摘要
飞机泊位自动引导的实施对提高机场信息化和自动化水平至关重要，基于视觉的泊位自动引导方法因为具有信息丰富、效果直观及成本低等优点一直受到国内外学者的关注。利用图像处理技术检测飞机边缘轮廓，识别出飞机机型进而跟踪，完成自动引导关键技术算法研究。本文主要针对特殊天气下利用图像处理手段，重点研究了满足特殊天气下泊位图像去噪等预处理算法、泊位飞机的轮廓检测、识别和跟踪等自动引导的关键技术。
首先，深入研究了特殊天气环境下图像增强和去噪等预处理算法。针对光照过强、夜间等特殊环境光照条件导致对比度不均衡问题，提出了分段变换方法，此算法实现简单，运算速度快，提高了图像对比度，能够满足系统的实时性要求；针对雾霾天气时能见度降低，造成检测识别困难，提出了基于暗原色优先的形态学去雾算法，有效提高目标的清晰度，保留图像细节边缘，去雾效果自然逼真，同时满足实时性和鲁棒性要求。
其次，针对目标飞机分割问题研究了边缘检测算法和阴影分割算法。在边缘检测方面，针对边缘的细节及噪声问题，提出了基于自适应权重边缘检测算法；在图像分割方面，运动物体的阴影被标记为前景会增加目标识别和跟踪算法的复杂度，提出了一种将形态学的幂变换与无边界主动轮廓线模型结合的阴影分割算法，牺牲很短的数学形态学平滑的时间，换来了主动轮廓的快速收敛，从而减少了总的运算时间，并且抑制了泊位飞机分割产生的“拖尾”现象，准确有效的分割出运动目标的阴影区域。
再次，研究了基于加权形态学的泊位飞机的特征提取和基于神经网络的飞机识别方法。针对特征提取问题，提出利用加权形态学提取飞机的特征，解决了飞机机型匹配难题，形态学提取目标特征，同时去除了图像噪声，提高识别环节的准确性和效率，然后应用神经网络进行机型识别，取得了较好效果，实现低能见度下飞机机型识别，算法具有稳健性、准确性。
最后，为了提高飞机跟踪的准确性，首先对均值漂移算法和传统粒子滤波算法的优缺点进行分析，在此基础上提出了递增自调整粒子滤波跟踪算法，采用递增自调整和位姿估计器使粒子向最优方向处移动，解决重采样过程中丧失多样性的问题，实现了采样粒子数量少，能够“智能”找到最优状态，仿真结果表明该算法具有良好的鲁棒性。
仿真实验表明：所提出的算法对视觉飞机泊位引导系统的检测、机型识别和跟踪定位都有明显的提高，有一定的实用价值。
The implementation of aircraft docking auto-guide to improve airport the level of informationand automation is essential, a method based on visual docking auto-guide because theinformation-rich, intuitive effects and low cost has been subject to the attention of scholars at homeand abroad. Image pre-processing and identification and tracking of the various aircraft in differentweather conditions restrict multifaceted uncertain factors, so the difficulty of visual docking guidanceand key technologies, thisarticle focuses on four aspects of work.
Firstly, the conducting depth studies of image preprocessing algorithms of image enhancementand denoising in special weather conditions. In order to better adjust the contrast of image, thepiecewise linear transformation algorithm is proposed, which is simple, fast operation, to meet thereal-time requirements of the system. For fog weather, a novel improved edge detection method isproposed based on dark color priority and morphology defogging algorithm, which improves theclarity of the goal, preserves image detail edge to natural and realistic defogging, while meeting thereal-time and automatic requirements.
Secondly, the segmentation of guided objects is researched. In edge detection, a new adaptiveweighted edge detection algorithm is proposed which takes into account the details of the edge andnoise removal. In the segmentation, taking into account the shadow of a moving object is marked forthe prospects to increase object tracking difficulty, matching the complexity of the algorithm as wellas posture evaluation algorithm, proposed a power transformation of the morphology of andborderless active contour model combined with the shadow segmentation algorithm, which not onlyfilters noise and preserves image details, improves the shadow segmentation precision, but alsoreduces the times of iteration. It also exploits the potential that active edgeless contour can be used inimages with complex backgrounds. Consequently preferably solve docking aircraft image objectpartition question.
