地空背景下扩展目标稳定跟踪技术研究
|
摘要
扩展目标跟踪技术是图像处理领域的一个重要组成部分，在现实生活中也有较强的应用前景。但是，由于目标及其所处背景的多样性，使得没有一种有效的算法可以解决所有的跟踪问题。同时，目标姿态变化、旋转变化、运动模糊及其光照变化等因素的存在，也给跟踪算法的研制带来了困难。目前，虽然有很多成功经典的算法被陆续提出，但是仍有很多问题没有解决。本文针对这些问题，分析了一般目标跟踪算法的组成模块和处理流程以及扩展目标稳定跟踪技术的难点，并且研究了两种经典跟踪算法的优势和缺点。在此基础上，对扩展目标的稳定跟踪技术进行了深入研究。主要包括三个方面：
首先，深入研究特征对扩展目标跟踪算法性能的影响。从特征选择和融合的角度解决扩展目标跟踪问题。文章对扩展目标所具有的、较为常用的特征进行了介绍。对于单个特征不足以对目标进行有效跟踪的问题，考虑使用多个特征融合跟踪。分析了多种特征级别的融合方式。并在此基础上，提出一种基于目标轮廓直线的参数方程和边缘灰度直方图相结合的跟踪算法。首先，利用Hough变换得到待匹配直线的直线参数方程，同时建立该直线边缘的归一化灰度直方图，由此得到的初始模板包含了目标的空间位置和像素分布信息。然后，在后续帧中，利用梯度方向和参数方程对分割后的像素进行聚类，得到多条待匹配直线。最后，利用灰度直方图匹配算法获得直线边缘的精确位置。实验证明该算法对处于复杂背景下、存在局部短时遮挡的、包含直线边缘的目标有很好的跟踪效果。
其次，深入研究模板匹配算法中的关键技术点，包括模板的创建和模板的更新。从解决尺度问题的角度来阐述扩展目标跟踪算法的研究。本文从目标的灰度信息分布特点出发，提出一种基于加权信息熵的初始位置修正算法，首先，在搜索窗口中获取测试样本，然后，计算各个样本的加权信息熵，接着，通过先验信息对样本进行筛选，获得熵值最小区域，从而得到修正后的目标位置。从背景和目标的可区分性上来验证算法的有效性，实验结果表明，该算法对于处在复杂背景下的目标能够正确、可靠稳定的对其位置进行修正。
对于模板尺度修正问题，使用SIFT特征点在前后两帧中的匹配关系求得模板变化的仿射变换参数，由此，对模板尺度进行自适应更新。在Meanshift算法框架下测试算法效果，实验证明，SIFT特征可以有效解决模板尺度更新问题。
最后，深入研究稀疏特征和目标外观模型对扩展目标跟踪算法性能的影响。从目标外观模型的角度阐述扩展目标跟踪问题。压缩跟踪算法作为一种新的算法，具有简单、高效、实时的优点，但该算法依然存在缺陷。首先，在复杂背景或有遮挡等情况下，容易较快的引进误差；其次，跟踪窗口保持不变，使得不能正确跟踪目标位置且不能准确更新正负样本；最后，搜索样本数目大，导致跟踪速度不理想。针对这些问题，利用前后帧跟踪点的直方图对比来判断遮挡的发生，并自适应的改变更新系数；采用在原算法最优匹配点周围小范围多尺度搜索更优位置的方法，来适应目标尺寸的变化；引入粗精跟踪策略，在不同阶段使用不同数量的子特征集进行匹配，以筛选样本、减少计算量。这些改进避免了算法缺陷导致的跟踪失败，提高了跟踪效率。实验证明，改进后的算法比原算法具有更好的鲁棒性且跟踪速度更快。
同时，进一步提出一种新的融合尺度不变特征和压缩特征的目标跟踪算法以解决姿态变换、光照变化、旋转和运动模糊下目标的稳定准确跟踪问题。算法使用压缩特征对目标和背景进行描述，通过在图像帧中采集到的正负样本在线训练和学习支持向量机分类器，将跟踪任务构建为一个二类分类问题。使用该分类器对下一帧的目标和背景进行分类，以从而获得精确的目标位置和区域。同时，算法使用前后两帧的尺度不变特征特征点之间的对应匹配关系求解目标尺寸变化值，从而实现模板大小的自适应调整。将算法与其他算法在某些图像序列上的跟踪比较显示，该算法在有效性、正确性和鲁棒性上性能优越。
Extended target tracking technology is an important part of the field of imageprocessing. There are strong prospects in real life. However, due to the diversity ofthe target and its background which makes no effective tracking algorithm can solveall problems. Simultaneously, it is a challenging task to develop efective andefcient appearance models for robust object tracking due to factors such as posevariation, illumination change, occlusion, and motion blur. While much success andclassical algrithms has been demonstrated, numerous issues remain to be addressed.Aiming at these problems, analyse the blocks and processes of the general targettracking algorithm, as well as difficulties in stabilizing extended target trackingtechnology, and studied two classical tracking algorithm’ advantages anddisadvantages, and on this basis, the stability of the extended target trackingtechniques were studied. Mainly includes three aspects:
Firstly, in-depth study of the impact of the expansion feature target trackingalgorithm performance. Solve the problem of extended target tracking featureselection and fusion perspective. Many commonly features were introdeced. For asingle feature is insufficient to effectively target tracking problem, consider usingmultiple feature fusion tracking. Analyse the way of fusion, and on this basis, anonline combined two kinds of features method for visual object tracking wasproposed. A feature set was built by combining object contour’s linear parametricequation and edge histogram. Firstly, the Hough transform is used to detect line inpicture and obtain the parameters of the line, meanwhile, get the histogram at thesame position of the line. The resulting initial template contains the location andpixel distribution information of the target. Secondly, in the subsequent frames,pixels divided and clustered by gradient direction and parameter equation wouldform more than one line which was to be matched. At last, obtain the exact locationof the straight edge using the histogram matching algorithm. The experimentalresults indicate that the algorithm can run effectively when occlusion andcomplicated backgrounds happened, and perform favorably on challengingsequences in terms of efficiency, accuracy and robustness.
Secondly, in-depth study of the template creation and updating. To solve theproblem from the perspective of the scale change. A modified initial position algorithm based on the weighted information entropy was proposed. At first, obtaintest samples in the search window. Then, calculate the weighted information entropyof each sample. Next, the sample is filtered out by priori information to obtain theminimum entropy region and the corrected target position. According to thedifferences beteen background and objectives to distinguish and verify theeffectiveness of the algorithm. Experimental results show that the algorithm is in thetarget complicated background can correct, reliable and stable correction of itsposition.
For the problem of fixing template scale, use the SIFT feature matchingbetween two frames to obtained the affine transformation parameters which causedby changing in the template, thereby adaptively update the template scale. Test thealgorithm results under the framework of Meanshift. The experiment proved that,SIFT features can effectively solve the problem.
Finally, in-depth study of the characteristics and effects of sparse appearancemodels for extended target tracking algorithm performance. From the perspective ofthe target appearance model describes the expansion of target tracking. Real-Timecompressive tracking was a simple and effective tracking algorithm. However, therewere a number of problems which need to be addressed. First of all, it was easy tointroduce errors due to factors such as occlusion and clutter. Secondly, it couldn’tupdate the positive and negative samples accurately while using fixed trackingwindow. At last, the number of testing samples was too large, which affected thespeed of tracking. The occlusion was checked by comparison between consecutiveframes’ histograms, and the coefficient can be also updated adaptively by thecomparison result. We searched for more specified areas with multi-scales to find outthe best matching place, and to handle scale change of the target on the basis of theoriginal algorithm’s tracking result. The different numbers of sub features sets wereutilized to filter the testing samples. In that case, the speed of tracking process wouldbe improved. The strategies we proposed would improve the original algorithm’sperformance to avoid the failure of tracking. The experimental results indicate thatthe algorithm can run in real-time and perform favorably against state-of-the-artalgorithms on challenging sequences in terms of efficiency, accuracy and robustness.
Further more, In this paper, we propose an algorithm based on SIFT andcompressive features to develop effective and efficient appearance models for robustobject tracking due to factors such as pose variation, illumination change, occlusion, and motion blur. The algrithm describe the target and background with compressivefeatures which labled as positive and negative specimens sampling from frames. Thetracking task is formulated as a binary classification via a SVM classifier with onlineupdate in the compressed domain. In new frame, utilize the classifier to abtain thetarger’s position. Meanwhile, introduce SIFT to solve the target size change, so as toachieve adaptive template size. The proposed tracking algorithm performs favorablyagainst state-of-the-art algorithms on challenging sequences in terms of efficiency,accuracy and robustness.
