Deep Hazardous Events Detection in Top-Down Fish-Eye Images for Railway Applications
Résumé
A current trend in railway application research is the development of an autonomous train for regional lines[1].
This line of research aims at reducing human input needed to operate a train to optimize train traffic. This in
turn could lead to significant improvement in terms of train flow and energy consumption of the railway
infrastructure. However, an autonomous train prototype must provide safety guarantees to be put on the
market. It must identify safety issues that are currently under a conductor or an on-platform personnel’s
responsibility. A common source of personal injuries in the railway context are pedestrians stuck in train
automatic doors and dragged when the train departs[2]. This paper aims at introducing a deep learning
solution to identify such safety concerns in due time in addition to current doors obstacle detection systems.
We more specifically study the use of an anomaly detection algorithm for this task. These are commonly used
in video surveillance systems but their use cases are sensibly different from the vicinity of train doors. A
previous work[1] introduces a new anomaly detection dataset called FRailTRI20_DOD depicting a set of
hazardous events in the vicinity of train doors. This paper proposes a set of modifications to a deep learning-
based anomaly detection algorithm of the literature to adapt it to this dataset. Additionally, the proposed
modifications are the first work to provide good practices to deal with this dataset specificities.
Fichier principal
Deep_Hazardous_Events_Detection_in_Top-Down_Fish-Eye_Images_for_Railway_Applications .pdf (1.45 Mo)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)