全景图像拼接方法研究与实现
|
摘要
全景图像拼接理论、技术和方法是当前图像处理领域的一个研究热点，主要解决因成像设备的视角限制，不能直接拍摄到360度全视场图像的问题。该项研究的进展对推动大地测绘、医学影像合成、军用全景成像作战支持系统，以及民用全景相机等技术的提升具有十分重要的现实意义和明显的工程应用前景。
本文以单相机和多相机的环形运动获取的图像作为研究对象，深入研究了基于特征的全景图像拼接技术的理论和方法，针对当前全景图像拼接问题提出了一系列完整的解决方案，并对全景图像拼接所涉及的图像预处理、图像配准、图像定位、捆绑调整、图像测光优化、过渡区融合、全景投影输出等七个关键处理过程给出了详细的原理剖析和具体实现算法，最后通过C++语言设计并实现了全景图像拼接系统。
在图像预处理中，本文针对原始图像存在径向失真问题，对所用成像设备用张正友法标定来获取所需的相机内参数；以多项式法逼近成像设备的径向失真，用非线性迭代估计多项式系数来获取最优失真参数；然后再利用相机内参数和失真参数对原始图像进行校正，来获取无失真图像的方法，有效地解决了成像设备标定和图像径向失真校正的问题。
在图像配准中，本文针对不同成像设备、不同时间、不同视角获取的同一场景的多幅图像的匹配问题，围绕着基于特征的配准方案开展了深入的研究。首先引用图像不变矩改进了SIFT特征提取方法，并用之获取了图像的特征；然后利用Best Bin Firs（tBBF）搜索法获得初匹配集合，并给出了改进RANSAC算法和用之提纯初匹配集合；最后利用全相机运动投影变换模型和提纯后的匹配集合计算图像间的变换矩阵，完成图像配准。
针对图像级联变换带来的累积误差和所有图像投影（拼接）在全景图上的失真变形问题，本文以Levenberg-Marquardt（L-M）算法进行捆绑调整，有效地消除了图像级联累积误差和投影到全景图的失真变形。
针对不同图像间测光参数不同，带来的拼接后全景图整体亮度和颜色不均匀、不自然的问题，本文给出了新的测光调整技术，对全部图像间的整体亮度和颜色差异进行优化调整，达到了良好的图像测光调整效果。
图像融合主要用于解决因图像拼接部分的局部亮度差异造成的“拼接缝”和图像配准与捆绑调整误差带来的“鬼影”问题。文中，首先利用基于距离变换的方法找到最优缝合线，然后以小波多分辨率分析技术结合cos(x)平滑函数给出了新的多分辨率过渡区融合方法，取得了更好的消除拼接痕迹效果。
针对当前全景图格式单一，不能满足多领域需求的问题，文中讨论了6种常用投影方法，并给出了将全景图像以这6种常用投影格式进行输出的算法。
最后综合本文给出的改进全景图像拼接方法，使用C++语言，研究开发了全景图像拼接系统（automatic panoramic image mosaic system-APIMS）。该系统具有把以小视角相机获取的带有重叠区域的图像拼接成为360°视角的高质量全景图的能力。通过三组不同获取图像方法的实验表明，APIMS可实现通用性很强的高质量全景图像拼接，从而验证了本文给出的全景图像拼接方法的正确性和有效性。此外，本文还以一组包含主观和客观评价的对比实验，展示了本文给出的全景图像拼接方法比传统拼接方法在时间、效果和质量上具备的优势。本文设计完成的APIMS不但可用于地图测绘、医学影像合成、虚拟现实、计算机视觉等民用领域，经过适当修改后也可用于坦克、潜艇等需要全景作战支持系统的军用领域。
Panoramic image mosaic theory, techniques and methods is currently a hot topic inimage processing. It mainly solve the problem that due to the limited perspective of imagingequipment, the360-degree field of view image cannot be directly taken. This research canpromote the progress of land survey, medical image synthesis, panoramic images of militarycombat support systems, civil panoramic camera and other technologies. It has very greatpractical importance and significant engineering application perspective.
In this paper, the study object is the image obtained by a circular motion of a singlecamera and multi-camera. The theory and methods of the panoramic image stitchingtechnology based on the characteristics is studied in-depth. For the current problem onpanoramic image stitching, a series of complete solutions are proposed. Image preprocessing,image registration, image location, bundle adjustment, photometric optimization, transitionalzone fusion and panoramic projection involved in image mosaic is analyzed in detail andspecific realization algorithm is given. Finally a panoramic image mosaic system is designedand implemented using C++language.
For the radial distortion of the original image in the image pre-processing, parameters ofthe camera are obtained using Zhang zhengyou calibration method for imaging equipment;polynomial is used to approximate the radial distortion of imaging device with non-lineariterative estimation of polynomial coefficients to obtain the optimal distortion parameters;then the original image is corrected using the camera parameters and distortion parameters toobtain distortion-free images. The imaging device calibration and the correction of radialdistortion are effectively solved.
In image registration, feature-based registration is researched deeply for matchingproblems of multiple images of the same scene obtained by different imaging devices, atdifferent times and at different angles. SIFT feature extraction methods are improved usingimage invariant moments and the characteristics of the image is obtained; then using Best BinFirst (BBF) search method, a collection of the early matches are obtained and an improvedRANSAC algorithm is given; finally adopting the projection transformation model of thewhole camera movement and the the matching set after purification, transformation matrix iscalculated and image registration is complete.
For the cumulative error caused by image cascade transform and the problem ofdistortion and deformation involved in the projection (stitching) of all images on the panorama, bundle adjustment based on Levenberg-Marquardt (LM) algorithm effectivelyeliminates the accumulated error and deformation effect.
For the problem that since images have different photometric parameters, the wholepanorama after stitching has uneven and unnatural brightness and color, a new photometricadjustment technique is proposed. This method optimally adjusts overall brightness and colordifferences of all the images and achieves a good image photometric adjustment effect.
Image fusion is mainly used to solve the "seam-line" caused by local differences inbrightness in image stitching part and the "ghosting" caused by registration error inregistration and bundle adjustment. In this paper, the optimal stitch line is found using themethod based on distance transform. Then the wavelet multi-resolution analysis combinedwith cos (x) smooth function is adopted to achieve better stitching trace elimination effect.
For the problem that panorama has single format and cannot meet the needs ofmulti-domain, six commonly used projection methods are discussed in this paper and givesthe output algorithm of panoramic image using these six common projection format.
Finally, combined with the improved panoramic image stitching method, automaticpanoramic image mosaic system (automatic panoramic image mosaic system-APIMS) isresearched and realized programming in C++language. The system has the ability to stitchimages with overlapping regions from a small angle camera into high-quality360°panorama.The results of three group-experiment show that APIMS can achieve very versatile andhigh-quality panoramic image, which prove the accuracy and effectiveness of the proposedimproved panoramic image stitching method. A set of subjective and objective evaluation ofthe contrast experiments show that APIMS and the corresponding improved panoramic imagemosaic technique outperform than traditional stitching methods in time, effect and quality.Therefore, APIMS is suitable for not only mapping, medical imaging synthesis, virtual reality,computer vision and other civilian areas, but also military field of panoramic combat supportsystems such as tanks and submarines.