Thirdly, for the features extraction and recognition of aircraft objects, this article analyzes theinvariant moments of rotation, translation, scale invariance, a fast and effective identification methodis proposed which apply weighted morphological to be preprocessing simultaneous extraction of thecharacteristics of the aircraft, to solve the problem of aircraft models to match. Morphologicalfeatures in the feature extraction to remove image noise, improved recognition accuracy andefficiency, to achieve the robustness, the neural network model identification to solve the problem in the docking system, and achieved good results and accuracy of low visibility automatic dockingguided system.
Finally, this paper analyzed the advantages and disadvantages of the MS and the traditionalparticle filter algorithms, an improved particle filter tracking algorithm is proposed to accurately trackthe docking aircraft Algorithm uses incremental self-adjustment and posture estimation and allowsparticles to move at the optimum direction, it solves the loss of diversity in the resampling process.The algorithm realized the small number of sample particles and capable of "smart" to find theoptimal state, the experiments show that the algorithm has good robustness.
Simulation results show that: the proposed algorithms for the detection and model identificationand tracking of visual docking guidance system have significantly improved; there is a high value inengineering.
引文
[1] Thomas A. Stasko. Aircraft docking system. US,4249159,1981,2.
[2]高庆吉，支源，胡琢，王立文.泊位引导系统中运动物体的检测与分类[J].中国民航大学学报,2007,25(1):7-11.
[3] Siemens Aktiengesellschaft. Docking system for airport terminals. US,6542086,2003,4.
[4] Safegate Internat AB. Aircraft identification and docking guidance systems. US, CN,1399767,2003,03.
[5] Honeywell International Inc. Autonomous landing guidance system. US,6591171,2003,7.
[6]胡丹丹，高庆吉，支源.背景分割和阴影检测算法研究[J].中国图象图形学报,2008,8:1486-1491.
[7]张心柯.基于机器视觉的目标跟踪算法研究[D].天津，中国民航大学,2007.
[8]高庆吉，韩广东，陈浩.信息融合技术在机场泊位系统中的应用[J].微计算机信息,2008,24(30):32-34.
[9]李国，杨国庆，张心珂等.一种基于尺度不变特征点的运动目标检测算法[J].信息与控制，2008,37(3):280-283.
[10]姜恒乐，吕继荣.关于机场激光引导系统的Matlab仿真[J].机场工程,2007(3):7-10.
[11]马思慧.基于对目安全二极管激光定位的飞机泊位引导系统[J].电子产品世界，2005(01A):82-84.
[12] Ali S Z, Choudhry M A. A generalized higher order neural network for aircraft recognition in avideo docking system [J]. Neural Computing&Applications,2010,19(1):21-32.
[13] Kashani H R, Saridis G N. Intelligent control for urban traffic systems [J]. Automatic,1983,19(2):191-197.
[14] Sage K. and S. Young. Computer vision for security applications.1998:2-5.
[15] Marr D and Poggio T. A. A computational theory of human stereo vision[C]. Proc. Royal Soc.London,1979,204:201-328.
[16] Chaumete F andBoukir S. Structure from motion using an active vision paradigm[C]. PatrenRecognition, Conference A: Computer Vision and Applications, Proceedings,1992,1:41-44.
[17] Gaspar J. N. Winters and J. Santos Victor.Vision-based navigation and environmentalrepresentations with an omni directional camera. Robotics and Automation[C]. IEEETransactions,2000,16(6):890-898.
[18] Davidson G, Grifftths H D. Wavelet detection scheme for small target in sea clutter [J]. IEEEElectronics Letters,2002,38(19):1128-1130.
[19]贾云得.机器视觉[M].科学出版社,北京,2000:56-58.
[20] Cheng S C S, Kamath C．Robust techniques for background subtraction in urban traffic video[C].Proceeding of SPIE．San Jose,2004:881-892.
