混合交通视频检测算法研究
|
摘要
混合交通是我国交通的主要特征。交通信息采集是有效进行交通管理与控制的前提。视频检测技术可自动获取全面的交通场景信息,广泛应用于道路交通数据采集、交叉口控制、交通事故处理、远程视频监控等交通领域,是未来交通信息采集的主要手段。
针对混合交通视频检测算法在背景初始化、背景模型更新、阴影检测和物体分类识别等方面存在的主要问题,本文进行了深入系统的研究,提出了一种基于聚类识别的背景初始化算法,能够获取具有运动物体的初始背景,可克服缓慢运动大型物体造成的影响,实现遮挡率大于50%的背景初始化;提出了基于对象级的混合高斯背景模型更新方法,克服了像素级混合高斯模型中长时间停车和交通拥挤等现象可能造成的背景模型不能有效更新、使运动物体成为背景的一部分的问题;提出了基于RGB颜色变化度的自适应阴影检测算法,克服了颜色特性阴影检测方法中固定阈值的缺陷,可根据当前目标的特点自适应地进行阴影检测;提出了基于矩向量的混合交通物体特征提取与表达方法,利用SVM多分类学习机制,建立了基于SVM的识别分类算法,满足了混合交通物体识别的需要。
本文取得的上述成果,为进一步研究混合交通视频检测算法奠定了基础。
Mixed traffic is the main characteristic of our country traffic. Traffic information collection is the precondition of the effective traffic management and controlling. Video detection technology can automatically obtain comprehensive information mixed traffic scenario, Can be widely used in road traffic data collection, intersection control, traffic processing, remote video surveillance and other traffic areas, and it will be the main means of collecting information in the future.
At present, it has made significant research results at the traffic video detection technology in China and abroad, but there are still some problems to constrain the traffic video detection technology, mostly of them are: 1) Background initialization and update, currently background model were assumed initial background , it does not include the prospect of sport, and the background update process does not consider the prospect of exercise, it limits the use of background model conditions and application scope, to make background model update can not overcome the traffic congestion, signal control, the formation of long-stay parking and traffic objects slow movement on the impact of the background updates, which will make movement object update as the background, causing movement objects false; 2) Shadow detection algorithm, the objects with the movement shadow has the same moving peculiarity of objects, and the shadow region and move objects closely linked, it probably caused the mistaken classification of objects, however the shadow detection algorithm used a fixed pre-determined threshold for background detection at present, that is difficult to satisfy the needs of practical applications; 3) Camera calibration parameters, the camera parameter calibration can achieve the projection mapping of world coordinates and image coordinates, which is the basis for carrying out traffic movement objects analysis and determination, their algorithm directly affects the precision and accuracy of the traffic analysis; 4) Mixed traffic object recognition, the mixed traffic is the main characteristics of our country transport, mixed traffic classification is the basic and premise of mixed traffic information obtained, At present, domestic and international traffic video detection algorithm is mainly identify vehicle classification, it lacks methods to recognize mixed traffic objects, restricting the scope of application, and also difficult to satisfy the actual needs of mixed traffic in our country.
For the main problems of mixed traffic video detection, this article has been made a systematic research on the background model, the shadow detection, camera calibration, mixed-traffic objects classification and recognition, the main study results are as follows: In order to obtain the effective movement initial background to make the background model has selection updated in accordance to object moving information, this paper presents the background of identification based on cluster initialization algorithms and object-level based on a mixture of Gaussian background model update method. Background initialization phase, which is using the variable sliding window detect each pixel smoothing of all non-overlapping sub-sequences, to obtain probably background; Then select each smooth middle sample point of sub-sequences to build a classification sequence set; Finally under the unknown category of unsupervised clustering to identify thought, access to background subset implementation background initialization. Background update stage, according to motion segmentation, object recognition, kalman tracking sports and other high-level semantic expression, access to the prospect of targeted movement object information to determine whether the current point is the prospect objects or not. If it is the prospect objects, it does not be updated, otherwise, in accordance with the pixel-level Gaussian background model updating, in order to achieve the target level based on a mixture of Gaussian background update. All different traffic video sequences experimental results show that, this method has good adaptable, it could overcome the effect of the slow movement of large objects, the prospects for the impact of blocking the implementation rate of more than 50% of the background initialization. The method overcomes the pixel-level mixed-Gaussian model of long-stay parking and traffic situation on the impact of the background update.
In light of the shadow detection algorithm does not consider the characteristics of sports objects and adaptive threshold, and adopting fixed, uniform threshold segmentation exercise shadow problem, according to the movement objectives characteristics of RGB color changing degree, adapting to the shadow detection algorithm is based on the RGB color changing degrees.The algorithm based on region segmentation, access to regional sports objects; using the optical properties of the shadow to access the candidate region; in accordance with the method of hypothesis testing, statistics for each candidate region of the RGB color changing degree of the shadow, making the shadow of the regional expression of the candidate for the mixed Gaussian distribution; Using EM algorithm implementation Gaussian Mixture Parameter Estimation, to obtain the shadow of the Gaussian distribution region; In accordance with the principles of 2.5σadaptive define the shadow detection threshold, making the shadow detected implementation. The algorithm overcomes the color characteristics of the shadow detection method of defects fixed threshold, and in accordance with the characteristics of the current goal for adaptively Detected shadow. Under different traffic status Videos treatment effect shows that the method has good robustness and adaptability, it satisfies to the actual needs of Traffic Video Detection.
For existing scene reconstruction algorithm, it has high computational complexity and robustness of the bad disadvantage, this paper uses a black-box based on the mapping transformation method has been applied to traffic video calibration tests quickly and easily achieve 2-D space measurement Express. The method firstly is based on the Harris operator sub-pixel level corner detection algorithm, to obtain the characteristics of angle reference points, and select Group 4 corner; Combined with the corresponding corner of the image coordinates and world coordinates, according to the linear mapping model of the image coordinates and world coordinates using the matrix equation to obtain the camera parameters. There is only one piece of template images, in calibration process, comparing with traditional methods, this this reduces the number of feature points with the template to simplify the calculated. Experimental results show that the method is stability, high accuracy, the characteristics of simple algorithms.
As for the lack of mixed traffic object classification and recognition rapid and effective algorithms couldn’t satisfy to actual needs of mixed traffic in our country, this paper bring forward the method of mixed traffic object feature extraction and expression which is based on the moment vector, using SVM multi-classification learning mechanism, set up SVM-based identification classification algorithm. In the feature extraction phase, firstly to obtain objects focus, then determine the moving object contour points with the focus characteristics of the expression, to build sports moment vector, as the characteristics of movement objects; In studying classification phase, according to different objects Moment vector samples, using SVM learning mechanism to obtain samples of each type of optimal classification hyperplane; In the identification stage, using objects characteristics vector and samples of optimal classification hyperplane in study phase to obtain the movement objects classification and recognition. Different video sequences of objects of mixed traffic detection results show that the classification algorithm has good performance and mixed traffic can meet the needs of object recognition.