本文以单相机和多相机的环形运动获取的图像作为研究对象，深入研究了基于特征的全景图像拼接技术的理论和方法，针对当前全景图像拼接问题提出了一系列完整的解决方案，并对全景图像拼接所涉及的图像预处理、图像配准、图像定位、捆绑调整、图像测光优化、过渡区融合、全景投影输出等七个关键处理过程给出了详细的原理剖析和具体实现算法，最后通过C++语言设计并实现了全景图像拼接系统。
在图像预处理中，本文针对原始图像存在径向失真问题，对所用成像设备用张正友法标定来获取所需的相机内参数；以多项式法逼近成像设备的径向失真，用非线性迭代估计多项式系数来获取最优失真参数；然后再利用相机内参数和失真参数对原始图像进行校正，来获取无失真图像的方法，有效地解决了成像设备标定和图像径向失真校正的问题。
在图像配准中，本文针对不同成像设备、不同时间、不同视角获取的同一场景的多幅图像的匹配问题，围绕着基于特征的配准方案开展了深入的研究。首先引用图像不变矩改进了SIFT特征提取方法，并用之获取了图像的特征；然后利用Best Bin Firs（tBBF）搜索法获得初匹配集合，并给出了改进RANSAC算法和用之提纯初匹配集合；最后利用全相机运动投影变换模型和提纯后的匹配集合计算图像间的变换矩阵，完成图像配准。
针对图像级联变换带来的累积误差和所有图像投影（拼接）在全景图上的失真变形问题，本文以Levenberg-Marquardt（L-M）算法进行捆绑调整，有效地消除了图像级联累积误差和投影到全景图的失真变形。
针对不同图像间测光参数不同，带来的拼接后全景图整体亮度和颜色不均匀、不自然的问题，本文给出了新的测光调整技术，对全部图像间的整体亮度和颜色差异进行优化调整，达到了良好的图像测光调整效果。
图像融合主要用于解决因图像拼接部分的局部亮度差异造成的“拼接缝”和图像配准与捆绑调整误差带来的“鬼影”问题。文中，首先利用基于距离变换的方法找到最优缝合线，然后以小波多分辨率分析技术结合cos(x)平滑函数给出了新的多分辨率过渡区融合方法，取得了更好的消除拼接痕迹效果。
针对当前全景图格式单一，不能满足多领域需求的问题，文中讨论了6种常用投影方法，并给出了将全景图像以这6种常用投影格式进行输出的算法。
最后综合本文给出的改进全景图像拼接方法，使用C++语言，研究开发了全景图像拼接系统（automatic panoramic image mosaic system-APIMS）。该系统具有把以小视角相机获取的带有重叠区域的图像拼接成为360°视角的高质量全景图的能力。通过三组不同获取图像方法的实验表明，APIMS可实现通用性很强的高质量全景图像拼接，从而验证了本文给出的全景图像拼接方法的正确性和有效性。此外，本文还以一组包含主观和客观评价的对比实验，展示了本文给出的全景图像拼接方法比传统拼接方法在时间、效果和质量上具备的优势。本文设计完成的APIMS不但可用于地图测绘、医学影像合成、虚拟现实、计算机视觉等民用领域，经过适当修改后也可用于坦克、潜艇等需要全景作战支持系统的军用领域。
Panoramic image mosaic theory, techniques and methods is currently a hot topic inimage processing. It mainly solve the problem that due to the limited perspective of imagingequipment, the360-degree field of view image cannot be directly taken. This research canpromote the progress of land survey, medical image synthesis, panoramic images of militarycombat support systems, civil panoramic camera and other technologies. It has very greatpractical importance and significant engineering application perspective.
In this paper, the study object is the image obtained by a circular motion of a singlecamera and multi-camera. The theory and methods of the panoramic image stitchingtechnology based on the characteristics is studied in-depth. For the current problem onpanoramic image stitching, a series of complete solutions are proposed. Image preprocessing,image registration, image location, bundle adjustment, photometric optimization, transitionalzone fusion and panoramic projection involved in image mosaic is analyzed in detail andspecific realization algorithm is given. Finally a panoramic image mosaic system is designedand implemented using C++language.
For the radial distortion of the original image in the image pre-processing, parameters ofthe camera are obtained using Zhang zhengyou calibration method for imaging equipment;polynomial is used to approximate the radial distortion of imaging device with non-lineariterative estimation of polynomial coefficients to obtain the optimal distortion parameters;then the original image is corrected using the camera parameters and distortion parameters toobtain distortion-free images. The imaging device calibration and the correction of radialdistortion are effectively solved.
In image registration, feature-based registration is researched deeply for matchingproblems of multiple images of the same scene obtained by different imaging devices, atdifferent times and at different angles. SIFT feature extraction methods are improved usingimage invariant moments and the characteristics of the image is obtained; then using Best BinFirst (BBF) search method, a collection of the early matches are obtained and an improvedRANSAC algorithm is given; finally adopting the projection transformation model of thewhole camera movement and the the matching set after purification, transformation matrix iscalculated and image registration is complete.
For the cumulative error caused by image cascade transform and the problem ofdistortion and deformation involved in the projection (stitching) of all images on the panorama, bundle adjustment based on Levenberg-Marquardt (LM) algorithm effectivelyeliminates the accumulated error and deformation effect.
For the problem that since images have different photometric parameters, the wholepanorama after stitching has uneven and unnatural brightness and color, a new photometricadjustment technique is proposed. This method optimally adjusts overall brightness and colordifferences of all the images and achieves a good image photometric adjustment effect.
Image fusion is mainly used to solve the "seam-line" caused by local differences inbrightness in image stitching part and the "ghosting" caused by registration error inregistration and bundle adjustment. In this paper, the optimal stitch line is found using themethod based on distance transform. Then the wavelet multi-resolution analysis combinedwith cos (x) smooth function is adopted to achieve better stitching trace elimination effect.
For the problem that panorama has single format and cannot meet the needs ofmulti-domain, six commonly used projection methods are discussed in this paper and givesthe output algorithm of panoramic image using these six common projection format.
Finally, combined with the improved panoramic image stitching method, automaticpanoramic image mosaic system (automatic panoramic image mosaic system-APIMS) isresearched and realized programming in C++language. The system has the ability to stitchimages with overlapping regions from a small angle camera into high-quality360°panorama.The results of three group-experiment show that APIMS can achieve very versatile andhigh-quality panoramic image, which prove the accuracy and effectiveness of the proposedimproved panoramic image stitching method. A set of subjective and objective evaluation ofthe contrast experiments show that APIMS and the corresponding improved panoramic imagemosaic technique outperform than traditional stitching methods in time, effect and quality.Therefore, APIMS is suitable for not only mapping, medical imaging synthesis, virtual reality,computer vision and other civilian areas, but also military field of panoramic combat supportsystems such as tanks and submarines.
引文
[1] Milgram, D. L.. Computer methods for creating photomosaics[J]. IEEE Transactions onComputers,1975,24(11):1113–1119
[2] Brown J.A., Ashlock D., Orth J., Houghten S.. Autogeneration of fractal photographicmosaic images[C].2011IEEE Congress of Evolutionary Computation,2011:1116-1123
[3] Leonard McMillan, Gary Bishop. Plenoptic modeling: an image-based renderingsystem[C]. Pro. of the22nd annual conference on Computer graphics and interactivetechniques,1995:39-46
[4] Wang Haiying, Qin Kaihuai. Construction of panoramic image mosaics based on affinetransform and graph cut[C]. International Conference on Image Processing and PatternRecognition in Industrial Engineering,2010:1-6
[5] Kweon Gyeong il, Choi Young ho. Image-processing based panoramic camera employingsingle fisheye lens[J]. Journal of the Optical Society of Korea,2010,14(3):245-259
[6] Lin na LI, Nan GENG. Algorithm for Sequence Image Automatic Mosaic based on SIFTFeature[C]. WASE International Conference on Information Engineering,2010:203-206
[7] Ho Sean, David Philip. Automatic Generation of360°Panorama from Image Sequences[C].Proceedings of the SPIE on Applications of Digital Image Processing.2008:1-9
[8] Xiong, Y., K. Pulli. Fast panorama stitching for high-quality panoramic images on mobilephones[J]. IEEE Transactions on Consumer Electronics,2010,56(2):298-306
[9] Li J., J. Du. Study on panoramic image stitching algorithm[C]. Proceedings of the2ndPacific-Asia Conference on Circuits, Communications and System,2010:417-420
[10]张赢,汪荣峰,廖学军.数字地图图幅接边的虚拼接算法[J].计算机工程与设计,2010,31(16):3640-3643
[11]张传胜,邵春雷.人眼像差校正仪视网膜微血管图像拼接[J].液晶与显示,2011,25(6):884-889
[12] Soper Timothy D., Chandler John E., Porter Michael P., Seibel Eric J.. Constructingspherical panoramas of a bladder phantom from endoscopic video using bundleadjustment[C]. Progress in Biomedical Optics and Imaging-Proceedings of SPIE,2011:1-12
[13]赵毅力,徐丹.基于全景图像的虚拟漫游系统研究[J].计算机与现代化,2011,16(6):11-14
[14] Arif W.N.W.A., Ahmad W.F.W., Nordin S.M.. Applying virtual reality panoramasimulation environment in technical communication[C]. Information TechnologyInternational Symposium,2010:1-5
[15] Jacques Laurent, Duval Laurent, Chaux Caroline, Peyré, Gabriel. A panorama onmultiscale geometric representations, intertwining spatial, directional and frequencyselectivity[J]. Signal Processing,2011,91(12):2699-2730
[16] Kuglin, Hines. The phase correction image alignment method[C]. Proceedings of IEEEInternational Conference on Cybernetices and Society,1975:163-165
[17] Alliney S., Morandi C.. Digital image registration using projections[J]. IEEE Transactionon Pattern Analysis and Machine Intelligence,1986,8(2):222-233
[18] Reddy B.S., Chatterji B.N.. An fft-based technique for transaction, rotation, and scaleinvariant image registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[19]李中科,吴乐南.基于霍夫变换和相位相关的图像配准方法[J].信号处理,2004,20(2):166-169
[20]李忠新,茅耀斌,王执铨.基于对数极坐标映射的图像拼接方法[J].中国图象图形学报,2005,10(1):59-63
[21]方俊伟,翟超,金熠.相位相关法实现图像拼接的仿真和优化[J].计算机应用与软件,2008,25(1):207-208
[22] Zhang Z., Deriche R., Faugeras O., Luong Q.T., A robust technique for matching twouncalibrated images through the recovery of the unknown epipolar geometry[J].Artificial Intelligence Journal,1995,78:87-119
[23] Szeliski R.. Video mosaics for virtual environments[J]. IEEE Computer Graphics andApplications,1996,16(2):16-20
[24] McMillan L., Bishop G.. Plenoptic modeling: An image-based rendering system[C].Computer Graphics (SIGGRAPH'95),1995:39–46
[25] Zokai S., Wolberg G.. Image Registration Using Log-Polar Mappings for Recovery ofLarge-Scale Similarity and Projective Transformations[J]. IEEE Transactions on ImageProcessing,2005,14(10):1422-1434
[26] Chen S.E.. QuickTime VR-an image-based approach to virtual environmentnavigation.[C]. Computer Graphics (SIGGRAPH'95),1995:29–38
[27]蒋晓瑜,黄应清.基于小波变换的多分辨模板匹配[J].中国图象图形学报,2000,5(4):304-308
[28]罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970
[29]李志刚,纪玉波,薛全.边界重叠图象的一种快速拼接算法[J].计算机工程,2000,26(5):37-38
[30] Beymer D., Shashua A.,Poggio T.. Example Based Image Analysis and Synthesis[C]. A.I. Memo1431, Massachusetts Institute of Technology,1993:1-20.
[31] Szeliski R.. Image mosaicing for tele-reality applications[C]. lEEE Computer Society onApplications of ComputerVision,1994:44-53
[32] Zoghlami I., Faugeras O., Deriche, R.. Using geometric corners to build a2D mosaicfrom a set of images[C]. In IEEE Computer Society Conference on Computer Visionand Pattern Recognition,1997:420–425
[33] Capel D., Zisserman A.. Automated mosaicing with super-resolution zoom[C]. In IEEEComputer Society Conference on Computer Vision and Pattern Recognition,1998:885–891
[34] McLauchlan P.F., Jaenicke A.. Image mosaicing using sequential bundle adjustment[J].Image and Vision Computing,2002,20(9-10):751–759
[35] Triggs B. et al.. Bundle adjustment-a modern synthesis[C]. In International Workshop onVision Algorithms,1999:298–372
[36] Handmann U., Leefken I., Seelen W.v.. Scene Interpretation and behavior planning fordriver assistance[C]. In Enhanced and Synthetic Vision,2000:201-212
[37]肖昕,李岩.中值滤波均值快速算法在高光谱图像处理系统中的应用[J].微计算机应用,2005,26(02):129-132
[38] Burt P.J., Adelson E.H.. A multiresolution spline with applications to imagemosaics[J].ACM Transactions on Graphics,1983,2(4):217-236
[39] Daubechies I.. Ten lectures on wavelets[M]. Number61in CBMS-NSF Series in AppliedMathematics. SIAM, Philadelphia,1992:1-80
[40] Nercessian S., Panetta K.,Agaian S.. Image fusion using the Parameterized LogarithmicDual Tree Complex Wavelet Transform[C]. IEEE International Conference onTechnologies for Homeland Security,2010:296-302
[41] Sekhar A. S., Prasad M. N.. A novel approach of image fusion on MR and CT imagesusing wavelet transforms[C]. Int. Conf. Electron. Comput. Technol,2011:172-176
[42] Jing Yuanshu, Zhang Huijun, Wang Jin, Li Yacun, Toshiaki Ichinose. Image fusion usingwavelet transforms for monitoring eutrophication of taihu lake in china. Int. WorkshopEduc. Technol. Train. Int. Workshop Geosci. Remote Sens.,2008:210-213
[43] Brown M., Lowe D.. Recognizing panoramas[C]. In Ninth International Conference onComputer Vision,2003:1218–1225
[44]李艳丽,向辉.稳健的球面全景图全自动生成算法[J].计算机辅助设计与图形学学报,2007,19(11):1393-1398
[45]高超,张鑫,王云丽.一种基于SIFT特征的航拍图像序列自动拼接方法[J].计算机应用,2007,27(11):2789-2792
[46]杨艳伟,郭宝龙.柱面全景图像自动拼接算法[J].计算机工程与应用,2009,45(9):171-173
[47] Brown M., Lowe D.G.. Automatic panoramic image stitching using invariant features[J].Int. J. Comput. Vision,2007,74(1):59-73
[48] Arfaoui Aymen, Plante France. Camera calibration using composed cubic splines[J].Geomatica,2011,65(2):189-197
[49] Draréni Jamil, Roy Sébastien, Sturm Peter. Plane-based calibration for linear cameras[J].International Journal of Computer Vision,2011,91(2):146-156
[50] Ricolfe Viala Carlos, Sánchez Salmerón Antonio José. Using the camera pin-hole modelrestrictions to calibrate the lens distortion model[J]. Optics and Laser Technology,2011,43(6):996-1005
[51] Brauers Johannes, Aach Til. Geometric calibration of lens and filter distortions formultispectral filter-wheel cameras[J]. Optics and Laser Technology,2011,20(2):496-506
[52] Bogre, Michelle. Pinhole Revival[M]. Popular Photography,1988:216-220
[53]马颂德,张正友.计算机视觉一计算理论与算法基础[M].北京:科学出版社,1998:37-44
[54] Wei G., Ma S.. Implicit and explicit camera calibration: Theory and experiments[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(5):469–480
[55] Luong Q.T., Faugerasv O.. Self-calibration of a moving camera from pointcorrespondences and fundamental matrices[J]. The International Journal of ComputerVision,1997,22(3):261–289
[56] Zhang Z.. A flexible new technique for camera calibration[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330–1334
[57] Espuny Ferran, Aranda Joan, Burgos Gil José I.. Camera self-calibration with parallelscrew axis motion by intersecting imaged horopters[C]. Lecture Notes in ComputerScience,2011:1-12
[58] Lichti Derek D., Kim Changjae. A comparison of three geometric self-calibrationmethods for range cameras[J]. Remote Sensing,2011,3(5):1014-1028
[59] Faig W.. Calibration of close-range photogrammetry systems: Mathematicalformulation[J]. Photogrammetric Engineering and Remote Sensing,1975,41(12):1479–1486
[60] Faugeras O., Toscani G.. The calibration problem for stereo[C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition,1986:15–20
[61] More J.. The levenberg-marquardt algorithm, implementation and theory[C]. In LectureNotes in Mathematics630: Numerical Analysis,1978:105-116:
[62] Nomura Y., Sagara M., H. Naruse, A. Ide. Simple calibration algorithm for highdistortionlens camera[J]. IEEE PAMI,1992,14(11):1095–1099
[63] Hartley R.I., Zisserman A.. Multiple View Geometry in Computer Vision[M]. CambridgeUniversity Press,2004:178-193
[64] Alvarez L., Gómez L., Sendra J.R.. An Algebraic Approach to Lens Distortion by LineRectification[J]. Journal of Mathematical Imaging and Vision,2008,35(1):36-50
[65] Steele J.M.. The Cauchy Schwarz Master Class[M]. Cambridge University Press,2004.
