固定背景下单/多目标行人跟踪算法研究
|
摘要
智能视频监控是近年来计算机视觉领域的研究重点和热点之一,在安全防护、智能交通、行为分析等领域有着广阔的应用前景。行人目标检测与跟踪是智能视频监控的关键技术,也是后续目标识别、行为分析等的研究基础。本文主要研究摄像机固定情况下,复杂场景中的行人单目标稳态跟踪问题和固定背景下行人多目标跟踪问题。
目标检测是跟踪的基础,本文比较了三种常用的目标检测算法并分析各自的优缺点,结合具体的应用环境,采用混合高斯模型建立背景图像,利用背景差法检测前景目标,最后通过阴影去除、形态学滤波以及连通域分析等后续操作获取完整的前景目标。
对于行人单目标跟踪问题,为实现目标的稳定跟踪,提高跟踪算法的鲁棒性,本文在粒子滤波算法的基础上,提出了一种多特征自适应融合的单目标跟踪算法。首先由人工选取跟踪目标,通过比较各种颜色和纹理特征区分目标和背景能力的大小,选取最优的两个特征来描述目标。分别以这两个特征为目标模型进行粒子滤波处理可以得到两个关于目标位置的估计结果。若两个估计结果相近,则说明选择的特征有效,跟踪正确；若两个估计结果存在较大差异,则说明其中一个或两个特征失效,跟踪结果出现大的偏离,此时需要根据上一帧估计结果的可靠性决定是否返回上一帧图像重新选取最优特征并再次进行粒子滤波估计。只有在两个估计结果相近时才更新目标模型,从而确保目标模型不发生大的偏移。
对于多目标跟踪问题,本文根据场景中目标个数较多,目标状态复杂多变等情况,在考虑算法实时性的基础上,采用基于区域检测的多目标跟踪算法。首先通过基于混合高斯背景建模的背景差法获取前景目标,根据当前帧检测的前景目标与跟踪目标区域间的重合情况,可以构建两者之间的关联矩阵,根据矩阵行和列之间的关系可以将目标状态归为以下五类：目标出现、正常状态、目标融合、目标分裂和目标消失。对于不同的目标状态,采用不同的处理方法。在这五种目标状态中,由于造成目标分裂的原因较为复杂,本文详细分析了可能引起目标分裂的四种原因,并提出了相应的处理方法,特别是对于多目标融合后分裂的情况,提出了基于颜色匹配的跟踪算法。
实验结果显示本文提出的单目标跟踪算法在背景剧烈变化和相似物体干扰的情况下可以较好的实现目标跟踪,多目标跟踪算法则可以有效的处理多目标的融合以及分裂等特殊情况。
Intelligent video surveillance is the research focus in the field of computer vision in recent years, and has a broad application in the field of security, intelligent transportation and behavior analysis. Pedestrian target detection and tracking is the key technology of intelligent video surveillance, and it is also the research foundation of subsequent target identification and behavior analysis. This paper will research the single target tracking problem with complex background and multi-target tracking problem with fixed background.
Target detection is the basis for tracking. This paper first analyzes the advantages and disadvantages of three commonly used target detection algorithms. Considering the specific application environment, background subtraction method with Gaussian mixture background model is selected to detect foreground objects. Finally, complete foreground objects will be extracted through shadow removal, morphological filtering and connected component analysis.
For single target tracking problem, in order to improve the robustness of the tracking algorithm, we proposed an adaptive multi-feature integration single-target tracking algorithm based on particle filter algorithm. First, select the tracking target manually. By comparing the ability of distinguishing between the target and the background of a variety of color and texture features, we select the two optimal features to describe the target. Taking the two selected features as two different target models, two estimation results of target position will be obtained by using particle filter algorithm. If the two estimation results are similar, it means the selected features are active and the tracking result is reliable. If the two estimation results are quite different, it means one or two selected features are unreliable and the tracking result has a large offset. For this case, the reliability of estimated result of last frame will be used to decide whether to return the last frame to reselect optimal features and do particle filter estimation in current frame again. In order to ensure the accuracy of the target models. the target models will be updated only when the two estimated results are similar.