In this paper, the mainly study results achieved on mapping traffic scenes, background initialization, background update model, shadow detection and identify and classification of mixed-traffic, which are the theoretical basis for further study mixed traffic video detection algorithms and achieve mixed traffic video detection technology.
针对混合交通视频检测算法在背景初始化、背景模型更新、阴影检测和物体分类识别等方面存在的主要问题,本文进行了深入系统的研究,提出了一种基于聚类识别的背景初始化算法,能够获取具有运动物体的初始背景,可克服缓慢运动大型物体造成的影响,实现遮挡率大于50%的背景初始化;提出了基于对象级的混合高斯背景模型更新方法,克服了像素级混合高斯模型中长时间停车和交通拥挤等现象可能造成的背景模型不能有效更新、使运动物体成为背景的一部分的问题;提出了基于RGB颜色变化度的自适应阴影检测算法,克服了颜色特性阴影检测方法中固定阈值的缺陷,可根据当前目标的特点自适应地进行阴影检测;提出了基于矩向量的混合交通物体特征提取与表达方法,利用SVM多分类学习机制,建立了基于SVM的识别分类算法,满足了混合交通物体识别的需要。
本文取得的上述成果,为进一步研究混合交通视频检测算法奠定了基础。
Mixed traffic is the main characteristic of our country traffic. Traffic information collection is the precondition of the effective traffic management and controlling. Video detection technology can automatically obtain comprehensive information mixed traffic scenario, Can be widely used in road traffic data collection, intersection control, traffic processing, remote video surveillance and other traffic areas, and it will be the main means of collecting information in the future.
At present, it has made significant research results at the traffic video detection technology in China and abroad, but there are still some problems to constrain the traffic video detection technology, mostly of them are: 1) Background initialization and update, currently background model were assumed initial background , it does not include the prospect of sport, and the background update process does not consider the prospect of exercise, it limits the use of background model conditions and application scope, to make background model update can not overcome the traffic congestion, signal control, the formation of long-stay parking and traffic objects slow movement on the impact of the background updates, which will make movement object update as the background, causing movement objects false; 2) Shadow detection algorithm, the objects with the movement shadow has the same moving peculiarity of objects, and the shadow region and move objects closely linked, it probably caused the mistaken classification of objects, however the shadow detection algorithm used a fixed pre-determined threshold for background detection at present, that is difficult to satisfy the needs of practical applications; 3) Camera calibration parameters, the camera parameter calibration can achieve the projection mapping of world coordinates and image coordinates, which is the basis for carrying out traffic movement objects analysis and determination, their algorithm directly affects the precision and accuracy of the traffic analysis; 4) Mixed traffic object recognition, the mixed traffic is the main characteristics of our country transport, mixed traffic classification is the basic and premise of mixed traffic information obtained, At present, domestic and international traffic video detection algorithm is mainly identify vehicle classification, it lacks methods to recognize mixed traffic objects, restricting the scope of application, and also difficult to satisfy the actual needs of mixed traffic in our country.
For the main problems of mixed traffic video detection, this article has been made a systematic research on the background model, the shadow detection, camera calibration, mixed-traffic objects classification and recognition, the main study results are as follows: In order to obtain the effective movement initial background to make the background model has selection updated in accordance to object moving information, this paper presents the background of identification based on cluster initialization algorithms and object-level based on a mixture of Gaussian background model update method. Background initialization phase, which is using the variable sliding window detect each pixel smoothing of all non-overlapping sub-sequences, to obtain probably background; Then select each smooth middle sample point of sub-sequences to build a classification sequence set; Finally under the unknown category of unsupervised clustering to identify thought, access to background subset implementation background initialization. Background update stage, according to motion segmentation, object recognition, kalman tracking sports and other high-level semantic expression, access to the prospect of targeted movement object information to determine whether the current point is the prospect objects or not. If it is the prospect objects, it does not be updated, otherwise, in accordance with the pixel-level Gaussian background model updating, in order to achieve the target level based on a mixture of Gaussian background update. All different traffic video sequences experimental results show that, this method has good adaptable, it could overcome the effect of the slow movement of large objects, the prospects for the impact of blocking the implementation rate of more than 50% of the background initialization. The method overcomes the pixel-level mixed-Gaussian model of long-stay parking and traffic situation on the impact of the background update.
In light of the shadow detection algorithm does not consider the characteristics of sports objects and adaptive threshold, and adopting fixed, uniform threshold segmentation exercise shadow problem, according to the movement objectives characteristics of RGB color changing degree, adapting to the shadow detection algorithm is based on the RGB color changing degrees.The algorithm based on region segmentation, access to regional sports objects; using the optical properties of the shadow to access the candidate region; in accordance with the method of hypothesis testing, statistics for each candidate region of the RGB color changing degree of the shadow, making the shadow of the regional expression of the candidate for the mixed Gaussian distribution; Using EM algorithm implementation Gaussian Mixture Parameter Estimation, to obtain the shadow of the Gaussian distribution region; In accordance with the principles of 2.5σadaptive define the shadow detection threshold, making the shadow detected implementation. The algorithm overcomes the color characteristics of the shadow detection method of defects fixed threshold, and in accordance with the characteristics of the current goal for adaptively Detected shadow. Under different traffic status Videos treatment effect shows that the method has good robustness and adaptability, it satisfies to the actual needs of Traffic Video Detection.
For existing scene reconstruction algorithm, it has high computational complexity and robustness of the bad disadvantage, this paper uses a black-box based on the mapping transformation method has been applied to traffic video calibration tests quickly and easily achieve 2-D space measurement Express. The method firstly is based on the Harris operator sub-pixel level corner detection algorithm, to obtain the characteristics of angle reference points, and select Group 4 corner; Combined with the corresponding corner of the image coordinates and world coordinates, according to the linear mapping model of the image coordinates and world coordinates using the matrix equation to obtain the camera parameters. There is only one piece of template images, in calibration process, comparing with traditional methods, this this reduces the number of feature points with the template to simplify the calculated. Experimental results show that the method is stability, high accuracy, the characteristics of simple algorithms.
As for the lack of mixed traffic object classification and recognition rapid and effective algorithms couldn’t satisfy to actual needs of mixed traffic in our country, this paper bring forward the method of mixed traffic object feature extraction and expression which is based on the moment vector, using SVM multi-classification learning mechanism, set up SVM-based identification classification algorithm. In the feature extraction phase, firstly to obtain objects focus, then determine the moving object contour points with the focus characteristics of the expression, to build sports moment vector, as the characteristics of movement objects; In studying classification phase, according to different objects Moment vector samples, using SVM learning mechanism to obtain samples of each type of optimal classification hyperplane; In the identification stage, using objects characteristics vector and samples of optimal classification hyperplane in study phase to obtain the movement objects classification and recognition. Different video sequences of objects of mixed traffic detection results show that the classification algorithm has good performance and mixed traffic can meet the needs of object recognition.
In this paper, the mainly study results achieved on mapping traffic scenes, background initialization, background update model, shadow detection and identify and classification of mixed-traffic, which are the theoretical basis for further study mixed traffic video detection algorithms and achieve mixed traffic video detection technology.
