面向水质监测的鱼类目标跟踪与运动行为建模系统研究
|
摘要
生物水质自动监测方法目前被广泛应用于水体的质量监测和安全预警中,其特点是利用水生生物的生理特性以及对不同水质的行为特性反应水体质量的变化以及水体污染的程度,从生物学角度为水体质量评价提供依据。较传统的理化分析方法,生物检测可以综合多种有毒物质的相互作用,判定有毒物质的质量浓度和生物运动特征之间的直接关系。但是,如何快速有效地提取生物的运动特征,是生物水质自动监测方法的主要研究内容。
本文以鱼类作为水质监测的传感器,研究了计算机视觉在水质监测中应用,初步构建了一个面向水质监测的鱼类目标跟踪与运动行为建模系统。研究内容主要包括:鱼类运动目标的实时检测与跟踪、鱼类运动行为建模以及鱼类运动监测平台的搭建。研究工作归纳如下:
1.研究了基于模糊推理背景差分的鱼类运动目标实时检测方法?
针对传统背景差分算法背景帧更新速度慢且不够精确的问题,本文提出了基于模糊推理的背景更新算法。该算法能快速提取鱼类运动目标的背景,实时、准确地分离出鱼类运动目标的前景。同时,为了增强算法的鲁棒性,本文引入了抗噪声的模糊推理来克服环境变化的影响。
2.研究了基于自动Camshift二次检索的鱼类运动目标跟踪方法?
针对传统Camshift算法不能实现全自动及多目标跟踪的问题,本文结合模糊推理背景差分和二次搜索,提出了Camshift自动跟踪算法,有效地克服了目标无法自动跟踪以及跟踪不准确、易丢失的现象。并在此基础上,引入了轮廓的标识思想,采用多Camshift跟踪器实现了Camshift算法的多目标跟踪。
3.研究了基于PTW模型的鱼类运动行为建模方法?
根据目标检测与跟踪得到的鱼类运动的位移及计算得到的速度与角速度,研究了基于PTW模型的鱼类运动行为建模方法。建立正常情况下鱼类运动的速度、角速度与轨迹模型,为鱼类的异常运动提供判断标准。
4.研究了基于计算机视觉的鱼类运动监测平台?
提出了面向水质监测的鱼类目标跟踪与运动行为建模的平台体系结构。开发了鱼类视频采集模块、视觉跟踪模块与鱼类运动行为建模模块的平台软件。
Biomonitoring techniques, with the vantage of biological basis for water quality assessment by observing physiological properties and different reactions of aquatic animals to water qualities and pollution degree, have been universally applied to water quality monitor and security pre-warning systems of environmental quality. Compared to traditional physico-chemical analysis, biological detection is capable of analyzing the interplays of multiple toxic substances and determining the direct relations between the mass concentration of toxic substances and movement features of aquatic animals. Thus, the attention of automatically biological monitoring of water quality is concentrated on effective and efficient extractions of the movement features of aquatic animals.
By taking fishes as the sensors of water quality monitor, this paper has analyzed the application of computer vision in water quality monitoring, and a system of fish tracking and movement behavior modeling for water quality monitor has been constructed initially in the process. The research focuses of this paper include real-time detecting of the fish movement, constructions of both the behavioral modeling and the monitoring platform of fish movement. To be specific, followings are four focal perspectives to be expounded in this paper.
The real time detecting method based on fuzzy inference of background difference is first to be explored in this paper. In the attempt to improve the refresh rate and quality of the background frame offered by traditional background difference algorithm, this paper has proposed another algorithm for updating background frame on the basis of fuzzy inference and difference in frame. Through fuzzy inference, the background of the object will be extracted efficiently and the foregrounds will be correctly separated in real time. Meanwhile, fuzzy inference of anti-noises will also be introduced to strengthen the robustness of the algorithm and further to overcome environmental factors.
Second, the object tracking algorithm based on twice searching of auto-Camshift will be explored. As to the fact that traditional Camshift algorithm fails to realize auto and multi-objects tracking, this paper, with fuzzy inference background difference and twice searching as its major methodology, has proposed the auto-Camshift tracking algorithm to feasibly overcome traditional tracking problems such as incompetent of auto-tracking and unsatisfactory tracking results. Furthermore, contour marks and multi-Camshift tracker are introduced to achieve the multi-object tracking of Camshift algorithm.
