基于视觉注意的运动目标跟踪系统
|
摘要
视频运动目标分析是计算机视觉领域的一个核心问题,在军事、视频监控、等许多方面有着广泛的应用前景。本文主要针对视频运动目标分析应用于智能交通的场景,重点研究了基于注意机制的运动目标检测、单体运动目标跟踪、以及多运动目标之间跟踪焦点转移三个方面的问题,并加以实现和改进。
本文按照基于注意力机制的显著区域的提取、显著区域内运动目标跟踪焦点的保持,以及显著区域内运动目标跟踪焦点转移的流程来撰写。
首先在显著区域提取部分,提出基于视觉注意机制的目标检测算法。通过引入注意力机制概念,结合图像的动态特征和静态进行目标检测。对传统的基于动态特征的目标检测方式进行改进:结合混合高斯建模以及帧间差分法进行前景提取,并在图像的最佳尺度中进行图像填充,有效解决了检测目标的空洞现象,同时在背景更新中提出局部更新方法,避免局部背景突变而发生误检;基于静态特征的目标检测根据提取的显著区域保持原始物体的一致性特点,从面积和体积上对检测目标进行约束,成功解决因形态学作用而“膨胀“现象。
其次在显著区域内跟踪焦点的保持方面,提出对于跟踪区域显著性的保持以及连续跟踪的算法。一旦确定跟踪显著区域,保持该区域的显著性大小,抑制其他显著区域的显著性。在此基础上,保持对该区域内的运动目标连续跟踪。并在跟踪过程中提出了基于粒子滤波的多相似度的条件密度跟踪算法。改进了粒子滤波的重采样过程,利用区域局部性原理,使权值大的粒子周围分布较多的粒子,有效地较少了粒子的贫化现象,然后对图像中的各个方向进行跟踪,将非刚体运动形式中的倾斜、旋转转化成各个方向上的线性运动,降低计算复杂度,并将该算法与目标常用的跟踪算法进行比较,结果显示,该算法有效地提高了跟踪精度。
最后在跟踪焦点的切换机制方面,提出通过视觉注意机制的切换机制,进行跟踪焦点转移的算法。检测图像内所有显著区域的显著性大小,抑制中心区域,对其他显著区域的显著性进行排序,根据自底向上的任务驱动,使跟踪焦点总是集中在显著性最大的显著区域内的运动目标中。
Video-based analysis of moving objects is a core issue in the field of computer vision and there are broad prospects in the military, video surveillance, and many other areas. In this paper, I select ITS as my research example, and focused on the problems of object detection, single moving object tracking and tracking focus tracking shift, and implement and improve it.
This paper is about three topics which are objects detections, single object tracking and tracking focus shift.
In the part of extraction in a prominent area, I proposed a algorithm of visual attention-based objection detection. This paper introduces the concept of attention and detects the moving objects which integrated the moving feature and visual feature in the image. For the former this paper improves the detection method as follows: extract the foreground by Gaussian Mixture Model, fill them in the best gauge of the image, and then update the local background which solves the problem of image holes effectively. For the latter, the main job is to control the areas of the detected objects.
In the part of the retention of tracking focus, I proposed a algorithm of the definition of the tracking region and tracking focus. The tracking was defined when system is initialed, keep the value of the prominent area, inhibit other significant area and track the moving objects in this place continuously. In the tracking process, this paper proposes a new algorithm based on multi-likelihood condensation-conditional density propagation. This algorithm can reduce the dimension of non-rigid state vector object such as rotation and the degree of tilt by verifying likelihood of the parameters in each particle (the level and vertical of coordinates) each. The experimental data shows that this algorithm plays a good job.
In the part of tracking focus shift, I proposed a algorithm of the tracking shift based on the visual attention shift mechanism. All the values of prominent area were computed and sorted by the value. Finally our tracking focus shift mechanism would always concentrate the tracking focus whose value is the biggest.
