Fast car crash detection in video

Vicente Enrique Machaca Arceda; Elian Laura Riveros

doi:10.1109/CLEI.2018.00081

Fast car crash detection in video

Vicente Enrique Machaca Arceda, Elian Laura Riveros

Resultado de la investigación: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

5 Citas (Scopus)

Resumen

In this work, we aim to detect car crash accidents in video. We propose a three-stage framework: The first one is a car detection method using convolutional neural networks, in this case, we used the net You Only Look Once (YOLO); the second stage is a tracker in order to focus each car; then the final stage for each car we use the Violent Flow (ViF) descriptor with a Support Vector Machine (SVM) in order to detect the car crashes. Our proposal is almost in real time with just 0.5 seconds of delay and also we got a 89% accuracy detecting car crashes.

Idioma original	Inglés
Título de la publicación alojada	Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018
Editorial	Institute of Electrical and Electronics Engineers Inc.
Páginas	632-637
Número de páginas	6
ISBN (versión digital)	9781728104379
DOI	https://doi.org/10.1109/CLEI.2018.00081
Estado	Publicada - oct. 2018
Evento	44th Latin American Computing Conference, CLEI 2018 - Sao Paulo, Brasil Duración: 1 oct. 2018 → 5 oct. 2018

Serie de la publicación

Nombre	Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018

Conferencia

Conferencia	44th Latin American Computing Conference, CLEI 2018
País/Territorio	Brasil
Ciudad	Sao Paulo
Período	1/10/18 → 5/10/18

Nota bibliográfica

Publisher Copyright:
© 2018 IEEE.

Acceder al documento

10.1109/CLEI.2018.00081

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

@inproceedings{e25716069bcb48a19dbd24e7f0900734,

title = "Fast car crash detection in video",

abstract = "In this work, we aim to detect car crash accidents in video. We propose a three-stage framework: The first one is a car detection method using convolutional neural networks, in this case, we used the net You Only Look Once (YOLO); the second stage is a tracker in order to focus each car; then the final stage for each car we use the Violent Flow (ViF) descriptor with a Support Vector Machine (SVM) in order to detect the car crashes. Our proposal is almost in real time with just 0.5 seconds of delay and also we got a 89% accuracy detecting car crashes.",

keywords = "Car Crash, Convolutional Networks, Deep Learning, SVM, ViF",

author = "{Machaca Arceda}, {Vicente Enrique} and {Laura Riveros}, Elian",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; null ; Conference date: 01-10-2018 Through 05-10-2018",

year = "2018",

month = oct,

doi = "10.1109/CLEI.2018.00081",

language = "Ingl{\'e}s",

series = "Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "632--637",

booktitle = "Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018",

address = "Estados Unidos",

}

Machaca Arceda, VE & Laura Riveros, E 2018, Fast car crash detection in video. En Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018., 8786306, Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 632-637, 44th Latin American Computing Conference, CLEI 2018, Sao Paulo, Brasil, 1/10/18. https://doi.org/10.1109/CLEI.2018.00081

Fast car crash detection in video. / Machaca Arceda, Vicente Enrique; Laura Riveros, Elian.

Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 632-637 8786306 (Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018).

Resultado de la investigación: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Fast car crash detection in video

AU - Machaca Arceda, Vicente Enrique

AU - Laura Riveros, Elian

PY - 2018/10

Y1 - 2018/10

N2 - In this work, we aim to detect car crash accidents in video. We propose a three-stage framework: The first one is a car detection method using convolutional neural networks, in this case, we used the net You Only Look Once (YOLO); the second stage is a tracker in order to focus each car; then the final stage for each car we use the Violent Flow (ViF) descriptor with a Support Vector Machine (SVM) in order to detect the car crashes. Our proposal is almost in real time with just 0.5 seconds of delay and also we got a 89% accuracy detecting car crashes.

AB - In this work, we aim to detect car crash accidents in video. We propose a three-stage framework: The first one is a car detection method using convolutional neural networks, in this case, we used the net You Only Look Once (YOLO); the second stage is a tracker in order to focus each car; then the final stage for each car we use the Violent Flow (ViF) descriptor with a Support Vector Machine (SVM) in order to detect the car crashes. Our proposal is almost in real time with just 0.5 seconds of delay and also we got a 89% accuracy detecting car crashes.

KW - Car Crash

KW - Convolutional Networks

KW - Deep Learning

KW - SVM

KW - ViF

UR - http://www.scopus.com/inward/record.url?scp=85071129921&partnerID=8YFLogxK

U2 - 10.1109/CLEI.2018.00081

DO - 10.1109/CLEI.2018.00081

M3 - Contribución a la conferencia

AN - SCOPUS:85071129921

T3 - Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018

SP - 632

EP - 637

BT - Proceedings - 2018 44th Latin American Computing Conference, CLEI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 1 October 2018 through 5 October 2018

ER -

Fast car crash detection in video

Resumen

Serie de la publicación

Conferencia

Nota bibliográfica

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto