视频监控中人体异常行为分析的研究与实现
|
摘要
智能视频监控系统能够从摄像头拍摄的视频图像序列中检测、跟踪和识别运动目标，继而分析理解运动目标的行为，从而完成智能安全防范的任务。视频监控中的异常行为检测能够将监控系统中大量对安防无用的信息忽略掉，从而节省大量的人力物力，是近年来被广泛关注的研究领域。它以摄像机拍摄到的视频图像序列为研究对象，以准确性较高的运动目标检测、跟踪和分类为研究基础，以实现目标的行为分析理解的研究目的。
本文基于运动目标分析和运动轨迹分析，对视频监控中的边界越线、遗留物以及人体滞留徘徊这些简单异常行为的检测算法进行了一些探索性的研究，本文的主要工作如下：
1．分析研究了作为异常分析检测基础的运动目标检测、跟踪和分类的几种主要算法。
2．分析了运动目标分析和运动轨迹分析的研究方法。在运动目标分析方面主要研究了目标区域的描述方法、运动目标的表示方法和运动目标的基本特征等方面的内容。在运动轨迹分析方面主要给出了基于距离-方向角的运动轨迹表示方法和运动轨迹曲线主方向角的求解方法。
3．采用基于运动空间的方法，结合运动目标分析和运动轨迹分析所提供的运动目标的运动特征信息，给出了边界越线和遗留物异常检测方法，以及人体滞留徘徊异常行为检测的方法。其中，改进了遗留物异常检测中背景更新的算法。
最后，本文在VC++6.0开发环境和OpenCV计算机视觉类库相结合下实现了相关算法，并对实验结果进行了分析。实验结果表明该算法能够正确、快速地实现视频图像序列中边界越线、遗留物的异常检测，以及人体滞留徘徊异常行为的检测，同时能够满足系统所需的实时性要求。
Intelligent Video Surveillance (IVS) is a kind of security technology to automate objectdetection, tracking, recognition, and activity analysis in image sequences, which are captured bycamera. The analysis and recognition of human abnormal behavior of IVS, which are being moreand more popular, can not only ignore a large of useless information, but also save a lot of humanand material resources. Its research object is the image sequences captured by camera, and it aims atunderstanding the object’s action based on object detection, tracking and recognition.
This paper studies simple human abnormal behavior of IVS such as crossing line, abandonedobject and hovering. The main contributions of this thesis are summarized as follow:
1. Make a further study on the algorithm of object detection, tracking and recognition.
2. Make a further study on the research method of motion analysis and motion trajectoryanalysis. Research on motion object analysis includes the descriptive method of object area andobject, and the motion feature of the object. Research on motion trajectory analysis includes themotion trajectory’s representation based on distance-direction angle, and the solving method ofmain direction angle.
3. This paper gives the recognition method of achieving the abnormal detection such ascrossing line and abandoned object, and recognizing the simple human abnormal behavior hovering,relying on activity analysis based on motion space and the motion feature proposed by the motionanalysis and motion trajectory analysis. Furthermore, improve the background update algorithm inhuman abnormal behavior of abandoned object.
At last, this paper accomplishes the algorithm in the environment of VC++6.0 and OpenCV,and analysis the experiment results. Experimental results certify that the algorithm can fast andaccurately achieve the abnormal detection such as crossing line and abandoned object, andrecognize the simple human abnormal behavior hovering in image sequences. In addition thealgorithm can meet the needs of real-time of the system.
