Detection of traffic accidents using artificial intelligence

Jesus Gerardo Ávila Sánchez; Francisco Eneldo López Monteagudo; Francisco Javier Martinez Ruiz; Leticia del Carmen Ríos Rodríguez

doi:10.5935/jetia.v10i46.1109

Authors

Jesus Gerardo Ávila Sánchez Autonomous University of Zacatecas, Av. López Velarde No. 801 CP 98060 Zacatecas, México http://orcid.org/0000-0001-8518-2023 (unauthenticated)
Francisco Eneldo López Monteagudo Autonomous University of Zacatecas, Av. López Velarde No. 801 CP 98060 Zacatecas, México http://orcid.org/0000-0001-6082-1546 (unauthenticated)
Francisco Javier Martinez Ruiz Autonomous University of Zacatecas, Av. López Velarde No. 801 CP 98060 Zacatecas, México http://orcid.org/0000-0002-8842-7556 (unauthenticated)
Leticia del Carmen Ríos Rodríguez Autonomous University of Zacatecas, Av. López Velarde No. 801 CP 98060 Zacatecas, México http://orcid.org/0000-0002-1005-020X (unauthenticated)

DOI:

https://doi.org/10.5935/jetia.v10i46.1109

Abstract

This article analyzes different architectures with which a neural network can be developed using computer vision with the objective of detecting traffic accidents. For the development of the software, the Java Script programming language was used, reaching the conclusion that the best architecture to use is a Convolutional Neural Network since it has the capabilities of detecting features within the images. At the same time, a database was developed with the necessary characteristics for the functioning of the neural network.