本文按照基于注意力机制的显著区域的提取、显著区域内运动目标跟踪焦点的保持,以及显著区域内运动目标跟踪焦点转移的流程来撰写。
首先在显著区域提取部分,提出基于视觉注意机制的目标检测算法。通过引入注意力机制概念,结合图像的动态特征和静态进行目标检测。对传统的基于动态特征的目标检测方式进行改进:结合混合高斯建模以及帧间差分法进行前景提取,并在图像的最佳尺度中进行图像填充,有效解决了检测目标的空洞现象,同时在背景更新中提出局部更新方法,避免局部背景突变而发生误检;基于静态特征的目标检测根据提取的显著区域保持原始物体的一致性特点,从面积和体积上对检测目标进行约束,成功解决因形态学作用而“膨胀“现象。
其次在显著区域内跟踪焦点的保持方面,提出对于跟踪区域显著性的保持以及连续跟踪的算法。一旦确定跟踪显著区域,保持该区域的显著性大小,抑制其他显著区域的显著性。在此基础上,保持对该区域内的运动目标连续跟踪。并在跟踪过程中提出了基于粒子滤波的多相似度的条件密度跟踪算法。改进了粒子滤波的重采样过程,利用区域局部性原理,使权值大的粒子周围分布较多的粒子,有效地较少了粒子的贫化现象,然后对图像中的各个方向进行跟踪,将非刚体运动形式中的倾斜、旋转转化成各个方向上的线性运动,降低计算复杂度,并将该算法与目标常用的跟踪算法进行比较,结果显示,该算法有效地提高了跟踪精度。
最后在跟踪焦点的切换机制方面,提出通过视觉注意机制的切换机制,进行跟踪焦点转移的算法。检测图像内所有显著区域的显著性大小,抑制中心区域,对其他显著区域的显著性进行排序,根据自底向上的任务驱动,使跟踪焦点总是集中在显著性最大的显著区域内的运动目标中。
Video-based analysis of moving objects is a core issue in the field of computer vision and there are broad prospects in the military, video surveillance, and many other areas. In this paper, I select ITS as my research example, and focused on the problems of object detection, single moving object tracking and tracking focus tracking shift, and implement and improve it.
This paper is about three topics which are objects detections, single object tracking and tracking focus shift.
In the part of extraction in a prominent area, I proposed a algorithm of visual attention-based objection detection. This paper introduces the concept of attention and detects the moving objects which integrated the moving feature and visual feature in the image. For the former this paper improves the detection method as follows: extract the foreground by Gaussian Mixture Model, fill them in the best gauge of the image, and then update the local background which solves the problem of image holes effectively. For the latter, the main job is to control the areas of the detected objects.
In the part of the retention of tracking focus, I proposed a algorithm of the definition of the tracking region and tracking focus. The tracking was defined when system is initialed, keep the value of the prominent area, inhibit other significant area and track the moving objects in this place continuously. In the tracking process, this paper proposes a new algorithm based on multi-likelihood condensation-conditional density propagation. This algorithm can reduce the dimension of non-rigid state vector object such as rotation and the degree of tilt by verifying likelihood of the parameters in each particle (the level and vertical of coordinates) each. The experimental data shows that this algorithm plays a good job.
In the part of tracking focus shift, I proposed a algorithm of the tracking shift based on the visual attention shift mechanism. All the values of prominent area were computed and sorted by the value. Finally our tracking focus shift mechanism would always concentrate the tracking focus whose value is the biggest.
引文
[1]史其信,陆化普.中国ITS发展战略构想.公路交通科技, 1998,15(3):13-16.
[2]杨兆升.智能运输系统概论[M].北京:人民交通出版社,2003.
[3]王俊.智能交通信息采集子系统的研究与实现[D].武汉:华中科技大学,2006.
[4]朱琴.多运动目标检测和跟踪算法的研究[D].南京:南京理工大学, 2008.
[5] G. Hoffman, C. Breazeal. Cost-Based Anticipatory Action Selection for Human-Robot Fluency[M].IEEE Transactions in Robotics 2007:919-926.