For multi-target tracking, there may be a large number of targets in the scene and the states of the targets may be complex. Considering the real-time nature of the algorithm, the multi-target tracking algorithm will be based on region detection in this paper. First, the background subtraction method based on Gaussian mixture background model will be used to extract foreground objects. Then, according to the coincidence between the foreground objects in current frame and the tracking targets in last frame, a correlation matrix will be constructed between them. According to the relationship between the rows and columns, target state can be grouped into five categories:target appear, normal state, target fusion, target split and target disappeared. Different target state corresponds to different tracking algorithm. Because the reasons for target split are more complex, this paper analyzes the reasons which may cause target split and proposes the corresponding processing methods. Especially for the split after the integration of multi-target, we propose a tracking algorithm based on color matching.
Experimental results show that the single target tracking algorithm is better in the case of the dramatic changes background and similar objects interference, and the multi-target tracking algorithm can effectively deal with the special case of the multi-target fusion and split.
目标检测是跟踪的基础,本文比较了三种常用的目标检测算法并分析各自的优缺点,结合具体的应用环境,采用混合高斯模型建立背景图像,利用背景差法检测前景目标,最后通过阴影去除、形态学滤波以及连通域分析等后续操作获取完整的前景目标。
对于行人单目标跟踪问题,为实现目标的稳定跟踪,提高跟踪算法的鲁棒性,本文在粒子滤波算法的基础上,提出了一种多特征自适应融合的单目标跟踪算法。首先由人工选取跟踪目标,通过比较各种颜色和纹理特征区分目标和背景能力的大小,选取最优的两个特征来描述目标。分别以这两个特征为目标模型进行粒子滤波处理可以得到两个关于目标位置的估计结果。若两个估计结果相近,则说明选择的特征有效,跟踪正确；若两个估计结果存在较大差异,则说明其中一个或两个特征失效,跟踪结果出现大的偏离,此时需要根据上一帧估计结果的可靠性决定是否返回上一帧图像重新选取最优特征并再次进行粒子滤波估计。只有在两个估计结果相近时才更新目标模型,从而确保目标模型不发生大的偏移。
对于多目标跟踪问题,本文根据场景中目标个数较多,目标状态复杂多变等情况,在考虑算法实时性的基础上,采用基于区域检测的多目标跟踪算法。首先通过基于混合高斯背景建模的背景差法获取前景目标,根据当前帧检测的前景目标与跟踪目标区域间的重合情况,可以构建两者之间的关联矩阵,根据矩阵行和列之间的关系可以将目标状态归为以下五类：目标出现、正常状态、目标融合、目标分裂和目标消失。对于不同的目标状态,采用不同的处理方法。在这五种目标状态中,由于造成目标分裂的原因较为复杂,本文详细分析了可能引起目标分裂的四种原因,并提出了相应的处理方法,特别是对于多目标融合后分裂的情况,提出了基于颜色匹配的跟踪算法。
实验结果显示本文提出的单目标跟踪算法在背景剧烈变化和相似物体干扰的情况下可以较好的实现目标跟踪,多目标跟踪算法则可以有效的处理多目标的融合以及分裂等特殊情况。
Intelligent video surveillance is the research focus in the field of computer vision in recent years, and has a broad application in the field of security, intelligent transportation and behavior analysis. Pedestrian target detection and tracking is the key technology of intelligent video surveillance, and it is also the research foundation of subsequent target identification and behavior analysis. This paper will research the single target tracking problem with complex background and multi-target tracking problem with fixed background.
Target detection is the basis for tracking. This paper first analyzes the advantages and disadvantages of three commonly used target detection algorithms. Considering the specific application environment, background subtraction method with Gaussian mixture background model is selected to detect foreground objects. Finally, complete foreground objects will be extracted through shadow removal, morphological filtering and connected component analysis.
