智能视频系统中若干关键技术的研究
|
摘要
在现今复杂的安全形式和迫切的市场需求共同推动下,智能视频技术作为一种全新的安全监管手段,已成为近年来信息科学和安防技术领域中的研究和应用热点。智能视频将传统视频监控技术和现代模式识别图形图像处理算法结合,在无需外界干预的情况下,通过对视频数据流的分析,自动完成场景中目标的检测和跟踪,并在此基础上进行目标行为理解和辅助决策,实现人不在回路中的智能监控,带来了监控技术的革命。
尽管智能视频的基本流程很早就被提出,相关核心算法也已经过了较长时间的发展,但智能视频技术在实际应用中仍然面临一些困难：现有算法易受真实环境中光照变化等各种干扰因素的影响,目标的特殊运动状态以及与背景环境区分性不佳同样会导致算法性能的急剧下降。因此,能有效应对复杂背景条件和目标特殊运动状态、准确高效且稳定性好的运动目标检测与跟踪算法仍将是很长一段时间内研究者们追求的目标。本文立足于智能视频分析技术的应用研究,对智能视频系统中的运动目标检测和目标跟踪等若干核心关键问题进行研究,全文涉及到的主要工作包括以下几方面：
1.针对现有传统GMM算法应对低速目标时易出现前景破碎的性能局限,提出了基于前景模型匹配和短时稳定度的运动目标检测算法。算法对传统GMM算法中背景模型匹配失败时生成的前景模型加以利用并引入前景模型匹配和更新机制防止前景模型向背景模型转换导致的慢速目标漏检,同时提出短时稳定度指标衡量一段时间内的像素值波动以应对低区分性目标。实验结果表明短时稳定度和前景模型结合增强了算法对低速低区分性目标的适应性。
2.提出了一种基于前景模型匹配和短时稳定度的遗留物检测算法。遗留物是慢速目标的极限情况,算法中使用前景模型表征遗留物,并以最高的优先级保证其先于背景模型和后来像素值进行匹配,降低了背景模型与遗留物误匹配的错误风险,防止遗留物被背景吸收。多场景下的遗留物检测实验结果验证了算法的可行性。
3.在多维统计信号分析理论框架下提出了基于十六通道独立分量分析算法并综合四种不同观测信号生成方式的运动目标检测算法。独立分量分析和主分量分析算法是现今较有代表性的多维统计信号分析方法,现有基于独立分量分析和主分量分析的运动目标检测算法大多使用单一观测信号生成方式和双通道信号进行检测,无法为前景分离提供更多有效信息,常导致目标检测不完整。大量的对比实验验证了不同通道数和观测信号生成方式下ICA算法的检测性能差异,证明了使用大通道数和多种观测信号生成方式带来的检测性能提升,同时也验证了多维统计方法和其他多种运动目标检测方法在算法特性上存在的差异。
4.针对现有基于Meanshift的目标跟踪算法使用固定量化阶数生成核直方图的问题,提出了使用直方图动态量化级的Meanshift目标跟踪算法。算法在大景深场景中根据目标尺寸的变化动态改变直方图阶数,并使用动态时间规整算法进行不同维度特征的匹配。对比实验结果表明改进算法能在大景深场景中自动调节量化级阶数,并以此达到更低的平均帧处理耗时。
5.作为对前述理论的综合和工程化运用,在上述智能视频核心算法的基础上设计实现了一套智能视频系统。按照智能视频的一般流程分别给出了各个模块的开发过程并在此基础上集成为一套具备智能监控功能的实用化系统。系统可以实现对多通道视频数据的实时智能监控,具有虚拟警戒区域设置、入侵报警、关键帧保存、入侵视频回放和环境参数集成显示等功能,对智能视频系统的具体功能和应用价值进行了更直观的演示验证。
Motivated by today's complex security situation and urgent application requirements, intelligent video technology, as a new method for security supervision, has become a hotspot in both scientific research and engineering technology. Intelligent video surveillance technology combines traditional video surveillance techniques with modern pattern recognition and graphics/image processing algorithms, it automatically detects and tracks objects by analyzing the video stream without any manual intervention. Even more, behavior understanding and assistant decision-making can be achieved based on the objects'information obtained from detection/tracking module. Intelligent video surveillance technology brings a Man-Not-in-the-Loop automatic monitoring, which leads to a revolution in video surveillance technology.
Although the standard flow of intelligent video has been proposed and the core algorithm has also been developed for a long time, the application of intelligent video technology still faces some difficulties:current algorithms are vulnerable to a variety of interfering factors such as illumination changing in real environment, the object's special moving pattern as well as its indistinguishable surface may also lead to a sharp decline in performance. Therefore, researchers are still looking forward to more effective and stable algorithms which are capable of precisely dealing with complex background and special motion patterns in object detection and tracking. In this dissertation, core algorithms in intelligent video system such as moving objects detection and tracking are researched, the research work in this dissertation mainly includes the following aspects:
1. Aiming at the problem that existing GMM algorithm prone to get broken target when dealing with slowly moving object, a moving object detection algorithm based on foreground model matching and short-term stability measure was proposed. Potential foreground models that generated at each pixel were used to match the incoming pixel and a matching mechanism was developed to update the foreground models. Meanwhile, the short-term stability measure was employed to deal with foreground component which was fluctuating in its neighboring region. Experimental results showed that the combination of foreground matching and short-term stability measure enhanced the adaptability to slowly moving objects.
2. An abandoned object detection algorithm based on foreground model matching and short-term stability measure was proposed. Abandoned object is the extreme case of slowly moving object. The proposed algorithm used foreground models to characterize the abandoned object, and ensure their the highest priority to firstly match the following pixel values rather than background model s, reducing the risk of foreground pixel mismatching the background models and hence prevent the abandoned objects being absorbed into background. Abandoned object detection results under multiple scenarios verified the feasibility of the proposed algorithm.
3. A sixteen-channel ICA based motion detection algorithm using four observation vector generation methods was proposed. Independent component analysis and principal component analysis were typical multi-dimensional statistical signal analysis methods. The existing moving object detection algorithm based on independent component analysis and principal component analysis using just single method for observation vector generation and two-channel data for separation, unable to provide more effective information for separation, and hence resulting in incomplete detection result. A large number of comparative experiments shown the difference on detection performance under different observation signal generation methods and different channel numbers, and validated the improvement by selecting larger channel number and using four different observation signal generation methods. The characteristic differences between statistical methods and a variety of other traditional methods are also verified in the experiments.
4. Aiming at existing Meanshift based object tracking algorithm using fixed quantization order to generate a histogram, an improved Meanshift object tracking algorithm using adaptive quantization order in color space was proposed. Quantization order was dynamically changed according to the size changing of the moving objects, and DTW was employed to measure the similarity of features with different length. Comparative experiments demonstrated that the improved algorithm improved the calculation flexibility and achieved a lower average per-frame time consuming.
5. As an engineering application of above theories, an intelligent video surveillance system was designed and implemented based on a set of core intelligent video algorithms. In accordance with the general flow of intelligent video processing, the detailed development process of each module were given and an intelligent video surveillance system which can be put into practical use was integrated based on the individual modules. The system realized many real-time multi-channel intelligent monitoring functions such as virtual alert line setting, intrusion alarm, key frame preservation, invasive video playback and integrated environmental parameters displaying. It well demonstrated the specific functions and application value of intelligent video surveillance system.
尽管智能视频的基本流程很早就被提出,相关核心算法也已经过了较长时间的发展,但智能视频技术在实际应用中仍然面临一些困难：现有算法易受真实环境中光照变化等各种干扰因素的影响,目标的特殊运动状态以及与背景环境区分性不佳同样会导致算法性能的急剧下降。因此,能有效应对复杂背景条件和目标特殊运动状态、准确高效且稳定性好的运动目标检测与跟踪算法仍将是很长一段时间内研究者们追求的目标。本文立足于智能视频分析技术的应用研究,对智能视频系统中的运动目标检测和目标跟踪等若干核心关键问题进行研究,全文涉及到的主要工作包括以下几方面：
1.针对现有传统GMM算法应对低速目标时易出现前景破碎的性能局限,提出了基于前景模型匹配和短时稳定度的运动目标检测算法。算法对传统GMM算法中背景模型匹配失败时生成的前景模型加以利用并引入前景模型匹配和更新机制防止前景模型向背景模型转换导致的慢速目标漏检,同时提出短时稳定度指标衡量一段时间内的像素值波动以应对低区分性目标。实验结果表明短时稳定度和前景模型结合增强了算法对低速低区分性目标的适应性。
2.提出了一种基于前景模型匹配和短时稳定度的遗留物检测算法。遗留物是慢速目标的极限情况,算法中使用前景模型表征遗留物,并以最高的优先级保证其先于背景模型和后来像素值进行匹配,降低了背景模型与遗留物误匹配的错误风险,防止遗留物被背景吸收。多场景下的遗留物检测实验结果验证了算法的可行性。
3.在多维统计信号分析理论框架下提出了基于十六通道独立分量分析算法并综合四种不同观测信号生成方式的运动目标检测算法。独立分量分析和主分量分析算法是现今较有代表性的多维统计信号分析方法,现有基于独立分量分析和主分量分析的运动目标检测算法大多使用单一观测信号生成方式和双通道信号进行检测,无法为前景分离提供更多有效信息,常导致目标检测不完整。大量的对比实验验证了不同通道数和观测信号生成方式下ICA算法的检测性能差异,证明了使用大通道数和多种观测信号生成方式带来的检测性能提升,同时也验证了多维统计方法和其他多种运动目标检测方法在算法特性上存在的差异。
4.针对现有基于Meanshift的目标跟踪算法使用固定量化阶数生成核直方图的问题,提出了使用直方图动态量化级的Meanshift目标跟踪算法。算法在大景深场景中根据目标尺寸的变化动态改变直方图阶数,并使用动态时间规整算法进行不同维度特征的匹配。对比实验结果表明改进算法能在大景深场景中自动调节量化级阶数,并以此达到更低的平均帧处理耗时。
5.作为对前述理论的综合和工程化运用,在上述智能视频核心算法的基础上设计实现了一套智能视频系统。按照智能视频的一般流程分别给出了各个模块的开发过程并在此基础上集成为一套具备智能监控功能的实用化系统。系统可以实现对多通道视频数据的实时智能监控,具有虚拟警戒区域设置、入侵报警、关键帧保存、入侵视频回放和环境参数集成显示等功能,对智能视频系统的具体功能和应用价值进行了更直观的演示验证。
Motivated by today's complex security situation and urgent application requirements, intelligent video technology, as a new method for security supervision, has become a hotspot in both scientific research and engineering technology. Intelligent video surveillance technology combines traditional video surveillance techniques with modern pattern recognition and graphics/image processing algorithms, it automatically detects and tracks objects by analyzing the video stream without any manual intervention. Even more, behavior understanding and assistant decision-making can be achieved based on the objects'information obtained from detection/tracking module. Intelligent video surveillance technology brings a Man-Not-in-the-Loop automatic monitoring, which leads to a revolution in video surveillance technology.
Although the standard flow of intelligent video has been proposed and the core algorithm has also been developed for a long time, the application of intelligent video technology still faces some difficulties:current algorithms are vulnerable to a variety of interfering factors such as illumination changing in real environment, the object's special moving pattern as well as its indistinguishable surface may also lead to a sharp decline in performance. Therefore, researchers are still looking forward to more effective and stable algorithms which are capable of precisely dealing with complex background and special motion patterns in object detection and tracking. In this dissertation, core algorithms in intelligent video system such as moving objects detection and tracking are researched, the research work in this dissertation mainly includes the following aspects:
1. Aiming at the problem that existing GMM algorithm prone to get broken target when dealing with slowly moving object, a moving object detection algorithm based on foreground model matching and short-term stability measure was proposed. Potential foreground models that generated at each pixel were used to match the incoming pixel and a matching mechanism was developed to update the foreground models. Meanwhile, the short-term stability measure was employed to deal with foreground component which was fluctuating in its neighboring region. Experimental results showed that the combination of foreground matching and short-term stability measure enhanced the adaptability to slowly moving objects.
2. An abandoned object detection algorithm based on foreground model matching and short-term stability measure was proposed. Abandoned object is the extreme case of slowly moving object. The proposed algorithm used foreground models to characterize the abandoned object, and ensure their the highest priority to firstly match the following pixel values rather than background model s, reducing the risk of foreground pixel mismatching the background models and hence prevent the abandoned objects being absorbed into background. Abandoned object detection results under multiple scenarios verified the feasibility of the proposed algorithm.
3. A sixteen-channel ICA based motion detection algorithm using four observation vector generation methods was proposed. Independent component analysis and principal component analysis were typical multi-dimensional statistical signal analysis methods. The existing moving object detection algorithm based on independent component analysis and principal component analysis using just single method for observation vector generation and two-channel data for separation, unable to provide more effective information for separation, and hence resulting in incomplete detection result. A large number of comparative experiments shown the difference on detection performance under different observation signal generation methods and different channel numbers, and validated the improvement by selecting larger channel number and using four different observation signal generation methods. The characteristic differences between statistical methods and a variety of other traditional methods are also verified in the experiments.