[6] Tsu-Tian L. Research on Intelligent Transportation Systems in Taiwan[J]. Proceedings of 27th Chinese Control Conference, 2008, Vol 1: 18-23.
[7] Dickinson K W, Wan C L. Road traffic monitoring using the Trip II system[J]. IEEE 2nd Int. Conf. Road Traffic Minitoring, London, 1989, 56-60.
[8] Koller D.Towards Rubust Automatic Traffic Scene Analysis in Real-time[J]. Int. Conf. Pattern Recognition, Jerusalem, Israel, 1994, 126-131.
[9]唐晓静,琚生根,周刚.一种基于智能信息平台的ITS系统设计方案[J].西南民族大学学报.自然科学版., 2007, 33(3): 652-657.
[10]琚生根.基于信息平台的智能交通指挥中心监控系统研究与设计[D].成都,四川大学. 2005.
[11]任江涛,张毅.一种面向信息应用的ITS体系结构[J].公路交通科技, 2001.
[12]任江涛,张毅,李志恒.面向信息应用的ITS信息模型及交换模式[J] .清华大学学报(自然科学版), 2002.
[13]弗兰西斯.克里克.惊人的假说—灵魂的科学探索[M].湖南科学技术出版社.
[14]吴新年,汪云九.视觉注意的认知和神经生物学模型[J].心理学动态,1995,3:16-22.
[15]李庆瀛.基于视觉注意的移动机器人目标跟踪技术研究[D].大连:大连理工大学, 2008.
[16]邵静.协同视觉选择注意计算模型研究[D].合肥:合肥工业大学, 2008.
[17]傅世敏.视觉选择性注意的机制及其在视觉信息处理中的作用[D] .安徽:中国科学技术大学,1998.
[18] Itti Laurent, Koch Christof, Niebur Ernst. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on PAMI, 1998, 20(11): 1254-1259.
[19] Itti Laurent, Koch Christof. A comparison of feature combination strategies for saliency-based visual attention[C]. Proc SPIE. 1999, 3644:473-482.
[20] Itti Laurent. Visual attention and target detection in cluttered natural scenes[J]. Optical Engineering, 2001, 40(9): 1784-1793.
[21]吴田富.视觉选择性注意机制计算模型及其在物体识别中的应用[D].安徽:合肥工业大学, 2005.
[22] Blaser Erik, Sperling George, Lu Zhonglin. Measuring the amplification of attention[C]. Proceedings of theNational Academy of Sciences of the United States of America, 1999, 96:11681-11686.
[23] Tsotsos J K, Culhane S M, Wai WY K. Modelling visual attention via selecting tuning[J]. Artificial Intelligence, 1995, 78(1-2):507-545.
[24] Niebur E, Koch C. Computational architecture for attention. Parasuraman R. The Attention Brain [M]. MA: MITPress, 1998. 163-186.
[25]肖乐斌,龚建华,谢传节.线性四叉树和线性八叉树领域寻找的一种新算法[J].测绘学报, 1998: 27(3).
[26]钱乐乐.基于视觉层次感知机制的图像理解方法研究[D].安徽:合肥工业大学,2009.
[27] Olshausen B A, Anderson C H, Van Essen D C. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information[J]. The Journal of Neuroscience, 1993, 13(11): 4700-4719.
[28] Koch C, Ullman S. Shifts in selective visual attention: towards the underlying neural circuitry[J]. Human Neurobiology, 1985, 4: 219-227.
[29] Milanese R, Gil S, PunT. Attentive mechanisms for dynamic and static scene analysis[J] . Optical Engineering, 1995, 34(8): 2428-2434.
[30] Baluja S, Pomerleau D A. Expectation-based selective attention for visual monitoring and control of a robot vehicle [J]. Robotics and Autonomous Systems, 1997, 22(3-4): 329-344.
[31] Li Zhaoping. Asaliencymap in primary visual cortex [J]. TRENDS in Cognitive Science, 2002, 6(1): 9-16.
[32]单列.视觉注意机制的若干关键技术及应用研究[D].安徽:中国科技大学, 2008.
