动态场景中的运动目标检测与跟踪技术
|
摘要
运动目标检测和跟踪技术是近年来计算机视觉、图像处理、模式识别和人工智能等领域的研究热点。该技术已经应用于智能机器人、智能交通、科学探测等领域。通常图像序列分为:静态场景图像序列和动态场景图像序列,在基于图像的目标检测和跟踪研究中,动态场景图像序列更符合实际应用、更有研究价值,因此动态场景中运动目标的检测和跟踪是该研究领域的重点。
本论文主要研究了动态场景中运动目标检测和跟踪的方法。为了提高全局运动估计和补偿的精度和速度,提出了一种改进的自适应去除局部运动的方法。实现了运动目标模板的自动提取,解决了传统Mean Shift跟踪算法需要手动确定目标区域的问题。本文研究工作包括以下几个部分:
首先介绍了摄像机的运动模型。在分析了摄像机在三维空域中运动的数学模型基础上,给出了目前常用的摄像机运动模型,即基于透视投影的八参数模型和基于平行投影的六参数模型。
然后用基于特征的方法估计全局运动。利用SIFT算法提取具有较高精确度和稳定性的图像特征点。为了提高全局运动估计和补偿的精度,本文根据特征点运动矢量特性,提出了一种改进的自适应去除局部运动的方法。并通过实验验证了本文的算法能够取得较高估计精度和较好的补偿效果。
用帧间差分法检测动态场景中的运动目标。先根据两帧图像间的全局运动参数,对两帧图像进行运动补偿,使两帧图像的背景对齐,再将补偿后的当前帧图像和参考帧图像进行差分,检测运动目标。
最后利用MRF分割算法对差分的图像进行分割。采用数学形态学中闭运算的方法将目标内部的空洞和不连续的边缘填充完整,并去除孤立的噪声点,得到含有完整目标区域的二值化图像。再根据二值化图像水平投影和垂直投影的顶点坐标,实现目标区域的自动提取。解决了传统的Mean Shift跟踪算法需要手动确定目标区域的问题,最终实现了目标的自动跟踪。
The moving target detecting and tracking technology has become a hot topic in the fields of computer vision, image processing, pattern recognition, artificial intelligence and so on. It has already been used in many areas such as intelligent robot, intelligent transportation and video supervising. Usually the image sequences are classified into static one and dynamic one. The latter is more tally with practice and valuable in the domain of target detection and tracking based on image sequences, so target detection and tracking in dynamic scene is the important part for this research domain.
This paper mainly researches the methods of detecting and tracking of moving target in image sequences acquired by a mobile camera. In order to improve the accuracy and velocity of the global estimation and compensation, an improved adaptive noise reduction method is proposed. Target area is obtained automatically which solves the problem that the target area needs to be determined artificially in traditional Mean Shift algorithm.
The primary researches of this paper include sections as following:
Firstly introduce the camera motion models. The motion of camera in spatial domain is analyzed, and the typical camera motion model: the eight parameters model based on perspective projection and the six parameters model based on parallel projection are also introduced.
Then the method based on feature is used for global motion estimation. The SIFT algorithm is applied for getting high accurate and stable features. In order to improve the accuracy of global estimation and compensation, it is necessary to eliminate points with local motion. An improved adaptive noise reduction method is proposed in this paper, which is effective demonstrated by the experimental results.
Frame difference is used to detect moving target in dynamic scene. The motion compensation for the two frame images is done at first to get a similar background according to the estimated global motion parameters of two frame images. Then moving target is detected by the difference between the compensated image and the reference image.
Finally the MRF segmentation algorithm is used for segmenting the difference images. In this paper, the holes and the edges are filled through closing operation in the field of mathematical morphology, after that, a binary image including complete target area is obtained. Then, a target template is got via mapping the coordinates of the horizontal projection and perpendicular projection vertexes to the corresponding original images. Finally, target area is picked up automatically which solves the problem that the target area needs to be determined artificially in traditional Mean Shift algorithm, and automatic target tracking is realized.