Third, this paper has demonstrated the PTW based modeling method of fish movement behavior, which will be expounded on the basis of displacement of the fish movement tracked and assessed as well as the velocity and angle velocity calculated. Meanwhile, the velocity and locus model of fish movement under normal condition is also established to offer a criterion for abnormal fish movement.
Last but not least, a system platform of fish tracking and movement behavior modeling for water quality monitor has also been proposed and a software platform for fish video capturing model, vision processing model and fish behavioral model initially constructed.
本文以鱼类作为水质监测的传感器,研究了计算机视觉在水质监测中应用,初步构建了一个面向水质监测的鱼类目标跟踪与运动行为建模系统。研究内容主要包括:鱼类运动目标的实时检测与跟踪、鱼类运动行为建模以及鱼类运动监测平台的搭建。研究工作归纳如下:
1.研究了基于模糊推理背景差分的鱼类运动目标实时检测方法?
针对传统背景差分算法背景帧更新速度慢且不够精确的问题,本文提出了基于模糊推理的背景更新算法。该算法能快速提取鱼类运动目标的背景,实时、准确地分离出鱼类运动目标的前景。同时,为了增强算法的鲁棒性,本文引入了抗噪声的模糊推理来克服环境变化的影响。
2.研究了基于自动Camshift二次检索的鱼类运动目标跟踪方法?
针对传统Camshift算法不能实现全自动及多目标跟踪的问题,本文结合模糊推理背景差分和二次搜索,提出了Camshift自动跟踪算法,有效地克服了目标无法自动跟踪以及跟踪不准确、易丢失的现象。并在此基础上,引入了轮廓的标识思想,采用多Camshift跟踪器实现了Camshift算法的多目标跟踪。
3.研究了基于PTW模型的鱼类运动行为建模方法?
根据目标检测与跟踪得到的鱼类运动的位移及计算得到的速度与角速度,研究了基于PTW模型的鱼类运动行为建模方法。建立正常情况下鱼类运动的速度、角速度与轨迹模型,为鱼类的异常运动提供判断标准。
4.研究了基于计算机视觉的鱼类运动监测平台?
提出了面向水质监测的鱼类目标跟踪与运动行为建模的平台体系结构。开发了鱼类视频采集模块、视觉跟踪模块与鱼类运动行为建模模块的平台软件。
Biomonitoring techniques, with the vantage of biological basis for water quality assessment by observing physiological properties and different reactions of aquatic animals to water qualities and pollution degree, have been universally applied to water quality monitor and security pre-warning systems of environmental quality. Compared to traditional physico-chemical analysis, biological detection is capable of analyzing the interplays of multiple toxic substances and determining the direct relations between the mass concentration of toxic substances and movement features of aquatic animals. Thus, the attention of automatically biological monitoring of water quality is concentrated on effective and efficient extractions of the movement features of aquatic animals.
By taking fishes as the sensors of water quality monitor, this paper has analyzed the application of computer vision in water quality monitoring, and a system of fish tracking and movement behavior modeling for water quality monitor has been constructed initially in the process. The research focuses of this paper include real-time detecting of the fish movement, constructions of both the behavioral modeling and the monitoring platform of fish movement. To be specific, followings are four focal perspectives to be expounded in this paper.
The real time detecting method based on fuzzy inference of background difference is first to be explored in this paper. In the attempt to improve the refresh rate and quality of the background frame offered by traditional background difference algorithm, this paper has proposed another algorithm for updating background frame on the basis of fuzzy inference and difference in frame. Through fuzzy inference, the background of the object will be extracted efficiently and the foregrounds will be correctly separated in real time. Meanwhile, fuzzy inference of anti-noises will also be introduced to strengthen the robustness of the algorithm and further to overcome environmental factors.
Second, the object tracking algorithm based on twice searching of auto-Camshift will be explored. As to the fact that traditional Camshift algorithm fails to realize auto and multi-objects tracking, this paper, with fuzzy inference background difference and twice searching as its major methodology, has proposed the auto-Camshift tracking algorithm to feasibly overcome traditional tracking problems such as incompetent of auto-tracking and unsatisfactory tracking results. Furthermore, contour marks and multi-Camshift tracker are introduced to achieve the multi-object tracking of Camshift algorithm.
