红外弱小多目标实时检测跟踪技术研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着常规兵器朝着一体化、信息化和远程精确打击方向发展,装备信息化、平台自动化、侦查远程化、弹药制导化、系统网络化、毁伤多样化等趋势和特点日益明显,上述变化均对常规兵器试验鉴定提出了新的更高要求。作为试验鉴定的重要组成部分,通过测量目标弹体飞行弹道参数来揭示被测试武器装备内在性能和固有特性已成为靶场采用的最直接最有效的手段,且其面临着愈加严峻地挑战。在靶场光学测量设备中,常用的可见光成像系统拍摄的可见光图像包含清晰的弹体信息,通过判读可以得到弹体飞行轨迹和姿态参数,但可见光成像容易受天气环境影响,当目标弹体与成像背景颜色相近时,很难进行目标弹体的识别,这些局限性导致在试验中不能保证拍摄到的可见光图像可以用于完成对目标弹体飞行弹道参数的精确测量。
     近些年来,随着红外技术的不断发展,红外测量以其捕获能力强、作用距离远、对天气和背景的适应性较好等特点,越来越受靶场光测的青睐。可当目标为远距离成像时,其在靶面的成像占据很小的像元数量,且目标信噪比低,容易被背景淹没。因此,红外弱小目标的检测跟踪问题一直是机器视觉领域的难题。同时导弹及飞行器甚至炮弹的运动速度及机动性能越来越强,尤其是当视场中为多目标时,检测与跟踪能否实时实现也关系到系统性能的高低。本文的研究内容可为我国靶场红外测量系统的研制提供相应的理论研究基础和技术支持。
     结合在研国防科研项目需求,本文探讨了靶场常见的天空背景下的红外弱小多目标的检测与跟踪问题。遵循传统的研究步骤,本文将该问题分为图像预处理、弱小多目标检测与多目标跟踪三个部分进行研究。在深入分析国内外红外弱小多目标检测跟踪研究现状和研究进展的基础上,在图像预处理部分,本文将图像多尺度几何分析的最新研究进展引入红外图像预处理,提出了采用剪切波变换的红外图像预处理方法。多目标检测方面,结合弱小目标描述模型,提出了基于尺度空间的红外弱小多目标检测算法,用于在复杂背景下快速而准确地检测出多个弱小目标。在多目标跟踪方面,提出一种结合改进的辅助粒子滤波与马尔科夫随机场的多目标跟踪算法,将多目标的跟踪问题转换为图模型的推理问题。同时设计了基于多DSP处理器的多目标跟踪器硬件平台,对移植后的算法进行了多项实验测试,验证了算法与硬件平台系统方案的正确性和可行性。
With the development of conventional weapons heading towards integration,informationization and remote precision strike, the trends and characteristics aboutinformationization of equipments, automation of platform, remote implement ofdetection, navigation of ammunition, networking of systems, diversify of devastationhas become increasingly evident, these changes mentioned above are proposing newand higher demands on conventional weapons tests. As an important part of the test,measurement of the target missile flight trajectory parameters is the most direct andeffective means used by a firing range to reveal the intrinsic properties and theinherent characteristics of the weaponry, and now this method is facing increasinglyserious challenges. Visible light imaging system is a kind of commonly used opticalmeasurement equipment in a firing range. The visible light images often containclear information about the targets, the flight path of the missile body and its attitudeparameters can be precisely obtained through interpretation, but the images arevulnerable to the impact of weather conditions, and when the targets body imagingsimilar to the color of the background, it is difficult to identify the target from thebackgrounds. With these limitations, it can not guarantee that the visible light imagescan be used to complete the accurate measurement of the flight trajectory parametersof the target missile body.
     In recent years, with the continuous development of infrared technology, it is increasingly favored by the firing range to use infrared image because of its distancemeasurement, the noticeable ability of capture, and fine adaptability to the weatherand backgrounds. However, when the targets have a far distance with the infraredoptical measure equipment, the image of the targets are small, with weak signals,and are submerged in complex backgrounds, all of these make the detection andtracking of the targets very difficult. Therefore, the question of how to detect andtracking the dim and small targets in complex backgrounds is becoming a technicaldifficulty today. On the other hand, considering the system performance index points,especially when the number of target is larger than one, the real-time implementationis more take pains. so, it is visible that the research on real-time infrared smalltargets detection and tracking not only has an important theoretical significance, butalso has significant practical value.