本论文主要研究了动态场景中运动目标检测和跟踪的方法。为了提高全局运动估计和补偿的精度和速度,提出了一种改进的自适应去除局部运动的方法。实现了运动目标模板的自动提取,解决了传统Mean Shift跟踪算法需要手动确定目标区域的问题。本文研究工作包括以下几个部分:
首先介绍了摄像机的运动模型。在分析了摄像机在三维空域中运动的数学模型基础上,给出了目前常用的摄像机运动模型,即基于透视投影的八参数模型和基于平行投影的六参数模型。
然后用基于特征的方法估计全局运动。利用SIFT算法提取具有较高精确度和稳定性的图像特征点。为了提高全局运动估计和补偿的精度,本文根据特征点运动矢量特性,提出了一种改进的自适应去除局部运动的方法。并通过实验验证了本文的算法能够取得较高估计精度和较好的补偿效果。
用帧间差分法检测动态场景中的运动目标。先根据两帧图像间的全局运动参数,对两帧图像进行运动补偿,使两帧图像的背景对齐,再将补偿后的当前帧图像和参考帧图像进行差分,检测运动目标。
最后利用MRF分割算法对差分的图像进行分割。采用数学形态学中闭运算的方法将目标内部的空洞和不连续的边缘填充完整,并去除孤立的噪声点,得到含有完整目标区域的二值化图像。再根据二值化图像水平投影和垂直投影的顶点坐标,实现目标区域的自动提取。解决了传统的Mean Shift跟踪算法需要手动确定目标区域的问题,最终实现了目标的自动跟踪。
The moving target detecting and tracking technology has become a hot topic in the fields of computer vision, image processing, pattern recognition, artificial intelligence and so on. It has already been used in many areas such as intelligent robot, intelligent transportation and video supervising. Usually the image sequences are classified into static one and dynamic one. The latter is more tally with practice and valuable in the domain of target detection and tracking based on image sequences, so target detection and tracking in dynamic scene is the important part for this research domain.
This paper mainly researches the methods of detecting and tracking of moving target in image sequences acquired by a mobile camera. In order to improve the accuracy and velocity of the global estimation and compensation, an improved adaptive noise reduction method is proposed. Target area is obtained automatically which solves the problem that the target area needs to be determined artificially in traditional Mean Shift algorithm.
The primary researches of this paper include sections as following:
Firstly introduce the camera motion models. The motion of camera in spatial domain is analyzed, and the typical camera motion model: the eight parameters model based on perspective projection and the six parameters model based on parallel projection are also introduced.
Then the method based on feature is used for global motion estimation. The SIFT algorithm is applied for getting high accurate and stable features. In order to improve the accuracy of global estimation and compensation, it is necessary to eliminate points with local motion. An improved adaptive noise reduction method is proposed in this paper, which is effective demonstrated by the experimental results.
Frame difference is used to detect moving target in dynamic scene. The motion compensation for the two frame images is done at first to get a similar background according to the estimated global motion parameters of two frame images. Then moving target is detected by the difference between the compensated image and the reference image.
Finally the MRF segmentation algorithm is used for segmenting the difference images. In this paper, the holes and the edges are filled through closing operation in the field of mathematical morphology, after that, a binary image including complete target area is obtained. Then, a target template is got via mapping the coordinates of the horizontal projection and perpendicular projection vertexes to the corresponding original images. Finally, target area is picked up automatically which solves the problem that the target area needs to be determined artificially in traditional Mean Shift algorithm, and automatic target tracking is realized.