Third, this paper has demonstrated the PTW based modeling method of fish movement behavior, which will be expounded on the basis of displacement of the fish movement tracked and assessed as well as the velocity and angle velocity calculated. Meanwhile, the velocity and locus model of fish movement under normal condition is also established to offer a criterion for abnormal fish movement.
Last but not least, a system platform of fish tracking and movement behavior modeling for water quality monitor has also been proposed and a software platform for fish video capturing model, vision processing model and fish behavioral model initially constructed.
引文
[1]蔡庆华.中国水污染综合治理的生态学思考[J].环境保护, 2007, 7(07B): 46-48.
[2]韩吉,薛国东.水污染及水污染的生物治理[J].吉林水利, 2008, 1(308): 44-46.
[3]德永健.近年我国重大水污染事件[J].中国人大, 2007, 07(17): 27.
[4]刘晓茹,李贵宝,孙天华.水质监测的自动化、网络化发展[J].第八届海峡两岸水利科技交流研讨会, 2004, 12.
[5] HJ/T96-104-2003,中华人民共和国环境保护行业标准.北京:中国环境科学出版社, 2003.
[6]李志良.鱼类行为学在水质在线监测与预警中的应用研究[D].山东师范大学, 2008, 04.
[7]刘伟成,单乐州,谢起浪,林少珍.生物监测在水环境污染监测中的应用[J].环境与健康, 2008, 25(5): 456-458.
[8]刘小卫,陆光华.主动生物监测技术在水环境风险评价中的应用[J].环境监测管理与技术, 2008, 20(3): 12-15.
[9]谢建春.水体污染与水生动物[J].生物学通报, 2001, 36(6): 10~11.
[10]王海洲,刘文华,侯福林.在线生物监测技术及其应用研究[J].生物学通报, 2007, 42(1): 15~16.
[11]李俊文.辽河水质监测与分析[J].地下水, 2008, 30(1): 61~64.
[12]马文漪,杨柳燕.环境微生物工程[M].南京:南京大学出版社, 1998.
[13]凯思斯著,曹凤中译.水污染的生物监测[M].北京:中国环境科学出版社, 1989.
[14]许木启,曹宏,王玉龙.原生动物群落多样性变化与汉沽稳定塘水质净化效能相互关系的研究[J].生态学报, 2002, 20(2): 283~287.
[15] Kumaran R., Bengt D. Principles and applications of thermal biosensors[J]. Biosensors & Bioelectronics, 2001, 16: 417~423.
[16] Manju G., Asha C., Malhotra B. Application of conducting polymers to biosensors[J]. Biosensors & Bioelectronics, 2002, 17: 345~359.
[17]郑怀礼,龚迎昆.用于环境监测的生物传感技术[J].光谱学与光谱分析, 2003, 23(2): 411~414.
[18]王玉华,赵学民,周怀东.水质自动监测技术及其应用分析[J].水文, 2004, 24(3): 54~56.
[19]林志芬,于红霞,许士奋,王连生.发光菌生物毒性测试方法的改进[J].环境科学, 2001, 02.
[20]童中华,廖军.利用淡水发光菌评估电化学处理模拟印染废水的效果[J].环境安全, 1997, 16(2).
[21]高继军,张力平,马梅.应用淡水发光菌研究二元重金属混合物的联合毒性[J].上海环境科学, 2003, 22(11).
[22]严珍,陈曦,李伟,王小如.海洋环境水质监测的发光菌生物传感器研制[A].中国化学会第七届分析化学年会暨原子光谱学术会议论文集[C],广西:广西师范大学, 2000.
[23]张凤民,胡炜.十三种硝基苯类化合物对大型蚤急性毒性的实验[J].黑龙江环境通报, 1998.
[24]黄国兰,孙红文.邻苯二甲酸二丁酯对大型蚤的毒性作用研究[J].环境化学, 1998, 17(5).
[25]吴永贵,黄建国,袁玲.利用水溞的趋光行为监测水质[J].中国环境科学, 2004.
[26]孙红文,黄国兰.偶氮染料对斜生栅藻的毒性作用及结构活性相关性研究[J].环境科学, 1998, 19(4).
[27]康瑞娟,施定基.用于微藻培养的气升式光生物反应器[J].化学反应工程与工艺, 2001.
[28]陈德辉,章宗涉.藻类批量培养中的比增长率最大值[J].水生生物学报, 1998.
