A SMART VISION SYSTEM

 Smart Vision System According to the report of WHO (World Health Organization) Approximately 285 Million people are visually impaired out of them 39 million are completely blind and 246 million have low vision. 82% of all blind are over 50 years old. There are 285 mill

Project Title

A SMART VISION SYSTEM

Project Area of Specialization

Artificial Intelligence

Project Summary

 Smart Vision System

According to the report of WHO (World Health Organization) Approximately 285 Million people are visually impaired out of them 39 million are completely blind and 246 million have low vision. 82% of all blind are over 50 years old. There are 285 million people who are unable to walk independently and they are facing a lot of difficulties in their life.

In this AI world, we are introducing a smart vision system which can help the visually impaired people to detect the object in their surroundings. This system can give help people to move on their ways, to read characters, to detect object in general like Humans, cars, bikes, and walls etc.

In order to support visually impaired people, we developing an Electronic Vision System using IR sensor to detect any object, Ultrasonic Sensor to detect the range of the object, text to speech module to convert text into Audio, a camera to click the pictures of the surroundings to give the vision power to the system and detect which object is in front of it. We are using Raspberry pi 4 Processor which is using to process the data. We are looking forward to give the vision power to our society using AI Technology. This Vision system can help our differentially able people to live more efficiently in this world.

Project Objectives

Millions of people are visually impaired and we are developing a system which can work as an eye for them. This will give them a reason to be more self-confidence, increase their life quality and help them to be Independent from their disability.

Project Implementation Method

1. Input from the IR Sensor for the object detection.
2. Input from the Ultra sonic sensor for the distance calculation of an object.
3. Images from the Pi-cam for the object classification.
4. Processing of the data and conversion of object distance and object name into text through our processor.
5. Conversion of text into Audio through text to speech module and Deliverance of this audio directly into the ear of user.

Benefits of the Project

There are millions of people who can’t see and perform their basic daily routine work. This project will give them a power of vision. So that they can walk and do their work more efficiently. It will also improve the quality of life, it will also decrease the chances of their fall and fractures and improve their chances of living longer.

Technical Details of Final Deliverable

To Identify the object in front of people we use different equipment like IR Sensor, Ultrasonic sensor and a pi-cam. An IR sensor will detect the object and ultrasonic sensor is use to calculate the range of the object. PI-Cam will take the images and classified the object. After this all input data, Raspberry pi takes a decision like which object is in front of a person and how far it is. Camera will continuously take the images and match them with data through OpenCV framework is used to develop the AI model which gives Cafeemodel for the raspberry pi. Python program is used to get the input through camera and handle the interaction between the model and the input. Then, it shows the output on the screen as a text. Text to

speech module takes the text as an input and converts it to an audio output which goes directly into the user‘s ears.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

Health

Core Technology

Artificial Intelligence(AI)

Other Technologies

Wearables and Implantables

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com