Raspberry Pi Augmentation: A Cost Effective Solution To Google Glass

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 03 | Mar -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 1439
Raspberry Pi Augmentation: A cost effective solution to Google Glass
Nikhil Paonikar1, Samuel Kumar2, Manoj Bramhe3
1,2UG student, Department of Information Technology,
St. Vincent Pallotti College of Engineering and Technology, Maharashtra, India
3Associate Professor and H.O.D., Department of Information Technology,
St. Vincent Pallotti College of Engineering and Technology, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In this paper, we present the concept of using a
Raspberry Pi as the main computer. This human
enhancement is voice controlled, uses a camera module to
interact with the outside world and process the retrieved
information for real-time use by the wearer. It uses this
augmentation as a brain-computer interface to connect to
the web, extract and process information from the physical
world. As a forward stride in wearable technology, this
device intends to employ the disciplines of speech synthesis,
cloud computing and image processing in order to serve the
user as a primary portable computer that is voice-enabled
and always ready for interaction.
Key Words: Wearable Technology, Augmentation,
Wearable Device, Human Enhancement, Brain-
Computer Interface, Human-computer interaction.
1. INTRODUCTION
The terms “wearable technology” refers to electronic
devices, particularly computers that are incorporated into
items of clothing and more eminent in accessories which
can comfortably be worn on the body. Wearable devices
are capable of performing many of the same computing
tasks as smartphones, tablets and laptops; however, in
some cases, wearable technology are proficient enough to
outperform these portable devices entirely. Wearable tech
tend to be better engineered and often employ cutting
edge technologies that are rarely found in hand-held
technology on the market today. These relatively new
wearable devices can provide sensory and scanning
features not usually seen in mobile and laptop devices,
such as biofeedback and tracking of physiological function.
The wearable is being developed to make it function as a
human enhancement. It is engineered to acquire data from
the surrounding environment of the user through a
camera integrated within the head-mounted augmentation
and processing that data in real-time via the Raspberry Pi.
The information obtained by processing this data will be
then projected onto a semi-transparent glass which would
be suspended to the anterior of the augmentation. This
augmentation also has an artificial intelligence that
responds to the user’s voice and performs the instructed
tasks. The system has the capability of detecting faces and
motion to some degree.
2. LITERATURE SURVEY
According to Kevin Warwick in [1], what constitutes a
Brain-Computer Interface (BCI) can be extremely broad. A
standard keyboard could be so regarded. It is clear
however, that virtual reality systems, e.g. glasses
containing a miniature computer screen for a remote visual
experience (Mann 1997), are felt by some researchers to fit
this category. Certain body conditions, such as stress or
alertness, can be indeed be monitored in this way.
In their paper on a wearable personal cloud [2], authors
Hasan and Khan describe personal terminal devices as
interactive devices capable of wireless communications
like WiFi, Bluetooth, ZigBee. Such devices include, but are
not limited to, smartphones, smartwatches, tablet
computers, smart-glasses, health monitors, and other IoT
devices. They even posit that this kind of wearable tech
utilizes lower hardware specifications to function as
resource constraint devices, in terms of computational
power, battery, memory and storage.
Computer vision [3] is the technology in which
machines are able to interpret/extract necessary
information from an image. Computer vision technology
includes various fields like image processing, image
analysis and machine vision. It includes certain aspect of
artificial intelligence techniques like pattern recognition.
The machines which implement computer vision
techniques require image sensors which detect
electromagnetic radiation which are usually in the form of
ultraviolet rays or light rays.
In his paper [4], Ronald T. Azuma describes a unique
characteristic of augmented reality; besides adding objects
to a real environment, AR also has the potential to remove
them. Current work has focused on adding virtual objects
to a real environment. However, graphic overlays might
also be used to remove or hide parts of the real
environment from a user. For example, to remove a desk in

