吉林大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (4): 1286-1294.doi: 10.13229/j.cnki.jdxbgxb201704039

• 论文 • 上一篇    下一篇

视频监控的数据驱动背景模型

李志慧1, 夏英集1, 曲昭伟1, 任景琛2   

  1. 1.吉林大学 交通学院,长春 130022;
    2.北京师范大学 统计学院,北京 100875
  • 收稿日期:2016-04-28 出版日期:2017-07-20 发布日期:2017-07-20
  • 通讯作者: 曲昭伟(1962-),男,教授,博士生导师.研究方向:交通控制.E-mail:quzw@jlu.edu.cn
  • 作者简介:李志慧(1977-),男,副教授,博士.研究方向:交通视频检测与处理.E-mail:lizhih@jlu.edu.cn
  • 基金资助:
    国家自然科学基金项目(51278220); 吉林省重点科技攻关项目(20140204028SF); 吉林省科技发展计划重点项目(20130206093SF).

Data-driven background model in video surveillance

LI Zhi-hui1, XIA Ying-ji1, QU Zhao-wei1, REN Jing-chen2   

  1. 1.College of Transportation, Jilin University, Changchun 130022, China;
    2.School of Statistics, Beijing Normal University, Beijing 100875,China
  • Received:2016-04-28 Online:2017-07-20 Published:2017-07-20

RICH HTML

0   

PDF (PC)

112

摘要： 针对现有背景模型假设引起的失效问题,根据数据驱动思想,建立了一种基于数据驱动的背景模型表示方法。该方法通过全格式动态线性化的无模型自适应控制方法,引入系统的伪梯度向量,结合多步历史数据,建立背景表达和选择性更新策略,获取视频背景。实验过程通过不同场景视频序列和经典背景模型方法进行对比,实验结果表明:本文算法具有背景更新效果较好、计算量适中、鲁棒性强等优点,且克服了机理模型中对模型假设的依赖及模型失效等问题。因此,本文基于数据驱动的背景模型算法可为在线视频检测系统的背景抽取提供有力的技术支持和参考。

关键词: 计算机应用, 背景更新, 无模型自适应控制, 背景差分, 视频监控

Abstract: The current modeling assumption may induce background distortion. To solve this problem, a new background model based on data-driven theory is proposed. Model-free adaptive control method is used to express the value of the online video sequence. The slow process of background illumination change is regarded as a nonlinear time-varying system, and is expressed via dynamic linearization using pseudo-gradient vector. Then, the expression is iterated with the combination of historical data and selective background update method to complete the background model iteration process. Experiments are carried out based on different video cases. Results show that the model can get better foreground and more stable background than Kalman filter and Gaussian-mixture model. Furthermore, the data-driven method of the proposed model overcomes the disadvantages of the mechanism models, and its computational efficiency and robustness make it applicable to online video processing and detection of moving objects.

Key words: computer application, background update, model-free adaptive control, background subtraction, video surveillance

中图分类号: 