[66] Sawhney H., Kumar R.. True multi-image alignment and its application to mosaicing andlens distortion correction[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1999,21(3):235–243
[67] Duraisamy Prakash, Shen Yao, Yuan Xiaohui. Image registration error analysis usingpattern recognition algorithms[C]. The International Society for Optical Engineering,2010:1-9
[68] Murray Paul, Marshall Stephen. A new design tool for feature extraction in noisy imagesbased on grayscale hit-or-miss transforms[J]. IEEE Transactions on Image Processing,2011,20(7):1938-1948
[69] Koenderink J., van Doorn A.. Representation of Local Geometry in the Visual System[J].Biological Cybernetics,1987,55(6):367-375
[70] Freeman W., Adelson E.. The Design and Use of Steerable Filters[J]. IEEE Trans. PatternAnalysis and Machine Intelligence,1991,13(9):891-906
[71] Van Gool L., Moons T., D. Ungureanu. Affine/Photometric Invariants for Planar IntensityPatterns[C]. Proc. Fourth European Conf. Computer Vision,1996:642-651
[72] Belongie S., Malik J., J. Puzicha. Shape Matching and Object Recognition Using ShapeContexts[J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,2(4):509-522
[73] Schaffalitzky F., ZissermanA.. Multi-View Matching for Unordered Image Sets[C]. Proc.Seventh European Conf. Computer Vision,2002:414-431
[74] Lazebnik S., Schmid C., Ponce J.. Sparse Texture Representation Using Affine-InvariantNeighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition,2003:319-324
[75] Mikolajczyk K., Schmid C.. Scale and Affine Invariant Interest Point Detectors[J]. Int'l J.Computer Vision,2004,1(60):63-86
[76] Mikolajczyk K., Schmid C.. A performance evaluation of local descriptors[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27:1615–1630
[77] Harris C., Stephens M.. A Combined Corner and Edge Detector[C]. Proc. Alvey VisionConf.,1988:147-151
[78] Lowe D.. Object Recognition from Local Scale-Invariant Features[C]. Proc. Seventh Int'lConf. Computer Vision,1999:1150-1157
[79] Lowe D.. Distinctive Image Features from Scale-Invariant Keypoints[J]. Int'l J.Computer Vision,2004,2(60):91-110
[80] Khalifa Mahmoud, Bingru Yang, Mohammed Ammar. A robust SIFT feature for fastoffline arabic words classification[C]. IEEE International Conference on ComputerScience and Automation Engineering,2011:83-86
[81]冯炜．图像场景分类的关键技术研究．北京：北京交通大学硕士论文，2008:14-19
[82] Koenderink J.J.. The structure of images[J]. Biological Cybernetics,1984,50(5):363-396
[83] Lindeberg, T.. Scale-space theory: A basic tool for analysing structures at differentscales[J]. Journal of Applied Statistics,1994,21(2):224-270
[84] Lee Taehee, Soatto Stefano. Feature tracking and object recognition on a hand-held[C].9th IEEE International Symposium on Mixed and Augmented Reality2010: Scienceand Technology,2011:1-5
[85] Bentley J.. Multidimensional binary search trees used for associative searching[C].Commun. ACM18,1975:509-517
[86]徐望明．基于内容的图像检索技术研究．武汉：武汉科技大学硕士论文，2008:20-25
[87] Beis Jeff, Lowe D.G.. Shape indexing using approximate nearest-neighbour search inhigh-dimensional spaces[C]. Conference onComputerVision and PatternRecognition,1997:1000–1006
[88] Szeliski R.. Image alignment and stitching: A Tutorial[R]. Technical ReportMSR-TR-2004-92. Microsoft Research2004
[89]胡志萍．图像特征提取、匹配和新视点图像生成技术研究．大连：大连理工大学博士论文，2005:10-15,54
[90] Hartley R.I.. Estimation of Relative Camera Positions for Uncalibrated Cameras[C].Proceedings of the Second European Conference on Computer Vision,1992:579-587
[91] Fischler M.A., Bolles R.C.. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography. Comm. of the ACM,1981,24(6):381–395
[92] Brown D.C.. The bundle adjustment-progress and prospects[J]. Int. ArchivesPhotogrammetry,1976,21(3):1-33
[93] Granshaw S.. Bundle adjustment methods in engineering photogrammetry[J].Photogrammetric Record,1980,10(56):181–207
[94] Cooper M.A.R., Cross P.A.. Statistical concepts and their application in photogrammetryand surveying[J]. Photogrammetric Record,1988,12(71):637–663
[95] Cooper M.A.R.,Cross P.A.. Statistical concepts and their application inphotogrammetry and surveying (continued)[J]. Photogrammetric Record,1991,13(77):645–678
[96] Hartley R.I., A. Zisserman. Multiple View Geometry in Computer Vision[M]. CambridgeUniversity Press,2004:434-456
[97] HIEBERT K.. An evaluation of mathematical software that solves nonlinear least squaresproblems[J]. ACM Transactions on Mathematical Software.1981,7(1):1–16
[98] Soper Timothy D., Chandler John E., Porter Michael P., Seibel Eric J.. Constructingspherical panoramas of a bladder phantom from endoscopic video using bundleadjustment[C]. Progress in Biomedical Optics and Imaging,2011:1-12
[99] Fang Xianyong, Pan Zhigeng, Luo Bin, Wu Fuli, Guo Sanhua. Robust image mosaicwith RANSAC and bundle adjustment[C]. Journal of Computational InformationSystems,2008,4(4):1613-1619
[100] LEVENBERG K.. A method for the solution of certain non-linear problems in leastsquares[J]. The Quarterly of Applied Mathematics,1944,2(2):164–168
[101] MARQUARDT D.. An algorithm for the least-squares estimation of nonlinearparameters[J]. SIAM J. Appl. Math,1963,11(2):431–441.
