基于混合高斯模型和主成分分析的轨迹分析行为识别方法

doi:10.3969/j.issn.0372-2112.2016.01.021

电子学报 ›› 2016, Vol. 44 ›› Issue (1): 143-149.DOI: 10.3969/j.issn.0372-2112.2016.01.021

基于混合高斯模型和主成分分析的轨迹分析行为识别方法

田国会¹, 尹建芹^1,2, 闫云章¹, 李国栋¹

1. 山东大学控制科学与工程学院, 山东济南 250061;
2. 济南大学信息科学与工程学院山东省网络环境智能计算技术重点实验室, 山东济南 250022

收稿日期:2014-06-19 修回日期:2014-10-16 出版日期:2016-01-25
- 通讯作者:
- 尹建芹
- 作者简介:
- 田国会 男,1969年8月出生,河北河间人,教授、博士生导师.1990年、1993年和1997年分别在山东大学、山东工业大学和东北大学获理学学士、工学硕士和工学博士学位.现为山东大学服务机器人研究室主任,主要从事服务机器人、智能空间等方面的研究. E-mail:g.h.tian@sdu.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61203341,No.61075092); 山东省自然科学基金 (No.ZR2011FM011); 山东省高等学校科技发展计划 (No.J11LG01)

Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition

TIAN Guo-hui¹, YIN Jian-qin^1,2, YAN Yun-zhang¹, LI Guo-dong¹

1. School of Control Science and Engineering, Shandong University, Jinan, Shandong 250061, China;
2. Shandong Provincial Key Laboratory of Network Based Intelligent Computing, School of Information Science and Engineering, University of Jinan, Jinan, Shandong 250022, China

Received:2014-06-19 Revised:2014-10-16 Online:2016-01-25 Published:2016-01-25

摘要/Abstract

摘要：

针对家庭辅助生活应用场景下的目标意图识别和异常行为判别问题,提出了一种基于目标轨迹的行为分析方法.首先,提出了关键点和关键区域的概念,将家庭环境划分为不同的关键点和关键区域,并以此来描述和区分不同轨迹;然后,提出了利用混合高斯模型的关键点及关键区域获取算法,将轨迹转化为关键点及关键区域表示,并以此为基础进行了行为意图的识别和部分异常轨迹的判断;最后,借助主成分分析的方法弥补混合高斯聚类在异常轨迹识别方面的缺陷,提高了识别准确率.实验表明,该方法能够有效的对行为意图和异常行为进行识别.

关键词: 意图识别, 异常行为检测, 轨迹分析, 混合高斯聚类, 主成分分析

Abstract:

In order to solve the problems of human motion intention recognition and abnormal behavior detection in home environment, a trajectory analysis based algorithm is discussed in this paper.Firstly, the home environment is divided into different key points and areas, so that the motion trajectory can be described by them.Moreover, based on mixture Gaussian model, the problems of motion intention recognition and abnormal behavior detection are analyzed.Finally, the PCA algorithm is applied to improve the accuracy of abnormal behavior detection.The experimental results show the effectiveness and reliability of the above conclusions.

Key words: motion intention recognition, abnormal behavior detection, motion trajectory analysis, Gaussian mixture clustering, principal component analysis

中图分类号:

TP391

田国会, 尹建芹, 闫云章, 等. 基于混合高斯模型和主成分分析的轨迹分析行为识别方法[J]. 电子学报, 2016, 44(1): 143-149.

TIAN Guo-hui, YIN Jian-qin, YAN Yun-zhang, et al. Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition[J]. Acta Electronica Sinica, 2016, 44(1): 143-149.

