Smart Navigation System for Blind using Raspberry Pi

Project Title

Smart Navigation System for Blind using Raspberry Pi

Project Area of Specialization Artificial IntelligenceProject Summary

The World Health Organisation (WHO) estimated in 2019 that 2.2 billion people have visual impairments worldwide. One of the biggest obstacles to visual impairment is decreased mobility and difficulties in discovering and getting around new and unfamiliar environments. Over time, blind and visually impaired people have used different methods and devices, such as long white canes and guide dogs, to aid in mobility and to increase safe and independent travel. These mechanisms are used to search for obstacles in front of the blind person, and they operate in a manner similar to a flashlight, which has very narrow directivity. To make it more realistic we are going to design smart glasses using deep learning which will be way more comfortable, safe, and independent than the devices available in the market and listed above. Our smart glasses will have the ability to analyze and tell the type of object in front of the visually impaired person by using advanced technologies. We are going to make it with inexpensive components so that our smart glasses are affordable for needy people.

Project Objectives

1. Detection of the obstacles.
2. Decision-making with the help of Raspberry Pi.
3. Guidance to the user in the form of human audible sound.

Project Implementation Method

The ultrasonic sensor mounted on the front side of the glasses will send out sound waves and receive them back. In this operation, Raspberry Pi will find the flight time and further calculate the distance accordingly. Built-in speakers will be used to give voice feedback to the user about the obstacle’s distance.

The camera which will be mounted on the front side of the glasses will capture the front view and compare the objects in the view with the predefined data saved in memory and it will tell the type of obstacle/object by using the same voice feedback system.

Benefits of the Project

1. No surgery needs
2. Proper guidelines for blinds
3. Help low vision conditions

Technical Details of Final Deliverable

These smart glasses will use an ultrasonic sensor and a camera. We will use Python open CV library with YOLO for real-time detection and for the speech module we will use gTTS. Data from the camera and ultrasonic sensors will be gathered in real-time and fed to Raspberry Pi. Based on the analysis of the data, Raspberry Pi will decide what to command the visually impaired person. It will tell the person how far/near the obstacle is and the type of object (human, sofa, car, etc.)

Final Deliverable of the Project HW/SW integrated systemCore Industry TelecommunicationOther Industries IT , Manufacturing , Health Core Technology Artificial Intelligence(AI)Other Technologies Wearables and Implantables, OthersSustainable Development Goals Good Health and Well-Being for People, Industry, Innovation and Infrastructure, Life on LandRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	21100
Raspberry Pi	Equipment	1	15000	15000
Pi Camera	Equipment	1	1400	1400
Glasses	Equipment	1	1000	1000
Battery	Equipment	2	600	1200
Ultrasonic Sensor	Equipment	1	200	200
Charge Controller	Equipment	1	400	400
SD Card	Equipment	1	1400	1400
Earphones	Equipment	1	500	500