基于多模信息融合的公共区域视频监控系统研究
|
摘要
视频监控系统是信息科学、计算机科学、机器视觉等学科理论及各种硬件和技术相结合的综合系统,可以为突发性事件的取证、分析、研究提供及时、全面和可靠的信息,帮助管理人员合理调动资源,有针对性地制定解决方案,从而提高安全防范水平。视频监控以其在城市治安管理上的独特优势,已经成为当今人工智能领域的一个研究热点。然而,目前的视频监控系统结构简单,其各部分的算法仍存在一些缺陷,因此迫切需要采取更先进的技术,提高视频监控系统在实际应用中的可行性、稳定性和实时性。
本文从视频监控系统的整体结构入手,运用智能信息处理的相关技术,对其中涉及到的相关理论方法进行研究。首先,针对运动目标检测过程易受背景抖动、环境光线变化等外界因素干扰而造成目标提取失败这一问题,提出一种基于时域差分法和背景减除法相结合的运动目标检测方法,降低了噪声对目标检测所造成的误判,并且对背景扰动、阴影等影响有较好地抑制作用,使检测的准确率明显提高;其次,在对运动目标识别与分类的研究中,采用D-S(Dempster-Shafer)证据理论对运动目标的面积、速度和形状复杂度进行多特征信息融合。针对D-S证据理论在证据高冲突下失效这一问题,采用一种优化权值分配模型的改进方法,有效地消除了冲突证据对融合结果的影响,使目标识别的结果更加合理、客观;最后,将基于参数化主动轮廓模型的目标跟踪方法应用于本文设计的基于多模块信息融合的视频监控系统中。该系统通过集成运动检测模块、头部检测模块、目标识别模块、主动轮廓跟踪四个模块,克服单个模块的局限性来提高监控系统整体性能,为复杂环境下的运动目标的检测、识别与跟踪提供了一种新途径。
本文对提出的运动目标检测方法、目标识别分类方法以及开发的视频监控系统进行了大量的实验,验证了这些方法在实际应用中的有效性,具有一定的理论价值和实用价值。
The visual surveillance system is the complex combination system of information science, computer science, machine vision and all kinds of hardware, technology and theories. The visual surveillance system not only provide prompt, comprehensive and the reliable information for sudden event’s evidence collection, analysis and research, but also help administrators transfer the resources reasonably, and works out the pertinence solution. Thus the visual surveillance system can remarkable raises the level of security protection.
Starting with the overall structure of visual surveillance system, this thesis has studied the main involved theories by utilizing the technique of intelligence information processing. Firstly, the paper proposed a novel method for moving-objects detection based on fusion of background subtraction and an improved three frames differencing in view of the influence of applications in the reality, such as light changes, camera shake, backgrounds disturbing and so on. The experimental results show that the new method effectively decreases the misjudgments caused by noise, significantly improves the accuracy, and can meet the needs of real-time. Secondly, aiming at the problem of target identification in the multi-features fusion of the visual surveillance system, a improved Dempster-Shafter evidence theory are put forward on the basis of optimization theory, which have effectively solved the problem of object recognition in the condition of high evidence conflict. This algorithm is used for video surveillance system to distinguish vehicle, people and other objects. Through analyzing the simulation example, the results show that the algorithm can gives a more reasonable combination results and has a good adaptive ability. At last, the visual surveillance system based on fusion of mult-model data is designed, which integrates motion detector module, head detector module, target recognition module and parametric active contours tracker module. The main goal of using more than one module is to make up for deficiencies in the individual modules, thus achieving a better overall tracking performance than each single module could provide.
Lots of experiments are also provided for theories put forward in this thesis, including moving-objects detection and adaptive background updating method, object recognition method, and at result the effectiveness and feasibility of these methods are proved.
本文从视频监控系统的整体结构入手,运用智能信息处理的相关技术,对其中涉及到的相关理论方法进行研究。首先,针对运动目标检测过程易受背景抖动、环境光线变化等外界因素干扰而造成目标提取失败这一问题,提出一种基于时域差分法和背景减除法相结合的运动目标检测方法,降低了噪声对目标检测所造成的误判,并且对背景扰动、阴影等影响有较好地抑制作用,使检测的准确率明显提高;其次,在对运动目标识别与分类的研究中,采用D-S(Dempster-Shafer)证据理论对运动目标的面积、速度和形状复杂度进行多特征信息融合。针对D-S证据理论在证据高冲突下失效这一问题,采用一种优化权值分配模型的改进方法,有效地消除了冲突证据对融合结果的影响,使目标识别的结果更加合理、客观;最后,将基于参数化主动轮廓模型的目标跟踪方法应用于本文设计的基于多模块信息融合的视频监控系统中。该系统通过集成运动检测模块、头部检测模块、目标识别模块、主动轮廓跟踪四个模块,克服单个模块的局限性来提高监控系统整体性能,为复杂环境下的运动目标的检测、识别与跟踪提供了一种新途径。
本文对提出的运动目标检测方法、目标识别分类方法以及开发的视频监控系统进行了大量的实验,验证了这些方法在实际应用中的有效性,具有一定的理论价值和实用价值。
The visual surveillance system is the complex combination system of information science, computer science, machine vision and all kinds of hardware, technology and theories. The visual surveillance system not only provide prompt, comprehensive and the reliable information for sudden event’s evidence collection, analysis and research, but also help administrators transfer the resources reasonably, and works out the pertinence solution. Thus the visual surveillance system can remarkable raises the level of security protection.
Starting with the overall structure of visual surveillance system, this thesis has studied the main involved theories by utilizing the technique of intelligence information processing. Firstly, the paper proposed a novel method for moving-objects detection based on fusion of background subtraction and an improved three frames differencing in view of the influence of applications in the reality, such as light changes, camera shake, backgrounds disturbing and so on. The experimental results show that the new method effectively decreases the misjudgments caused by noise, significantly improves the accuracy, and can meet the needs of real-time. Secondly, aiming at the problem of target identification in the multi-features fusion of the visual surveillance system, a improved Dempster-Shafter evidence theory are put forward on the basis of optimization theory, which have effectively solved the problem of object recognition in the condition of high evidence conflict. This algorithm is used for video surveillance system to distinguish vehicle, people and other objects. Through analyzing the simulation example, the results show that the algorithm can gives a more reasonable combination results and has a good adaptive ability. At last, the visual surveillance system based on fusion of mult-model data is designed, which integrates motion detector module, head detector module, target recognition module and parametric active contours tracker module. The main goal of using more than one module is to make up for deficiencies in the individual modules, thus achieving a better overall tracking performance than each single module could provide.
Lots of experiments are also provided for theories put forward in this thesis, including moving-objects detection and adaptive background updating method, object recognition method, and at result the effectiveness and feasibility of these methods are proved.
引文
[1]王洪波,李海平,董强.舰船综合网络视频监控系统设计[J].舰船科学技术, 2007, 29(1): 129-132.
[2]荆永良,张华,耿群.商业银行视频监控系统发展趋势研究[J].金融发展研究, 2009, 4: 48-49.
[3]任明,朱伟,朱寿建.视频智能交通系统的设计与实现[J].交通运输系统工程与信息, 2002, 2 (3): 79-81.
[4]严捷丰.交通视频监控中的车辆检测与跟踪技术研究[D].合肥:中国科学技术大学, 2008.
[5] Collins Retal. A system for video surveillance and monitoring: VSAM final report [C]. Carnegie Mellon University: Technical Report CMU, 2000.
[6] N. T. Siebel, S. J. Maybank. Fusion of multiple tracking algorithms for robust people tracking [C]. Proceedings of the 7th European Conference on Computer Vision, Denmark. 2002: 373-387.
[7] N. T. Siebel, S. J. Maybank. The ADVISOR visual surveillance system [C]. In Proceedings of the ECCV 2004 Workshop“Applications of Computer Vision”. Prague, Czech Republic. 2004: 103-111.
[8] Maggioni C, Kammerer B. Gesture Computer: History, Design, and Applications. Computer Vision for Human-Machine Interaction [M]. Cambridge: Cambridge University Press, 1998.
