Perimeter Security Monitoring of Small Sample $\Phi-{}$OTDR Based on Multi-Scale Feature Fusion

Distributed optical fiber vibration sensing technology based on the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\Phi$</tex>-OTDR principle holds significant application value in the field of perimeter security monitoring. However, in practical applications, the limited number of target event samples presents a small-sample challenge, restricting the performance and generalizability of monitoring systems. To address this issue, this paper proposes a method that achieves high classification accuracy for signal classification tasks involving four typical intrusion events under small-sample conditions. Experimental validation was conducted using field-collected data, and the results demonstrate that the proposed method can achieve high classification precision and event recognition rates even with small sample sizes. This provides an effective solution for optical fiber-based perimeter security monitoring in real-world scenarios.