高精度特征配准的图像序列稳定算法研究
|
摘要
目前,电子稳像技术EIS(Electronic Image Stabilization)是视频处理、计算机视觉等领域的研究热点。由于具有稳像精度高、体积小、重量轻、功耗低以及成本低等优点,它在军事和民用领域中都有着非常广阔的应用前景。电子稳像的关键技术包括运动估计和运动补偿,其中,序列帧间的运动估计是电子稳像的基础。因此人们进行了大量的研究,提出了多种不同的运动估计算法。本论文在分析各经典算法优劣的基础上,对电子稳像的各项关键技术进行了研究和探讨,并提出一种基于特征匹配的电子稳像算法,具有一定学术价值与实用价值。主要研究内容概括如下:
①本论文对电子稳像技术的国内外研究进展及常用方法进行回顾和总结。阐述了电子稳像的基本原理、基本方法和处理过程,并讨论了其实现的关键技术。介绍了电子稳像中几种常见的典型算法,分析了各算法的优缺点。着重指出,由于能够处理图像序列帧间的复杂运动,基于特征的方法是电子稳像的重要算法。本论文就是采用基于特征的方法。
②运动估计是通过对图像进行分析,估算摄像机的全局运动参数。如何提高运动估计的效率和精度是电子稳像技术研究的重点。本论文针对摄像机在复杂运动环境中的视频稳定,提出一种基于边缘图像配准的高精度电子稳像方法。该方法首先同时检测图像的边缘和边缘上的角点特征;然后,利用匹配点对引导边缘匹配,并筛选适量分布均匀的匹配点对求取初始全局运动估计;最后,改进粒子滤波器以对边缘图像进行配准来获得精确全局运动参数,进一步提高了运动估计的精度。
③对于存在自主扫描的稳像系统,首先要判断并分离摄像机的自主扫描和随机抖动。本论文根据Kalman滤波的基本原理,结合所提出的图像数学模型,设计出对摄像机全局运动矢量进行平滑以分离抖动和自主扫描的Kalman滤波器。实验结果表明该方法在去除高频抖动的同时能较好地保留摄像机的自主扫描。
④针对图像抖动补偿后产生的“未定义区域”,分析了传统的处理方法——图像裁剪和拼接的各自特点。本论文将图像拼接技术用于“未定义区域”的重建。该方法解决了“未定义区域”造成的信息丢失和图像降质问题,提高了图像序列的视觉效果。
本论文最后介绍了电子稳像技术的评价指标,对实际拍摄的视频图像进行了稳像实验,并对稳像效果进行了分析。实验结果证明了所提出稳像算法的有效性。
Currently, the technology of EIS is an important research area of video processing and computer vision. Because of its advantages of high image stabilizing precision, compact size, lightweight, low power consumption and reasonable price, it will have extensive application prospect in military affairs and civil cameras. The key technology of the EIS includes motion estimation and motion compensation, and the motion estimation between adjacent frames is the foundation of EIS. Thus, a lot of research are carried out and several algorithms of motion estimation are proposed. Basing on the analysis on advantages and shortcomings of the typical algorithms, the key technology of EIS is discussed and an algorithm based on feature registration is presented. The proposed algorithm is both of academic value and practical value. The main research works in this thesis are as follows:
①The research progress at home and abroad and the common methods of EIS are reviewed and summarized. In this thesis, the basic principles, methods and process of the electronic image stabilization are described, and the key technology of the realization is discussed. Several typical algorithms of EIS and their advantages and shortcomings are introduced and analyzed. It emphatically points out that the algorithm based on feature matching is considered as the important method, because of its perfect performance to deal with the complex dither between image frames. And this kind of algorithm is used in the thesis.
