Augmented Reality

Hardware/Software requirement:

•  Processor
•  Display,
•  Sensors (MEMS, accelerometer, GPS,solid state compass )
•  Camera

AR Core doesn’t require specialised sensors, but a smartphone does require special support to run
it. So smartphone should be equipped for AR Core.
Software Requirement
Android 7.0 or later and access to the Google Play Store.
Currently available Devices in the market:  Device list

Types of AR :-

Marker Based Augmented Reality (Supported by AR-Core Lib)

Copyright : SelfEye

•  Marker-based augmented reality (also called Image Recognition) uses a camera and some type of visual marker, such as a QR/2D code, to produce a result only when the marker is sensed by a reader.
• Marker based applications use a camera on the device to distinguish a marker from any other real world object. 
• Distinct, but simple patterns (such as a QR code) are used as the markers, because they can be easily recognised and do not require a lot of processing power to read.
• The position and orientation is also calculated, in which some type of content and/or information is then overlaid the marker.

For Detail Information :-   Implementing Augmented Reality in Android Using ARCore

Implementation Algorithm :-

1. SLAM (Simultaneous Localisation and Mapping) (Not yet Provided with AR Core Lib):

• SLAM is the most effective way to render virtual images over real-world objects.
• SLAM simultaneously localizes sensors with respect to their surroundings, while at the same time mapping the structure of the environment. 
• SLAM is an approach to solve complex AR simulation problems and is not any specific algorithm or software.
•  The SLAM system is, in fact, a set of algorithms aimed at solving simultaneous localisation and mapping problem. This can be done in multiple ways and now every augmented reality development kit has its upon to providing SLAM functionality.

2. Recognition based:

•  Recognition (or marker) based augmented reality uses a camera to identify visual markers or objects, such as a QR/2D code or natural feature tracking (NFT) markers, to showcase an overlay only when the marker is sensed by the device.
•  Marker-based AR technology depends upon device camera to distinguish a marker from other real-world objects.
•  Not only the marker image but the position and orientation can also be calculated.
• Once recognise the marker on screen is replaced with a virtual 3D version of the corresponding object. This is done to permit the user to observe the object in more detail and from various angles.
• Rotating the marker would rotate the virtual replication as well.

ARCore Implementation:  Recognise and Augment Images

Markerless Augmented Reality (Supported by ARCore Lib)

Copyright : SelfEye

Markerless (also called location-based, position-based, or GPS) augmented reality, uses a GPS, digital compass, velocity meter, or accelerometer which is embedded in the device to provide data based on your location.

•  It is most commonly used for mapping directions, finding nearby businesses, and other location-centric mobile applications.

Implementation Algorithm :-

•  location-based AR relies on a GPS, digital compass, velocity meter, or accelerometer to provide data about the location and the augmented reality visualisations are activated based on these inputs. 
• Some common uses of location-based AR include mapping directions, finding nearby services, and other location-centric mobile apps.

Superimposition Based Augmented Reality (Supported by ARCore Lib)

Copyright : SelfEye

Superimposition based augmented reality either partially or fully replaces the original view of an object with a newly augmented view of that same object.

•  In superimposition based augmented reality, object recognition plays a vital role because the application cannot replace the original view with an augmented one if it cannot determine what the object is.

Technologies used to recognise objects and its surrounding:

The Augmented Reality technology can work using one of the following three approaches:

Development Tools: (Tool-kits for AR Development)

1. Vuforia: need license

2. Kudan: need license

3. Wikitude: need license

4. ARKit:

5. ARCore:

Implementation to be Explored:

1. Draw custom 2D/3D figure on virtual surfaces. Recognize Virtual Surfaces by Camera and

sensor inputs. Design a figure and place it on a virtual Surface. Click here to quick start

2. Use camera to identify visual markers or objects, such as a QR/2D code or natural feature

tracking (NFT) markers, to showcase an overlay only when the marker is sensed by the device.

Recognize Images

3. Identify two similar Objects. Identify 3D objects and find the similarities between them by

using available Libraries and Algorithms( SLAM -Simultaneous Vocalisation and Mapping or

similar technology).

AR-core Android Packages:  available Packages in Java