[9] Pentland A. Looking at people: Sensing for ubiquitous and wearable computing [C]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(1): 107-119.
[10]孙庆杰.静态图像中人体检测技术研究[D].中国科学院博士学位论文, 2004.
[11]王亮,胡卫民,谭铁牛.人运动的视觉分析综述[J].计算机学报, 2002, 25(3): 225-237.
[12] C.Stauffer, W.E.L. Grimson, Learning Patterns of Activity Using Real-Time Tracking [J]. IEEE Transactions on Pattern Analysis arid Machine Intelligence, 2000, 11(8): 747-757.
[13] C.Stauffer, W.E.L. Grimson, Adaptive Background Mixture Models for Real-Time Tracking [C]. Pro Computer Visition and Pattern Recognition (CVPR’99), June 1999.
[14] Haritaoglu I, Harwood D, Davis L. W4: Real-time surveillance of people and their activities [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (8): 809-830.
[15] McKenna Setal. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80 (1): 42-56.
[16] Karmann K, Brandt A. Moving object recognition using an adaptive background memory [C]. In: Cappellini V ed. Time varying Image Processing and Moving Object Recognition. Amsterdam, Netherlands, 1990.
[17]艾海舟,乐秀宇.面向视觉监控实时跟踪的动态背景更新方法[J].计算机工程与应用. 2001, 19: 104-106.
[18]刘永,戴礼荣,宋彦.一种静态背景下的运动目标提取算法[J].中国图形图像学报, 2003, 8(7): 759-763.
[19]王栓,艾海舟,何克忠.基于差分图像的多运动目标的检测与跟踪[J].中国图形图像学报, 1999, 4(6): 470-474.
[20]陈坚,李在铭.场景监视中的运动目标检测技术[J].信号处理, 2001, 17:337-341.
[21]谢敏,黄贤武,仲兴荣等.基于信息融合的视频序列图像中运动目标分割的研究[J].电子与信息学报.2004, 02, 146-151.
[22] Meyer D, Denzler J, Niemann H. Model based extraction of articulated objects in image sequences for gait analysis [C]. In: Proc IEEE International Conference on Image Processing, Santa Barbara,California 1997: 78-81.
[23]伏思华,张小虎.基于序列图像的运动目标实时检测方法[J].光学技术. 2004, 02: 87-89, 94.
[24]刘永信,魏平,侯朝桢.视频图像中运动目标检测的快速方法[J].仪器仪表学报. 2002, S3: 163-166.
[25]章毓晋.图像工程(中册)图像分析.清华大学出版社, 2005.
[26]韩彦平,吕梅柏.基于视频图像的运动目标识别与跟踪方法研究[J].弹舰与制导学报. 2006, 26(2): 383-386.
[27]周西汉,刘勃,周荷琴.一种基于对称差分和背景消减的运动检测方法.计算机仿真. 2005, 22(4): 117-119.
[28] Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV color information [A]. In: Proceedings of IEEE Intelligent Transportation Systems conference [C]. Oakland, CA, USA, 2001: 334-339.
[29]王小艺,侯朝桢,原菊梅,刘载文.基于优化策略改进的D-S证据识别算法[J].光电子·激光, 2006, 17(8): 999-1003.
[30]陈文吉.信息统合系统目标识别相关技术研究.北京理工大学博士论文, 2004, 7.
[31] Larsen, H. L., Yager, R. R. A framework for fuzzy recognition technology system. Man and Cybernetics, Part C, IEEE Transactions on, 2000, 30(1): 65-76.
[32]权太范.信息融合神经网络-模糊推理理论与应用.北京:国防科技出版社, 2002.
[33] Dempster A P. Upper and lower probabilities induced by a multi-valued mapping [J]. The Annual Math Statistic, 1967, 38(4): 325-339.
[34] Shafer G A. Mathematical theory of evidence [M]. Princeton University Press, 1976: 19-63.
[35] Xu Congfu, Geng Weidong, Pan Yunhe. Review of Demspter-Shafer method for data fusion [J]. Acta Electronica Sinica, 2001, 29(3): 393-396.
