基于模型的目标提取及其在智能交通中的应用
|
摘要
随着图像处理和模式识别技术以及计算机硬件水平的提高,越来越多的信息是通过对图像或视频的处理和分析来获得的。在智能交通系统中两个非常重要的信息——交通工具标识码以及道路交通信息就可以通过对图像或视频的处理和分析来获得。本论文主要研究了从复杂的背景中提取出静态的交通工具标识码以及动态的运动车辆的主要关键技术和算法。
实际中通过摄像机采集到的交通工具图像中往往包含有大量的噪声,因此交通工具标识码往往很难通过简单的处理直接获得。为此,首先提出了一种鲁棒的图像预处理算法。该算法在突出交通工具图像中的文字特征的同时,抑制了图像中的各种噪声,并且最大程度地降低了光照的不均匀对字符提取的影响。在图像预处理过程中,结合了自适应线性滤波以及自适应非线性滤波各自的特点,使得预处理后的图像通过简单的投影直方图分析即可得到较好的定位结果。然后根据实际中的交通工具标识码中各字符间的相互位置和排列关系,提出了一系列的标准字符排列模型。最后计算定位得到的各备选字符行中各字符之间的排列关系,将所有备选字符行字符的排列关系依原始位置进行组合后,再与标准排列模型进行匹配即可得到标识码的自动分割结果。基于排列模型的交通工具标识码自动提取算法可以很好地抵抗图像中其他字符或标识的影响,试验证明具有很高的正确提取率。
对于运动车辆的检测或提取,一种广泛采用的方法是背景减法。背景减法进行运动目标检测的关键技术之一是背景的建模方法。一种好的背景建模方法得到的背景模型应能准确地反映真实背景的变化。本论文中提出了两种有效的背景建模方法:基于判决反馈的背景建模方法和基于近似中值滤波的背景建模方法。基于判决反馈的背景建模方法根据背景减法后象素属于前景或背景的判决结果来进行背景的更新,只有那些被判为背景的当前点才参与当前背景的更新中。通过这种方法,可以很好地消除运动目标在背景更新过程中造成的“拖尾”效应。基于近似中值滤波的背景建模方法克服了传统中值滤波运算量大和对内存需求高的缺点,采用近似方法迭代得到图像序列的中间值,并以其作为背景的估计。考虑到利用图像的颜色信息能够更加准确地进行运动目标的检测,论文中还使用了一种运算简单的颜色空间模型——rgs颜色空间模型。试验结果表明,基于颜色信息的判决反馈法背景建模以及基于颜色信息的近似中值滤波法背景建模均能取得很好的背景模型,同时基于颜色信息的运动目标检测能够有效消除运动车辆的阴影对车辆检测的影响。
在论文的最后,讨论了运动车辆检测在整个交通信息采集系统中的作用,并
With the development of science and technology, more and more information are obtained through the processing and analysis of images and videos. The vehicle Identity code information and the traffic information in the urban road, which are the two important kinds of information in intelligent transportation systems, can also be obtained through the analysis of image sequences. The main focus of this dissertation is on the key problems and their solutions for automatic extraction of static and motive objects, especially the vehicle Identity code in an image and motive vehicles in a traffic scene, in sophisticated backgrounds.With different kinds of noises on the image, the vehicle Identity code can hardly be extracted. Initially, the vehicle image is filtered with both adaptive linear and nonlinear filters in order to reduce noises so that the candidate text lines can be properly located. Then, a series of standard align templates has been brought forward according to the standard align modes of the vehicle identity (ID) codes. Finally, the align mode of each candidate text line is obtained and then matched with those standard templates, and the vehicle ID codes can be extracted automatically. Through this method, other characters or marks in the vehicle image can be automatically abandoned and have no influence on the extraction of the ID codes.Background subtraction method is the widely used method to detect motive objects. The key technique to background subtraction is background modeling. A good background model can reflect the true background and can change from time to time according to the real scene. Two kinds of effective background modeling methods are proposed in this dissertation. One is iterative decision-based background modeling and the other is approximated median filter based background modeling. In the first method, the decision of whether a current pixel is a background pixel or a foreground pixel is first made, then only those background pixels are used for the updating of the new background. By doing this, the pixels which belong to a motive object will not be blended to the new background, resulting in a more accurate background model. In the second method, median value of a pixel histogram is used for the estimation of the background. To obtain the median value of a pixel histogram, we need to save the last few frames of the image sequences and sort them in order, which consumes both time and memory spaces. So in the second method, we use some iterative techniques to obtain the median value approximately. By using this method, both the time complexity and space complexity are small, and the obtained background model is relatively good. In order to obtain a more accurate detection result, color information is also applied in the background modeling. A color space called "rgs" color space is used here for its simplicity of conversion with RGB color space. When color information is utilized in the two background modeling methods, they can detect the motive vehicles effectively and efficiently. Another advantage of using color information is that it can help to eliminate the influence of the vehicle shadows.At the end of the dissertation, the role of motive vehicle detection in the traffic
information gathering system is stated. In order to build a real-time system with high efficiency, several optimization techniques are proposed for an embedded DSP system, which is used for gathering the traffic information.Experiment results show that the proposed methods have good performance.