参考文献

[1] 王传旭, 刘云, 厉万庆.基于时空特征点的非监督姿态建模和行为识别的算法研究[J].电子学报, 2011, 39(8):1751-1756. Wang Chuanxu, Liu Yun, Li Wanqing.Research of unsupervised posture modeling and action recognition based on spatial-temporal interesting points[J].Acta Electronica Sinica, 2011, 39 (8):1751-1756.(in Chinese)
[2] 蒋建国, 等.多摄像机视域内的目标活动分析[J].电子学报, 2014, 42 (2):306-311. Jiang Jianguo, et al.Activity analysis cross multi-Camera[J].Acta Electronica Sinica, 2014, 42 (2):306-311.(in Chinese)
[3] Lou J, Liu Q, Tan T, et al.Semantic interpretation of object activities in a surveillance system[A].The 16th International Conference on Pattern Recognition[C].USA:IEEE, 2002, 3.777-780.
[4] Buzan D, et al.Extraction and clustering of motion trajectories in video[A].The 17th International Conference on Pattern Recognition[C].USA:IEEE, 2004, 2.521-524.
[5] Hu W, Li X, Tian G, et al.An incremental DPMM-based method for trajectory clustering, modeling, and retrieval[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5):1051-1065.
[6] Restrepo J C, et al.Trajectory generation for a robotic in a robocup test scenery using Kalman filter and B-spline curves[A].XVII Symposium of Image, Signal Processing, and Artificial Vision (STSIVA)[C].USA:IEEE, 2012.110-115.
[7] Dyana A, et al.Combining features for shape and motion trajectory of video objects for efficient content based video retrieval[A].International Conference on Advances in Pattern Recognition[C].USA:IEEE, 2009.113-116.
[8] Kolesnikov A.Efficientonline algorithms for the polygonal approximation of trajectory data[A].The 2th IEEE International Conference on Mobile Data Management (MDM)[C].USA:IEEE, 2011, 1.49-57.
[9] Naftel A, Khalid S.Motion trajectory learning in the DFT-coefficient feature space[A].IEEE International Conference on Computer Vision Systems[C].USA:IEEE, 2006.47-47.
[10] Morris B T, Trivedi M M.A survey of vision-based trajectory learning and analysis for surveillance[J].IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(8):1114-1127.
[11] Morris B, Trivedi M.Learning trajectory patterns by clustering:Experimental studies and comparative evaluation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE, 2009.312-319.
[12] Calderara S, Prati A, Cucchiara R.Mixtures of von mises distributions for people trajectory shape analysis[J].IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(4):457-471.
[13] Ratanamahatana C A, Keogh E.Three myths about dynamic time warping data mining[A].Proceedings of SIAM International Conference on Data Mining[C].USA:SIAM, 2005.506-510.
[14] Atev S, Miller G, Papanikolopoulos N P.Clustering of vehicle trajectories[J].IEEE Transactions on Intelligent Transportation Systems, 2010, 11(3):647-657.
[15] Piotto N, Conci N, De Natale F G B.Syntactic matching of trajectories for ambient intelligence applications[J].IEEE Transactions on Multimedia, 2009, 11(7):1266-1275.
[16] Choudry M U, Beach T A C, et al.A stochastic framework for movement strategy identification and analysis[J].IEEE Transactions on Human-Machine Systems, 2013, 43(3):314-327.
[17] Nascimento J C, Marques J S, Lemos J M.Modeling and classifying human activities from trajectories using a class of space-varying parametric motion fields[J].IEEE Transactions on Image Processing, 2013, 22(5):2066-2080.
[18] Kang J, Park S U, Chung M J.Online motion segmentation using spatially-constrained j-linkage in dynamic scene[A].IEEE International Conference on Robotics and Biomimetics[C].USA:IEEE, 2012.1854-1860.
[19] Saleemi I, Shafique K, Shah M.Probabilistic modeling of scene dynamics for applications in visual surveillance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(8):1472-1485.
[20] Bennewitz M, Burgard W, Thrun S.Using EM to learn motion behaviors of persons with mobile robots[A].IEEE/RSJ International Conference on Intelligent Robots and Systems[C].USA:IEEE, 2002, 1.502-507.
[21] Bashir F I, Khokhar A A, Schonfeld D.Segmented trajectory based indexing and retrieval of video data[A].Proceedings of International Conference on Image Processing[C].USA:IEEE, 2003.623-626.
[22] 尹建芹, 田国会, 等.面向家庭服务的人体动作识别[J].四川大学学报(工程科学版), 2011, 43(4):101-107. Yin Jianqin, Tian Guohui, et al.Human action recognition ori-ented to family service[J].Journal of Sichuan University (Engineering Science Edition), 2011, 43(4):101-107.(in Chinese)
[23] Fraley C.Algorithms for model-based Gaussian hierarchical clustering[J].SIAM Journal on Scientific Computing, 1998, 20(1):270-281.
[24] Pachoud S, Maggio E, Cavallaro A.Grouping motion trajectories[A].IEEE International Conference on Acoustics, Speech and Signal Processing[C].USA:IEEE, 2009.1477-1480.
[25] 桂树, 郭立, 陆海先.基于 MUGG 的轨迹建模与异常检测[J].中国科学院研究生院学报, 2013, 30(2):244-250. Gui Shu, Guo Li, Lu Haixian.MUGG-based modeling of trajectories and anomaly detection[J].Journal of Graduate University of Chinese Academy of Sciences, 2013, 30(2):244-250.(in Chinese)
[26] Akhter I, Sheikh Y, Khan S, et al.Trajectory space:A dual representation for nonrigid structure from motion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(7):1442-1456.
[27] Lee K K, Xu Y.Modeling human actions from learning[A].IEEE/RSJ International Conference on Intelligent Robots and Systems[C].USA:IEEE, 2004, 3.2787-2792.