[36]孙红雨,向阳,郭银景. D-S证据理论在车辆几何参数动态测量中的应用[J].计算机应用, 2009, 29(6): 1371-1375.
[37]张平定,孙炜,白剑林等. D-S理论与模糊理论在指挥系统目标识别融合中的应用[J].火力与指挥控制, 2009, 34(5): 98-100.
[38] Zadeh L. A simple view of the Demspter-Shafer theory of evidence and its implication for rule of combination [J]. AI magazine, 1986, 7(1): 85-90.
[39] Lefevre E. Belief function combination and conflict management [J]. Information Fusion, 2002, (3): 111-114.
[40] Yager R. On the Dempster-Shafer framework and new combination rules [J]. Information Sciences, 1986, 41(2): 93-137.
[41]孙全,叶秀清,顾伟康.一种新的基于证据理论的合成公式[J].电子学报, 2000, 28(8): 117-119.
[42]刘海燕,赵宗贵,刘熹. D-S证据理论中冲突证据的合成方法[J].电子科技大学学报, 2008, 37(5): 701-704.
[43] Murphy C K. Combining belief functions when evidence conflicts [J]. Decision Support Systems, 2000, 29(1): 1-9.
[44]王小艺,刘载文,侯朝桢.一种基于最优权重分配的D-S改进算法[J].系统工程理论与实践, 2006, (11): 103-107.
[45] Jousselem A, Grenier D, Bosse E. A new distance between two bodie s of evidence [J]. Information Fusion, 2001, 2: 91-101.
[46] James Kennedy, Russell C. Eberhart. Particle Swarm Optimization. Perth, Western Australia, IEEEInternational Conference on Neural Networks, 1995, 1942-1948.
[47]雷开友.粒子群算法及其应用研究[D].西南大学, 2006.
[48]纪震,廖惠连,吴青华.粒子群算法及应用[M].科学出版社, 2009.
[49]雷秀娟,史忠科.粒子群优化算法在函数优化中的应用及参数分析[J].计算机工程与应用, 2008, 44(28): 53-54, 90.
[50]张艳丽,保文星.粒子群优化算法在图像边缘检测中的研究应用[J].计算机技术与发展, 2009, 19(5): 26-29.
[51]郑林,韩崇昭,左东广等.基于多特征融合的运动目标识别[J].系统仿真学报, 2004, 16(5): 1081-1084.
[52]高钰,常永亮,穆战松.基于运动目标识别技术的视频监控系统[J].计算技术与自动化, 2005, 24(4): 29-31.
[53]熊荣炎,姜弢,马成顺.基于特征值的运动目标快速检测与跟踪[J].齐齐哈尔大学学报(自然科学版). 2007, 02.
[54]李豪杰,林守勋,张勇东.基于视频的人体运动捕捉综述[J].计算机辅助设计与图形学学报. 2006, 18(11): 1645-1651.
[55] Karaulova I, Hall P and Marshall A. A hierarchical model of dynamics for tracking people with a single video camera [C]. In: British Machine Vision Conference, Bristol, UK, 2000: 352-361.
[56] Niyogi S, Adelson E. Analyzing and recognizing walking figures in XYT. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, 1994: 469-474.
[57] Wachter S, Nagel H-H. Tracking persons in monocular image sequences [J]. Computer Vision and Image Understanding, 1999, 74 (3): 174-192.
[58] Polana R, Nelson R. Low level recognition of human motion [J]. In: Proc IEEE Work shop on Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994. 77-82.
[59] Segen J, Pingali S. A camera-based system for tracking people in real time [M]. In: Proc International Conference on Pattern Recognition, Vienna, 1996. 63-67.
[60] Jang D, Choi H. Active models for tracking moving objects [J]. Pattern Recognition, 2000, 33(7): 1135-1146.
[61] Chen. H, Liu.T. Multi-object tracking using dynamical graph matching [R]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001, 2:210-217.
[62] Wren C, Azarbayejani A, Darrell T, et al. [J]. Real-time tracking of the human body [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 780-785.
[63] Kass M, Witkin A, Terzopoulos D. Snakes [J]. Active contour models [J]. International Journal of Computer Vision, 1987, 1(4):321-331.