[102] Yang Shanxiao, Yang Guangying. Emotion recognition of EMG based on improvedL-M BP neural network and SVM[J]. Journal of Software,2011,6(8):1529-1536
[103] Gao Junhong, Kim Seon Joo, Brown Michael S.. Constructing image panoramas usingdual-homography warping[C]. Proceedings of the IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition,2011:49-56
[104]王雷斌．基于计算机视觉的图像拼接技术研究．北京：首都师范大学博士论文，2008:45-49
[105] Gormer Steffen, Hold Stephanie, Kummert Anton, Iurgel Uri, Meuter Mirko.Multi-Exposure Image Acquisition for Automotive High Dynamic Range Imaging [C].IEEE Conference on Intelligent Transportation Systems,2010:1881-1886
[106] Yu Hongsheng, Jin Weiqi. Brightness adaptive algorithm for image mosaic seamlessfusion[C]. The International Society for Optical Engineering,2010:1-9
[107] Bao Paul. Image mosaics with wavelet domain seam-lines[C]. IEEE Symposium onComputers and Informatics,2011:419-424
[108] Weiss Kenneth, De Floriani Leila, Mesmoudi Mohammed Mostefa. Multiresolutionanalysis of3D images based on discrete distortion[C]. International Conference onPattern Recognition,2010:4093-4096
[109] Pan Jun, Wang Mi. A seam-line optimized method based on difference image andgradient image[C].19th International Conference on Geoinformatics,2011:1-6
[110] Levin A., Zomet A., Peleg S., Weiss Y.. Seamless Image Stitching in the GradientDomain[C]. In Proceedings of ECCV,2004:377-389
[111] Pousset P., Duplaquet M.L.. SPOT image mosaic and dynamic programming[C].Proc.EUSIPCO,1990:1854-1861
[112] Duplaquet M.L.. Building large image mosaics with invisible seam-lines[C]. In Proc.SPIE AeroSence,1998:369-377
[113] Alexei A., Efros, William T., Freeman. Image quilting for texture synthesis andtransfer[C]. Proceedings of SIGGRAPH,2001:2341-346
[114] Avidan S., Shamir A.. Seam Carving for Content-Aware Image Resizing[J]. ACMTransactions on Graphics,2007,26(3):1-9
[115] Bellman R., Kalaba R.. Dynamic programming and modern control theory[M].Academic Press Inc.,1965:236-242
[116] Thomas H.. Map projections and airborne moving map displays[C]. Digital AvionicsSystems Conference of IEEE/AIAA,1991:493-498
[117] Wang Jiechen, Chen Yanming, Li Li, Li Lifan. The Module Design of Map ProjectionTransformation Based on Object-Oriented[C]. International Forum on InformationTechnology and Applications,2009:574-578
[118] Lee L.P. The Nomenclature and Classification of Map Projections[M]. Empire SurveyRev7,1944:190-200
[119] Brosz J, Samavati F.. Shape Defined Panoramas[C]. Shape Modeling InternationalConference,2010:57-67
[120] Beom Su Kim, Hyung Il Koo, Nam Ik Cho. A new image projection method forpanoramic image stitching[C]. IEEE International Workshop on Multimedia SignalProcessing,2010:128-132
[121] Ni K.S., Nguyen T.Q.. Adaptable K-nearest neighbor for image interpolation[C]. EEEInternational Conference on Acoustics, Speech and Signal Processing,2008:1297-1300
[122] Heechang Kim, Soonjong Jin, Siyoung Yang, Jechang Jeong. Enhanced Edge-WeightedImage Interpolation Algorithm[C]. Eighth International Conference on HybridIntelligent Systems,2008:957-958
[123] Mihajlovic Z., Goluban A., Zagar M.. Frequency domain analysis of B-splineinterpolation[C]. Proceedings of the IEEE International Symposium on IndustrialElectronics,1999:193-198
[124] Akhtar P., Azhar F.. A Single Image Interpolation Scheme for Enhanced SuperResolution in Bio-Medical Imaging[C].4th International Conference on Bioinformaticsand Biomedical Engineering,2010:1-5
[125] Lehmann T.M., Gonner C., Spitzer K.. Survey: interpolation methods in medical imageprocessing[J]. IEEE Transactions on Medical Imaging,1999,18(11):1049-1075
[126] Can A., Stewart C.V., Roysam B., Tanenbaum H.L.. A Feature-based Technique for joint,linear estimation of high-order image-to-mosaic transformations. IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(3):412-419
[127] HU M.K.. Visual pattern recognition by moment invariants, IRE Trans Inf Theory,1962,8(2):179-187
[128] José Torre o R.A., Jo o Fernandes L.. Linear-nonlinear neuronal model for shape fromshading[C]. Pattern Recognition Letters,2011:1223-1239
[129] Li Zhaoqi, Niu Ling, Gao Chengying. Linear-nonlinear neuronal model for shape fromshading[C].3rd International Congress on Image and Signal Processing,2010:830-834
[130] Park Kee-Hyon, Park Dae-Geun, Ha Yeong-Ho. High dynamic range image acquisitionfrom multiple low dynamic range images based on estimation of scene dynamicrange[J]. Journal of Imaging Science and Technology,2009,53(2):1-12
[131] Grossberg M., Nayar S.. Modeling the Space of Camera Response Functions[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2004,26(10):1272-1282
[132] Johne B.. Digital Image Processing[M]. Springer,2002:197-200
[133] Mitsunaga, T., Nayar S.. Radiometric Self Calibration[C]. In: IEEE Conference onComputer Vision and Pattern Recognition.1999:374-380
[134] Goldman D.B., Chen J.H.. Vignette and exposure calibration and compensation[C]. InThe10th IEEE International Conference on Computer Vision,2005:899-906
[135] Litvinov A., Schechner Y.Y.. Radiometric framework for image mosaicking[J]. J. Opt.Soc. Am.,2005,22(5):839-848
[136] Grossberg M., Nayar S.. Determining the Camera Response from Images: What isKnowable?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1455-1467
[137] Rosenfeld A., Pfaltz J.L.. Sequential operations in digital picture processing[J]. Journalof the Association for Computing Machinery,1966,13(4):471-494
[138] Kenneth R. castleman. Digital Image Processing[M]. New Jersey: Prentice Hall,1996:475-477
[139] Garg Girisha, Singh Vijander, Gupta J.R.P., Mittal A.P.. Optimal algorithm for ECGdenoising using Discrete Wavelet Transforms[C]. IEEE International Conference onComputational Intelligence and Computing Research,2010:577-580
[140] Coxeter H.S.M.. Introduction to Geometry[M].2nd ed. New York: Wiley,1969:93,289-290
[141] Pearson F.. Map Projections: Theory and Applications[M]. Boca Raton, FL: CRC Press,1990:195-196
[142] Snyder J.P.. Map Projections-A Working Manual[M]. U.S. Geological SurveyProfessional Paper1395. Washington, DC: U.S. Government Printing Office,1987:243-248
[2] Brown J.A., Ashlock D., Orth J., Houghten S.. Autogeneration of fractal photographicmosaic images[C].2011IEEE Congress of Evolutionary Computation,2011:1116-1123
[3] Leonard McMillan, Gary Bishop. Plenoptic modeling: an image-based renderingsystem[C]. Pro. of the22nd annual conference on Computer graphics and interactivetechniques,1995:39-46
[4] Wang Haiying, Qin Kaihuai. Construction of panoramic image mosaics based on affinetransform and graph cut[C]. International Conference on Image Processing and PatternRecognition in Industrial Engineering,2010:1-6