     Based on national defense scientific research needs, this paper discusses thedetection and tracking problems of infrared dim small multi-targets under complexbackgrounds. Following the traditional research steps, this paper divide the probleminto three parts study, the pre-processing of image, the detection of the dim smallmulti-targets and targets tracking. Based on the deep analysis of this problem athome and abroad, in the part of pre-processing of image, the latest researchachievement of image multi-scale geometric analysis---Shearlet Transform isintroduced, and based on that theory, a new method in image pre-processing isproposed; To solve the second part of the problem---the detection of small dimtargets, a method based on scale-space theory was proposed. In the last part, analgorithm combine improved auxiliary particle filter with Markov random field isproposed to solve the problem of targets tracking, and simulate multi-tracking modelby using Markov random field. Finally, a multi targets tracking hardware platformusing three DSPs is introduced, through a number of experiments this paper test thetransplantation of the algorithm, verify the correctness and feasibility of the systemprogram and algorithms.
引文
[1]朱玮,赵立荣,柳玉晗等.光电经纬仪子母弹多目标提取方法[J].光学精密工程,2008,16(11):2140-2144
    [2]杨露,金星,沈怀荣.利用光学成像进行子母弹多子弹抛射弹道测量[J].弹箭与制导学报,2004,24(2):58-61
    [3]何小勇,吴钦章,高晓东.光电经纬仪子母弹多子弹轨迹交会法[J].光电工程,2006,33(9):15-18
    [4]陈犇.靶场光测定位方法研究与应用[D]:[硕士学位论文].长沙:国防科学技术大学,2011
    [5]魏长安.红外小目标检测与跟踪算法研究[D]:[博士学位论文].哈尔滨:哈尔滨工业大学,2009
    [6]汪大宝.复杂背景下的红外弱小目标检测与跟踪技术研究[D]:[博士学位论文].西安:西安电子科技大学,2010
    [7] Barnett J. Statistical analysis of median subtraction filtering with application topoint target detection in infrared background [J]. Proc. SPIE.1989,1050:10-18
    [8] Gonzalez R C, Woods R E. Digital Image Processing,2nd Edition [M]. USA:Prentice Hall,2003.56-62
    [9] M.M. Hadhoud, D.W. Thomas. The Two Dimensional Adaptive (TDLMS)Algorithm [J].IEEE Trans. Circ. Sys.1988,35(5):485-494
    [10]李吉成,沈振康.红外起伏背景下运动点目标的检测方法[J].红外与激光工程,1997,26(6):8-13
    [11]曾雅琼,陈钱.基于改进的双边滤波的单帧红外弱小目标背景抑制[J].红外技术,2011,33(9):537-540
    [12]汪大宝,刘上干,寇小明.基于MRF的自适应正则化红外背景杂波抑制算法[J].红外与毫米波学报,2009,28(6):440-444
    [13]武斌,姬红兵,李鹏.基于三阶累积量的红外弱小运动目标检测新方法[J].红外与毫米波学报,2006,25(5):364-367
    [14] Xiong Yan, Peng Jiaxiong. An Effective Method for Trajectory Detection ofMoving Pixel-sized Target [C]. Proceed of IEEE Inter Confer on Systems, Man andCybernetics,Vancouver,Canada,1995,3:2570-2575
    [15]陈颖.序列图像中微弱点状运动目标检测及跟踪技术研究[D]:[博士学位论文].成都:电子科技大学,2003
    [16] Thayaparan T, Kennedy S. Detection of a Maneuvering Air Target in Sea-ClutterUsing Joint Time-Frequency Analysis Techniques [J]. IEE Processing, Radar, Sonarand Navigation,2004,151(1):19-30