[29]王春风,方展强.汞和硒对剑尾鱼的急性毒性及其安全浓度评价[J].环境科学与技术, 2005.
[30]汤一平,尤思思,叶永杰,金顺敬.基于机器视觉的生物式水质监测仪的开发[J].工业控制计算机, 2006, 19(6): 64-66.
[31]霍传林,王菊英.鱼体内EROD活性对多氯联苯类的指示作用[J].海洋环境科学, 2002, 21(1).
[32] S. Dasiopoulou, V. Mezaris, I. Kompatsiaris, V. K. Papastathis, M. G. Strintzis. Knowledge-assisted semantic video object detection [J]. IEEE Transactions on Circuits ans System for Video Technology, 2005, 15(10): 1210-1224.
[33] A. Mittal, N. Paragios, Motion-based background subtraction using adaptive kernel density estimation[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, 302-309.
[34] A. Bugeau, P. Perez. Detection and segmentation of moving objects in highly dynamic scenes [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007.
[35] G. Zhang, J. Jia, W. Xiong, T.T. Wong, P.A. Heng, H. Bao. Moving object extraction with a hand-held camera[C]. IEEE International Conference on Computer Vision, 2007.
[36] Z. Yin, R. Collins. Belief propagation in a 3d spatio-temproal mrf for moving object detection [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007.
[37] J. J. Gibson. The perception of the visual world. Boston: Houghton Mifflin, 1950.
[38] Hui-Fuang Ng. Automatic thresholding for defect detection[J]. Pattern Recognition Letters,2006, 27: 1644-1649.
[39] Horn B KP,Schunck B G. Determining Optical Flow[J]. Artificial Intelligence, 1981, 17: 185-203.
[40] C. Wren, A. Azarbayejani, T. Darrell, A. Pentland. Pfinder: Real-time tracking of the human body[J]. IEEE Trans. On Patt. Anal. and Machine Intell, 1997, 19(7): 780-785.
[41]孙立光,杨新苗.面向混合交通流的全景图像检测方法研究[A]. 2007第三届中国智能交通年会学术委员会. 2007第三届中国智交通年会论文集[C].东南大学, 2007.
[42]朱明旱,罗大庸.基于帧间差分背景模型的运动物体检测与跟踪[J].计算机测量与控制, 2006, 14(8): 1004-1006.
[43] C. Stauffer, W.E.L. Grimson. Adaptive background mixture models for real-time tracking [C]. Proc IEEE CVPR 1999, 1999, 246-252.
[44] Koivunen T. A noise-insensitive motion detector[J]. IEEE TCE, 1992, 38(3): 168-174
[45] R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D.Duggins, Y.Tsin, D.Tolliver, N. Enomoto, O.Hasegawa, P. Burt, L. Wixson. Asystem for video surveillance and monitoring [R]. 2000.
[46] Y. Kameda, M. Minoh. A human motion estimation method using 3-successive video frames [C]. ICVSM, 1996, 135-140.
[47] Aggarwal J K,Nandhakumar N. On the computation of motion from sequences of images-A review[J]. Proceedings of the IEEE, 1988, 76(8): 917-935.
[48] Coifman B,Beymer D,Mclauchlan P,Malik J. A real-time computer vision sustem for vehicle tracking andtraffic surveillance[J]. Transportation Research Part C, 1998, 6(4): 271-288.
[49] Wang L,Hu W M,Tan T N. A survey of visual analysis of human motion[J]. Chinese Journal of Computers, 2002, 25(3): 225-237.
[50] A. Yilmaz, O.Javed, M.Shah. Object tracking: A survey[J]. ACM Computing Surveys, 2006, 38(4): 13.
[51] R.E. Kalman, A new approach to linear filtering and prediction problems[J]. American Society of Mechanical Engineers, Journal of Basic Engineering, 1960, 82: 35-45.
[52] Bar-Shalom Y, Fortmann T. A new extension of the Kalman filter to nonlinear system[J]. Proceedings of SPIE, 1997, 3068: 182-93.
[53] Salmond D, Gordon N, Smith A. A novel approach to nonlinear/non-Gaussian Bayesian state estimation[J]. IEEE Proceeding on Radar,Sonar and Navigation, 1993, 140(2): 107-113.
