Wearable Devices for Increasing the Quality of Life for the Visually Impaired

jabgoldfishAI and Robotics

Oct 19, 2013 (3 years and 10 months ago)

87 views

Wearable Devices for Increasing the Quality of Life for the Visually Impaired

ABSTRACT

TITLE:
Wearable Devices for Increasing the Quality of Life for the Visually Impaired

BACKGROUND:

There are approximately 14 million visually impaired people in the United States of those 109,000 use long canes
to get around and

just over 7,000 Americans use guide dogs.

For most it is inconvenient to use the traditional
solutions to navigate their environment.

OBJECTIVE:

The goal of this work is to significantly increase the quality of life for a visually impaired subject. The results of
the effusiveness of the device are measured by giving a quality of life survey before and after using the device.

METHODS:


In order to create this device certain methods

was used

such as related works and Clint’s feedback.

PROTOTYPE CONSTRUCTION:

Consist of the components and schematic which was used for the layout of the prototype.


RESULTS:

[Add text here.]

CONCLUSIONS:

[Add text here.]


BACKGROUND

What causes visual impairment?


Illnesses
-

such as diabetes, cataracts, glaucoma, cornea disorder



Genetic or inherited from the parents to their children



Eyes not fully developed before birth



Accident to the eye



Some people who are 50 years of age and older


There are four types of visual impairment:


Partially sighted
-

little visual problems



Low vision
-

even with the help of glasses or contact lenses, some individuals still have problems with their
vision



Legally blind


is defined as visual acuity of 20/200 or less in the better eye with best correction, or their
field of vision is 20 degrees or less in the better eye.




Totally blind
-

are people who do not have vision at all and must use something to help them such as
learning Braille, guide dog, visual devices, or a cane


Contributors: Brilleasha Moore, Charles Bardel, Darrin M. Hanna, PhD; Clint

OBJECTIVE

The goal of this work is to significantly increase the quality of life for a visually impaired subject.
The results of the effusiveness of the device are measured by giving a quality of life survey before
and after using the device.

METHODS


Related Works


What others have created in wearable devices [Add description of key point.]


Clint’s feedback


Clint’s feedback was mainly a description of the problems he was having in everyday


Components for the obstacle device


The PIC


Is a microcontroller that handles


the data processing of the


sensors and output to the wrist bands



Sensors


The sensors are small ultrasonic

transmitters and receivers

that “ping” the local environment


-

Mainly detects proximity


IR sensors are more direct then


the ultrasonic sensors.




Components for the wrist bands


Rechargeable Telephone Battery


4 volts, 500mAh


Long lasting than AA or AAA batteries



Motor


DC motor from old cell


phones because its meant


for low power systems and it was free and convenient


Prototype Construction

Obstacle device


Components


Schematic

CONCLUSIONS

Meeting design criteria


Can detect objects within defined range


Can detect an increase in distance from the sensors to the ground (down stairs)


The type of object doesn

t have much affect in sensing the object


Objects that are not directly facing the sensors are harder to detect


The false positives and false negatives are too high for practical use

Sensor Data and Output

For additional information please contact:



Department of Computer Science and Engineering


Rochester, MI 48309


Tel. 248
-
370
-
2200


Fax 248
-
370
-
4625


SIBHI/UnCoRe 2007


Approximately 109,000
visually impaired people
in the United States use
long canes to get
around.



Just over 7,000
Americans use dog
guides.

Clint’s Feedback


Clint have problems with really bright days and low contrast objects.


Have a problem with detecting curbs or stairs


Unable to know a new environment


Knows an environment very well from memory


He doesn't want a guide dog because he doesn't want to put up with taking care of it.


Don’t want the device to go off all the time thus adjustable head set.


Large thigh pad with different vibrating zones or

four vibrating wrist

band and ankle
brace (Hanna's idea)


Concerned about the detection angle



How wide or narrow can the device detect




Related Works


Wearable low vision aid (WLVA)

-

http://www.hitl.washington.edu/projects/wlva
/


Created a low power, portable, and assistive device to aid the visually impaired.


WLVA that incorporates infrared (IR) illumination and efficient machine vision algorithms to
identify potential walking hazards and a scanning fiber display to present bright icons to warn the
user.


The WLVA hardware will undergo a significant reduction in size, using a single tubular
piezoelectric actuator less than 2mm in diameter to generate over 50 times more pixels while
maintaining its extreme low cost.


A printed circuit board has been designed to significantly reduce the weight and size of the
backpack electronics as well.



Wearable system for mobility improvement of visually impaired people

-

http://infoscience.epfl.ch/getfile.py?recid=99038&mode=best


Obstacle detection system for the visually impaired


The user is alerted of closed obstacles in range while traveling in their environment.


The system detects obstacle that surrounds the user by using multi
-
sonar system and sending
appropriate vibro
-
tactile feedback.



The system aims at increasing the mobility of visually impaired people by offering new sensing
abilities.


However, with maximum power consumption below the Watt, the system can run for


hours out of a single battery supply.


The current system still need little improvements before a perfect fit to the application but
demonstrates perfectly its usability
.



Virtual Reality for the Nearly Blind
-

http://www.cs.bris.ac.uk/Research/MobileWearable/blind.html


This project seeks to use the capability of the neural network classifier developed at Bristol
University to provide navigation clues for people with low vision.


This neural network classifier is capable of recognizing common objects in outdoor scenes and
can label over 90% of the objects in an image into the correct object classes.


The new system will involve a small camera, which will pass images to a small computer which
will then display a highly stylized image of the scene on a pair of virtual reality spectacles.


Important objects such as cars, roads and pavements will be presented in vivid, highly contrasting
colors for easy identification.


This project started in 1997 with funding for a 3
-
year PhD studentship provided by the National
Eye Research Centre. Additional funding for a further PhD student and a 3
-
year Research
assistant has now been provided by EPSRC and Quintek plc.


Subjects for testing the system will be provided by the Bristol Eye Hospital. Initial tests of the
system on a low vision subject from the Bristol National Institute for the Blind has demonstrated
that such a system can provide a considerable improvement in the subjects ability to interpret a
scene.


Algorithm for collecting and processing data for the wearable device

foreach(sonic sensor in device){


foreach(dataslot in queue){



If (data is highest recorded)



Record as new high



If (first data collected for a sonic sensor)



Continue



Else



Store the data from the sensor in the queue


}

foreach(data in queue)

Find lowest for this set and divide it by highest ever recorded and record it

}

Record reading from infrared sensor

If (irdata less than acceptable range to floor

OR difference between previous irdata readings is greater than acceptable
range)


Set output of the motors to full power and activate both


Continue

If (center sensor is less than normalized middle range)


Set output of the motors to medium power and activate both


Continue

If (left sensor is less than normalized close range)


Set flag to set output of motors to weak power and flag to activate left
motor

If (right sensor is less than normalized close range)


Set flag to set output of motors to weak power and flag to activate right
motor

Activate motors and output power according to flags

Repeat until it stops sensing

Sensors Circuit

Schematic

Microchip

Program

Pseudo
-
code

Table on the left

Chair on left

Facing chair

Chair on right

Set down sensors

Future Works


Quality of life Survey


Integrate other sensors for a more robust system


Creating the location device and money denomination device