引文
[1] L. Fujimoto, Y. Yamada, T. Morizono, Y. Umetani, and T. Maeno, Development of artificial finger skin to detect incipient slip for realization of static friction sensation. In IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems, 2003:15-21 P
[2] A. Azarbayejani, C. Wren, and A. Pentland, Real-time 3-d tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):780-785 P
[3]陈远.复杂场景中视觉运动目标检测与跟踪.华中科技大学博士学位论文.2008:1-5页
[4] Fujiyoshi H, Kanade T. VSAM: Video Surveillance and Monitoring Project. Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 2003, 57(9): 1068-1072 P
[5]覃剑.视频序列中的运动目标检测与跟踪研究.重庆大学博士学位论文.2008:2-3页
[6] Haritaoglu I, Harwood D, Davis L S.W: Real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8): 809-830 P
[7]郑世友.动杰场景图像序列中运动目标检测与跟踪.东南大学博士学位论文.2005:3-4页
[8]刘洋.运动视觉中目标的精确提取与跟踪技术.西安电子科技大学博士学位论文.2007:6-7页
[9]张波.基于粒子滤波的图像跟踪算法研究.上海交通大学博士学位论文.2007:3-4页
[10]邢卓异.基于图像的目标识别与跟踪方法研究.哈尔滨工程大学博士学位论文.2007:1-3页
[11]张继霞.智能视频监控中人体的检测与跟踪研究.大连理工大学硕士学位论文.2007:2-4页
[12] Y. Tsaig, A. Averbuch, Automatic Segmentation of Moving Objects in Video Sequences: A Region Labeling Approach, IEEE Trans. on Circuits System and Video Technology, 2002, Vo1.12(7): 597-612 P
[13] T. Papadimitriou, K. I. Diamantaras, M. G. Strintzis, Video Scene Segmentation Using Spatial Contours and 3-D Robust Motion Estimation, IEEE Trans. on Circuits System and Video Technology, 2004, Vo1.14(4): 485-497 P
[14] Yasushi Mae, Yoshiaki Shirai, Jun Miura, Object tracking in cluttered background based on optical flow and edges, Proceedings of the l3th International Conference on Pattern Recognition, 1996, Vol.l: 196-200 P
[15] Trucco E, Tommasini T, Roberto V, Near-recursive optical flow from weighted image differences. IEEE Transactions on Systems, Man, and Cybemetics, Part B:Cbyemetics, 2005, 3S(1): 124-129 P
[16] A. Bebrad. A. Sbabrolmi. S. A. Motamedi and K. Madam, A Robust Vision-based Moving Target Detection and Tracking System, In proceedings of Image and Vision Computing conference (IVCNZ2001). Universiy of Otago. Dunedin. New Zealand. 2001. November 26-28 P
[17] Shao J, Zhou Shaohua Kevin, Zheng Qinfen. Robust appearance based tracking of moving object from moving platform, 2004, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, v4, 215-218 P
[18] Xinggang Liu, Xiaochuan Luo, Shanqing Li Huiping Zhao, Integration Method Research for the Detection of Moving Multi-Targets in Complex Dynamic Scenes, Proceedings of the 6th World Congress on Intelligent Control and Automation, 2006: 10230-10235 P
[19] Foresti, G.L., Object recognition and tracking for remote video surveillance, IEEE Transactions on Circuits and Systems for Video Technology, 1999. 9(7): 1045-1062 P
[20] A. Cavallaro, T. Ebrahim, Accurate video object segmentation through change detection, Proceedings of IEEE International Conference onMultimedia and Expo, 2002, 445-448 P
[21]刘明刚.候朝焕运动日标的自动分割与跟踪.电子与信息学报.2002, 24(8):1009-1016页
[22]沈娟,杜宇人,高浩军.复杂背景下运动目标跟踪技术.电子工程师.2007,33(5):49-51页