    [17] L. Yang, J. Yang, K. Yang. Adaptive Detection for Infrared Small Target UnderSea-sky Complex Background [J]. Electron Letters,2004,40(17):1083-1085
    [18] Chapa J Q, Rao R M. Algorithms for Designing Wavelets to mathc a specifiedsignal [J]. IEEE Trans On Signal Processing,2000,48(12):3395-3406
    [19] Daubechies I. The Wavelet Transform, Time-Frequency Localization and SignalAnalysis [J]. IEEE Trans On Information Theory,1990,36(5):961-1005
    [20]朱斌,樊祥,马东辉等.天空红外图像非平稳背景的小波域抑制[J].红外与激光工程,2008,S2:635-637
    [21]张翔,张建奇,秦翰林等.刘菁基于对偶树复小波变换的红外弱小目标背景抑制[J].光子学报,2010,39(9):1672-1677
    [22] R N Strickland, H I Hahn. Wavelet Transform Methods for Object Detection andRecovery [J]. IEEE Trans On Image Processing,1997,6(5):724-735
    [23] D Daviesy, P Palmery, M Mirmehdiz. Detection and Tracking of Very SmallLow Contrast Objects [C]. British Machine Vision Conference,2001,599-608
    [24] E J Candes.Ridgelets:Theory and Applications [D].USA:Department ofStatistics,Stanford University,1998
    [25] E L Pennec,S Mallat.Image compression with geometrical wavelets [A].InProc.of ICIP'2000[C].Vancouver,Canada,September.2000.661-664
    [26] M N Do,M Vetterli.Contourlets Beyond Wavelets [C].Academic Press,2002
    [27]石丹,李庆武,倪雪.基于Contourlet变换的红外图像非线性增强算法[J].光学学报,2009,29(2):342-346
    [28]刘瑞明,刘尔琦,杨杰等.核Fukunage-Koontz变换检测红外弱小目标[J].红外与毫米波学报,2008,27(1):47-51
    [29] Yong Yang, Yang Xinfang, Wang Bingxun, et al. A Small Target DetectionMethod Based on Generalized S-Transform [C]. International Conference onApperceiving Computing and Intelliqence Analysis,2008:189-192
    [30]李欣,赵亦工,陈冰.基于分类的红外云层背景弱小目标检测方法[J].光学学报,2009,29(11):3036-3042
    [31]万明,张凤鸣,雷洪利等.一种利用十字窗口识别红外弱小目标的新方法[J].光子学报,2011,40(5):764-767
    [32] Otsu N. A threshold selection method from gray-level histogram [J]. IEEE Trans.on Systems, Man, and Cybernetics,1979,9(1):62-66
    [33] Beghdadi A, Negrate AL, Lesegno P. V. Entropic thresholding using a blocksoure model [J]. Computer Models Image Process,1995,57:197-205
    [34] Torr P.H.S, Zisserman A. Concerning Bayesian motion segmentation, modelaveraging, matching and the trifocal tensor [C]. Fifth European Conference onComputer Vision.Germany Freiburg: Springer Verlag,1998
    [35] Changfa Xu, Minghong Pi, Chunxi Zhu, Guokuan Li. Interpolating-wavelet andits application [J]. In Proceedings of SPIE Vol,35-45
    [36] L. H. Sun, Y. Z. Wang, Y. Q. He. Design and Implement of Infrared Small TargetReal-time Detection System Based on Pipeline Technology [C].27th InternationalCongress on High-Speed Photography and Photonics, Xi'an, China,2007. Proc. ofSPIE,6279-6283
    [37]杨卫平,李吉成,沈振康.分层投票表决目标检测方法及其性能分析[J].红外技术,2003,25(6):10-13
    [38]邹江威,陈曾平.应用形态学与图像流法的空间小目标提取方法[J].光电工程,2005,32(4):13-15