4. Aiming at existing Meanshift based object tracking algorithm using fixed quantization order to generate a histogram, an improved Meanshift object tracking algorithm using adaptive quantization order in color space was proposed. Quantization order was dynamically changed according to the size changing of the moving objects, and DTW was employed to measure the similarity of features with different length. Comparative experiments demonstrated that the improved algorithm improved the calculation flexibility and achieved a lower average per-frame time consuming.
5. As an engineering application of above theories, an intelligent video surveillance system was designed and implemented based on a set of core intelligent video algorithms. In accordance with the general flow of intelligent video processing, the detailed development process of each module were given and an intelligent video surveillance system which can be put into practical use was integrated based on the individual modules. The system realized many real-time multi-channel intelligent monitoring functions such as virtual alert line setting, intrusion alarm, key frame preservation, invasive video playback and integrated environmental parameters displaying. It well demonstrated the specific functions and application value of intelligent video surveillance system.
引文
[1]http://news.qq.com/a/20131105/005330.htm.
[2]李杰.智能视频监控系统的研究和应用[D].北京邮电大学,2012
[3]Dedeoglu Y. Moving object detection, tracking and classification for smart video surveillance[D]. bilkent university,2004.
[4]王晨.智能视频监控系统设计[D].南京理工大学,2007.
[5]Haritaoglu I, Harwood D, Davis L S. W 4:Real-time surveillance of people and their activities[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(8):809-830.
[6]T Tan T N, Sullivan G D, Baker K D. Model-based localisation and recognition of road vehicles[J]. International Journal of Computer Vision,1998,27(1):5-25.
[7]Wren C R, Azarbayejani A, Darrell T, et al. Pfinder:Real-time tracking of the human body[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1997,19(7):780-785.
[8]Olson T, Brill F. Moving object detection and event recognition algorithms for smart cameras[C]//Proc. DARPA Image Understanding Workshop.1997,20(5): 205-208.
[9]Lipton A J, Fujiyoshi H, Patil R S. Moving target classification and tracking from real-time video[C]//Applications of Computer Vision,1998. WACV'98. Proceedings., Fourth IEEE Workshop on. IEEE,1998:8-14.
[10]N. T. Siebel, S. Maybank. The advisor visual surveillance system. Proc. of the ECCV Workshop on Applications of Computer Vision,2004,103-111.
[11]http://www.objectvideo.com/
[12]Hu W, Tan T, Wang L, et al. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,2004,34(3):334-352.
[13]Kameda Y and Minoh M. A human motion estimation method using 3-successive video frames[C]. International conference on virtual systems and multimedia. 1996:135-140;
[14]Collins R T, Lipton A, Kanade T et al.. A system for video surveillance and monitoring:VSAM final report[R]. Technical report CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University, May 2000.
[15]D. Meyer, J. Denzler, and H. Niemann. Model based extraction of articulated objects in image sequences for gait analysis[C], Proc. IEEE Int. Conf. Image Processing,1998:78-81.
[16]Manzanera A and Richefeu J C. A new motion detection algorithm based on ∑-△ background estimation [J]. Pattern Recognition Letters,2007,28(3):320-328.
[17]Rymel J, Renno J, Greenhill D, et al. Adaptive eigen-backgrounds for object detection[C]. IEEE International Conference on Image Processing,2004,3: 1847-1850;
[18]Tsai D M and Lai S C. Independent component analysis-based background subtraction for indoor surveillance[J]. IEEE Transactions on Image Processing, 2009,18(1):158-167.
[19]Stauffer C and Grimson W E L. Adaptive background mixture models for real-time tracking[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999,246-252.
[20]KaewTraKulPong P, Bowden R. An improved adaptive background mixture model for real-time tracking with shadow detection [J]. Video-Based Surveillance Systems.2001:135-144.
[21]Sun Y, Yuan B. Hierarchical GMM to handle sharp changes in moving object detection[J]. Electronics Letters,2004,40(13):801-802.
[22]Zang Q, Klette R. Robust background subtraction and maintenance[C]//Pattern Recognition,2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE,2004,2:90-93.
[23]Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes[C]//Computer Vision,2003. Proceedings. Ninth IEEE International Conference on. IEEE,2003:1305-1312.
[24]Li L, Huang W, Gu I Y H, et al. Statistical modeling of complex backgrounds for foreground object detection[J]. Image Processing, IEEE Transactions on,2004, 13(11):1459-1472.
[25]Di Stefano L, Mattoccia S, Mola M. A change-detection algorithm based on structure and colour[C]//Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance,2003. IEEE,2003:252-259.
[26]Seki M, Wada T, Fujiwara H, et al. Background subtraction based on cooccurrence of image variations[C]//Computer Vision and Pattern Recognition, 2003. Proceedings.2003 IEEE Computer Society Conference on. IEEE,2003,2: Ⅱ-65-Ⅱ-72 vol.2.
[27]A. Elgammal, R. Duraiswami, D. Harwood and L. S. Davis, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance," Proceedings of the IEEE, vol.90, no.7, pp.1151-1163,2002
[28]Lee D S. Effective Gaussian mixture learning for video background subtraction[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005,27(5): 827-832.
[29]Harville M. A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models[M]//Computer Vision—ECCV 2002. Springer Berlin Heidelberg,2002:543-560.
[30]Lee D S, Hull J J, Erol B. A Bayesian framework for Gaussian mixture background modeling[C]//Image Processing,2003. ICIP 2003. Proceedings.2003 International Conference on. IEEE,2003,3:III-973-6 vol.2.
[31]Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Pattern Recognition,2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE,2004,2:28-31.
[32]Zhang Y, Liang Z, Hou Z, et al. An adaptive mixture gaussian background model with online background reconstruction and adjustable foreground mergence time for motion segmentation[C]//Industrial Technology,2005. ICIT 2005. IEEE International Conference on. IEEE,2005:23-27.
[33]Tan R, Huo H, Qian J, et al. Traffic video segmentation using adaptive-k gaussian mixture model[M]//Advances in Machine Vision, Image Processing, and Pattern Analysis. Springer Berlin Heidelberg,2006:125-134.
[34]Tang Z, Miao Z. Fast background subtraction and shadow elimination using improved gaussian mixture model [C]//Haptic, Audio and Visual Environments and Games,2007. HAVE 2007. IEEE International Workshop on. IEEE,2007: 38-41.
[35]K. Quast and A. Kaup. Real-time moving object detection in video sequences using spatio-temporal adaptive gaussian mixture models[C], Proceedings of the International Conference on Computer Vision Theory and Applications, Angers, France,2010:413-418.
[36]Yang, S. and Hsu, C. Background modeling from GMM likelihood combined with spatial and color coherency[C]. IEEE International Conference on Image Processing, Atlanta, GA,2006:2801-2804.
[37]J. Choi, Y.J. Yoo and J.Y. Choi. Adaptive shadow estimator for removing shadow of moving object[J], Computer. Vision and Image Understand,2010: 1017-1029.
[38]D. Salas-Gonzaleza, E. E. Kuruoglu, and D. P. Ruiz. Modelling with mixture of symmetric stable distributions using Gibbs sampling[J]. Signal Processing,2010. 90(3):774-783.
[39]朱碧婷,郑世宝.基于高斯混合模型的空间域背景分离法及阴影消除法[J].中国图象图形学报,2008,13(10)：1906-1909.
[40]马义德,朱望飞,安世霞,等.改进的基于高斯混合模型的运动目标检测方法[J].计算机应用,2007,27(10)：2544-2546.
[41]Utasi A, Czuni L. Reducing the foreground aperture problem in mixture of Gaussians based motion detection[C]//Systems, Signals and Image Processing, 2007 and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services.14th International Workshop on. IEEE,2007:157-160.
[42]H Wang, D Suter, A Re-Evaluation of Mixture-of-Gaussian background modeling.30th Internation Conference on Acoustics, Speech, and Signal Processing, Pennsylvania, USA, (2005) 1017-1020.
[43]Ahmad Fakharian, Saman Hosseini and Thomas Gustafsson. Hybrid object detection using improved gaussian mixture model[C], International Conference on Control, Automation and Systems. KINTE X, Gyeonggi-do, Korea,2011, 1475-1479.
[44]Chuan-Yu Cho, Wei-Hao Tung and Jia-Shung Wang. A crowd-filter for detection of abandoned objects in crowded area[C].3rd International Conference on Sensing Technology,2008:581-584.
[45]Chi-Hung Chuang and Jun-Wei Hsieh. Carried Object Detection Using Ratio Histogram and its Application to Suspicious Event Analysis. IEEE trans, 2009,19(6):911-916.
[46]Jianting Wen, Haifeng Gong et al.. Generative model for abandoned object detection[C]. ICIP 2009:853-856.
[47]F. Porikli. Detection of Temporarily Static Regions by Processing Video at Different Frame Rates[C].2007 IEEE conference on advanced video and signal based surveillance.2007.236-241.
[48]R. Miezianko, D. Pokrajac. Detecting and Recognizing Abandoned Objects in Crowed Environments[C]. Proc. of Computer Vision Systems.2008:241-250.
[49]孔英会,张新新,王蕴珠.智能视频监控系统中物体遗留检测方法的研究[J].计算机工程与科学,2010,32(6)：118-121.
[50]Auvinet E, Grossmann E, Rougier C, Dahmane M, et al.. Left-luggage detection using homographies and simple heuristics[J], in Proceedings of the 9th IEEE International Workshop on Performance Evaluation in Tracking and Surveillance (PETS'06), New York, USA, June,2006:51-58.
[51]Guler S, Silverstein J. A, Pushee I. H, Stationary objects in multiple object tracking[C]. Proc. IEEE Conference on Advanced Video and Signal Based Surveillance, London, U.K.2007:248-253.
[52]Stringa E, Regazzoni C. S, Real-time video-shot detection for scene surveillance applications[J], IEEE Trans. Image Processing,2000, vol.9, no.1:69-79.
[53]Chih-Yang Lin, Wen-Hao Wang, An abandoned objects management system based on the gaussian mixture model[C], International Conference on Convergence and Hybrid Information Technology,2008:169-175.
[54]Li X, Zhang C, Zhang D. Abandoned objects detection using double illumination invariant foreground masks[C]//Pattern Recognition (ICPR),2010 20th International Conference on. IEEE,2010:436-439.
[55]Lee T W. Independent component analysis[M]. Springer US,1998.
[56]Cardoso J F, Souloumiac A. Blind beamforming for non-Gaussian signals[C]//IEE Proceedings F (Radar and Signal Processing). IET Digital Library, 1993,140(6):362-370.
[57]Belouchrani A, Abed-Meraim K, Cardoso J F, et al. A blind source separation technique using second-order statist'cs[J]. Signal Processing, IEEE Transactions on,1997,45(2):434-444.
[58]Cardoso J F, Souloumiac A. Jacobi angles for simultaneous diagonalization[J]. SLAM journal on matrix analysis and applications,1996,17(1):161-164.
[59]Cardoso J F. Infomax and maximum likelihood for blind source separation. IEEE Signal Processing Letters,1997,4(4):112-114.
[60]Bell AJ, Sejnowski TJ. An information maximization approach to blind separation and blind deconvolution [J]. Neural Computation,1995,7(6):1129-1159.
[61]Lee T W, Girolami M, Sejnowski T J. Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources[J]. Neural computation,1999,11(2):417-441.
[62]Hyvarinen A, Oja E. A fast fixed-point algorithm for independent component analysis[J]. Neural computation,1997,9(7):1483-1492.
[63]Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis[J]. Neural Networks, IEEE Transactions on,1999,10(3):626-634.
[64]Bach F R, Jordan M I. Kernel independent component analysis[J]. The Journal of Machine Learning Research,2003,3:1-48.
[65]Choi S, Cichocki A, Amari S I. Flexible independent component analysis[J]. Journal of VLSI signal processing systems for signal, image and video technology, 2000,26(1-2):25-38.
[66]Georgiev P, Theis F, Cichocki A. Sparse component analysis and blind source separation of underdetermined mixtures[J]. Neural Networks, IEEE Transactions on,2005,16(4):992-996.
[67]Kim T, Eltoft T, Lee T W. Independent vector analysis:An extension of ICA to multivariate components[M]//Independent Component Analysis and Blind Signal Separation. Springer Berlin Heidelberg,2006:165-172.
[68]Makeig S, Bell A J, Jung T P, et al. Independent component analysis of electroencephalographic data[J]. Advances in neural information processing systems,1996:145-151.
[69]Delorme A, Makeig S. EEGLAB:an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J]. Journal of neuroscience methods,2004,134(1):9-21.
[70]James C J, Hesse C W. Independent component analysis for biomedical signals[J]. Physiological measurement,2005,26(1):R15.
[71]Casey M A, Westner A. Separation of mixed audio sources by independent subspace analysis[C]//Proceedings of the International Computer Music Conference.2000:154-161.
[72]Murata N, Ikeda S, Ziehe A. An approach to blind source separation based on temporal structure of speech signals[J]. Neurocomputing,2001,41(1):1-24.
[73]Lee T W, Orglmeister R. A contextual blind separation of delayed and convolved sources[C]//Acoustics, Speech, and Signal Processing,1997. ICASSP97, IEEE International Conference on. IEEE,1997,2:1199-1202.
[74]Lu C J, Lee T S, Chiu C C. Financial time series forecasting using independent component analysis and support vector regression [J]. Decision Support Systems, 2009,47(2):115-125.
[75]Lee S I, Batzoglou S. Application of independent component analysis to microarrays[J]. Genome biology,2003,4(11):R76-R76.
[76]Du H, Qi H, Wang X, et al. Band selection using independent component analysis for hyperspectral image processing[C]//Applied Imagery Pattern Recognition Workshop,2003. Proceedings.32nd. IEEE,2003:93-98.
[77]付毓生,谢艳,皮亦鸣,侯印鸣.基于独立分量分析的极化SAR图像非监督分类方法[J].电波科学学报2007.4 22(2)：255-260.
[78]刘喜武,刘洪,李幼铭.独立分量分析及其在地震信息处理中应用初探[J].地球物理学进展,2003,18(1)：090-096.
[79]Farid H, Adelson E H. Separating reflections from images by use of independent component analysis[J]. JOSAA,1999,16(9):2136-2145.
[80]Umeyama S, Godin G. Separation of diffuse and specular components of surface reflection by use of polarization and statistical analysis of images[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(5):639-647.
[81]Bartlett M S, Movellan J R, Sejnowski T J. Face recognition by independent component analysis[J]. Neural Networks, IEEE Transactions on,2002,13(6): 1450-1464.
[82]Draper B A, Baek K, Bartlett M S, et al. Recognizing faces with PCA and ICA[J]. Computer vision and image understanding,2003,91(1):115-137.
[83]van Hateren J H, Ruderman D L. Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex[J]. Proceedings of the Royal Society of London. Series B: Biological Sciences,1998,265(1412):2315-2320.
[84]Umeyama S. Blind deconvolution of images using Gabor filters and independent component analysis[C]//Proc. Symp. Independent Component Analysis and Blind Signal Separation.2003:319-324.
[85]Gonzalez-Serrano F J, Molina-Bulla H Y, Murillo-Fuentes J J. Independent component analysis applied to digital image watermarking[C]//Acoustics, Speech, and Signal Processing,2001. Proceedings.(ICASSP'01).2001 IEEE International Conference on. IEEE,2001,3:1997-2000.
[86]Yamazaki M, Xu G, Chen Y W. Detection of moving objects by independent component analysis[M]//Computer Vision-ACCV 2006. Springer Berlin Heidelberg,2006:467-478.
[87]Tsai D M, Lai S C. Independent component analysis-based background subtraction for indoor surveillance[J]. Image Processing, IEEE Transactions on, 2009,18(1):158-167.
[88]Jimenez-Hernandez H. Background subtraction approach based on independent component analysis[J]. Sensors,2010,10(6):6092.
[89]Cardoso J F. Source separation using higher order moments[C]//Acoustics, Speech, and Signal Processing,1989. ICASSP-89.,1989 International Conference on. IEEE,1989:2109-2112.
[90]Aapo Hyvarinen, Juha Karthunen, Erkki Oja. Independent Component Analysis[M]. John Wiley and Sons Inc.,2001.
[91]Yang H H et al.1997. Adaptive on-line learning algorithm for blind separation: maximum entropy and minimum mutual information. Neura Networks,9(67): 1457-1481.
[92]Cootes T F, Edwards G J, Taylor C J. Active appearance models[M]//Computer Vision—ECCV'98. Springer Berlin Heidelberg,1998:484-498.
[93]Oliver N M, Rosario B, Pentland A P. A Bayesian computer vision system for modeling human interactions[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(8):831-843.
[94]De la Torre F, Black M J. Robust principal component analysis for computer vision[C]//Computer Vision,2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. IEEE,2001,1:362-369.
[95]Skocaj D, Leonardis A. Weighted and robust incremental method for subspace learning[C]//Computer Vision,2003. Proceedings. Ninth IEEE International Conference on. IEEE,2003:1494-1501.
[96]Li Y. On incremental and robust subspace learning[J]. Pattern recognition,2004, 37(7):1509-1518.
[97]Rymel J, Renno J, Greenhill D, et al. Adaptive eigen-backgrounds for object detection[C]//Image Processing,2004. ICIP'04.2004 International Conference on. IEEE,2004,3:1847-1850.
[98]Li R, Chen Y, Zhang X. Fast robust eigen-background updating for foreground detection[C]//Image Processing,2006 IEEE International Conference on. IEEE, 2006:1833-1836.
[99]Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transactions on Information Theory,1975,21(1):32-40.
[100]Cheng Y. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[101]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(5):603-619.
[102]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[103]Collins R T. Mean-shift blob tracking through scale space[C]//Computer Vision and Pattern Recognition,2003. Proceedings.2003 IEEE Computer Society Conference on. IEEE,2003,2:11-234-40 vol.2.
[104]Zhou H, Yuan Y, Shi C. Object tracking using SIFT features and mean shift[J]. Computer Vision and Image Understanding,2009,113(3):345-352.
[105]Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf. on ComputerVision and Pattern Recognition, Vol.2, pp.234-240,2003.
[106]Leichter I, Lindenbaum M, Rivlin E. Mean shift tracking with multiple reference color histograms[J]. Computer Vision and Image Understanding,2010, 114(3):400-408.
[107]Zivkovic Z, Krose B. An EM-like algorithm for color-histogram-based object tracking[C]//Computer Vision and Pattern Recognition,2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on. IEEE,2004,1: I-798-I-803.
[108]YANG C,DURASISWAMI R,DAVIS L. Efficient mean-shift tracking via a new similaritymeasure[C].In Proc IEEE Conf on Computer Vision and Pattern Recognition, San Dicgo:CA,2005,1:176-183.
[109]Schweitzer H, Bell J W, Wu F. Very fast template matching[C]//European Conference on Computer Vision,2002,358-372.
[110]Yang C, Duraiswami R, Gumerov N A, et al. Improved fast gauss transform and efficient kernel density estimation[C]//Proceedings of Ninth IEEE International Conference on Computer Vision. Washington DC:IEEE Society Press,2003:664-671.
[111]Scott D W. Multivariate density estimation:theory, practice, and visualization[M]. Wiley, com,2009.
[112]Wegman E J. Nonparametric probability density estimation:I. A summary of available methods[J]. Technometrics,1972,14(3):533-546.
[113]Izenman A J. Review Papers:Recent Developments in Nonparametric Density Estimation[Jj. Journal of the American Statistical Association,1991, 86(413):205-224.
[114]Sheather S J, Jones M C.A reliable data-based bandwidth selection method for kernel density estimation[J]. Journal of the Royal Statistical Society, Series B, 1991,53(3):683-690.
[115]Bradski G R. Computer vision face tracking for use in a perceptual user interface[J].1998.
[116]Han R, Jing Z, Li Y. Kernel-based visual tracking with continuous adaptive distribution[J]. Optical Engineering,2009,48(5):050501-050501-3.
[117]Kruskal J B. An overview of sequence comparison:Time warps, string edits, and macromolecules[J]. SIAM review,1983,25(2):201-237.
[2]李杰.智能视频监控系统的研究和应用[D].北京邮电大学,2012
[3]Dedeoglu Y. Moving object detection, tracking and classification for smart video surveillance[D]. bilkent university,2004.
[4]王晨.智能视频监控系统设计[D].南京理工大学,2007.
[5]Haritaoglu I, Harwood D, Davis L S. W 4:Real-time surveillance of people and their activities[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(8):809-830.
[6]T Tan T N, Sullivan G D, Baker K D. Model-based localisation and recognition of road vehicles[J]. International Journal of Computer Vision,1998,27(1):5-25.
[7]Wren C R, Azarbayejani A, Darrell T, et al. Pfinder:Real-time tracking of the human body[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1997,19(7):780-785.
[8]Olson T, Brill F. Moving object detection and event recognition algorithms for smart cameras[C]//Proc. DARPA Image Understanding Workshop.1997,20(5): 205-208.
[9]Lipton A J, Fujiyoshi H, Patil R S. Moving target classification and tracking from real-time video[C]//Applications of Computer Vision,1998. WACV'98. Proceedings., Fourth IEEE Workshop on. IEEE,1998:8-14.
[10]N. T. Siebel, S. Maybank. The advisor visual surveillance system. Proc. of the ECCV Workshop on Applications of Computer Vision,2004,103-111.
[11]http://www.objectvideo.com/
[12]Hu W, Tan T, Wang L, et al. A survey on visual surveillance of object motion and behaviors[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,2004,34(3):334-352.
[13]Kameda Y and Minoh M. A human motion estimation method using 3-successive video frames[C]. International conference on virtual systems and multimedia. 1996:135-140;
[14]Collins R T, Lipton A, Kanade T et al.. A system for video surveillance and monitoring:VSAM final report[R]. Technical report CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University, May 2000.
[15]D. Meyer, J. Denzler, and H. Niemann. Model based extraction of articulated objects in image sequences for gait analysis[C], Proc. IEEE Int. Conf. Image Processing,1998:78-81.
[16]Manzanera A and Richefeu J C. A new motion detection algorithm based on ∑-△ background estimation [J]. Pattern Recognition Letters,2007,28(3):320-328.
[17]Rymel J, Renno J, Greenhill D, et al. Adaptive eigen-backgrounds for object detection[C]. IEEE International Conference on Image Processing,2004,3: 1847-1850;
[18]Tsai D M and Lai S C. Independent component analysis-based background subtraction for indoor surveillance[J]. IEEE Transactions on Image Processing, 2009,18(1):158-167.
[19]Stauffer C and Grimson W E L. Adaptive background mixture models for real-time tracking[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,1999,246-252.
[20]KaewTraKulPong P, Bowden R. An improved adaptive background mixture model for real-time tracking with shadow detection [J]. Video-Based Surveillance Systems.2001:135-144.
[21]Sun Y, Yuan B. Hierarchical GMM to handle sharp changes in moving object detection[J]. Electronics Letters,2004,40(13):801-802.
[22]Zang Q, Klette R. Robust background subtraction and maintenance[C]//Pattern Recognition,2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE,2004,2:90-93.
[23]Monnet A, Mittal A, Paragios N, et al. Background modeling and subtraction of dynamic scenes[C]//Computer Vision,2003. Proceedings. Ninth IEEE International Conference on. IEEE,2003:1305-1312.
[24]Li L, Huang W, Gu I Y H, et al. Statistical modeling of complex backgrounds for foreground object detection[J]. Image Processing, IEEE Transactions on,2004, 13(11):1459-1472.
[25]Di Stefano L, Mattoccia S, Mola M. A change-detection algorithm based on structure and colour[C]//Proceedings. IEEE Conference on Advanced Video and Signal Based Surveillance,2003. IEEE,2003:252-259.
[26]Seki M, Wada T, Fujiwara H, et al. Background subtraction based on cooccurrence of image variations[C]//Computer Vision and Pattern Recognition, 2003. Proceedings.2003 IEEE Computer Society Conference on. IEEE,2003,2: Ⅱ-65-Ⅱ-72 vol.2.
[27]A. Elgammal, R. Duraiswami, D. Harwood and L. S. Davis, "Background and foreground modeling using nonparametric kernel density estimation for visual surveillance," Proceedings of the IEEE, vol.90, no.7, pp.1151-1163,2002
[28]Lee D S. Effective Gaussian mixture learning for video background subtraction[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005,27(5): 827-832.
[29]Harville M. A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models[M]//Computer Vision—ECCV 2002. Springer Berlin Heidelberg,2002:543-560.
[30]Lee D S, Hull J J, Erol B. A Bayesian framework for Gaussian mixture background modeling[C]//Image Processing,2003. ICIP 2003. Proceedings.2003 International Conference on. IEEE,2003,3:III-973-6 vol.2.
[31]Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction[C]//Pattern Recognition,2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE,2004,2:28-31.
[32]Zhang Y, Liang Z, Hou Z, et al. An adaptive mixture gaussian background model with online background reconstruction and adjustable foreground mergence time for motion segmentation[C]//Industrial Technology,2005. ICIT 2005. IEEE International Conference on. IEEE,2005:23-27.
[33]Tan R, Huo H, Qian J, et al. Traffic video segmentation using adaptive-k gaussian mixture model[M]//Advances in Machine Vision, Image Processing, and Pattern Analysis. Springer Berlin Heidelberg,2006:125-134.
[34]Tang Z, Miao Z. Fast background subtraction and shadow elimination using improved gaussian mixture model [C]//Haptic, Audio and Visual Environments and Games,2007. HAVE 2007. IEEE International Workshop on. IEEE,2007: 38-41.
[35]K. Quast and A. Kaup. Real-time moving object detection in video sequences using spatio-temporal adaptive gaussian mixture models[C], Proceedings of the International Conference on Computer Vision Theory and Applications, Angers, France,2010:413-418.
[36]Yang, S. and Hsu, C. Background modeling from GMM likelihood combined with spatial and color coherency[C]. IEEE International Conference on Image Processing, Atlanta, GA,2006:2801-2804.
[37]J. Choi, Y.J. Yoo and J.Y. Choi. Adaptive shadow estimator for removing shadow of moving object[J], Computer. Vision and Image Understand,2010: 1017-1029.
[38]D. Salas-Gonzaleza, E. E. Kuruoglu, and D. P. Ruiz. Modelling with mixture of symmetric stable distributions using Gibbs sampling[J]. Signal Processing,2010. 90(3):774-783.
[39]朱碧婷,郑世宝.基于高斯混合模型的空间域背景分离法及阴影消除法[J].中国图象图形学报,2008,13(10)：1906-1909.
