Design And Construction Of A Smart Ultrasonic Walking Stick For The Visually Impaired

Abstract

In our society, blind people consist a wide number of individuals. In order to improve the quality of life of a blind person, the smart cane was therefore created. This project aims to develop a smart cane for the blind with an ultrasonic sensor and an audio feedback system. This embedded system will mainly have two parts; the system of mobility and feedback. It was been fitted with an ultrasonic sensor for the mobility system, while the vibrating motor and audio input will provide input from the ultrasonic and the vibrating module. An Ultrasonic sensor was used to send the signal to the vibrating motor as soon as an obstacle is detected, which in turn triggers it. With audio feedback alerting the user of the presence of the obstacle, the vibrating motor vibrates with various strengths according to the distance of the obstacle. One major component incorporated into this embedded system is an ATmega328 single-chip microcontroller which was programed in the c language of which the original programing was written with Matlab. It involves the use of a convolution neural network which was trained on the CIFAR 10 dataset. This dataset was chosen because of its composition of images of objects likely to be found as obstacles on a blind man’s path. A 93.8% accuracy was obtained from an unsupervised learning on the data set, after which the C Matlab coder was used to translate the source code into C language for effective embedding into the ATmega328 microcontroller.