Intelligent detection and identification in fiber-optical perimeter intrusion monitoring system based on the FBG sensor network

详细信息    查看全文

• 作者：Huijuan Wu ; Ya Qian ; Wei Zhang ; Hanyu Li ; Xin Xie
• 关键词：Behavior impact classification ; fiber ; optical fence ; PIDS ; security ; FBG
• 刊名：Photonic Sensors
• 出版年：2015
• 出版时间：December 2015
• 年：2015
• 卷：5
• 期：4
• 页码：365-375
• 全文大小：1,290 KB
• 参考文献：[1]J. Geng, Y. Zou, S. Staines, M. Blake, and S. Jiang, “A real-time distributed fiber strain sensor for long-distance perimeter intruder detection,-In Optical Solutions for Homeland and National Security (Optical Society of America), U. S. A., pp. P3, 2005.
  [2]M. Szustakowski, W. Ciurapinski, N. Palka, and M. Zyczkowski, “Recent development of fibre optic sensors for perimeter security,-In Proceedings of the International Conference: Modern Problems of Radio Engineering, Telecommunications and Computer Science, Chile, pp. 158-62, 2002.
  [3]S. V. Shatalin, V. N. Treschikov, and A. J. Rogers, “Interferometric optical time-domain reflectometry for distributed optical-fiber sensing,-Applied Optics, 1998, 37(24): 5600-604.CrossRef ADS
  [4]J. Bush, C. A. Davis, P. G. Davis, A. Cekorich, and F. P. McNair, “Buried fiber intrusion detection sensor with minimal false alarm rates,-in Proc. SPIE, vol. 3489, pp. 285-95, 1998.
  [5]J. C. Juarez, E. W. Maier, K. N. Choi, and H. F. Taylor, “Distributed fiber-optic Intrusion sensor system,-Journal of Lightwave Techology, 2005, 23(6): 2081-087.CrossRef ADS
  [6]J. C. Juarez and H. F. Taylor, “Field test of a distributed fiber-optic intrusion sensor system for long perimeters,-Applied Optics, 2007, 46(11): 1968-971.CrossRef ADS
  [7]Y. J. Rao, J. Luo, Z. Ran, J. Yue, X. Luo, and Z. Zhou, “Long-distance fiber-optic F-OTDR intrusion sensing system,-in Proc. SPIE, vol. 7503, pp. 75031O--5031O-, 2009.CrossRef
  [8]F. Peng, Z. Wang, Y. Rao, and X. Jia, -06 km fully-distributed fiber-optic fence based on P-OTDR with 2nd-order Raman amplification,-in Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference (OFC/NFOEC), Anaheim, CA, pp. 1-, 2013.
  [9]A. D. Kersey, “Recent progress in Interferometric fibre sensor technology,-in Proc. SPIE, vol. 1367, pp. 2-2, 1990.CrossRef ADS
  [10]A. A. Chtcherbakov and P. L. Swart, “Polarization effects in the Sagnac-Michelson distributed disturbance location sensor,-Journal of Lightwave Technology, 1998, 16(6): 1404-412.CrossRef ADS
  [11]B. Kizlik, “Fibre optic distributed sensor in Mach-Zehnder interferometer configuration,-In Proceedings of the International Conference: Modern Problems of Radio Engineering, Telecommunications and Computer Science, Chile, pp. 128-30, 2002.
  [12]M. Szustakowski, W. M. Ciurapinski, and M. Zyczkowski, “Trends in optoelectronic perimeter security sensors,-in Proc. SPIE, vol. 6736, pp. 67360Q--7360Q-2, 2007.CrossRef ADS
  [13]L. Yuan and Y. Dong, “Loop topology based white light interferometric fiber optic sensor network for application of perimeter security,-Photonic Sensors, 2011, 1(3): 260-67.CrossRef ADS
  [14]A. D. Kersey, M. A. Davis, H. J. Partrick, M. Leblance, K. P. Koo, C. G. Askins, et al., “Fiber grating sensors,-Journal of Lightwave Technology, 1997, 15(8): 1442-463.CrossRef ADS
  [15]Y. Rao, “In-fibre Bragg grating sensors,-Measurement Science and Technology, 1997, 8(4): 355-75.CrossRef ADS
  [16]Y. Rao, “Recent progress in application of in-fiber Bragg grating sensors,-Optics and Lasers in Engineering, 1999, 31(4): 297-24.CrossRef ADS
  [17]Z. Ran, Y. Rao, N. Nie, and R. Chen, “Long-distance fiber Bragg grating sensor system based on hybrid Raman/erbium-doped fiber amplifier,-in Proc. SPIE, vol. 5855, pp. 583-86, 2005.CrossRef ADS
  [18]Q. Jiang, Y. Rao, and D. Zeng, “A fiber-optical intrusion alarm system based on quasi-distributed fiber Bragg grating sensors,-in APOS-8. 1st Asia-Pacific Optical Fiber Sensors Conference, Chengdu, China, pp. 1-, 2008.
  [19]H. Wu, Y. Rao, C. Tang, Y. Wu, and Y. Gong, “A novel FBG-based security fence enabling to detect extremely weak intrusion signals from nonequivalent sensor nodes,-Sensors and Actuators A: Physical, 2011, 167(2): 548-55.CrossRef
  [20]F. Blackmon and J. Pollock, “Blue Rose perimeter defense and security system,-in Proc. SPIE, vol. 6201, pp. 620123, 2006.CrossRef
  [21]D. Anderson, “Smart perimeter security,-Fiber-SenSys.,http://?www.?fibersensys.?com/?index.?php??option=?com_?docman&?task=?doc_?details&?gid=-5&?Itemid=-4 (2009).
  [22]H. Yan, G. Shi, Q. Wang, and S. Hao, “Identification of damaging activities for perimeter security,-in 2009 International Conference on Signal Processing Systems, Singapore, pp. 162-66, 2009.CrossRef
  [23]Y. Zhao, X. Shen, N. Georganas, and E. M. Petriu, “Part-based PCA for facial feature extraction and classification,-in IEEE International Workshop on Haptic Audio visual Environments and Games, Lecco, pp. 99-04, 2009.CrossRef
  [24]X. Han, D. Xu, and Y. Liu, “Application of principal components analysis in condenser fault diagnosis,-in The Sixth World Congress on Intelligent Control and Automation, Dalian, pp. 5666-669, 2006.
  