[5] Kweon Gyeong il, Choi Young ho. Image-processing based panoramic camera employingsingle fisheye lens[J]. Journal of the Optical Society of Korea,2010,14(3):245-259
[6] Lin na LI, Nan GENG. Algorithm for Sequence Image Automatic Mosaic based on SIFTFeature[C]. WASE International Conference on Information Engineering,2010:203-206
[7] Ho Sean, David Philip. Automatic Generation of360°Panorama from Image Sequences[C].Proceedings of the SPIE on Applications of Digital Image Processing.2008:1-9
[8] Xiong, Y., K. Pulli. Fast panorama stitching for high-quality panoramic images on mobilephones[J]. IEEE Transactions on Consumer Electronics,2010,56(2):298-306
[9] Li J., J. Du. Study on panoramic image stitching algorithm[C]. Proceedings of the2ndPacific-Asia Conference on Circuits, Communications and System,2010:417-420
[10]张赢,汪荣峰,廖学军.数字地图图幅接边的虚拼接算法[J].计算机工程与设计,2010,31(16):3640-3643
[11]张传胜,邵春雷.人眼像差校正仪视网膜微血管图像拼接[J].液晶与显示,2011,25(6):884-889
[12] Soper Timothy D., Chandler John E., Porter Michael P., Seibel Eric J.. Constructingspherical panoramas of a bladder phantom from endoscopic video using bundleadjustment[C]. Progress in Biomedical Optics and Imaging-Proceedings of SPIE,2011:1-12
[13]赵毅力,徐丹.基于全景图像的虚拟漫游系统研究[J].计算机与现代化,2011,16(6):11-14
[14] Arif W.N.W.A., Ahmad W.F.W., Nordin S.M.. Applying virtual reality panoramasimulation environment in technical communication[C]. Information TechnologyInternational Symposium,2010:1-5
[15] Jacques Laurent, Duval Laurent, Chaux Caroline, Peyré, Gabriel. A panorama onmultiscale geometric representations, intertwining spatial, directional and frequencyselectivity[J]. Signal Processing,2011,91(12):2699-2730
[16] Kuglin, Hines. The phase correction image alignment method[C]. Proceedings of IEEEInternational Conference on Cybernetices and Society,1975:163-165
[17] Alliney S., Morandi C.. Digital image registration using projections[J]. IEEE Transactionon Pattern Analysis and Machine Intelligence,1986,8(2):222-233
[18] Reddy B.S., Chatterji B.N.. An fft-based technique for transaction, rotation, and scaleinvariant image registration[J]. IEEE Transaction on Image Processing,1996,5(8):1266-1271
[19]李中科,吴乐南.基于霍夫变换和相位相关的图像配准方法[J].信号处理,2004,20(2):166-169
[20]李忠新,茅耀斌,王执铨.基于对数极坐标映射的图像拼接方法[J].中国图象图形学报,2005,10(1):59-63
[21]方俊伟,翟超,金熠.相位相关法实现图像拼接的仿真和优化[J].计算机应用与软件,2008,25(1):207-208
[22] Zhang Z., Deriche R., Faugeras O., Luong Q.T., A robust technique for matching twouncalibrated images through the recovery of the unknown epipolar geometry[J].Artificial Intelligence Journal,1995,78:87-119
[23] Szeliski R.. Video mosaics for virtual environments[J]. IEEE Computer Graphics andApplications,1996,16(2):16-20
[24] McMillan L., Bishop G.. Plenoptic modeling: An image-based rendering system[C].Computer Graphics (SIGGRAPH'95),1995:39–46
[25] Zokai S., Wolberg G.. Image Registration Using Log-Polar Mappings for Recovery ofLarge-Scale Similarity and Projective Transformations[J]. IEEE Transactions on ImageProcessing,2005,14(10):1422-1434
[26] Chen S.E.. QuickTime VR-an image-based approach to virtual environmentnavigation.[C]. Computer Graphics (SIGGRAPH'95),1995:29–38
[27]蒋晓瑜,黄应清.基于小波变换的多分辨模板匹配[J].中国图象图形学报,2000,5(4):304-308
[28]罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970
[29]李志刚,纪玉波,薛全.边界重叠图象的一种快速拼接算法[J].计算机工程,2000,26(5):37-38
[30] Beymer D., Shashua A.,Poggio T.. Example Based Image Analysis and Synthesis[C]. A.I. Memo1431, Massachusetts Institute of Technology,1993:1-20.
[31] Szeliski R.. Image mosaicing for tele-reality applications[C]. lEEE Computer Society onApplications of ComputerVision,1994:44-53
[32] Zoghlami I., Faugeras O., Deriche, R.. Using geometric corners to build a2D mosaicfrom a set of images[C]. In IEEE Computer Society Conference on Computer Visionand Pattern Recognition,1997:420–425
[33] Capel D., Zisserman A.. Automated mosaicing with super-resolution zoom[C]. In IEEEComputer Society Conference on Computer Vision and Pattern Recognition,1998:885–891
[34] McLauchlan P.F., Jaenicke A.. Image mosaicing using sequential bundle adjustment[J].Image and Vision Computing,2002,20(9-10):751–759
[35] Triggs B. et al.. Bundle adjustment-a modern synthesis[C]. In International Workshop onVision Algorithms,1999:298–372
[36] Handmann U., Leefken I., Seelen W.v.. Scene Interpretation and behavior planning fordriver assistance[C]. In Enhanced and Synthetic Vision,2000:201-212
[37]肖昕,李岩.中值滤波均值快速算法在高光谱图像处理系统中的应用[J].微计算机应用,2005,26(02):129-132
[38] Burt P.J., Adelson E.H.. A multiresolution spline with applications to imagemosaics[J].ACM Transactions on Graphics,1983,2(4):217-236
[39] Daubechies I.. Ten lectures on wavelets[M]. Number61in CBMS-NSF Series in AppliedMathematics. SIAM, Philadelphia,1992:1-80
[40] Nercessian S., Panetta K.,Agaian S.. Image fusion using the Parameterized LogarithmicDual Tree Complex Wavelet Transform[C]. IEEE International Conference onTechnologies for Homeland Security,2010:296-302
[41] Sekhar A. S., Prasad M. N.. A novel approach of image fusion on MR and CT imagesusing wavelet transforms[C]. Int. Conf. Electron. Comput. Technol,2011:172-176
[42] Jing Yuanshu, Zhang Huijun, Wang Jin, Li Yacun, Toshiaki Ichinose. Image fusion usingwavelet transforms for monitoring eutrophication of taihu lake in china. Int. WorkshopEduc. Technol. Train. Int. Workshop Geosci. Remote Sens.,2008:210-213
[43] Brown M., Lowe D.. Recognizing panoramas[C]. In Ninth International Conference onComputer Vision,2003:1218–1225
[44]李艳丽,向辉.稳健的球面全景图全自动生成算法[J].计算机辅助设计与图形学学报,2007,19(11):1393-1398
[45]高超,张鑫,王云丽.一种基于SIFT特征的航拍图像序列自动拼接方法[J].计算机应用,2007,27(11):2789-2792
[46]杨艳伟,郭宝龙.柱面全景图像自动拼接算法[J].计算机工程与应用,2009,45(9):171-173
[47] Brown M., Lowe D.G.. Automatic panoramic image stitching using invariant features[J].Int. J. Comput. Vision,2007,74(1):59-73
[48] Arfaoui Aymen, Plante France. Camera calibration using composed cubic splines[J].Geomatica,2011,65(2):189-197
[49] Draréni Jamil, Roy Sébastien, Sturm Peter. Plane-based calibration for linear cameras[J].International Journal of Computer Vision,2011,91(2):146-156
[50] Ricolfe Viala Carlos, Sánchez Salmerón Antonio José. Using the camera pin-hole modelrestrictions to calibrate the lens distortion model[J]. Optics and Laser Technology,2011,43(6):996-1005
[51] Brauers Johannes, Aach Til. Geometric calibration of lens and filter distortions formultispectral filter-wheel cameras[J]. Optics and Laser Technology,2011,20(2):496-506
[52] Bogre, Michelle. Pinhole Revival[M]. Popular Photography,1988:216-220
[53]马颂德,张正友.计算机视觉一计算理论与算法基础[M].北京:科学出版社,1998:37-44
[54] Wei G., Ma S.. Implicit and explicit camera calibration: Theory and experiments[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(5):469–480
[55] Luong Q.T., Faugerasv O.. Self-calibration of a moving camera from pointcorrespondences and fundamental matrices[J]. The International Journal of ComputerVision,1997,22(3):261–289