②The object of motion estimation is to analyze the adjacent frames and estimate the motion parameter of the camera. How to improve the efficiency and accuracy of the motion estimation is the research emphasis. In order to keep the video stream stable when the camera works in complex movement state, a high-accuracy electronic image stabilization method based on edge image registration is presented. In the proposed method, edge feature and corner are detected from the frames at the same time. Matched points are then utilized to guide edge matching, and a proper number of well distributed corresponding points are selected to get initial global motion estimation. Finally, to obtain accurate global motion parameters, improved particle filter is applied to edge image registration to further improve the image stabilization precision.
③When the movement of the camera include random jitter and intentional motion, we must distinguish them firstly. According to the basic principle of Kalman filter and the mathematical model proposed in the thesis, a Kalman filter used to distinguish camera scan from dithering by smoothing the global motion vector are designed. Experimental results show that the method can not only alleviate the vibration but also can preserve the initiative scan of the camera.
④Image tailoring and mosaic are often used to reconstruct the undefined regions which generated after the dither image compensated. The thesis analyses the respective characteristics of them. And the image mosaic is used to reconstruct the undefined regions. This method solves the common problems of information loss and image degradation brought by the undefined regions, and also improves the visual effect of the image sequence.
Evaluation indexes of the EIS are introduced at the end of the thesis and several image stabilization experiments have been carried out with the video image sequence taken by hand-held camera. In addition, the stabilization effect is evaluated. The simulation and experimental rusults demonstrated that this method of EIS proposed in the thesis is feasible.
①本论文对电子稳像技术的国内外研究进展及常用方法进行回顾和总结。阐述了电子稳像的基本原理、基本方法和处理过程,并讨论了其实现的关键技术。介绍了电子稳像中几种常见的典型算法,分析了各算法的优缺点。着重指出,由于能够处理图像序列帧间的复杂运动,基于特征的方法是电子稳像的重要算法。本论文就是采用基于特征的方法。
②运动估计是通过对图像进行分析,估算摄像机的全局运动参数。如何提高运动估计的效率和精度是电子稳像技术研究的重点。本论文针对摄像机在复杂运动环境中的视频稳定,提出一种基于边缘图像配准的高精度电子稳像方法。该方法首先同时检测图像的边缘和边缘上的角点特征;然后,利用匹配点对引导边缘匹配,并筛选适量分布均匀的匹配点对求取初始全局运动估计;最后,改进粒子滤波器以对边缘图像进行配准来获得精确全局运动参数,进一步提高了运动估计的精度。
③对于存在自主扫描的稳像系统,首先要判断并分离摄像机的自主扫描和随机抖动。本论文根据Kalman滤波的基本原理,结合所提出的图像数学模型,设计出对摄像机全局运动矢量进行平滑以分离抖动和自主扫描的Kalman滤波器。实验结果表明该方法在去除高频抖动的同时能较好地保留摄像机的自主扫描。
④针对图像抖动补偿后产生的“未定义区域”,分析了传统的处理方法——图像裁剪和拼接的各自特点。本论文将图像拼接技术用于“未定义区域”的重建。该方法解决了“未定义区域”造成的信息丢失和图像降质问题,提高了图像序列的视觉效果。
本论文最后介绍了电子稳像技术的评价指标,对实际拍摄的视频图像进行了稳像实验,并对稳像效果进行了分析。实验结果证明了所提出稳像算法的有效性。
Currently, the technology of EIS is an important research area of video processing and computer vision. Because of its advantages of high image stabilizing precision, compact size, lightweight, low power consumption and reasonable price, it will have extensive application prospect in military affairs and civil cameras. The key technology of the EIS includes motion estimation and motion compensation, and the motion estimation between adjacent frames is the foundation of EIS. Thus, a lot of research are carried out and several algorithms of motion estimation are proposed. Basing on the analysis on advantages and shortcomings of the typical algorithms, the key technology of EIS is discussed and an algorithm based on feature registration is presented. The proposed algorithm is both of academic value and practical value. The main research works in this thesis are as follows:
①The research progress at home and abroad and the common methods of EIS are reviewed and summarized. In this thesis, the basic principles, methods and process of the electronic image stabilization are described, and the key technology of the realization is discussed. Several typical algorithms of EIS and their advantages and shortcomings are introduced and analyzed. It emphatically points out that the algorithm based on feature matching is considered as the important method, because of its perfect performance to deal with the complex dither between image frames. And this kind of algorithm is used in the thesis.