For single target tracking problem, in order to improve the robustness of the tracking algorithm, we proposed an adaptive multi-feature integration single-target tracking algorithm based on particle filter algorithm. First, select the tracking target manually. By comparing the ability of distinguishing between the target and the background of a variety of color and texture features, we select the two optimal features to describe the target. Taking the two selected features as two different target models, two estimation results of target position will be obtained by using particle filter algorithm. If the two estimation results are similar, it means the selected features are active and the tracking result is reliable. If the two estimation results are quite different, it means one or two selected features are unreliable and the tracking result has a large offset. For this case, the reliability of estimated result of last frame will be used to decide whether to return the last frame to reselect optimal features and do particle filter estimation in current frame again. In order to ensure the accuracy of the target models. the target models will be updated only when the two estimated results are similar.
For multi-target tracking, there may be a large number of targets in the scene and the states of the targets may be complex. Considering the real-time nature of the algorithm, the multi-target tracking algorithm will be based on region detection in this paper. First, the background subtraction method based on Gaussian mixture background model will be used to extract foreground objects. Then, according to the coincidence between the foreground objects in current frame and the tracking targets in last frame, a correlation matrix will be constructed between them. According to the relationship between the rows and columns, target state can be grouped into five categories:target appear, normal state, target fusion, target split and target disappeared. Different target state corresponds to different tracking algorithm. Because the reasons for target split are more complex, this paper analyzes the reasons which may cause target split and proposes the corresponding processing methods. Especially for the split after the integration of multi-target, we propose a tracking algorithm based on color matching.
Experimental results show that the single target tracking algorithm is better in the case of the dramatic changes background and similar objects interference, and the multi-target tracking algorithm can effectively deal with the special case of the multi-target fusion and split.
引文
[1]万缨,韩毅,卢汉清.运动目标检测算法的探讨[J].计算机仿真,2006,23(010)：221-226.
[2]王盼.视频中运动目标检测与跟踪技术研究[D].杭州电子科技大学硕士学位论文,2009.
[3]张森悦,李一波.复杂条件下的运动目标检测方法研究综述[J].沈阳航空工业学院学报,2008,25(3)：59-63.
[4]刘泉志.基于视频的运动目标检测与跟踪算法研究[D].上海交通大学硕士学位论文,2010.
[5]张颖.视频序列中目标检测与跟踪方法研究[D].西安电子科技大学硕士学位论文,2011.
[6]朱明旱,罗大庸,曹倩霞.帧间差分与背景差分相融合的运动目标检测算法[J].计算机测量与控制,2005,13(3)：215-217.
[7]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图象图形学报,2008,13(4)：729-734.
[8]Herrero-Jaraba E, Orrite-Urunuela C, Senar J. Detected motion classification with a double-background and a neighborhood-based difference[J]. Pattern Recognition Letters,2003,24(12):2079-2092.
[9]蔡荣太,吴元昊,王明佳,等.视频目标跟踪算法综述[J].电视技术,2010(012)：135-138.
[10]李玮.基于视频图像序列的目标跟踪方法研究[D].山东大学硕士学位论文,2011.
[11]王汉斌.基于视频的目标检测与跟踪技术研究[D].南京航空航天大学硕士学位论文,2009.
[12]金克琼.视频监控系统中运动目标检测与跟踪的研究[D].武汉理工大学硕士学位论文,2010.
[13]Jepson A D, Fleet D J. El-Maraghi T F. Robust online appearance models for visual tracking[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2003, 25(10):1296-1311.
[14]Matthews L, Ishikawa T, Baker S. The template update problem[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(6):810-815.
[15]Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(3):266-280.
[16]Peterfreund N. Robust tracking of position and velocity with Kalman snakes[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1999,21(6): 564-569.
[17]Fieguth P, Terzopoulos D. Color-based tracking of heads and other mobile objects at video frame rates[C].Computer Vision and Pattern Recognition,1997. Proceedings.,1997 IEEE Computer Society Conference on. IEEE,1997:21-27.
[18]Wang J, Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking[J]. Image Processing, IEEE Transactions on,2008,17(2):235-240.
[19]Jang D S, Choi H I. Active models for tracking moving objects[J]. Pattern Recognition,2000,33(7):1135-1146.