引文
[1].彭春华刘建业,刘岳峰.车辆检测传感器综述[J].传感器与微系统. 2007, 26(6): 4-9.
[2].Chatziioanou Alypios, Hockaday Stephen L. M., Kaighn Shirlee. Video image processing systems:applications in transportation. In; 1995; Piscataway, NJ, USA: IEEE; 1995. p. 17-20.
[3]. Hoose N., 1992. IMPACTS: an image analysis tool for motorway surveillance. Tra c Engineering andControl 33(3),, 140±147. [J].
[4]. Tziakos I., Cavallaro A., Xu L. Q. Video event segmentation and visualisation in non-linear subspace[J].Pattern Recognition Letters. 2009, 30(2): 123-131.
[5]. Chachich A., Pau, A., Barber, A., Kennedy, K., Olejniczak, E., Hackney, J., Sun, Q., Mireles, E., 1996.Tra c sensor, using a color vision method. In: Transportation Sensors and Controls: Collision AvoidanceTra c Management, and ITS SPIE Proc. Vol. 2902, pp. 156-165. [J].
[6]. Chao T., Lau, B., Park, Y., 1996 Vehicle detection and classi?cation in shadowy tra c images usingwavelets and, neural networks. In: Transportation Sensors and Controls: Collision Avoidance Tra cManagement, and ITS,, SPIE Proc. Vol. 2902 pp. 136-147. [J].
[7]. Edie L., 1963. Discussion of traffic stream measurements and definitions. In: Proceedings of the SecondInternational, Symposium on the Theory of Traffic Flow OECD, Paris, France, pp. 139-154. [J].
[8]. Furuhashi Toshio, Inagaki Renya, Mochii Masayoshi. ECONOMIC RADAR VIDEO TRANSMISSIONUTILIZING BAND COMPRESSION TECHNIQUE[J]. NEC Research & Development. 1973, (28): 80-88.
[9]. Seacombe R. J., Shilling A. G. REMOTE VIDEO MONITORING SYSTEMS[J]. Engineering (London).1976, 216(11): 802-803.
[10]. Coifman B., Beymer D., McLauchlan P. A real-time computer vision system for vehicle tracking andtraffic surveillance[J]. Transportation Research Part C-Emerging Technologies. 1998, 6(4): 271-288.
[11]. C. Ridder, O. Munkelt, Kirchner. and H. Adaptive background estimation and foreground detectionusing kalman filtering[J]. Proc International Conference on recent Advances in Mechatronics. 1995: 193-199.
[12]. Wren Christopher Richard, Azarbayejani Ali, Darrell Trevor. Pfinder: real-time tracking of the humanbody[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19(7): 780-785.
[13]. Stauffer Chris, Grimson W. E. L. Adaptive background mixture models for real-time tracking[J].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999, 2:246-252.
[14].Kahl F., Hartley R., Hilsenstein V. Novelty detection in image sequences with dynamic background. In:Statistical Methods in Video Processing. Berlin: Springer-Verlag Berlin; 2004:117-128.
[15]. Costantini G., Casali D., Perfetti R. Analogic CNN algorithm for estimating position and size of movingobjects[J]. International Journal of Circuit Theory and Applications. 2004, 32(6): 509-522.
[16].Toyama Kentaro, Krumm John, Brumitt Barry. Wallflower: Principles and practice of backgroundmaintenance. In; 1999; Kerkyra, Greece: Institute of Electrical and Electronics Engineers Inc., Piscataway,NJ, USA; 1999. p. 255-261.
[17].李志慧,劳云腾,王殿海等.混合交通流视频检测中区域选择更新混合高斯背景模型研究[J]. ITS通讯. 2005, (02): 25-27.
[18]. Long Warren, Yang Yee-Hong. Stationary background generation: An alternative to the difference of two images[J]. Pattern Recognition. 1990, 23(12): 1351-1359.
[19].Li L., Wang F. Y. Approximate vehicle waiting time estimation using adaptive video-based vehicle tracking. In: Zheng N, Jiang X, lan X, editors. International Workshop on Intelligent Computer in Pattern Analysis/Synthesis; 2006 Aug 26-27; Xian, PEOPLES R CHINA; 2006. p. 105-114.
[20].Gutchess D., Trajkovic M., Cohen-Solal E.. A background model initialization algorithm for video surveillance. In; 2001; Vancouver, BC: Institute of Electrical and Electronics Engineers Inc.; 2001. p. 733-740.
[21].Marco Cristani Manuele Bicego, Vittorio Murino. Multi-level background initialization using Hidden Markov Models. In: First ACM SIGMM international workshop on Video surveillance; 2003; 2003. p. 11-20.
[22].Andrea Colombari Andrea Fusiello, and Vittorio Murino. Background Initialization in Cluttered Sequences. In: Computer Vision and Pattern Recognition Workshop; 2006 17-22 June 2006: 17-22 June 2006; 2006. p. 197- 197.
[23].Prati A. Cucchiara, R. Mikic, I. Trivedi, M.M. Analysis and detection of shadows in video streams: a comparative evaluation. In: CVPR; 2001; 2001. p. 571-576.
[24]. Prati A., Mikic I., Trivedi M. M.. Detecting moving shadows: Algorithms and evaluation[J]. IEEE Trans Pattern Anal Mach Intell. 2003, 25(7): 918-923.
[25]. Salvador Elena, Cavallaro Andrea, Ebrahimi Touradj. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding. 2004, 95(2): 238-259.
[26]. J.W. Hsieh , W.F. Hu , C.J. Chang. Shadow elimination for effective moving object detection by gaussian shadow modeling[J]. Image and Vision Computing. November 2003, 21(6): 505-516.
[27].S. Nadimi, Bhanu B. Moving shadow detection using a physics-based approach. In: Sixteen IEEE International Conference on Pattern Recognition; August 2002.; Quebec City,Canada August 2002. p. 701-704.
[28]. Leone A., Distante C. Shadow detection for moving objects based on texture analysis[J]. Pattern Recognition. 2007, 40(4): 1222-1233.
[29]. Zhang Z.Y. A flexible new technique for camera calibration [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000, 22(11): 1330-1334.
[30]. Tsai R.Y. A Versatile Camera Calibration Technique for High - Accuracy 3D Machine Vision Metrology Using Off- the - Shelf TV Cameras and Lenses [J]. IEEE Journal of Robotic and Automation. 1987, 3(4): 323– 342.
[31].胡勇,王从军,黄树槐.双目视觉传感器的自动标定[J].武汉理工大学学报. 2005, 27(10): 67-69.
[32].Dron. Lisa. Dynamic camera self-calibration from controlled motion sequences. In: Proc IEEE Conf on Computer Vision and Pattern Recognition; 1993; 1993. p. 501–506.
[33]. Bogomolov Y Dror G, Lapchev S.et al.Classification of Moving Targets Based on Motion and Appearance[A].British Machine Vision Conference,2003,2,429~438.. [J].
