Why content is key for AR platforms

Content in the context of Augmented Reality (AR), is defined as the presentation of existing information in a format applicable to the current world-view. This takes the form of visual and/or audio but can also take on other sensory formats such as touch or even smell.

This distinction between content and information is important to understand when considering the functional applications of AR platforms. In simple terms, an AR platform will not create information but rather consume it from existing sources and create, package and deliver it as AR content.

AR platforms such as Appearition’s Experience Management System (EMS), rely on the availability of information to create and deliver contextually relevant content to connected clients. AR platforms should, therefore, be regarded as mediums for connecting to existing data stores and aggregating and formatting that information based upon the context of the intended audience.

There are several challenges facing AR platforms today. At the outset, any effective platform must provide an intuitive user interface that is accessible and available to non-technical users. More often, it will be business staff who will be interacting with the platform to manage and create information and content.

  1. Access to information

A key concern of AR platforms is access to information. This demands connection and integration to various types of data stores. It comes with adherence to security and authentication protocols, data privacy laws and compliance and the support of various types of data formats such as CSV, XML and JSON.

With this concern comes the fundamental need of having a scalable, robust and highly responsive infrastructure for reliable functional performance.

  1. Contextualising information

Once information is available to the AR platform, it is important to be able to classify and group it. This will become an integral step in content creation as it will be important to link the context of the audience with the context of the information.

Meta-data is a common concept used in IT systems to help with classification. You can apply meta-data to existing information and then filter and query that when creating content.

  1. Delivering a good user experience (UX)

A well delivered UX has these two common properties: relevance to what we are doing and is quick to load. The former is something we have already touched on above. The latter is about network latency and is best understood when we think about today’s websites. According to studies, more than 40% of users bounce from websites that take more than 3 seconds to load. This is directly related to internet connectivity speeds and the amount of content being delivered to the browser. The same principle applies to AR experiences, however, instead of the latency concerns of HTML, AR is concerned about the speed of recognition, the stability of tracking and the download and rendering of immersive content such as 3D models or 360-degree videos.

A critical factor for AR is a reliable and fast wireless network connection. Whilst the current 4G technology does enable us to watch videos and images seamlessly, when it comes to immersive AR experiences, content is much bigger and heavier than standard website content. As such, we eagerly look forward to 5G which aims to revolutionise our world again with quick access to immersive content.

Whilst the promise of 5G is very much a future aspiration, there are strategies today that can be considered when designing and building AR solutions with latency in mind. Can you anticipate and pre-download AR content before the user has asked for it? Can you place content closer to the user to minimise too many hops around the world? Can you break up the content into smaller chunks and stagger how and when it’s presented?

Conclusion

In many respects, we are exposed to information all the time and in different ways. Since the dawn of humanity, we have exchanged information by communicating and interacting with each other. We then became exposed to printed information in the form of books, newspapers and magazines. In more recent times information has emerged in the form of TV and radio. Finally, the invention of the internet and social media has exploded our access to information at our fingertips. We use information all the time to make important decisions at work, school, home and in social settings. Filtering and deciphering this information in a way that is relevant to what we are doing now, has always been and will continue to be a struggle.

AR content is the means to access and view contextually relevant information in our world.

Simon Galanakis is a passionate advocate of effective AR experiences and is currently Appearition’s Platform Architect and Senior Solution Designer.

Read More

Using Machine Learning to leverage the power of Augmented Reality

Augmented Reality (AR) in its current definition is the overlay of digital information on a real-world view. In practical terms, it is the process of recognising specific physical objects in a device’s camera and superimposing digital content such as video, audio or 3D models.

Visual recognition is one aspect of AR which encompasses image, object, scene and facial recognition. Computer vision technology is used to identify shapes and patterns through a complicated set of mathematical models. These models and processes are all facets of Machine Learning (ML) that drive Artificial Intelligence (AI).

ML is the science of “teaching” the system to look for commonalities and patterns and assessing the probability that a match is found. Effectively, with a set of mathematical models in place, the system is fed a collection of information that represents a positive match. For instance, if we want to teach the system to identify a cat, we provide thousands of images of cats and let the system process and find common visual patterns across all the images.

This is known as deep learning where the outcome is a system that can recognise and track almost any pattern. With this capability, we can inject a virtual projection into the area that is being recognised and tracked to deliver, what is called, an augmented reality experience.

The power of AI and ML is being able to make decisions based on the real-world scenario. Let’s consider its application in a security surveillance system. A machine that has been trained to detect weapons, such as knives and guns, can be used to observe CCTV security vision. In real-time, it can look for patterns in the scene that resemble its definition of a weapon. If identified, a notification alarm could be raised for someone to act.

Pattern recognition is not limited to visual only. Auditory, gesture and other data patterns can also be “taught” using ML. Continuing with our security surveillance example, a trained machine could be used to listen to sounds in the environment and detect patterns of shouting or offensive language being used.

The challenges

One of the hurdles in training a machine to identify patterns is sourcing enough material that is deemed a “positive match”. In these cases, systems are designed with feedback loops to allow machines to “learn by experience”. If for some reason the machine fails to detect what it is supposed to, it can be taught what was missing in the initial dataset and be trained to act on it the next time it occurs. All this is supported by an aspect of ML called “convolutional neural networks”. Different nodes that perform specific mathematical functions on the dataset are interconnected to achieve the specified outcome.