[23] Calvagno G, Fantozzi F, Rinaldo R, Feature based global and local motion estimation for videoconference sequences, IEEE International Conference on Image Processing, 2001, 102-105 P
[24] Laganiere R, Gilbert S, Roth G, Robust object pose estimation from feature-based, IEEE Transactions on Instrumentation and Measurement, 2006, SS(4):1270-1280 P
[25] Wren, C.R., Real-time tracking of the human body, IEEE Transaction Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785 P
[26] Andrade E L, Woods J C, Khan E, Region-based analysis and retrieval for tracking of semantic objects and provision of augmented information in interactive sport scenes. IEEE Transactions on Multimedia, 2005, 7(6): 1084-1095 P
[27] Gastaud M, Barlaud M, Aubert G., Combining shape prior and statistical features for active contour segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(S): 726-734 P
[28]贾沛璋,朱征桃.最优估计及其应用.科学出版社,1984:10-62页
[29] Shu-Chiang Chung, Chung-Ming Kuo, Po-Yi Shih, Rate-constrained motion estimation using Kalman filter, Journal of Visual Communication and Image Representation, 2006(4):929-946 P
[30]张广军,机器视觉.科学出版社,2005:24-30页
[31]林学訚,王宏等译.计算机视觉—一种现代方法北京电子工业出版社,2004:17-29页
[32] Y.Q.Shi, X.A.Xia. Threshholding Multiresolution Block Matching algorithm. IEEE Trans on Circuits and Systems for Video Technology, 2002,7(2):437-440 P
[33] K.P.Joon ,C.P.Yong, W.K.Dong. An Adaptive Motion Decision System for Digital Image Stabilizer based on Edge Pattern Matching. IEEE Trans Consumer Electronic, 2002, 36(3):607-616 P
[34]闫敬文.数字图像处理.国防工业出版社,2007:122-124页
[35]韩月玲,朱丹,王玉良,杨光宇.一种基于灰度投影的实时电子稳像方法.仪器仪表学报.2008, 29(8):512-515页
[36] Lee K W. Ryu S W. Lee S J. Park K T. Motion based object tracking with mobile Camera. Electronics Letters. Vol.34. No.3. 1998:256-258 P
[37] Uomori K, et al. Automatic image stabilizing system by full-digital signal processing, IEEE Trans. Consumer Electronics, 1990, 36:510-519 P
[38]郑世友,费树岷,刘怀,龙飞.动态场景图像序列中运动目标检测新方法.中国图象图形学报.2007,12(9):1590-1597页
[39] Erdem C e. Karabulut G Z. Yanmaz E. Anarim E. Motion Estimation in the frequency domain Using Fuzzy c-planes clustering. IEEE Trans. Image processing, 2001: 1873-1879 P
[40]宋永江,夏良正,杨世周.多直线全局运动估计及其在图像稳定中的应用.东南大学学报.2002, 32(2):151-157页
[41]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.光电子激光.2004,15(1):73-77页
[42] Kuhn, P.M, Camera motion estimation using feature points in MPEG compressed domain, IEEE International Conference on Image Processing, 2000, v3:596-599 P
[43] David G.Lowe, Local Feature View clustering for 3D object recognition, Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001, 1: 682-688 P
[44]吴锐航.基于SIFT特征的图像检索技术研究.厦门大学硕士学位论文.2007:7-8页
[45] Hu Zhiping, Ou Zongying, Virtual Manufacturing Environment Rendering Based on the Image Warping, Proceedings of the 6th International Conference on Frontiers of Design and Manufacturing, 2004:506-507 P
[46] McMillan L, Bishop G, Plenoptic modeling: an image-based rendering system. In SIGGRAPH 95,Los Angeles, California, 1995: 39-46 P
[47] David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, 2004, 60(2): 91-110 P