[20]刘闯,龚声蓉,崔志明,等.基于角点采样的多目标跟踪方法[J].中国图象图形学报,2008,13(10)：1873-1877.
[21]Tan T N, Sullivan G D, Baker K D. Model-based localisation and recognition of road vehicles[J]. International Journal of Computer Vision,1998,27(1):5-25.
[22]徐腾飞.视频序列中基于检测的多目标跟踪研究[D].南京邮电大学硕士学位论文,2011.
[23]Horn B K P, Schunck B G. Determining optical flow[J]. Artificial intelligence, 1981,17(1):185-203.
[24]Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]. Proceedings of the 7th international joint conference on Artificial intelligence.1981.
[25]Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking[C]. Computer Vision and Pattern Recognition,1999. IEEE Computer Society Conference on. IEEE,1999,2.
[26]何西华.视频运动目标检测与跟踪算法研究[D].电子科技大学硕士学位论文,2008.
[27]王宁.图像的阴影检测与去除算法研究[D].北京：北京交通大学硕士学位论文,2008.
[28]Roller D, Daniilidis K, Nagel H H. Model-based object tracking in monocular image sequences of road traffic scenes [J]. International Journal of Computer Vision, 1993,10(3):257-281.
[29]Cucchiara R, Grana C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2003,25(10):1337-1342.
[30]刘雪,常发亮,王华杰.运动目标检测中的阴影去除方法[J].微处理机,2009,29(5)：116-117.
[31]Wang H, Suter D. Background subtraction based on a robust consensus method[C]. Pattern Recognition,2006. ICPR 2006.18th International Conference on. IEEE, 2006,1:223-226.
[32]Nummiaro K, Koller-Meier E, Van Gool L. Object tracking with an adaptive color-based particle filter [J]. Pattern Recognition,2002:353-360.
[33]张涛,费树岷,胡刚.基于多特征信息自适应融合的视频目标跟踪算法[J].系统科学与数学,2010,30(6)：761-767.
[34]Ryu H R, Huber M. A particle filter approach for multi-target tracking[C]. Intelligent Robots and Systems,2007. IROS 2007. IEEE/RSJ International Conference on. IEEE,2007:2753-2760.
[35]Scharcanski J. de Oliveira A B, Cavalcanti P G, et al. A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions[J]. Vehicular Technology, IEEE Transactions on,2011,60(2):381-389.
[36]Hue C, Le Cadre J P, Perez P. Tracking multiple objects with particle filtering[J]. Aerospace and Electronic Systems, IEEE Transactions on,2002,38(3):791-812.
[37]王爱平.视频目标跟踪技术研究[D].国防科学技术大学博士学位论文,2011.
[38]Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]. Computer Vision and Pattern Recognition,2000. Proceedings. IEEE Conference on. IEEE,2000,2:142-149.
[39]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002, 24(5):603-619.
[40]蒋旻,许勤,尚涛,等.基于粒子滤波和Mean-shift的跟踪算法[J].计算机工程,2010.
[41]Maggio E, Cavallaro A. Hybrid particle filter and mean shift tracker with adaptive transition model[C]. Proc. of IEEE Signal Processing Society International Conference on Acoustics, Speech, and Signal Processing (ICASSP).2005:19-23.
[42]段萌远.视频监控中目标跟踪技术研究[D].武汉：华中科技大学硕士学位论文,2007.
[43]Bar-Shalom Y. Li X R, Kirubarajan T. Estimation with applications to tracking and navigation:theory algorithms and software[M]. Wiley-Interscience,2001.
[44]Julier S J, Uhlmann J K. New extension of the Kalman filter to nonlinear systems[C]. AeroSense'97. International Society for Optics and Photonics,1997: 182-193.
[45]张波.基于粒子滤波的图像跟踪算法研究[D].上海：上海交通大学博士学位论文,2007.
[46]张苗辉.基于粒子滤波的目标跟踪算法研究[D].河南：河南大学硕士学位论文，2008.
[47]吴宝成.粒子滤波重采样算法研究及其应用[D].哈尔滨：哈尔滨工业大学硕士学位论文,2006.
