Smart Glasses for blinds

Project Title

Smart Glasses for blinds

Project Area of Specialization Artificial IntelligenceProject Summary

Developing a tool for the visually impaired people is not a recently

emerged problem. But developing a computer aided tool is a still

developing area. The aim of all these systems is to help the user in

navigation without the help of a second person. There are several

works using computer vision techniques. But there is no existing

method that help to solve the all basic needs of blind person .All

existing systems are designed only for a specific purpose. In this

project, we propose new method which combines the key aspects

of some use full methods and added some extra capabilities for

assisting the blind person. This new system may solve some of

major problems of blind persons that are still existing. Also, we give

a comparison and analysis of the current use full navigation

methods.

And Guardian can track blind person through android application

Project Objectives

1- Our main purpose of this product is to help blind people see, not

literally but make life a little bit easier for them

2-Glasses can capture image via camera

3-Glasses can recognize images and determine each object in the

images

4-Compute the distance between the person and each object

5-Convert the information to voice using headphone

6-Tracking the blind person through android Application

Project Implementation Method

1.Calibration

• Chessboard is used to get intrinsic and extrinsic parameters

including lens distortion to be used in rectification and other

steps.

• Results in this step are stored in files with yml extensions

which can be accessed through code statements

2.Rectification

Two main steps are done in this phase:

• Remove the lens distortion according to the parameters

received from the calibration phase

• Align the two images where any point in the left image will

be on the same line in the right image (using epipolar lines)

3.Correspondence

• Matching between the two images is done using the aligned

images from rectification by finding the position of each

point in the two images

• Calculating the disparity using the value of x because the

two cameras are in the same position of y

• The output of this phase is disparity map

4.Triangulation

• All the previous phases are dealing with 2D images, but this

phase is building the 3D image using the depth map

• Calculating the Z dimension using the previous results and

the output is depth map

• In the depth map objects in front of the camera will be blue

and objects far away from the camera will be red

5.Segmentation

• Works on the 2D image again to separate objects from each

other and to separate objects from the background which

makes it easier to calculate the distance and recognizing

the object

• The output of this phase is binary matrix (1’s represent

objects and 0’s represent background)

6.Recognition

• Using the segmentation results and the 2D input image to

recognize the objects

• Recognizing objects done by extracting features from each

object and comparing them with the objects in the training

set

7.Matching the results and compute distance

• After segmentation in (2D) and triangulation (3D), each

object is connected to its Z dimension values to calculate

the distance between the blind person and each object in

the image

8.Convert the results to voice

• Results of distance measurement and recognition are

converted to text then converted to voice that helps blind

person to overcome obstacles

Benefits of the Project

1. Decreased the dependency of blind person on others person

2. Gardian knows the current position of blind person in any instance.

Technical Details of Final Deliverable

Tools:

• Web Camera

• Raspberry pi 4

• OpenCV

• Headphone

Technologies:

• Computer vision

• Segmentation

• Hardware

Speech Synthesis

Final Deliverable of the Project HW/SW integrated systemCore Industry ManufacturingOther Industries Education , IT Core Technology Artificial Intelligence(AI)Other Technologies Internet of Things (IoT)Sustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	29850
Raspberry pi 4 Gb	Equipment	1	15000	15000
Convertor	Equipment	1	350	350
GSM Module	Equipment	1	2700	2700
GPS Module	Equipment	1	1800	1800
Power Bank 10000mah	Equipment	1	2000	2000
Web Cam	Equipment	3	1500	4500
Memory Card 64Gb	Equipment	1	1200	1200
Ultra Sonic Sensor	Equipment	2	400	800
Pi Casing	Miscellaneous	1	400	400
Wires	Miscellaneous	6	100	600
Headphone	Equipment	1	500	500