[40]马义德,朱望飞,安世霞,等.改进的基于高斯混合模型的运动目标检测方法[J].计算机应用,2007,27(10)：2544-2546.
[41]Utasi A, Czuni L. Reducing the foreground aperture problem in mixture of Gaussians based motion detection[C]//Systems, Signals and Image Processing, 2007 and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services.14th International Workshop on. IEEE,2007:157-160.
[42]H Wang, D Suter, A Re-Evaluation of Mixture-of-Gaussian background modeling.30th Internation Conference on Acoustics, Speech, and Signal Processing, Pennsylvania, USA, (2005) 1017-1020.
[43]Ahmad Fakharian, Saman Hosseini and Thomas Gustafsson. Hybrid object detection using improved gaussian mixture model[C], International Conference on Control, Automation and Systems. KINTE X, Gyeonggi-do, Korea,2011, 1475-1479.
[44]Chuan-Yu Cho, Wei-Hao Tung and Jia-Shung Wang. A crowd-filter for detection of abandoned objects in crowded area[C].3rd International Conference on Sensing Technology,2008:581-584.
[45]Chi-Hung Chuang and Jun-Wei Hsieh. Carried Object Detection Using Ratio Histogram and its Application to Suspicious Event Analysis. IEEE trans, 2009,19(6):911-916.
[46]Jianting Wen, Haifeng Gong et al.. Generative model for abandoned object detection[C]. ICIP 2009:853-856.
[47]F. Porikli. Detection of Temporarily Static Regions by Processing Video at Different Frame Rates[C].2007 IEEE conference on advanced video and signal based surveillance.2007.236-241.
[48]R. Miezianko, D. Pokrajac. Detecting and Recognizing Abandoned Objects in Crowed Environments[C]. Proc. of Computer Vision Systems.2008:241-250.
[49]孔英会,张新新,王蕴珠.智能视频监控系统中物体遗留检测方法的研究[J].计算机工程与科学,2010,32(6)：118-121.
[50]Auvinet E, Grossmann E, Rougier C, Dahmane M, et al.. Left-luggage detection using homographies and simple heuristics[J], in Proceedings of the 9th IEEE International Workshop on Performance Evaluation in Tracking and Surveillance (PETS'06), New York, USA, June,2006:51-58.
[51]Guler S, Silverstein J. A, Pushee I. H, Stationary objects in multiple object tracking[C]. Proc. IEEE Conference on Advanced Video and Signal Based Surveillance, London, U.K.2007:248-253.
[52]Stringa E, Regazzoni C. S, Real-time video-shot detection for scene surveillance applications[J], IEEE Trans. Image Processing,2000, vol.9, no.1:69-79.
[53]Chih-Yang Lin, Wen-Hao Wang, An abandoned objects management system based on the gaussian mixture model[C], International Conference on Convergence and Hybrid Information Technology,2008:169-175.
[54]Li X, Zhang C, Zhang D. Abandoned objects detection using double illumination invariant foreground masks[C]//Pattern Recognition (ICPR),2010 20th International Conference on. IEEE,2010:436-439.
[55]Lee T W. Independent component analysis[M]. Springer US,1998.
[56]Cardoso J F, Souloumiac A. Blind beamforming for non-Gaussian signals[C]//IEE Proceedings F (Radar and Signal Processing). IET Digital Library, 1993,140(6):362-370.
[57]Belouchrani A, Abed-Meraim K, Cardoso J F, et al. A blind source separation technique using second-order statist'cs[J]. Signal Processing, IEEE Transactions on,1997,45(2):434-444.
[58]Cardoso J F, Souloumiac A. Jacobi angles for simultaneous diagonalization[J]. SLAM journal on matrix analysis and applications,1996,17(1):161-164.
[59]Cardoso J F. Infomax and maximum likelihood for blind source separation. IEEE Signal Processing Letters,1997,4(4):112-114.
[60]Bell AJ, Sejnowski TJ. An information maximization approach to blind separation and blind deconvolution [J]. Neural Computation,1995,7(6):1129-1159.
[61]Lee T W, Girolami M, Sejnowski T J. Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources[J]. Neural computation,1999,11(2):417-441.
[62]Hyvarinen A, Oja E. A fast fixed-point algorithm for independent component analysis[J]. Neural computation,1997,9(7):1483-1492.
[63]Hyvarinen A. Fast and robust fixed-point algorithms for independent component analysis[J]. Neural Networks, IEEE Transactions on,1999,10(3):626-634.
[64]Bach F R, Jordan M I. Kernel independent component analysis[J]. The Journal of Machine Learning Research,2003,3:1-48.
[65]Choi S, Cichocki A, Amari S I. Flexible independent component analysis[J]. Journal of VLSI signal processing systems for signal, image and video technology, 2000,26(1-2):25-38.
[66]Georgiev P, Theis F, Cichocki A. Sparse component analysis and blind source separation of underdetermined mixtures[J]. Neural Networks, IEEE Transactions on,2005,16(4):992-996.
[67]Kim T, Eltoft T, Lee T W. Independent vector analysis:An extension of ICA to multivariate components[M]//Independent Component Analysis and Blind Signal Separation. Springer Berlin Heidelberg,2006:165-172.
[68]Makeig S, Bell A J, Jung T P, et al. Independent component analysis of electroencephalographic data[J]. Advances in neural information processing systems,1996:145-151.
[69]Delorme A, Makeig S. EEGLAB:an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J]. Journal of neuroscience methods,2004,134(1):9-21.
[70]James C J, Hesse C W. Independent component analysis for biomedical signals[J]. Physiological measurement,2005,26(1):R15.
[71]Casey M A, Westner A. Separation of mixed audio sources by independent subspace analysis[C]//Proceedings of the International Computer Music Conference.2000:154-161.
[72]Murata N, Ikeda S, Ziehe A. An approach to blind source separation based on temporal structure of speech signals[J]. Neurocomputing,2001,41(1):1-24.
[73]Lee T W, Orglmeister R. A contextual blind separation of delayed and convolved sources[C]//Acoustics, Speech, and Signal Processing,1997. ICASSP97, IEEE International Conference on. IEEE,1997,2:1199-1202.
[74]Lu C J, Lee T S, Chiu C C. Financial time series forecasting using independent component analysis and support vector regression [J]. Decision Support Systems, 2009,47(2):115-125.
[75]Lee S I, Batzoglou S. Application of independent component analysis to microarrays[J]. Genome biology,2003,4(11):R76-R76.
[76]Du H, Qi H, Wang X, et al. Band selection using independent component analysis for hyperspectral image processing[C]//Applied Imagery Pattern Recognition Workshop,2003. Proceedings.32nd. IEEE,2003:93-98.
