Skip to main content
WorldCist'20 - 8th World Conference on Information Systems and Technologies

Full Program »

Study of the pattern recognition algorithms for the automation of a smart semaphore through FPGAs.

The comparative study of the pattern recognition algorithms was performed: color matching algorithm, cross correlation algorithm and optical character recognition algorithm (OCR), the results indicated the most appropriate algorithm for the implementation of an intelligent traffic light using FPGAs . The present study was divided into two stages, the first is the design of the hardware whose objective is to control the prototype of intelligent traffic lights implemented; The second is the design of the software that aims to develop an application for the acquisition of images and process them to be analyzed by the pattern recognition algorithm, to evaluate the data obtained parameters such as accuracy and response time were used. As a result, it was obtained that the most suitable algorithm was the color matching that has an accuracy of 100% and a response time of 3ms.

Erik Fernando Méndez Garcés
University of the Andes
Ecuador

Gabriela Mafla
University of the Andes
Ecuador

José Ortíz
University of the Andes
Ecuador

 


Powered by OpenConf®
Copyright ©2002-2018 Zakon Group LLC