Pipeline intrusion events recognition method based on AWTFE image enhancement for DAS
In this paper, we propose an image enhancement method for reliable threat event recognition in distributed acoustic sensing systems. The method significantly enhances image features of threat events, achieving classification accuracies of 96.69%, 97.65%, and 99.96% for intrusion event recognition using 2D-CNN, ResNet18, and Vgg13_BN networks, respectively.
Authors
- Lang Xie
- Yunjiang Rao (ORCID: https://orcid.org/0000-0003-0717-5586)
- Yu Wu (ORCID: https://orcid.org/0000-0002-0327-8935)
- Shibo Han (ORCID: https://orcid.org/0000-0002-5216-5718)
- XU Jing-cai
Institutions
- University of Electronic Science and Technology of China (CN)
Publication Details
- Published
- 2025-05-22
- DOI
- https://doi.org/10.1117/12.3060906
- Citations
- 1
- Primary Topic
- Smart Grid and Power Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.73