Obstacle Detection And Navigation System For Visually Impaired

There are many tools developed for blind people nowadays, but most of them have limited detection range and cannot be monitored wirelessly. This thesis discusses about an electronic navigation system (END), which is designed for the visually impaired people. The END is developed to have better detec...

Full description

Saved in:
Bibliographic Details
Main Author: Selvraju, Avinaash
Format: Thesis
Language:English
Published: 2019
Subjects:
Online Access:http://eprints.usm.my/48477/1/Obstacle%20Detection%20And%20Navigation%20System%20For%20Visually%20Impaired.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There are many tools developed for blind people nowadays, but most of them have limited detection range and cannot be monitored wirelessly. This thesis discusses about an electronic navigation system (END), which is designed for the visually impaired people. The END is developed to have better detection range and angle with the feature of Internet of Things (IOT). Three ultrasonic sensors are proposed to detect obstacle. The distance between obstacle and the sensor is measured. The error of distance given by the system is calculated in order to see the performance of the system. The performance of three ultrasonic sensors versus one ultrasonic and the optimum distance between the sensors are investigated in this project. The movement of the visually impaired person can be monitored wirelessly and the operator can give instruction to the visually impaired person through speaker. For streaming the voice between the visually impaired person and system operator or vice versa, the Mumble VoIP is used. Arduino DUE is used to control the ultrasonic sensors. Signals received from the ultrasonic sensors are sent wirelessly to Raspberry Pi 3 controller by the use of Bluetooth module. The latitude and longitude of the user are provided by the GPS module where this data can be accessed in a log file and can be used for further processing by accessing the cloud database. Results show that the system is successfully developed and the latitude and longitude of the location can be viewed in log file. Three sensors give the best result with detection angle has increased by 125% compared to 1 sensor. With 5% or less detection error, the optimum distance between the sensors is 1 cm and the maximum distance that it can measure is 420 cm.