    [39] Reed I S, Gagliardi R M, Stotts L. Optical Moving Target Detection with3-DMatch Filtering [J]. IEEE Trans. on Aeros. Electron. Sys.,1998,24(4):327-336
    [40] Blostein S D, Huang T S. Detecting Small Moving Objects in Image SequencesUsing Sequential Hypothesis Testing [J]. IEEE Trans on Signal Processing,1991,39(7):1611-1629
    [41] Liou R, Azimi Sadjadi M R. Detection of Dim Target in High ClutteredBackground Using High Order Correlation Method [J]. IEEE Trans on Aerospace andElectronic System,1993,28(3):840-856
    [42] Wax N. Signal-to-noise improvement and the statistics of tracking populations[J]. Journal of Applied Physics,1955,26(10):586-595
    [43] Sittler R W. An optimal data association problem in surveillance theory [J].IEEETransactions on Military Electronics,1964,8(2):125-139
    [44]朱自谦,王淑兰.多目标跟踪(MTT)技术的发展[J].航空电子技术,1995,3:48-51
    [45] M. R. Morelande, S. Challa. Manoeuvring Target Tracking in Clutter usingParticle Filters [J]. IEEE Trans. Aeros. Electron.Sys.2005,41(1):252-269
    [46]杨磊.复杂背景条件下的红外小目标检测与跟踪算法研究[D]:[博士学位论文].上海:上海交通大学,2006
    [47]陈晓荣,陈淑芬.变维卡尔曼滤波实现运动目标的跟踪[J].仪器仪表学报,2006,27(9):1163-1166
    [48] Bar-Shalom Y, Fortmann T. Tracking and data association [M].Acad. Press.New York.1988
    [49] D. L. Alspach, H. W. Sorenson. Nonlinear Bayesian Estimation using GaussianSum Approximation [J].IEEE Trans. on AC,1972,17(4):439-448
    [50] Julier S, Uhlmann J. A new extension of the Kalman filter to nonlinear systems[C].Proc. SPIE,1997,3068:182-193
    [51] S. Zhou, R. Chellappa, B. Moghaddam. Visual Tracking and Recognition usingAppearance-adaptive Models in Particle Filters [J]. IEEE Trans. Image Proc.2004,13(11):1491-1505
    [52] C. Chang, R. Ansari. Kernel Particle Filter for Visual Tracking [J]. Signal Proc.Lett.2005,12(3):242-245
    [53]张辉,赵保军,唐林波等.变维卡尔曼滤波实现运动目标的跟踪[J].光学学报,2010,30(5):1291-1296
    [54]严柏军,郑链,王克勇.基于不变矩特征匹配的快速目标检测算法[J].红外技术,2001,23(6):8-11
    [55]梁敏,刘贵喜.基于自适应混合滤波的多目标跟踪算法[J].光学学报,2010,30(9):2554-2561
    [56]蒋永馨,金俣欣,王孝通等.基于马尔可夫随机场的运动目标检测[J].计算机工程与应用,2010,46(15):182-184
    [57]孔军,汤心溢,蒋敏等.采用尺度空间特征点匹配的红外目标跟踪[J].红外与激光工程,2011,40(11):2104-2109
    [58]邓晓波.杂波中的弱小目标检测与跟踪研究[D]:[博士学位论文].成都:电子科技大学,2010
    [59]徐军.红外图像中弱小目标检测技术研究[D]:[博士学位论文].西安:西安电子科技大学,2003
    [60] R. Edmondson, M. Rodgers, M. Banish. Ranganath.Single-Frame ImageProcessing Techniques for Low-SNR Infrared Imagery [J]. Infrared Technology andApplications. Proc. of SPIE.2008,6940:6943
    [61]李朝晖,陈明.对于杂散背景中的目标红外成像特性研究[J].红外技术,2005,27(2):109-114
    [62]张天序.成像自动目标识别[M].湖北科学技术出版社,2005:41-51
    [63] Gonzalez R. C, Woods R. E. Digital Image Processing,2nd Edition [M]:2003
    [64] Muller M. Saliency Measures in Cluttered IR Images for ATR [C].SPIE. Apr1999.150-154