②The object of motion estimation is to analyze the adjacent frames and estimate the motion parameter of the camera. How to improve the efficiency and accuracy of the motion estimation is the research emphasis. In order to keep the video stream stable when the camera works in complex movement state, a high-accuracy electronic image stabilization method based on edge image registration is presented. In the proposed method, edge feature and corner are detected from the frames at the same time. Matched points are then utilized to guide edge matching, and a proper number of well distributed corresponding points are selected to get initial global motion estimation. Finally, to obtain accurate global motion parameters, improved particle filter is applied to edge image registration to further improve the image stabilization precision.
③When the movement of the camera include random jitter and intentional motion, we must distinguish them firstly. According to the basic principle of Kalman filter and the mathematical model proposed in the thesis, a Kalman filter used to distinguish camera scan from dithering by smoothing the global motion vector are designed. Experimental results show that the method can not only alleviate the vibration but also can preserve the initiative scan of the camera.
④Image tailoring and mosaic are often used to reconstruct the undefined regions which generated after the dither image compensated. The thesis analyses the respective characteristics of them. And the image mosaic is used to reconstruct the undefined regions. This method solves the common problems of information loss and image degradation brought by the undefined regions, and also improves the visual effect of the image sequence.
Evaluation indexes of the EIS are introduced at the end of the thesis and several image stabilization experiments have been carried out with the video image sequence taken by hand-held camera. In addition, the stabilization effect is evaluated. The simulation and experimental rusults demonstrated that this method of EIS proposed in the thesis is feasible.
引文
[1] Lewis G R. Image Stabilization Techniques for Lang Range Camera [J]. Proc. SPIE, 1980, 242(8):215-220.
[2]赵红颖,金宏.电子稳像技术概述[J],光学精密工程, 2001, 9(4): 351-357.
[3]钟平,于前洋.机载摄像设备图像稳定方法探讨明[J],光电工程. 2002, 29(12):73-80.
[4]钟平,于钱洋,王明佳.提高用于电子稳像的灰度投影算法精度的方法[J].光电子·激光. 2003, 2(14):183-188.
[5]韩绍坤,赵跃进.电子稳像技术及其发展[J].光学技术, 2001, 27(1):71-73.
[6] CHANG J Y, HU W F, CHENG M H, et al. Digital image translational and rotational motion stabilization using optical flow technique [J]. IEEE Trans on Consumer Electronics, 2002, 48(1):108-115.
[7] Srinivasan S, Chellappa R. Image stabilization and mosaicing using the overlapped basis optical flow field[C]. IEEE International Conference on Image Processing, 1997, 3(2):356-359.
[8]孙辉,赵红颖,熊经武.基于光流模型的图像运动估计方法[J].光学精密工程, 2002, 10(5):443-44.
[9]孙辉,快速灰度投影算法及其在电子稳像中的应用[J].光学精密工程, 2007 15(3):412-416.
[10]赵红颖,晏磊等.灰度投影拟和算法稳定船载侦察系统获得的视频图像[J].仪器仪表学报. 2004, 25(4):279-283.
[11]冯驰,张怡.基于全搜索块匹配法的电子图像稳定[J].自动化技术与应用, 2004, 23(6):49-51
[12] Xu L D, Fangwen Fu, Xinggang Lin. Circular block matching based video stabilization[C]. Proc.of SPIE. On Visual Communications and Image Proeessing, 2005, 1307-1314.
[13] Liu A K, Feig E. A block-based gradient descent search algorithm for block motion estimation in video coding[C]. IEEE Trans on Circuits System Video Technology.1996, 6(4):419-423.