[77]付毓生,谢艳,皮亦鸣,侯印鸣.基于独立分量分析的极化SAR图像非监督分类方法[J].电波科学学报2007.4 22(2)：255-260.
[78]刘喜武,刘洪,李幼铭.独立分量分析及其在地震信息处理中应用初探[J].地球物理学进展,2003,18(1)：090-096.
[79]Farid H, Adelson E H. Separating reflections from images by use of independent component analysis[J]. JOSAA,1999,16(9):2136-2145.
[80]Umeyama S, Godin G. Separation of diffuse and specular components of surface reflection by use of polarization and statistical analysis of images[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(5):639-647.
[81]Bartlett M S, Movellan J R, Sejnowski T J. Face recognition by independent component analysis[J]. Neural Networks, IEEE Transactions on,2002,13(6): 1450-1464.
[82]Draper B A, Baek K, Bartlett M S, et al. Recognizing faces with PCA and ICA[J]. Computer vision and image understanding,2003,91(1):115-137.
[83]van Hateren J H, Ruderman D L. Independent component analysis of natural image sequences yields spatio-temporal filters similar to simple cells in primary visual cortex[J]. Proceedings of the Royal Society of London. Series B: Biological Sciences,1998,265(1412):2315-2320.
[84]Umeyama S. Blind deconvolution of images using Gabor filters and independent component analysis[C]//Proc. Symp. Independent Component Analysis and Blind Signal Separation.2003:319-324.
[85]Gonzalez-Serrano F J, Molina-Bulla H Y, Murillo-Fuentes J J. Independent component analysis applied to digital image watermarking[C]//Acoustics, Speech, and Signal Processing,2001. Proceedings.(ICASSP'01).2001 IEEE International Conference on. IEEE,2001,3:1997-2000.
[86]Yamazaki M, Xu G, Chen Y W. Detection of moving objects by independent component analysis[M]//Computer Vision-ACCV 2006. Springer Berlin Heidelberg,2006:467-478.
[87]Tsai D M, Lai S C. Independent component analysis-based background subtraction for indoor surveillance[J]. Image Processing, IEEE Transactions on, 2009,18(1):158-167.
[88]Jimenez-Hernandez H. Background subtraction approach based on independent component analysis[J]. Sensors,2010,10(6):6092.
[89]Cardoso J F. Source separation using higher order moments[C]//Acoustics, Speech, and Signal Processing,1989. ICASSP-89.,1989 International Conference on. IEEE,1989:2109-2112.
[90]Aapo Hyvarinen, Juha Karthunen, Erkki Oja. Independent Component Analysis[M]. John Wiley and Sons Inc.,2001.
[91]Yang H H et al.1997. Adaptive on-line learning algorithm for blind separation: maximum entropy and minimum mutual information. Neura Networks,9(67): 1457-1481.
[92]Cootes T F, Edwards G J, Taylor C J. Active appearance models[M]//Computer Vision—ECCV'98. Springer Berlin Heidelberg,1998:484-498.
[93]Oliver N M, Rosario B, Pentland A P. A Bayesian computer vision system for modeling human interactions[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(8):831-843.
[94]De la Torre F, Black M J. Robust principal component analysis for computer vision[C]//Computer Vision,2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on. IEEE,2001,1:362-369.
[95]Skocaj D, Leonardis A. Weighted and robust incremental method for subspace learning[C]//Computer Vision,2003. Proceedings. Ninth IEEE International Conference on. IEEE,2003:1494-1501.
[96]Li Y. On incremental and robust subspace learning[J]. Pattern recognition,2004, 37(7):1509-1518.
[97]Rymel J, Renno J, Greenhill D, et al. Adaptive eigen-backgrounds for object detection[C]//Image Processing,2004. ICIP'04.2004 International Conference on. IEEE,2004,3:1847-1850.
[98]Li R, Chen Y, Zhang X. Fast robust eigen-background updating for foreground detection[C]//Image Processing,2006 IEEE International Conference on. IEEE, 2006:1833-1836.
[99]Fukunaga K, Hostetler L. The estimation of the gradient of a density function, with applications in pattern recognition[J]. IEEE Transactions on Information Theory,1975,21(1):32-40.
[100]Cheng Y. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[101]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,24(5):603-619.
[102]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577.
[103]Collins R T. Mean-shift blob tracking through scale space[C]//Computer Vision and Pattern Recognition,2003. Proceedings.2003 IEEE Computer Society Conference on. IEEE,2003,2:11-234-40 vol.2.
[104]Zhou H, Yuan Y, Shi C. Object tracking using SIFT features and mean shift[J]. Computer Vision and Image Understanding,2009,113(3):345-352.
[105]Collins R. Mean-shift blob tracking through scale space[C]. In Proc. Of IEEE Conf. on ComputerVision and Pattern Recognition, Vol.2, pp.234-240,2003.
[106]Leichter I, Lindenbaum M, Rivlin E. Mean shift tracking with multiple reference color histograms[J]. Computer Vision and Image Understanding,2010, 114(3):400-408.
[107]Zivkovic Z, Krose B. An EM-like algorithm for color-histogram-based object tracking[C]//Computer Vision and Pattern Recognition,2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on. IEEE,2004,1: I-798-I-803.
[108]YANG C,DURASISWAMI R,DAVIS L. Efficient mean-shift tracking via a new similaritymeasure[C].In Proc IEEE Conf on Computer Vision and Pattern Recognition, San Dicgo:CA,2005,1:176-183.
[109]Schweitzer H, Bell J W, Wu F. Very fast template matching[C]//European Conference on Computer Vision,2002,358-372.
[110]Yang C, Duraiswami R, Gumerov N A, et al. Improved fast gauss transform and efficient kernel density estimation[C]//Proceedings of Ninth IEEE International Conference on Computer Vision. Washington DC:IEEE Society Press,2003:664-671.
[111]Scott D W. Multivariate density estimation:theory, practice, and visualization[M]. Wiley, com,2009.
[112]Wegman E J. Nonparametric probability density estimation:I. A summary of available methods[J]. Technometrics,1972,14(3):533-546.
[113]Izenman A J. Review Papers:Recent Developments in Nonparametric Density Estimation[Jj. Journal of the American Statistical Association,1991, 86(413):205-224.
[114]Sheather S J, Jones M C.A reliable data-based bandwidth selection method for kernel density estimation[J]. Journal of the Royal Statistical Society, Series B, 1991,53(3):683-690.
[115]Bradski G R. Computer vision face tracking for use in a perceptual user interface[J].1998.
[116]Han R, Jing Z, Li Y. Kernel-based visual tracking with continuous adaptive distribution[J]. Optical Engineering,2009,48(5):050501-050501-3.
[117]Kruskal J B. An overview of sequence comparison:Time warps, string edits, and macromolecules[J]. SIAM review,1983,25(2):201-237.