[21] Xiang Shiming, Chen Rui, Deng Yu, et al．Motion segmentation via on-line Gaussian mixturemodel and texture[J]．Journal of Computer-Aided Design&Computer Graphics,2005,17(7):1504-1509.
[22]骆云志，刘志红.视频监控技术发展综述[J].兵工自动化,2009,28(1):1-3.
[23]单勇.复杂条件下视频运动目标检测和跟踪[D].北京，国防科技大学,2006.
[24]潘金山，苏志勋.运动细节估计的光流场方法[J].计算机辅助设计与图形学学报,2011,23(8):1433-144.
[25]张泽旭，李金宗，李宁宁.基于光流场分割和Canny边缘提取融合算法的运动目标检测[J].电子学报,2003,31(9):1299-1302.
[26] Endres G G, Edwards G. Jane’s Airline Recognition Guide [R]. Oleksandr74,2010.
[27]阮秋琦.数字图像处理学[M].北京,电子工业出版社,2001.
[28] Wren C, Azarbayejani A, Darrell T, et al. Pfinder: Real-time tracking of the human body [J].IEEE Trans Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[29] Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking[C].Proceedings of the1999IEEE Computer Society Conference on Computer Vision and PatternRecognition,1999,2:246-252.
[30] Kaew TraKulPong P, Bowden R. An improved adaptive background mixture model for realtimetracking with shadow detection[C].2nd European Workshop on Advanced Video BasedSurveillance Systems,2001,53(8):1-5.
[31] Zivkovic Z, Van der Heijden F. Recursive unsupervised learning of finite mixture models [J].IEEE Trans Pattern Analysis and Machine Intelligence,2004,26(5):651-656.
[32] Kassm, witkina. Snakes: Active contourmodels [J]. Interna-tional Journal on ComputerVision,1988,1(4):321-331.
[33]李培华，田文.主动轮廓模型(蛇模型)综述[J].软件学报,2001,11(6):751-757.
[34] Vieren C, Cabestating F, Postaire J. Catching moving objects with snakes for motion tracking [J].Pattern Recognition Letters,1995,16(7):679-685.
[35]叶昆权，战荫伟.结合数学形态学和无边界主动轮廓模型的图像分割方法[J].计算机应用,2009,29(9):2398-2405.
[36]吴佳，张永红，白净等.基于分水岭变换和主动轮廓模型的舌体轮廓图像分割[J].清华大学学报:自然科学版,2008,48(6):32-38.
[37]杨珺，史忠科.基于小波提升框架的交通目标检测与跟踪[J].交通信息与安全,2011,29(5):135-139.
[38] Stringa E.Morphological change detection algorithms for surveillance applications[C]. BritishMachine Vision Conference, Bristol,2000:402-411.
[39]汪林林，杨帆，王佐成.自适应多方向模糊形态学边缘检测算法[J].计算机应用研究,2009,26(3):1177-1179.
[40] Lihui Jiang, Deming Ren and Xuhu Lu. Speckle suppressing based on morphological filter andfuzzy logic [J]. Chinese Optics Letters,2003,1(12):689-691.
[41] Lihui Jiang, Yanying Guo. Image edge detection based on adaptive weighted morphology [J].Chinese Optics Letters,2007,5(2):77-78.
[42] M. H. Sedaaghi and Q. H. Wu. Weighted Morphological filter [J]. Electronics Letter,1998,34(2):1566-1567.
[43] P. Soille and H. Talbot. Directional morphological filtering[C]. IEEE Trans.Pattern Anal.Machine Intell,2001,23(11):1313-1329.
[44] Bai Hongliang, Liu Changping. A hybrid license plate extraction method based on edge statisticsand morphology [J]. Pattern Recognition,2004,2(8):831-834.
[45] Haritaoglu I, Harwood D and Davis L. W4:real-time surveillance of people and their activities[J].IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
[46] McKenna S et al．Tracking groups of people[J]．Computer Vision and Image Understanding,2000,80(1):42-56.
[47] Park, Jin Yeong, Jun, et al. Experiments on vision guided docking of an autonomous underwatervehicle using one camera [J]. Ocean Engineering,2009,36(1):48-61.
