DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Anomaly Detection on the Rail Lines Using Semantic Segmentation and Self-supervised Learning

Jahan, Kanwal and Umesh, Jeethesh Pai and Roth, Michael (2021) Anomaly Detection on the Rail Lines Using Semantic Segmentation and Self-supervised Learning. In: 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021. IEEE. IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021), 4th-7th Dec. 2021, USA. doi: 10.1109/SSCI50451.2021.9659920. ISBN 978-1-7281-9048-8.

[img] PDF


This paper introduces a novel application of anomaly detection on the rail lines using deep learning methods on camera data. We propose a two-fold approach for identifying irregularities like coal, dirt, and obstacles on the rail tracks. In the first stage, a binary semantic segmentation is performed to extract only the rails from the background. In the second stage, we deploy our proposed autoencoder utilizing the self-supervised learning techniques to address the unavailability of labelled anomalies. The extracted rails from stage one are divided into multiple patches and are fed to the autoencoder, which is trained to reconstruct the non-anomalous data only. Hence, during the inference, the regeneration of images with any abnormalities produces a larger reconstruction error. Applying a predefined threshold to the reconstruction errors can detect an anomaly on a rail track. Stage one, rail extracting network achieves a high value of 52:78% mean Intersection over Union (mIoU). The second stage autoencoder network converges well on the training data. Finally, we evaluate our two-fold approach on real scenario test images, no false positives or false negative

Item URL in elib:https://elib.dlr.de/144681/
Document Type:Conference or Workshop Item (Speech)
Title:Anomaly Detection on the Rail Lines Using Semantic Segmentation and Self-supervised Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Jahan, KanwalUNSPECIFIEDhttps://orcid.org/0009-0000-6977-239XUNSPECIFIED
Roth, MichaelUNSPECIFIEDhttps://orcid.org/0000-0002-4812-346XUNSPECIFIED
Journal or Publication Title:2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:Yes
Keywords:Semantic segmentation, self-supervised learning, autoencoders, deep learning, mIoU, UNet, a
Event Title:IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2021)
Event Location:USA
Event Type:international Conference
Event Dates:4th-7th Dec. 2021
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Rail Transport
DLR - Research area:Transport
DLR - Program:V SC Schienenverkehr
DLR - Research theme (Project):V - Digitalisierung und Automatisierung des Bahnsystems (old)
Location: Braunschweig
Institutes and Institutions:Institute of Transportation Systems > Information Gathering and Modelling, BS
Deposited By: Jahan, Kanwal
Deposited On:07 Jan 2022 08:42
Last Modified:20 Nov 2023 12:28

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.