[48]Fidaner I B, Akarun L. Combined color and texture tracking for video post-editing[C]. Computer and Information Sciences,2008. ISCIS'08.23rd International Symposium on. IEEE,2008:1-6.
[49]田卉,沈庭芝,赵三元,等.综合颜色和纹理特征的粒子滤波人脸跟踪算法[J].北京理工大学学报,2010,30(004)：469-473.
[50]陶杰,毕笃彦.一种基于粒子滤波的特征融合跟踪算法[J].光电工程,2009,35(11)：13-17.
[51]Stern H, Efros B. Adaptive color space switching for face tracking in multi-colored lighting environments[C]. Automatic Face and Gesture Recognition,2002. Proceedings. Fifth IEEE International Conference on. IEEE,2002:249-254.
[52]Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tracking features[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005, 27(10):1631-1643.
[53]Freeman W T, Roth M. Orientation histograms for hand gesture recognition[C]. International Workshop on Automatic Face and Gesture Recognition.1995,12: 296-301.
[54]Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. Computer Vision and Pattern Recognition,2005. CVPR 2005. IEEE Computer Society Conference on. IEEE,2005,1:886-893.
[55]黄茜,顾杰峰,杨文亮.基于梯度向量直方图的行人检测[J].科学技术与工程,2009(13)：3646-3651.
[56]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].西安电子科技大学博士学位论文,2009.
[57]Yang T, Pan Q, Li J, et al. Real-time multiple objects tracking with occlusion handling in dynamic scenes[C]. Computer Vision and Pattern Recognition,2005. CVPR 2005. IEEE Computer Society Conference on. IEEE,2005,1:970-975.
[58]张乐华.多人跟踪中目标分裂与合并问题研究[D].北京邮电大学硕士学位论文,2009.
[59]Takala V, Pietikainen M. Multi-object tracking using color, texture and motion[C]. Computer Vision and Pattern Recognition,2007. CVPR'07. IEEE Conference on. IEEE,2007:1-7.
[60]Kyriakides I, Morrell D, Papandreou-Suppappola A. A particle filtering approach to constrained motion estimation in tracking multiple targets[C]. Signals, Systems and Computers,2005. Conference Record of the Thirty-Ninth Asilomar Conference on. IEEE,2005:94-98.
[61]Morelande M R, Musicki D. Fast multiple target tracking using particle filters[C]. Decision and Control,2005 and 2005 European Control Conference. CDC-ECC05. 44th IEEE Conference on. IEEE.2005:530-535.
[62]毛爽.多目标检测跟踪算法研究[D].济南：山东大学硕士学位论文,2008.
[2]王盼.视频中运动目标检测与跟踪技术研究[D].杭州电子科技大学硕士学位论文,2009.
[3]张森悦,李一波.复杂条件下的运动目标检测方法研究综述[J].沈阳航空工业学院学报,2008,25(3)：59-63.
[4]刘泉志.基于视频的运动目标检测与跟踪算法研究[D].上海交通大学硕士学位论文,2010.
[5]张颖.视频序列中目标检测与跟踪方法研究[D].西安电子科技大学硕士学位论文,2011.
[6]朱明旱,罗大庸,曹倩霞.帧间差分与背景差分相融合的运动目标检测算法[J].计算机测量与控制,2005,13(3)：215-217.
[7]刘鑫,刘辉,强振平,等.混合高斯模型和帧间差分相融合的自适应背景模型[J].中国图象图形学报,2008,13(4)：729-734.
[8]Herrero-Jaraba E, Orrite-Urunuela C, Senar J. Detected motion classification with a double-background and a neighborhood-based difference[J]. Pattern Recognition Letters,2003,24(12):2079-2092.
[9]蔡荣太,吴元昊,王明佳,等.视频目标跟踪算法综述[J].电视技术,2010(012)：135-138.
[10]李玮.基于视频图像序列的目标跟踪方法研究[D].山东大学硕士学位论文,2011.