基于混合高斯模型和主成分分析的轨迹分析行为识别方法

Gaussian Mixture Models and Principal Component Analysis Based Human Trajectory Behavior Recognition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	肜娅峰, 陈晨, 陈德运, 何勇军. 基于贝叶斯主成分分析的i-vector说话人确认方法[J]. 电子学报, 2021, 49(11): 2186-2194.
[2]	刘金平, 王杰, 唐朝晖, 贺俊宾, 谢永芳, 马天雨. 基于自适应滑窗递归稀疏主成分分析的工业过程故障监测[J]. 电子学报, 2020, 48(9): 1795-1803.
[3]	蒋留兵, 周小龙, 车俐. 基于无载波超宽带雷达的小样本人体动作识别[J]. 电子学报, 2020, 48(3): 602-615.
[4]	徐少平, 李崇禧, 林官喜, 唐祎玲, 胡凌燕. 基于主成分分析与深度神经网络的快速噪声水平估计算法[J]. 电子学报, 2019, 47(2): 274-281.
[5]	胡钢, 徐翔, 张维明, 周鋆. 基于主成分分析的网络节点重要性指标贡献评价[J]. 电子学报, 2019, 47(2): 358-365.
[6]	田文飚, 芮国胜, 董道广, 康健. 基于盲自适应KLT的蒸发波导压缩感知方法[J]. 电子学报, 2018, 46(9): 2068-2074.
[7]	宁德军, 叶培根, 刘琴, 李梅. 基于存储库数据挖掘的开源软件成功度量方法[J]. 电子学报, 2018, 46(12): 2930-2935.
[8]	常侃, 张智勇, 陈诚, 覃团发. 采用低秩与加权稀疏分解的视频前景检测算法[J]. 电子学报, 2017, 45(9): 2272-2280.
[9]	谢晓丹, 李伯虎, 柴旭东. 计算和存储空间受限下的数据稀疏核分析方法[J]. 电子学报, 2017, 45(6): 1362-1366.
[10]	顾凌云, 吕文志, 杨勇, 高军峰, 官金安, 周到. 基于PCANet和SVM的谎言测试研究[J]. 电子学报, 2016, 44(8): 1969-1973.
[11]	贾已真, 李松斌, 蒋雨欣, 戴琼兴, 邓浩江. 基于共生特性的G.729A基音调制信息隐藏的检测[J]. 电子学报, 2015, 43(8): 1513-1517.
[12]	史加荣, 周水生, 郑秀云. 多线性鲁棒主成分分析[J]. 电子学报, 2014, 42(8): 1480-1486.
[13]	王文波, 张晓东, 汪祥莉. 基于主成分分析的经验模态分解消噪方法[J]. 电子学报, 2013, 41(7): 1425-1430.
[14]	林琳, 陈虹, 陈建. 基于鲁棒听觉特征的说话人识别[J]. 电子学报, 2013, 41(3): 619-624.
[15]	蒋晔;唐振民. 短语音说话人辨认的研究[J]. 电子学报, 2011, 39(4): 953-957.