实际中通过摄像机采集到的交通工具图像中往往包含有大量的噪声,因此交通工具标识码往往很难通过简单的处理直接获得。为此,首先提出了一种鲁棒的图像预处理算法。该算法在突出交通工具图像中的文字特征的同时,抑制了图像中的各种噪声,并且最大程度地降低了光照的不均匀对字符提取的影响。在图像预处理过程中,结合了自适应线性滤波以及自适应非线性滤波各自的特点,使得预处理后的图像通过简单的投影直方图分析即可得到较好的定位结果。然后根据实际中的交通工具标识码中各字符间的相互位置和排列关系,提出了一系列的标准字符排列模型。最后计算定位得到的各备选字符行中各字符之间的排列关系,将所有备选字符行字符的排列关系依原始位置进行组合后,再与标准排列模型进行匹配即可得到标识码的自动分割结果。基于排列模型的交通工具标识码自动提取算法可以很好地抵抗图像中其他字符或标识的影响,试验证明具有很高的正确提取率。
对于运动车辆的检测或提取,一种广泛采用的方法是背景减法。背景减法进行运动目标检测的关键技术之一是背景的建模方法。一种好的背景建模方法得到的背景模型应能准确地反映真实背景的变化。本论文中提出了两种有效的背景建模方法:基于判决反馈的背景建模方法和基于近似中值滤波的背景建模方法。基于判决反馈的背景建模方法根据背景减法后象素属于前景或背景的判决结果来进行背景的更新,只有那些被判为背景的当前点才参与当前背景的更新中。通过这种方法,可以很好地消除运动目标在背景更新过程中造成的“拖尾”效应。基于近似中值滤波的背景建模方法克服了传统中值滤波运算量大和对内存需求高的缺点,采用近似方法迭代得到图像序列的中间值,并以其作为背景的估计。考虑到利用图像的颜色信息能够更加准确地进行运动目标的检测,论文中还使用了一种运算简单的颜色空间模型——rgs颜色空间模型。试验结果表明,基于颜色信息的判决反馈法背景建模以及基于颜色信息的近似中值滤波法背景建模均能取得很好的背景模型,同时基于颜色信息的运动目标检测能够有效消除运动车辆的阴影对车辆检测的影响。
在论文的最后,讨论了运动车辆检测在整个交通信息采集系统中的作用,并
With the development of science and technology, more and more information are obtained through the processing and analysis of images and videos. The vehicle Identity code information and the traffic information in the urban road, which are the two important kinds of information in intelligent transportation systems, can also be obtained through the analysis of image sequences. The main focus of this dissertation is on the key problems and their solutions for automatic extraction of static and motive objects, especially the vehicle Identity code in an image and motive vehicles in a traffic scene, in sophisticated backgrounds.With different kinds of noises on the image, the vehicle Identity code can hardly be extracted. Initially, the vehicle image is filtered with both adaptive linear and nonlinear filters in order to reduce noises so that the candidate text lines can be properly located. Then, a series of standard align templates has been brought forward according to the standard align modes of the vehicle identity (ID) codes. Finally, the align mode of each candidate text line is obtained and then matched with those standard templates, and the vehicle ID codes can be extracted automatically. Through this method, other characters or marks in the vehicle image can be automatically abandoned and have no influence on the extraction of the ID codes.Background subtraction method is the widely used method to detect motive objects. The key technique to background subtraction is background modeling. A good background model can reflect the true background and can change from time to time according to the real scene. Two kinds of effective background modeling methods are proposed in this dissertation. One is iterative decision-based background modeling and the other is approximated median filter based background modeling. In the first method, the decision of whether a current pixel is a background pixel or a foreground pixel is first made, then only those background pixels are used for the updating of the new background. By doing this, the pixels which belong to a motive object will not be blended to the new background, resulting in a more accurate background model. In the second method, median value of a pixel histogram is used for the estimation of the background. To obtain the median value of a pixel histogram, we need to save the last few frames of the image sequences and sort them in order, which consumes both time and memory spaces. So in the second method, we use some iterative techniques to obtain the median value approximately. By using this method, both the time complexity and space complexity are small, and the obtained background model is relatively good. In order to obtain a more accurate detection result, color information is also applied in the background modeling. A color space called "rgs" color space is used here for its simplicity of conversion with RGB color space. When color information is utilized in the two background modeling methods, they can detect the motive vehicles effectively and efficiently. Another advantage of using color information is that it can help to eliminate the influence of the vehicle shadows.At the end of the dissertation, the role of motive vehicle detection in the traffic
information gathering system is stated. In order to build a real-time system with high efficiency, several optimization techniques are proposed for an embedded DSP system, which is used for gathering the traffic information.Experiment results show that the proposed methods have good performance.
引文
[1] Syed, Y.A.;Sarfraz, M., Color edge enhancement based fuzzy segmentation of license plates, Information Visualisation, 2005. Proceedings. Ninth International Conference on, 6-8 July 2005 Page(s):227-232
[2] Yungang Zhang;Changshui Zhang, A new algorithm for character segmentation of license plate, Intelligent Vehicles Symposium, 2003. Proceedings. IEEE, 9-11 June 2003 Page(s):106-109
[3] T. Sirithinaphong and K. Chamnongthai, The recognition of car license plate for automatic parking system, in Proc. 5th Int. Symp. Signal Processing and its Applications, 1998, pp. 455-457.
[4] N. H. C. Yung, K. H. Au, and A. H. S. Lai, Recognition of vehicle registration mark on moving vehicles in an outdoor environment, IEEE International conference on Intelligent Transportation Systems, 1999, pp. 418-422.
[5] S. Draghici, A neural network based artificial vision system for license plate recognition system, International Journal for Neural Systems, Vol. 8, pages 112-113, February 1997.
[6] R. A. Lotufo, A. D. Morgan, andA. S. Johnson, "Automatic number plate recognition," Inst. Elect. Eng. Colloquium on Image Analysis for Transport Applications, pp. 6/1-6/6, 1990.
[7] I. S. Igual, G. A. Garcia, and A. P. Jimenez, "Preprocessing and recognition of characters in container codes," in Proc. 16th Int. Conf. Pattern Recognition, vol. 3, Aug. 2002, pp. 143-146.
[8] K.-W. Wan et al., "An integrated multiple neural network architecture for reading alphanumeric characters in complex scenes," in IEEE Int. Conf. Neutral Networks, vol. 7, 1994, pp. 4384-4389.
[9] M. Goccia, M. Bruzzo, C. Scagliola, and S. Dellepiane, "Recognition of container code characters through gray-level feature extraction and gradient-based classifier optimization," in Proc. 7th Int. Conf. Document Analysis and Recognition, Aug. 2003, pp. 973-977.
[10] 张引,潘云鹤,“彩色汽车图象牌照定位新方法”,中国图象图形学报,Vol.6,No.4Apr.2001,pp.374-377.
[11] 赵雪春,戚飞虎,“基于彩色分割的车牌自动识别技术”,上海交通大学学报,Vol 32,No.10,Oct.1998.pp.4-9.