本文基于运动目标分析和运动轨迹分析，对视频监控中的边界越线、遗留物以及人体滞留徘徊这些简单异常行为的检测算法进行了一些探索性的研究，本文的主要工作如下：
1．分析研究了作为异常分析检测基础的运动目标检测、跟踪和分类的几种主要算法。
2．分析了运动目标分析和运动轨迹分析的研究方法。在运动目标分析方面主要研究了目标区域的描述方法、运动目标的表示方法和运动目标的基本特征等方面的内容。在运动轨迹分析方面主要给出了基于距离-方向角的运动轨迹表示方法和运动轨迹曲线主方向角的求解方法。
3．采用基于运动空间的方法，结合运动目标分析和运动轨迹分析所提供的运动目标的运动特征信息，给出了边界越线和遗留物异常检测方法，以及人体滞留徘徊异常行为检测的方法。其中，改进了遗留物异常检测中背景更新的算法。
最后，本文在VC++6.0开发环境和OpenCV计算机视觉类库相结合下实现了相关算法，并对实验结果进行了分析。实验结果表明该算法能够正确、快速地实现视频图像序列中边界越线、遗留物的异常检测，以及人体滞留徘徊异常行为的检测，同时能够满足系统所需的实时性要求。
Intelligent Video Surveillance (IVS) is a kind of security technology to automate objectdetection, tracking, recognition, and activity analysis in image sequences, which are captured bycamera. The analysis and recognition of human abnormal behavior of IVS, which are being moreand more popular, can not only ignore a large of useless information, but also save a lot of humanand material resources. Its research object is the image sequences captured by camera, and it aims atunderstanding the object’s action based on object detection, tracking and recognition.
This paper studies simple human abnormal behavior of IVS such as crossing line, abandonedobject and hovering. The main contributions of this thesis are summarized as follow:
1. Make a further study on the algorithm of object detection, tracking and recognition.
2. Make a further study on the research method of motion analysis and motion trajectoryanalysis. Research on motion object analysis includes the descriptive method of object area andobject, and the motion feature of the object. Research on motion trajectory analysis includes themotion trajectory’s representation based on distance-direction angle, and the solving method ofmain direction angle.
3. This paper gives the recognition method of achieving the abnormal detection such ascrossing line and abandoned object, and recognizing the simple human abnormal behavior hovering,relying on activity analysis based on motion space and the motion feature proposed by the motionanalysis and motion trajectory analysis. Furthermore, improve the background update algorithm inhuman abnormal behavior of abandoned object.
At last, this paper accomplishes the algorithm in the environment of VC++6.0 and OpenCV,and analysis the experiment results. Experimental results certify that the algorithm can fast andaccurately achieve the abnormal detection such as crossing line and abandoned object, andrecognize the simple human abnormal behavior hovering in image sequences. In addition thealgorithm can meet the needs of real-time of the system.
引文
[1]王素玉,沈兰荪.智能视觉监控技术研究进展[J].中国图像图形学报. 2007, 12(9):1505-1514.
[2]孔晓东.智能视频监控技术研究[D].上海交通大学博士论文. 2008.3.
[3] Kino Y., Watanabe T., Shimosakoda Y. and Nakagawa S. Automated detection of human forvisual surveillance system[C]. In: Proc IEEE International Conference on Pattern Recognition,Vienna, 1996:865-869.
[4] Remagnino P., Tan T., Baker K. Multi-agent visual surveillance of dynamic scenes[J]. Image andVision Computing. 1998, 16(8):529-532.
[5] Collins R., et al. A system for video surveillance and monitoring: VSAM final report, CarnegieMellon University: Technical Report: CMU-RI-TR-00-12, 2000:606-610.
[6] Wren C.R., finder P. Real-time tracking of the human body[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence, 1998:425-429.
[7] Imai A., Shimada N. and Shiras Y. Hand posture estimation in complex background s byconsidering[C]. Asian Conference on Computer Vision, 2007:751-767.
[8] Fared F.D.T., Campoy J., Ambadar Z. and Cohn J.F. Temporal segmentation of facialbehavior[C]. International Conference on Computer Vision, 2007:639-651.
[9] Wael Abd-Almageed and Larry Davis. Human Detection using Iterative Feature Selection andLogistic Principal Component Analysis[C]. International Conference Robotics and Automation,2008:121-125.