[64]董春利,董育宁,王莉.活动轮廓模型目标跟踪算法综述[J].计算机工程与应用, 2008, 44(34): 208-212.
[65] Paragios N, Deriche R. Geodesic active regions and level set methods for motion estimation and tracking [J]. Computer Vision and Image Understanding, 2005, 97(3): 259-282.
[66] Williams D J, Shah M. A fast algorithm for contours and survature estimation [J]. Computer Vision, Graphics and Image Processing: Image Understanding, 1992, 55(1): 14-26.
[67] Peterfreund N. Robust tracking of position and velocity with Kalman snakes [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (6): 564-569.
[68]查宇飞,张育,毕笃彦.基于区域活动轮廓运动目标跟踪方法的研究[J].中国图像图形学报, 2006, 11(12). 1844-1848.
[69]罗嘉,韦志辉.基于几何活动轮廓模型的目标跟踪与快速运动估计[J].中国图像图形学报,2009, 14(7). 1361-1368.
[70]方挺,杨忠,沈春林.一种基于主动轮廓模型的运动目标跟踪方法[J].信息与控制, 2008, 37(1): 99-103.
[71]杨莉,李玉山.复杂背景下的多运动目标轮廓检测[J].电子与信息学报, 2005, 2 (2): 306-309.
[2]荆永良,张华,耿群.商业银行视频监控系统发展趋势研究[J].金融发展研究, 2009, 4: 48-49.
[3]任明,朱伟,朱寿建.视频智能交通系统的设计与实现[J].交通运输系统工程与信息, 2002, 2 (3): 79-81.
[4]严捷丰.交通视频监控中的车辆检测与跟踪技术研究[D].合肥:中国科学技术大学, 2008.
[5] Collins Retal. A system for video surveillance and monitoring: VSAM final report [C]. Carnegie Mellon University: Technical Report CMU, 2000.
[6] N. T. Siebel, S. J. Maybank. Fusion of multiple tracking algorithms for robust people tracking [C]. Proceedings of the 7th European Conference on Computer Vision, Denmark. 2002: 373-387.
[7] N. T. Siebel, S. J. Maybank. The ADVISOR visual surveillance system [C]. In Proceedings of the ECCV 2004 Workshop“Applications of Computer Vision”. Prague, Czech Republic. 2004: 103-111.
[8] Maggioni C, Kammerer B. Gesture Computer: History, Design, and Applications. Computer Vision for Human-Machine Interaction [M]. Cambridge: Cambridge University Press, 1998.
[9] Pentland A. Looking at people: Sensing for ubiquitous and wearable computing [C]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(1): 107-119.
[10]孙庆杰.静态图像中人体检测技术研究[D].中国科学院博士学位论文, 2004.
[11]王亮,胡卫民,谭铁牛.人运动的视觉分析综述[J].计算机学报, 2002, 25(3): 225-237.
[12] C.Stauffer, W.E.L. Grimson, Learning Patterns of Activity Using Real-Time Tracking [J]. IEEE Transactions on Pattern Analysis arid Machine Intelligence, 2000, 11(8): 747-757.
[13] C.Stauffer, W.E.L. Grimson, Adaptive Background Mixture Models for Real-Time Tracking [C]. Pro Computer Visition and Pattern Recognition (CVPR’99), June 1999.
[14] Haritaoglu I, Harwood D, Davis L. W4: Real-time surveillance of people and their activities [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (8): 809-830.
[15] McKenna Setal. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80 (1): 42-56.
[16] Karmann K, Brandt A. Moving object recognition using an adaptive background memory [C]. In: Cappellini V ed. Time varying Image Processing and Moving Object Recognition. Amsterdam, Netherlands, 1990.
[17]艾海舟,乐秀宇.面向视觉监控实时跟踪的动态背景更新方法[J].计算机工程与应用. 2001, 19: 104-106.
[18]刘永,戴礼荣,宋彦.一种静态背景下的运动目标提取算法[J].中国图形图像学报, 2003, 8(7): 759-763.
