Abstract

ALARCON VARGAS, Adrián Javier. Detection of vertical traffic signaling with convolutional neural networks based on residual blocks. Fides Et Ratio [online]. 2022, vol.24, n.24, pp.165-194. ISSN 2071-081X.

Abstract The objective of the present work is to train a neural network capable of detecting vertical traífic signaling and classify it using residual blocks, as they allow deeper neural networks. The methodology used for the development of the neural network comprises four phases: neural network definition, training, utilization, and maintenance of the neural network. For the development of the neural network there are two datasets, the first is of Germán origin, consists of 50,000 images and is widely used for the classification of traífic signs; and the second of Bolivian origin, which has 9,548 road images. The percentage of eíficiency of the neural network no. 1 with the GTSRB dataset is high, obtaining a valué of 94.36%, it also includes high valúes in the classification report, otherwise, it happens with the Bolivia dataset because the dataset is unbalanced

Keywords : GTSRB; Segmentation; Image Processing; Traífic Accidents; Classification; ResNet; ResUnet.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )