Modelo de detección y análisis de señales de tránsito y deterioro de la superficie vial en carreteras 4G y 5G haciendo uso de redes neuronales convolucionales

Abstract

Convolutional Neural Networks (CNNs) have revolutionized image processing and computer vision due to their ability to detect patterns and features in large volumes of data, being applied in fields such as autonomous driving, surveillance, and medical diagnosis. This project, developed in collaboration with Inversiones Gutiérrez García, aims to design a technological solution for 4G and 5G highway concessionaires in Colombia, improving the management and monitoring of road conditions through advanced artificial intelligence techniques. Using neural networks, specifically Yolo NAS, it addresses the creation of databases, labeling, and training focused on traffic signals and road deterioration.