[48] Ning H Z, Tan T N, Wang L, et al. People tracking based on motion model and motionconstraints with automatic initialization [J]. Pattern Recognition,2004,37(7):1423-1440.
[49] Frideman N and Russell S. Image segmentation in video sequences: a probabilistic approach[C].Proc the Thirteenth Conference on Uncertainty in Artificial Intelligence, Rhode Island,1997,86-89.
[50] Thompson W B, Pong T C. Detection moving objects [J]. Int J Comp Vision,1990(4):39-57.
[51] Tsaia, Yezzia, Willsky A S. A curve evolution approach to smoothing and segmentation using theMumford-Shah function [C]. Proceedings of the2000IEEE Computer Society Conference onComputer Vision and Pattern Recognition. Washington,2000:119-124.
[52]龚芳，张学武，孙浩.基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测[J].光学学报,2012,32(4):169-177.
[53] Osama Masoud, Nikolaos P, Papanikolopoulos. A Novel Method for Tracking and CountingPedestrians in Real-Time Using a Single Camera[J]．IEEE Transactions on Vehicular Technology,2001,50(5):1267-1278.
[54] Chang T, Gong S and Ong E．Tracking multiple people under occlusion using multiplecameras[C]. British Machine Vision Conference, Bristol, UK,2000:566-575.
[55] Giovanni Sebastian, Sebastiano Stramaglia. A Bayesian approach for the median filter in imageprocessing [J]. IEEE Transaction on signal processing,1997,62:303-309.
[56] Wang J Y, Chen X L, Gao W. Online selection discriminative tracking features using particlefilter[C]. IEEE Conf. On Computer Vision and Pattern Recognition, New York, IEEE Press,2005:1037-1042.
[57] Kwon J, Lee K.M andPark F. C. Visual tracking via geometric particle filtering on the affinegroup with optimal importance functions[C]. Proceedings of the IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2009:991-998.
[58] Nummiaro K, Koller-Meier E, Gool L V. An adaptive color-based particle filter[J]. Image andVision Computing,2003,21(1):100-110.
[59] Isard M, Blake A. Contour tracking by stochastic propagation of conditional density[C].Proceeding European Confonference on Computer Vision, Berlin: Springer-Verlag,1996:343-356.
[60]赵春晖等.视频图像运动目标分析[M].国防工业出版社，北京,2001,6.
[61]李培华.一种新颖的基于颜色信息的粒子滤波器跟踪算法[J].计算机学报,2009,32(12):2455-2463.
[62] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Transaction on PatternAnalysis and Machine Intelligence,2003,4(3):564-577.
[63] Das S, Bhanu B. A system for model-based object recognition in perspective aerial images [J].Pattern recognition,1998,31(4):465-491.
[64] Conrad Sanderson, Danny Gibbins, Stephen Searle. On statistical approaches to target silhouetteclassification in difficult conditions [J]. Digital Signal Processing,2008,18(3):375-390.
[65] Dickmanns E.D. The development of machine vision for road vehicles in the last decade [J].IEEE Intelligent Vehicle Symposium,2002,6(1):268-281.
[66] Zhu H et al. A new local multiscale Fourier analysis for medical imaging [J]. Medical Physics,2003,30(6):1134-1141.
[67] Zhao, T, Nevatia, R. Car detection in low resolution aerial image[C]. Proceedings of the IEEEConference on Computer Vision,2001:710-717.
[68]易子麟，尹东，胡安洲等.基于非局部均值滤波的SAR图像去噪[J].电子与信息学报,2012，34(4):950-955.
[69] Mitsuji Muneyasu, Kentaro Hutta, Takao, Himamoto. Edge preserving smoothing using medianneural hybrid filters [J]. J, franklin. Jnst,1998,335B(5):1145-1156.
[70] OungSik Choi, Raghu Kirshnapuram. A Robust Approach to Image Enhancement Based onFuzzy Logic[C]. IEEE Transaction on Image Processing,1997,6(6):808-825.