[48] Canlin Li, Lizhuang Ma, A new framework for feature descriptor based on SIFT, Pattern Recognition Letters, 2009:544–557 P
[49] Andrea Vedaldi, An open implementation of the SIFT detector and descriptor, UCLA CSD Technical Report, 2007:2 P
[50] Xuelong Hu, Yingcheng Tang, Zhenghua Zhang, Video Object Matching Based On SIFT Algorithm, IEEE International Conference Neural Networks & Signal Processing, 2008:412-415 P
[51]张少辉等.一种基于图像特征点提取及匹配的方法.北京航空航天大学学报.2008,34(5):516-519页
[52]朱广新.基于特征点匹配的图像拼接及医学应用.南京理工硕士学位论文.2007:23-24页
[53] Chengyuan Tang, Yileh Wu, Mawkae Hor, Wenhung Wang, Modified SIFT Description for Image Matching Under Interfereence, Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, 2008: 3294-3300 P
[54]戚世贵.基于图像特征点的提取匹配及应用.吉林大学硕士学位论文.2005:26-28页
[55]徐望明.基于内容的图像检索技术研究.武汉科技大学硕士学位论文.2008:19-24页
[56]郭雷,高世伟,杜亚琴,杨宁,陈亮.改进的基于LMA算法的电子稳像技术.微电子学与计算机.2008,25(8):76-80页
[57]贺玉文,杨士强,钟玉琢.全局运动估计中特征点选取和鲁棒性分析.计算机学报.2001,24(3):236-241页
[58]吴思,张勇东,林守勋,李豪杰.动态场景视频序列中的前景区域自动提取.计算机辅助设计与图形学学报.2005,17(2):259-363页
[59] Sharaf, A. Marvasti, F. Motion compensation using spatial transformationswith forward mapping Signal Processing: Image Communication, 1999,v14, n3: 209-227 P
[60] Rath, Gagan B. Makur, Anamitra, Iterative least squares and compression based estimations for a four-parameter linear global motion model and global motion compensation, IEEE Transactions on Circuits and Systems for Video Technology, 1999,v9, n7: 1075-1099 P
[61]王耀南,李树涛.毛建旭.计算机图像处理与识别技术.高等教育出版社,2001:141-144页
[62] Juanjuan Zhu, Baolong Guo, Electronic image stabilization system based on global feature tracking, Journal of Systems Engineering and Electronics, v19, n2, April, 2008: 228-233 P
[63] Li S Z. Markov Random Field Modeling in Image Analysis. [M]. New York: Springer-Verlag, 2001
[64] R. Chellappa, Two Dimensional Discrete Gaussian Markov Random Field Models for Image Processing, Progress in Pattern Recognition, 1985, 2:79-112 P
[65] John M. Hammersley and Peter Clifford, Markov fields on finite graphs and lattices Unpublished, 1971
[66] Julian Besag, Spatial Interaction and the Statistical Analysis of Lattice Systems, Journal of the Royal Statistical Society, Series B, 1974, 36: 192-236 P
[67]付信际.合成孔径雷达图像分类与目标检测技术研究.中国科学院研究生院博士学位论文.2005:34-40页
[68]王鹏伟.基于多尺度理论的图像分割方法研究.中国电子科技大学博士学位论文.2007:61-70页
[69]杨文明,刘济林,王其聪.结合时空信息的视频对象平面自动提取算法.计算机辅助设计与图形学学报.2006, 18(6):l-5页
[70] Fing Yan-qiu, Chin Wir-fan, Lang Bin,et al. A new algorithm for image segmentation based on Gibbs random field and fuzzy c-means clustering, Acta Flectronica Sinica, 2004,32(4):45-47 P
[71]贺兴华,周媛媛,王继阳,周晖等.MATLAB7.x图像处理.人民邮电出版社,2006:182-183页
[72]阮秋琦,阮宇智等译.数字图像处理.电子工业出版社,2007:423-426页
[73] Yizong Cheng. Mean Shift, Mode Seeking, and Clustering. IEEE Transactions On Patttern Analysis and Machine Intelligence, 1995, Vol.17, No.8:790-799 P
[74]张波.基于粒子滤波的图像跟踪算法研究.上海交通大学博士学位论文.2007:32-34页
[75] Dorin Comaniciu, Peter Meer. Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions On Patttern Analysis and Machine Intelligence, 2002, Vol.24, No.5:603-620 P