[33] J.M.Wolfe, T.S.Horowitz. Opinion: What attributes guide the deployment of visual attention and how do they do it[J]. Nature Neuroseience, 2004, 5:l-7.
[34] N.Hans-Christoph. Salience from feature contrast: additivity across dimensions[J]. Vision Research, 2000, 40:1183-1201.
[35] N.Hans-Christoph. Salience from feature contrast: temporal properties of saliency mechanism[J]. Vision Research, 2000, 40:2421-2435.
[36] N. Hans Christoph. Salience from feature contrast: variation switch texture density[J]. Vision Research,2000, 40:3181-3200.
[37]纪小鹏.智能交通系统中车辆视频检测、识别与跟踪方法的研究[D].青岛:中国海洋大学,2006.
[38] Koller D.Towards Robust Automatic Traffic Scene Analysis in Real-time[J].Int. Conf. Pattern Recoginition, 1994:126-131.
[39]唐晓静,琚生根,周刚.一种基于智能信息平台的ITS系统设计方案[J] .西南民族大学学报.自然科学版,2007,33(3): 652-657.
[40] A. Bensrhair, M. Bertozzi, A. Broggi, P. Miche, S. Mousset and G. Toulminet. A Cooperative Approach to Vision-based Vehicle Detection[M].IEEE Intelligent Transportation Systems Conference Proceeding, Oakland(CA) USA ,2001: 207-212.
[41] J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques[J]. International Journal ofComputer Vision, 1994, 12(1): 42-77.
[42] Bainbridge-smith, A. Lane, R. G. Determining optical flow using a differential method[J]. Image and Vision Computing, 2004, 15:11-22.
[43] Ying Wu. Optical Flow and Motion Analysis[J]. ECE510-Computer Vision Notes Series 6, Electrical & Computer Engineering Northwest University, Evanston, IL.
[44] Chiou-Shann Fuh, Petros Maragos. Region-Based Optical Flow Estimation[J]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on.1989:130-135.
[45] Nagel, H.-H., Haag, M. Bias-corrected optical flow estimation for road vehicle tracking[J]. ComputerVision. Sixth International Conference on,1998: 1006-1011.
[46]沈海浪,平西建,许志勇.一种基于背景重建的运动目标检测算法[J].信息工程大学学报2004,5 (3): 69-71.
[47] Toyama K, Krumm J, Brumitt B. Wallfollower. Principles and practice of background maintenance[J]. International Conference on Computer Vision, Greece, 1999:244-261.
[48]方帅,薛方正,徐心和.基于背景建模的动态目标检测算法的研究与仿真[J].系统仿真学报, 2005:17(1).
[49]阮秋琦.数字图像处理学(第二版)[M].北京:电子工业出版社,2007:334-338.
[50]冈萨雷斯.数字图像处理(第二版) [M].电子工业出版社,2007:70-80.
[51]赵英男. Gabor滤波器在车辆检测和车型识别中的应用研究[D].南京:南京理工大学,2004.
[52]张宗杰.视频监控中运动目标检测与跟踪关键技术研究[D].苏州:苏州大学,2007.
[53]于成忠.视频序列中运动目标的提取与跟踪[D].南京:东南大学,2006.
[54]顾庆.基于视觉信息的运动体位置提取算法和实验研究[D].吉林:吉林大学, 2007.
[55]魏瑞斌.基于多特征的运动目标跟踪[D].陕西:西北大学, 2007.
[56]李安平.复杂环境下的视频目标跟踪算法研究[D].上海:上海交通大学, 2007 .
[57]吴宝成.粒子滤波器重采样算法研究及其应用[D].哈尔滨:哈尔滨工业大学,2006.
[58]王昆.基于粒子滤波器的机动目标跟踪技术[D].南京:南京理工大学, 2007.
[59]杨莉.图像特征检测与运动目标分割算法的研究和实现[D].西安:西安电子科技大学, 2004 .