[14] Ko S J, Lee S H, LEE K H. Fast digital image stabilizer based on gray-coded bit-plane matching [J]. IEEE Trans on Consumer Electronics, 1999, 45(3):598-603.
[15] Ertürk S. Digital image stabilization with sub-image phase correlation based global motion estimation [J]. IEEE Trans on Consumer Electronics, 2003, 49(4): 1320-1325.
[16]邓红梅,吴四夫.基于相位相关算法的研究与实现[J].信息技术, 2005, 4(36):19-20.
[17] Wolberg G, Zokai S. Roubust image registration using log-polar transform[C]. Proc. IEEE Int. Conf.Image Processing. 2000:493-496.
[18] Ertürk S. Translation , Rotation and scale stabilization of image sequences[J]. Elecronic Letters IEEE, 2003.39(17):1245-1246
[19] SHI Jianbo, TOMASI C. Good Features To Track[C]. IEEE Conf. Computer Vision and Pattern Recognition, 1994: 593-600.
[20] HU R, SHU R J, SHEN I F, et al. Video stabilization using scale-invariant features[C]. Proceedings of IEEE International Conference Information Visualization. SWITZERLAND, 2007: 871-877.
[21] BATTIATO S, GALLO G, PUGLISIG, et al. SIFT Features Tracking for Video Stabilization[C]. Proceedings of International Conference on Image Analysis and Processing. Modena, ITALY 2007: 825-830.
[22]钟平,于前洋,金光.基于特征点匹配技术的运动估计及补偿方法研究闭[J].光电子激光. 2004, 15:7-80.
[23] YaoY S, Chellappa Rama. Tracking a dynamic set of feature points[J]. IEEE Trans.on Image Processing, 1995, 4(10):1382-1385.
[24]朱娟娟,郭宝龙.电子稳像的特征点跟踪算法[J].光学学报, 2006, 26(4):516-521.
[25]朱娟娟.电子稳像理论及其应用研究[D].博士论文.西安电子科技大学. 2009.
[26]曹红杏,柳稼航,阮萍. L-M算法在变换矩阵计算中的应用[J].现代电子技术, (24):99-101
[27] Smith S M, Brady J M. SUSAN-a new approach to low level image processing[J].Journal Computer Vision, 1997, 23(1):45-78.
[28]章毓晋,图像处理和分析[M],清华大学出版社, 2000:182-184.
[29]何斌,马天予,王运坚等. Visual C++数字图像处理(第二版)[M],人民邮电出版社, 2003:394-397.
[30]尹德森,赵跃进,杨佩原等.基于Canny边缘检测的数字稳像算法研究[J].光学技术, 2007, 32(3):450-455.
[31] Kovesi P. Invariant Measures of Image Features from Phase Information [D]. PhD thesis, The University of Western Australia, Department of Psychology, 1996.
[32] Kovesi P. Image Features from Phase Congruency[J]. A Journal of Computer Vision Research, 1999, 1(3):1-26.
[33] Kovesi P. Edges Are Not Just Steps[C]. Proceedings of ACCV2002: The Fifth Asian Conference on Computer Vision. 2002.
[34]肖鹏峰,冯学智,赵书河等,一种基于相位一致的高分辨率遥感图像特征检测方法[J].遥感学报, 2007, 11(3):303-310.
[35] Kovesi P. Phase congruency detects corners and edges [C] Proceedings of the Australian Pattern Recognition Society Conference, Sydney, 2003: 10-12.
[36] Mokhtarian F, Suomela R. Robust image corner detection through Curvature Scale Space[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(12):1376-1381.
[37] Mokhtarian F, Mohanna F. Enhancing the curvature scale space corner detector[C]. In: Proc. Scandingavian Conf.on Image Analysis. Norway, Bergen,2001:145-152.
[38] Mokhtarian F, Mackworth A K. A Theory of Multi-Scale, Curvature-Based Shape Representation for Planar Curves[J]. IEEE Trans on pattern Analysis and Machine Intelligence, 1992,14(8):789-805
[39] Roseenfeld A, E.Johnston. Angle detection on digital curves[J]. IEEE Trans. Computer, 1973, 22:875-878.
