Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques

According to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveill...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sergio Robles-Serrano, German Sanchez-Torres, John Branch-Bedoya
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	urban traffic accident deep learning accident detection recurrent neural networks convolutional neural networks Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/198e70c8d1cc42e7880cc1c02bba8bb8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:198e70c8d1cc42e7880cc1c02bba8bb8
record_format	dspace
spelling	oai:doaj.org-article:198e70c8d1cc42e7880cc1c02bba8bb82021-11-25T17:17:27ZAutomatic Detection of Traffic Accidents from Video Using Deep Learning Techniques10.3390/computers101101482073-431Xhttps://doaj.org/article/198e70c8d1cc42e7880cc1c02bba8bb82021-11-01T00:00:00Zhttps://www.mdpi.com/2073-431X/10/11/148https://doaj.org/toc/2073-431XAccording to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveillance and intelligent traffic systems, an automated traffic accident detection approach becomes desirable for computer vision researchers. Nowadays, Deep Learning (DL)-based approaches have shown high performance in computer vision tasks that involve a complex features relationship. Therefore, this work develops an automated DL-based method capable of detecting traffic accidents on video. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure.Sergio Robles-SerranoGerman Sanchez-TorresJohn Branch-BedoyaMDPI AGarticleurban traffic accidentdeep learningaccident detectionrecurrent neural networksconvolutional neural networksElectronic computers. Computer scienceQA75.5-76.95ENComputers, Vol 10, Iss 148, p 148 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	urban traffic accident deep learning accident detection recurrent neural networks convolutional neural networks Electronic computers. Computer science QA75.5-76.95
spellingShingle	urban traffic accident deep learning accident detection recurrent neural networks convolutional neural networks Electronic computers. Computer science QA75.5-76.95 Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
description	According to worldwide statistics, traffic accidents are the cause of a high percentage of violent deaths. The time taken to send the medical response to the accident site is largely affected by the human factor and correlates with survival probability. Due to this and the wide use of video surveillance and intelligent traffic systems, an automated traffic accident detection approach becomes desirable for computer vision researchers. Nowadays, Deep Learning (DL)-based approaches have shown high performance in computer vision tasks that involve a complex features relationship. Therefore, this work develops an automated DL-based method capable of detecting traffic accidents on video. The proposed method assumes that traffic accident events are described by visual features occurring through a temporal way. Therefore, a visual features extraction phase, followed by a temporary pattern identification, compose the model architecture. The visual and temporal features are learned in the training phase through convolution and recurrent layers using built-from-scratch and public datasets. An accuracy of 98% is achieved in the detection of accidents in public traffic accident datasets, showing a high capacity in detection independent of the road structure.
format	article
author	Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya
author_facet	Sergio Robles-Serrano German Sanchez-Torres John Branch-Bedoya
author_sort	Sergio Robles-Serrano
title	Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
title_short	Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
title_full	Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
title_fullStr	Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
title_full_unstemmed	Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques
title_sort	automatic detection of traffic accidents from video using deep learning techniques
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/198e70c8d1cc42e7880cc1c02bba8bb8
work_keys_str_mv	AT sergioroblesserrano automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques AT germansancheztorres automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques AT johnbranchbedoya automaticdetectionoftrafficaccidentsfromvideousingdeeplearningtechniques
_version_	1718412514725724160

Automatic Detection of Traffic Accidents from Video Using Deep Learning Techniques

Ejemplares similares