首先，深入研究特征对扩展目标跟踪算法性能的影响。从特征选择和融合的角度解决扩展目标跟踪问题。文章对扩展目标所具有的、较为常用的特征进行了介绍。对于单个特征不足以对目标进行有效跟踪的问题，考虑使用多个特征融合跟踪。分析了多种特征级别的融合方式。并在此基础上，提出一种基于目标轮廓直线的参数方程和边缘灰度直方图相结合的跟踪算法。首先，利用Hough变换得到待匹配直线的直线参数方程，同时建立该直线边缘的归一化灰度直方图，由此得到的初始模板包含了目标的空间位置和像素分布信息。然后，在后续帧中，利用梯度方向和参数方程对分割后的像素进行聚类，得到多条待匹配直线。最后，利用灰度直方图匹配算法获得直线边缘的精确位置。实验证明该算法对处于复杂背景下、存在局部短时遮挡的、包含直线边缘的目标有很好的跟踪效果。
其次，深入研究模板匹配算法中的关键技术点，包括模板的创建和模板的更新。从解决尺度问题的角度来阐述扩展目标跟踪算法的研究。本文从目标的灰度信息分布特点出发，提出一种基于加权信息熵的初始位置修正算法，首先，在搜索窗口中获取测试样本，然后，计算各个样本的加权信息熵，接着，通过先验信息对样本进行筛选，获得熵值最小区域，从而得到修正后的目标位置。从背景和目标的可区分性上来验证算法的有效性，实验结果表明，该算法对于处在复杂背景下的目标能够正确、可靠稳定的对其位置进行修正。
对于模板尺度修正问题，使用SIFT特征点在前后两帧中的匹配关系求得模板变化的仿射变换参数，由此，对模板尺度进行自适应更新。在Meanshift算法框架下测试算法效果，实验证明，SIFT特征可以有效解决模板尺度更新问题。
最后，深入研究稀疏特征和目标外观模型对扩展目标跟踪算法性能的影响。从目标外观模型的角度阐述扩展目标跟踪问题。压缩跟踪算法作为一种新的算法，具有简单、高效、实时的优点，但该算法依然存在缺陷。首先，在复杂背景或有遮挡等情况下，容易较快的引进误差；其次，跟踪窗口保持不变，使得不能正确跟踪目标位置且不能准确更新正负样本；最后，搜索样本数目大，导致跟踪速度不理想。针对这些问题，利用前后帧跟踪点的直方图对比来判断遮挡的发生，并自适应的改变更新系数；采用在原算法最优匹配点周围小范围多尺度搜索更优位置的方法，来适应目标尺寸的变化；引入粗精跟踪策略，在不同阶段使用不同数量的子特征集进行匹配，以筛选样本、减少计算量。这些改进避免了算法缺陷导致的跟踪失败，提高了跟踪效率。实验证明，改进后的算法比原算法具有更好的鲁棒性且跟踪速度更快。
同时，进一步提出一种新的融合尺度不变特征和压缩特征的目标跟踪算法以解决姿态变换、光照变化、旋转和运动模糊下目标的稳定准确跟踪问题。算法使用压缩特征对目标和背景进行描述，通过在图像帧中采集到的正负样本在线训练和学习支持向量机分类器，将跟踪任务构建为一个二类分类问题。使用该分类器对下一帧的目标和背景进行分类，以从而获得精确的目标位置和区域。同时，算法使用前后两帧的尺度不变特征特征点之间的对应匹配关系求解目标尺寸变化值，从而实现模板大小的自适应调整。将算法与其他算法在某些图像序列上的跟踪比较显示，该算法在有效性、正确性和鲁棒性上性能优越。
Extended target tracking technology is an important part of the field of imageprocessing. There are strong prospects in real life. However, due to the diversity ofthe target and its background which makes no effective tracking algorithm can solveall problems. Simultaneously, it is a challenging task to develop efective andefcient appearance models for robust object tracking due to factors such as posevariation, illumination change, occlusion, and motion blur. While much success andclassical algrithms has been demonstrated, numerous issues remain to be addressed.Aiming at these problems, analyse the blocks and processes of the general targettracking algorithm, as well as difficulties in stabilizing extended target trackingtechnology, and studied two classical tracking algorithm’ advantages anddisadvantages, and on this basis, the stability of the extended target trackingtechniques were studied. Mainly includes three aspects:
Firstly, in-depth study of the impact of the expansion feature target trackingalgorithm performance. Solve the problem of extended target tracking featureselection and fusion perspective. Many commonly features were introdeced. For asingle feature is insufficient to effectively target tracking problem, consider usingmultiple feature fusion tracking. Analyse the way of fusion, and on this basis, anonline combined two kinds of features method for visual object tracking wasproposed. A feature set was built by combining object contour’s linear parametricequation and edge histogram. Firstly, the Hough transform is used to detect line inpicture and obtain the parameters of the line, meanwhile, get the histogram at thesame position of the line. The resulting initial template contains the location andpixel distribution information of the target. Secondly, in the subsequent frames,pixels divided and clustered by gradient direction and parameter equation wouldform more than one line which was to be matched. At last, obtain the exact locationof the straight edge using the histogram matching algorithm. The experimentalresults indicate that the algorithm can run effectively when occlusion andcomplicated backgrounds happened, and perform favorably on challengingsequences in terms of efficiency, accuracy and robustness.
Secondly, in-depth study of the template creation and updating. To solve theproblem from the perspective of the scale change. A modified initial position algorithm based on the weighted information entropy was proposed. At first, obtaintest samples in the search window. Then, calculate the weighted information entropyof each sample. Next, the sample is filtered out by priori information to obtain theminimum entropy region and the corrected target position. According to thedifferences beteen background and objectives to distinguish and verify theeffectiveness of the algorithm. Experimental results show that the algorithm is in thetarget complicated background can correct, reliable and stable correction of itsposition.
For the problem of fixing template scale, use the SIFT feature matchingbetween two frames to obtained the affine transformation parameters which causedby changing in the template, thereby adaptively update the template scale. Test thealgorithm results under the framework of Meanshift. The experiment proved that,SIFT features can effectively solve the problem.
Finally, in-depth study of the characteristics and effects of sparse appearancemodels for extended target tracking algorithm performance. From the perspective ofthe target appearance model describes the expansion of target tracking. Real-Timecompressive tracking was a simple and effective tracking algorithm. However, therewere a number of problems which need to be addressed. First of all, it was easy tointroduce errors due to factors such as occlusion and clutter. Secondly, it couldn’tupdate the positive and negative samples accurately while using fixed trackingwindow. At last, the number of testing samples was too large, which affected thespeed of tracking. The occlusion was checked by comparison between consecutiveframes’ histograms, and the coefficient can be also updated adaptively by thecomparison result. We searched for more specified areas with multi-scales to find outthe best matching place, and to handle scale change of the target on the basis of theoriginal algorithm’s tracking result. The different numbers of sub features sets wereutilized to filter the testing samples. In that case, the speed of tracking process wouldbe improved. The strategies we proposed would improve the original algorithm’sperformance to avoid the failure of tracking. The experimental results indicate thatthe algorithm can run in real-time and perform favorably against state-of-the-artalgorithms on challenging sequences in terms of efficiency, accuracy and robustness.
Further more, In this paper, we propose an algorithm based on SIFT andcompressive features to develop effective and efficient appearance models for robustobject tracking due to factors such as pose variation, illumination change, occlusion, and motion blur. The algrithm describe the target and background with compressivefeatures which labled as positive and negative specimens sampling from frames. Thetracking task is formulated as a binary classification via a SVM classifier with onlineupdate in the compressed domain. In new frame, utilize the classifier to abtain thetarger’s position. Meanwhile, introduce SIFT to solve the target size change, so as toachieve adaptive template size. The proposed tracking algorithm performs favorablyagainst state-of-the-art algorithms on challenging sequences in terms of efficiency,accuracy and robustness.
引文
[1] Blake A, Isard M. Active Contours: The Application of Techniques form Graphics, Vision,Control Theory and Statistics to Visual Tracking of Shapes in Motion[C]. New York:Springer-Verlag,1998
[2] Kenneth. R. Castelman著,朱志刚等译,数字图像处理[M],北京:电子工业出版社,1998.
[3]王健,张桂林.复杂背景下运动目标的实时跟踪[J].计算机与数字工程,Vol33,2005:18-21.
[4]常发亮.彩色图像分割与复杂场景下视觉目标跟踪方法研究[D].济南:山东大学，2005.
[5]王健.均值平移算法在计算视觉中的应用[D].武汉：华中科技大学,2005.
[6]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方法[J].计算机工程与应用,2004.
[7] G. R. Bradski. Computer vision face tracking for use in a perceptual user interface[J], In Proc.IEEE Workshop Applications of Computer Vision,1998,2:214-219.
[8] J. Tua, H. Taob, and T. Huang. Face as mouse through visual face tracking[J], CVIU,2007,108(1-2):35-40.