[10] Vitaladevuni S. N., Kellokumpu V., and Davis L. S. Action Recognition using BallisticDynamics[J]. Computer Vision and Pattern Recognition, 2008:23-28.
[11] Abhinav Gupta, Trista Chen, Francine Chen, Don Kimber and Larry Davis. Context andObservation Driven Latent Variable Model for Human Pose Estimation[J]. Computer Visionand Pattern Recognition, 2008:246-252.
[12] Moeslund T. B., Hilton A., Kruger V. A survey of advances in vision-based human motioncapture and analysis[J]. Computer Vision and Image Understanding, 2006, 104: 90-126.
[13]胡卫明,谢丹,谭铁牛,沈俊.轨迹分布模式学习的层次自组织神经网络学习方法[J],计算机学报. 2003, 26(4):417-426
[14] Suchendra M, Bhandarkar, Xing zhiluo. Fast and robust background updating for real-timetraffic surveillance and monitoring[C]. In Proceedings of the 2005 IEEE Computer SocietyConference on Computer Vision and Pattern Recognition, Washington, 2005, 1063-1069.
[15] Eveno N, Caplier A. and Coulon P.Y. Accurate and quasi-automatic lip tracking[J]. IEEETransactions on Circuits and Systems for Video Technology. 2004, 14(5):706-715.
[16] Mukherjec D.P., Ray N. and Acton S.T. Level set analysis for leukocyte detection andtracking[J]. IEEE Transactions on Image processing. 2004, 13(4):562-572.
[17] Sang Hyun Kim. Rae-Hong Park, An Efficient Algorithm for Video Sequence Matching Usingthe Modified Hausdorff Distance and the Directed Divergence[J]. IEEE Transactions onCircuits and Systems for Video Technology, 2002, 12(7):127-131.
[18]张星明.视频图象捕获及运动检测技术的实现[J].计算机工程. 2002, 8(8):130-132.
[19] Me Kenna S, et al. Tracking groups of people[J]. Computer Vision and Image Understanding,2000, 80(l):42-56.
[20] Lee Dar-Shyang, Effective Gaussian Mixture Learning for Video Background Subtraction[J].IEEE Transactions on Pattern Analysis And Machine Intelligence, 2005, 27(5):72-75.
[21] Arseneau S, Cooperstock J. Real-time image segmentation for action recognition[C]. In: Proc.IEEE Pacific Rim Conference on Communications, Computer and Signal Processing, Victoria,Canada, 1999:86-89.
[22]聂伟乐,瞿建荣.基于OpenCV的运动目标光流算法仿真[J].应用光学. 2008,29(6):867-869.
[23] Paragios N and Deriche R. Geodesic active contours and level sets for the detection andtracking of moving objects[J]. IEEE Transactions Pattern Analysis and Machine Intelligence,2000, 22(3):266-280.
[24] Comaniciu D., Ramesh V. and Meer P. Kernel-based object tracking[J]. IEEE Transaction onPattern Analysis and Machine Intelligence, 2003, 25(5):564-577.
[25] Charalampidis D, Jilkov V P and Nguyen T M. Enhanced image feature extraction for objecttracking[C]. Proceedings of the 7th International Conference on Information Fusion, 2005:1569-1575.
[26] Nummiaro K, Koller-Meier E and Van Gool L. an adaptive color-based particle filter[J]. Imageand Vision Computing, 2003, 21(1):99-110.
[27]郑世友.动态场景图像序列中运动目标检测与跟踪[D].东南大学博士学位论文. 2005.
[28] Jorge Bandanas, Jose Miguel, Sanchez, Filiberto Pla. Motion-based segmentation and regiontracking in image sequences [J]. Pattern Recognition, 2001, 2(34):661-670.
[29] Paragios N and Deriche R. Geodesic active contours and level sets for the detection andtracking of moving objects [J]. IEEE Transactions Pattern Analysis and MachineIntelligence[C], 2000, 22(3):266-280.
