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 thermography data: tensor low-rankness, local smoothness, and non-local similarity. The effectiveness of the proposed algorithm is validated using both simulated and experimentally collected temperature field. Results show that the proposed reconstruction algorithm requires only 10% of the temperature data to reconstruct the complete temperature field. The fitted in-plane thermal diffusivity exhibits less than a 5% error compared to the complete temperature field fitting. The proposed method demonstrates competitive reconstruction quality and generalization ability compared to existing algorithms.

Lock-in thermography is widely used in determining the thermal properties of films by extracting the amplitude and phase of thermal waves. However, achieving high phase detection accuracy typically requires sophisticated infrared (IR) cameras. In this work, we present a regression methodology based on Bayesian optimization to determine the in-plane thermal diffusivity of thin films. Unlike conventional approaches that rely on lock-in algorithms, where amplitude and phase are treated as intermediate quantities, our method directly incorporates time-sequential thermograms into the regression process. The thermal diffusivity and phase offset are automatically extracted by minimizing the mean absolute error between measured and simulated normalized temperatures. This method is validated through measurements on a stainless-steel film, demonstrating that accurate results can be achieved using only a few thermograms per modulation period. These findings highlight the feasibility, robustness, and reduced system requirements of the proposed approach, making it particularly promising for characterizing composite films and advanced thermal interfacial materials.