[11]王汉斌.基于视频的目标检测与跟踪技术研究[D].南京航空航天大学硕士学位论文,2009.
[12]金克琼.视频监控系统中运动目标检测与跟踪的研究[D].武汉理工大学硕士学位论文,2010.
[13]Jepson A D, Fleet D J. El-Maraghi T F. Robust online appearance models for visual tracking[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2003, 25(10):1296-1311.
[14]Matthews L, Ishikawa T, Baker S. The template update problem[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(6):810-815.
[15]Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(3):266-280.
[16]Peterfreund N. Robust tracking of position and velocity with Kalman snakes[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1999,21(6): 564-569.
[17]Fieguth P, Terzopoulos D. Color-based tracking of heads and other mobile objects at video frame rates[C].Computer Vision and Pattern Recognition,1997. Proceedings.,1997 IEEE Computer Society Conference on. IEEE,1997:21-27.
[18]Wang J, Yagi Y. Integrating color and shape-texture features for adaptive real-time object tracking[J]. Image Processing, IEEE Transactions on,2008,17(2):235-240.
[19]Jang D S, Choi H I. Active models for tracking moving objects[J]. Pattern Recognition,2000,33(7):1135-1146.
[20]刘闯,龚声蓉,崔志明,等.基于角点采样的多目标跟踪方法[J].中国图象图形学报,2008,13(10)：1873-1877.
[21]Tan T N, Sullivan G D, Baker K D. Model-based localisation and recognition of road vehicles[J]. International Journal of Computer Vision,1998,27(1):5-25.
[22]徐腾飞.视频序列中基于检测的多目标跟踪研究[D].南京邮电大学硕士学位论文,2011.
[23]Horn B K P, Schunck B G. Determining optical flow[J]. Artificial intelligence, 1981,17(1):185-203.
[24]Lucas B D, Kanade T. An iterative image registration technique with an application to stereo vision[C]. Proceedings of the 7th international joint conference on Artificial intelligence.1981.
[25]Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking[C]. Computer Vision and Pattern Recognition,1999. IEEE Computer Society Conference on. IEEE,1999,2.
[26]何西华.视频运动目标检测与跟踪算法研究[D].电子科技大学硕士学位论文,2008.
[27]王宁.图像的阴影检测与去除算法研究[D].北京：北京交通大学硕士学位论文,2008.
[28]Roller D, Daniilidis K, Nagel H H. Model-based object tracking in monocular image sequences of road traffic scenes [J]. International Journal of Computer Vision, 1993,10(3):257-281.
[29]Cucchiara R, Grana C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2003,25(10):1337-1342.
[30]刘雪,常发亮,王华杰.运动目标检测中的阴影去除方法[J].微处理机,2009,29(5)：116-117.
[31]Wang H, Suter D. Background subtraction based on a robust consensus method[C]. Pattern Recognition,2006. ICPR 2006.18th International Conference on. IEEE, 2006,1:223-226.
[32]Nummiaro K, Koller-Meier E, Van Gool L. Object tracking with an adaptive color-based particle filter [J]. Pattern Recognition,2002:353-360.
[33]张涛,费树岷,胡刚.基于多特征信息自适应融合的视频目标跟踪算法[J].系统科学与数学,2010,30(6)：761-767.
[34]Ryu H R, Huber M. A particle filter approach for multi-target tracking[C]. Intelligent Robots and Systems,2007. IROS 2007. IEEE/RSJ International Conference on. IEEE,2007:2753-2760.
[35]Scharcanski J. de Oliveira A B, Cavalcanti P G, et al. A Particle-Filtering Approach for Vehicular Tracking Adaptive to Occlusions[J]. Vehicular Technology, IEEE Transactions on,2011,60(2):381-389.
[36]Hue C, Le Cadre J P, Perez P. Tracking multiple objects with particle filtering[J]. Aerospace and Electronic Systems, IEEE Transactions on,2002,38(3):791-812.
[37]王爱平.视频目标跟踪技术研究[D].国防科学技术大学博士学位论文,2011.