[30]郭礼华,袁晓彤,李建华.基于直方图的Snake视频对象跟踪算法[J].中国图象图形学报.2005, 10(2):197-202.
[31]徐方明.视频图像中的运动目标检测算法研究[D].南京邮电大学硕士论文. 2010.
[32]郎苏娟.基于背景建模的运动目标检测[D].南京邮电大学硕士论文. 2010.
[33]徐腾飞.视频序列中基于检测的多目标跟踪研究[D].南京邮电大学硕士论文. 2011.
[34] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-timevideo[C]. In Proc IEEE Workshop on Application of Computer Vision, Princeton, NJ,1998:8-41.
[35] Hongymg Meng, Nick Pears. Descriptive temporal template features for visual motionrecognition[J]. Pattern Recognition Letters, 2009, 30(12):1049-1058.
[36] Kevin Cannons and Richard Wildes. Spatiotemporal Oriented Energy Features for Visua1Tracking[J]. Computer Vision-ACCV, 2007, 20(7):532-543.
[37]黄士崇.视频图像的运动目标分析[M].北京:国防工业出版社. 1999.
[38] Sun H., Feng T. and Tan T. Robust extraction of moving objects from image sequences[C]. In:Proc the Fourth Asian Conference on Computer Vision, Taiwan, 2000, 961-964.
[39]全晓臣.智能视频监控中的运动目标检测和跟踪技术研究[D].浙江大学硕士学位论文.2008.
[40] Oren Boiman and Michal Irani. Detecting irregularities in images and in video[C]. Proc. IEEEint. conf. Computer Vision, 2005:462-469.
[41] Du You-tian, Chen Feng, Xu wen-li, Li Yong-bin. A Survey on the Vision-based HumanMotion Recognition[J]. A Cta Electronica Sinica, 2007, 35(1):84-90.
[42] Chia-Feng Juang, and Chia-Ming Chang. Human Body Posture Classification by a NeuralFuzzy Network and Home Care System Application[J]. IEEE Transactions System, Man, andCybernetics[C], 2007, 37(6):984-994.
[43] Alessandro Mecocci, Massirno Pannozzo. A Completely Autonomous System That LearnsAnomalous Movement in Advanced Video Surveillance Applications[C]. IEEE InternationalConference on Image Processing, 2005, 2(24):586-589.
[44] Haritaoglu I., Harwood D., Davis L. S. W4: real-time surveillance of people and theiractivities[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.
[45] Neil Johnson, David Hogg. Learning the Distribution of object Trajectories for EventRecognition[J]. Image and Vision Computer, 1996, 14(8):609-615.
[46] Weiming Hu, Dan Xie, Tieniu Tan, Steve Maybank. Learning Activity Patterns Using FuzzySelf-Organizing Neural Network[J]. IEEE Transactions on Systems, Man, and CyberneticsPart B: Cybernetics, 2004, 34(3):1618-1626.
[47] Remagnino P., Tan T., Baker K. Agent Oriented Annotation in Model Based visualSurveillance[C]. Proc. of ICCV, 1998.
[48] Jung B., Sukhatme G.S. A generalized region-based approach for multi-target tracking inoutdoor environments[C]. Proceedings of 2004 IEEE International Conference on Roboticsand Automation, 2004, 3(7):2189-2195.
[49] Aaron F.Bobick, Andrew D.Wilson. A State-Based Approach to the Representation andRecognition of Gesture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997, 6(1): 43-52.
[50] Massimiliano Pierobon, Marco Marcon, August Sarti. Clustering of Human Actions usingInvariant Body Shape Descriptor and Dynamic Time Warping[J], IEEE, 2005:182-186.
[51] Lv F., Nevatia R. and Lee M.W. 3D human action recognition using spatial-temporal motiontemplates[C]. IEEE International Conference on Computer Vision Workshop on HCI, 2005,37(66): 120-130.
[52] Scott Thede M., Mary P. Harper. A second-order Hidden Markov Model for part-of-speechtagging[C]. Proceedings of the 37th annual meeting of the Association for ComputationalLinguistics on Computational Linguistics. 1999:175-182.
[53]刘继敏,史忠植.一种基于图像的信息检索方法[J].软件学报. 2000, 11(1):110-115.
[54] Liao H, Chang J, Chen L. A Localized Approach to Abandoned Luggage Detection withForeground-Mask Sampling[C]. 2008. 5th, IEEE Int. Conference on AVSS, Santa Fe, NewMexico, USA: IEEE Press, 2008:132-139.
[55]汤一平,富吉勇,陈耀宇.基于全方位计算机视觉的遗留物检测系统[J].计算机测量与控制. 2010.18(3):518-523.
[56]方瑜,滕奇志,李科伟,龚国静.复杂场景下遗留物的检测[J].计算机仿真. 2011. 28(1):281-285.
[57]王伟嘉,刘辉,沙莉,刘鑫,姜华.滞留与偷窃物体实时检测与分类算法[J].计算机应用.2007. 27(10): 2591-2594.
[2]孔晓东.智能视频监控技术研究[D].上海交通大学博士论文. 2008.3.
[3] Kino Y., Watanabe T., Shimosakoda Y. and Nakagawa S. Automated detection of human forvisual surveillance system[C]. In: Proc IEEE International Conference on Pattern Recognition,Vienna, 1996:865-869.
[4] Remagnino P., Tan T., Baker K. Multi-agent visual surveillance of dynamic scenes[J]. Image andVision Computing. 1998, 16(8):529-532.
[5] Collins R., et al. A system for video surveillance and monitoring: VSAM final report, CarnegieMellon University: Technical Report: CMU-RI-TR-00-12, 2000:606-610.
[6] Wren C.R., finder P. Real-time tracking of the human body[J]. IEEE Transactions on PatternAnalysis and Machine Intelligence, 1998:425-429.
[7] Imai A., Shimada N. and Shiras Y. Hand posture estimation in complex background s byconsidering[C]. Asian Conference on Computer Vision, 2007:751-767.
[8] Fared F.D.T., Campoy J., Ambadar Z. and Cohn J.F. Temporal segmentation of facialbehavior[C]. International Conference on Computer Vision, 2007:639-651.
[9] Wael Abd-Almageed and Larry Davis. Human Detection using Iterative Feature Selection andLogistic Principal Component Analysis[C]. International Conference Robotics and Automation,2008:121-125.
[10] Vitaladevuni S. N., Kellokumpu V., and Davis L. S. Action Recognition using BallisticDynamics[J]. Computer Vision and Pattern Recognition, 2008:23-28.
[11] Abhinav Gupta, Trista Chen, Francine Chen, Don Kimber and Larry Davis. Context andObservation Driven Latent Variable Model for Human Pose Estimation[J]. Computer Visionand Pattern Recognition, 2008:246-252.
[12] Moeslund T. B., Hilton A., Kruger V. A survey of advances in vision-based human motioncapture and analysis[J]. Computer Vision and Image Understanding, 2006, 104: 90-126.
[13]胡卫明,谢丹,谭铁牛,沈俊.轨迹分布模式学习的层次自组织神经网络学习方法[J],计算机学报. 2003, 26(4):417-426
[14] Suchendra M, Bhandarkar, Xing zhiluo. Fast and robust background updating for real-timetraffic surveillance and monitoring[C]. In Proceedings of the 2005 IEEE Computer SocietyConference on Computer Vision and Pattern Recognition, Washington, 2005, 1063-1069.
[15] Eveno N, Caplier A. and Coulon P.Y. Accurate and quasi-automatic lip tracking[J]. IEEETransactions on Circuits and Systems for Video Technology. 2004, 14(5):706-715.
