Detección de infracciones y matrículas en motocicletas, mediante visión artificial, aplicado a sistemas inteligentes de transporte
Archivos
Fecha
2020-06-01
Título de la revista
ISSN de la revista
Título del volumen
Editor
Associacao Iberica de Sistemas e Tecnologias de Informacao
Resumen
Incomplete operation of transportation systems has led to an increase in illegal passenger transportation, by the means of motorcycles, at worldwide, causing high accident rates. In the intermediate cities of Colombia, the main control method applied to informal transportation is to impose fines to identified offenders by transit authorities. This work proposes the development of an application that, by means of computer vision, serves as a tool for transit officers in the detections of three infringements types committed by motorcyclists: not wearing a helmet; circulate in prohibited areas; transporting passenger in sites where it’s not allowed. Our case study was Valledupar city, where 105 motorcyclists’ images were taken while they are driving. Results show an accuracy of 87,5% in infringements detection, showing the relevance of this application as an assistance tool to disincentive informal transportation. © 2020, Associacao Iberica de Sistemas e Tecnologias de Informacao. All rights reserved.
Descripción
Palabras clave
AI, Mobile applications, Object detection, OCR, Public transportation