[34]. Rivlin E Rudzsky M.et al.A Real-Time System for Classification of Moving Objects[A].IEEE Conference on Computer Vision and Pattern Recognition,2002,3,688~691.. [J].
[35]. Lipton A Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[A].IEEE Workshop on Application of Computer Vision,1998,8~14.. [J].
[36]. Toth D Aach T. Detection and Recognition of Moving Objects Using Statistical Motion Detection and Fourier Descriptors[C].International Conference on Image Analysis and Processing,2003,430~435.. [J].
[37]. Kuno Y Watanabe T, Shimosakoda Y. Automated detection of human for visual surveillance system[A].Proc IEEE International Conference on Pattern Recognition,1996,865~869.. [J].
[38]. O.Javed M. Shah. Tracking and Object Classification for Automated Surveillance[C].Proc of ECCV,2002,Part IV,343~357.. [J].
[39]. Cutler R Davis L. Robust Real-time periodic motion detection analysis and application[J].IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8),781~796.. [J].
[40]. Lipton A. J., Heartwell C. H., Haering N.. Automated video protection, monitoring & detection[J]. Ieee Aerospace and Electronic Systems Magazine. 2003, 18(5): 3-18.
[41].Wixson,A.Selinger L. Classifying moving objects as rigid or non-rigid without correspondences. In: Proc.Of DARPA Image Understanding Workshop; 1998; 1998. p. 341~358.
[42]. Wong Kwan-Yee K., Mendonca Paulo R. S., Cipolla Roberto. Camera calibration from surfaces of revolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003, 25(2): 147-161.
[43]. Wong Kwan-Yee K., Zhang Guoqiang, Liang Chen. 1D camera geometry and its application to the self-calibration of circular motion sequences[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008, 30(12): 2243-2248.
[44].Wong Winnifred, Hornsey Richard I. Calibration of a saccadic camera system to adapt to lens distortions. In; 2005; Bellingham WA, WA 98227-0010, United States: International Society for Optical Engineering; 2005. p. 59692.
[45]. Brown D. C. Close- range camera calibration[J]. 1971, 37(8): 855-866.
[46]. Chen I. Hsien, Wang Sheng-Jyh. An efficient approach for dynamic calibration of multiple cameras[J]. IEEE Transactions on Automation Science and Engineering. 2009, 6(1): 187-194.
[47]. Zhong Zhi-Guang, Zhao Yi-Ming, Lin Xue-Ming. Camera calibration method based on arbitrary point pairs[J]. Jiqiren/Robot. 2008, 30(1): 85-90.
[48]. Zhao Zi-Jian, Liu Yun-Cai. New multi-camera calibration algorithm based on 1D objects[J]. Journal of Zhejiang University: Science A. 2008, 9(6): 799-806.
[49]. Zhao Honghua, Ge Louis. Camera calibration using neural network for image-based soil deformation measurement systems[J]. Geotechnical Testing Journal. 2008, 31(2): 192-197.
[50].Paisitkriangkrai S., Shen C., Zhang J. Performance evaluation of local features in human classification and detection. In: Digital Image Computing Technology and Applications Conference 2007; 2008 2007; Queensland, AUSTRALIA; 2008. p. 236-246.
[51].Yu Zhijing, Li Xinxin, Tian Wei. Camera calibration method used in computer vision coordinate measurement systems. In; 2008; Bellingham WA, WA 98227-0010, United States: SPIE; 2008. p. 68291.
[52]. Yang Zang-Jian, Fu Tai-Ran, Cheng Xiao-Fang. Calibration for control parameters of digital color camera[J]. Guangxue Jishu/Optical Technique. 2008, 34(3): 375-378.
[53].Sun Jin, Gu Hongbin, Qin Xiaolin. A new camera calibration based on vanishing point. In; 2008; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2008. p.2371-2376.
[54]. Sigernes Fred, Holmes Jeffrey Morgan, Dyrland Margit. Sensitivity calibration of digital colour cameras for auroral imaging[J]. Optics Express. 2008, 16(20): 15623-15632.
[55].Peng Gang, Huang Xinhan, Gao Jian. Camera modeling and distortion calibration for mobile robot vision. In; 2008; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2008. p. 1657-1662.
[56].Yang Zhonggen, Cao Fang. Linear six-point algorithm of camera self-calibration and 3D reconstruction from single-view or multi-views. In; 2007; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2007. p. 4129134.
[57].Xianghua Ying, Hongbin Zha. Camera calibration using principal-axes aligned conics. In; 2007; Heidelberg, D-69121, Germany: Springer Verlag; 2007. p. 138-148.
[58].Wang Lu, You Suya, Neumann Ulrich. Single view camera calibration for augmented virtual environments. In; 2007; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Computer Society; 2007. p. 255-258.
[59]. Fraser C. S., Veress S. A. SELF-CALIBRATION OF A FIXED-FRAME MULTIPLE-CAMERA SYSTEM[J]. Photogrammetric Engineering and Remote Sensing. 1980, 46(11): 1439-1445.
[60].Abbot A. Lynn. Merging multiple stereo surface maps through camera self-calibration. In; 1991; Piscataway, NJ, USA: Publ by IEEE; 1991. p. 356-360.
[61].Daily Michael J. Self-calibration of a multi-camera vision system. In; 1991; San Jose, CA, USA: Publ by Maple Press, Inc; 1991. p. 810-815.
[62].Dron Lisa. Dynamic camera self-calibration from controlled motion sequences. In; 1993; Piscataway, NJ, USA: Publ by IEEE; 1993. p. 501-506.
[63].Ashworth R., Darkin C. G., Dickinson K. W.. APPLICATIONS OF VIDEO IMAGE PROCESSING FOR TRAFFIC CONTROL SYSTEMS. In; 1986; London, Engl: IEE; 1986. p. 119-122.
[64].Zhuang Hanqi. Self-calibration approach to extrinsic parameter estimation of stereo cameras. In; 1994; Piscataway, NJ, USA: Publ by IEEE; 1994. p. 3428-3433.
[65]. Zhuang Hanqi. Self-calibration approach to extrinsic parameter estimation of stereo cameras[J]. Robotics and Autonomous Systems. 1995, 15(3): 189-197.
[66]. Fraser Clive S. Digital camera self-calibration[J]. ISPRS Journal of Photogrammetry and Remote Sensing. 1997, 52(4): 149-159.
[67].Sturm Peter. Camera self-calibration: a case against Kruppa's equations. In; 1998; Los Alamitos, CA, USA: IEEE Comp Soc; 1998. p. 172-175.
[68].Ying Shan, Boon Goh Wooi. Camera self-calibration from video sequences with changing focal length. In; 1998; Los Alamitos, CA, USA: IEEE Comp Soc; 1998. p. 176-180.
[69]. de Agapito Lourdes, Hartley Richard I., Hayman Eric. Linear self-calibration of a rotating and zooming camera[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999, 1: 15-21.
[70]. Pollefeys Marc, Koch Reinhard, Van Gool Luc. Self-calibration and metric reconstruction inspite of varying and unknown intrinsic camera parameters[J]. International Journal of Computer Vision. 1999, 32(1): 7-25.