  • U495
[1] Cutler R, Davis L. View-based detection and analysis of periodic motion[C]//Fourteenth International Conference on Pattern Recognition, Brisbane, 1998: 495-500.
[2] Messelodi S, Modena C M, Segata N, et al. A Kalman filter based background updating algorithm robust to sharp illumination changes[J]. Lecture Notes in Computer Science, 2005, 3617: 163-170.
[3] Ridder C, Munkelt O, Kirchner H. Adaptive background estimation and foreground detection using Kalman-filtering[C]//Proceedings of the International Conference on Recent Advances in Mechatronics, Istanbul, 1995: 193-199.
[4] Chen J Y, Luo X L. The restoration of motion blurred images based on the background modeling[J]. Applied Mechanics & Materials, 2014, 687-691: 3591-3595.
[5] Chan A B, Mahadevan V, Vasconcelos N. Generalized Stauffer-Grimson background subtraction for dynamic scenes[J]. Machine Vision and Applications, 2011, 22(5): 751-766.
[6] Power P W, Schoonees J A. Understanding background mixture models for foreground segmentation[C]//Proceedings Image and Vision Computing, New Zealand, 2002: 267-271.
[7] Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Colorado, 1999: 247-252.
[8] Wen W, Jiang T, Gou Y F. Moving object detection based on improved background updating method for Gaussian mixture model[J]. Advanced Materials Research, 2014, 1049-1050: 1561-1565.
[9] Maddalena L, Petrosino A. A self-organizing approach to background subtraction for visual surveillance applications[J]. IEEE Transactions on Image Processing, 2008, 17(7): 1168-1177.
[10] Maddalena L, Petrosino A. A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection[J]. Neural Computing and Applications, 2009, 19(2): 179-186.
[11] Barnich O, Van Droogenbroeck M. ViBe: A Universal background subtraction algorithm for video sequences[J]. IEEE Transactions on Image Processing, 2011, 20(6): 1709-1724.
[12] Barnich O, Van Droogenbroeck M, VIBE: a powerful random technique to estimate the background in video sequences[C]//2009 IEEE International Conference on Acoustics, Speech, And Signal Processing, New York, 2009: 945-948.
[13] 侯忠生, 许建新. 数据驱动控制理论及方法的回顾和展望[J]. 自动化学报, 2009, 35(6): 650-667.
Hou Zhong-sheng, Xu Jian-xin. On data-driven control theory: the state of the art and perspective[J]. Acta Automatica Sinica, 2009, 35(6): 650-667.
[14] Chao L, Yi Z, Kun M, et al. Wide-area power system stabiliser based on model-free adaptive control[J]. IET Control Theory & Applications, 2015, 9(13): 1996-2007.
[15] 侯忠生, 董航瑞, 金尚泰. 基于坐标补偿的自动泊车系统无模型自适应控制[J]. 自动化学报, 2015, (4): 823-831.
Hou Zhong-sheng, Dong Hang-rui, Jin Shang-tai. Model-free adaptive control with coordinates compensation for automatic car parking systems. Acta Automatica Sinica, 2015, 41(4): 823-831.
[16] Zhu Yuan-ming, Hou Zhong-sheng. Controller dynamic linearisation-based model-free adaptive control framework for a class of non-linear system[J]. IET Control Theory & Applications, 2015, 9(7): 1162-1172.
[17] Kadri M B. Rejecting multiplicative input disturbance using fuzzy model-free adaptive control[J]. Arabian Journal for Science and Engineering, 2014, 39(3): 2381-2392.
[18] Xu D, Jiang B, Shi P. A novel model-free adaptive control design for multivariable industrial processes[J]. IEEE Transactions on Industrial Electronics, 2014, 61(11): 6391-6398.
[19] Hou Zhong-sheng, Zhu Yuan-ming. Controller-dynamic-linearization-based model free adaptive control for discrete-time nonlinear systems[J]. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2301-2309.
[20] 侯忠生. 无模型自适应控制的现状与展望[J]. 控制理论与应用, 2006, 23(4): 586-592.
Hou Zhong-sheng. On model-free adaptive control: the state of the art and perspective[J]. Control Theory & Applications, 2006, 23(4): 586-592.
[21] 侯忠生. 再论无模型自适应控制[J]. 系统科学与数学, 2014, 34(10): 1182-1191.
Hou Zhong-sheng. Highlight and perspective on model free adaptive control[J]. Journal of Systems Science and Complexity, 2014, 34(10): 1182-1191.
[22] 金尚泰. 无模型学习自适应控制的若干问题研究及其应用[D]. 北京: 电子信息工程学院, 北京交通大学, 2008.
Jin Shang-tai.On model free learning adaptive control and applications[D].Beijing:School of Electronic and Information Engineering,Beijing Jiaotong University,2008.
[23] 崔智高, 李艾华, 冯国彦. 动态背景下融合运动线索和颜色信息的视频目标分割算法[J]. 光电子:激光,2014(8):1548-1557.
Cui Zhi-gao, Li Ai-hua, Feng Guo-yan. A video object segmentation algorithm for dynamic bacjground combining motion cue with color information[J]. Journal of Optoelectronics:Laser,2014(8):1548-1557.
