基于综合特征的光纤周界安防系统 高效入侵事件识别

黄翔东; 张皓杰; 刘琨; 马春宇; 刘铁根

doi:10.7498/aps.66.124206

摘要

在光纤周界安防系统中，急需对入侵事件实现准确而高效的识别，对事件特征做简练而恰当的描述是其关键所在.本文提出一种基于综合特征的入侵事件识别方法，该方法引入全相位滤波器组将输入信号并行分解为多个频率通道，以提取这些通道的归一化功率值；进而与信号过零率相结合，构成包含时域信息、频域信息的综合特征向量；最后将该特征向量馈入径向基函数神经网络即可准确识别出攀爬、敲击、晃动、剪切四种常见的入侵动作.实验证明，本文方法相比于现有的经验模态分解方法，不仅提高了精度，而且显著加快了识别速度.

关键词:

Abstract

In an optical fiber perimeter security system, due to the fact that a large quantity of samples are collected in the process of data acquisition, this heavy data burden inevitably degrades the efficiency and accuracy of intrusion recognition. Hence, it is urgent to remove the redundancy of the collected data records, which essentially requires to describe event features in a concise and proper way. In this paper, we propose a synthesized feature based intrusion recognition method, which is especially suitable to describing the fiber intrusion vibration signals with both wide bandwidth and high nonstationarity. Firstly, the all-phase filter bank characterized by large sidelobe attenuation and high flexibility of coefficient configuration, is employed to parallelly divide the input signal into multiple frequency channels, from which the power values can be accurately calculated. Secondly, the crossing rate of the input signal is combined with these power values to construct a synthetical feature vector, in which both the time-domain information and frequency-domain information are incorporated together. Finally, these synthetical feature vectors are fed into a radial-basis-function network based classifier to recognize 4 common intrusions (climbing, knocking, waggling and cutting). Essentially, the high efficiency of our proposed scheme lies in the parallel pipeline mode of the configurable filter bank and simple calculation of features, which facilitates speeding up the intrusion recognition. The high accuracy of our proposed scheme lies in two aspects: 1) the all-phase filter bank possesses small inter-channel interference, which helps to reduce the inter-coupling between output power values; 2) the synthesis of both frequency-domain information and time-domain information ensures the completeness of feature description. Experiments show that the sensing range of the proposed scheme can reach 2.25 km. Moreover, compared with the empirical mode decomposition based method, the proposed method not only improves the precision, but also significantly speeds up the recognition.

Keywords:

作者及机构信息

1.
天津大学电气自动化与信息工程学院, 天津 300072;

2.
天津大学精密仪器与光电子工程学院, 天津 300072

通信作者: 刘琨, beiyangkl@tju.edu.cn

基金项目: 国家自然科学基金（批准号：61671012，61475114）资助的课题.

Authors and contacts

1.
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China;

2.
College of Precision Instrument and Opto-electronics Engineering, Tianjin University, Tianjin 300072, China

Corresponding author: Liu Kun, beiyangkl@tju.edu.cn

参考文献

[1]	Rangaswamy S, van Doorn E 2012 US Patent 8 232 878
[2]	Girao P M B S, Postolache O A, Faria J A B, Pereira J M C D 2001 IEEE Sens. J. 1 322
[3]	Gong H, Song H, Zhang S 2014 IEEE Sens. J. 14 777
[4]	Yu S Y, Sun S L 2008 Laser Infrared 34 345 (in Chinese) [于胜云, 孙胜利 2008 激光与红外 34 345]
[5]	Fan Z M 2008 China Security Protection 3 42 (in Chinese) [樊治敏 2008 中国安防 3 42]
[6]	Sun Q Z, Liu D M, Liu H R, He Y, Yuan J G 2006 Proc. SPIE 6344 63440K
[7]	Sun Q Z, Liu D M, Liu H R, Shum P 2007 Proc. SPIE 6781 67814D
[8]	Xie S R, Zhang M, Lai S R, Liao Y B 2010 Proc. SPIE 7677 76770A
[9]	Jiang L H, Yang R Y 2012 J. Comput. 7 1453
[10]	Juarez J C, Maier E W, Choi K N, Taylor H F 2005 IEEE J. Lightw. Technol. 23 2081
[11]	Xie S R, Zou Q L, Wang L W, Zhang M, Li Y H, Liao Y B 2011 IEEE J. Lightw. Technol. 29 362
[12]	Huang X D, Yu J, Liu K, Liu T G, Chen Q N 2014 IEEE Photon. Technol. Lett. 26 1956
[13]	Liu L, Sun W, Zhou Y, Li Y, Zheng J, Ren B T 2014 Pattern Recognition (Berlin Heidelberg: Springer) pp595-603
[14]	Mahmoud S S, Visagathilagar Y, Katsifolis 2012 Photon. Sens. 2 225
[15]	Liu K, Tian M, Liu T G, Jiang J F, Ding Z Y, Chen Q N, Ma C Y, He C, Hu H F, Zhang X Z 2015 IEEE J. Lightw. Technol. 33 4885
[16]	Li K Y, Zhao X Q, Sun X H, Wan S R 2015 Acta Phys. Sin. 64 054304 (in Chinese) [李凯彦, 赵兴群, 孙小菡, 万遂人 2015 物理学报 64 054304]
[17]	Huang X D, Jing S X, Wang Z H, Xu Y, Zheng Y Q 2015 IEEE Trans. Signal Process. 64 1173
[18]	Wang Z H, Huang X D 2009 All Phase Spectrum Analysis and Filtering Technology of Digital Signal (Beijing: Publishing House of Electronics Industry) pp14-31 (in Chinese) [王兆华, 黄翔东 2009 数字信号全相位谱分析与滤波技术 (北京:电子工业出版社) 第14-31页]
[19]	Huang X D, Wang Y D, Liu K, Liu T G, Ma C Y, Chen Q N 2016 IEEE Photon. J. 8 1
[20]	Huan H X, Hien T T H, Tue H H 2011 IEEE Trans. Neural Netw. 22 982
[21]	Lyons W B, Ewald H, Lewis E 2002 J. Mater. Process. Technol. 127 23
[22]	Huang X D, Wang Y D, Liu K, Liu T G, Ma C Y, Tian M 2016 IEEE J. Lightw. Technol. 34 5049