    [65] Christopher W K. Infrared target detection: signal and noise sensitivity analysisthesis [J]. Dec1989.15~20
    [66]吴成柯,戴善荣,陆心如.图像通信[M].西安:西安电子科技大学出版社,1990
    [67]吴文健,胡碧茹,满业辉译.地面目标和背景的热红外特性[M].北京:国防工业出版社,2004
    [68]王东鹤.周扫式多谱段战地预警系统的研究[D]:[博士学位论文].北京:中国科学院研究生院,2010
    [69]徐南荣,卞南华.红外辐射与制导[M].北京:国防工业出版社,1997
    [70]郝继平,黄平华,杜成功.红外搜索设备作用距离等效分析与应用[J].应用光学,2004,25(4):41-44
    [71]张弘,赵保军,毛二可.复杂背景下红外点目标检测的预处理[J].红外与激光工程,2001(2),96-100
    [72]林长青,孙胜利,陈桂林.复杂背景下含点目标单帧红外图像的预处理[J].激光与红外,2006(9):900-903
    [73]张艳晶.复杂云背景下红外运动小目标检测算法研究[D]:[硕士学位论文].北京:国防科技大学,2003
    [74]吴巍.红外图像序列小目标的特性分析与检测[J].红外与激光工程,2002,31(2):146-149
    [75]陈朝阳,张桂林.提高红外点目标图像单帧检测概率的背景抑制法[J].华中理工大学学报,1997,27(6):21-24
    [76] Alexis P.Tzannes, Dana H.Brooks. Point Target Detection in IR ImageSequences. A Hypothesis-testing Approach Based on Target and Clutter TemporalProfile Modeling [J]. Opt. Eng,2000,39(8).2270-2278
    [77]安毓英,曾晓东.光电探测原理[M].西安:西安电子科技大学出版社,2004
    [78] ChristoPher WK.Infrared target deteetion:signal and noise sensitivity analysisthesis [C].SPIE,1989.AD207-215
    [79] Nishiguchi K, Kobayashi M, Ichikawa A.Small Target Detection from ImageSequences Using Recursive Max Filter[C].SPIE.1995.153-165
    [80]艾斯卡尔.红外搜寻与跟踪系统关键技术研究[D]:[博士学位论文].成都:电子科技大学,2002
    [81]高颖慧,李吉成,沈振康.外小目标检测的预处理技术研究[J].红外与激光工程,2004,33(2),154-158
    [82]韩客松.复杂背景下红外点目标检测的预处理[J].系统工程与电子技术,2000,22(l):52-54
    [83]冈萨雷斯.数字图像处理[M].北京:电子工业出版社,2004:186-196
    [84] Barnett J.Statistical analysis of median subtraction filtering with application topoint target detection in inrfared background [J]. Proc. SPIE.1989,1050:10-18
    [85]崔屹.数字图像处理技术与应用[M].北京:电子工业出版社,1993
    [86]陈贺新.非线性滤波器与数字图像处理[M].北京:国防工业出版社,1997
    [87]张黄群,于盛林,白银刚.形态学图像去噪中结构元素选取原则[J].数据采集与处理,2008,23(12):81-83
    [88]汪国有,陈振学,李乔亮.复杂背景下红外弱小目标检测的算法研究综述[J].红外技术,2006,28(5):287-292
    [89]董鸿燕,李吉成,沈振康.基于高通滤波和顺序滤波的小目标检测[J].系统工程与电子技术,2004,26(5):596-598
    [90]杨磊.复杂背景条件下的红外弱小目标检测与跟踪算法研究[D]:[博士学位论文].武汉:华中科技大学博士论文,2006
    [91] Mallat S, Hwang W L. Singularity detection and processing with wavelets. IEEETrans. Inform. Theory,1992,38(2):617-643
    [92] Mallat S. A wavelet tour of signal processing (Second edition)[M].Beijing:China Machine Press,2002
    [93] Li Guokuan, Peng Jiaxiong, Li Hong. Infrared imaging dim target detectionbased on wavelet transform [J].Huazhong Univ of Sci&Tech,200028(5):69-71
    [94]秦翰林,周慧鑫,刘上乾.基于二代小波变换的红外图像非线性增强算法[J].光学学报,2009,29(2):353-356
    [95] R. C. Gonzalez, R. E. Woods.数字图像处理(第二版)[M]:阮秋琦,阮宇智译.北京:电子工业出版社.2003
    [96]范玉雷.复杂背景下的红外弱小目标检测[D]:[硕士学位论文].西安:西安电子科技,2008
    [97]冉启文,谭立英.小波分析与分数傅里叶变换及应用[M].国防工业出版社,2003
    [98]朱斌,樊祥,马东辉等.天空红外图像非平稳背景的小波域抑制[J].红外与激光工程,2008, S2:635-637
    [99] Guo K, Labate D. Optimally sparse multidimensional representation usingshearlets [J]. SIAM J. Math Anal.2008,39(1):298-318