[40] Lowe D. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision.2004, 2(60):91–110.
[41] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors [C]. Proceedings of the Conference on Computer Vision and Pattern Recognition. 2004: 511–517
[42] Bay H, Tuytelaars T, et al. SURF: Speeded up robust features [C]. European Conference on Computer Vision, 2006: 404-417.
[43]刘博文,余松煜,杨小康,徐奕.宽基线主动视觉中感兴趣目标的对应技术[J].中国图象图形学报. 2007, 12(10):1917-1921.
[44] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[45] Winder S A J, Brown M. Learning local image descriptors [C] Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007: 17-24.
[46] Tola E, Lepetit V, Fua P. A fast local descriptor for dense matching [C] Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, AK, 2008:1-8.
[47] A Murat Tekalp. Digital video processing数字视频处理(影印版)[M].清华大学出版社. 1998
[48] Carlos Guesrin, Fabio Cozman, M Godoy Simoes. Industrial Applications Of Image Mosaicing And Stabilization[C]. Second International Conference on Knowledge-Based Intelligent Electronic Systems. 1998, 4:21-23
[49] Sanjeev M, Arulampalam, Maskell S, Gordon N, et al. A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking [J]. IEEE Trans on Signal Processing, 2002, 50(2): 174-188.
[50] Sim D G, Kwon O K, Park R H. Object matching algorithm using robust Hausdorff distance measures [J]. IEEE Trans on Image Processing, 1999, 8(3):425-429.
[51]孙瑾,顾宏斌,秦小麟等.一种鲁棒型Hausdorff距离图像匹配方法[J].中国图象图形学报2008 13(4):761-767
[52]孟龙,林行刚.视频抖动矫正系统中的运动滤波[J].清华大学学报(自然科学版), 2005, 45(1):41-43.
[53] Jin J S, Zhu Zhigang, Xu Guangyou. A Stable Vision System for Moving Vehicles[J]. IEEE Trans on Intelligent Transportation Systems, 2000, 1(1):32-39.
[54] Litvin A, Konrad J, Karl W. Probabilistic video stabilization using Kalman filtering and mosaicking[C].Proceedings of SPIE Conference on Electronic Imaging, Santa Clara, 2003:20–24.
[55] Uomori K, Morimura A, Ishii H, et al. Automatic image stabilizing system by full-digital signal processing[J]. IEEE Trans On Consumer Electronics, 1990, 36(3):510-519.
[56] Amol Prakash, Antoine McNamara, Ashish Guptu, et al. Automatic image stabilization[J]. CSE567, IEEE, 2002, 48(1):108-115.
[57]杨雨东,徐光佑,朱志刚. 2.5维数字图像序列稳定方法[J].计算机学报, 1998, 21(Suppl.):277-284.
[58] Zhu Z, Xu G, Yang Y, Jin. J S Camera stabilization based on 2.5D motion estimation and inertial motion filtering[C]. IEEE International Conference on Intelligent Vehicles,1998:329-334.
[59] Meng L, Lin X G, Wang G J, et al. Motion filter for video stabilizing systems[J]. Journal of Tsinghua University(清华大学学报), 2005, 45(1):41-43.
[60] Yan W D, Mohan S Kankanhalli. Detection and removal of lighting & shaking artifacts in home videos.[J] Proceedings of the tenth ACM international conference on multimedia. 2002, 107-116.
[61]杨占龙.基于特征点的图像配准与拼接技术研究[D].博士论文.西安电子科技大学. 2008.
[62] Yasuyuki, Matsushita, Eyal Ofek, Tang X O. Full-frame video stabilization [C]. IEEE Conference on Computer Vision and Pattern Recognition 2006:1150-1163
[63]方贤勇,潘志庚,徐丹.图像拼接的改进算法[J].计算机辅助设计与图形学学报, 2003, 15(11):1362-1365
[64]苗立刚.视频监控中的图像拼接与合成算法研究[J].仪器仪表学报, 2009, 30(4):857-861
[65] Morimoto C, Chellappa R. Evaluation of image stabilization algorithms [C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing, 1998(5):2789-2792.