[16] Mukherjec D.P., Ray N. and Acton S.T. Level set analysis for leukocyte detection andtracking[J]. IEEE Transactions on Image processing. 2004, 13(4):562-572.
[17] Sang Hyun Kim. Rae-Hong Park, An Efficient Algorithm for Video Sequence Matching Usingthe Modified Hausdorff Distance and the Directed Divergence[J]. IEEE Transactions onCircuits and Systems for Video Technology, 2002, 12(7):127-131.
[18]张星明.视频图象捕获及运动检测技术的实现[J].计算机工程. 2002, 8(8):130-132.
[19] Me Kenna S, et al. Tracking groups of people[J]. Computer Vision and Image Understanding,2000, 80(l):42-56.
[20] Lee Dar-Shyang, Effective Gaussian Mixture Learning for Video Background Subtraction[J].IEEE Transactions on Pattern Analysis And Machine Intelligence, 2005, 27(5):72-75.
[21] Arseneau S, Cooperstock J. Real-time image segmentation for action recognition[C]. In: Proc.IEEE Pacific Rim Conference on Communications, Computer and Signal Processing, Victoria,Canada, 1999:86-89.
[22]聂伟乐,瞿建荣.基于OpenCV的运动目标光流算法仿真[J].应用光学. 2008,29(6):867-869.
[23] Paragios N and Deriche R. Geodesic active contours and level sets for the detection andtracking of moving objects[J]. IEEE Transactions Pattern Analysis and Machine Intelligence,2000, 22(3):266-280.
[24] Comaniciu D., Ramesh V. and Meer P. Kernel-based object tracking[J]. IEEE Transaction onPattern Analysis and Machine Intelligence, 2003, 25(5):564-577.
[25] Charalampidis D, Jilkov V P and Nguyen T M. Enhanced image feature extraction for objecttracking[C]. Proceedings of the 7th International Conference on Information Fusion, 2005:1569-1575.
[26] Nummiaro K, Koller-Meier E and Van Gool L. an adaptive color-based particle filter[J]. Imageand Vision Computing, 2003, 21(1):99-110.
[27]郑世友.动态场景图像序列中运动目标检测与跟踪[D].东南大学博士学位论文. 2005.
[28] Jorge Bandanas, Jose Miguel, Sanchez, Filiberto Pla. Motion-based segmentation and regiontracking in image sequences [J]. Pattern Recognition, 2001, 2(34):661-670.
[29] Paragios N and Deriche R. Geodesic active contours and level sets for the detection andtracking of moving objects [J]. IEEE Transactions Pattern Analysis and MachineIntelligence[C], 2000, 22(3):266-280.
[30]郭礼华,袁晓彤,李建华.基于直方图的Snake视频对象跟踪算法[J].中国图象图形学报.2005, 10(2):197-202.
[31]徐方明.视频图像中的运动目标检测算法研究[D].南京邮电大学硕士论文. 2010.
[32]郎苏娟.基于背景建模的运动目标检测[D].南京邮电大学硕士论文. 2010.
[33]徐腾飞.视频序列中基于检测的多目标跟踪研究[D].南京邮电大学硕士论文. 2011.
[34] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-timevideo[C]. In Proc IEEE Workshop on Application of Computer Vision, Princeton, NJ,1998:8-41.
[35] Hongymg Meng, Nick Pears. Descriptive temporal template features for visual motionrecognition[J]. Pattern Recognition Letters, 2009, 30(12):1049-1058.
[36] Kevin Cannons and Richard Wildes. Spatiotemporal Oriented Energy Features for Visua1Tracking[J]. Computer Vision-ACCV, 2007, 20(7):532-543.
[37]黄士崇.视频图像的运动目标分析[M].北京:国防工业出版社. 1999.