[56] Zhang Z.. A flexible new technique for camera calibration[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,2000,22(11):1330–1334
[57] Espuny Ferran, Aranda Joan, Burgos Gil José I.. Camera self-calibration with parallelscrew axis motion by intersecting imaged horopters[C]. Lecture Notes in ComputerScience,2011:1-12
[58] Lichti Derek D., Kim Changjae. A comparison of three geometric self-calibrationmethods for range cameras[J]. Remote Sensing,2011,3(5):1014-1028
[59] Faig W.. Calibration of close-range photogrammetry systems: Mathematicalformulation[J]. Photogrammetric Engineering and Remote Sensing,1975,41(12):1479–1486
[60] Faugeras O., Toscani G.. The calibration problem for stereo[C]. In Proceedings of theIEEE Conference on Computer Vision and Pattern Recognition,1986:15–20
[61] More J.. The levenberg-marquardt algorithm, implementation and theory[C]. In LectureNotes in Mathematics630: Numerical Analysis,1978:105-116:
[62] Nomura Y., Sagara M., H. Naruse, A. Ide. Simple calibration algorithm for highdistortionlens camera[J]. IEEE PAMI,1992,14(11):1095–1099
[63] Hartley R.I., Zisserman A.. Multiple View Geometry in Computer Vision[M]. CambridgeUniversity Press,2004:178-193
[64] Alvarez L., Gómez L., Sendra J.R.. An Algebraic Approach to Lens Distortion by LineRectification[J]. Journal of Mathematical Imaging and Vision,2008,35(1):36-50
[65] Steele J.M.. The Cauchy Schwarz Master Class[M]. Cambridge University Press,2004.
[66] Sawhney H., Kumar R.. True multi-image alignment and its application to mosaicing andlens distortion correction[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1999,21(3):235–243
[67] Duraisamy Prakash, Shen Yao, Yuan Xiaohui. Image registration error analysis usingpattern recognition algorithms[C]. The International Society for Optical Engineering,2010:1-9
[68] Murray Paul, Marshall Stephen. A new design tool for feature extraction in noisy imagesbased on grayscale hit-or-miss transforms[J]. IEEE Transactions on Image Processing,2011,20(7):1938-1948
[69] Koenderink J., van Doorn A.. Representation of Local Geometry in the Visual System[J].Biological Cybernetics,1987,55(6):367-375
[70] Freeman W., Adelson E.. The Design and Use of Steerable Filters[J]. IEEE Trans. PatternAnalysis and Machine Intelligence,1991,13(9):891-906
[71] Van Gool L., Moons T., D. Ungureanu. Affine/Photometric Invariants for Planar IntensityPatterns[C]. Proc. Fourth European Conf. Computer Vision,1996:642-651
[72] Belongie S., Malik J., J. Puzicha. Shape Matching and Object Recognition Using ShapeContexts[J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,2(4):509-522
[73] Schaffalitzky F., ZissermanA.. Multi-View Matching for Unordered Image Sets[C]. Proc.Seventh European Conf. Computer Vision,2002:414-431
[74] Lazebnik S., Schmid C., Ponce J.. Sparse Texture Representation Using Affine-InvariantNeighborhoods[C]. Proc. Conf. Computer Vision and Pattern Recognition,2003:319-324
[75] Mikolajczyk K., Schmid C.. Scale and Affine Invariant Interest Point Detectors[J]. Int'l J.Computer Vision,2004,1(60):63-86
[76] Mikolajczyk K., Schmid C.. A performance evaluation of local descriptors[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2005,27:1615–1630
[77] Harris C., Stephens M.. A Combined Corner and Edge Detector[C]. Proc. Alvey VisionConf.,1988:147-151
[78] Lowe D.. Object Recognition from Local Scale-Invariant Features[C]. Proc. Seventh Int'lConf. Computer Vision,1999:1150-1157
[79] Lowe D.. Distinctive Image Features from Scale-Invariant Keypoints[J]. Int'l J.Computer Vision,2004,2(60):91-110
[80] Khalifa Mahmoud, Bingru Yang, Mohammed Ammar. A robust SIFT feature for fastoffline arabic words classification[C]. IEEE International Conference on ComputerScience and Automation Engineering,2011:83-86
[81]冯炜．图像场景分类的关键技术研究．北京：北京交通大学硕士论文，2008:14-19
[82] Koenderink J.J.. The structure of images[J]. Biological Cybernetics,1984,50(5):363-396
[83] Lindeberg, T.. Scale-space theory: A basic tool for analysing structures at differentscales[J]. Journal of Applied Statistics,1994,21(2):224-270
[84] Lee Taehee, Soatto Stefano. Feature tracking and object recognition on a hand-held[C].9th IEEE International Symposium on Mixed and Augmented Reality2010: Scienceand Technology,2011:1-5
[85] Bentley J.. Multidimensional binary search trees used for associative searching[C].Commun. ACM18,1975:509-517
[86]徐望明．基于内容的图像检索技术研究．武汉：武汉科技大学硕士论文，2008:20-25
[87] Beis Jeff, Lowe D.G.. Shape indexing using approximate nearest-neighbour search inhigh-dimensional spaces[C]. Conference onComputerVision and PatternRecognition,1997:1000–1006
[88] Szeliski R.. Image alignment and stitching: A Tutorial[R]. Technical ReportMSR-TR-2004-92. Microsoft Research2004
[89]胡志萍．图像特征提取、匹配和新视点图像生成技术研究．大连：大连理工大学博士论文，2005:10-15,54
[90] Hartley R.I.. Estimation of Relative Camera Positions for Uncalibrated Cameras[C].Proceedings of the Second European Conference on Computer Vision,1992:579-587
[91] Fischler M.A., Bolles R.C.. Random sample consensus: A paradigm for model fittingwith applications to image analysis and automated cartography. Comm. of the ACM,1981,24(6):381–395
[92] Brown D.C.. The bundle adjustment-progress and prospects[J]. Int. ArchivesPhotogrammetry,1976,21(3):1-33
[93] Granshaw S.. Bundle adjustment methods in engineering photogrammetry[J].Photogrammetric Record,1980,10(56):181–207
[94] Cooper M.A.R., Cross P.A.. Statistical concepts and their application in photogrammetryand surveying[J]. Photogrammetric Record,1988,12(71):637–663
[95] Cooper M.A.R.,Cross P.A.. Statistical concepts and their application inphotogrammetry and surveying (continued)[J]. Photogrammetric Record,1991,13(77):645–678
[96] Hartley R.I., A. Zisserman. Multiple View Geometry in Computer Vision[M]. CambridgeUniversity Press,2004:434-456
[97] HIEBERT K.. An evaluation of mathematical software that solves nonlinear least squaresproblems[J]. ACM Transactions on Mathematical Software.1981,7(1):1–16
[98] Soper Timothy D., Chandler John E., Porter Michael P., Seibel Eric J.. Constructingspherical panoramas of a bladder phantom from endoscopic video using bundleadjustment[C]. Progress in Biomedical Optics and Imaging,2011:1-12
[99] Fang Xianyong, Pan Zhigeng, Luo Bin, Wu Fuli, Guo Sanhua. Robust image mosaicwith RANSAC and bundle adjustment[C]. Journal of Computational InformationSystems,2008,4(4):1613-1619
[100] LEVENBERG K.. A method for the solution of certain non-linear problems in leastsquares[J]. The Quarterly of Applied Mathematics,1944,2(2):164–168
[101] MARQUARDT D.. An algorithm for the least-squares estimation of nonlinearparameters[J]. SIAM J. Appl. Math,1963,11(2):431–441.