[9] S. Alberto and J. V. Juan. An approach of visual motion analysis[J]. Pattern RecognitionLetters,2005,26(3):355-368
[10] Collins R. et al. A system for video surveillance and monitoring: VSAM final report[R].Carnegie Mellon University, Technical Report: CMU-RI-TR-00-12,2000.
[11] A. Elgammal, R. Duraiswami, D. Harwood, et a1. Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance[J]. Proceedings of theIEEE,2002,90(7):1151-1163.
[12] R. Babu, P. Patrick, fez, et a1. Robust tracking with motion estimation and localKernel-based color modeling[J], Image Vision Computing,2007,25(8):1205-1216.
[13] W. Hu et al., A Survey on Visual Surveillance of Object Motion and Behaviors[J], IEEETrans. Systems, Man, and Cybernetics, Part C: Applications and Reviews,2004,34(3):334-352.
[14] Harris, W. J., The Development of IVHS in North America[C]. IEEE Vehicle Navigation&Information System Conference Proceedings，1994. Plenary: P.3-10.
[15] M. Naylor C.I.A., Annotated Digital Video for Intelligent Surveillance and OptimizedRetrieval[R].2003，University of Reading and Kingston University: UK.
[16] V. Keanaker and R. Zabih. Bayesian Multi-Camera Surveillance[C]. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1999,1(2):253-259.
[17] Markandey V, Reid A, Wang S. Motion Estimation for Moving Target Detection[J]. IEEETrans on Aerospace and Electronic Systems,1996,32(3):866-874
[18] Tonissen S M, Evans R J. Techniques for Low SNR Target Detection and Tracking[C].International Symposium on Signal Processing and its Application,1996:21-24
[19] Denney B S, Figueiredo R J. Optimal Point Target Detection Using Adaptive AutoRegressive Background Prediction[J]. SPIE,4048(2000):46~57
[20]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报.2006,4(32),603-617
[21] D. Comaniciu and P Meer. MS analysis and applications[C]. IEEE International Conferenceon Computer vision,1999,1(2):1197-1203.
[22] X. Han, P. Zhang and H. Li. MAP Spatial Pyramid Mean Shift for object tracking[C]. SPIEVisual Communications and Image Processing,2010.
[23] H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via online boosting[C]. InBMVC,2006,47-56.
[24] D. Ross, J. Lim, R. Lin and M. Yang. Incremental learning for robust visual tracking[C],IJCV, May2008,77(1):125-141.
[25] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised on-line boosting for robusttracking[C]. In ECCV,2008.
[26] B. Babenko, M. Yang and S. Belongie. Visual Tracking with Online Multiple InstanceLearning[C]. In Proc. IEEE Conf. Comp. Vision Pattern Recognition2009.
[27]王再欢.基于模型的三维飞机目标识别研究[D].西安：西北工业大学硕士学位论文，2005.
[28] Sang-Cheol Park, Sung-Hoon Lim, Bong-Kee Sin, Seong-Whan Lee. Tracking non-rigidobjects using probabilistic Hausdorff distance matching[J]. Pattern Recognition,2005,38:2373-2384
[29] Wu Y., Huang T. S. Robust Visual Tracking by Integrating Multiple Cues Based onCo-Inference Learning. International Journal of Computer Vision.2004,58(1):55-71
[30] Cannons K., Wildes R. Spatiotemporal Oriented Energy Features for Visual Tracking.2007
[31] Roos D., Lim J., Yang M.-H. Adaptive Probabilistic Visual Tracking with IncrementalSubspace Update[C]. Proceedings of the eighth European conference on computer vision. Berlin:Springer,2004:
[32] J. Kwon and K. M. Lee. Tracking of abrupt motion using Monte Carlo estimation[C]. ECCV,2008
[33] Y. Li, H. Ai, T. Yamashita, S. Lao, and M. Kawade. Tracking in low frame rate video: Acascade particle filter with discriminative observers of different lifespans[C]. CVPR,2007
[34] Senior A., Hampapur A., Tian Y.-L., et al. Appearance models for occlusion handling[J].Image and Vision Computing.2006,24(11):1233-1243
[35] Tao Y., Quan P., Jing L., et al. Real-time multiple objects tracking with occlusion handlingin dynamic scenes[C]. Proceedings of IEEE Conference on Computer Vision and PatternRecognition. San Diego, CA, USA:IEEE,2005:970-975
[36] Yilmaz A., Xin L., Shah M. Contour-based object tracking with occlusion handling in videoacquired using mobile cameras[C]. IEEE Transactions on Pattern Analysis and MachineIntelligence,.2004,26(11):1531-1536
[37] Roman G., Ron K., Ehud R., et al. Fast Geodesic Active Contours[C]. Proceedings of theSecond International Conference on Scale-Space Theories in Computer Vision. Corfu, Greece:Springer-Verlag,1999:
[38] Nguyen H. T., Smeulders A. W. M. Fast occluded object tracking by a robust appearancefilter[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,26(8):1099-1104
[39]左红英.基于背景建模的动态目标检测算法的研究[D].长沙：湖南大学,2007.
[40]罗小兰.视频跟踪中的背景建模[D].长沙：国防科技大学,2007.
[41]王智灵,周露平,陈宗海.针对不同信息特征的鲁棒背景建模技术分析[J].模式识别与人工智能,2009,22(2):240-245.
[42]刘锦峰.图像模板匹配快速算法研究[D].长沙：中南大学,2007.
[43]陈潇.基于特征的视频跟踪算法研究[D].西安：西安电子科技大学.2008
[44]肖敬若.复杂背景下的实时目标跟踪技术研究[D].西安：西北工业大学.2006
[45]张焱.地面背景下成像目标跟踪技术研究[D].长沙：国防科学技术大学.2008
[46] Giorgio Bonmassar, Eric L. Sehwartz. Improved Cross-Correlation for Template Matchingon the Laplacian Pyramid[J]. Pattern Recognition Letters,1998,19:765-770
[47]姜凯,陈海霞,汤建华.一种快速图像匹配算法的设计与实现[J].计算机工程与应用,2004,40(11):87-89.
[48]冯谦.基于局部特征的视频目标跟踪方法研究[D].成都：电子科技大学,2013
[49]杨昕梅.复杂背景下运动目标识别和稳定跟踪技术研究[D].北京：中国科学院研究生院，1997
[50]魏波.点时空约束图像目标跟踪理论与实时实现技术研究[D].成都：电子科技大学,2000
[51]应陈克,胡文江,赵亦工.复杂背景下目标模板更新算法研究[J].遥测遥控,2006,11.Vo27(6):34-39.
[52]刘扬.抗遮挡的运动目标跟踪算法研究[D].北京：中国科学院研究生院.2010.
[53] Pan Jiyan, Hu Bo. Robust Object Tracking against Template Drift[C]. Proc. IEEE Int. Conf.on Image Processing(ICIP),3: III-353-III-356,2007.
[54] Pan Jiyan, Hu Bo. Robust, Zhang Jianqiu. Robust and Accurate Object Tracking underVarious Types of Occlusions[J].IEEE Transactions on Circuits and Systems for VideoTechnology(T-CSVT),18(2):223-236,2008.
[55]潘吉彦.具有自适应遮挡处理与模板漂移抑制的视频目标跟踪算法[D].上海:复旦大学,2008.
[56]任仙怡,周晓,张桂林,张天序.基于仿射变换与模板更新策略的目标跟踪方法[J].华中科技大学学报.2001,29,(12):50-51,63.
[57]吉书鹏,张桂林,丁晓青.地面复杂场景图像相关跟踪算法研究[J].激光与红外,2002,32(6).
[58] Wong, S. Advanced correlation tracking of objects in cluttered imagery[J]. Proceedings ofSPIE, vol.5810(2005).
[59]雷涛.光电成像动态目标稳定跟踪技术研究[D].北京：中国科学院大学，2013
[60]周进.多模复合图像跟踪技术[D].北京:中国科学院研究生院,2008.
[61] Fukunaga K., Hostetler L. D. The estimation of the gradient of a density function withapplications in pattern recognition. IEEE Transactions on Information Theory.1975,21(1):32-40
[62] Comaniciu D., Meer P. Mean shift: A robust approach toward feature space analysis. IEEETransactions on Pattern Analysis and Machine Intelligence.2002,24(5):564-577
[63]王书朋.视频目标跟踪算法研究[D].西安：西安电子科技大学.2009
[64]卢宇.移动背景下目标检测与跟踪技术研究[D].北京：中国科学院研究生院.2009
[65] Peter Meer. Real-Time Tracking of Non-Rigid Objects using Mean Shift[C]. IEEE CVPR2000,2:142-149
[66] Kailath T. The divergence and Bhattacharyya distance measures in signal selection. IEEETrans. on Commun. Technol.,1967,COM-15:52-60.