[66] Wang Zhou, Bovik A C, Sheikh H R. Image quality assessment: from error visibility to structural similarity [J].IEEE Trans on Image Processing, 2004, 13 (4):600-612.
[67]王宇庆,刘维亚,王勇.一种基于局部方差和结构相似度的图像质量评价方法[J].光电子·激光, 2008, 19(11):1546-1553.
[68]狄红卫,刘显峰.基于结构相似度的图像融合质量评价[J].光子学报, 2006, 35(5):766-771.
[69] Zhou Wang, Bovik A C. Auniversal image quality index[J]. IEEE Signal Processing Letters, 2002, 9(3):181-84.
[2]赵红颖,金宏.电子稳像技术概述[J],光学精密工程, 2001, 9(4): 351-357.
[3]钟平,于前洋.机载摄像设备图像稳定方法探讨明[J],光电工程. 2002, 29(12):73-80.
[4]钟平,于钱洋,王明佳.提高用于电子稳像的灰度投影算法精度的方法[J].光电子·激光. 2003, 2(14):183-188.
[5]韩绍坤,赵跃进.电子稳像技术及其发展[J].光学技术, 2001, 27(1):71-73.
[6] CHANG J Y, HU W F, CHENG M H, et al. Digital image translational and rotational motion stabilization using optical flow technique [J]. IEEE Trans on Consumer Electronics, 2002, 48(1):108-115.
[7] Srinivasan S, Chellappa R. Image stabilization and mosaicing using the overlapped basis optical flow field[C]. IEEE International Conference on Image Processing, 1997, 3(2):356-359.
[8]孙辉,赵红颖,熊经武.基于光流模型的图像运动估计方法[J].光学精密工程, 2002, 10(5):443-44.
[9]孙辉,快速灰度投影算法及其在电子稳像中的应用[J].光学精密工程, 2007 15(3):412-416.
[10]赵红颖,晏磊等.灰度投影拟和算法稳定船载侦察系统获得的视频图像[J].仪器仪表学报. 2004, 25(4):279-283.
[11]冯驰,张怡.基于全搜索块匹配法的电子图像稳定[J].自动化技术与应用, 2004, 23(6):49-51
[12] Xu L D, Fangwen Fu, Xinggang Lin. Circular block matching based video stabilization[C]. Proc.of SPIE. On Visual Communications and Image Proeessing, 2005, 1307-1314.
[13] Liu A K, Feig E. A block-based gradient descent search algorithm for block motion estimation in video coding[C]. IEEE Trans on Circuits System Video Technology.1996, 6(4):419-423.
[14] Ko S J, Lee S H, LEE K H. Fast digital image stabilizer based on gray-coded bit-plane matching [J]. IEEE Trans on Consumer Electronics, 1999, 45(3):598-603.
[15] Ertürk S. Digital image stabilization with sub-image phase correlation based global motion estimation [J]. IEEE Trans on Consumer Electronics, 2003, 49(4): 1320-1325.
[16]邓红梅,吴四夫.基于相位相关算法的研究与实现[J].信息技术, 2005, 4(36):19-20.
[17] Wolberg G, Zokai S. Roubust image registration using log-polar transform[C]. Proc. IEEE Int. Conf.Image Processing. 2000:493-496.
[18] Ertürk S. Translation , Rotation and scale stabilization of image sequences[J]. Elecronic Letters IEEE, 2003.39(17):1245-1246
[19] SHI Jianbo, TOMASI C. Good Features To Track[C]. IEEE Conf. Computer Vision and Pattern Recognition, 1994: 593-600.