[60]李春明.视频图像中的运动人体检测和人脸识别[D]西安电子科技大学, 2005.
[61]鲁照华.视频编码算法研究及其无线传输实现[D].天津:天津大学, 2005.
[62]毕凌燕.交叠正交变换与视频分割编码的研究[D].广州:华南理工大学, 2003 .
[63]赵坤.复杂环境下红外小目标检测与跟踪技术研究[D].哈尔滨:哈尔滨工程大学, 2006 .
[64]冯志全.运动人手的三维跟踪方法研究[D].山东:山东大学, 2006 .
[65] Sheng-Tong Zhong; Fei Hao. Hand Tracking by Particle Filtering with Elite Particles Mean Shift. Frontier of Computer Science and Technology[J]. 2008. FCST '08. Japan-China Joint Workshop on 27-28 Dec. 2008:163–167.
[66] Pérez P, Blake A, and Gangnet M. JetStream. Probabilistic contour extraction with particles. Proc[J]. Int Conf on Computer 2001: 524-531.
[67] Doucet A, and Gordon N. Sequential Monte Carlo Methods in Practice[C]. 2001:64-125.
[68] Zhu Ye, Zhi-Qiang Liu. Genetic condensation for motion tracking. Machine Learning and Cybernetics[J]. 2005(3):2518-2524.
[69] Djuric P M; Bugallo M F, Miguez J. Density assisted particle filters for state and parameter estimation[J]. IEEE International Conference on. 2004(2):701-710.
[70] C. M. Privitera, L. W. Stark. Algorithms for defining visual regions-of-interest:comparison with eye fixations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(19):970-982.
[71] H. W. Kwak, H. Egeth. Consequences of allocating attention to locations and to other attributes[J]. Percept. Psychophys, 1992, 51:455-464.
[2]杨兆升.智能运输系统概论[M].北京:人民交通出版社,2003.
[3]王俊.智能交通信息采集子系统的研究与实现[D].武汉:华中科技大学,2006.
[4]朱琴.多运动目标检测和跟踪算法的研究[D].南京:南京理工大学, 2008.
[5] G. Hoffman, C. Breazeal. Cost-Based Anticipatory Action Selection for Human-Robot Fluency[M].IEEE Transactions in Robotics 2007:919-926.
[6] Tsu-Tian L. Research on Intelligent Transportation Systems in Taiwan[J]. Proceedings of 27th Chinese Control Conference, 2008, Vol 1: 18-23.
[7] Dickinson K W, Wan C L. Road traffic monitoring using the Trip II system[J]. IEEE 2nd Int. Conf. Road Traffic Minitoring, London, 1989, 56-60.
[8] Koller D.Towards Rubust Automatic Traffic Scene Analysis in Real-time[J]. Int. Conf. Pattern Recognition, Jerusalem, Israel, 1994, 126-131.
[9]唐晓静,琚生根,周刚.一种基于智能信息平台的ITS系统设计方案[J].西南民族大学学报.自然科学版., 2007, 33(3): 652-657.
[10]琚生根.基于信息平台的智能交通指挥中心监控系统研究与设计[D].成都,四川大学. 2005.
[11]任江涛,张毅.一种面向信息应用的ITS体系结构[J].公路交通科技, 2001.
[12]任江涛,张毅,李志恒.面向信息应用的ITS信息模型及交换模式[J] .清华大学学报(自然科学版), 2002.
[13]弗兰西斯.克里克.惊人的假说—灵魂的科学探索[M].湖南科学技术出版社.
[14]吴新年,汪云九.视觉注意的认知和神经生物学模型[J].心理学动态,1995,3:16-22.
[15]李庆瀛.基于视觉注意的移动机器人目标跟踪技术研究[D].大连:大连理工大学, 2008.
[16]邵静.协同视觉选择注意计算模型研究[D].合肥:合肥工业大学, 2008.
[17]傅世敏.视觉选择性注意的机制及其在视觉信息处理中的作用[D] .安徽:中国科学技术大学,1998.