[12] 刘奕陈学俭蒋治华,“一种利用颜色信息的车牌字符分割新算法”,计算机应用与软件,Vol.22,No.8.Aug.2005,pp.98-100
[13] Mullot, R.;Olivier, C.;Bourdon, J.L.;Courtellemont, P.;Labiche, J.;Lecourtier, Y.;Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON '91., 1991 International Conference on, 28 Oct.-l Nov. 1991 Page(s):1739-1744 vol.3
[14] K.-W. Wan et al., "An integrated multiple neural network architecture for reading alphanumeric characters in complex scenes," in IEEE Int. Conf. Neutral Networks, vol. 7, 1994, pp. 4384-4389.
[15] D.-S. Kim and S.-I. Chien, "Automatic car license plate extraction using modified generalized symmetry transform and image warping," in Proc. IEEE Int. Symp. Industrial Electronics (ISIE'01), vol. 3, June 2001, pp. 2022-2027.
[16] Y. Zhang and C. Zhang, "A new algorithm for character segmentation of license plate," in Proc. IEEE Intelligent Vehicles Symp., June 2003, pp. 106-109.
[17]. Atsushi Saito, Masatoshi Kinachi, Shiro Ogata: Silhouette Vision: New Video Vehicle Detection Field Proven Robust and Accurate Proceeding of 6th World Congress on Intelligent Transport Systems, Toronto.Canada.
[18]. A.Bensrhair, M.Bertozzi, A.Broggi, P.Miche, S.Mousset, and GToulminet: A Cooperative Approach to Visionbased Vehicle Detection IEEE Intelligent Transportation Systems Conference Proceeding, Oakland (CA) USA August 25-29 2001 Page 207-212.
[19]. D. Kollery, K. Daniilidisy and H.-H. Nagelyz Institut fur Algorithmen und Kognitive Systeme Fakultat fur Informatik der Universitat Karlsruhe (TH) etc, Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes INTERNATIONAL JOURNAL OF COMPUTER VISION 10:3(1993)257-281.
[20] C.Setchell ,E.L.Dagless, Vision -Based road traffic monitoring sensor, IEE 2001, IEE proceedings online. 78-84.
[21] C. Wren, A. Azabayejani, T. Darrel, and A. Pentland, P_finder: Real-time tracking of the human body," IEEE Transactions on Pattern Analysis and Machine Intelligence 19, pp. 780-785, July 1997.
[22] J. Heikkila and O. Silven, A real-time system for monitoring of cyclists and pedestrians," in Second IEEE Workshop on Visual Surveillance, pp. 246{252, (Fort Collins, Colorado), Jun 1999.
[23]. G. Halevy and D. Weinshall, \Motion of disturbances: detection and tracking of multi-body non-rigid motion,"Maching Vision and Applications 11, pp. 122-137, 1999.
[24].T. Boult et al., Frame-rate omnidirectional surveillance and tracking of camuaged and occluded targets," in Proceedings Second IEEE Workshop on Visual Surveillance, pp. 48-55, (Fort Collins, CO), June 1999.
[25] Image Processing and Moving Object Recognition, V. Cappellini, ed., 2, pp. 289-307, Elsevier Science Publishers B.V.,1990.
[26] D. Koller, J. Weber, and J. Malik, \Robust multiple car tracking with occlusion reasoning," Tech. Rep. UCB/CSD-93-780, EECS Department, University of California, Berkeley, Oct 1993.
[27] K. Toyama, J. Krumm, B. Brumitt and B. Meyers: Wallower: Principles and practice of background maintenance in: International Conference on Computer Vision (1999) pp. 255-261.
[28] Y. Ivanov, C. Stau_er, A. Bobick and W. E. L. Grimson: Video surveillance of interactions in: Second IEEE Workshop on Visual Surveillance Fort Collins, Colorado (Jun. 1999) pp. 82-90.
[29] C. Stauer and W. E. L. Grimson: Adaptive background mixture models for real-time tracking in: Computer Vision and Pattem Recognition Fort Collins, Colorado (Jun. 1999) pp. 246-252.
[30] N. M. Oliver, B. Rosario, and A. P. Pentland, "A Bayesian Computer Vision System for Modeling Human Interactions," IEEE Trans. on Patt. Anal. and Machine Intell., vol. 22, no. 8, pp. 831-843, 2000.
[31] 沈定刚,李艳斌,戚飞虎。汽车牌照自动定位算法。无线电通信技术,1995,21[5]: p35—38。
[32] 王少杰,朱志刚。货运列车车型车号自动分割和识别算法。模式识别与人工智能,1998, 11[3]:p319—334。
[33] 林纯青等。汽车图像中字符目标的提取算法。上海交通大学学报,1998,32(10):1—4。
[34] J Barroso, E L Dagless. Number Plate Reading Using Computer Vision. Proceedings of the IEEE International Symposium on Industrial Electronics, 1997, p761—766.
[35] Joe C. H. Poon, et al. A Robust vision system for vehicle licence plate recognition using grey-scale morphology. Proceedings of the IEEE International Symposium on Industrial Electronics, 1995, p394—399.
[36] Parisi R, et al. Car Plate Recognition By Neural Networks And Image Processing. Proceedings of the IEEE International Symposium on Circuits and Systems, 1998, p195—198.
[37] Richard G. Casey, Eric Lecolinet. A Survey of Methods and Strategies in Character Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence.Vol 18,No 7, 1996, p690-706.
[38] Mei Yu, Yong Deak Kim. An approach to korean license plate recognition based on vertical edge matching。 IEEE International Conference on Systems, Man, and Cybernetics. 2000, p2975—2980。
[39] 丁莉雅,基于视频处理的交通信息采集,浙江大学硕士学位论文,2003。
[40] Rafaei C. Gonzalez, Richard E. Woods, Digital Image Processing, Prentice Hall.
[41] 郑南宁,计算机视觉与模式识别,国防工业出版社,1998-3
[42] Osama Masoud and Nikolaos P. Papanikolopoulos, Senior Member, IEEE A Novel Method for Tracking and Counting Pedestrians in Real-Time Using a Single Camera IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 50, NO. 5, SEPTEMBER 2001 1267
[43] R.M.Haralick, S.R.Steraberg, X.Zhuang. Image Anlysis Using Mathematical Morphology. IEEE Transaction on Pattern Analysis and Machine Intelligent, Vol. 2529, No.4, July 1987.
