Deep convolutional neural networks for detection of rail surface defects

Deep convolutional neural networks for detection of rail surface defects

Faghih Roohi, S. (TU Delft Team Bart De Schutter)
Hajizadeh, S. (TU Delft Railway Engineering)
Nunez, Alfredo (TU Delft Railway Engineering)
Babuska, R. (TU Delft OLD Intelligent Control & Robotics)
De Schutter, B.H.K. (TU Delft Team Bart De Schutter)

Estevez, Pablo A. (editor)
Angelov, Plamen P. (editor)
Del Moral Hernandez, Emilio (editor)

2016

In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and detect rail surface defects. Therefore, automated detection of rail defects can help to save time and costs, and to ensure rail transportation safety. However, one major challenge is that the extraction of suitable features for detection of rail surface defects is a non-trivial and difficult task. Therefore, we propose to use convolutional neural networks as a viable technique for feature learning. Deep convolutional neural networks have recently been applied to a number of similar domains with success. We compare the results of different network architectures characterized by different sizes and activation functions. In this way, we explore the efficiency of the proposed deep convolutional neural network for detection and classification. The experimental results are promising and demonstrate the capability of the proposed approach.

Rails
Neural networks
Convolution
Training
Feature extraction
Insulation life
Degradation

http://resolver.tudelft.nl/uuid:e9926cc3-7ff8-4447-a30f-8a897c84b5ed

https://doi.org/10.1109/IJCNN.2016.7727522

IEEE, Piscataway, NJ, USA

978-1-5090-0619-9

Proceedings 2016 International Joint Conference on Neural Networks (IJCNN)

IJCNN 2016, 2016-07-24 → 2016-07-29, Vancouver, Canada

Accepted Author Manuscript

Institutional Repository

conference paper

© 2016 S. Faghih Roohi, S. Hajizadeh, Alfredo Nunez, R. Babuska, B.H.K. De Schutter