A Deep Generative Approach for Rail Foreign Object Detections via Semi-supervised Learning

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Journal / PublicationIEEE Transactions on Industrial Informatics
Publication statusOnline published - 9 Feb 2022

Abstract

In this paper, we develop a deep generative approach for detecting foreign objects appearing on the rail track site without pre-defining the scope of objects. The detection procedure consists of three steps: 1) The model composed of an autoencoder and a discriminator is developed via unsupervised training based on normal rail images only; 2) The detection of abnormal rails is implemented based on the anomaly score obtained via the trained autoencoder; and 3) Foreign objects are finally detected by filtering the subtle dissimilarity in normal areas and highlighting abnormal areas. The effectiveness of the proposed framework for the rail foreign object detection is validated with images collected by a train equipped with visual sensors. Computational results demonstrate that our proposal is capable to achieve an impressive performance on detecting numerous foreign objects. Moreover, two groups of benchmarking methods are employed to verify the superiority of the proposed framework.

Research Area(s)

  • Foreign object detection, image analytics, Image reconstruction, Inspection, Object detection, Rail transportation, Rails, railway infrastructure, semi-supervised learning, Semisupervised learning, Training, transportation safety