Phase-sensitive optical time domain reflectometry (Φ-OTDR) is a highly sensitive distributed vibration sensing technology crucial for pipeline safety monitoring. However, its sensitivity makes it susceptible to environmental interference, leading to frequent false alarms by misclassifying routine activities as threats. To enable accurate threat identification and rapid response, this study proposes a lightweight LightPatch Vision Transformer (LP-ViT) model suitable for edge deployment. We establish a mapping between excavator-pipeline distance and threat levels: “direct intrusion” (within 5 m), “high-risk operation” (within 10 m), and “background construction” (beyond 15 m). The LP-ViT model is developed through structural optimization and parameter compression of the standard Vision Transformer, achieving a 96.6% reduction in parameter count while maintaining a high classification accuracy of 89.9%. Furthermore, via knowledge distillation, we derive an ultra-lightweight student model with merely 0.37 M parameters, which achieves an inference latency of 5.5 ms per sample, enabling millisecond-level threat detection and response. The proposed solution effectively enhances both the classification accuracy and real-time performance of Φ-OTDR systems in complex environments, providing a practical pathway for implementing edge intelligence in pipeline safety monitoring.

Accurate reconstruction of complete temperature fields from sparsely sampled infrared thermography data is of great significance for reducing data acquisition burden, improving measurement efficiency, and enabling reliable thermal property inversion. This paper proposes a tensor completion algorithm based on multiple priors to reconstruct the complete temperature field from limited infrared thermography data. Reconstruction is achieved by enhancing three priors in the observed temperature data: tensor low-rankness, local smoothness, and non-local similarity. The effectiveness of the proposed algorithm is validated using experimentally acquired complete temperature field from a polyethylene terephthalate film. The results show that the proposed algorithm can accurately reconstruct the complete temperature field using only 10% of the original temperature data. The reconstructed temperature field enables extraction of the in-plane thermal diffusivity with an error of less than 5% compared with that obtained from the complete temperature field. Furthermore, the proposed method demonstrates competitive reconstruction accuracy and strong generalization capability compared with existing reconstruction algorithms.