[71]吴亚东，孙世新.基于二维小波收缩与非线性扩散的混合图像去噪算法[J].电子学报,2006,1:163-166.
[72] Zong X, Laine A F, Geiser E A, et al. De-noising and contrast enhancement via waveletshrinkage and non-linear adaptive gain [A]. Wavelet Applications3: Proceeding of SPIE,Orlando, FL,1996,2726:566-574.
[73] Dawei Oi and Fan Guo. Medical Image Edge Detection Based on Omni-directional Multi-scaleStructure Element of Mathematical Morphology[C]. Proceedings of the IEEE InternationalConference on Automation and Logistics August Jinan, China,2007:18-21.
[74]胡明昊，任明武，杨静宇.一种基于直方图模式的运动目标实时跟踪算法[J].计算机工程与应用,2004,4(3):72-73.
[75] STARK J A. Adaptive image contrast enhancement using generalizations of histogramequalization [J]. IEEE Transactions on Image Processing,2000,9(5):889-896.
[76]刘莉，吴秀清，牛宗标.模糊图像中的飞机识别方法[J].计算机仿真,2006,23(3):164-166.
[77] Stahl M, Aach T. Et al. Noise resistant weak structure enhancement for digital radiography[A].SPIE Conference on Image Processing, San Diego,1999,2:1406-1417.
[78]支源.机场泊位视觉引导系统关键技术研究[D].天津，中国民航大学，2007.
[79] YF Khellah and P Fieguth. Statistical processing of large image sequences [J]. IEEE Trans.Imageprocessing,2005,14(6):80-92.
[80]崔彦平.运动目标姿态与速度测量的理论与实现研究[D].天津，天津大学,2006.
[81]姜勇.基于计算机视觉导引系统中若干关键技术的研究与实现[D].南京，南京航空航天大学,2006.
[82]王素玉，沈兰荪.智能视觉监控技术研究进展[J].中国图象图形学报,2007,12(9):1505-1514.
[83]胡窦明，赵海生，李云川等.一种基于同态滤波的红外图像增强新方法[J].红外技术,2012,34(4):224-228.
[84] Seow M-J, Asari V K. Ratio rule and homomorphic filter for enhancement of digital colourimage [J]. Neurocomputing,2006,69(7):954-958.
[85]董涛，董慧颖.基于大气调制传递函数的天气退化图像复原方法研究[J].沈阳理工大学学报,2006,25(5):39-42.
[86]詹翔，周焰.一种基于局部方差的雾天图像增强算法[J].计算机应用,2007,27(2):510-512.
[87]孙玉宝，肖亮等.基于偏微分方程的户外图像去雾方法[J].系统仿真学报,2007,19(16)：3739-3744.
[88] Kopf J, Neubert B, Chen B, et al. Deep photo: Model based photograph enhancement andviewing [J]. ACM Transactions on Graphics,2008,27(5):116-1-116-10.
[89] He kaiming, Sun jian and Tang xiaoou. Single image haze removal using dark channel prior [C].Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition,2009:1956-1963.
[90]王燕，伍博等.一种单幅图像去雾方法[J].电光与控制,2011,4(18):65-67.
[91] Fattal R. Single image dehazing[C]. Proceedings of Acmsiggraph Conference2008, Los Angeles,2008.
[92] Tan R. Visibility in bad weather from a single image[C], Proceedings of the IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,2008:1-8.
[93] Horn and Schunck. Determining optical flow [J]. Artificial Intelligence,1981,17:185-204.
[94]陈震，高满屯.图像光流场计算技术研究进展[J].中国图像图形学报,2002,7A(5):434-439.
[95]魏志强，纪筱鹏，冯业伟.基于自适应背景图像更新的运动目标检测方法[J].电子学报,2005,33(12):2261-2264.
[96] Canny J. A computational approach to edge detection[C]. IEEE Transactions on Pattern Analysisand Machine Intelligence,1986,8(6):679-698.
[97] Bajcsy R. Kovag S Multiresolution ethstic matching [J]. Computer vision graphics and imageprocessing,1989,46(1):1-21.