[67]赵建伟，刘重庆.适用于遮挡问题的目标跟踪算法[J].计算机辅助设计与图形学学报，2003,15(9):1092-1095
[68] Robertson S, Hull DA. The TREC-9filtering track final report, In: Voorhees EM, HarmanDK eds. Proceedings of the9th Text Retrieval Conference (TREC-9), Gaithersburg: NISTSpecial Publication,2001:25-40
[69]魏伟波.基于图像的目标自动识别与跟踪技术研究[D].南京：南京理工大学.2006
[70]孙伟.基于粒子滤波的视频目标跟踪关键技术及应用研究[D].西安：西安电子科技大学,2009
[71]薛陈,朱明,刘春香.遮挡情况下目标跟踪算法综述.中国光学与应用光学,2009,2(5):388-394
[72] Caulfield D, Dawson-Howe K. Evaluation of multi-Part models for Mean-shift tracking [C].International Machine Vision and Image Processing Conference,2008,77-82
[73] Kalman R E. A new approach to linear filtering and Prediction Problems [J].Transactions ofthe ASME-Journal of Basic Engineering,1960,82(series D):35-45
[74] Isard M, Blake A. Condensation-conditional density Propagation for visual tracking[J].International Journal of Computer Vision,1998,29(l):197-208.
[75]汪颖进.目标跟踪过程中的遮挡问题研究[D].武汉：华中科技大学，2004,
[76]刘玉.基于特征点的运动目标跟踪技术研究[D].南京：南京航空航天大学.2011
[77]胡硕.基于小波理论的目标检测与快速目标跟踪算法研究[D].北京：中国科学院研究生院.2006
[78]陈远.复杂场景中视觉运动目标检测与跟踪[D].武汉：华中科技大学.2008
[79]卢晓鹏.视频序列中目标跟踪技术研究[D].北京：中国科学院研究生院.2007
[80]程建.基于粒子滤波的视觉跟踪算法研究及其在红外成像制导中的应用[D].上海：上海交通大学,2006.
[81] Hu W C, Yang C Y, Huang D Y. Robust real-time ship detection and tracking for visualsurveillance of cage aquaculture[J]. Journal of Visual Communication and Image Representation,2011,22(6):543-556.
[82]尹宏鹏,柴毅,匡金骏, et al.一种基于多特征自适应融合的运动目标跟踪算法[J].光电子.激光,2010,(06):917-923.
[83] Wang J Q, Yagi Y. Integrating color and shape-texture features for adaptive real-time objecttracking[J]. IEEE Transactions on Image Processing,2008,17(2):235-240.
[84] Wang Q, Chen F, Xu W L. Adaptive multi-cue tracking by online appearance learning[J].Neurocomputing,2011,74(6):1035-1045.
[85] Helman Stern B E. Adaptive color space switching for face tracking in multi-coloredlighting environments[C], Proceedings of Fifth IEEE International Conference on AutomaticFace and Gesture Recognition,2002:249-254.
[86] Hewei Z Z. Online feature extraction and selection for object tracking[C]. Proceedings ofIEEE International Conference on Mechatronics and Automation, Harbin,2007,3497-3502.
[87] Stiller C, Leon F P, Kruse M. Information fusion for automotive applications-Anoverview[J]. Information Fusion,2011,12(4):244-252.
[88]相入喜.复杂环境下的目标跟踪算法研究[D].重庆：重庆大学,2012
[89]钟权，周进等，基于Hough变换和边缘灰度直方图的直线跟踪算法[J].光电工程，2014（已录用）
[90] N. Dalal, B. Triggs. Histograms of oriented gradients for human detection[C]. IEEEConference on Computer Vision and Pattern Recognition,2005,886-893
[91]景亮.复杂环境下自动目标识别检测技术研究[D].成都：电子科技大学，2013
[92]解晓萌.复杂背景下运动目标检测和识别关键技术研究[D].广州：华南理工大学,2012
[93]李先锋.基于特征优化和多特征融合的杂草识别方法研究[D].江苏：江苏大学，2010
[94] Beliakov, G., James, S., Troiano, L.. Texture recognition by using level co-occurrence matrixand various aggregation functions[C]. IEEE world Congress on Computational Intelligence,2008.
[95] Ojala T P, Harwood D M. A comparative study of texture measures with classification basedon feature distributions[J]. Pattern Recognition,1996,29(1):51-59.
[96]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D].重庆：重庆大学.2009
[97]王永明，王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社.2010
[98] Mokhtarian F, Suomela, R. Curvature Scale Space Based Image Corner Detection[C]. Proc.European Signal Processing Conference, Island of Rhodes, Greece,1999,8.
[99] Dorez R. Widuch S. Signature characteristic points determination by means of the IPAN99algorithm. Medical Informatics I Technologies,2007
[100] Hans P. Moravec. Towards automatic visual obstacle avoidance[C]. In: Proceedings ofInternational Joint Conference on Artificial Intelligence. Cambridge, MA, USA,1977:584-590.
[101] Chris Harris, Mike Stephens. A Combined Corner and Edge Detector[C]. Proceedings ofthe4th Alvey Vision Conference.1988:147-151.
[102] Stephen M. Smith, J. Michael Brady. SUSAN-A New Approach to Low Level ImageProcessing [J]. International Journal of Computer Vision.1997,1:45-78.
[103]李双.基于Harris-SIFT和归一化割算法的车辆检测与识别[D].哈尔滨：哈尔滨工程大学.2012
[104] Shannon C E. The mathematical theory of communication[J]. The Bell System TechnicalJournal.1948,27:279-428,623-656.
[105] Birchfield S, Elliptical Head Tracking Using Intensity Gradients and Color Histograms [C].In: Proceedings of the international conference on Computer Vision and Patten Recognition,1998,232-237.
[106] Conaire C, Connor N, Thermo-visual feature fusion for object tracking using multiplespatiogram trackers[C]. In: Proceedings of conference on Machine vision and applications2007.
[107] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiplefeatures[J]. Pattern Recognition.2004,2:184-187.
[108] Spengler M. and Schiele B., Towards Robust Multi-cue Integration for Visual Tracking,Machine Vision and Applications,2003,14:50-58.
[109] Anping Li, Zhongliang Jing, and Shiqiang Hu, Particle Filter based Visual Tracking withMulti-cue Adaptive Fusion[J], Chinese Optics Letters,3,2005,326.
[110]韩日升.基于核的变尺度视频目标跟踪算法研究[D].上海：上海交通大学,2009
[111]杨慧军.基于特征融合的自动目标识别技术研究[D].上海：上海交通大学,2008
[112] J. Yang, J. Y. Yang, D. Zhang, J. F. Lu. Feature fusion: parallel strategy vs. serialstrategy[J]. Pattern Recognition,2003,36:1369-1381.
[113] Liu C. J., Wechsler H. A shape and texture-based enhanced Fisher classifier for facerecognition [J]．IEEE Transactions on Image Processing,2001,10(4)：598-608．
[114]邵妍.基于多特征融合的商标图像检索[D].南京：南京理工大学,2013
[115] R. T. Collins, Y. Liu. On-Line Selection of Discriminative Tracking Features[C]. IEEEInternational Conference on Computer Vision,2003,1:346-352
[116] Huan Liu, Lei Yu. Toward integrating feature selection algorithms for classification andclustering[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(4):491-502.
[117] Hough P. V. C. A Method and Means for Recognizing Complex Patterns[P]. US Patent3,1962.12.18.
[118] Duda R. O. and Hart P. E. Using the Hough transforms to detect lines and curves inpictures[J]. Communications of the ACM,1972,15(1):11~15.
[119] Duda R. O.,Hart P. E., and Stork D. G. Pattern Classification [M]. Wiley, New York,2ndedition,2000:537~542
[120] Canny J. F. A computational approach to edge detection[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1986,8(6):679-698,.
[121] Swain M.J. and D. H. Ballard, Color Indexing[J]. Intern.J. Comp. Vis.,1991.7(l):P.11-32.
[122] Lindeberg T. Scale-space for discrete signals [J]. IEEE Trans. on Pattern Analysis andMachine Intelligence,1990,12(3):234-254.
[123] Lindeberg T. Feature detection with automatic scale selection [J]. International Journal ofComputer Vision,1998,30(2):79-116.
[124] Lowe, David G. Object recognition from local scale-invariant features[C]. In Proc. of IEEEConf. on Computer Vision, Vol.2,1999, pp.1150-1157.
[125] Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf. onComputer Vision and Pattern Recognition, Vol.2,2003, pp.234-240.
[126] Zhang Li-Ke, Zhao Hongguang, Real time mean shift tracking using the Gabor wavelet[C].Proceedings of the2007IEEE International Conference on Mechatronics and Automation,ICMA, pp1617-1621.2007
[127] Parameswaran, V., Ramesh, V., Zoghlami, I.: Tunable Kernels for Tracking. In: Proceedingof International Conference on Computer Vision and Pattern Recognition, pp.2179–2186(2006)
[128]陈朝阳,丁明跃,周成平.基于对数极坐标映射的目标跟踪方法[J].电子学报,2001,29(9), pp.1173-1175.