[54] Isard M, Blake A. CONDENSATION-Conditional density propagation for visual tracking[J]. International Journal of Computer Vision, 1998, 29(1): 5-28.
[55] Cheng Y. Mean Shift,Mode Seeking and Clustering[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.
[56] Comaniciu D, Ramesh V, Meer P. Kernel-Based Object Tracking[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-575.
[57] Bradski G.R, Computer Vision Face Tracking for Use in a Perceptual User Interface[J]. IEEE Workshop on Applications of Computer Vision, 1998: 214-219.
[58] Kass M , Witkin A , Terzopoulous D. Snakes : active contour models[J]. Proceedings of the First International Conference on Computer Vision, IEEE Computer Society Press , 1987. 259– 268.
[59] Szeliski R, Terzopoulos D. Physically-Based and probalistic modeling for computer vision[J]. Socity of Photo-Optical Instrumentation Engineers, 1991: 140-152.
[60] Menet S, Saint-Marc P, Medioni G. B-Snakes: Implementation and application to stereo[J]. Proceedings DARPA, 1990: 720-726.
[61] Won K, Choon-Young L, Ju-Jang L. Tracking moving object using Snake's jump based on image flow[J]. Mechatronics, 2001: 119-216.
[62] Vieren C, Cabestaing F, Postaire J. Catching moving objects with snakes for motion tracking[J]. Pattern Recognition Letters, 1995, 16(7): 679-685. [ 63 ] Osher S, Sethian J A. Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988, 79(1): 12-49.
[64] N. Paragios, R. Deriche. Geodesic Active Regions: A new framework to deal with frame partition problems in computer vision[J]. Journal of Visual Communication and Image Representation, 2002: 249-268.
[65] Mansouri A R, Konrad J. Multiple motion segmentation with level sets[J]. IEEE Transactions on Image Processing, 2003. 12(2): 201-220.
[66] Freedman D, Zhang Tao. Active contours for tracking distributions[J]. IEEE Transactions on Image Processing, 2004, 13(4): 518-526.
[67] Cover T M, Hart P E. Nearest neighbor pattern classification[J]. IEEE Trans Inform Theory, 1967, 13: 57-67.
[68] D Reid. An algorithm for tracking multiple target[J]. IEEE Trans on Automat and Contr, 1979, 24(6): 84-90.
[69] Samuel Blackman, Robert Popoli. Design and analysis of modern tracking systems[M]. Boston:Artech House, 1999.
[70]项新建.基于模糊数学与统计理论集成的多传感器数据融合方法[J].传感技术学报,2004,6(2): 197-199.
[71] A. Esmin, G. Lambert-Torres, A.Z. de Souza. A hybrid particle optimization applied to loss power minimization[J]. IEEE Transactions on Power Systems, 2005, 20(2): 859-866.
[72]康莉,谢维信,黄敬雄.一种基于蚁群算法的多目标跟踪数据关联方法[J].电子学报, 2008, 36(3): 586-589.
[73] Zadeh L A.The concept of a linguisticvariable and its applications to approximate reasoning[J]. Information Science, 1974, 8: 199-249.
[74] Comaniciu D,Ramesh V,Meer P. Realtime tracking of non rigid objects using Mean Shift. IEEE Computer vision and Pattern recognition, 2000(2): 1422-1429.
[75] Comaniciu D,Meer P. Mean Shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.
[76] Harrington S. Computer graphics, a programming approach. New York: McGraw Hill Company, 1987: 376-388.
[77] Hongxia Chu, Shujiang Ye, Qingchang Guo, Xia Liu. Object Tracking Algorithm based on Camshift algorithm combinating with difference in frame.In: Proceedings of IEEE International Conference on Automation and Logistics, 2007: 51-55.
[78] Zhu Minhan, Luo Dayong. Moving objects detection and tracking based on two consecutive frames subtraction background model, Computer measurement and control, 2006, 14(8): 1004-1006.
[79] J.Gautrais, S.Motsch, C.Jost, M.Soria, A.Campo, R.Fournier, S.Bianco and G.Theraulaz,Analyzing fish movement as a persistent turning walker, in preparation.
[80] I.Aoki, A simulation study on the schooling mechanism in fish, Bulletin of the Japan Society of Scientific Fisheries, 48 (1982), pp. 1081–1088.