[98]付萍，方帅，徐心和等.视频监控系统中运动目标检测的阴影去除方法[J].计算机工程,2007,33(10):22-24.
[99] Rita Cucchiara, Et al. Improving shadow suppression in moving object detection with HSV colorinformation[C]. The4th International IEEE Conference on Intelligent Transportation System,2001:334-339.
[100]Rosin P L, Ellis T. Image difference threshold strategies and shadow detection[C]. The6thBritish Machine Vision Conference,1994:347-356.
[101]Loncaric, S. A survey of shape analysis techniques [J]. Pattern Recognition,31(8):983-1001.
[102]郭艳颖.基于形态神经网络的识别算法研究与实现[D].天津，中国民航大学,2007.
[103]蒋立辉，赵春晖.基于模糊形态滤波的斑点噪声抑制[J].信号处理,2003,19(5):486-489.
[104]A. Yilmaz, O. Javed and M. Shah. Object tracking: A survey [J]. Proceedings of AcmsiggraphConference Computer Survey,2006,38(4):1-45.
[105]Alessandro Bevilacqua. Effective shadow detection in traffic monitoring applications [J].Journal of WSCG,2003,11(1):57-64.
[106]Jun-Wei Hsieh, Wen-Fong Hu, Chia-Jung Chang, Yung-Sheng Chen. Shadow elimination foreffective moving object detection by Gaussian shadow modeling [J]. Image and Visio Computing,2003,21(6):505-516.
[107]Vieren C, Cabestating F, Postaire J. Catching moving objects with snakes for motion tracking [J].Pattern Recognition Letters,1995,16(7):679-685.
[108]Endres G G, Edwards G. Jane’s Airline Recognition Guide [R], Oleksandr74,2010.
[109]廖闻剑，成瑜.三维飞机自动识别的一种有效方法[J].航空学报,1998,19(6):730-735.
[110]曾鹏鑫.动态场景下多运动目标检测及跟踪方法研究[D].长春，东北大学,2005.
[111]王树国，黄勇杰，张生.可见光图像中飞机目标的特征选择及提取[J].哈尔滨工业大学学报,2010,42(7):1056-1059.
[112]Das S, Bhanu B. A system for model-based object recognition in perspective aerial images [J].Pattern recognition,1998,31(4):465-491.
[113]马时平，毕笃彦，陈岚岚.基于图像匹配技术的飞机识别[J].计算机工程,2004,30(5)：159-160.
[114]张名成，吴秀清，王鹏伟.基于闭合轮廓提取和部分特征匹配的飞机识别[J].计算机仿真,2006,23(11):193-197.
[115]林霖.基于几何特征的飞机部位识别跟踪算法[J].红外,2007,28(8):131-135.
[116]李兴唐，曹立华，王思雯.仿射变换的飞行器识别[J].光学精密工程,2009,17(2):402-408.
[117]Courtney R. L. A broad view of ITS standards in the US[C]. Proceeding of IntelligentTransportation System,1997:529-536.
[118]Heng Wei, Qingyan Yang, Moghorabi A. Improve applicability of ITS-generated data viaprioritizing positioning of surveillance devices over a road network[C]. Proceeding of IntelligentTransportation Systems,2003:590-597.
[119]Wang H, Suter D, Schindler K and Shen C. Adaptive object tracking based on an effectiveappearance filter [J]. IEEE Transactions. Pattern Anal. Mach. Intell,2007,29(9):1661-1667.
[120]Porikli F, Tuzel O andMeer P. Covariance tracking using model update based on lie algebra[C].Proceedings of the IEEE Computer Society Conference on Computer Vision and PatternRecognition,2006:728-735.
[121]Nummiaroa E. K.-M. K andGool L. An adaptive color-based particle filters [J]. Image VisualComputer,2003,21(1):99-110.
[122]Zhang X, Hu W, Maybank S and Li X. Graph based discriminative learning for robust andefficient object tracking[C]. Proc. ICCV,2007:1-8.
[123]Isard M and Blake A. Condensation: Conditional density propagation for visual tracking [J].International Journal Computer Visual.1998,29(1):5-28.
