Publication detail

Advancing Perimeter Security: Integrating DAS and CNN for Object Classification in Fiber Vicinity

TOMAŠOV, A. ZÁVIŠKA, P. DEJDAR, P. KLÍČNÍK, O. DA ROS, F. HORVÁTH, T. MÜNSTER, P.

Original Title

Advancing Perimeter Security: Integrating DAS and CNN for Object Classification in Fiber Vicinity

Type

journal article in Web of Science

Language

English

Original Abstract

This paper presents an advanced perimeter protection system that integrates phase-sensitive Optical Time-Domain Reflectometry ( Φ -OTDR) with Convolutional Neural Networks (CNNs) for real-time event classification near optical fibers. The proposed approach enhances traditional security methods by providing robust monitoring in challenging environments, such as low visibility and large-scale areas. We evaluated multiple signal preprocessing techniques, including Fast Fourier Transform (FFT), Redundant Discrete Fourier Transform (RDFT), Discrete Wavelet Transform (DWT), and Mel-Frequency Cepstral Coefficients (MFCC), to optimize classification accuracy and computational efficiency. While MFCC achieved the highest accuracy (85.61%), RDFT provided the best balance between performance (85.47%) and real-time feasibility, making it the preferred method for deployment. The system successfully differentiates events such as vehicle movement, fence manipulation, and construction work, while anomaly detection capabilities further enhance security by identifying irregular activities with minimal error. These findings demonstrate the potential of integrating fiber-optic sensing with deep learning to develop scalable, real-time perimeter protection solutions for critical infrastructure, border surveillance, and urban security.

Keywords

Convolutional neural networks;distributed acoustic sensing;event classification;perimeter protection;phase-sensitive optical time-domain reflectometry

Authors

TOMAŠOV, A.; ZÁVIŠKA, P.; DEJDAR, P.; KLÍČNÍK, O.; DA ROS, F.; HORVÁTH, T.; MÜNSTER, P.

Released

8. 4. 2025

Publisher

IEEE

Location

Online

ISBN

2169-3536

Periodical

IEEE Access

Year of study

13

Number

1

State

United States of America

Pages from

63600

Pages to

63610

Pages count

11

URL

Full text in the Digital Library

BibTex

@article{BUT197717,
  author="Adrián {Tomašov} and Pavel {Záviška} and Petr {Dejdar} and Ondřej {Klíčník} and Francesco {Da Ros} and Tomáš {Horváth} and Petr {Münster}",
  title="Advancing Perimeter Security: Integrating DAS and CNN for Object Classification in Fiber Vicinity",
  journal="IEEE Access",
  year="2025",
  volume="13",
  number="1",
  pages="63600--63610",
  doi="10.1109/ACCESS.2025.3558594",
  issn="2169-3536",
  url="https://ieeexplore.ieee.org/document/10955273"
}