Hazardous Events Detection in Automatic Train Doors Vicinity Using Deep Neural Networks - Archive ouverte HAL
Conference Papers Year : 2021

Hazardous Events Detection in Automatic Train Doors Vicinity Using Deep Neural Networks

Abstract

In the field of train transportation, personal injuries due to train automatic doors are still a common occurrence. This paper aims at implementing a computer vision solution as part of a safety detection system to identify automatic doors-related hazardous events to reduce their occurrence and their severity. Deep anomaly detection algorithms are often applied on CCTV video feeds to identify such hazardous events. However, the anomalous events identified by those algorithms are often simpler than most common occurrences in transport environments, hindering their widespread usage. Since such events are of quite a diverse nature and no dataset featuring them exist, we create a specilically-tailored dataset composed of real-case scenarios of hazardous events near train doors. We then study an anomaly detection algorithm from the literature on this dataset and propose a set of modifications to better adapt it to our railway context and to subsequently ease its application to a wider range of use-cases.
No file

Dates and versions

hal-03524635 , version 1 (13-01-2022)

Identifiers

Cite

Olivier Laurendin, Sébastien Ambellouis, Anthony Fleury, Ankur Mahtani, Sanaa Chafik, et al.. Hazardous Events Detection in Automatic Train Doors Vicinity Using Deep Neural Networks. AVSS 2021, 17th IEEE International Conference on Advanced Video and Signal Based Surveillance, Nov 2021, Washigton, D.C., United States. 7p, ⟨10.1109/AVSS52988.2021.9663863⟩. ⟨hal-03524635⟩
93 View
0 Download

Altmetric

Share

More