[44] 李立源,陈维南.一种强鲁棒的完全确定型的快速阈值化方法.PR&AI.Vol.6. No.3,Sep.1993.
[45] AHMED ELGAMMAL, RAMANI DURAISWAMI,etc, Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance, PROCEEDINGS OF THE IEEE, VOL. 90, NO. 7, JULY 2002, pp. 1151-1163
[46] Yaser Sheikhand Mubarak Shah, Bayesian Modeling of Dynamic Scenes for Object Detection, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 11, NOVEMBER 2005, pp. 1778-1792
[47] A. Elgammal, R. Duraiswami, and L. S. Davis, "Efficient computation of kernel density estimation using fast gauss transform with applications for segmentation and tracking," Proc. IEEE 2nd Int.Workshop Statistical and Computational Theories of Vision, July 2001.
[48] C. Lambert, S. Harrington, C. Harvey, and A. Glodjo, "Efficient on-line nonparametric kernel density estimation," Algorithmica, no. 25, pp. 37-57, 1999.
[49] Chow C K, Kaneko T.Automatic Boundary Detection of the Left Ventricle from Cineangiograms. Comput. Biomed. Res, 5, 388-410, 1972.
[50] T.Pun. Entropic Thresholding, A New Approach. CGIP Vol.16, p210-239, 1981.
[51] Coetzee C, et al. PC Based Number Plate Recognition Systems. Proceedings of the IEEE International Symposium on Industrial Electronics, 1998, p605～610.
[52] S. U. Lee and S. Y. Chung, "A comparative performance study of several global thresholding techniques for segmentation," Comput. Vis., Graph., Image Process., vol. 52, pp. 171-190, 1990.
[53] Otsu, "Minimum error thresholding," Pattern Recognit., vol. 19, no. 1, pp. 41-47, 1986.
[54] J. Kittler and J. lllingworth, "On threshold selection using clustering criteria," IEEE Trans. Syst., Man, Cybern., vol. SMC-15, pp. 652-655, Sept/Oct. 1985.
[55] K. Suzuki, I. Horiba, and N. Sugie, "Neural edge enhancer for supervised edge enhancement from noisy images," IEEE Trans. Pattern Anal. Machine Intell., vol. 25, pp. 1582-1596, Dec. 2003.
[56] R Soille, Morphological Image Analysis: Principles and Applications. Berlin, Germany: Spdnger-Verlag, 1999.
[57] Y. Hawwar and A. Reza, "Spatially adaptive multiplicative noise image denoising technique," IEEE Trans. Image Processing, vol. 11, pp. 1397-1404, Dec. 2002.
[58] D. Van De Ville et al., "Noise reduction by fuzzy image filtering," IEEE Trans. Fuzzy Syst., vol. 11, pp. 429-436, Aug. 2003.
[59] E Voci, S. Eiho, N. Sugimoto, and H. Sekibuchi, "Estimating the gradient in the perona-malik equation," IEEE Signal Processing Mag., vol. 21, pp. 39-65, May 2004.
[60] J. W. Tukey, "Nonlinear (nonsuperposable) methods for smoothing data," in Proc. Congr. Rec. Electronics and Aerospace Systems Conv. (EASCON'74), 1974, p. 673.
[61] K.-P. Karmann and A. Brandt, Moving object recognition using an adaptive background memory," in Time-Varying
[62] 贾云得,机器视觉,科学出版社,2000
[63] Fang, M., Chiu, M.-Y., Liang, C.-C., Singh, A., Industrial neural vision system for underground railway station platform surveillance, Intelligent Vehicles '93 Symposium, pp207- 212.1993
[64] 基于视频图像的复杂背景中流动人群数目的识别,铁道学报,2003年10月,Vol.25, pp55-59,2003
[65] 朱茵,陆化普,2004:中国智能交通发展趋势,综合运输,2004年第2期,pp10-15,2004
[66] 王笑京,智能交通与道路交通安全,交通世界,2004年第10期,pp53—55,2004
[67] 贺国光,再谈ITS的几个基本理论问题,交通运输系统工程与信息,2004年第2期, pp17—24,2004
[68] 周少华,智能交通系统的发展与思考,河南科技,2004年第3期,pp40—41,2004
[69] Bainbridge-Smith, A. Lane, R.G, Determining optical flow using a differential method, Image and Vision Computing, 1997 vol.15, pp11—22, 2004
[70] Horn B. K. P., Schunk B. G., Determining Optical Flow, Artificial Intelligence, 1981, vol. 17, pp185—203, 1981
[71] Barron J. L., Thacker N. A., Tutorial: Computing 2D and 3D Optical Flow, Internal Tinamemo, No. 2004-12, ppl—12, 2004
[72] Barron J. L., Fleet D. J., Beauchemin S. S., Burkitt T. A., Performance of Optical Flow Techniques, Int. J. computer Vision, 1994 vol.12, pp44-77, 1994
[73] Ying Wu, Optical Flow and Motion Analysis, ECE510—Computer Vision Notes Series 6, Electrical & Computer Engineering Northwestern University, Evanston, IL
[74] Chiou-Shann Fuh, Petros Maragos, Region-Based Optical Flow Estimation, Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89, IEEE Computer Society Conference on, pp130-135, 1989
[75] Nagel, H.-H., Haag, M., Bias-corrected optical flow estimation for road vehicle tracking, Computer Vision, 1998. Sixth International Conference on, pp 1006—1011, 1998
[76] Cornelia, Shulman, David, Aloimonos, Yiannis, The Statistics of Optical Flow, Computer Vision and Image Understanding, 2001 Vol. 82, ppl—32, 2001
[77] Cucchiara, R., Grana, C., Piccardi, M., Prati, A., Detecting Moving Objects, Ghosts, and Shadows in Video Streams, Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 25, Issue 10, Oct. 2003 pp1337-1342, 2003
[78] N. Friedman and S. Russell, "Image segmentation in video sequences: A probabilistic approach," In Proceedings Thirteenth Conf. on Uncertainty in Arti.cial Intelligence, 1997.