[71].Hu R., Ji Q. Camera self-calibration from ellipse correspondences. In; 2001: Institute of Electrical and Electronics Engineers Inc.; 2001. p. 2191-2196.
[72]. Liu J. S., Chuang J. H. Self-calibration with varying focal length from two images obtained by a camera with small rotation and general translation[J]. Pattern Recognition Letters. 2001, 22(13): 1393-1404.
[73].Cheng Zhaolin, Lao Weilun, Kam Alvin H.. A linear self-calibration approach for camera focal length estimation. In; 2004; New York, NY 10016-5997, United States: Institute of Electrical and Electronics Engineers Inc.; 2004. p. 717-722.
[74].Habed A., Boufama B. S. Self-calibration of a simplified camera using Kruppa equations. In; 2004; Los Alamitos, CA 90720-1314, United States: IEEE Computer Society; 2004. p. 446-450.
[75].Zhang Qilong, Pless Robert. Self-calibration algorithms for cameras and laser range finders. In; 2004; Bellingham, WA 98227-0010, United States: International Society for Optical Engineering; 2004. p. 344-353.
[76].Cao Xiaochun, Xiao Jiangjian, Foroosh Hassan. Self-calibration using constant camera motion. In; 2006; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2006. p. 595-598.
[77]. Habed Adlane, Boufama Boubakeur. Camera self-calibration from bivariate polynomial equations and the coplanarity constraint[J]. Image and Vision Computing. 2006, 24(5): 498-514.
[78]. Wang Pu, Gu Dong-Hua, Zhuang Chun-Hua. Camera self-calibration technique based on the foundation matrix[J]. Beijing Gongye Daxue Xuebao / Journal of Beijing University of Technology. 2007, 33(4): 362-365.
[79].Kannala Juho, Brandt Sami S., Heikkila Janne. Self-calibration of central cameras by minimizing angular error. In; 2008; Setubal, 2910-595, Portugal: Inst. for Syst. and Technol. of Inf., Control and Commun. (INSTICC); 2008. p. 28-35.
[80].Zhang Zhengyou. Flexible camera calibration by viewing a plane from unknown orientations. In; 1999; Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc.; 1999. p. 666-673.
[81]. Tsai Roger Y. VERSATILE CAMERA CALIBRATION TECHNIQUE FOR HIGH-ACCURACY 3D MACHINE VISION METROLOGY USING OFF-THE-SHELF TV CAMERAS AND LENSES[J]. IEEE Journal of Robotics and Automation. 1987, RA-3(4): 323-344.
[82].Tsai Roger Y. EFFICIENT AND ACCURATE CAMERA CALIBRATION TECHNIQUE FOR 3D MACHINE VISION. In; 1986; New York, NY, USA: IEEE; 1986. p. 364-374.
[83].Abdel-Aziz Y.I., Karara H.M. Direct linear transformation into object space coordinates in close-range photogrammetry. In: Proc Symp Close-Range Photogrammetry; 1971; 1971. p. 1-18.
[84]. Riou L., Jacquet G., Fayolle J.. Calibration method of a two-camera system in a face-to-face configuration designed for fast-flow study[J]. Journal of Flow Visualization and Image Processing. 2000, 7(2): 123-141.
[85]. A.Shashua. Algebraic function for recognition[J]. IEEE T rans PAM I. 1995, (17): 779-789.
[86].Brady M., Wang H. Corner detection for 3D vision using array processors. In; 1994: Springer-Verlag GmbH & Company KG; 1994. p. 91.
[87].Moravec H.P. Towards automatic visual obstacle avoidance. In: Proceedings of the 5th International Joint Conference on Artificial Intelligence; 1977; Carnegie-Mellon University: Pittsburgh, PA; 1977.
[88]. Smith S.M, Brady J.M. SUSAN-a new approach to low level image processing[J]. Journal of ComputerVision. 1997, 2(1): 45-78.
[89]. Trajkovic M., Hedley M. Fast corner detection[J]. Image and Vision Computing. 1998, 16(1): 75-87.
[90].Harris C.G., Stephens M.J. A Combined Corner and Edge Detector. In: Proceedings Fourth Alvey Vision Conference; 1988; Manchester; 1988. p. 147-151.
[91]. Noble J.A. Images as functions and sets[J]. Image and Vision Computer. 1992, 10(1): 19-29.
[92].Zuniga Oscar A., Haralick Robert M. CORNER DETECTION USING THE FACET MODEL. In; 1983; New York, NY, USA: IEEE; 1983. p. 30-37.
[93].Laganiere Robert. Morphological corner detection. In; 1998; Piscataway, NJ, USA: IEEE; 1998. p. 280-285.
[94]. Laganiere Robert. Morphological operator for corner detection[J]. Pattern Recognition. 1998, 31(11): 1643-1652.
[95].艾海周,武勃.图像处理、分析与机器视觉.北京:人民邮电出版社; 2003.9.
[96]. L Vincent, P Soille. Watersheds in digital spaces: an efficient algorithm based on immersion simulations[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. 1991, 13(6): 583-598.
[97].Beucher S. Watershed hierarchical segmentation and waterfall algorithm: Kluwer Academic Publishers; 1994.
[98]. Higgins W E, Ojard E J. 3D images and use of markers and other topological information to reduce oversegmentations[J]. Computers in medical imaging and Graphics. 1993, (17): 387-395.
[99]. Meyer F., Beucher S. Morphological Segmentation[J]. Journal of Visual Communication on Image Representation. September 1990, 1(1): 21-46.
[100].V.Vapnik. The nature of statistical learning theory. New York: Springer-Verlag; 1995.
[101].R.Webb Andrew.统计模式识别.北京:电子工业出版社; 2004.
[102].N.Cristianini, J.S.Taylor.支持向量机导论.北京:电子工业出版社; 2005.
[103].O.Zuniga, R.M.Haralick. Corner detection using the facet model. In: Computer Vision and Pattern Recognition; 1983; Los Alamitos,CA: IEEE; 1983. p. 30~37.
[104].H.P.Moravec. Towards automatic visual obstacle avoidance. In: Proceedings of the 5th International Joint Conference on Artificial Intelligence; 1977; Carnegie-Mellon University: Pittsburgh,PA; 1977.
[105].C.G.Harris, M.J.Stephens. A Combined Corner and Edge Detector. In: Proceedings Fourth Alvey Vision Conference; 1988; Manchester; 1988. p. 147~151.
[106].郑南宁.计算机视觉与模式识别.北京:国防工业出版社; 1998.
[107].Zang Q., Klette R. Object classification and tracking in video surveillance. In: Petkov N, Westenberg MA, editors. 10th International Conference on Computer Analysis of Images and Patterns; 2003 Aug 25-27; Groningen, Netherlands; 2003. p. 198-205.
[108].O.Javed, M.Shah. Tracking and Object Classification for Automated Surveillance. In: Proc of ECCV; 2002; 2002. p. 343~357.
