Fast car crash detection in video

Vicente Enrique Machaca Arceda, Elian Laura Riveros

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión 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 originalInglés
Título de la publicación alojadaProceedings - 2018 44th Latin American Computing Conference, CLEI 2018
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas632-637
Número de páginas6
ISBN (versión digital)9781728104379
DOI
EstadoPublicada - oct. 2018
Evento44th Latin American Computing Conference, CLEI 2018 - Sao Paulo, Brasil
Duración: 1 oct. 20185 oct. 2018

Serie de la publicación

NombreProceedings - 2018 44th Latin American Computing Conference, CLEI 2018

Conferencia

Conferencia44th Latin American Computing Conference, CLEI 2018
País/TerritorioBrasil
CiudadSao Paulo
Período1/10/185/10/18

Nota bibliográfica

Publisher Copyright:
© 2018 IEEE.

Huella

Profundice en los temas de investigación de 'Fast car crash detection in video'. En conjunto forman una huella única.

Citar esto