[18] Itti Laurent, Koch Christof, Niebur Ernst. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on PAMI, 1998, 20(11): 1254-1259.
[19] Itti Laurent, Koch Christof. A comparison of feature combination strategies for saliency-based visual attention[C]. Proc SPIE. 1999, 3644:473-482.
[20] Itti Laurent. Visual attention and target detection in cluttered natural scenes[J]. Optical Engineering, 2001, 40(9): 1784-1793.
[21]吴田富.视觉选择性注意机制计算模型及其在物体识别中的应用[D].安徽:合肥工业大学, 2005.
[22] Blaser Erik, Sperling George, Lu Zhonglin. Measuring the amplification of attention[C]. Proceedings of theNational Academy of Sciences of the United States of America, 1999, 96:11681-11686.
[23] Tsotsos J K, Culhane S M, Wai WY K. Modelling visual attention via selecting tuning[J]. Artificial Intelligence, 1995, 78(1-2):507-545.
[24] Niebur E, Koch C. Computational architecture for attention. Parasuraman R. The Attention Brain [M]. MA: MITPress, 1998. 163-186.
[25]肖乐斌,龚建华,谢传节.线性四叉树和线性八叉树领域寻找的一种新算法[J].测绘学报, 1998: 27(3).
[26]钱乐乐.基于视觉层次感知机制的图像理解方法研究[D].安徽:合肥工业大学,2009.
[27] Olshausen B A, Anderson C H, Van Essen D C. A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information[J]. The Journal of Neuroscience, 1993, 13(11): 4700-4719.
[28] Koch C, Ullman S. Shifts in selective visual attention: towards the underlying neural circuitry[J]. Human Neurobiology, 1985, 4: 219-227.
[29] Milanese R, Gil S, PunT. Attentive mechanisms for dynamic and static scene analysis[J] . Optical Engineering, 1995, 34(8): 2428-2434.
[30] Baluja S, Pomerleau D A. Expectation-based selective attention for visual monitoring and control of a robot vehicle [J]. Robotics and Autonomous Systems, 1997, 22(3-4): 329-344.
[31] Li Zhaoping. Asaliencymap in primary visual cortex [J]. TRENDS in Cognitive Science, 2002, 6(1): 9-16.
[32]单列.视觉注意机制的若干关键技术及应用研究[D].安徽:中国科技大学, 2008.
[33] J.M.Wolfe, T.S.Horowitz. Opinion: What attributes guide the deployment of visual attention and how do they do it[J]. Nature Neuroseience, 2004, 5:l-7.
[34] N.Hans-Christoph. Salience from feature contrast: additivity across dimensions[J]. Vision Research, 2000, 40:1183-1201.
[35] N.Hans-Christoph. Salience from feature contrast: temporal properties of saliency mechanism[J]. Vision Research, 2000, 40:2421-2435.
[36] N. Hans Christoph. Salience from feature contrast: variation switch texture density[J]. Vision Research,2000, 40:3181-3200.
[37]纪小鹏.智能交通系统中车辆视频检测、识别与跟踪方法的研究[D].青岛:中国海洋大学,2006.
[38] Koller D.Towards Robust Automatic Traffic Scene Analysis in Real-time[J].Int. Conf. Pattern Recoginition, 1994:126-131.
[39]唐晓静,琚生根,周刚.一种基于智能信息平台的ITS系统设计方案[J] .西南民族大学学报.自然科学版,2007,33(3): 652-657.
[40] A. Bensrhair, M. Bertozzi, A. Broggi, P. Miche, S. Mousset and G. Toulminet. A Cooperative Approach to Vision-based Vehicle Detection[M].IEEE Intelligent Transportation Systems Conference Proceeding, Oakland(CA) USA ,2001: 207-212.
[41] J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques[J]. International Journal ofComputer Vision, 1994, 12(1): 42-77.
[42] Bainbridge-smith, A. Lane, R. G. Determining optical flow using a differential method[J]. Image and Vision Computing, 2004, 15:11-22.
