Contents

ABSTRACT................................................................................................................3
CHAPTER 1: INTRODUCTION...............................................................................4
INTRODUCTION......................................................................................................4
BACKGROUND HISTORY.......................................................................................5
MOTIVATIONS.........................................................................................................6
SCOPE......................................................................................................................6
ASSUMPTIONS........................................................................................................6
CONSTRAINTS.........................................................................................................7
CHAPTER 2: SOFTWARE REQUIREMENT SPECIFICATION......................7
INTRODUCTION......................................................................................................7
CHAPTER 3: FUNCTIONAL SPECIFICATION.....................................................8
FUNCTIONAL REQUIREMENTS............................................................................8
NON-FUNCTIONAL REQUIREMENTS..................................................................9
APPLICATION INTERFACE...................................................................................9
LOGIN PAGE.........................................................................................................10
SIGNUP PAGE.......................................................................................................10
APPLICATION ARCHITECTURE.........................................................................11
USE CASE DIAGRAM............................................................................................11
Abstract

Most existing Augmented Reality (AR) and Mixed Reality (MR) systems are able to understand
the 3D geometry of the surroundings but lack the ability to detect and classify complex objects in
the real world. Such capabilities can be enabled with deep Convolutional Neural Networks
(CNN), but it remains difficult to execute large networks on mobile devices. Offloading object
detection to the edge or cloud is also very challenging due to the stringent requirements on high
detection accuracy and low end-to-end latency. The long latency of existing offloading
techniques can significantly reduce the detection accuracy due to changes in the user’s view. To
address the problem, we design a system that enables high accuracy object detection for
commodity AR/MR system running at 60fps. The system employs low latency offloading
techniques, decouples the rendering pipeline from the offloading pipeline, and uses a fast object
tracking method to maintain detection accuracy. The result shows that the system can improve
the detection accuracy by 20.2%-34.8% for the object detection and human key point detection
tasks, and only requires 2.24ms latency for object tracking on the AR device. Thus, the system
leaves more time and computational resources to render virtual elements for the next frame and
enables higher quality AR/MR experiences.

CHAPTER 1: INTRODUCTION
Introduction
Augmented reality (AR) is an interactive experience of a real-world environment where the
objects that reside in the real world are enhanced by computer-generated perceptual information,
sometimes across multiple sensory modalities,
including visual, auditory, haptic, somatosensory and olfactory. An augogram is a computer-
generated image that is used to create AR. Augography is the science and practice of making
augograms for AR. AR can be defined as a system that fulfills three basic features: a
combination of real and virtual worlds, real-time interaction, and accurate 3D registration of
virtual and real objects. The overlaid sensory information can be constructive (i.e. additive to the
natural environment), or destructive (i.e. masking of the natural environment). This experience is
seamlessly interwoven with the physical world such that it is perceived as an immersive aspect
of the real environment. In this way, augmented reality alters one's ongoing perception of a real-
world environment, whereas virtual reality completely replaces the user's real-world environment
with a simulated one. Augmented reality is related to two largely synonymous terms: mixed
reality and computer-mediated reality.
Augmented reality is used to enhance natural environments or situations and offer perceptually
enriched experiences. With the help of advanced AR technologies (e.g. adding computer vision,
incorporating AR cameras into smartphone applications and object recognition) the information
about the surrounding real world of the user becomes interactive and digitally manipulated.
Information about the environment and its objects is overlaid on the real world. This information
can be virtual or real, e.g. seeing other real sensed or measured information such as
electromagnetic radio waves overlaid in exact alignment with where they actually are in space.
Augmented reality also has a lot of potential in the gathering and sharing of tacit knowledge.
Augmentation techniques are typically performed in real time and in semantic contexts with
environmental elements. Immersive perceptual information is sometimes combined with
supplemental information like scores over a live video feed of a sporting event. This combines
the benefits of both augmented reality technology and heads up display technology (HUD).

Background History

AR in the 1960s. In 1968 Ivan Sutherland and Bob Sproull created a first head-mounted display,
they called it The Sword of Damocles. Obviously, it was a rough device that displayed primitive
computer graphics.

AR in the 1970s. In 1975 Myron Krueger created Videoplace – an artificial reality laboratory.

The scientist envisioned the interaction with digital stuff by human movements. This concept
later was used for certain projectors, video cameras, and onscreen silhouettes. 

AR in the 1980s. In 1980 Steve Mann developed a first portable computer called EyeTap,

designed to be worn in front of the eye. It recorded the scene to superimposed effects on it later,
and show it all to a user who could also play with it via head movements. In 1987 Douglas
George and Robert Morris developed the prototype of a heads-up display (HUD). It displayed
astronomical data over the real sky. 

AR in the 1990s. The year 1990 marked the birth of the “augmented reality” term. It first

appeared in the work of Thomas Caudell and David Mizell – Boeing company researchers. In
1992 Louis Rosenberg of the US Air Force created the AR system called “Virtual Fixtures”.  In
1999, a group of scientists led by Frank Delgado and Mike Abernathy tested new navigation
software, which generated runways and streets data from a helicopter video.

AR in the 2000s. In 2000 a Japanese scientist Hirokazu Kato developed and

published ARToolKit – an open-source SDK. Later it was adjusted to work with Adobe. In 2004
Trimble Navigation presented an outdoor helmet-mounted AR system. In 2008 Wikitude made
the AR Travel Guide for Android mobile devices.

AR today. In 2013 Google beta tested the Google Glass – with internet connection via

Bluetooth. In 2015 Microsoft presented two brand new technologies: Windows
Holographic and HoloLens (an AR goggles with lots of sensors to display HD holograms). In
2016 Niantic launched Pokemon Go game for mobile devices. The app blew the gaming industry
up and earned $2 million in a just first week.

