J].计算机工程与设计，2008，29(24):6302-6304.
[163]史榕，许惠平，陈华根.遥感影像数据融合技术及融合质量评价研究[J].鲁东大学学报(自然科学版)，2008，24(2):130-134.
[164]李伟.多源图像融合质量的综合评价体系研究[J].深圳信息职业技术学院学报，2008，6(2):83-88.
[165]宋宝森，付永庆，宋海亮.一种消除图像拼接痕迹的新方法[J].计算机科学，2011，38(2):260-263.
[166]汪志云，黄梦为.基于直方图的图像增强及其MATLAB实现[J].计算机工程与科学,2006(28):55-58.
[167]王国美，陈孝威. SIFT特征匹配算法研究[J].盐城工学院学报(自然科学版)，2007，20(2):1-5.