25 October 2017 Features extraction algorithm about typical railway perimeter intrusion event
Author Affiliations +
Proceedings Volume 10464, AOPC 2017: Fiber Optic Sensing and Optical Communications; 104641I (2017) https://doi.org/10.1117/12.2285278
Event: Applied Optics and Photonics China (AOPC2017), 2017, Beijing, China
Abstract
Research purposes: Optical fiber vibration sensing system has been widely used in the oil, gas, frontier defence, prison and power industries. But, there are few reports about the application in railway defence. That is because the surrounding environment is complicated and there are many challenges to be overcomed in the optical fiber vibration sensing system application. For example, how to eliminate the effects of vibration caused by train, the natural environments such as wind and rain and how to identify and classify the intrusion events. In order to solve these problems, the feature signals of these events should be extracted firstly. Research conclusions: (1) In optical fiber vibration sensing system based on Sagnac interferometer, the peak-to-peak value, peak-to-average ratio, standard deviation, zero-crossing rate, short-term energy and kurtosis may serve as feature signals. (2) The feature signals of resting state, climbing concrete fence, breaking barbed wire, knocking concrete fence and rainstorm have been extracted, which shows significant difference among each other. (3) The research conclusions can be used in the identification and classification of intrusion events.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jieyun Zhou, Jieyun Zhou, Chaodong Wang, Chaodong Wang, Lihai Liu, Lihai Liu, } "Features extraction algorithm about typical railway perimeter intrusion event", Proc. SPIE 10464, AOPC 2017: Fiber Optic Sensing and Optical Communications, 104641I (25 October 2017); doi: 10.1117/12.2285278; https://doi.org/10.1117/12.2285278
PROCEEDINGS
6 PAGES


SHARE
Back to Top