[79] Kato, S. Joga, J. Rittscher, and A. Blake, "An HMM-based segmentation method for traf.c monitoring movies," IEEE Trans. on PAMI, vol. 24, no. 9, pp. 1291-1296, 2002.
[80] M. Harville, "A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models," In Proceedings of ECCV, 2002.
[81] P. J. Withagen, K. Schutte, and F. Groen, "Likelihood-based object tracking using color histograms and EM," In Proceedings ICIP USA, pp. 589-592, 2002.
[82] A. Prati, I. Mikic, M. Trivedi, and R. Cucchiara, "Detecting moving shadows: Formulation, algorithms and evaluation," IEEE Trans. on PAMI. vol. 25, no. 7, pp. 918-924, 2003.
[83] E.Hayman and J. Eklundh, "Statistical Background Subtraction for a Mobile Observer" , In Proceedings ICCV, 2003.
[84] Freight Containers—Coding, Identification, and Marking, 1995. ISO 6346.
[85] R. Guo, S.M. Pandit, Automatic threshold selection based on histogram modes and a discriminant criterion, Machine Vision and Applications, 10 (1998) 331-338.
[86] J. Cai, Z.Q. Liu, A New Thresholding Algorithm Based on All-Pole Model, ICPR'98, Int. Conf. on Pattern Recognition, Australia, 1998, pp:34-36.
[87] D.E. Lloyd, Automatic Target Classification Using Moment Invariant of Image Shapes, Technical Report, RAE IDN AWl26, Farnborough-UK, December 1985.
[88] M.K. Yanni, E. Home, A New Approach to Dynamic Thresholding, EUSIPCO-9: Eurpean Conf. on Signal Processing, Vol. 1, Edinburg, 1994, pp:34-44.
[89] N.B. Venkateswarluh, R.D. Boyle, New segmentation techniques for document image analysis, Image and Vision Computing, 13 (1995) 573-583.
[90] N. Friel, I.S. Molchanov, A new thresholding technique based on random sets, Pattern Recognition, 32 (1999) 1507-1517.
[91] Luc P. Devroye. On the inequality of Cover and Hart in nearest neighbor discrimination.IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-3:75{78, 1981.
[92] James C. Bezdek and Sankar K. Pal, editors. Fuzzy Models for Pattern Recognition: Methods that search for structures in data. IEEE Press, New York, NY, 1992.
[93] Abraham Kandel. Fuzzy Techniques in Pattern Recognition. Wiley, New York, NY, 1982.
[94] E. A. Patrick and F. E Fischer, Ⅲ. A generalized k-nearest neighbor rule.Information and Control, 16:128{152, 1970.
[95] Anil, K.,Jain, Richard, C., Dubes: Algorithms for Clustering Data. Prentice Hall (1988)
[96] Jerome, H.,Friedman, Forest, Baskett, Leonard, J.,Shustek.: An algorithm for finding nearest neighbours. IEEE transactions on Computers C-24 (1975) 1000-1006
[97] Texas Instruments, TMS320C6000 Optimizing Compiler User's Guide. SPRU187I.
[98] Texas Instruments, TMS320C6000 Programmer's Guide. SPRU198.
[99] Texas Instruments, TMS320C6000 Technical Brief, SPRU197D.
[100] Texas Instruments, TMS320C6000 CPU and Instruction Set Reference Guide, SPRU189F.
[101] 崔屹,图像处理与分析——数学形态学方法及应用,科学出版社,2000
[102] David J. Kruglinski, Programming Visual C++, fourth edition, Microsoft Press.
[103] Ding Liya, Liujilin, Intelligent Freight Train ID Recognition System, The IEEE 5th International Conference on Intelligent Transportation Systems, 3-6 September 2002, Singapore
[104] JSJ Li, WH Holmes, Analog implementation of median filter for real-time signal processing, Circuits and Systems, IEEE Transactions on, 1988
[105] Z WANG, D ZHANG, Progressive switching median filter for the removal of impulse noise from highly corrupted images, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS—Ⅱ: ANALOG AND DIGITAL SIGNAL PROCESSING, VOL. 46, NO. 1, JANUARY 1999
[106] NC Gallagher, GL Wise, Theoretical Analysis of the Properties of Median Filters. IEEE TRANS. ACOUST., SPEECH, AND SIGNAL, PROC. 29:66, 1136-1141, 1981
[107] Tao Chen and Hong Ren Wu, Adaptive Impulse Detection Using Center-Weighted Median Filters IEEE SIGNAL PROCESSING LETTERS, VOL. 8, NO. 1, JANUARY 2001
[108] R. Fablet and P. Bouthemy, Motion Recognition Using Nonparametric Image Motion Models Estimated from Temporal and Multiscale Co-Occurrence Statistics, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 12, DECEMBER 2003, pp.1619-1624.
[109] 刘智勇,智能交通控制理论及其应用,科学出版社,2003
[2] Yungang Zhang;Changshui Zhang, A new algorithm for character segmentation of license plate, Intelligent Vehicles Symposium, 2003. Proceedings. IEEE, 9-11 June 2003 Page(s):106-109
[3] T. Sirithinaphong and K. Chamnongthai, The recognition of car license plate for automatic parking system, in Proc. 5th Int. Symp. Signal Processing and its Applications, 1998, pp. 455-457.
[4] N. H. C. Yung, K. H. Au, and A. H. S. Lai, Recognition of vehicle registration mark on moving vehicles in an outdoor environment, IEEE International conference on Intelligent Transportation Systems, 1999, pp. 418-422.
[5] S. Draghici, A neural network based artificial vision system for license plate recognition system, International Journal for Neural Systems, Vol. 8, pages 112-113, February 1997.
[6] R. A. Lotufo, A. D. Morgan, andA. S. Johnson, "Automatic number plate recognition," Inst. Elect. Eng. Colloquium on Image Analysis for Transport Applications, pp. 6/1-6/6, 1990.