[129] Feng. Tang and Hai. Tao, Object tracking with dynamic feature graph. Proceedings2ndJoint IEEE International Workshop on Visual Surveillance and Performance Evaluation ofTracking and Surveillance, VS-PETS,2005,25-32.
[130] Z. Kalal, K. Mikolajczyk, J. Matas. Tracking Learning Detection[C]. Pattern Analysis andMachine Intelligence,2011.
[131] Si-Hun Sung. Adaptive window algorithm with four-direction sizing factors for robustcorrelation-based tracking, IEEE,1997,208-215
[132] S. Avidan. Support Vector Tracking[C]. IEEE Transactions on Pattern Analysis andMachine Intelligence, pp.1064-1072,2004.
[133] R. Collins, Y. Liu, and M. Leordeanu. Online Selection of Discriminative TrackingFeatures[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27, no.10, pp.1631–1643,2005.
[134] H. Grabner and H. Bischof. On-line boosting and vision[C]. Conference on ComputerVision and Pattern Recognition,2006.
[135] Zhang Kaihua, Zhang Lei, Yang Ming-Hsuan: Real-Time Compressive Tracking[C]. ECCV,Florence, Italy, Oct8-112012, Part III, LNCS7574, pp.866–879,2012.
[136] Avidan S. Ensemble tracking[C]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(2):261-271.
[137] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[C]. IEEE TransactionsPattern Analysis and Machine Intelligence,2003,25(5):564~575
[138] N. Alt, S. Hinterstoisser, and N. Navab. Rapid Selection of Reliable Templates for VisualTracking[C]. In CVPR,2010.
[139] I. Matthews, T. Ishikawa, and S. Baker. The Template Update Problem[C]. PAMI,2004,26(6):810-815.
[140] Mei X, Ling H. Robust Visual Tracking using L1Minimization[C]. Proc. IEEE ICCV2009.
[141] Milansonka著，艾海舟等译，图像处理、分析与机器视觉(第二版)[M]，北京:人民邮电出版社，2003
[142] D. Lowe. Distinctive image features from scale-invariant keypoints[J]. In Journal ofComputer Vision.2004,60(2):91-110.
[143] A. E. Abdel-Hakim, A. A. Farag. CSIFT: A SIFT Descriptor with Color InvariantCharacteristics[C]. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition(CVPR2006).2006:1978-1983.
[144]常向魁.视频运动目标跟踪算法研究[D].河南：河南大学.2007
[145]邱雪娜.基于视觉的运动目标跟踪算法及其在移动机器人中的应用[D].上海：华东理工大学,2011
[146] Fischler M, Bolles R. Random sample consensus. A paradigm for model fitting withapplication to image analysis and automated cartography[C]. Commun. Assoc. Comp. Mach,1981,24.
[147]彭宁嵩，杨杰，刘志，等．Mean-shift跟踪算法中核函数窗宽的自动选取[J]．软件学报，2005，l6(9):1542-1550
[148] Donoho L. Compressed sensing[J]. IEEE Trans. On Information Theory.2006,52(4):1289-1306.
[149] D. Donoho, Y. Tsaig. Extensions of compressed sensing[J]. Signal Processing,2006,86(3):533-548
[150] E. Candes, J. Romberg, T. Tao. Robust uncertainty principles: exact signal reconstructionfrom highly incomplete frequency information[J]. IEEE Transactions on Information Theory,2006,52(2):489-509
[151] E. Candes, J. Romberg, T. Tao. Stable signal recovery from incomplete and inaccuratemeasurements [J]. International Journal of Pure and Applied Mathematics,2006,59(8):1207-1223
[152] Wright J, Yang Y, Ganesh A, et al. Robust Face Recognition via Sparse Representation [J].IEEE Trans. PAMI,2009,31(2):210-227.
[153]牛长锋,复杂背景下视频运动目标跟踪的研究[D],北京：北京理工大学.2010
[154]路锦正,基于稀疏表示的图像超分辨率重构技术研究[D],成都：电子科技大学.2013
[155] Achlioptas D.: Database-friendly random projections: Johnson-Lindenstrauss with binarycoins[J]. J. Comput. Syst. Sci2003,66,671-687
[156] Baraniuk R., Davenport M., DeVore R., Wakin M.: A simple proof of the restrictedisometry property for random matrices[J]. Constr. Approx2008,28,253-263
[157] Babenko B., Yang M.-H., Belongie S.: Robust object tracking with online multiple instancelearning[C]. PAMI2011,33,1619-1632
[158] Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objectsusing a view-based representation[C]. IJCV1998,38,63-84
[159] Mei, X., Ling, H. Robust visual tracking and vehicle classification via sparserepresentation[C]. PAMI.2011,33,2259-2272
[160] Li, H., Shen, C., Shi, Q.: Real-time visual tracking using compressive sensing[C]. In:CVPR, pp.1305–1312(2011)
[161] Stalder S., Grabner H., Van Gool L. Beyond semi-supervised tracking: Tracking should beas simple as detection, but not simpler than recognition[C]. in: Proceedings of IEEE InternationalConference on Computer Vision Workshops, Kyoto, Japan,2009,1409-1416.
[162] Zhang K., Song H. Real-time visual tracking via online weighted multiple instancelearning. Pattern Recognition,46.
[163] Zeisl B., Leistner C., Saffari A., et al. On-line semi-supervised multiple instanceboosting[C]. in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,San Francisco, CA, USA,2010,1879-1879.
[164] Goh K, Chang E and Li B. Using one-class and two-class SVMs for MultiClass imageannotation[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(10):1333-1346.
[165]万华林, Morshed U, Chowdhury.基于支持向量机的图像语义分类[J].软件学报,2003,14(11):1891-1899.
[166]付岩,王耀威,王伟强,等．SVM用于基于内容的自然图像分类和检索[J]．计算机学报,2003,26(10):1261-1265.
[167]路晶,金奕江,马少平,等．使用基于SVM的否定概率和法的图像标注[J]．智能系统学报,2006,1(1):62-66.
[168] Grauman K and Darrell T. Pyramid Match Kernels: Discriminative Classification with Setsof Image Features[R]. Technical Report MIT-CSAIL-TR-2006-020, MIT CSAIL, Cambridge,MA, March,2006.
[169] Grauman K, Darrell T. Approximate Correspondences in High Dimensions[C]. Advancesin Neural Information Processing Systems,2007:505-512.
[170] Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features: Spatial Pyramid Matching forRecognizing Natural Scene Categories[C]. Proceedings of IEEE International Conference onComputer Vision and Pattern Recognition,2006:2169-2178.
[171] Opelt A, Pinz A, Fussenegger M, et al. Generic Object Recognition with Boosting[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2008,28(3):16-431.
[172]刘丽丽.基于形状特征的运动目标分类方法研究[D],长沙：湖南大学,2006
[173] Raskutti B, Kowalczyk A. Extreme rebalancing for SVMs: a cage study [J]. News letter ofthe ACM Special Interest Group on Knowledge Discovery and Data Mining,2004,6(1):61-68.
[174] Joachims T. Making large-scale SVM Learning Practical [C]．In B Scholkopf．EtcAdvances in kernel Methods-support vector learning, Cambridge, MIT press,2007,169-184．
[175] H．H．Lin, T．L．Liu and J．H．Chuang．A Probabilistic SVM Approach for BackgroundScene initialization[C]．In Proceedings of IEEE International Conference on Image Processing,2002, V01．3:893-896．
[176] Ng A., Jordan M.: On discriminative vs. generative classifier: a comparison of logisticregression and naive bayes. In: NIPS, pp.841-848(2002)
[177] Diaconis P., Freedman D. Asymptotics of graphical projection pursuit. Ann. Stat.12,228-235(1984)
[178]钟权，周进等.一种改进的实时压缩跟踪算法[J].光电工程,2014(已录用)
[179] C Cortes, V Vapnik. Support vector networks[J]. Machine Learning,1995,20:273-295.
[2] Kenneth. R. Castelman著,朱志刚等译,数字图像处理[M],北京:电子工业出版社,1998.
[3]王健,张桂林.复杂背景下运动目标的实时跟踪[J].计算机与数字工程,Vol33,2005:18-21.
[4]常发亮.彩色图像分割与复杂场景下视觉目标跟踪方法研究[D].济南:山东大学，2005.
[5]王健.均值平移算法在计算视觉中的应用[D].武汉：华中科技大学,2005.
[6]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方法[J].计算机工程与应用,2004.
[7] G. R. Bradski. Computer vision face tracking for use in a perceptual user interface[J], In Proc.IEEE Workshop Applications of Computer Vision,1998,2:214-219.