施引文献

[1]	Rangaswamy S, van Doorn E 2012 US Patent 8 232 878
[2]	Girao P M B S, Postolache O A, Faria J A B, Pereira J M C D 2001 IEEE Sens. J. 1 322
[3]	Gong H, Song H, Zhang S 2014 IEEE Sens. J. 14 777
[4]	Yu S Y, Sun S L 2008 Laser Infrared 34 345 (in Chinese) [于胜云, 孙胜利 2008 激光与红外 34 345]
[5]	Fan Z M 2008 China Security Protection 3 42 (in Chinese) [樊治敏 2008 中国安防 3 42]
[6]	Sun Q Z, Liu D M, Liu H R, He Y, Yuan J G 2006 Proc. SPIE 6344 63440K
[7]	Sun Q Z, Liu D M, Liu H R, Shum P 2007 Proc. SPIE 6781 67814D
[8]	Xie S R, Zhang M, Lai S R, Liao Y B 2010 Proc. SPIE 7677 76770A
[9]	Jiang L H, Yang R Y 2012 J. Comput. 7 1453
[10]	Juarez J C, Maier E W, Choi K N, Taylor H F 2005 IEEE J. Lightw. Technol. 23 2081
[11]	Xie S R, Zou Q L, Wang L W, Zhang M, Li Y H, Liao Y B 2011 IEEE J. Lightw. Technol. 29 362
[12]	Huang X D, Yu J, Liu K, Liu T G, Chen Q N 2014 IEEE Photon. Technol. Lett. 26 1956
[13]	Liu L, Sun W, Zhou Y, Li Y, Zheng J, Ren B T 2014 Pattern Recognition (Berlin Heidelberg: Springer) pp595-603
[14]	Mahmoud S S, Visagathilagar Y, Katsifolis 2012 Photon. Sens. 2 225
[15]	Liu K, Tian M, Liu T G, Jiang J F, Ding Z Y, Chen Q N, Ma C Y, He C, Hu H F, Zhang X Z 2015 IEEE J. Lightw. Technol. 33 4885
[16]	Li K Y, Zhao X Q, Sun X H, Wan S R 2015 Acta Phys. Sin. 64 054304 (in Chinese) [李凯彦, 赵兴群, 孙小菡, 万遂人 2015 物理学报 64 054304]
[17]	Huang X D, Jing S X, Wang Z H, Xu Y, Zheng Y Q 2015 IEEE Trans. Signal Process. 64 1173
[18]	Wang Z H, Huang X D 2009 All Phase Spectrum Analysis and Filtering Technology of Digital Signal (Beijing: Publishing House of Electronics Industry) pp14-31 (in Chinese) [王兆华, 黄翔东 2009 数字信号全相位谱分析与滤波技术 (北京:电子工业出版社) 第14-31页]
[19]	Huang X D, Wang Y D, Liu K, Liu T G, Ma C Y, Chen Q N 2016 IEEE Photon. J. 8 1
[20]	Huan H X, Hien T T H, Tue H H 2011 IEEE Trans. Neural Netw. 22 982
[21]	Lyons W B, Ewald H, Lewis E 2002 J. Mater. Process. Technol. 127 23
[22]	Huang X D, Wang Y D, Liu K, Liu T G, Ma C Y, Tian M 2016 IEEE J. Lightw. Technol. 34 5049

计量

文章访问数: 4764
PDF下载量: 235
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

搜索

留言板