Cargando…

A deep neural framework for real-time vehicular accident detection based on motion temporal templates

Vehicular accident prediction and detection has recently garnered curiosity and large amounts of attention in machine learning applications and related areas, due to its peculiar and fascinating application potentials in the development of Intelligent Transportation Systems (ITS) that play a pivotal...

Descripción completa

Detalles Bibliográficos
Autores principales: Bakheet, Samy, Al-Hamadi, Ayoub
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647364/
https://www.ncbi.nlm.nih.gov/pubmed/36387580
http://dx.doi.org/10.1016/j.heliyon.2022.e11397
_version_ 1784827371528912896
author Bakheet, Samy
Al-Hamadi, Ayoub
author_facet Bakheet, Samy
Al-Hamadi, Ayoub
author_sort Bakheet, Samy
collection PubMed
description Vehicular accident prediction and detection has recently garnered curiosity and large amounts of attention in machine learning applications and related areas, due to its peculiar and fascinating application potentials in the development of Intelligent Transportation Systems (ITS) that play a pivotal role in the success of emerging smart cities. In this paper, we present a new vision-based framework for real-time vehicular accident prediction and detection, based on motion temporal templates and fuzzy time-slicing. The presented framework proceeds in a stepwise fashion, starting with automatically detecting moving objects (i.e., on-road vehicles or roadside pedestrians), followed by dynamically keep tracking of the detected moving objects based on temporal templates, clustering and supervised learning. Then, an extensive set of local features is extracted from the temporal templates of moving objects. Finally, an effective deep neural network (DNN) model is trained on the extracted features to detect abnormal vehicle behavioral patterns and thus predict an accident just before it occurs. The experiments on real-world vehicular accident videos demonstrate that the framework can yield mostly promising results by achieving a hit rate of 98.5% with a false alarm rate of 4.2% that compare very favorably to those from existing approaches, while still being able to deliver delay guarantees for realtime traffic monitoring and surveillance applications.
format Online
Article
Text
id pubmed-9647364
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-96473642022-11-15 A deep neural framework for real-time vehicular accident detection based on motion temporal templates Bakheet, Samy Al-Hamadi, Ayoub Heliyon Research Article Vehicular accident prediction and detection has recently garnered curiosity and large amounts of attention in machine learning applications and related areas, due to its peculiar and fascinating application potentials in the development of Intelligent Transportation Systems (ITS) that play a pivotal role in the success of emerging smart cities. In this paper, we present a new vision-based framework for real-time vehicular accident prediction and detection, based on motion temporal templates and fuzzy time-slicing. The presented framework proceeds in a stepwise fashion, starting with automatically detecting moving objects (i.e., on-road vehicles or roadside pedestrians), followed by dynamically keep tracking of the detected moving objects based on temporal templates, clustering and supervised learning. Then, an extensive set of local features is extracted from the temporal templates of moving objects. Finally, an effective deep neural network (DNN) model is trained on the extracted features to detect abnormal vehicle behavioral patterns and thus predict an accident just before it occurs. The experiments on real-world vehicular accident videos demonstrate that the framework can yield mostly promising results by achieving a hit rate of 98.5% with a false alarm rate of 4.2% that compare very favorably to those from existing approaches, while still being able to deliver delay guarantees for realtime traffic monitoring and surveillance applications. Elsevier 2022-11-03 /pmc/articles/PMC9647364/ /pubmed/36387580 http://dx.doi.org/10.1016/j.heliyon.2022.e11397 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Research Article
Bakheet, Samy
Al-Hamadi, Ayoub
A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title_full A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title_fullStr A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title_full_unstemmed A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title_short A deep neural framework for real-time vehicular accident detection based on motion temporal templates
title_sort deep neural framework for real-time vehicular accident detection based on motion temporal templates
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9647364/
https://www.ncbi.nlm.nih.gov/pubmed/36387580
http://dx.doi.org/10.1016/j.heliyon.2022.e11397
work_keys_str_mv AT bakheetsamy adeepneuralframeworkforrealtimevehicularaccidentdetectionbasedonmotiontemporaltemplates
AT alhamadiayoub adeepneuralframeworkforrealtimevehicularaccidentdetectionbasedonmotiontemporaltemplates
AT bakheetsamy deepneuralframeworkforrealtimevehicularaccidentdetectionbasedonmotiontemporaltemplates
AT alhamadiayoub deepneuralframeworkforrealtimevehicularaccidentdetectionbasedonmotiontemporaltemplates