[8] J. Tua, H. Taob, and T. Huang. Face as mouse through visual face tracking[J], CVIU,2007,108(1-2):35-40.
[9] S. Alberto and J. V. Juan. An approach of visual motion analysis[J]. Pattern RecognitionLetters,2005,26(3):355-368
[10] Collins R. et al. A system for video surveillance and monitoring: VSAM final report[R].Carnegie Mellon University, Technical Report: CMU-RI-TR-00-12,2000.
[11] A. Elgammal, R. Duraiswami, D. Harwood, et a1. Background and foreground modelingusing nonparametric kernel density estimation for visual surveillance[J]. Proceedings of theIEEE,2002,90(7):1151-1163.
[12] R. Babu, P. Patrick, fez, et a1. Robust tracking with motion estimation and localKernel-based color modeling[J], Image Vision Computing,2007,25(8):1205-1216.
[13] W. Hu et al., A Survey on Visual Surveillance of Object Motion and Behaviors[J], IEEETrans. Systems, Man, and Cybernetics, Part C: Applications and Reviews,2004,34(3):334-352.
[14] Harris, W. J., The Development of IVHS in North America[C]. IEEE Vehicle Navigation&Information System Conference Proceedings，1994. Plenary: P.3-10.
[15] M. Naylor C.I.A., Annotated Digital Video for Intelligent Surveillance and OptimizedRetrieval[R].2003，University of Reading and Kingston University: UK.
[16] V. Keanaker and R. Zabih. Bayesian Multi-Camera Surveillance[C]. IEEE ComputerSociety Conference on Computer Vision and Pattern Recognition,1999,1(2):253-259.
[17] Markandey V, Reid A, Wang S. Motion Estimation for Moving Target Detection[J]. IEEETrans on Aerospace and Electronic Systems,1996,32(3):866-874
[18] Tonissen S M, Evans R J. Techniques for Low SNR Target Detection and Tracking[C].International Symposium on Signal Processing and its Application,1996:21-24
[19] Denney B S, Figueiredo R J. Optimal Point Target Detection Using Adaptive AutoRegressive Background Prediction[J]. SPIE,4048(2000):46~57
[20]侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报.2006,4(32),603-617
[21] D. Comaniciu and P Meer. MS analysis and applications[C]. IEEE International Conferenceon Computer vision,1999,1(2):1197-1203.
[22] X. Han, P. Zhang and H. Li. MAP Spatial Pyramid Mean Shift for object tracking[C]. SPIEVisual Communications and Image Processing,2010.
[23] H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via online boosting[C]. InBMVC,2006,47-56.
[24] D. Ross, J. Lim, R. Lin and M. Yang. Incremental learning for robust visual tracking[C],IJCV, May2008,77(1):125-141.
[25] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised on-line boosting for robusttracking[C]. In ECCV,2008.
[26] B. Babenko, M. Yang and S. Belongie. Visual Tracking with Online Multiple InstanceLearning[C]. In Proc. IEEE Conf. Comp. Vision Pattern Recognition2009.
[27]王再欢.基于模型的三维飞机目标识别研究[D].西安：西北工业大学硕士学位论文，2005.
[28] Sang-Cheol Park, Sung-Hoon Lim, Bong-Kee Sin, Seong-Whan Lee. Tracking non-rigidobjects using probabilistic Hausdorff distance matching[J]. Pattern Recognition,2005,38:2373-2384
[29] Wu Y., Huang T. S. Robust Visual Tracking by Integrating Multiple Cues Based onCo-Inference Learning. International Journal of Computer Vision.2004,58(1):55-71
[30] Cannons K., Wildes R. Spatiotemporal Oriented Energy Features for Visual Tracking.2007
[31] Roos D., Lim J., Yang M.-H. Adaptive Probabilistic Visual Tracking with IncrementalSubspace Update[C]. Proceedings of the eighth European conference on computer vision. Berlin:Springer,2004:
[32] J. Kwon and K. M. Lee. Tracking of abrupt motion using Monte Carlo estimation[C]. ECCV,2008
[33] Y. Li, H. Ai, T. Yamashita, S. Lao, and M. Kawade. Tracking in low frame rate video: Acascade particle filter with discriminative observers of different lifespans[C]. CVPR,2007
[34] Senior A., Hampapur A., Tian Y.-L., et al. Appearance models for occlusion handling[J].Image and Vision Computing.2006,24(11):1233-1243
[35] Tao Y., Quan P., Jing L., et al. Real-time multiple objects tracking with occlusion handlingin dynamic scenes[C]. Proceedings of IEEE Conference on Computer Vision and PatternRecognition. San Diego, CA, USA:IEEE,2005:970-975
[36] Yilmaz A., Xin L., Shah M. Contour-based object tracking with occlusion handling in videoacquired using mobile cameras[C]. IEEE Transactions on Pattern Analysis and MachineIntelligence,.2004,26(11):1531-1536
[37] Roman G., Ron K., Ehud R., et al. Fast Geodesic Active Contours[C]. Proceedings of theSecond International Conference on Scale-Space Theories in Computer Vision. Corfu, Greece:Springer-Verlag,1999:
[38] Nguyen H. T., Smeulders A. W. M. Fast occluded object tracking by a robust appearancefilter[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2004,26(8):1099-1104
[39]左红英.基于背景建模的动态目标检测算法的研究[D].长沙：湖南大学,2007.
[40]罗小兰.视频跟踪中的背景建模[D].长沙：国防科技大学,2007.
[41]王智灵,周露平,陈宗海.针对不同信息特征的鲁棒背景建模技术分析[J].模式识别与人工智能,2009,22(2):240-245.
[42]刘锦峰.图像模板匹配快速算法研究[D].长沙：中南大学,2007.
[43]陈潇.基于特征的视频跟踪算法研究[D].西安：西安电子科技大学.2008
[44]肖敬若.复杂背景下的实时目标跟踪技术研究[D].西安：西北工业大学.2006
[45]张焱.地面背景下成像目标跟踪技术研究[D].长沙：国防科学技术大学.2008
[46] Giorgio Bonmassar, Eric L. Sehwartz. Improved Cross-Correlation for Template Matchingon the Laplacian Pyramid[J]. Pattern Recognition Letters,1998,19:765-770
[47]姜凯,陈海霞,汤建华.一种快速图像匹配算法的设计与实现[J].计算机工程与应用,2004,40(11):87-89.
[48]冯谦.基于局部特征的视频目标跟踪方法研究[D].成都：电子科技大学,2013
[49]杨昕梅.复杂背景下运动目标识别和稳定跟踪技术研究[D].北京：中国科学院研究生院，1997
[50]魏波.点时空约束图像目标跟踪理论与实时实现技术研究[D].成都：电子科技大学,2000
[51]应陈克,胡文江,赵亦工.复杂背景下目标模板更新算法研究[J].遥测遥控,2006,11.Vo27(6):34-39.
[52]刘扬.抗遮挡的运动目标跟踪算法研究[D].北京：中国科学院研究生院.2010.
[53] Pan Jiyan, Hu Bo. Robust Object Tracking against Template Drift[C]. Proc. IEEE Int. Conf.on Image Processing(ICIP),3: III-353-III-356,2007.
[54] Pan Jiyan, Hu Bo. Robust, Zhang Jianqiu. Robust and Accurate Object Tracking underVarious Types of Occlusions[J].IEEE Transactions on Circuits and Systems for VideoTechnology(T-CSVT),18(2):223-236,2008.
[55]潘吉彦.具有自适应遮挡处理与模板漂移抑制的视频目标跟踪算法[D].上海:复旦大学,2008.
[56]任仙怡,周晓,张桂林,张天序.基于仿射变换与模板更新策略的目标跟踪方法[J].华中科技大学学报.2001,29,(12):50-51,63.
[57]吉书鹏,张桂林,丁晓青.地面复杂场景图像相关跟踪算法研究[J].激光与红外,2002,32(6).
[58] Wong, S. Advanced correlation tracking of objects in cluttered imagery[J]. Proceedings ofSPIE, vol.5810(2005).
[59]雷涛.光电成像动态目标稳定跟踪技术研究[D].北京：中国科学院大学，2013
[60]周进.多模复合图像跟踪技术[D].北京:中国科学院研究生院,2008.
[61] Fukunaga K., Hostetler L. D. The estimation of the gradient of a density function withapplications in pattern recognition. IEEE Transactions on Information Theory.1975,21(1):32-40
[62] Comaniciu D., Meer P. Mean shift: A robust approach toward feature space analysis. IEEETransactions on Pattern Analysis and Machine Intelligence.2002,24(5):564-577
[63]王书朋.视频目标跟踪算法研究[D].西安：西安电子科技大学.2009
[64]卢宇.移动背景下目标检测与跟踪技术研究[D].北京：中国科学院研究生院.2009
[65] Peter Meer. Real-Time Tracking of Non-Rigid Objects using Mean Shift[C]. IEEE CVPR2000,2:142-149
[66] Kailath T. The divergence and Bhattacharyya distance measures in signal selection. IEEETrans. on Commun. Technol.,1967,COM-15:52-60.