[102] Yang Shanxiao, Yang Guangying. Emotion recognition of EMG based on improvedL-M BP neural network and SVM[J]. Journal of Software,2011,6(8):1529-1536
[103] Gao Junhong, Kim Seon Joo, Brown Michael S.. Constructing image panoramas usingdual-homography warping[C]. Proceedings of the IEEE Computer Society Conferenceon Computer Vision and Pattern Recognition,2011:49-56
[104]王雷斌．基于计算机视觉的图像拼接技术研究．北京：首都师范大学博士论文，2008:45-49
[105] Gormer Steffen, Hold Stephanie, Kummert Anton, Iurgel Uri, Meuter Mirko.Multi-Exposure Image Acquisition for Automotive High Dynamic Range Imaging [C].IEEE Conference on Intelligent Transportation Systems,2010:1881-1886
[106] Yu Hongsheng, Jin Weiqi. Brightness adaptive algorithm for image mosaic seamlessfusion[C]. The International Society for Optical Engineering,2010:1-9
[107] Bao Paul. Image mosaics with wavelet domain seam-lines[C]. IEEE Symposium onComputers and Informatics,2011:419-424
[108] Weiss Kenneth, De Floriani Leila, Mesmoudi Mohammed Mostefa. Multiresolutionanalysis of3D images based on discrete distortion[C]. International Conference onPattern Recognition,2010:4093-4096
[109] Pan Jun, Wang Mi. A seam-line optimized method based on difference image andgradient image[C].19th International Conference on Geoinformatics,2011:1-6
[110] Levin A., Zomet A., Peleg S., Weiss Y.. Seamless Image Stitching in the GradientDomain[C]. In Proceedings of ECCV,2004:377-389
[111] Pousset P., Duplaquet M.L.. SPOT image mosaic and dynamic programming[C].Proc.EUSIPCO,1990:1854-1861
[112] Duplaquet M.L.. Building large image mosaics with invisible seam-lines[C]. In Proc.SPIE AeroSence,1998:369-377
[113] Alexei A., Efros, William T., Freeman. Image quilting for texture synthesis andtransfer[C]. Proceedings of SIGGRAPH,2001:2341-346
[114] Avidan S., Shamir A.. Seam Carving for Content-Aware Image Resizing[J]. ACMTransactions on Graphics,2007,26(3):1-9
[115] Bellman R., Kalaba R.. Dynamic programming and modern control theory[M].Academic Press Inc.,1965:236-242
[116] Thomas H.. Map projections and airborne moving map displays[C]. Digital AvionicsSystems Conference of IEEE/AIAA,1991:493-498
[117] Wang Jiechen, Chen Yanming, Li Li, Li Lifan. The Module Design of Map ProjectionTransformation Based on Object-Oriented[C]. International Forum on InformationTechnology and Applications,2009:574-578
[118] Lee L.P. The Nomenclature and Classification of Map Projections[M]. Empire SurveyRev7,1944:190-200
[119] Brosz J, Samavati F.. Shape Defined Panoramas[C]. Shape Modeling InternationalConference,2010:57-67
[120] Beom Su Kim, Hyung Il Koo, Nam Ik Cho. A new image projection method forpanoramic image stitching[C]. IEEE International Workshop on Multimedia SignalProcessing,2010:128-132
[121] Ni K.S., Nguyen T.Q.. Adaptable K-nearest neighbor for image interpolation[C]. EEEInternational Conference on Acoustics, Speech and Signal Processing,2008:1297-1300
[122] Heechang Kim, Soonjong Jin, Siyoung Yang, Jechang Jeong. Enhanced Edge-WeightedImage Interpolation Algorithm[C]. Eighth International Conference on HybridIntelligent Systems,2008:957-958
[123] Mihajlovic Z., Goluban A., Zagar M.. Frequency domain analysis of B-splineinterpolation[C]. Proceedings of the IEEE International Symposium on IndustrialElectronics,1999:193-198
[124] Akhtar P., Azhar F.. A Single Image Interpolation Scheme for Enhanced SuperResolution in Bio-Medical Imaging[C].4th International Conference on Bioinformaticsand Biomedical Engineering,2010:1-5
[125] Lehmann T.M., Gonner C., Spitzer K.. Survey: interpolation methods in medical imageprocessing[J]. IEEE Transactions on Medical Imaging,1999,18(11):1049-1075
[126] Can A., Stewart C.V., Roysam B., Tanenbaum H.L.. A Feature-based Technique for joint,linear estimation of high-order image-to-mosaic transformations. IEEE Transactions onPattern Analysis and Machine Intelligence,2002,24(3):412-419
[127] HU M.K.. Visual pattern recognition by moment invariants, IRE Trans Inf Theory,1962,8(2):179-187
[128] José Torre o R.A., Jo o Fernandes L.. Linear-nonlinear neuronal model for shape fromshading[C]. Pattern Recognition Letters,2011:1223-1239
[129] Li Zhaoqi, Niu Ling, Gao Chengying. Linear-nonlinear neuronal model for shape fromshading[C].3rd International Congress on Image and Signal Processing,2010:830-834
[130] Park Kee-Hyon, Park Dae-Geun, Ha Yeong-Ho. High dynamic range image acquisitionfrom multiple low dynamic range images based on estimation of scene dynamicrange[J]. Journal of Imaging Science and Technology,2009,53(2):1-12
[131] Grossberg M., Nayar S.. Modeling the Space of Camera Response Functions[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2004,26(10):1272-1282
[132] Johne B.. Digital Image Processing[M]. Springer,2002:197-200
[133] Mitsunaga, T., Nayar S.. Radiometric Self Calibration[C]. In: IEEE Conference onComputer Vision and Pattern Recognition.1999:374-380
[134] Goldman D.B., Chen J.H.. Vignette and exposure calibration and compensation[C]. InThe10th IEEE International Conference on Computer Vision,2005:899-906
[135] Litvinov A., Schechner Y.Y.. Radiometric framework for image mosaicking[J]. J. Opt.Soc. Am.,2005,22(5):839-848
[136] Grossberg M., Nayar S.. Determining the Camera Response from Images: What isKnowable?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(11):1455-1467
[137] Rosenfeld A., Pfaltz J.L.. Sequential operations in digital picture processing[J]. Journalof the Association for Computing Machinery,1966,13(4):471-494
[138] Kenneth R. castleman. Digital Image Processing[M]. New Jersey: Prentice Hall,1996:475-477
[139] Garg Girisha, Singh Vijander, Gupta J.R.P., Mittal A.P.. Optimal algorithm for ECGdenoising using Discrete Wavelet Transforms[C]. IEEE International Conference onComputational Intelligence and Computing Research,2010:577-580
[140] Coxeter H.S.M.. Introduction to Geometry[M].2nd ed. New York: Wiley,1969:93,289-290
[141] Pearson F.. Map Projections: Theory and Applications[M]. Boca Raton, FL: CRC Press,1990:195-196
[142] Snyder J.P.. Map Projections-A Working Manual[M]. U.S. Geological SurveyProfessional Paper1395. Washington, DC: U.S. Government Printing Office,1987:243-248
© 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 |