Improved locating algorithm of railway tunnel personnel based on collaborative information fusion in Internet of Things

Abstract

With larger-scale of railway construction in China, there are more and more larger-scale tunnel projects in process. Tunnel engineering constructions are very difficult, high risk, and there are many unpredictable factors that may cause safety issues, such as landslides, roof caving and water bursts, threatening the construction personnel’s safety. The personnel positioning tracking systems have been studied and applied preliminarily in railway tunnel construction. It is important to know how many people are underground, and workers must sign in/out one by one at tunnel entrances when they come in or leave; a process that is time-consuming and sometimes irritating to those who line up and must exit one-by-one to sign in. Active Radio Frequency Identification (RFID) systems can respond to transponders on the personnel’s helmets or jackets to quickly identify workers coming and going without stopping to sign in and out. It can also alert management when a person enters without a transponder. Indoor moving target recognition and tracking in Internet of Things is a popular research and application topic in recent years. This paper proposes an indoor moving target recognition and tracking method based on RFID and Charge Coupled Device (CCD) collaborative information fusion. First, RFID technique and the proposed extended virtual reference elimination (extended virtual reference elimination) approach are used to recognize and to coarsely locate the target. Second, based on the coarse localization results, the monitoring/sleeping control of different CCDs will be realized. Subsequently, the background-difference method is used to detect the target in CCD monitoring image and realize precise localization with multiple angle of view fusion. Finally, with weighted average of the two localization results, the moving target location is obtained. The method combines the advantages of RFID fast recognition and localization and CCD precise localization. The experiment results indicate that the proposed collaborative information fusion method can effectively improve the accuracy and real-time performance of indoor moving target tracking.

Keywords

Internet of Things RFID technology CCD image processing collaborative information fusion extended virtual reference elimination (extended VIRE)

Get full access to this article

View all access options for this article.

References

Ardevan

Beno

(2007) An active vision system for multitarget surveillance in dynamic environments. IEEE Transactions on Systems, Man, and Cybernetics 37(1): 190–198.

Cheng-Ch

Syh-S

Pau

(2015) Particle filter design for mobile robot localization based on received signal strength indicator. Transactions of the Institute of Measurement and Control 38(11): 1311–1319.

Choi

Lee

(2011) A hierarchical algorithm for indoor mobile robot localization using RFID sensor fusion. IEEE Transactions on Industrial Electronics 58(6): 2226–2235.

Ding

Jin

Ren

(2013) An intelligent self-organization scheme for the Internet of Things. IEEE Computational Intelligence Magazine 8(3): 41–53.

Junfeng

Kwe

Jun

(2015) A novel multi-sensors fusion framework based on Kalman Filter and neural network for AFS application. Transactions of the Institute of Measurement and Control 37(9): 1049–1059.

Kamol

Nikolaidis

Ueda

(2007) RFID based object localization system using ceiling cameras with particle filter. Future Generation Communication and Networking 1(1): 37–42.

Mathieu

Dos santos

(2008) RFID tags: Positioning principles and localization techniques. In: Wireless Days, London, UK, 23–25 September, pp. 1–5. IEEE.

Mohamed

Tahir

Adnan

(2010) Background modelling and background subtraction performance for object detection. In: International Colloquium on Signal Processing and Its Applications (CSPA), London, UK, 25–28 January, pp. 236–241.

Liu

Lau

(2004) LANDMARC: Indoor location Sensing Using Active RFID. In: Wireless Networks, London, UK, 23–25 September, pp. 701–710.

10.

Zhang

Souryal

(2011) RFID-based localization and tracking technologies. IEEE Wireless Communications 18(2): 45–51.

11.

Park

Hashimoto

(2009) Autonomous mobile robot navigation using passive RFD in indoor environment. IEEE Transactions on Industrial Electronics 56(7): 2366–2373.

12.

Roman

Horst

(2010) Localization and trajectory reconstruction in surveillance cameras with non over lapping views. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(4): 709–721.

13.

Saab

Nakad

(2011) A standalone RFID indoor positioning system using passive tags. IEEE Transactions on Industrial Electronics 58(5): 1961–1970.

14.

Wang

Zhang

(2011) Ranging error classification based indoor TOA localization algorithm. Chinese Journal of Scientific Instrument 32(12): 2851–2856.

15.

Wang

(2007) Collaborative signal processing for target tracking in distributed wireless sensor networks. Parallel and Distributed Computing 67(5): 501–515.

16.

Wang

Sun

(2012) Target localization in wireless sensor networks using sparse signal reconstruction. Chinese Journal of Scientific Instrument 33(2): 362–368.

17.

Weiss

Picard

(2010) Maximum-likelihood position estimation of network nodes using range measurements. IET Signal Processing 2(4): 394–404.

18.

Xiuzhi

Guanrong

Songmin

(2015) Velocity measurement for omni-directional intelligent wheelchair. Transactions of the Institute of Measurement and Control 38(11): 1320–1333.

19.

Zhang

(2009) Research on distance measurement based on RSSI of ZigBee. In: Proceedings of the 2009 ISECS International Colloquium on Computing, Communication, Control,and Management, Chengdu, China, 22–25 January, pp. 210–212.

20.

Zhao

Liu

(2007) VIRE: Active RFID-based localization using virtual reference elimination. In: International Conference on Parallel Processing, ICPP, Wuhan, China, 12–15 September, pp.56–66.