[43] Ying Wu. Optical Flow and Motion Analysis[J]. ECE510-Computer Vision Notes Series 6, Electrical & Computer Engineering Northwest University, Evanston, IL.
[44] Chiou-Shann Fuh, Petros Maragos. Region-Based Optical Flow Estimation[J]. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on.1989:130-135.
[45] Nagel, H.-H., Haag, M. Bias-corrected optical flow estimation for road vehicle tracking[J]. ComputerVision. Sixth International Conference on,1998: 1006-1011.
[46]沈海浪,平西建,许志勇.一种基于背景重建的运动目标检测算法[J].信息工程大学学报2004,5 (3): 69-71.
[47] Toyama K, Krumm J, Brumitt B. Wallfollower. Principles and practice of background maintenance[J]. International Conference on Computer Vision, Greece, 1999:244-261.
[48]方帅,薛方正,徐心和.基于背景建模的动态目标检测算法的研究与仿真[J].系统仿真学报, 2005:17(1).
[49]阮秋琦.数字图像处理学(第二版)[M].北京:电子工业出版社,2007:334-338.
[50]冈萨雷斯.数字图像处理(第二版) [M].电子工业出版社,2007:70-80.
[51]赵英男. Gabor滤波器在车辆检测和车型识别中的应用研究[D].南京:南京理工大学,2004.
[52]张宗杰.视频监控中运动目标检测与跟踪关键技术研究[D].苏州:苏州大学,2007.
[53]于成忠.视频序列中运动目标的提取与跟踪[D].南京:东南大学,2006.
[54]顾庆.基于视觉信息的运动体位置提取算法和实验研究[D].吉林:吉林大学, 2007.
[55]魏瑞斌.基于多特征的运动目标跟踪[D].陕西:西北大学, 2007.
[56]李安平.复杂环境下的视频目标跟踪算法研究[D].上海:上海交通大学, 2007 .
[57]吴宝成.粒子滤波器重采样算法研究及其应用[D].哈尔滨:哈尔滨工业大学,2006.
[58]王昆.基于粒子滤波器的机动目标跟踪技术[D].南京:南京理工大学, 2007.
[59]杨莉.图像特征检测与运动目标分割算法的研究和实现[D].西安:西安电子科技大学, 2004 .
[60]李春明.视频图像中的运动人体检测和人脸识别[D]西安电子科技大学, 2005.
[61]鲁照华.视频编码算法研究及其无线传输实现[D].天津:天津大学, 2005.
[62]毕凌燕.交叠正交变换与视频分割编码的研究[D].广州:华南理工大学, 2003 .
[63]赵坤.复杂环境下红外小目标检测与跟踪技术研究[D].哈尔滨:哈尔滨工程大学, 2006 .
[64]冯志全.运动人手的三维跟踪方法研究[D].山东:山东大学, 2006 .
[65] Sheng-Tong Zhong; Fei Hao. Hand Tracking by Particle Filtering with Elite Particles Mean Shift. Frontier of Computer Science and Technology[J]. 2008. FCST '08. Japan-China Joint Workshop on 27-28 Dec. 2008:163–167.
[66] Pérez P, Blake A, and Gangnet M. JetStream. Probabilistic contour extraction with particles. Proc[J]. Int Conf on Computer 2001: 524-531.
[67] Doucet A, and Gordon N. Sequential Monte Carlo Methods in Practice[C]. 2001:64-125.
[68] Zhu Ye, Zhi-Qiang Liu. Genetic condensation for motion tracking. Machine Learning and Cybernetics[J]. 2005(3):2518-2524.
[69] Djuric P M; Bugallo M F, Miguez J. Density assisted particle filters for state and parameter estimation[J]. IEEE International Conference on. 2004(2):701-710.
[70] C. M. Privitera, L. W. Stark. Algorithms for defining visual regions-of-interest:comparison with eye fixations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(19):970-982.
[71] H. W. Kwak, H. Egeth. Consequences of allocating attention to locations and to other attributes[J]. Percept. Psychophys, 1992, 51:455-464.