[2].Chatziioanou Alypios, Hockaday Stephen L. M., Kaighn Shirlee. Video image processing systems:applications in transportation. In; 1995; Piscataway, NJ, USA: IEEE; 1995. p. 17-20.
[3]. Hoose N., 1992. IMPACTS: an image analysis tool for motorway surveillance. Tra c Engineering andControl 33(3),, 140±147. [J].
[4]. Tziakos I., Cavallaro A., Xu L. Q. Video event segmentation and visualisation in non-linear subspace[J].Pattern Recognition Letters. 2009, 30(2): 123-131.
[5]. Chachich A., Pau, A., Barber, A., Kennedy, K., Olejniczak, E., Hackney, J., Sun, Q., Mireles, E., 1996.Tra c sensor, using a color vision method. In: Transportation Sensors and Controls: Collision AvoidanceTra c Management, and ITS SPIE Proc. Vol. 2902, pp. 156-165. [J].
[6]. Chao T., Lau, B., Park, Y., 1996 Vehicle detection and classi?cation in shadowy tra c images usingwavelets and, neural networks. In: Transportation Sensors and Controls: Collision Avoidance Tra cManagement, and ITS,, SPIE Proc. Vol. 2902 pp. 136-147. [J].
[7]. Edie L., 1963. Discussion of traffic stream measurements and definitions. In: Proceedings of the SecondInternational, Symposium on the Theory of Traffic Flow OECD, Paris, France, pp. 139-154. [J].
[8]. Furuhashi Toshio, Inagaki Renya, Mochii Masayoshi. ECONOMIC RADAR VIDEO TRANSMISSIONUTILIZING BAND COMPRESSION TECHNIQUE[J]. NEC Research & Development. 1973, (28): 80-88.
[9]. Seacombe R. J., Shilling A. G. REMOTE VIDEO MONITORING SYSTEMS[J]. Engineering (London).1976, 216(11): 802-803.
[10]. Coifman B., Beymer D., McLauchlan P. A real-time computer vision system for vehicle tracking andtraffic surveillance[J]. Transportation Research Part C-Emerging Technologies. 1998, 6(4): 271-288.
[11]. C. Ridder, O. Munkelt, Kirchner. and H. Adaptive background estimation and foreground detectionusing kalman filtering[J]. Proc International Conference on recent Advances in Mechatronics. 1995: 193-199.
[12]. Wren Christopher Richard, Azarbayejani Ali, Darrell Trevor. Pfinder: real-time tracking of the humanbody[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19(7): 780-785.
[13]. Stauffer Chris, Grimson W. E. L. Adaptive background mixture models for real-time tracking[J].Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999, 2:246-252.
[14].Kahl F., Hartley R., Hilsenstein V. Novelty detection in image sequences with dynamic background. In:Statistical Methods in Video Processing. Berlin: Springer-Verlag Berlin; 2004:117-128.
[15]. Costantini G., Casali D., Perfetti R. Analogic CNN algorithm for estimating position and size of movingobjects[J]. International Journal of Circuit Theory and Applications. 2004, 32(6): 509-522.
[16].Toyama Kentaro, Krumm John, Brumitt Barry. Wallflower: Principles and practice of backgroundmaintenance. In; 1999; Kerkyra, Greece: Institute of Electrical and Electronics Engineers Inc., Piscataway,NJ, USA; 1999. p. 255-261.
[17].李志慧,劳云腾,王殿海等.混合交通流视频检测中区域选择更新混合高斯背景模型研究[J]. ITS通讯. 2005, (02): 25-27.
[18]. Long Warren, Yang Yee-Hong. Stationary background generation: An alternative to the difference of two images[J]. Pattern Recognition. 1990, 23(12): 1351-1359.
[19].Li L., Wang F. Y. Approximate vehicle waiting time estimation using adaptive video-based vehicle tracking. In: Zheng N, Jiang X, lan X, editors. International Workshop on Intelligent Computer in Pattern Analysis/Synthesis; 2006 Aug 26-27; Xian, PEOPLES R CHINA; 2006. p. 105-114.
[20].Gutchess D., Trajkovic M., Cohen-Solal E.. A background model initialization algorithm for video surveillance. In; 2001; Vancouver, BC: Institute of Electrical and Electronics Engineers Inc.; 2001. p. 733-740.
[21].Marco Cristani Manuele Bicego, Vittorio Murino. Multi-level background initialization using Hidden Markov Models. In: First ACM SIGMM international workshop on Video surveillance; 2003; 2003. p. 11-20.
[22].Andrea Colombari Andrea Fusiello, and Vittorio Murino. Background Initialization in Cluttered Sequences. In: Computer Vision and Pattern Recognition Workshop; 2006 17-22 June 2006: 17-22 June 2006; 2006. p. 197- 197.
[23].Prati A. Cucchiara, R. Mikic, I. Trivedi, M.M. Analysis and detection of shadows in video streams: a comparative evaluation. In: CVPR; 2001; 2001. p. 571-576.
[24]. Prati A., Mikic I., Trivedi M. M.. Detecting moving shadows: Algorithms and evaluation[J]. IEEE Trans Pattern Anal Mach Intell. 2003, 25(7): 918-923.
[25]. Salvador Elena, Cavallaro Andrea, Ebrahimi Touradj. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding. 2004, 95(2): 238-259.
[26]. J.W. Hsieh , W.F. Hu , C.J. Chang. Shadow elimination for effective moving object detection by gaussian shadow modeling[J]. Image and Vision Computing. November 2003, 21(6): 505-516.
[27].S. Nadimi, Bhanu B. Moving shadow detection using a physics-based approach. In: Sixteen IEEE International Conference on Pattern Recognition; August 2002.; Quebec City,Canada August 2002. p. 701-704.
[28]. Leone A., Distante C. Shadow detection for moving objects based on texture analysis[J]. Pattern Recognition. 2007, 40(4): 1222-1233.
[29]. Zhang Z.Y. A flexible new technique for camera calibration [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000, 22(11): 1330-1334.
[30]. Tsai R.Y. A Versatile Camera Calibration Technique for High - Accuracy 3D Machine Vision Metrology Using Off- the - Shelf TV Cameras and Lenses [J]. IEEE Journal of Robotic and Automation. 1987, 3(4): 323– 342.
[31].胡勇,王从军,黄树槐.双目视觉传感器的自动标定[J].武汉理工大学学报. 2005, 27(10): 67-69.
[32].Dron. Lisa. Dynamic camera self-calibration from controlled motion sequences. In: Proc IEEE Conf on Computer Vision and Pattern Recognition; 1993; 1993. p. 501–506.
[33]. Bogomolov Y Dror G, Lapchev S.et al.Classification of Moving Targets Based on Motion and Appearance[A].British Machine Vision Conference,2003,2,429~438.. [J].
[34]. Rivlin E Rudzsky M.et al.A Real-Time System for Classification of Moving Objects[A].IEEE Conference on Computer Vision and Pattern Recognition,2002,3,688~691.. [J].