[19]王栓,艾海舟,何克忠.基于差分图像的多运动目标的检测与跟踪[J].中国图形图像学报, 1999, 4(6): 470-474.
[20]陈坚,李在铭.场景监视中的运动目标检测技术[J].信号处理, 2001, 17:337-341.
[21]谢敏,黄贤武,仲兴荣等.基于信息融合的视频序列图像中运动目标分割的研究[J].电子与信息学报.2004, 02, 146-151.
[22] Meyer D, Denzler J, Niemann H. Model based extraction of articulated objects in image sequences for gait analysis [C]. In: Proc IEEE International Conference on Image Processing, Santa Barbara,California 1997: 78-81.
[23]伏思华,张小虎.基于序列图像的运动目标实时检测方法[J].光学技术. 2004, 02: 87-89, 94.
[24]刘永信,魏平,侯朝桢.视频图像中运动目标检测的快速方法[J].仪器仪表学报. 2002, S3: 163-166.
[25]章毓晋.图像工程(中册)图像分析.清华大学出版社, 2005.
[26]韩彦平,吕梅柏.基于视频图像的运动目标识别与跟踪方法研究[J].弹舰与制导学报. 2006, 26(2): 383-386.
[27]周西汉,刘勃,周荷琴.一种基于对称差分和背景消减的运动检测方法.计算机仿真. 2005, 22(4): 117-119.
[28] Cucchiara R, Grana C, Piccardi M, et al. Improving shadow suppression in moving object detection with HSV color information [A]. In: Proceedings of IEEE Intelligent Transportation Systems conference [C]. Oakland, CA, USA, 2001: 334-339.
[29]王小艺,侯朝桢,原菊梅,刘载文.基于优化策略改进的D-S证据识别算法[J].光电子·激光, 2006, 17(8): 999-1003.
[30]陈文吉.信息统合系统目标识别相关技术研究.北京理工大学博士论文, 2004, 7.
[31] Larsen, H. L., Yager, R. R. A framework for fuzzy recognition technology system. Man and Cybernetics, Part C, IEEE Transactions on, 2000, 30(1): 65-76.
[32]权太范.信息融合神经网络-模糊推理理论与应用.北京:国防科技出版社, 2002.
[33] Dempster A P. Upper and lower probabilities induced by a multi-valued mapping [J]. The Annual Math Statistic, 1967, 38(4): 325-339.
[34] Shafer G A. Mathematical theory of evidence [M]. Princeton University Press, 1976: 19-63.
[35] Xu Congfu, Geng Weidong, Pan Yunhe. Review of Demspter-Shafer method for data fusion [J]. Acta Electronica Sinica, 2001, 29(3): 393-396.
[36]孙红雨,向阳,郭银景. D-S证据理论在车辆几何参数动态测量中的应用[J].计算机应用, 2009, 29(6): 1371-1375.
[37]张平定,孙炜,白剑林等. D-S理论与模糊理论在指挥系统目标识别融合中的应用[J].火力与指挥控制, 2009, 34(5): 98-100.
[38] Zadeh L. A simple view of the Demspter-Shafer theory of evidence and its implication for rule of combination [J]. AI magazine, 1986, 7(1): 85-90.
[39] Lefevre E. Belief function combination and conflict management [J]. Information Fusion, 2002, (3): 111-114.
[40] Yager R. On the Dempster-Shafer framework and new combination rules [J]. Information Sciences, 1986, 41(2): 93-137.
[41]孙全,叶秀清,顾伟康.一种新的基于证据理论的合成公式[J].电子学报, 2000, 28(8): 117-119.
[42]刘海燕,赵宗贵,刘熹. D-S证据理论中冲突证据的合成方法[J].电子科技大学学报, 2008, 37(5): 701-704.
[43] Murphy C K. Combining belief functions when evidence conflicts [J]. Decision Support Systems, 2000, 29(1): 1-9.
[44]王小艺,刘载文,侯朝桢.一种基于最优权重分配的D-S改进算法[J].系统工程理论与实践, 2006, (11): 103-107.
[45] Jousselem A, Grenier D, Bosse E. A new distance between two bodie s of evidence [J]. Information Fusion, 2001, 2: 91-101.
