Abstract

The problem of foreign object intrusion onto the track bed often occurs in the actual operation process of high-speed railways. To solve the problem, we propose an anomaly detection method for the ballastless track bed, which is based on semantic segmentation. Firstly, we put forward the RFODLab semantic segmentation network according to the randomness of foreign objects distribution, and a small proportion of target pixels in the track image. The segmentation results of track image obtained through this model can be used to obtain the accurate pixel information of foreign objects. To further improve the recall and precision, the channel attention mechanism is introduced for the backbone network of the model to aggregate the context information of images, which achieves the weighted constraints of the model on the area to be recognized. Furthermore, to improve the model performance affected by unbalanced sample category distribution during the anomaly detection, we modify the loss function by balancing distribution of each category. The experimental results show that our proposed method can effectively segment various types of anomalies on the ballastless track bed including broken elastic strips, animal carcasses, and fallen pieces. The precision of anomaly detection on the test set can reach 90% while the recall can be maintained at more than 95%. The anomaly detection results on actual lines also verify the effectiveness of the method.

Highlights

  • China's railway lines feature the long mileage, large spatial span, and complex and changeable conditions, raising high requirements for the efficient operation and maintenance of railway infrastructures

  • In order to further improve the semantic segmentation network’s capacity to extract the features of foreign objects on the track bed, the channel attention mechanism is introduced for the backbone network (ResNet 50) of the model

  • We propose the RFODLab semantic segmentation network for detection of foreign objects on the ballastless track bed

Read more

Summary

INTRODUCTION

China's railway lines feature the long mileage, large spatial span, and complex and changeable conditions, raising high requirements for the efficient operation and maintenance of railway infrastructures. The key point is to distinguish foreign object that does not belong to the inherent track facilities from a large number of normal track images This problem belongs to the category of anomaly detection. The model makes it possible to solve the problem of a large number of false alarms caused by the great similarity between some foreign objects and certain existing facilities of the ballastless track bed. The loss function combining Focal Loss and Dice Loss is adopted for the RFODLab network Through this loss function, a balance is achieved in the category proportion of foreign objects and backgrounds, and the problem of unbalanced sample category distribution caused by the excessive proportion of backgrounds in track images is solved to a certain extent

RELATED WORK
Preliminary
RFODLab Semantic Segmentation Network
Channel Attention Mechanism
Loss Function
Dataset and Preprocessing
Results and Analysis
Evaluation Indicator
Actual Line Test
Findings
CONCLUSIONS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call