[7] I. S. Igual, G. A. Garcia, and A. P. Jimenez, "Preprocessing and recognition of characters in container codes," in Proc. 16th Int. Conf. Pattern Recognition, vol. 3, Aug. 2002, pp. 143-146.
[8] K.-W. Wan et al., "An integrated multiple neural network architecture for reading alphanumeric characters in complex scenes," in IEEE Int. Conf. Neutral Networks, vol. 7, 1994, pp. 4384-4389.
[9] M. Goccia, M. Bruzzo, C. Scagliola, and S. Dellepiane, "Recognition of container code characters through gray-level feature extraction and gradient-based classifier optimization," in Proc. 7th Int. Conf. Document Analysis and Recognition, Aug. 2003, pp. 973-977.
[10] 张引,潘云鹤,“彩色汽车图象牌照定位新方法”,中国图象图形学报,Vol.6,No.4Apr.2001,pp.374-377.
[11] 赵雪春,戚飞虎,“基于彩色分割的车牌自动识别技术”,上海交通大学学报,Vol 32,No.10,Oct.1998.pp.4-9.
[12] 刘奕陈学俭蒋治华,“一种利用颜色信息的车牌字符分割新算法”,计算机应用与软件,Vol.22,No.8.Aug.2005,pp.98-100
[13] Mullot, R.;Olivier, C.;Bourdon, J.L.;Courtellemont, P.;Labiche, J.;Lecourtier, Y.;Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON '91., 1991 International Conference on, 28 Oct.-l Nov. 1991 Page(s):1739-1744 vol.3
[14] K.-W. Wan et al., "An integrated multiple neural network architecture for reading alphanumeric characters in complex scenes," in IEEE Int. Conf. Neutral Networks, vol. 7, 1994, pp. 4384-4389.
[15] D.-S. Kim and S.-I. Chien, "Automatic car license plate extraction using modified generalized symmetry transform and image warping," in Proc. IEEE Int. Symp. Industrial Electronics (ISIE'01), vol. 3, June 2001, pp. 2022-2027.
[16] Y. Zhang and C. Zhang, "A new algorithm for character segmentation of license plate," in Proc. IEEE Intelligent Vehicles Symp., June 2003, pp. 106-109.
[17]. Atsushi Saito, Masatoshi Kinachi, Shiro Ogata: Silhouette Vision: New Video Vehicle Detection Field Proven Robust and Accurate Proceeding of 6th World Congress on Intelligent Transport Systems, Toronto.Canada.
[18]. A.Bensrhair, M.Bertozzi, A.Broggi, P.Miche, S.Mousset, and GToulminet: A Cooperative Approach to Visionbased Vehicle Detection IEEE Intelligent Transportation Systems Conference Proceeding, Oakland (CA) USA August 25-29 2001 Page 207-212.
[19]. D. Kollery, K. Daniilidisy and H.-H. Nagelyz Institut fur Algorithmen und Kognitive Systeme Fakultat fur Informatik der Universitat Karlsruhe (TH) etc, Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes INTERNATIONAL JOURNAL OF COMPUTER VISION 10:3(1993)257-281.
[20] C.Setchell ,E.L.Dagless, Vision -Based road traffic monitoring sensor, IEE 2001, IEE proceedings online. 78-84.
[21] C. Wren, A. Azabayejani, T. Darrel, and A. Pentland, P_finder: Real-time tracking of the human body," IEEE Transactions on Pattern Analysis and Machine Intelligence 19, pp. 780-785, July 1997.
[22] J. Heikkila and O. Silven, A real-time system for monitoring of cyclists and pedestrians," in Second IEEE Workshop on Visual Surveillance, pp. 246{252, (Fort Collins, Colorado), Jun 1999.
[23]. G. Halevy and D. Weinshall, \Motion of disturbances: detection and tracking of multi-body non-rigid motion,"Maching Vision and Applications 11, pp. 122-137, 1999.
[24].T. Boult et al., Frame-rate omnidirectional surveillance and tracking of camuaged and occluded targets," in Proceedings Second IEEE Workshop on Visual Surveillance, pp. 48-55, (Fort Collins, CO), June 1999.
[25] Image Processing and Moving Object Recognition, V. Cappellini, ed., 2, pp. 289-307, Elsevier Science Publishers B.V.,1990.
[26] D. Koller, J. Weber, and J. Malik, \Robust multiple car tracking with occlusion reasoning," Tech. Rep. UCB/CSD-93-780, EECS Department, University of California, Berkeley, Oct 1993.
[27] K. Toyama, J. Krumm, B. Brumitt and B. Meyers: Wallower: Principles and practice of background maintenance in: International Conference on Computer Vision (1999) pp. 255-261.
[28] Y. Ivanov, C. Stau_er, A. Bobick and W. E. L. Grimson: Video surveillance of interactions in: Second IEEE Workshop on Visual Surveillance Fort Collins, Colorado (Jun. 1999) pp. 82-90.
[29] C. Stauer and W. E. L. Grimson: Adaptive background mixture models for real-time tracking in: Computer Vision and Pattem Recognition Fort Collins, Colorado (Jun. 1999) pp. 246-252.
[30] N. M. Oliver, B. Rosario, and A. P. Pentland, "A Bayesian Computer Vision System for Modeling Human Interactions," IEEE Trans. on Patt. Anal. and Machine Intell., vol. 22, no. 8, pp. 831-843, 2000.
[31] 沈定刚,李艳斌,戚飞虎。汽车牌照自动定位算法。无线电通信技术,1995,21[5]: p35—38。
[32] 王少杰,朱志刚。货运列车车型车号自动分割和识别算法。模式识别与人工智能,1998, 11[3]:p319—334。
[33] 林纯青等。汽车图像中字符目标的提取算法。上海交通大学学报,1998,32(10):1—4。
[34] J Barroso, E L Dagless. Number Plate Reading Using Computer Vision. Proceedings of the IEEE International Symposium on Industrial Electronics, 1997, p761—766.
[35] Joe C. H. Poon, et al. A Robust vision system for vehicle licence plate recognition using grey-scale morphology. Proceedings of the IEEE International Symposium on Industrial Electronics, 1995, p394—399.
