Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection
Accurate and fast identification of vibration signals detected based on the phase-sensitive optical time-domain reflectometer (Φ-OTDR) is crucial in reducing the false-alarm rate of the long-distance distributed vibration warning system. This study proposes a computer vision-based Φ-OTDR multi-vibra...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/3/1127 |
| _version_ | 1797484629930803200 |
|---|---|
| author | Nachuan Yang Yongjun Zhao Jinyang Chen |
| author_facet | Nachuan Yang Yongjun Zhao Jinyang Chen |
| author_sort | Nachuan Yang |
| collection | DOAJ |
| description | Accurate and fast identification of vibration signals detected based on the phase-sensitive optical time-domain reflectometer (Φ-OTDR) is crucial in reducing the false-alarm rate of the long-distance distributed vibration warning system. This study proposes a computer vision-based Φ-OTDR multi-vibration events detection method in real-time, which can effectively detect perimeter intrusion events and reduce personnel patrol costs. Pulse accumulation, pulse cancellers, median filter, and pseudo-color processing are employed for vibration signal feature enhancement to generate vibration spatio-temporal images and form a customized dataset. This dataset is used to train and evaluate an improved YOLO-A30 based on the YOLO target detection meta-architecture to improve system performance. Experiments show that using this method to process 8069 vibration data images generated from 5 abnormal vibration activities for two types of fiber optic laying scenarios, buried underground or hung on razor barbed wire at the perimeter of high-speed rail, the system mAP@.5 is 99.5%, 555 frames per second (FPS), and can detect a theoretical maximum distance of 135.1 km per second. It can quickly and effectively identify abnormal vibration activities, reduce the false-alarm rate of the system for long-distance multi-vibration along high-speed rail lines, and significantly reduce the computational cost while maintaining accuracy. |
| first_indexed | 2024-03-09T23:08:10Z |
| format | Article |
| id | doaj.art-b3ac2a416a15438e9206df6a1d6c6946 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T23:08:10Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b3ac2a416a15438e9206df6a1d6c69462023-11-23T17:50:55ZengMDPI AGSensors1424-82202022-02-01223112710.3390/s22031127Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target DetectionNachuan Yang0Yongjun Zhao1Jinyang Chen2Data and Target Engineering Institute, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaData and Target Engineering Institute, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaData and Target Engineering Institute, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaAccurate and fast identification of vibration signals detected based on the phase-sensitive optical time-domain reflectometer (Φ-OTDR) is crucial in reducing the false-alarm rate of the long-distance distributed vibration warning system. This study proposes a computer vision-based Φ-OTDR multi-vibration events detection method in real-time, which can effectively detect perimeter intrusion events and reduce personnel patrol costs. Pulse accumulation, pulse cancellers, median filter, and pseudo-color processing are employed for vibration signal feature enhancement to generate vibration spatio-temporal images and form a customized dataset. This dataset is used to train and evaluate an improved YOLO-A30 based on the YOLO target detection meta-architecture to improve system performance. Experiments show that using this method to process 8069 vibration data images generated from 5 abnormal vibration activities for two types of fiber optic laying scenarios, buried underground or hung on razor barbed wire at the perimeter of high-speed rail, the system mAP@.5 is 99.5%, 555 frames per second (FPS), and can detect a theoretical maximum distance of 135.1 km per second. It can quickly and effectively identify abnormal vibration activities, reduce the false-alarm rate of the system for long-distance multi-vibration along high-speed rail lines, and significantly reduce the computational cost while maintaining accuracy.https://www.mdpi.com/1424-8220/22/3/1127phase-sensitive optical time-domain reflectometercomputer visiontarget detectionreal-time processing |
| spellingShingle | Nachuan Yang Yongjun Zhao Jinyang Chen Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection Sensors phase-sensitive optical time-domain reflectometer computer vision target detection real-time processing |
| title | Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection |
| title_full | Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection |
| title_fullStr | Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection |
| title_full_unstemmed | Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection |
| title_short | Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection |
| title_sort | real time φ otdr vibration event recognition based on image target detection |
| topic | phase-sensitive optical time-domain reflectometer computer vision target detection real-time processing |
| url | https://www.mdpi.com/1424-8220/22/3/1127 |
| work_keys_str_mv | AT nachuanyang realtimephotdrvibrationeventrecognitionbasedonimagetargetdetection AT yongjunzhao realtimephotdrvibrationeventrecognitionbasedonimagetargetdetection AT jinyangchen realtimephotdrvibrationeventrecognitionbasedonimagetargetdetection |