Cristian Molina1 and Morelva Saeteros2, 1Salesian Polytechnic University, Quito, Ecuador, 2University of Deusto, Bizkaia, Spain
The present work focuses on the need of giving independence, safety and generating a better lifestyle for people with visual impairment. The work seeks to be an aid so that people with visual impairment can mobilize in a better manner, recognizing signage useful for their performance, such as pedestrian traffic lights, bus stops, pedestrian crossings, also, evaluate the model haar-cascade image detection methods to provide a better response to the user. The input to the system is a continuous video sequence, which analyses and gives the user and audible output of the different traffic signs. This process is based on an embedded system, which consists of a Raspberry Pi 3 B+ single board computer, a v2.1 Raspberry camera and headphones, the system was designed to be a low cost tool that can be adapted to the white cane for the support and autonomy of people with visual impairment.
Artificial Vision, Signage, OpenCV, Match Template, Haar-Classifier.