Motivations
 Education: interactive models for learning and training purposes, from mathematics to
chemistry.

 Medicine/healthcare: to help diagnose, monitor, train, localize, etc.

 Military: for advanced navigation, marking objects in real time.

 Art / installations / visual arts / music.

 Tourism: data on destinations, sightseeing objects, navigation, and directions.

 Broadcasting: enhancing live events and event streaming by overlaying content.

 Industrial design: to visualize, calculate or model.

Scope
Regarding technological progress, augmented reality word is thrown around a lot these days. But
in addition to being used to catch Pokemon and adding filters to your Snapchat, augmented
reality is a new whole universe waiting to be explored.

Augmented reality is when a computer-generated image is projected into the environment of a

user. It is a way of blurring the lines between the real world and the digital world by
superimposing virtual images in the content of the real world.
Augmented Reality displays virtual images into reality by accessing the GPS, sensors, display,
camera and other components of hardware and software devices, typically smartphones.

Of location-based mobile applications increased, image recognition and tracking for Mobile
Apps 3D virtual applications, there are many mobile applications that use augmented reality.

The application of Augmented Reality is endless. Here is a look at the main industries in which
Apps Mobile Augmented creates a revolution.

Assumptions

Augmented reality (AR) has moved beyond headsets and gaming and into industries like
manufacturing and healthcare. Here’s how to explain what AR is – and isn’t – to a variety of
audiences. When you say augmented reality, people often think of movies like “Iron Man.” But
augmented reality (AR) has moved beyond Hollywood, headsets, and gaming and into use cases
such as inspection and repair. As interest in AR grows, IT leaders will need to discuss what
AR can and can’t do in terms that colleagues, customers, and other audiences will understand.

IDC predicts that worldwide spending on augmented reality (AR) and virtual reality (VR) will
reach $160 billion in 2023, up significantly from their $16.8 billion forecast for 2019.
“Augmented reality is gaining share in the commercial market due to its ability to facilitate tasks,
provide access to resources, and solve complex problems,” says Marcus Torchia, IDC’s research
director for Customer Insights & Analysis. Industries like manufacturing, utilities,
telecommunications, retail, healthcare, and logistics are increasingly adopting AR for a variety of
uses, including assembly, maintenance and repair, education and training, retail showcasing, and
diagnostics. Yet AR may not be that well understood by others in the enterprise. Many people
mistakenly equate AR with virtual reality, although the two offer distinctly different ways of
shifting a user’s experience. Some people assume it’s a futuristic tech. Others may have no idea
that AR could have broad applicability in the enterprise and that it can be delivered in any
number of ways.

Constraints

Augmented reality still has some challenges to overcome. For instance, people may not want to
rely on their smartphones, which often have small screens on which to superimpose information.
For that reason, wearable devices like augmented-reality capable contact lenses and glasses will
provide users with more convenient, expansive views of the world around them. Screen real
estate will no longer be an issue. In the near future, you may be able to play a real-time strategy
game on your computer, or you can invite a friend over, put on your AR glasses, and play on the
tabletop in front of you.

There is such a thing as too much information. Just as smartphone and internet addictions are
concerns, an overreliance on augmented reality could mean that people are missing out on what's
right in front of them. Some people may prefer to use their AR iPhone applications rather than an
experienced tour guide, even though a tour guide may be able to offer a level of interaction, an
experience and a personal touch unavailable in a computer program. And there are times when a
real plaque on a building is preferable to a virtual one, which would be accessible only by people
with certain technologies.

There are also privacy concerns. Image-recognition software coupled with AR will, quite soon,
allow us to point our phones at people, even strangers, and instantly see information from
their Facebook, Twitter, Amazon, LinkedIn or other online profiles. With most of these services
people willingly put information about themselves online, but it may be an unwelcome shock to
meet someone, only to have him instantly know so much about your life and background.
CHAPTER 2: SOFTWARE REQUIREMENT SPECIFICATION
Introduction

It has developed rapidly from science fiction concept to a science-based reality. AR is a type of
virtual reality where the real world is enhanced or expanded through virtual elements, usually
showcasing the elements on the view of a real world through a visual device.

Augmented reality works in different ways and used for many reasons, but in most cases virtual
objects are projected in the real world, developing an illusion that they occupy a similar space.
Augmented reality devices feature a display, a processor, a sensor, and an input device. These
devices include gaming consoles, contact lenses, eyeglasses, head-mounted displays,
smartphones, monitors, and others. Touch and sound feedback can be added to an augmented
reality system.

Functional Requirements

Overview of Functional requirements and Modules

Login: - User enter correct Email and Password to Login in Application and go to main activity.
If user is not registered then first signup to login the application.

Signup: We can get some information of user such as name, email, password and contact.

Add Assets: We can add some objects with their brief description or name of that object, we can
add and generate the pattern of the object.

Start Camera: - accessing the app through the camera. The camera in work can be back camera
as well as front camera according to the convenience of the user.

Detect Object: -The camera will point towards the object and detect it(the user doesn’t have to
take the picture, the picture will be taken automatically for the history log

Gather Information: - After detecting the object, all the related information should be loaded.
Details of information is given in next section.

Collect Sensor Data: - When the object is getting detected, the mobile will store the sensory
data from the mobile (sensors like gyroscope and accelerometer)

Create AR objects: - Based on the object detected it will create an AR object and will show on
the screen
Place AR objects: - According to the collected sensor data, the object is shown besides the
object after doing following check accordingly.

Non-Functional Requirements

 Safety Requirements
 Security Requirements
 Additional Application Requirements

Application Interface

 Splash Screen
Login Page

Signup Page
Application Architecture

Use Case Diagram