[46] James Kennedy, Russell C. Eberhart. Particle Swarm Optimization. Perth, Western Australia, IEEEInternational Conference on Neural Networks, 1995, 1942-1948.
[47]雷开友.粒子群算法及其应用研究[D].西南大学, 2006.
[48]纪震,廖惠连,吴青华.粒子群算法及应用[M].科学出版社, 2009.
[49]雷秀娟,史忠科.粒子群优化算法在函数优化中的应用及参数分析[J].计算机工程与应用, 2008, 44(28): 53-54, 90.
[50]张艳丽,保文星.粒子群优化算法在图像边缘检测中的研究应用[J].计算机技术与发展, 2009, 19(5): 26-29.
[51]郑林,韩崇昭,左东广等.基于多特征融合的运动目标识别[J].系统仿真学报, 2004, 16(5): 1081-1084.
[52]高钰,常永亮,穆战松.基于运动目标识别技术的视频监控系统[J].计算技术与自动化, 2005, 24(4): 29-31.
[53]熊荣炎,姜弢,马成顺.基于特征值的运动目标快速检测与跟踪[J].齐齐哈尔大学学报(自然科学版). 2007, 02.
[54]李豪杰,林守勋,张勇东.基于视频的人体运动捕捉综述[J].计算机辅助设计与图形学学报. 2006, 18(11): 1645-1651.
[55] Karaulova I, Hall P and Marshall A. A hierarchical model of dynamics for tracking people with a single video camera [C]. In: British Machine Vision Conference, Bristol, UK, 2000: 352-361.
[56] Niyogi S, Adelson E. Analyzing and recognizing walking figures in XYT. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, 1994: 469-474.
[57] Wachter S, Nagel H-H. Tracking persons in monocular image sequences [J]. Computer Vision and Image Understanding, 1999, 74 (3): 174-192.
[58] Polana R, Nelson R. Low level recognition of human motion [J]. In: Proc IEEE Work shop on Motion of Non-Rigid and Articulated Objects, Austin, TX, 1994. 77-82.
[59] Segen J, Pingali S. A camera-based system for tracking people in real time [M]. In: Proc International Conference on Pattern Recognition, Vienna, 1996. 63-67.
[60] Jang D, Choi H. Active models for tracking moving objects [J]. Pattern Recognition, 2000, 33(7): 1135-1146.
[61] Chen. H, Liu.T. Multi-object tracking using dynamical graph matching [R]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, 2001, 2:210-217.
[62] Wren C, Azarbayejani A, Darrell T, et al. [J]. Real-time tracking of the human body [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19 (7): 780-785.
[63] Kass M, Witkin A, Terzopoulos D. Snakes [J]. Active contour models [J]. International Journal of Computer Vision, 1987, 1(4):321-331.
[64]董春利,董育宁,王莉.活动轮廓模型目标跟踪算法综述[J].计算机工程与应用, 2008, 44(34): 208-212.
[65] Paragios N, Deriche R. Geodesic active regions and level set methods for motion estimation and tracking [J]. Computer Vision and Image Understanding, 2005, 97(3): 259-282.
[66] Williams D J, Shah M. A fast algorithm for contours and survature estimation [J]. Computer Vision, Graphics and Image Processing: Image Understanding, 1992, 55(1): 14-26.
[67] Peterfreund N. Robust tracking of position and velocity with Kalman snakes [J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (6): 564-569.
[68]查宇飞,张育,毕笃彦.基于区域活动轮廓运动目标跟踪方法的研究[J].中国图像图形学报, 2006, 11(12). 1844-1848.
[69]罗嘉,韦志辉.基于几何活动轮廓模型的目标跟踪与快速运动估计[J].中国图像图形学报,2009, 14(7). 1361-1368.
[70]方挺,杨忠,沈春林.一种基于主动轮廓模型的运动目标跟踪方法[J].信息与控制, 2008, 37(1): 99-103.
[71]杨莉,李玉山.复杂背景下的多运动目标轮廓检测[J].电子与信息学报, 2005, 2 (2): 306-309.