[35]. Lipton A Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[A].IEEE Workshop on Application of Computer Vision,1998,8~14.. [J].
[36]. Toth D Aach T. Detection and Recognition of Moving Objects Using Statistical Motion Detection and Fourier Descriptors[C].International Conference on Image Analysis and Processing,2003,430~435.. [J].
[37]. Kuno Y Watanabe T, Shimosakoda Y. Automated detection of human for visual surveillance system[A].Proc IEEE International Conference on Pattern Recognition,1996,865~869.. [J].
[38]. O.Javed M. Shah. Tracking and Object Classification for Automated Surveillance[C].Proc of ECCV,2002,Part IV,343~357.. [J].
[39]. Cutler R Davis L. Robust Real-time periodic motion detection analysis and application[J].IEEE Trans Pattern Analysis and Machine Intelligence,2000,22(8),781~796.. [J].
[40]. Lipton A. J., Heartwell C. H., Haering N.. Automated video protection, monitoring & detection[J]. Ieee Aerospace and Electronic Systems Magazine. 2003, 18(5): 3-18.
[41].Wixson,A.Selinger L. Classifying moving objects as rigid or non-rigid without correspondences. In: Proc.Of DARPA Image Understanding Workshop; 1998; 1998. p. 341~358.
[42]. Wong Kwan-Yee K., Mendonca Paulo R. S., Cipolla Roberto. Camera calibration from surfaces of revolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2003, 25(2): 147-161.
[43]. Wong Kwan-Yee K., Zhang Guoqiang, Liang Chen. 1D camera geometry and its application to the self-calibration of circular motion sequences[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008, 30(12): 2243-2248.
[44].Wong Winnifred, Hornsey Richard I. Calibration of a saccadic camera system to adapt to lens distortions. In; 2005; Bellingham WA, WA 98227-0010, United States: International Society for Optical Engineering; 2005. p. 59692.
[45]. Brown D. C. Close- range camera calibration[J]. 1971, 37(8): 855-866.
[46]. Chen I. Hsien, Wang Sheng-Jyh. An efficient approach for dynamic calibration of multiple cameras[J]. IEEE Transactions on Automation Science and Engineering. 2009, 6(1): 187-194.
[47]. Zhong Zhi-Guang, Zhao Yi-Ming, Lin Xue-Ming. Camera calibration method based on arbitrary point pairs[J]. Jiqiren/Robot. 2008, 30(1): 85-90.
[48]. Zhao Zi-Jian, Liu Yun-Cai. New multi-camera calibration algorithm based on 1D objects[J]. Journal of Zhejiang University: Science A. 2008, 9(6): 799-806.
[49]. Zhao Honghua, Ge Louis. Camera calibration using neural network for image-based soil deformation measurement systems[J]. Geotechnical Testing Journal. 2008, 31(2): 192-197.
[50].Paisitkriangkrai S., Shen C., Zhang J. Performance evaluation of local features in human classification and detection. In: Digital Image Computing Technology and Applications Conference 2007; 2008 2007; Queensland, AUSTRALIA; 2008. p. 236-246.
[51].Yu Zhijing, Li Xinxin, Tian Wei. Camera calibration method used in computer vision coordinate measurement systems. In; 2008; Bellingham WA, WA 98227-0010, United States: SPIE; 2008. p. 68291.
[52]. Yang Zang-Jian, Fu Tai-Ran, Cheng Xiao-Fang. Calibration for control parameters of digital color camera[J]. Guangxue Jishu/Optical Technique. 2008, 34(3): 375-378.
[53].Sun Jin, Gu Hongbin, Qin Xiaolin. A new camera calibration based on vanishing point. In; 2008; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2008. p.2371-2376.
[54]. Sigernes Fred, Holmes Jeffrey Morgan, Dyrland Margit. Sensitivity calibration of digital colour cameras for auroral imaging[J]. Optics Express. 2008, 16(20): 15623-15632.
[55].Peng Gang, Huang Xinhan, Gao Jian. Camera modeling and distortion calibration for mobile robot vision. In; 2008; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2008. p. 1657-1662.
[56].Yang Zhonggen, Cao Fang. Linear six-point algorithm of camera self-calibration and 3D reconstruction from single-view or multi-views. In; 2007; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2007. p. 4129134.
[57].Xianghua Ying, Hongbin Zha. Camera calibration using principal-axes aligned conics. In; 2007; Heidelberg, D-69121, Germany: Springer Verlag; 2007. p. 138-148.
[58].Wang Lu, You Suya, Neumann Ulrich. Single view camera calibration for augmented virtual environments. In; 2007; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Computer Society; 2007. p. 255-258.
[59]. Fraser C. S., Veress S. A. SELF-CALIBRATION OF A FIXED-FRAME MULTIPLE-CAMERA SYSTEM[J]. Photogrammetric Engineering and Remote Sensing. 1980, 46(11): 1439-1445.
[60].Abbot A. Lynn. Merging multiple stereo surface maps through camera self-calibration. In; 1991; Piscataway, NJ, USA: Publ by IEEE; 1991. p. 356-360.
[61].Daily Michael J. Self-calibration of a multi-camera vision system. In; 1991; San Jose, CA, USA: Publ by Maple Press, Inc; 1991. p. 810-815.
[62].Dron Lisa. Dynamic camera self-calibration from controlled motion sequences. In; 1993; Piscataway, NJ, USA: Publ by IEEE; 1993. p. 501-506.
[63].Ashworth R., Darkin C. G., Dickinson K. W.. APPLICATIONS OF VIDEO IMAGE PROCESSING FOR TRAFFIC CONTROL SYSTEMS. In; 1986; London, Engl: IEE; 1986. p. 119-122.
[64].Zhuang Hanqi. Self-calibration approach to extrinsic parameter estimation of stereo cameras. In; 1994; Piscataway, NJ, USA: Publ by IEEE; 1994. p. 3428-3433.
[65]. Zhuang Hanqi. Self-calibration approach to extrinsic parameter estimation of stereo cameras[J]. Robotics and Autonomous Systems. 1995, 15(3): 189-197.
[66]. Fraser Clive S. Digital camera self-calibration[J]. ISPRS Journal of Photogrammetry and Remote Sensing. 1997, 52(4): 149-159.
[67].Sturm Peter. Camera self-calibration: a case against Kruppa's equations. In; 1998; Los Alamitos, CA, USA: IEEE Comp Soc; 1998. p. 172-175.
[68].Ying Shan, Boon Goh Wooi. Camera self-calibration from video sequences with changing focal length. In; 1998; Los Alamitos, CA, USA: IEEE Comp Soc; 1998. p. 176-180.
[69]. de Agapito Lourdes, Hartley Richard I., Hayman Eric. Linear self-calibration of a rotating and zooming camera[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999, 1: 15-21.
[70]. Pollefeys Marc, Koch Reinhard, Van Gool Luc. Self-calibration and metric reconstruction inspite of varying and unknown intrinsic camera parameters[J]. International Journal of Computer Vision. 1999, 32(1): 7-25.