[20] HU R, SHU R J, SHEN I F, et al. Video stabilization using scale-invariant features[C]. Proceedings of IEEE International Conference Information Visualization. SWITZERLAND, 2007: 871-877.
[21] BATTIATO S, GALLO G, PUGLISIG, et al. SIFT Features Tracking for Video Stabilization[C]. Proceedings of International Conference on Image Analysis and Processing. Modena, ITALY 2007: 825-830.
[22]钟平,于前洋,金光.基于特征点匹配技术的运动估计及补偿方法研究闭[J].光电子激光. 2004, 15:7-80.
[23] YaoY S, Chellappa Rama. Tracking a dynamic set of feature points[J]. IEEE Trans.on Image Processing, 1995, 4(10):1382-1385.
[24]朱娟娟,郭宝龙.电子稳像的特征点跟踪算法[J].光学学报, 2006, 26(4):516-521.
[25]朱娟娟.电子稳像理论及其应用研究[D].博士论文.西安电子科技大学. 2009.
[26]曹红杏,柳稼航,阮萍. L-M算法在变换矩阵计算中的应用[J].现代电子技术, (24):99-101
[27] Smith S M, Brady J M. SUSAN-a new approach to low level image processing[J].Journal Computer Vision, 1997, 23(1):45-78.
[28]章毓晋,图像处理和分析[M],清华大学出版社, 2000:182-184.
[29]何斌,马天予,王运坚等. Visual C++数字图像处理(第二版)[M],人民邮电出版社, 2003:394-397.
[30]尹德森,赵跃进,杨佩原等.基于Canny边缘检测的数字稳像算法研究[J].光学技术, 2007, 32(3):450-455.
[31] Kovesi P. Invariant Measures of Image Features from Phase Information [D]. PhD thesis, The University of Western Australia, Department of Psychology, 1996.
[32] Kovesi P. Image Features from Phase Congruency[J]. A Journal of Computer Vision Research, 1999, 1(3):1-26.
[33] Kovesi P. Edges Are Not Just Steps[C]. Proceedings of ACCV2002: The Fifth Asian Conference on Computer Vision. 2002.
[34]肖鹏峰,冯学智,赵书河等,一种基于相位一致的高分辨率遥感图像特征检测方法[J].遥感学报, 2007, 11(3):303-310.
[35] Kovesi P. Phase congruency detects corners and edges [C] Proceedings of the Australian Pattern Recognition Society Conference, Sydney, 2003: 10-12.
[36] Mokhtarian F, Suomela R. Robust image corner detection through Curvature Scale Space[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(12):1376-1381.
[37] Mokhtarian F, Mohanna F. Enhancing the curvature scale space corner detector[C]. In: Proc. Scandingavian Conf.on Image Analysis. Norway, Bergen,2001:145-152.
[38] Mokhtarian F, Mackworth A K. A Theory of Multi-Scale, Curvature-Based Shape Representation for Planar Curves[J]. IEEE Trans on pattern Analysis and Machine Intelligence, 1992,14(8):789-805
[39] Roseenfeld A, E.Johnston. Angle detection on digital curves[J]. IEEE Trans. Computer, 1973, 22:875-878.
[40] Lowe D. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision.2004, 2(60):91–110.
[41] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors [C]. Proceedings of the Conference on Computer Vision and Pattern Recognition. 2004: 511–517
[42] Bay H, Tuytelaars T, et al. SURF: Speeded up robust features [C]. European Conference on Computer Vision, 2006: 404-417.
[43]刘博文,余松煜,杨小康,徐奕.宽基线主动视觉中感兴趣目标的对应技术[J].中国图象图形学报. 2007, 12(10):1917-1921.
[44] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[45] Winder S A J, Brown M. Learning local image descriptors [C] Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007: 17-24.
[46] Tola E, Lepetit V, Fua P. A fast local descriptor for dense matching [C] Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Anchorage, AK, 2008:1-8.