[81] P.Degond, S.Motsch, Large-scale dynamics of the Persistent Turning Walker model of fish behavior, preprint
[82] P.Degond and S.Motsch, Continuum limit of self-driven particles with orientation interaction, preprint
[83] P.Degond and S.Motsch, Macroscopic limit of self-driven particles with orientation interaction, note, to be published.
[2]韩吉,薛国东.水污染及水污染的生物治理[J].吉林水利, 2008, 1(308): 44-46.
[3]德永健.近年我国重大水污染事件[J].中国人大, 2007, 07(17): 27.
[4]刘晓茹,李贵宝,孙天华.水质监测的自动化、网络化发展[J].第八届海峡两岸水利科技交流研讨会, 2004, 12.
[5] HJ/T96-104-2003,中华人民共和国环境保护行业标准.北京:中国环境科学出版社, 2003.
[6]李志良.鱼类行为学在水质在线监测与预警中的应用研究[D].山东师范大学, 2008, 04.
[7]刘伟成,单乐州,谢起浪,林少珍.生物监测在水环境污染监测中的应用[J].环境与健康, 2008, 25(5): 456-458.
[8]刘小卫,陆光华.主动生物监测技术在水环境风险评价中的应用[J].环境监测管理与技术, 2008, 20(3): 12-15.
[9]谢建春.水体污染与水生动物[J].生物学通报, 2001, 36(6): 10~11.
[10]王海洲,刘文华,侯福林.在线生物监测技术及其应用研究[J].生物学通报, 2007, 42(1): 15~16.
[11]李俊文.辽河水质监测与分析[J].地下水, 2008, 30(1): 61~64.
[12]马文漪,杨柳燕.环境微生物工程[M].南京:南京大学出版社, 1998.
[13]凯思斯著,曹凤中译.水污染的生物监测[M].北京:中国环境科学出版社, 1989.
[14]许木启,曹宏,王玉龙.原生动物群落多样性变化与汉沽稳定塘水质净化效能相互关系的研究[J].生态学报, 2002, 20(2): 283~287.
[15] Kumaran R., Bengt D. Principles and applications of thermal biosensors[J]. Biosensors & Bioelectronics, 2001, 16: 417~423.
[16] Manju G., Asha C., Malhotra B. Application of conducting polymers to biosensors[J]. Biosensors & Bioelectronics, 2002, 17: 345~359.
[17]郑怀礼,龚迎昆.用于环境监测的生物传感技术[J].光谱学与光谱分析, 2003, 23(2): 411~414.
[18]王玉华,赵学民,周怀东.水质自动监测技术及其应用分析[J].水文, 2004, 24(3): 54~56.
[19]林志芬,于红霞,许士奋,王连生.发光菌生物毒性测试方法的改进[J].环境科学, 2001, 02.
[20]童中华,廖军.利用淡水发光菌评估电化学处理模拟印染废水的效果[J].环境安全, 1997, 16(2).
[21]高继军,张力平,马梅.应用淡水发光菌研究二元重金属混合物的联合毒性[J].上海环境科学, 2003, 22(11).
[22]严珍,陈曦,李伟,王小如.海洋环境水质监测的发光菌生物传感器研制[A].中国化学会第七届分析化学年会暨原子光谱学术会议论文集[C],广西:广西师范大学, 2000.
[23]张凤民,胡炜.十三种硝基苯类化合物对大型蚤急性毒性的实验[J].黑龙江环境通报, 1998.
[24]黄国兰,孙红文.邻苯二甲酸二丁酯对大型蚤的毒性作用研究[J].环境化学, 1998, 17(5).
[25]吴永贵,黄建国,袁玲.利用水溞的趋光行为监测水质[J].中国环境科学, 2004.
[26]孙红文,黄国兰.偶氮染料对斜生栅藻的毒性作用及结构活性相关性研究[J].环境科学, 1998, 19(4).
[27]康瑞娟,施定基.用于微藻培养的气升式光生物反应器[J].化学反应工程与工艺, 2001.
[28]陈德辉,章宗涉.藻类批量培养中的比增长率最大值[J].水生生物学报, 1998.
[29]王春风,方展强.汞和硒对剑尾鱼的急性毒性及其安全浓度评价[J].环境科学与技术, 2005.
[30]汤一平,尤思思,叶永杰,金顺敬.基于机器视觉的生物式水质监测仪的开发[J].工业控制计算机, 2006, 19(6): 64-66.