[67]赵建伟，刘重庆.适用于遮挡问题的目标跟踪算法[J].计算机辅助设计与图形学学报，2003,15(9):1092-1095
[68] Robertson S, Hull DA. The TREC-9filtering track final report, In: Voorhees EM, HarmanDK eds. Proceedings of the9th Text Retrieval Conference (TREC-9), Gaithersburg: NISTSpecial Publication,2001:25-40
[69]魏伟波.基于图像的目标自动识别与跟踪技术研究[D].南京：南京理工大学.2006
[70]孙伟.基于粒子滤波的视频目标跟踪关键技术及应用研究[D].西安：西安电子科技大学,2009
[71]薛陈,朱明,刘春香.遮挡情况下目标跟踪算法综述.中国光学与应用光学,2009,2(5):388-394
[72] Caulfield D, Dawson-Howe K. Evaluation of multi-Part models for Mean-shift tracking [C].International Machine Vision and Image Processing Conference,2008,77-82
[73] Kalman R E. A new approach to linear filtering and Prediction Problems [J].Transactions ofthe ASME-Journal of Basic Engineering,1960,82(series D):35-45
[74] Isard M, Blake A. Condensation-conditional density Propagation for visual tracking[J].International Journal of Computer Vision,1998,29(l):197-208.
[75]汪颖进.目标跟踪过程中的遮挡问题研究[D].武汉：华中科技大学，2004,
[76]刘玉.基于特征点的运动目标跟踪技术研究[D].南京：南京航空航天大学.2011
[77]胡硕.基于小波理论的目标检测与快速目标跟踪算法研究[D].北京：中国科学院研究生院.2006
[78]陈远.复杂场景中视觉运动目标检测与跟踪[D].武汉：华中科技大学.2008
[79]卢晓鹏.视频序列中目标跟踪技术研究[D].北京：中国科学院研究生院.2007
[80]程建.基于粒子滤波的视觉跟踪算法研究及其在红外成像制导中的应用[D].上海：上海交通大学,2006.
[81] Hu W C, Yang C Y, Huang D Y. Robust real-time ship detection and tracking for visualsurveillance of cage aquaculture[J]. Journal of Visual Communication and Image Representation,2011,22(6):543-556.
[82]尹宏鹏,柴毅,匡金骏, et al.一种基于多特征自适应融合的运动目标跟踪算法[J].光电子.激光,2010,(06):917-923.
[83] Wang J Q, Yagi Y. Integrating color and shape-texture features for adaptive real-time objecttracking[J]. IEEE Transactions on Image Processing,2008,17(2):235-240.
[84] Wang Q, Chen F, Xu W L. Adaptive multi-cue tracking by online appearance learning[J].Neurocomputing,2011,74(6):1035-1045.
[85] Helman Stern B E. Adaptive color space switching for face tracking in multi-coloredlighting environments[C], Proceedings of Fifth IEEE International Conference on AutomaticFace and Gesture Recognition,2002:249-254.
[86] Hewei Z Z. Online feature extraction and selection for object tracking[C]. Proceedings ofIEEE International Conference on Mechatronics and Automation, Harbin,2007,3497-3502.
[87] Stiller C, Leon F P, Kruse M. Information fusion for automotive applications-Anoverview[J]. Information Fusion,2011,12(4):244-252.
[88]相入喜.复杂环境下的目标跟踪算法研究[D].重庆：重庆大学,2012
[89]钟权，周进等，基于Hough变换和边缘灰度直方图的直线跟踪算法[J].光电工程，2014（已录用）
[90] N. Dalal, B. Triggs. Histograms of oriented gradients for human detection[C]. IEEEConference on Computer Vision and Pattern Recognition,2005,886-893
[91]景亮.复杂环境下自动目标识别检测技术研究[D].成都：电子科技大学，2013
[92]解晓萌.复杂背景下运动目标检测和识别关键技术研究[D].广州：华南理工大学,2012
[93]李先锋.基于特征优化和多特征融合的杂草识别方法研究[D].江苏：江苏大学，2010
[94] Beliakov, G., James, S., Troiano, L.. Texture recognition by using level co-occurrence matrixand various aggregation functions[C]. IEEE world Congress on Computational Intelligence,2008.
[95] Ojala T P, Harwood D M. A comparative study of texture measures with classification basedon feature distributions[J]. Pattern Recognition,1996,29(1):51-59.
[96]尹宏鹏.基于计算机视觉的运动目标跟踪算法研究[D].重庆：重庆大学.2009
[97]王永明，王贵锦.图像局部不变性特征与描述[M].北京：国防工业出版社.2010
[98] Mokhtarian F, Suomela, R. Curvature Scale Space Based Image Corner Detection[C]. Proc.European Signal Processing Conference, Island of Rhodes, Greece,1999,8.
[99] Dorez R. Widuch S. Signature characteristic points determination by means of the IPAN99algorithm. Medical Informatics I Technologies,2007
[100] Hans P. Moravec. Towards automatic visual obstacle avoidance[C]. In: Proceedings ofInternational Joint Conference on Artificial Intelligence. Cambridge, MA, USA,1977:584-590.
[101] Chris Harris, Mike Stephens. A Combined Corner and Edge Detector[C]. Proceedings ofthe4th Alvey Vision Conference.1988:147-151.
[102] Stephen M. Smith, J. Michael Brady. SUSAN-A New Approach to Low Level ImageProcessing [J]. International Journal of Computer Vision.1997,1:45-78.
[103]李双.基于Harris-SIFT和归一化割算法的车辆检测与识别[D].哈尔滨：哈尔滨工程大学.2012
[104] Shannon C E. The mathematical theory of communication[J]. The Bell System TechnicalJournal.1948,27:279-428,623-656.
[105] Birchfield S, Elliptical Head Tracking Using Intensity Gradients and Color Histograms [C].In: Proceedings of the international conference on Computer Vision and Patten Recognition,1998,232-237.
[106] Conaire C, Connor N, Thermo-visual feature fusion for object tracking using multiplespatiogram trackers[C]. In: Proceedings of conference on Machine vision and applications2007.
[107] Serby D, Koller-Meier E, Van-Gool L, Probabilistic object tracking using multiplefeatures[J]. Pattern Recognition.2004,2:184-187.
[108] Spengler M. and Schiele B., Towards Robust Multi-cue Integration for Visual Tracking,Machine Vision and Applications,2003,14:50-58.
[109] Anping Li, Zhongliang Jing, and Shiqiang Hu, Particle Filter based Visual Tracking withMulti-cue Adaptive Fusion[J], Chinese Optics Letters,3,2005,326.
[110]韩日升.基于核的变尺度视频目标跟踪算法研究[D].上海：上海交通大学,2009
[111]杨慧军.基于特征融合的自动目标识别技术研究[D].上海：上海交通大学,2008
[112] J. Yang, J. Y. Yang, D. Zhang, J. F. Lu. Feature fusion: parallel strategy vs. serialstrategy[J]. Pattern Recognition,2003,36:1369-1381.
[113] Liu C. J., Wechsler H. A shape and texture-based enhanced Fisher classifier for facerecognition [J]．IEEE Transactions on Image Processing,2001,10(4)：598-608．
[114]邵妍.基于多特征融合的商标图像检索[D].南京：南京理工大学,2013
[115] R. T. Collins, Y. Liu. On-Line Selection of Discriminative Tracking Features[C]. IEEEInternational Conference on Computer Vision,2003,1:346-352
[116] Huan Liu, Lei Yu. Toward integrating feature selection algorithms for classification andclustering[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(4):491-502.
[117] Hough P. V. C. A Method and Means for Recognizing Complex Patterns[P]. US Patent3,1962.12.18.
[118] Duda R. O. and Hart P. E. Using the Hough transforms to detect lines and curves inpictures[J]. Communications of the ACM,1972,15(1):11~15.
[119] Duda R. O.,Hart P. E., and Stork D. G. Pattern Classification [M]. Wiley, New York,2ndedition,2000:537~542
[120] Canny J. F. A computational approach to edge detection[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence,1986,8(6):679-698,.
[121] Swain M.J. and D. H. Ballard, Color Indexing[J]. Intern.J. Comp. Vis.,1991.7(l):P.11-32.
[122] Lindeberg T. Scale-space for discrete signals [J]. IEEE Trans. on Pattern Analysis andMachine Intelligence,1990,12(3):234-254.
[123] Lindeberg T. Feature detection with automatic scale selection [J]. International Journal ofComputer Vision,1998,30(2):79-116.