[76] Dorin Comaniciu, Visvanathan Ramesh, Peter Meer. Kernel-Based Object Tracking. IEEE Transactions On Patttern Analysis and Machine Intelligence, 2003, Vol.25, No.5:564-577 P
[2] A. Azarbayejani, C. Wren, and A. Pentland, Real-time 3-d tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):780-785 P
[3]陈远.复杂场景中视觉运动目标检测与跟踪.华中科技大学博士学位论文.2008:1-5页
[4] Fujiyoshi H, Kanade T. VSAM: Video Surveillance and Monitoring Project. Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, 2003, 57(9): 1068-1072 P
[5]覃剑.视频序列中的运动目标检测与跟踪研究.重庆大学博士学位论文.2008:2-3页
[6] Haritaoglu I, Harwood D, Davis L S.W: Real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8): 809-830 P
[7]郑世友.动杰场景图像序列中运动目标检测与跟踪.东南大学博士学位论文.2005:3-4页
[8]刘洋.运动视觉中目标的精确提取与跟踪技术.西安电子科技大学博士学位论文.2007:6-7页
[9]张波.基于粒子滤波的图像跟踪算法研究.上海交通大学博士学位论文.2007:3-4页
[10]邢卓异.基于图像的目标识别与跟踪方法研究.哈尔滨工程大学博士学位论文.2007:1-3页
[11]张继霞.智能视频监控中人体的检测与跟踪研究.大连理工大学硕士学位论文.2007:2-4页
[12] Y. Tsaig, A. Averbuch, Automatic Segmentation of Moving Objects in Video Sequences: A Region Labeling Approach, IEEE Trans. on Circuits System and Video Technology, 2002, Vo1.12(7): 597-612 P
[13] T. Papadimitriou, K. I. Diamantaras, M. G. Strintzis, Video Scene Segmentation Using Spatial Contours and 3-D Robust Motion Estimation, IEEE Trans. on Circuits System and Video Technology, 2004, Vo1.14(4): 485-497 P
[14] Yasushi Mae, Yoshiaki Shirai, Jun Miura, Object tracking in cluttered background based on optical flow and edges, Proceedings of the l3th International Conference on Pattern Recognition, 1996, Vol.l: 196-200 P
[15] Trucco E, Tommasini T, Roberto V, Near-recursive optical flow from weighted image differences. IEEE Transactions on Systems, Man, and Cybemetics, Part B:Cbyemetics, 2005, 3S(1): 124-129 P
[16] A. Bebrad. A. Sbabrolmi. S. A. Motamedi and K. Madam, A Robust Vision-based Moving Target Detection and Tracking System, In proceedings of Image and Vision Computing conference (IVCNZ2001). Universiy of Otago. Dunedin. New Zealand. 2001. November 26-28 P
[17] Shao J, Zhou Shaohua Kevin, Zheng Qinfen. Robust appearance based tracking of moving object from moving platform, 2004, Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, v4, 215-218 P
[18] Xinggang Liu, Xiaochuan Luo, Shanqing Li Huiping Zhao, Integration Method Research for the Detection of Moving Multi-Targets in Complex Dynamic Scenes, Proceedings of the 6th World Congress on Intelligent Control and Automation, 2006: 10230-10235 P
[19] Foresti, G.L., Object recognition and tracking for remote video surveillance, IEEE Transactions on Circuits and Systems for Video Technology, 1999. 9(7): 1045-1062 P
[20] A. Cavallaro, T. Ebrahim, Accurate video object segmentation through change detection, Proceedings of IEEE International Conference onMultimedia and Expo, 2002, 445-448 P
[21]刘明刚.候朝焕运动日标的自动分割与跟踪.电子与信息学报.2002, 24(8):1009-1016页
[22]沈娟,杜宇人,高浩军.复杂背景下运动目标跟踪技术.电子工程师.2007,33(5):49-51页
[23] Calvagno G, Fantozzi F, Rinaldo R, Feature based global and local motion estimation for videoconference sequences, IEEE International Conference on Image Processing, 2001, 102-105 P