[36] Parisi R, et al. Car Plate Recognition By Neural Networks And Image Processing. Proceedings of the IEEE International Symposium on Circuits and Systems, 1998, p195—198.
[37] Richard G. Casey, Eric Lecolinet. A Survey of Methods and Strategies in Character Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence.Vol 18,No 7, 1996, p690-706.
[38] Mei Yu, Yong Deak Kim. An approach to korean license plate recognition based on vertical edge matching。 IEEE International Conference on Systems, Man, and Cybernetics. 2000, p2975—2980。
[39] 丁莉雅,基于视频处理的交通信息采集,浙江大学硕士学位论文,2003。
[40] Rafaei C. Gonzalez, Richard E. Woods, Digital Image Processing, Prentice Hall.
[41] 郑南宁,计算机视觉与模式识别,国防工业出版社,1998-3
[42] Osama Masoud and Nikolaos P. Papanikolopoulos, Senior Member, IEEE A Novel Method for Tracking and Counting Pedestrians in Real-Time Using a Single Camera IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 50, NO. 5, SEPTEMBER 2001 1267
[43] R.M.Haralick, S.R.Steraberg, X.Zhuang. Image Anlysis Using Mathematical Morphology. IEEE Transaction on Pattern Analysis and Machine Intelligent, Vol. 2529, No.4, July 1987.
[44] 李立源,陈维南.一种强鲁棒的完全确定型的快速阈值化方法.PR&AI.Vol.6. No.3,Sep.1993.
[45] AHMED ELGAMMAL, RAMANI DURAISWAMI,etc, Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance, PROCEEDINGS OF THE IEEE, VOL. 90, NO. 7, JULY 2002, pp. 1151-1163
[46] Yaser Sheikhand Mubarak Shah, Bayesian Modeling of Dynamic Scenes for Object Detection, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 11, NOVEMBER 2005, pp. 1778-1792
[47] A. Elgammal, R. Duraiswami, and L. S. Davis, "Efficient computation of kernel density estimation using fast gauss transform with applications for segmentation and tracking," Proc. IEEE 2nd Int.Workshop Statistical and Computational Theories of Vision, July 2001.
[48] C. Lambert, S. Harrington, C. Harvey, and A. Glodjo, "Efficient on-line nonparametric kernel density estimation," Algorithmica, no. 25, pp. 37-57, 1999.
[49] Chow C K, Kaneko T.Automatic Boundary Detection of the Left Ventricle from Cineangiograms. Comput. Biomed. Res, 5, 388-410, 1972.
[50] T.Pun. Entropic Thresholding, A New Approach. CGIP Vol.16, p210-239, 1981.
[51] Coetzee C, et al. PC Based Number Plate Recognition Systems. Proceedings of the IEEE International Symposium on Industrial Electronics, 1998, p605～610.
[52] S. U. Lee and S. Y. Chung, "A comparative performance study of several global thresholding techniques for segmentation," Comput. Vis., Graph., Image Process., vol. 52, pp. 171-190, 1990.
[53] Otsu, "Minimum error thresholding," Pattern Recognit., vol. 19, no. 1, pp. 41-47, 1986.
[54] J. Kittler and J. lllingworth, "On threshold selection using clustering criteria," IEEE Trans. Syst., Man, Cybern., vol. SMC-15, pp. 652-655, Sept/Oct. 1985.
[55] K. Suzuki, I. Horiba, and N. Sugie, "Neural edge enhancer for supervised edge enhancement from noisy images," IEEE Trans. Pattern Anal. Machine Intell., vol. 25, pp. 1582-1596, Dec. 2003.
[56] R Soille, Morphological Image Analysis: Principles and Applications. Berlin, Germany: Spdnger-Verlag, 1999.
[57] Y. Hawwar and A. Reza, "Spatially adaptive multiplicative noise image denoising technique," IEEE Trans. Image Processing, vol. 11, pp. 1397-1404, Dec. 2002.
[58] D. Van De Ville et al., "Noise reduction by fuzzy image filtering," IEEE Trans. Fuzzy Syst., vol. 11, pp. 429-436, Aug. 2003.
[59] E Voci, S. Eiho, N. Sugimoto, and H. Sekibuchi, "Estimating the gradient in the perona-malik equation," IEEE Signal Processing Mag., vol. 21, pp. 39-65, May 2004.
[60] J. W. Tukey, "Nonlinear (nonsuperposable) methods for smoothing data," in Proc. Congr. Rec. Electronics and Aerospace Systems Conv. (EASCON'74), 1974, p. 673.
[61] K.-P. Karmann and A. Brandt, Moving object recognition using an adaptive background memory," in Time-Varying
[62] 贾云得,机器视觉,科学出版社,2000
[63] Fang, M., Chiu, M.-Y., Liang, C.-C., Singh, A., Industrial neural vision system for underground railway station platform surveillance, Intelligent Vehicles '93 Symposium, pp207- 212.1993
[64] 基于视频图像的复杂背景中流动人群数目的识别,铁道学报,2003年10月,Vol.25, pp55-59,2003
[65] 朱茵,陆化普,2004:中国智能交通发展趋势,综合运输,2004年第2期,pp10-15,2004
[66] 王笑京,智能交通与道路交通安全,交通世界,2004年第10期,pp53—55,2004
[67] 贺国光,再谈ITS的几个基本理论问题,交通运输系统工程与信息,2004年第2期, pp17—24,2004
[68] 周少华,智能交通系统的发展与思考,河南科技,2004年第3期,pp40—41,2004
[69] Bainbridge-Smith, A. Lane, R.G, Determining optical flow using a differential method, Image and Vision Computing, 1997 vol.15, pp11—22, 2004
[70] Horn B. K. P., Schunk B. G., Determining Optical Flow, Artificial Intelligence, 1981, vol. 17, pp185—203, 1981
[71] Barron J. L., Thacker N. A., Tutorial: Computing 2D and 3D Optical Flow, Internal Tinamemo, No. 2004-12, ppl—12, 2004
[72] Barron J. L., Fleet D. J., Beauchemin S. S., Burkitt T. A., Performance of Optical Flow Techniques, Int. J. computer Vision, 1994 vol.12, pp44-77, 1994
[73] Ying Wu, Optical Flow and Motion Analysis, ECE510—Computer Vision Notes Series 6, Electrical & Computer Engineering Northwestern University, Evanston, IL
[74] Chiou-Shann Fuh, Petros Maragos, Region-Based Optical Flow Estimation, Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89, IEEE Computer Society Conference on, pp130-135, 1989
[75] Nagel, H.-H., Haag, M., Bias-corrected optical flow estimation for road vehicle tracking, Computer Vision, 1998. Sixth International Conference on, pp 1006—1011, 1998
[76] Cornelia, Shulman, David, Aloimonos, Yiannis, The Statistics of Optical Flow, Computer Vision and Image Understanding, 2001 Vol. 82, ppl—32, 2001
[77] Cucchiara, R., Grana, C., Piccardi, M., Prati, A., Detecting Moving Objects, Ghosts, and Shadows in Video Streams, Pattern Analysis and Machine Intelligence, IEEE Transactions on Volume 25, Issue 10, Oct. 2003 pp1337-1342, 2003
[78] N. Friedman and S. Russell, "Image segmentation in video sequences: A probabilistic approach," In Proceedings Thirteenth Conf. on Uncertainty in Arti.cial Intelligence, 1997.