[38] Sun H., Feng T. and Tan T. Robust extraction of moving objects from image sequences[C]. In:Proc the Fourth Asian Conference on Computer Vision, Taiwan, 2000, 961-964.
[39]全晓臣.智能视频监控中的运动目标检测和跟踪技术研究[D].浙江大学硕士学位论文.2008.
[40] Oren Boiman and Michal Irani. Detecting irregularities in images and in video[C]. Proc. IEEEint. conf. Computer Vision, 2005:462-469.
[41] Du You-tian, Chen Feng, Xu wen-li, Li Yong-bin. A Survey on the Vision-based HumanMotion Recognition[J]. A Cta Electronica Sinica, 2007, 35(1):84-90.
[42] Chia-Feng Juang, and Chia-Ming Chang. Human Body Posture Classification by a NeuralFuzzy Network and Home Care System Application[J]. IEEE Transactions System, Man, andCybernetics[C], 2007, 37(6):984-994.
[43] Alessandro Mecocci, Massirno Pannozzo. A Completely Autonomous System That LearnsAnomalous Movement in Advanced Video Surveillance Applications[C]. IEEE InternationalConference on Image Processing, 2005, 2(24):586-589.
[44] Haritaoglu I., Harwood D., Davis L. S. W4: real-time surveillance of people and theiractivities[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8):809-830.
[45] Neil Johnson, David Hogg. Learning the Distribution of object Trajectories for EventRecognition[J]. Image and Vision Computer, 1996, 14(8):609-615.
[46] Weiming Hu, Dan Xie, Tieniu Tan, Steve Maybank. Learning Activity Patterns Using FuzzySelf-Organizing Neural Network[J]. IEEE Transactions on Systems, Man, and CyberneticsPart B: Cybernetics, 2004, 34(3):1618-1626.
[47] Remagnino P., Tan T., Baker K. Agent Oriented Annotation in Model Based visualSurveillance[C]. Proc. of ICCV, 1998.
[48] Jung B., Sukhatme G.S. A generalized region-based approach for multi-target tracking inoutdoor environments[C]. Proceedings of 2004 IEEE International Conference on Roboticsand Automation, 2004, 3(7):2189-2195.
[49] Aaron F.Bobick, Andrew D.Wilson. A State-Based Approach to the Representation andRecognition of Gesture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997, 6(1): 43-52.
[50] Massimiliano Pierobon, Marco Marcon, August Sarti. Clustering of Human Actions usingInvariant Body Shape Descriptor and Dynamic Time Warping[J], IEEE, 2005:182-186.
[51] Lv F., Nevatia R. and Lee M.W. 3D human action recognition using spatial-temporal motiontemplates[C]. IEEE International Conference on Computer Vision Workshop on HCI, 2005,37(66): 120-130.
[52] Scott Thede M., Mary P. Harper. A second-order Hidden Markov Model for part-of-speechtagging[C]. Proceedings of the 37th annual meeting of the Association for ComputationalLinguistics on Computational Linguistics. 1999:175-182.
[53]刘继敏,史忠植.一种基于图像的信息检索方法[J].软件学报. 2000, 11(1):110-115.
[54] Liao H, Chang J, Chen L. A Localized Approach to Abandoned Luggage Detection withForeground-Mask Sampling[C]. 2008. 5th, IEEE Int. Conference on AVSS, Santa Fe, NewMexico, USA: IEEE Press, 2008:132-139.
[55]汤一平,富吉勇,陈耀宇.基于全方位计算机视觉的遗留物检测系统[J].计算机测量与控制. 2010.18(3):518-523.
[56]方瑜,滕奇志,李科伟,龚国静.复杂场景下遗留物的检测[J].计算机仿真. 2011. 28(1):281-285.
[57]王伟嘉,刘辉,沙莉,刘鑫,姜华.滞留与偷窃物体实时检测与分类算法[J].计算机应用.2007. 27(10): 2591-2594.