[31]霍传林,王菊英.鱼体内EROD活性对多氯联苯类的指示作用[J].海洋环境科学, 2002, 21(1).
[32] S. Dasiopoulou, V. Mezaris, I. Kompatsiaris, V. K. Papastathis, M. G. Strintzis. Knowledge-assisted semantic video object detection [J]. IEEE Transactions on Circuits ans System for Video Technology, 2005, 15(10): 1210-1224.
[33] A. Mittal, N. Paragios, Motion-based background subtraction using adaptive kernel density estimation[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, 302-309.
[34] A. Bugeau, P. Perez. Detection and segmentation of moving objects in highly dynamic scenes [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007.
[35] G. Zhang, J. Jia, W. Xiong, T.T. Wong, P.A. Heng, H. Bao. Moving object extraction with a hand-held camera[C]. IEEE International Conference on Computer Vision, 2007.
[36] Z. Yin, R. Collins. Belief propagation in a 3d spatio-temproal mrf for moving object detection [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007.
[37] J. J. Gibson. The perception of the visual world. Boston: Houghton Mifflin, 1950.
[38] Hui-Fuang Ng. Automatic thresholding for defect detection[J]. Pattern Recognition Letters,2006, 27: 1644-1649.
[39] Horn B KP,Schunck B G. Determining Optical Flow[J]. Artificial Intelligence, 1981, 17: 185-203.
[40] C. Wren, A. Azarbayejani, T. Darrell, A. Pentland. Pfinder: Real-time tracking of the human body[J]. IEEE Trans. On Patt. Anal. and Machine Intell, 1997, 19(7): 780-785.
[41]孙立光,杨新苗.面向混合交通流的全景图像检测方法研究[A]. 2007第三届中国智能交通年会学术委员会. 2007第三届中国智交通年会论文集[C].东南大学, 2007.
[42]朱明旱,罗大庸.基于帧间差分背景模型的运动物体检测与跟踪[J].计算机测量与控制, 2006, 14(8): 1004-1006.
[43] C. Stauffer, W.E.L. Grimson. Adaptive background mixture models for real-time tracking [C]. Proc IEEE CVPR 1999, 1999, 246-252.
[44] Koivunen T. A noise-insensitive motion detector[J]. IEEE TCE, 1992, 38(3): 168-174
[45] R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D.Duggins, Y.Tsin, D.Tolliver, N. Enomoto, O.Hasegawa, P. Burt, L. Wixson. Asystem for video surveillance and monitoring [R]. 2000.
[46] Y. Kameda, M. Minoh. A human motion estimation method using 3-successive video frames [C]. ICVSM, 1996, 135-140.
[47] Aggarwal J K,Nandhakumar N. On the computation of motion from sequences of images-A review[J]. Proceedings of the IEEE, 1988, 76(8): 917-935.
[48] Coifman B,Beymer D,Mclauchlan P,Malik J. A real-time computer vision sustem for vehicle tracking andtraffic surveillance[J]. Transportation Research Part C, 1998, 6(4): 271-288.
[49] Wang L,Hu W M,Tan T N. A survey of visual analysis of human motion[J]. Chinese Journal of Computers, 2002, 25(3): 225-237.
[50] A. Yilmaz, O.Javed, M.Shah. Object tracking: A survey[J]. ACM Computing Surveys, 2006, 38(4): 13.
[51] R.E. Kalman, A new approach to linear filtering and prediction problems[J]. American Society of Mechanical Engineers, Journal of Basic Engineering, 1960, 82: 35-45.
[52] Bar-Shalom Y, Fortmann T. A new extension of the Kalman filter to nonlinear system[J]. Proceedings of SPIE, 1997, 3068: 182-93.
[53] Salmond D, Gordon N, Smith A. A novel approach to nonlinear/non-Gaussian Bayesian state estimation[J]. IEEE Proceeding on Radar,Sonar and Navigation, 1993, 140(2): 107-113.
[54] Isard M, Blake A. CONDENSATION-Conditional density propagation for visual tracking[J]. International Journal of Computer Vision, 1998, 29(1): 5-28.
[55] Cheng Y. Mean Shift,Mode Seeking and Clustering[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.
[56] Comaniciu D, Ramesh V, Meer P. Kernel-Based Object Tracking[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-575.