[79] Kato, S. Joga, J. Rittscher, and A. Blake, "An HMM-based segmentation method for traf.c monitoring movies," IEEE Trans. on PAMI, vol. 24, no. 9, pp. 1291-1296, 2002.
[80] M. Harville, "A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models," In Proceedings of ECCV, 2002.
[81] P. J. Withagen, K. Schutte, and F. Groen, "Likelihood-based object tracking using color histograms and EM," In Proceedings ICIP USA, pp. 589-592, 2002.
[82] A. Prati, I. Mikic, M. Trivedi, and R. Cucchiara, "Detecting moving shadows: Formulation, algorithms and evaluation," IEEE Trans. on PAMI. vol. 25, no. 7, pp. 918-924, 2003.
[83] E.Hayman and J. Eklundh, "Statistical Background Subtraction for a Mobile Observer" , In Proceedings ICCV, 2003.
[84] Freight Containers—Coding, Identification, and Marking, 1995. ISO 6346.
[85] R. Guo, S.M. Pandit, Automatic threshold selection based on histogram modes and a discriminant criterion, Machine Vision and Applications, 10 (1998) 331-338.
[86] J. Cai, Z.Q. Liu, A New Thresholding Algorithm Based on All-Pole Model, ICPR'98, Int. Conf. on Pattern Recognition, Australia, 1998, pp:34-36.
[87] D.E. Lloyd, Automatic Target Classification Using Moment Invariant of Image Shapes, Technical Report, RAE IDN AWl26, Farnborough-UK, December 1985.
[88] M.K. Yanni, E. Home, A New Approach to Dynamic Thresholding, EUSIPCO-9: Eurpean Conf. on Signal Processing, Vol. 1, Edinburg, 1994, pp:34-44.
[89] N.B. Venkateswarluh, R.D. Boyle, New segmentation techniques for document image analysis, Image and Vision Computing, 13 (1995) 573-583.
[90] N. Friel, I.S. Molchanov, A new thresholding technique based on random sets, Pattern Recognition, 32 (1999) 1507-1517.
[91] Luc P. Devroye. On the inequality of Cover and Hart in nearest neighbor discrimination.IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-3:75{78, 1981.
[92] James C. Bezdek and Sankar K. Pal, editors. Fuzzy Models for Pattern Recognition: Methods that search for structures in data. IEEE Press, New York, NY, 1992.
[93] Abraham Kandel. Fuzzy Techniques in Pattern Recognition. Wiley, New York, NY, 1982.
[94] E. A. Patrick and F. E Fischer, Ⅲ. A generalized k-nearest neighbor rule.Information and Control, 16:128{152, 1970.
[95] Anil, K.,Jain, Richard, C., Dubes: Algorithms for Clustering Data. Prentice Hall (1988)
[96] Jerome, H.,Friedman, Forest, Baskett, Leonard, J.,Shustek.: An algorithm for finding nearest neighbours. IEEE transactions on Computers C-24 (1975) 1000-1006
[97] Texas Instruments, TMS320C6000 Optimizing Compiler User's Guide. SPRU187I.
[98] Texas Instruments, TMS320C6000 Programmer's Guide. SPRU198.
[99] Texas Instruments, TMS320C6000 Technical Brief, SPRU197D.
[100] Texas Instruments, TMS320C6000 CPU and Instruction Set Reference Guide, SPRU189F.
[101] 崔屹,图像处理与分析——数学形态学方法及应用,科学出版社,2000
[102] David J. Kruglinski, Programming Visual C++, fourth edition, Microsoft Press.
[103] Ding Liya, Liujilin, Intelligent Freight Train ID Recognition System, The IEEE 5th International Conference on Intelligent Transportation Systems, 3-6 September 2002, Singapore
[104] JSJ Li, WH Holmes, Analog implementation of median filter for real-time signal processing, Circuits and Systems, IEEE Transactions on, 1988
[105] Z WANG, D ZHANG, Progressive switching median filter for the removal of impulse noise from highly corrupted images, IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS—Ⅱ: ANALOG AND DIGITAL SIGNAL PROCESSING, VOL. 46, NO. 1, JANUARY 1999
[106] NC Gallagher, GL Wise, Theoretical Analysis of the Properties of Median Filters. IEEE TRANS. ACOUST., SPEECH, AND SIGNAL, PROC. 29:66, 1136-1141, 1981
[107] Tao Chen and Hong Ren Wu, Adaptive Impulse Detection Using Center-Weighted Median Filters IEEE SIGNAL PROCESSING LETTERS, VOL. 8, NO. 1, JANUARY 2001
[108] R. Fablet and P. Bouthemy, Motion Recognition Using Nonparametric Image Motion Models Estimated from Temporal and Multiscale Co-Occurrence Statistics, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 12, DECEMBER 2003, pp.1619-1624.
[109] 刘智勇,智能交通控制理论及其应用,科学出版社,2003