[24] 方宇强, 戴斌, 宋金泽, 等. 一种改进的基于活动轮廓和光流的运动目标分割方法[J]. 中南大学学报:自然科学版, 2011, 42(4): 1035-1042.
Fang Yu-qiang, Dai Bin, Song Jin-ze, et al. An improved moving objects segmentation method based on optical flow technique and active contour model[J]. Journal of Central South University (Science and Technology), 2011, 42(4): 1035-1042.
[25] 胡祝华, 赵瑶池, 程杰仁, 等. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报:工学版, 2014, 48(8): 1488-1495.
Hu Zhu-hua, Zhao Yao-chi, Cheng Jie-ren, et al. Moving object segmentation method based on improved DRLSE[J]. Journal of Zhejiang University(Engineering Science), 2014, 48(8): 1488-1495.
[26] 孙乐, 戴明, 李刚, 等. H.264压缩域中mean-shift聚类运动目标分割算法[J]. 光电子:激光, 2013(11):2205-2211.
Sun Le, Dai Ming, Li Gang, et al. An algorithm of mean-shift clustering-based moving object segmentation in H.264 compression domain[J]. Journal of Optoelectronics:Laser, 2013(11):2205-2211.
[27] 李静宇, 刘艳滢, 田睿, 等. 视频监控系统中的概率模型单目标跟踪框架[J]. 光学精密工程, 2015, 23(7): 2093-2099.
Li Jing-yu, Liu Yan-ying, Tian Rui, et al. Probabilistic model single target tracking framework for video surveillance system[J]. Optics and Precision Engineering, 2015, 23(7): 2093-2099.
[28] 张诚, 马华东, 傅慧源. 基于时空关联图模型的视频监控目标跟踪[J]. 北京航空航天大学学报, 2015, 41(4): 713-720.
Zhang Cheng,Ma Hua-dong,Fu Hui-yuan.Object tracking in surveillance videos using spatial-temporal correlation graph model[J].Journal of Beijing University of Aeronautics and Astronautics,2015,41(4):713-720.
[29] 朱周, 路小波. 考虑遮挡的视频车辆跟踪[J]. 东南大学学报:英文版, 2015, 31(2): 266-271.
Zhu Zhou, Lu Xiao-bo. Video-based vehicle tracking considering occlusion[J]. Journal of Southeast University (English Edition), 2015, 31(2): 266-271.
[30] Chen C C,Aggarwal J K, Ieee: An adaptive background model initialization algorithm with objects moving at different depths[C]//IEEE International Conference on Image Processing,New York,2008:2664-2667.
[31] Colombari A, Fusiello A. patch-based background initialization in heavily cluttered video[J]. IEEE Transactions on Image Processing, 2010, 19(4): 926-933.
[32] Hsiao H H, Leou J J. Background initialization and foreground segmentation for bootstrapping video sequences[J]. Eurasip Journal on Image and Video Processing, 2013: 12.
[33] Maddalena L, Petrosino A: Towards benchmarking scene background initialization[C]//ICIAP: New Trends in Image Analysis and Processing, Genova, 2015: 469-476.
[34] 李志慧, 张长海, 曲昭伟, 等. 交通流视频检测中背景初始化算法[J]. 吉林大学学报:工学版,2008,38(1):148-151.
Li Zhi-hui, Zhang Chang-hai, Qu Zhao-wei, Wei Wei, Wang Dian-hai. Background initialization algorithm in traffic flow video detection[J]. Journal of Jilin University (Engineering and Technology Edition), 2008,38(1):148-151.
[35] 赖浩喆. 潜油电泵无模型自适应控制[D]. 沈阳:沈阳工业大学电气工程学院,2015.
Lai Hao-zhe. Electrical submersible pump control based on model free adaptive control[D]. Shenyang: School of Electrical Engineering, Shenyang University of Technology, 2015.
[1] 刘富,宗宇轩,康冰,张益萌,林彩霞,赵宏伟. 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报(工学版), 2018, 48(6): 1844-1850.
[2] 王利民,刘洋,孙铭会,李美慧. 基于Markov blanket的无约束型K阶贝叶斯集成分类模型[J]. 吉林大学学报(工学版), 2018, 48(6): 1851-1858.
[3] 金顺福,王宝帅,郝闪闪,贾晓光,霍占强. 基于备用虚拟机同步休眠的云数据中心节能策略及性能[J]. 吉林大学学报(工学版), 2018, 48(6): 1859-1866.
[4] 赵东,孙明玉,朱金龙,于繁华,刘光洁,陈慧灵. 结合粒子群和单纯形的改进飞蛾优化算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1867-1872.
[5] 刘恩泽,吴文福. 基于机器视觉的农作物表面多特征决策融合病变判断算法[J]. 吉林大学学报(工学版), 2018, 48(6): 1873-1878.
[6] 欧阳丹彤, 范琪. 子句级别语境感知的开放信息抽取方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1563-1570.
[7] 刘富, 兰旭腾, 侯涛, 康冰, 刘云, 林彩霞. 基于优化k-mer频率的宏基因组聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1593-1599.
[8] 桂春, 黄旺星. 基于改进的标签传播算法的网络聚类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1600-1605.
[9] 刘元宁, 刘帅, 朱晓冬, 陈一浩, 郑少阁, 沈椿壮. 基于高斯拉普拉斯算子与自适应优化伽柏滤波的虹膜识别[J]. 吉林大学学报(工学版), 2018, 48(5): 1606-1613.
[10] 车翔玖, 王利, 郭晓新. 基于多尺度特征融合的边界检测算法[J]. 吉林大学学报(工学版), 2018, 48(5): 1621-1628.
[11] 赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.
[12] 黄辉, 冯西安, 魏燕, 许驰, 陈慧灵. 基于增强核极限学习机的专业选择智能系统[J]. 吉林大学学报(工学版), 2018, 48(4): 1224-1230.
[13] 傅文博, 张杰, 陈永乐. 物联网环境下抵抗路由欺骗攻击的网络拓扑发现算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1231-1236.
[14] 曹洁, 苏哲, 李晓旭. 基于Corr-LDA模型的图像标注方法[J]. 吉林大学学报(工学版), 2018, 48(4): 1237-1243.
[15] 侯永宏, 王利伟, 邢家明. 基于HTTP的动态自适应流媒体传输算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1244-1253.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发