[47] A Murat Tekalp. Digital video processing数字视频处理(影印版)[M].清华大学出版社. 1998
[48] Carlos Guesrin, Fabio Cozman, M Godoy Simoes. Industrial Applications Of Image Mosaicing And Stabilization[C]. Second International Conference on Knowledge-Based Intelligent Electronic Systems. 1998, 4:21-23
[49] Sanjeev M, Arulampalam, Maskell S, Gordon N, et al. A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking [J]. IEEE Trans on Signal Processing, 2002, 50(2): 174-188.
[50] Sim D G, Kwon O K, Park R H. Object matching algorithm using robust Hausdorff distance measures [J]. IEEE Trans on Image Processing, 1999, 8(3):425-429.
[51]孙瑾,顾宏斌,秦小麟等.一种鲁棒型Hausdorff距离图像匹配方法[J].中国图象图形学报2008 13(4):761-767
[52]孟龙,林行刚.视频抖动矫正系统中的运动滤波[J].清华大学学报(自然科学版), 2005, 45(1):41-43.
[53] Jin J S, Zhu Zhigang, Xu Guangyou. A Stable Vision System for Moving Vehicles[J]. IEEE Trans on Intelligent Transportation Systems, 2000, 1(1):32-39.
[54] Litvin A, Konrad J, Karl W. Probabilistic video stabilization using Kalman filtering and mosaicking[C].Proceedings of SPIE Conference on Electronic Imaging, Santa Clara, 2003:20–24.
[55] Uomori K, Morimura A, Ishii H, et al. Automatic image stabilizing system by full-digital signal processing[J]. IEEE Trans On Consumer Electronics, 1990, 36(3):510-519.
[56] Amol Prakash, Antoine McNamara, Ashish Guptu, et al. Automatic image stabilization[J]. CSE567, IEEE, 2002, 48(1):108-115.
[57]杨雨东,徐光佑,朱志刚. 2.5维数字图像序列稳定方法[J].计算机学报, 1998, 21(Suppl.):277-284.
[58] Zhu Z, Xu G, Yang Y, Jin. J S Camera stabilization based on 2.5D motion estimation and inertial motion filtering[C]. IEEE International Conference on Intelligent Vehicles,1998:329-334.
[59] Meng L, Lin X G, Wang G J, et al. Motion filter for video stabilizing systems[J]. Journal of Tsinghua University(清华大学学报), 2005, 45(1):41-43.
[60] Yan W D, Mohan S Kankanhalli. Detection and removal of lighting & shaking artifacts in home videos.[J] Proceedings of the tenth ACM international conference on multimedia. 2002, 107-116.
[61]杨占龙.基于特征点的图像配准与拼接技术研究[D].博士论文.西安电子科技大学. 2008.
[62] Yasuyuki, Matsushita, Eyal Ofek, Tang X O. Full-frame video stabilization [C]. IEEE Conference on Computer Vision and Pattern Recognition 2006:1150-1163
[63]方贤勇,潘志庚,徐丹.图像拼接的改进算法[J].计算机辅助设计与图形学学报, 2003, 15(11):1362-1365
[64]苗立刚.视频监控中的图像拼接与合成算法研究[J].仪器仪表学报, 2009, 30(4):857-861
[65] Morimoto C, Chellappa R. Evaluation of image stabilization algorithms [C]. Proceedings of International Conference on Acoustics, Speech, and Signal Processing, 1998(5):2789-2792.
[66] Wang Zhou, Bovik A C, Sheikh H R. Image quality assessment: from error visibility to structural similarity [J].IEEE Trans on Image Processing, 2004, 13 (4):600-612.
[67]王宇庆,刘维亚,王勇.一种基于局部方差和结构相似度的图像质量评价方法[J].光电子·激光, 2008, 19(11):1546-1553.
[68]狄红卫,刘显峰.基于结构相似度的图像融合质量评价[J].光子学报, 2006, 35(5):766-771.
[69] Zhou Wang, Bovik A C. Auniversal image quality index[J]. IEEE Signal Processing Letters, 2002, 9(3):181-84.