[57] Bradski G.R, Computer Vision Face Tracking for Use in a Perceptual User Interface[J]. IEEE Workshop on Applications of Computer Vision, 1998: 214-219.
[58] Kass M , Witkin A , Terzopoulous D. Snakes : active contour models[J]. Proceedings of the First International Conference on Computer Vision, IEEE Computer Society Press , 1987. 259– 268.
[59] Szeliski R, Terzopoulos D. Physically-Based and probalistic modeling for computer vision[J]. Socity of Photo-Optical Instrumentation Engineers, 1991: 140-152.
[60] Menet S, Saint-Marc P, Medioni G. B-Snakes: Implementation and application to stereo[J]. Proceedings DARPA, 1990: 720-726.
[61] Won K, Choon-Young L, Ju-Jang L. Tracking moving object using Snake's jump based on image flow[J]. Mechatronics, 2001: 119-216.
[62] Vieren C, Cabestaing F, Postaire J. Catching moving objects with snakes for motion tracking[J]. Pattern Recognition Letters, 1995, 16(7): 679-685. [ 63 ] Osher S, Sethian J A. Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988, 79(1): 12-49.
[64] N. Paragios, R. Deriche. Geodesic Active Regions: A new framework to deal with frame partition problems in computer vision[J]. Journal of Visual Communication and Image Representation, 2002: 249-268.
[65] Mansouri A R, Konrad J. Multiple motion segmentation with level sets[J]. IEEE Transactions on Image Processing, 2003. 12(2): 201-220.
[66] Freedman D, Zhang Tao. Active contours for tracking distributions[J]. IEEE Transactions on Image Processing, 2004, 13(4): 518-526.
[67] Cover T M, Hart P E. Nearest neighbor pattern classification[J]. IEEE Trans Inform Theory, 1967, 13: 57-67.
[68] D Reid. An algorithm for tracking multiple target[J]. IEEE Trans on Automat and Contr, 1979, 24(6): 84-90.
[69] Samuel Blackman, Robert Popoli. Design and analysis of modern tracking systems[M]. Boston:Artech House, 1999.
[70]项新建.基于模糊数学与统计理论集成的多传感器数据融合方法[J].传感技术学报,2004,6(2): 197-199.
[71] A. Esmin, G. Lambert-Torres, A.Z. de Souza. A hybrid particle optimization applied to loss power minimization[J]. IEEE Transactions on Power Systems, 2005, 20(2): 859-866.
[72]康莉,谢维信,黄敬雄.一种基于蚁群算法的多目标跟踪数据关联方法[J].电子学报, 2008, 36(3): 586-589.
[73] Zadeh L A.The concept of a linguisticvariable and its applications to approximate reasoning[J]. Information Science, 1974, 8: 199-249.
[74] Comaniciu D,Ramesh V,Meer P. Realtime tracking of non rigid objects using Mean Shift. IEEE Computer vision and Pattern recognition, 2000(2): 1422-1429.
[75] Comaniciu D,Meer P. Mean Shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.
[76] Harrington S. Computer graphics, a programming approach. New York: McGraw Hill Company, 1987: 376-388.
[77] Hongxia Chu, Shujiang Ye, Qingchang Guo, Xia Liu. Object Tracking Algorithm based on Camshift algorithm combinating with difference in frame.In: Proceedings of IEEE International Conference on Automation and Logistics, 2007: 51-55.
[78] Zhu Minhan, Luo Dayong. Moving objects detection and tracking based on two consecutive frames subtraction background model, Computer measurement and control, 2006, 14(8): 1004-1006.
[79] J.Gautrais, S.Motsch, C.Jost, M.Soria, A.Campo, R.Fournier, S.Bianco and G.Theraulaz,Analyzing fish movement as a persistent turning walker, in preparation.
[80] I.Aoki, A simulation study on the schooling mechanism in fish, Bulletin of the Japan Society of Scientific Fisheries, 48 (1982), pp. 1081–1088.
[81] P.Degond, S.Motsch, Large-scale dynamics of the Persistent Turning Walker model of fish behavior, preprint
[82] P.Degond and S.Motsch, Continuum limit of self-driven particles with orientation interaction, preprint
[83] P.Degond and S.Motsch, Macroscopic limit of self-driven particles with orientation interaction, note, to be published.