Artificial Intelligence-based Surveillance System for Railway Crossing Traffic

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F20%3APU137506" target="_blank" >RIV/00216305:26220/20:PU137506 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9226453" target="_blank" >https://ieeexplore.ieee.org/document/9226453</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/JSEN.2020.3031861" target="_blank" >10.1109/JSEN.2020.3031861</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Artificial Intelligence-based Surveillance System for Railway Crossing Traffic

Popis výsledku v původním jazyce

The application of Artificial Intelligence (AI) based techniques has strong potential to improve safety and efficiency in data-driven Intelligent Transportation Systems (ITS) as well as in the emerging Internet of Vehicles (IoV) services. This paper deals with the practical implementation of deep learning methods for increasing safety and security in a specific ITS scenario: railway crossings. This research work presents our proposed system called Artificial Intelligence-based Surveillance System for Railway Crossing Traffic (AISS4RCT) that is based on a combination of detection and classification methods focusing on various image processing inputs: vehicle presence, pedestrian presence, vehicle trajectory tracking, railway barriers at railway crossings, railway warnings, and light signaling systems. The designed system uses cameras that are suitably positioned to capture an entire crossing area at a given railway crossing. By employing GPU accelerated image processing techniques and deep neural networks, the system autonomously detects risky and dangerous situations at railway crossing in real-time. In addition, camera modules send data to a central server for further processing as well as notification to interested parties (police, emergency services, railway operators). Furthermore, the system architecture employs privacy-by-design and security-by-design best practices in order to secure all communication interfaces, protect personal data, and to increase personal privacy, i.e., pedestrians, drivers. Finally, we present field-based results of detection methods, and using the YOLO tiny model method we achieve average recall 89%. The results indicate that our system is efficient for evaluating the occurrence of objects and situations, and it’s practicality for use in railway crossings.

Název v anglickém jazyce

Artificial Intelligence-based Surveillance System for Railway Crossing Traffic

Popis výsledku anglicky

The application of Artificial Intelligence (AI) based techniques has strong potential to improve safety and efficiency in data-driven Intelligent Transportation Systems (ITS) as well as in the emerging Internet of Vehicles (IoV) services. This paper deals with the practical implementation of deep learning methods for increasing safety and security in a specific ITS scenario: railway crossings. This research work presents our proposed system called Artificial Intelligence-based Surveillance System for Railway Crossing Traffic (AISS4RCT) that is based on a combination of detection and classification methods focusing on various image processing inputs: vehicle presence, pedestrian presence, vehicle trajectory tracking, railway barriers at railway crossings, railway warnings, and light signaling systems. The designed system uses cameras that are suitably positioned to capture an entire crossing area at a given railway crossing. By employing GPU accelerated image processing techniques and deep neural networks, the system autonomously detects risky and dangerous situations at railway crossing in real-time. In addition, camera modules send data to a central server for further processing as well as notification to interested parties (police, emergency services, railway operators). Furthermore, the system architecture employs privacy-by-design and security-by-design best practices in order to secure all communication interfaces, protect personal data, and to increase personal privacy, i.e., pedestrians, drivers. Finally, we present field-based results of detection methods, and using the YOLO tiny model method we achieve average recall 89%. The results indicate that our system is efficient for evaluating the occurrence of objects and situations, and it’s practicality for use in railway crossings.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/FV40372" target="_blank" >FV40372: Autonomní systém pro detekci rizikových situací v dopravě založený na analýze obrazových sekvencí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE SENSORS JOURNAL

ISSN

1530-437X

e-ISSN

1558-1748

Svazek periodika

neuveden

Číslo periodika v rámci svazku

2020

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

15515-15526

Kód UT WoS článku

000673632700099

EID výsledku v databázi Scopus

—