    [100] Miao Q G, Shi C, Xu P, et al. A novel algorithm of image fusion usingshearlets [J]. Optics Communications,2010,284(6):1540-1547
    [101] Da Cunha A L, Zhou J P, Do M N. The nonsubsampled contourlet transform:theory, design,and applications [J]. IEEE Transactions on Image Processing,2006,15(10):3089-3101
    [102] Kutyniok G, Labate D. Resolution of the wave front set using continuousShearlets [J]. Transactions of The American Mathematical society,2009,361(5):719-754
    [103]侯建华,田金文.基于贝叶斯最大后验估计的局部自适应小波去噪[J].计算机工程,2006,32(11):13-16
    [104] Donoho D L, Johnstone I M. Adapting to Unknown Smoothness via WaveletShrinkage [J]. Journal of the American Statistical Assoc.,1995,90(12):1200-1224
    [105]王彪,李建文,王钟斐.基于小波分析的新阈值去噪方法[J].计算机工程与设计,2011,32(3):1099-1103
    [106]李财莲,李志先,孙即祥,等.一种新的小波收缩统一阈值函数[J].国防科技大学学报,2012,34(1):155-159
    [107] Donoho D L, Johnstone I M. Ideal Spatial Adaptation Via Wavelet Shrinkage[J]. Biometrika,1994,81(3):425-455
    [108]李欣,赵亦工,陈冰.基于分类的红外云层背景弱小目标检测方法[J].光学学报,2009,29(11):3036-3047
    [109]高陈强,田金文,土鹏.基于时域特性分析的红外运动小目标检测算法[J].红外与激光工程,2008,37(5):907-910
    [110]邹瑞滨,史彩成,毛二可.基于剪切波变换的复杂海面红外目标检测算法[J].仪器仪表学报,2011.32(5):1103-1107
    [111]张必银,张天序,桑农等.红外弱小运动目标实时检测的规整化滤波方法[J].红外与毫米波学报,2008,27(2):95-100
    [112]张强,蔡敬菊,张启衡等.基于局部极大值的红外弱小目标分割方法[J].红外技术,2011,33(1):41-44
    [113] Ostu N.A Threshold Selection Method from Gray-Level Histogram [J].IEEETrans.On Systems,Man And Cybernetics,1979,9(1):62-66
    [114]王博,张建奇.红外运动弱小目标的动态规划检测[J].电子科技大学学报,2009,38(4):613-616
    [115]王凯,孙德宝,彭嘉雄.红外图像序列运动小目标的图像流检测法[J].华中理工大学学报,1998,26(9):1-4
    [116] Reed I S, Gagliardi R M, Shao H M. Application of Three-DimensionalFiltering to Moving Target Detection [J]. IEEE Trans.on Aeros.Electron.Sys.,1983,19(6):898-905
    [117]肖利梅,曹洁,李策.基于多尺度相位谱的显著性运动目标检测[J].兰州理工大学学报,2011,37(4):90-94
    [118] D.J. Gregoris, S.K.W. Yu, S. Tritchew. Detection of dim targets in FLIRimagery using multiscale transforms [J]. Proceedings of the SPIE,1994(2269),62–71
    [119]孔军,汤心溢,蒋敏等.采用尺度空间特征点匹配的红外目标跟踪[J].红外与激光工程,2011,40(11):2104-2109
    [120]秦翰林,周慧鑫,刘群昌等.采用多尺度隐式马尔可夫模型的红外图像背景抑制[J].光学精密工程,2011,19(8):1950-1956
    [121]李鹏,陈钱,郑海鸥等.基于复杂背景的红外小目标图像预处理方法[J].红外与激光工程,2011,40(5):958-962
    [122]高晶,孙继银,刘婧等.基于区域模糊阈值的前视红外目标识别[J].光学精密工程,2011,19(12):3056-3063
    [123] Z. Zhang, Z. Cao, T. Zhang, L. Yan, Real-time detecting system for infraredsmall target[C]. Proceedings of the SPIE2007(6786),648-656
    [124]刘兴淼,王仕成,赵静.结合统计分布和非下采样Contourlet变换的红外小目标检测[J].光学精密工程,2011,19(4):908-915
    [125]吴一全,罗子娟.基于最小二乘支持向量机时域背景预测的红外弱小目标检测[J].兵工学报,2010,31(6):678-684
    [126]谭园园.前视红外目标检测与跟踪技术研究[D]:[硕士学位论文].西安:第二炮兵工程学院,2006
    [127]李龙.面向精确制导的红外目标检测、识别与跟踪技术研究[D]:[硕士学位论文].西安:第二炮兵工程学院,2007
    [128]侯志强,韩崇昭.视觉跟踪综述[J].自动化学报,2006,32(4):603-618