the real environment, draw a representation of the real
walls and floors behind the desk and "paint" that over the
real desk, effectively removing it from the user's sight. This
has been done in feature films. Doing this interactively in
an AR system will be much harder, but this removal may
not need to be photorealistic to be effective.
Furthermore, in [5], Durlach tells us that augmented
reality might apply to all senses, not just sight. So far,
researchers have focused on blending real and virtual
images and graphics. However, AR could be extended to
include sound. The user would wear headphones equipped
with microphones on the outside. The headphones would
add synthetic, directional 3-D sound, while the external
microphones would detect incoming sounds from the
environment. This would give the system a chance to mask
or cover up selected real sounds from the environment by
generating a masking signal that exactly cancelled the
incoming real sound. While this would not be easy to do, it
might be possible as discerned in [6]. Another example is
haptics; the science of applying touch (tactile) sensation
and control to interaction with computer applications.
Gloves with devices that provide tactile feedback might
augment real forces in the environment. E.g., a user might
run his hand over the surface of a real desk. Simulating
such a hard surface virtually is fairly difficult, but it is easy
to do in reality. Then the tactile effectors in the glove can
augment the feel of the desk, perhaps making it feel rough
in certain spots. This capability might be useful in some
applications, such as providing an additional cue that a
virtual object is at a particular location on a real desk.
In [7], Sin and Zaman used the glasses metaphor to
present virtual heavenly bodies on AR markers which they
can manipulate in front of them. Students wore a head-
mounted display so that both of their hands would be free
to handle the markers containing the virtual solar system.
A similar study in [8], by Shelton and Hedley had
argued that this visualization is advantageous because
students can more easily understand concepts such as day
and night when they can test for themselves what happens
when one side of the earth is occluded. The Raspberry Pi is
a credit card-sized computer that plugs into your TV and a
keyboard. It is a capable little computer which can be used
in electronics projects, and for many of the things that your
desktop PC does, like spreadsheets, word processing,
browsing the internet, and playing games. It also plays
high-definition video. It is designed to cost around Rs.
2,600 for the latest model [9].
According to Reaz, et al. in [10], artificial intelligence
has played a crucial part in the design and implementation
of future houses. Early research focused on the control of
home appliances but current trends are moving into a
creation of self-thinking home. In the recent years many
research projects were performed utilizing artificial
intelligence tools and techniques. Also, research projects
employing multi-agent system (MAS); is a system
composed of several agents, capable of speedy mutual
interaction between them, action prediction, artificial
neural network, fuzzy logic and reinforcement learning. It
is found that the combination of tools and techniques are
crucial for successful implementation. A platform for future
relative studies between different algorithms, architectures
which serves as a reference point for developing more
cutting edge smart home technologies has been theorized.
According to Sherri Stevens in her research on the leading
voice controlled UIs in [11], a major issue in the marketing
research industry is the fact that the majority of surveys
are not well suited to a mobile device. In many cases, it is
difficult to see all of the answer choices on a small screen
device, as answer choices on a second page are less likely
to be selected. Using the text to voice feature on mobile
phones may be a solution to this problem. We tested
several long answer lists – resulting in sensible data. This
area of research should be explored further as a way to
obtain reliable research data from respondents using a
small screen device when long answer lists are
unavoidable.
3. SYSTEM DESCRIPTION
3.1 Raspberry Pi
Raspberry Pi (4× ARM Cortex-A53, 1.2GHz) is used as the
primary computer. Raspberry pi is a credit card sized
computer that runs a Linux distribution. It is used to
connect the camera module and perform processing for
object recognition. It is also used to set up the hands-free
prototype of Alexa Voice Service by registering as a
developer and creating a client token.
3.2 Raspberry Pi Camera NoIR v2
The infrared Camera Module v2 (Pi NoIR) has a Sony
IMX219 8-megapixel sensor (compared to the 5-megapixel
OmniVision OV5647 sensor of the original camera). The Pi
NoIR offers everything the regular Camera Module offers,
with one difference: it does not employ an infrared filter.
(NoIR = No Infrared.) This means that pictures taken in
daylight look decidedly curious, but gives us the ability to
see in the dark with infrared lighting.
3.3 Augmented Reality Display
The augmented reality display is composed of a LCD
display screen that is projected on a semi-transparent
mirror through a Fresnel lens. The LCD display is
connected to the Raspberry Pi via GPIO pins. The
“/boot/config.txt “ file is modified to display the contents