[38]Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift[C]. Computer Vision and Pattern Recognition,2000. Proceedings. IEEE Conference on. IEEE,2000,2:142-149.
[39]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002, 24(5):603-619.
[40]蒋旻,许勤,尚涛,等.基于粒子滤波和Mean-shift的跟踪算法[J].计算机工程,2010.
[41]Maggio E, Cavallaro A. Hybrid particle filter and mean shift tracker with adaptive transition model[C]. Proc. of IEEE Signal Processing Society International Conference on Acoustics, Speech, and Signal Processing (ICASSP).2005:19-23.
[42]段萌远.视频监控中目标跟踪技术研究[D].武汉：华中科技大学硕士学位论文,2007.
[43]Bar-Shalom Y. Li X R, Kirubarajan T. Estimation with applications to tracking and navigation:theory algorithms and software[M]. Wiley-Interscience,2001.
[44]Julier S J, Uhlmann J K. New extension of the Kalman filter to nonlinear systems[C]. AeroSense'97. International Society for Optics and Photonics,1997: 182-193.
[45]张波.基于粒子滤波的图像跟踪算法研究[D].上海：上海交通大学博士学位论文,2007.
[46]张苗辉.基于粒子滤波的目标跟踪算法研究[D].河南：河南大学硕士学位论文，2008.
[47]吴宝成.粒子滤波重采样算法研究及其应用[D].哈尔滨：哈尔滨工业大学硕士学位论文,2006.
[48]Fidaner I B, Akarun L. Combined color and texture tracking for video post-editing[C]. Computer and Information Sciences,2008. ISCIS'08.23rd International Symposium on. IEEE,2008:1-6.
[49]田卉,沈庭芝,赵三元,等.综合颜色和纹理特征的粒子滤波人脸跟踪算法[J].北京理工大学学报,2010,30(004)：469-473.
[50]陶杰,毕笃彦.一种基于粒子滤波的特征融合跟踪算法[J].光电工程,2009,35(11)：13-17.
[51]Stern H, Efros B. Adaptive color space switching for face tracking in multi-colored lighting environments[C]. Automatic Face and Gesture Recognition,2002. Proceedings. Fifth IEEE International Conference on. IEEE,2002:249-254.
[52]Collins R T, Liu Y, Leordeanu M. Online selection of discriminative tracking features[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005, 27(10):1631-1643.
[53]Freeman W T, Roth M. Orientation histograms for hand gesture recognition[C]. International Workshop on Automatic Face and Gesture Recognition.1995,12: 296-301.
[54]Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. Computer Vision and Pattern Recognition,2005. CVPR 2005. IEEE Computer Society Conference on. IEEE,2005,1:886-893.
[55]黄茜,顾杰峰,杨文亮.基于梯度向量直方图的行人检测[J].科学技术与工程,2009(13)：3646-3651.
[56]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].西安电子科技大学博士学位论文,2009.
[57]Yang T, Pan Q, Li J, et al. Real-time multiple objects tracking with occlusion handling in dynamic scenes[C]. Computer Vision and Pattern Recognition,2005. CVPR 2005. IEEE Computer Society Conference on. IEEE,2005,1:970-975.
[58]张乐华.多人跟踪中目标分裂与合并问题研究[D].北京邮电大学硕士学位论文,2009.
[59]Takala V, Pietikainen M. Multi-object tracking using color, texture and motion[C]. Computer Vision and Pattern Recognition,2007. CVPR'07. IEEE Conference on. IEEE,2007:1-7.
[60]Kyriakides I, Morrell D, Papandreou-Suppappola A. A particle filtering approach to constrained motion estimation in tracking multiple targets[C]. Signals, Systems and Computers,2005. Conference Record of the Thirty-Ninth Asilomar Conference on. IEEE,2005:94-98.
[61]Morelande M R, Musicki D. Fast multiple target tracking using particle filters[C]. Decision and Control,2005 and 2005 European Control Conference. CDC-ECC05. 44th IEEE Conference on. IEEE.2005:530-535.
[62]毛爽.多目标检测跟踪算法研究[D].济南：山东大学硕士学位论文,2008.