[124] Lowe, David G. Object recognition from local scale-invariant features[C]. In Proc. of IEEEConf. on Computer Vision, Vol.2,1999, pp.1150-1157.
[125] Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf. onComputer Vision and Pattern Recognition, Vol.2,2003, pp.234-240.
[126] Zhang Li-Ke, Zhao Hongguang, Real time mean shift tracking using the Gabor wavelet[C].Proceedings of the2007IEEE International Conference on Mechatronics and Automation,ICMA, pp1617-1621.2007
[127] Parameswaran, V., Ramesh, V., Zoghlami, I.: Tunable Kernels for Tracking. In: Proceedingof International Conference on Computer Vision and Pattern Recognition, pp.2179–2186(2006)
[128]陈朝阳,丁明跃,周成平.基于对数极坐标映射的目标跟踪方法[J].电子学报,2001,29(9), pp.1173-1175.
[129] Feng. Tang and Hai. Tao, Object tracking with dynamic feature graph. Proceedings2ndJoint IEEE International Workshop on Visual Surveillance and Performance Evaluation ofTracking and Surveillance, VS-PETS,2005,25-32.
[130] Z. Kalal, K. Mikolajczyk, J. Matas. Tracking Learning Detection[C]. Pattern Analysis andMachine Intelligence,2011.
[131] Si-Hun Sung. Adaptive window algorithm with four-direction sizing factors for robustcorrelation-based tracking, IEEE,1997,208-215
[132] S. Avidan. Support Vector Tracking[C]. IEEE Transactions on Pattern Analysis andMachine Intelligence, pp.1064-1072,2004.
[133] R. Collins, Y. Liu, and M. Leordeanu. Online Selection of Discriminative TrackingFeatures[C]. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.27, no.10, pp.1631–1643,2005.
[134] H. Grabner and H. Bischof. On-line boosting and vision[C]. Conference on ComputerVision and Pattern Recognition,2006.
[135] Zhang Kaihua, Zhang Lei, Yang Ming-Hsuan: Real-Time Compressive Tracking[C]. ECCV,Florence, Italy, Oct8-112012, Part III, LNCS7574, pp.866–879,2012.
[136] Avidan S. Ensemble tracking[C]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(2):261-271.
[137] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[C]. IEEE TransactionsPattern Analysis and Machine Intelligence,2003,25(5):564~575
[138] N. Alt, S. Hinterstoisser, and N. Navab. Rapid Selection of Reliable Templates for VisualTracking[C]. In CVPR,2010.
[139] I. Matthews, T. Ishikawa, and S. Baker. The Template Update Problem[C]. PAMI,2004,26(6):810-815.
[140] Mei X, Ling H. Robust Visual Tracking using L1Minimization[C]. Proc. IEEE ICCV2009.
[141] Milansonka著，艾海舟等译，图像处理、分析与机器视觉(第二版)[M]，北京:人民邮电出版社，2003
[142] D. Lowe. Distinctive image features from scale-invariant keypoints[J]. In Journal ofComputer Vision.2004,60(2):91-110.
[143] A. E. Abdel-Hakim, A. A. Farag. CSIFT: A SIFT Descriptor with Color InvariantCharacteristics[C]. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition(CVPR2006).2006:1978-1983.
[144]常向魁.视频运动目标跟踪算法研究[D].河南：河南大学.2007
[145]邱雪娜.基于视觉的运动目标跟踪算法及其在移动机器人中的应用[D].上海：华东理工大学,2011
[146] Fischler M, Bolles R. Random sample consensus. A paradigm for model fitting withapplication to image analysis and automated cartography[C]. Commun. Assoc. Comp. Mach,1981,24.
[147]彭宁嵩，杨杰，刘志，等．Mean-shift跟踪算法中核函数窗宽的自动选取[J]．软件学报，2005，l6(9):1542-1550
[148] Donoho L. Compressed sensing[J]. IEEE Trans. On Information Theory.2006,52(4):1289-1306.
[149] D. Donoho, Y. Tsaig. Extensions of compressed sensing[J]. Signal Processing,2006,86(3):533-548
[150] E. Candes, J. Romberg, T. Tao. Robust uncertainty principles: exact signal reconstructionfrom highly incomplete frequency information[J]. IEEE Transactions on Information Theory,2006,52(2):489-509
[151] E. Candes, J. Romberg, T. Tao. Stable signal recovery from incomplete and inaccuratemeasurements [J]. International Journal of Pure and Applied Mathematics,2006,59(8):1207-1223
[152] Wright J, Yang Y, Ganesh A, et al. Robust Face Recognition via Sparse Representation [J].IEEE Trans. PAMI,2009,31(2):210-227.
[153]牛长锋,复杂背景下视频运动目标跟踪的研究[D],北京：北京理工大学.2010
[154]路锦正,基于稀疏表示的图像超分辨率重构技术研究[D],成都：电子科技大学.2013
[155] Achlioptas D.: Database-friendly random projections: Johnson-Lindenstrauss with binarycoins[J]. J. Comput. Syst. Sci2003,66,671-687
[156] Baraniuk R., Davenport M., DeVore R., Wakin M.: A simple proof of the restrictedisometry property for random matrices[J]. Constr. Approx2008,28,253-263
[157] Babenko B., Yang M.-H., Belongie S.: Robust object tracking with online multiple instancelearning[C]. PAMI2011,33,1619-1632
[158] Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objectsusing a view-based representation[C]. IJCV1998,38,63-84
[159] Mei, X., Ling, H. Robust visual tracking and vehicle classification via sparserepresentation[C]. PAMI.2011,33,2259-2272
[160] Li, H., Shen, C., Shi, Q.: Real-time visual tracking using compressive sensing[C]. In:CVPR, pp.1305–1312(2011)
[161] Stalder S., Grabner H., Van Gool L. Beyond semi-supervised tracking: Tracking should beas simple as detection, but not simpler than recognition[C]. in: Proceedings of IEEE InternationalConference on Computer Vision Workshops, Kyoto, Japan,2009,1409-1416.
[162] Zhang K., Song H. Real-time visual tracking via online weighted multiple instancelearning. Pattern Recognition,46.
[163] Zeisl B., Leistner C., Saffari A., et al. On-line semi-supervised multiple instanceboosting[C]. in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,San Francisco, CA, USA,2010,1879-1879.
[164] Goh K, Chang E and Li B. Using one-class and two-class SVMs for MultiClass imageannotation[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(10):1333-1346.
[165]万华林, Morshed U, Chowdhury.基于支持向量机的图像语义分类[J].软件学报,2003,14(11):1891-1899.
[166]付岩,王耀威,王伟强,等．SVM用于基于内容的自然图像分类和检索[J]．计算机学报,2003,26(10):1261-1265.
[167]路晶,金奕江,马少平,等．使用基于SVM的否定概率和法的图像标注[J]．智能系统学报,2006,1(1):62-66.
[168] Grauman K and Darrell T. Pyramid Match Kernels: Discriminative Classification with Setsof Image Features[R]. Technical Report MIT-CSAIL-TR-2006-020, MIT CSAIL, Cambridge,MA, March,2006.
[169] Grauman K, Darrell T. Approximate Correspondences in High Dimensions[C]. Advancesin Neural Information Processing Systems,2007:505-512.
[170] Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features: Spatial Pyramid Matching forRecognizing Natural Scene Categories[C]. Proceedings of IEEE International Conference onComputer Vision and Pattern Recognition,2006:2169-2178.
[171] Opelt A, Pinz A, Fussenegger M, et al. Generic Object Recognition with Boosting[J]. IEEETransactions on Pattern Analysis and Machine Intelligence,2008,28(3):16-431.
[172]刘丽丽.基于形状特征的运动目标分类方法研究[D],长沙：湖南大学,2006
[173] Raskutti B, Kowalczyk A. Extreme rebalancing for SVMs: a cage study [J]. News letter ofthe ACM Special Interest Group on Knowledge Discovery and Data Mining,2004,6(1):61-68.
[174] Joachims T. Making large-scale SVM Learning Practical [C]．In B Scholkopf．EtcAdvances in kernel Methods-support vector learning, Cambridge, MIT press,2007,169-184．
[175] H．H．Lin, T．L．Liu and J．H．Chuang．A Probabilistic SVM Approach for BackgroundScene initialization[C]．In Proceedings of IEEE International Conference on Image Processing,2002, V01．3:893-896．
[176] Ng A., Jordan M.: On discriminative vs. generative classifier: a comparison of logisticregression and naive bayes. In: NIPS, pp.841-848(2002)
[177] Diaconis P., Freedman D. Asymptotics of graphical projection pursuit. Ann. Stat.12,228-235(1984)
[178]钟权，周进等.一种改进的实时压缩跟踪算法[J].光电工程,2014(已录用)
[179] C Cortes, V Vapnik. Support vector networks[J]. Machine Learning,1995,20:273-295.