Semi-supervised rail defect detection from imbalanced image data

Semi-supervised rail defect detection from imbalanced image data

Hajizadeh, S. (TU Delft Railway Engineering)
Nunez, Alfredo (TU Delft Railway Engineering)
Tax, D.M.J. (TU Delft Pattern Recognition and Bioinformatics)

Acarman, Tankut (editor)

2016

Rail defect detection by video cameras has recently gained much attention in both
academia and industry. Rail image data has two properties. It is highly imbalanced towards the non-defective class and it has a large number of unlabeled data samples available for semisupervised learning techniques. In this paper we investigate if positive defective candidates selected from the unlabeled data can help improve the balance between the two classes and gain performance on detecting a specic type of defects called Squats. We compare data sampling techniques as well and conclude that the semi-supervised techniques are a reasonable alternative for improving performance on applications such as rail track Squat detection from image data.

imbalance data
semi-supervised learning
rail image data
rail defect detection

http://resolver.tudelft.nl/uuid:fe47bca8-1a70-47c7-83a0-b906ca7722fc

Proceedings of the 14th IFAC Symposium on Control in Transportation Systems, CTS 2016, Istanbul, Turkey

14th IFAC Symposium on Control in Transportation Systems, 2016-05-18 → 2016-05-20, ITU Faculty of Architecture, Istanbul, Turkey

Institutional Repository

conference paper

© 2016 S. Hajizadeh, Alfredo Nunez, D.M.J. Tax