[24] Laganiere R, Gilbert S, Roth G, Robust object pose estimation from feature-based, IEEE Transactions on Instrumentation and Measurement, 2006, SS(4):1270-1280 P
[25] Wren, C.R., Real-time tracking of the human body, IEEE Transaction Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785 P
[26] Andrade E L, Woods J C, Khan E, Region-based analysis and retrieval for tracking of semantic objects and provision of augmented information in interactive sport scenes. IEEE Transactions on Multimedia, 2005, 7(6): 1084-1095 P
[27] Gastaud M, Barlaud M, Aubert G., Combining shape prior and statistical features for active contour segmentation. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(S): 726-734 P
[28]贾沛璋,朱征桃.最优估计及其应用.科学出版社,1984:10-62页
[29] Shu-Chiang Chung, Chung-Ming Kuo, Po-Yi Shih, Rate-constrained motion estimation using Kalman filter, Journal of Visual Communication and Image Representation, 2006(4):929-946 P
[30]张广军,机器视觉.科学出版社,2005:24-30页
[31]林学訚,王宏等译.计算机视觉—一种现代方法北京电子工业出版社,2004:17-29页
[32] Y.Q.Shi, X.A.Xia. Threshholding Multiresolution Block Matching algorithm. IEEE Trans on Circuits and Systems for Video Technology, 2002,7(2):437-440 P
[33] K.P.Joon ,C.P.Yong, W.K.Dong. An Adaptive Motion Decision System for Digital Image Stabilizer based on Edge Pattern Matching. IEEE Trans Consumer Electronic, 2002, 36(3):607-616 P
[34]闫敬文.数字图像处理.国防工业出版社,2007:122-124页
[35]韩月玲,朱丹,王玉良,杨光宇.一种基于灰度投影的实时电子稳像方法.仪器仪表学报.2008, 29(8):512-515页
[36] Lee K W. Ryu S W. Lee S J. Park K T. Motion based object tracking with mobile Camera. Electronics Letters. Vol.34. No.3. 1998:256-258 P
[37] Uomori K, et al. Automatic image stabilizing system by full-digital signal processing, IEEE Trans. Consumer Electronics, 1990, 36:510-519 P
[38]郑世友,费树岷,刘怀,龙飞.动态场景图像序列中运动目标检测新方法.中国图象图形学报.2007,12(9):1590-1597页
[39] Erdem C e. Karabulut G Z. Yanmaz E. Anarim E. Motion Estimation in the frequency domain Using Fuzzy c-planes clustering. IEEE Trans. Image processing, 2001: 1873-1879 P
[40]宋永江,夏良正,杨世周.多直线全局运动估计及其在图像稳定中的应用.东南大学学报.2002, 32(2):151-157页
[41]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.光电子激光.2004,15(1):73-77页
[42] Kuhn, P.M, Camera motion estimation using feature points in MPEG compressed domain, IEEE International Conference on Image Processing, 2000, v3:596-599 P
[43] David G.Lowe, Local Feature View clustering for 3D object recognition, Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001, 1: 682-688 P
[44]吴锐航.基于SIFT特征的图像检索技术研究.厦门大学硕士学位论文.2007:7-8页
[45] Hu Zhiping, Ou Zongying, Virtual Manufacturing Environment Rendering Based on the Image Warping, Proceedings of the 6th International Conference on Frontiers of Design and Manufacturing, 2004:506-507 P
[46] McMillan L, Bishop G, Plenoptic modeling: an image-based rendering system. In SIGGRAPH 95,Los Angeles, California, 1995: 39-46 P
[47] David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, 2004, 60(2): 91-110 P
[48] Canlin Li, Lizhuang Ma, A new framework for feature descriptor based on SIFT, Pattern Recognition Letters, 2009:544–557 P