• 作者单位：Huijuan Wu (1)
  Ya Qian (1)
  Wei Zhang (1)
  Hanyu Li (2)
  Xin Xie (1)
  
  1. Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, 611731, China
  2. Chinese People’s Liberation Army (CPLA) Urumqi Institute of the Army, Urumqi, 830042, China
  
• 刊物类别：Physics and Astronomy
• 刊物主题：Chinese Library of Science
  Laser Technology and Physics and Photonics
  Microwaves, RF and Optical Engineering
  Measurement Science and Instrumentation
  Optics, Optoelectronics, Plasmonics and Optical Devices
  
• 出版者：University of Electronic Science and Technology of China, co-published with Springer
• ISSN：2190-7439

文摘

A real-time intelligent fiber-optic perimeter intrusion detection system (PIDS) based on the fiber Bragg grating (FBG) sensor network is presented in this paper. To distinguish the effects of different intrusion events, a novel real-time behavior impact classification method is proposed based on the essential statistical characteristics of signal’s profile in the time domain. The features are extracted by the principal component analysis (PCA), which are then used to identify the event with a K-nearest neighbor classifier. Simulation and field tests are both carried out to validate its effectiveness. The average identification rate (IR) for five sample signals in the simulation test is as high as 96.67%, and the recognition rate for eight typical signals in the field test can also be achieved up to 96.52%, which includes both the fence-mounted and the ground-buried sensing signals. Besides, critically high detection rate (DR) and low false alarm rate (FAR) can be simultaneously obtained based on the autocorrelation characteristics analysis and a hierarchical detection and identification flow. Keywords Behavior impact classification fiber-optical fence PIDS security FBG