of -+the screen as a mirror image; so as to project the
original content onto the semi-transparent mirror
seamlessly.
3.4 Intelligent User Interface
Verbal commands are interpreted by a voice processing
module. Amazon’s Alexa Voice Service (AVS) is used to
take user input and produce results in the form of auditory
or visual information. AVS is Amazon’s facility to provide
voice control to any device or electronic product.
3.5 Head-mount
The head-mount is a mechanical framework on which all
the components will be physically installed. It functions as
a helmet of sorts which can be strapped on to the user’s
head. All hardware components are fit over and around
the head-mount to maintain coherence of the
augmentation.
4. SYSTEM ARCHITECTURE
The primary processing is done on the Raspberry Pi which
also serves as the core module to the rest of the modules. A
screen is connected to the Pi via GPIO pins, or secondarily
via a VNC server connection.
The contents of the screen are displayed onto the semi-
transparent mirror which serves as a real-time heads-up
display for the user.
During boot-up, the camera module is initialized and some
scripts have to be run manually on the Linux terminal after
boot up. These scripts are used to initialize the AVS API to
the camera module.
Upon successful execution, the camera can be controlled
vocally. The captured image can be reverse-searched on
the Internet to identify objects or scenes from similar
images on the internet.
The entire hardware setup is powered by a 10,000 mAh
power bank. The augmentation can be supplied power
consistently for almost 14 hours. All constituent modules
including the Raspberry Pi, the headset, camera module
and peripherals (if any) are supplied power from the same
source.
Fig -1: Architecture of Raspberry Pi Augmentation
5. CONCLUSION
The augmentation is a cost-effective solution to available
wearable technology. Even its battery backup is more than
10 hours which is significantly ahead of current wearable
technology.
Besides low cost and high energy efficiency, the
augmentation is nowhere as disruptive as its competition.
It does not bother the user with unnecessary information
and its updates, backups are made when the device is being
charged.
The overall design of this wearable device has six modules;
the Raspberry Pi 3, which is the main processing unit of the
augmentation. The second module consists of the display
screen and the augmented reality display. The third
module is the intelligent user interface that responds to the
user’s requests via the fourth module; i.e. voice automation,
which will be effectuated using Alexa Voice Service. The
visual data acquisition will be done by the fifth module,
consisting of a camera without an infra-red filter. A minor
module to facilitate voice input will be a headset with a
microphone that will be used to receive vocal feedback
from the IUI in addition to controlling the wearable via
vocal commands.

The wearable acquires data from the user’s surroundings
and process it to provide information that will help the
wearer make better decisions. It works as an assistive
human enhancement by providing real-time information,
generated by processing the visual data from the user’s
surroundings and vocal commands given by the user using
the augmentation’s intelligent user interface.
REFERENCES
[1] L. Zonneveld, H. Dijstelbloem, D. Ringoir, “Reshaping
the human condition: exploring human enhancement,”
Amsterdam School for Cultural Analysis (ASCA), 2008.
[2] Ragib Hasan and Rasib Khan, “A Cloud You can Wear:
Towards a Mobile and Wearable Personal Cloud,”
University of Alabama at Birmingham, 2016.
[3] Pranav Mistry, Pattie Maes, “SixthSense: a wearable
gestural interface,” 2008, MIT Media Laboratory, 2008.
[4] Azuma, R.T., “A survey of augmented reality,” 6(4),
pp.355-385, 1997.
[5] Durlach, Nathaniel I. and Anne S. Mavor, “Virtual
Reality: Scientific and Technological Challenges,” (Report
of the Committee on Virtual Reality Research and
Development to the National Research Council) National
Academy Press. ISBN 0-309-05135-5, 1995.
[6] Wellner, Pierre, “Interacting with Paper on the
DigitalDesk,” CACM 36, 7, 86-96, July 1993.
[7] A.K. Sin and H.B. Zaman, “Live Solar System (LSS):
Evaluation of an Augmented Reality Book-Based
Educational Tool,” Proc. Int’l Symp. Information
Technology (ITSim), vol. 1, pp. 1-6, June 2010.
[8] B.E. Shelton and N.R. Hedley, “Exploring a Cognitive
Basis for Learning Spatial Relationships with Augmented
Reality,” Technology, Instruction, Cognition and Learning,
vol. 1, no. 4, pp. 323- 357, 2004.
[9] Raspberry Pi - Teach, Learn, and Make with Raspberry
Pi, [Online]: http://www.raspberrypi.org/help/faqs
[10] M.B.I Reaz, “Artificial Intelligence Techniques for
Advanced Smart Home Implementation,” ACTA TECHNICA
CORVINIENSIS- Bulletin of Engineering, ISSN 2067-3809,
2013.
[11] Sherri Stevens, “Giving Voice to Research,” CASRO
Digital Research Conference, Nashville, 2015.K. Elissa,
“Title of paper if known,” unpublished.

Raspberry Pi Augmentation: A Cost Effective Solution To Google Glass

More Related Content

What's hot (20)

Similar to Raspberry Pi Augmentation: A Cost Effective Solution To Google Glass (20)

More from IRJET Journal (20)

Recently uploaded (20)

Raspberry Pi Augmentation: A Cost Effective Solution To Google Glass