[49] Andrea Vedaldi, An open implementation of the SIFT detector and descriptor, UCLA CSD Technical Report, 2007:2 P
[50] Xuelong Hu, Yingcheng Tang, Zhenghua Zhang, Video Object Matching Based On SIFT Algorithm, IEEE International Conference Neural Networks & Signal Processing, 2008:412-415 P
[51]张少辉等.一种基于图像特征点提取及匹配的方法.北京航空航天大学学报.2008,34(5):516-519页
[52]朱广新.基于特征点匹配的图像拼接及医学应用.南京理工硕士学位论文.2007:23-24页
[53] Chengyuan Tang, Yileh Wu, Mawkae Hor, Wenhung Wang, Modified SIFT Description for Image Matching Under Interfereence, Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, 2008: 3294-3300 P
[54]戚世贵.基于图像特征点的提取匹配及应用.吉林大学硕士学位论文.2005:26-28页
[55]徐望明.基于内容的图像检索技术研究.武汉科技大学硕士学位论文.2008:19-24页
[56]郭雷,高世伟,杜亚琴,杨宁,陈亮.改进的基于LMA算法的电子稳像技术.微电子学与计算机.2008,25(8):76-80页
[57]贺玉文,杨士强,钟玉琢.全局运动估计中特征点选取和鲁棒性分析.计算机学报.2001,24(3):236-241页
[58]吴思,张勇东,林守勋,李豪杰.动态场景视频序列中的前景区域自动提取.计算机辅助设计与图形学学报.2005,17(2):259-363页
[59] Sharaf, A. Marvasti, F. Motion compensation using spatial transformationswith forward mapping Signal Processing: Image Communication, 1999,v14, n3: 209-227 P
[60] Rath, Gagan B. Makur, Anamitra, Iterative least squares and compression based estimations for a four-parameter linear global motion model and global motion compensation, IEEE Transactions on Circuits and Systems for Video Technology, 1999,v9, n7: 1075-1099 P
[61]王耀南,李树涛.毛建旭.计算机图像处理与识别技术.高等教育出版社,2001:141-144页
[62] Juanjuan Zhu, Baolong Guo, Electronic image stabilization system based on global feature tracking, Journal of Systems Engineering and Electronics, v19, n2, April, 2008: 228-233 P
[63] Li S Z. Markov Random Field Modeling in Image Analysis. [M]. New York: Springer-Verlag, 2001
[64] R. Chellappa, Two Dimensional Discrete Gaussian Markov Random Field Models for Image Processing, Progress in Pattern Recognition, 1985, 2:79-112 P
[65] John M. Hammersley and Peter Clifford, Markov fields on finite graphs and lattices Unpublished, 1971
[66] Julian Besag, Spatial Interaction and the Statistical Analysis of Lattice Systems, Journal of the Royal Statistical Society, Series B, 1974, 36: 192-236 P
[67]付信际.合成孔径雷达图像分类与目标检测技术研究.中国科学院研究生院博士学位论文.2005:34-40页
[68]王鹏伟.基于多尺度理论的图像分割方法研究.中国电子科技大学博士学位论文.2007:61-70页
[69]杨文明,刘济林,王其聪.结合时空信息的视频对象平面自动提取算法.计算机辅助设计与图形学学报.2006, 18(6):l-5页
[70] Fing Yan-qiu, Chin Wir-fan, Lang Bin,et al. A new algorithm for image segmentation based on Gibbs random field and fuzzy c-means clustering, Acta Flectronica Sinica, 2004,32(4):45-47 P
[71]贺兴华,周媛媛,王继阳,周晖等.MATLAB7.x图像处理.人民邮电出版社,2006:182-183页
[72]阮秋琦,阮宇智等译.数字图像处理.电子工业出版社,2007:423-426页
[73] Yizong Cheng. Mean Shift, Mode Seeking, and Clustering. IEEE Transactions On Patttern Analysis and Machine Intelligence, 1995, Vol.17, No.8:790-799 P
[74]张波.基于粒子滤波的图像跟踪算法研究.上海交通大学博士学位论文.2007:32-34页
[75] Dorin Comaniciu, Peter Meer. Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions On Patttern Analysis and Machine Intelligence, 2002, Vol.24, No.5:603-620 P
[76] Dorin Comaniciu, Visvanathan Ramesh, Peter Meer. Kernel-Based Object Tracking. IEEE Transactions On Patttern Analysis and Machine Intelligence, 2003, Vol.25, No.5:564-577 P