利用列車前方影像量測鋼軌曲率之研究

RESEARCH ON MEASURING THE CURVATURE OF RAILS BY USING IMAGES IN FRONT OF TRAINS

10.6652/JoCICHE.202106_33(4).0007

廖慶隆(Ching-Lung Liao)

鐵路 ； 鋼軌曲率 ； 攻角 ； 影像量測 ； 軌道監測 ； railway ； rail curvature ； angle of attack ； image measurement ； railway monitoring

中國土木水利工程學刊

33卷4期（2021 / 06 / 01）

317 - 326

繁體中文

本研究主要利用在鐵路車輛駕駛位置上看到之景象，轉化成可以辨識鋼軌流來向之照片串流，該鋼軌流經由鋼軌邊緣辨識取得鋼軌偏移量，並從照片串流中以逆向處理方式取得相關軌道幾何資訊及相機位置等，並據以量測鋼軌流來向之方向變化，轉換成串流形式之鋼軌曲率變化以及鐵路車輛之搖擺行為，由於此項觀測可在營運中的車輛進行，也可就歷史影片資料進行分析，不但可以隨時監測鐵路系統之路況及車況，並比對鋼軌歷史監測記錄串流，進行必要之養護及改善，此研究對於鐵路系統之舒適度及安全度之維持非常有用。

This research mainly uses the scene seen from the driving position of the railway vehicle to transform it into a photo stream that can identify the direction of the rail flow. The rail offset is obtained through the rail edge recognition, and the relevant track is obtained from the photo stream by reverse processing. Geometry information and camera position, etc., are used to measure the change in the direction of the rail flow, which is converted into a stream of rail curvature changes and the sway behavior of railway vehicles. This observation can be performed on vehicles in operation or on the analysis of historical video data can not only monitor the road conditions and vehicle conditions of the railway system at any time but also compare the historical monitoring records to perform necessary maintenance and improvement, which is very useful for maintaining the comfort and safety of the railway system.

1. 林宏達(2018)。光學非接觸式軌道檢測分析設備於軌道管理之應用。土木水利，45(1)，106-118。
   連結：
2. Guan, Q.,Zeng, J.,Jin, X.(2014).An angle of attack-based derailment criterion for wheel flange climbing.Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit,228(7),719-729.
3. Karakose, M.,Yaman, O.,Baygin, M.,Murat, K.,Akin, E.(2017).A New Computer Vision Based Method for Rail Track Detection and Fault Diagnosis in Railways.Vehicle System Dynamics,6(1),22-27.
4. Kostrzewski, M.(2018).Analysis of selected acceleration signals measurements obtained during supervised service conditions ⎯ study of hitherto approach.Journal of Vibroengineering,20(4),1850-1866.
5. Li, W.,Fang, Y.,Jiang, S.,Yang, C.,Han, Q.(2017).Inspection system for rail abnormal light band.Computer Engineering and Applications,53(9),246-252.
6. Liao, C. L.,Wang, S. M.,Ni, Y. Q.(2019).Application of driving recorder to evaluate rail irregularity and vehicle swing.Proceedings of the 12th International Workshop on Structural Health Monitoring,California:
7. Wang, S. M.,Liao, C. L.,Ni, Y. Q.(2020).A machine vision system based on driving recorder for automatic inspection of rail curvature.IEEE Sensors Journal,21(10),11291-11300.
8. Weston, P.,Roberts, C.,Yeo, G.,Stewart, E.(2015).Perspectives on railway track geometry condition monitoring from in-service railway vehicles.Vehicle System Dynamics,53(7),1063-1091.
9. 左玉良(2009)。從鋼軌光帶異常看高速線路軌道平順性。鐵道標準設計，4，13-16。
10. 郭振銘,林智強,陳柏旭,韓宗豪(2014)。車輛脫軌準則之探討。臺鐵資料季刊，350，36-42。