[124]Magee, D. Tracking multiple vehicles using foreground, background and motion models [J].Image Visual Computer.2004,22(2):143-155.
[125]Comaniciu D, Ramesh V. and Meer P. Kernel-based object tracking [J]. IEEE TransactionPattern Analysis Machine Intelligence,2003,25(5):564-577.
[126]Avidan S.Ensemble tracking [J]. IEEE Transaction Pattern Analysis Machine Intelligence,2007,29(2):261-271.
[127]郑永斌，黄新生，丰松江.SIFT和旋转不变LBP相结合的图像匹配算法[J].计算机辅助设计与图形学学报,2010,22(2):286-292.
[128]李远征，卢朝阳，高全学，李静.基于多特征融合的均值迁移粒子滤波跟踪算法[J].电子与信息学报,2010,32(2):411-415.
[129]万卫兵，霍宏，赵宇民.智能视频监控中目标检测与识别[M].上海：上海交通大学出版社,2010.
[130]卢晓鹏，殷学民，邹谋炎.一种基于颜色分别的混合视频跟踪方法[J].电子与信息学报,2008,30(2):259-262.
[131]高涛，何明一，戴玉超，白磷.多级LBP直方图序列特征的人脸识别[J].中国图象图形学报,2009,14(2):202-207.
[132]孙瑾，顾宏斌，郑吉平.一种基于梯度方向信息的运动目标检测算法[J].中国图象图形学报,2008,13(3):571-579.
[133]Comaniciu D, Ramesh V. Mean shift and optimal prediction for efficient object tracking[C]. TheIEEE International Conference on Image Processing,2000:70-73.
[134]Isard M, Blake A. Condensation-conditional density propagation for visual tracking [J]. Journalof Computer Vision,1998,29(1):5-28.
[135]Comaniciu Dorm, Meer Peter．Mean Shift: A Robust Approach Toward Feature Space[J]．PatternAnalysis and Machine Intelligence,2002,24(5):603-619.
[136]Collins R. Mean-shift blob tracking through scale space [J]. Proc IEEE Conference CompterVision Pattern Recognition,2003,6(9):234-240.
[137]Fox D, Hightower J, Liao L. Bayesian filtering for location estimation [J]. IEEE PervasiveComputing,2003,2(3):24-33.
[138]Doucet A, Freitas N. De andGordon N. Sequential Monte Carlo methods in practice[R]. InSpringer-verlag, New York,2001,2.
[139]Changjiang Yang, Ramani Duraiswami and Larry Davis. Efficient mean-shift tracking via a newsimilarity measure[C]. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition,2005:1063-69.
[140]Hager G and Belhumeur P. Real-time tracking of image regions with changes in geometry andillumination[C]. Proceedings of the IEEE Conference on Computer Vision and PatternRecognition,1996:403-410.
[141]Black M. J andJepson A. D. Eigentracking: Robust matching and tracking of articulated objectsusing view-based representation[C]. Proc. ECCV,1996:329-342.
[142]Ross D. A, Lim J, Lin R andYang M. Incremental learning for robust visual tracking [J].International Journal Computer Visual,2008,77(1-3):125-141.
[143]Vijayakumar S, Souza A. D and Schaal S. Incremental online learning in high dimensions [J].Neural Computer,2005,17(12):2602-2634.
[144]Tuzel O, Porikli F and Meer P. Learning on lie groups for invariant detection and tracking[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[145]Zhang X, Hu W, Maybank S et al. Sequential particle swarm optimization for visual tracking[C].Proc. IEEE CVPR,2008:1-8.
[146]Pocok J, Dance S and Lawless A. State estimation using the particle filter with mode tracking [J].Computer Fluids,2011,46(1):392-397.
[147]LiM, Tan Tieniu, Chen Wei and Huang Kaiqi. Efficient object tracking by incrementalself-tuning particle filtering on the affine group [J].IEEE Transactions on Image Processing,2012,21(3):1298-1313.
[148]胡琢.飞机泊位过程建模与三维测距算法研究[D].长春，东北电力大学,2007.