    [129]冯洋.多目标跟踪的数据关联算法研究[D]:[硕士学位论文].西安:西安电子科技大学,2008
    [130] A. Bal, M. S. Alam. Automatic Target Tracking in FLIR Image Sequences[C].Proc. of SPIE, Automatic Target Recognition XIV2004,5426:30-36
    [131]袁红卫,卢雁,毛海岑等.基于光流的运动小目标检测算法[J].光学与光电技术,2012,10(1):67-70
    [132]聂火亘,陈怀民,朱怡安.一种用于目标检测的复合差分法[J].西北工业大学学报,2009,27(1):88-92
    [133]魏瑞斌.基于多特征的运动目标跟踪[D]:[硕士学位论文].西安:西北大学,信号与信息处理,2007
    [134]徐琨,杨小军,郭兰英.一种基于空间直方图的多特征目标跟踪算法[J].计算机工程与应用,2012,48(19):28-31
    [135]孙荣春,孙俊喜,宋雪.一种基于多特征模型的Mean shift跟踪算法[J]:半导体光电,2011,32(5):733-736
    [136]牛长锋,刘玉树.融合多特征的粒子滤波目标跟踪算法[J]:华中科技大学学报(自然科学版),2010,38(1):18-21
    [137]祝琨.基于双目视觉信息的运动物体实时跟踪与测距[D]:[硕士学位论文].北京:北京交通大学,信号与信息处理,2008
    [138]钟左峰.双目视觉下运动目标的轨迹生成与分析[D]:[硕士学位论文].广州:广东工业大学,计算机应用技术,2011
    [139] SHAN C F, TAN T N, WEI Y CH. Real-time hand tracking using amean-shift embedded particle filter [J]. Pattern Recognition.2007,40:1958-1962
    [140]李荣华.基于AdaBoost与粒子滤波的人脸检测与跟踪[D]:[硕士学位论文].南京:南京理工大学,控制理论与控制工程,2010
    [141]蒋蔚.粒子滤波改进算法研究与应用[D]:[博士学位论文].哈尔滨:哈尔滨工业大学,2010
    [142]田隽.基于粒子滤波的视频目标跟踪算法的研究[D]:[博士学位论文].江苏:中国矿业大学,2010
    [143]程水英,张剑云.裂变自举粒子滤波[J]:电子学报,2008,36(3):500-504
    [144] Gordon N, Salmond D, SMITH A. Novel approach to nonlinear/non-gaussianbayesian state estimation[J]. IEE Proceedings on Radar and Signal Processing,1993,140(2):107-113
    [145] Ting Y, Ying W. Collaborative Tracking of Multiple Targets [C]. Proceedingsof IEEE Conference on Computer Vision and Pattern Recognition. Washington, DCIEEE Press,1995
    [146] Chang C and Ansara R. Kernel particle filter for visual tracking [J]. IEEESignal Processing Letters.2005,12(3):242-245
    [147] Shan C F, Tan T N, Wei Y CH. Real-time hand tracking using a mean-shiftembedded particle filter [J]. Pattern Recognition.2007,40:1958-1962
    [148] Darroch J N, Lauritzen S L, Speed T P. Markov-field and log-linear modelsfor contingency tables [J]. Annals of Statistics,1980,8(3):522-539
    [149] Edwards D. Introduction to Graphical Modelling [M]. Springer-Verlag,2ndedition,2000
    [150] Patrick P, Vermaak J. Data fusion for visual tracking with particle [J]. IEEE,2004,92(3):495-513
    [151]蒋永馨,金俣欣,王孝通等.基于马尔可夫随机场的运动目标检测[J].计算机工程与应用,2010,46(15):182-184
    [152] Paragios N, Rsmesh V. A MRF-based approach for real-time subwaymonitoring [C]. Processing of Computer Vision and Pattern Recognition,2001:295-313
    [153]薛陈,朱明,陈爱华.一种鲁棒的基于改进Mean-shift的目标跟踪算法[J].光学精密工程,2010,18(1):234-239
    [154]郭伟.复杂背景下红外目标检测与跟踪[D]:[博士学位论文].西安:西安电子科技大学,2008
    [155]李宏东,姚天翔译.模式分类[M].北京:机械工业出版社,2003
    [156]韩非,胡春梅,李伟.TMS320C6000系列DSP开发应用技巧[M].北京:中国电力出版社,2008
    [157]赵海霖,韦文,汤俊.多DSP平台下性能预测算法[J]:信息与电子工程,2011,9(4),472-477
    [158]尹九阳,方滨兴,张宏莉.基于单程序多数据流并行软件的性能预测法[J]:清华大学学报(自然科学版),2005,45(4),509-512

© 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