The opportunities

In a time when vast amounts of information is available at our fingertips, being able to recognise the world around us and decipher what is relevant will become critical. Whether at work, at home or in a social setting, successful real-world augmentation will rely on AI and ML observing and recognising our environment and adapting information to match our situation.

As hardware technology improves and wearable, handsfree devices become a reality, ML and AR will become an integral, yet ambient part of our lives.

Simon Galanakis is a passionate advocate of effective AR experiences and is currently Appearition’s Platform Architect and Senior Solution Designer.

Read More

Staff blog: EMS Data Integration al dente.

It is a rare chance that we can compare the joy of fine cuisine to the rawness and relevance of data in our EMS. How can the culinary art of a top hat restaurant be linked to data integration in the EMS? Well, aside from the fact that it is too close to lunch and I am hungry, the two concepts aren’t too distant from each other.

17.11.2013 ZDJECIA WIZERUNKOWE DLA RESTAURACJI BURGER KITCHEN TOMKA WOZNIAKA , FOT. MARCIN KLABAN

Let’s see… restaurants must cater for their hungry customers. Dumping raw produce on a plate and presenting it to them simply won’t cut it. So, the kitchen must clean and prep the produce, add a combination of sauces, spices and herbs, apply heat and eventually present a meal worthy to the paying customer. Produce arrives from a supplier to the back door and the kitchen will convert that produce into something palatable for the customer at the front of the restaurant.

splunk-logo-2-300x173

Data integration follows the same paradigm. Think of the EMS as the kitchen, data providers as the suppliers and users as the paying customers. So, users make requests to the EMS for information. The EMS requests raw data from various data providers and will aggregate, sort, filter and deliver a result set to the user. Splunk is an example of a data provider, which offers an extensive and powerful service for gathering, collating and filtering vast amounts of raw data. From the user, the EMS can collect information such as their identity and their location, and with that (and more)  the EMS (i.e. kitchen) can craft a tailored query to search that raw data in Splunk (i.e. supplier).  From then, contextually relevant information can be fed back and presented to the user (i.e. paying customer)  in a palatable format.
…mmm saucey data.

Image source: (x) (x)

 

CONTACT US

[contact-form-7 404 "Not Found"]

Read More

Staff blog: eCommerce the Past, Present and Future

“True wisdom comes to each of us when we realize how little we understand about life, ourselves, and the world around us.”

Socrates 470-399 BC

Commerce is the exchange of funds for goods or services. eCommerce is the same exchange, but without the use of physical cash swapping hands.

In 1982, the United States rolled out the first EFTPOS machine. For the first time in humanity’s history, someone could [lawfully] walk into a store, buy something and take it away without any currency exchanging hands. This was made possible because the buyer was now in possession of a plastic card instead of cash. The plastic card, known as a payment card, allowed the buyer to initiate a transaction electronically to transfer money from their bank account to the store’s bank account. Ah yes, whilst eCommerce can do away with cash, money will always be needed to buy stuff.

Today eCommerce is just another part of life. Whether we are picking up groceries from the local supermarket, paying our GP to examine us or buying a gift for our loved ones, it is eCommerce that makes all this possible. Furthermore, with the emergence of the internet, eCommerce has gone to the next level. From the comfort of our couches we can now buy, sell and transact almost anything online. Services such as eBay™ and PayPal™ enable us to exchange goods and services for funds without the need for physical shop fronts. Once again eCommerce has enabled the buyer to electronically transfer funds to the seller in exchange for the goods or service they’re getting.

The convenience and simplicity of eCommerce has also brought with it the serious risk and threat of criminal activity. Today a thief no longer hides behind a ski mask and holds up banks, instead they hide behind a keyboard and seek to take money directly from your bank account. Electronic theft is a serious concern for the eCommerce industry. Organisations and governments from all over the world have adopted measures to protect and safeguard our electronic funds. Payment Card Industry Data Security Standard version 1.0 (PCI DSS 1.0) was formed in 2004 by a group of organisations which include VISA card, MASTERCARD and American Express. The standard is managed and administered by a special council and dictates how payment card information must be transmitted and stored electronically. Whist this standard is not enforceable by law [yet], it is a strong influence for buyers having trust in a website. PCI DSS is continuously being reviewed and updated. Version 3.2 is planned for release in 2016.

So where will eCommerce takes us next? Well, the concept can never change: exchanging funds for goods or services electronically. However, the means we use to perform these transactions will certainly evolve. Enter the world of virtual reality and augmented reality… where life and technology are entwined. Imagine… you are walking in a market at the foot of the great pyramids at Giza. You walk past a stall selling beautiful statues of the ancient kings and pharaohs. One particular statue catches your eye. You look at it, touch it, pick it up, turn it around in your hands. It’s a work of art and you must have it. You turn to the store owner and you haggle for it until finally the store owner agrees to your price. He takes it away and wraps it up for you. You reach into your pocket, take out your wallet and look through it. You pull out 10 Egyptian pounds and hand it over to the store keeper, shake hands and say goodbye. You take off your glasses and your gloves and you find yourself sitting on your couch in your living room on the other side of the world. Three days later the doorbell rings and the UPS person hands you a package. You open it, unwrap it and there is your Egyptian statue, exactly as you saw it… what a beautiful world it will be!

 

CONTACT US

[contact-form-7 404 "Not Found"]

Read More