[71].Hu R., Ji Q. Camera self-calibration from ellipse correspondences. In; 2001: Institute of Electrical and Electronics Engineers Inc.; 2001. p. 2191-2196.
[72]. Liu J. S., Chuang J. H. Self-calibration with varying focal length from two images obtained by a camera with small rotation and general translation[J]. Pattern Recognition Letters. 2001, 22(13): 1393-1404.
[73].Cheng Zhaolin, Lao Weilun, Kam Alvin H.. A linear self-calibration approach for camera focal length estimation. In; 2004; New York, NY 10016-5997, United States: Institute of Electrical and Electronics Engineers Inc.; 2004. p. 717-722.
[74].Habed A., Boufama B. S. Self-calibration of a simplified camera using Kruppa equations. In; 2004; Los Alamitos, CA 90720-1314, United States: IEEE Computer Society; 2004. p. 446-450.
[75].Zhang Qilong, Pless Robert. Self-calibration algorithms for cameras and laser range finders. In; 2004; Bellingham, WA 98227-0010, United States: International Society for Optical Engineering; 2004. p. 344-353.
[76].Cao Xiaochun, Xiao Jiangjian, Foroosh Hassan. Self-calibration using constant camera motion. In; 2006; Piscataway, NJ 08855-1331, United States: Institute of Electrical and Electronics Engineers Inc.; 2006. p. 595-598.
[77]. Habed Adlane, Boufama Boubakeur. Camera self-calibration from bivariate polynomial equations and the coplanarity constraint[J]. Image and Vision Computing. 2006, 24(5): 498-514.
[78]. Wang Pu, Gu Dong-Hua, Zhuang Chun-Hua. Camera self-calibration technique based on the foundation matrix[J]. Beijing Gongye Daxue Xuebao / Journal of Beijing University of Technology. 2007, 33(4): 362-365.
[79].Kannala Juho, Brandt Sami S., Heikkila Janne. Self-calibration of central cameras by minimizing angular error. In; 2008; Setubal, 2910-595, Portugal: Inst. for Syst. and Technol. of Inf., Control and Commun. (INSTICC); 2008. p. 28-35.
[80].Zhang Zhengyou. Flexible camera calibration by viewing a plane from unknown orientations. In; 1999; Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc.; 1999. p. 666-673.
[81]. Tsai Roger Y. VERSATILE CAMERA CALIBRATION TECHNIQUE FOR HIGH-ACCURACY 3D MACHINE VISION METROLOGY USING OFF-THE-SHELF TV CAMERAS AND LENSES[J]. IEEE Journal of Robotics and Automation. 1987, RA-3(4): 323-344.
[82].Tsai Roger Y. EFFICIENT AND ACCURATE CAMERA CALIBRATION TECHNIQUE FOR 3D MACHINE VISION. In; 1986; New York, NY, USA: IEEE; 1986. p. 364-374.
[83].Abdel-Aziz Y.I., Karara H.M. Direct linear transformation into object space coordinates in close-range photogrammetry. In: Proc Symp Close-Range Photogrammetry; 1971; 1971. p. 1-18.
[84]. Riou L., Jacquet G., Fayolle J.. Calibration method of a two-camera system in a face-to-face configuration designed for fast-flow study[J]. Journal of Flow Visualization and Image Processing. 2000, 7(2): 123-141.
[85]. A.Shashua. Algebraic function for recognition[J]. IEEE T rans PAM I. 1995, (17): 779-789.
[86].Brady M., Wang H. Corner detection for 3D vision using array processors. In; 1994: Springer-Verlag GmbH & Company KG; 1994. p. 91.
[87].Moravec H.P. Towards automatic visual obstacle avoidance. In: Proceedings of the 5th International Joint Conference on Artificial Intelligence; 1977; Carnegie-Mellon University: Pittsburgh, PA; 1977.
[88]. Smith S.M, Brady J.M. SUSAN-a new approach to low level image processing[J]. Journal of ComputerVision. 1997, 2(1): 45-78.
[89]. Trajkovic M., Hedley M. Fast corner detection[J]. Image and Vision Computing. 1998, 16(1): 75-87.
[90].Harris C.G., Stephens M.J. A Combined Corner and Edge Detector. In: Proceedings Fourth Alvey Vision Conference; 1988; Manchester; 1988. p. 147-151.
[91]. Noble J.A. Images as functions and sets[J]. Image and Vision Computer. 1992, 10(1): 19-29.
[92].Zuniga Oscar A., Haralick Robert M. CORNER DETECTION USING THE FACET MODEL. In; 1983; New York, NY, USA: IEEE; 1983. p. 30-37.
[93].Laganiere Robert. Morphological corner detection. In; 1998; Piscataway, NJ, USA: IEEE; 1998. p. 280-285.
[94]. Laganiere Robert. Morphological operator for corner detection[J]. Pattern Recognition. 1998, 31(11): 1643-1652.
[95].艾海周,武勃.图像处理、分析与机器视觉.北京:人民邮电出版社; 2003.9.
[96]. L Vincent, P Soille. Watersheds in digital spaces: an efficient algorithm based on immersion simulations[J]. IEEE Trans on Pattern Analysis and Machine Intelligence. 1991, 13(6): 583-598.
[97].Beucher S. Watershed hierarchical segmentation and waterfall algorithm: Kluwer Academic Publishers; 1994.
[98]. Higgins W E, Ojard E J. 3D images and use of markers and other topological information to reduce oversegmentations[J]. Computers in medical imaging and Graphics. 1993, (17): 387-395.
[99]. Meyer F., Beucher S. Morphological Segmentation[J]. Journal of Visual Communication on Image Representation. September 1990, 1(1): 21-46.
[100].V.Vapnik. The nature of statistical learning theory. New York: Springer-Verlag; 1995.
[101].R.Webb Andrew.统计模式识别.北京:电子工业出版社; 2004.
[102].N.Cristianini, J.S.Taylor.支持向量机导论.北京:电子工业出版社; 2005.
[103].O.Zuniga, R.M.Haralick. Corner detection using the facet model. In: Computer Vision and Pattern Recognition; 1983; Los Alamitos,CA: IEEE; 1983. p. 30~37.
[104].H.P.Moravec. Towards automatic visual obstacle avoidance. In: Proceedings of the 5th International Joint Conference on Artificial Intelligence; 1977; Carnegie-Mellon University: Pittsburgh,PA; 1977.
[105].C.G.Harris, M.J.Stephens. A Combined Corner and Edge Detector. In: Proceedings Fourth Alvey Vision Conference; 1988; Manchester; 1988. p. 147~151.
[106].郑南宁.计算机视觉与模式识别.北京:国防工业出版社; 1998.
[107].Zang Q., Klette R. Object classification and tracking in video surveillance. In: Petkov N, Westenberg MA, editors. 10th International Conference on Computer Analysis of Images and Patterns; 2003 Aug 25-27; Groningen, Netherlands; 2003. p. 198-205.
[108].O.Javed, M.Shah. Tracking and Object Classification for Automated Surveillance. In: Proc of ECCV; 2002; 2002. p. 343~357.