Video Analytics and Facial Recognition

After this week of holidays and having presented Eye Tracking, we’re going to speak about Facial Recognition. Facial Recognition is a computer system that allows automatic identification of a person from a picture or a video frame (for example). Nowadays, it is easy to detect a face in a picture or video, the tools are performing from the moment it can detect a face on the camera or video. The smartphones, webcams and digital cameras now incorporate facial recognition as a tool for autofocus.

So what could be some of the applications of Face Recognition?

1. Police research to identify a theft recorded by a surveillance camera (close circuit television also focuses on the comportment recognition thanks to the steps analysis or suspect paths in a public area)
2.  Access control secured by a robot
3. And so on

In fact, you certainly already know about the topic via Facebook. The company had to abandon facial recognition in Europe; detecting people’s faces on pictures could put their private lives in jeopardy. But in the US, this technology keeps going: facial recognition is used by government agencies (FBI among others) and private companies. Furthermore, this technology should soon be used by the military industry. The US Air Force could have up to 30,000 drones in 2030 equipped with facial or biometric recognition allowing them to identify individuals depending on their size, age, kind and skin color. As a concrete example, the US used facial identification technologies to identify Osama Bin Laden.

So can you explain how it works? 

 

If you’re familiar with the TV show “Las Vegas” you undoubtedly have already seen it in application. Simply explained, you first need an image or video that is then sent to a software to scan it. The software will detect the position of the eyes to proceed to an alignment. In function of this alignment, a record of various characteristic points of the face is performed (nose, shape of the chin and so on). A geometric design is then saved and will serve as a base on which the researches will be performed.

So, are there any commercial usages of this? All the examples so far are military... 

Of course. The potential marketing and financial implications are pretty obvious. An Italian firm that designs mannequins has developed a model called “EyeSee” which is equipped with facial recognition cameras that record consumer behaviour and classifies them by age and gender. This will provide a better understanding of the client and how to efficiently target him. This reminds us of a passage from “Minority Report”.

Wow! This is quite fantastic....

Indeed it is! We shall leave you with one last piece of trivia. You may think this is pure science fiction but are you planning on going to Brazil for the next World Cup? If yes, be ready to be recorded by the “Robocop Glasses” that are equipped with a camera capable of recording 400 images per second and compare them with a numerical database of 13 million photos.
So if you were planning on doing something naughty in Rio, think twice! 

We hope you enjoyed this week's edition of this blog. Next week, we promise to bring you more action packed and exciting applications of the Video Analytics technology!

Video Analysis and Eye Tracking

And we're back again, and we're here to talk today about Eye Tracking technology. Surprised?

Well, you might think that that level of sophistication is still decades away but the truth is that Samsung is soon releasing the new S4, which can supposedly scroll and do many other fancy things....just by tracking your eyes. And its not just Samsung. LG is close on Samsung's tail and are working on launching LG Optimus G Pro with eye tracking technology as well. Also, Apple is embedding Eye Tracking technology to the next iPhone.

Here are a couple of links if you are interested in learning more.

http://blog.laptopmag.com/lg-samsungs-galaxy-s4-eye-tracking-tech-infringes-on-patents
http://www.phonesreview.co.uk/2013/03/17/iphone-6-or-5s-eye-tracking-and-keepsafe-possibilities/

This video should demonstrate how exciting and innovative this technology is.....

So how did all start?

Bloomberg BusinessWeek has an article which goes into how Eye Tracking evolved. Like many other great inventions such as radioactivity, and vulcanised rubber, Eye Tracking was also the product of an accident. Here's an excerpt from the article:

"In 1999, John Elvesjö, a 21-year-old Swedish engineering student, was experimenting with an infrared sensor to track movement. He had gotten the device to follow two tossed krona coins when he turned it around to look at it—and noticed something surprising. The sensor began following the movement of his eyes."

If you're interested in reading more, click here to read the full article.

How does Eye Tracking work?

It's quite simple, really. It's based entirely on Video Analytics. What you do is focus a camera on the subject's eye/eyes and using some very clever scientific tools and calculations, for example, you can figure out what the person is looking at and for how long. This is very useful because using this, you can now understand the subject's reactions to external stimuli - which can be used in ingenious ways to develop marketing tools and do psychological analytics.   

All this must be very expensive?

When you consider the sophistication of the technology, the variety of applications this has (more on this later) and the implications of understanding human behaviour, the costs actually are not so high. The reason is quite simple. We already have technology that can track items. Think about military applications - remember the Top Gun pilots "locking in" on their targets? The locks work by tracking the targets they are applied to. 

Our eyes, in reality, are not much different that any other object and hence, in the same way, can be tracked easily. The technology already exists. It just needs to be enhanced to capture the certain nuances of the human eye, like retinal dilation, etc. So, to sum up, Eye Tracking is comparatively cheaper to develop and implement. It also explains why all the phone manufacturers are doing it, right?

 

Tell me more about potential applications....

Sure. There are a lot of interesting and innovative applications for this technology but here are just a few examples:

1) Marketing
Using Video Analytics, Marketing specialists can monitor what attracts a customer's attention. How? Simply by using a camera to trace what you're looking at and for how long. In fact, this isn't even fiction any more. Its already be done and we can see the demonstration here:

2) Gaming Industry
Last week we talked about Kinect. But some firms are taking it a step further. Imagine being able to point and shoot in a video game using only your eyes!  This is still under developmental stage but already in some cases, you can control your virtual armoury with your eyes - specially in classics like World of Warcraft. Here's an example:

3) Communication
This is one field in which Video Analytics in the form of Eye Tracking could make a huge impact and make life a lot simpler for a lot of unfortunate people. We are talking here about people who have lost their ability to communicate verbally, and/or otherwise incapable of using their limbs to communicate. Eye Tracking can step in here and allow these people to communicate in ways which was not thinkable even until a few years ago. Here's an example of how this technology was used by students at the University of Rochester to help people with the Locked-In system to communicate with the world again:

Here are just three examples, and there are many more applications that this could be applied to. In fact, we haven't even covered military usage, security enhancement and more commercial usages like replacing your TV remote, etc. However, we hope this snapshot convinces you of the huge potential that this technology has and how it will change the world in which we live in in the years to come.

You've got me hooked. What next?

Next week, we intend to bring you more Video Analytics awesomeness. Do return next week to find out more applications and usages that we will present to you then! 

Actually, no. Not next week. Next week, we are off for Semana Santa. For those that aren't accustomed to Spanish holidays, its a week off we have here in Spain to celebrate Easter (or just to unwind and take a breath from the hectic pace of MBA life). But do come back in two weeks' time to check on us again! 

Till then, Happy Easters! And Happy Semana Santa!

Video Analytics in the Gaming Industry

So, as promised, we are back again. A quick recap of last week's post before we dive into this week's exciting update. Last week we spoke about what Video Analytics is, how it works and some usages it can be applied to.  If you didn’t read it, we recommend you spend 2 mins looking at the last post. In summary, Video Analytics is the usage of software to analyze video footage, and then applying this to many interesting areas!

Right, so what do you have for us this week then?

 

This week we shall look at the application of Video Analytics in the Gaming industry. Take a quick look at your Wii, or XBOX for example. You've been using it all the time, even though you might not have realised it. We hope this post captures your interest, demonstrates the awesome potential of this technology and gets you hooked to this blog!

We super geeks of the Majo Club have been playing games for a very long time now. From the Super Mario Bros 3 on the NES, to Goldeneye on the N64, and now Call of Duty on the Xbox 360; you name it, we've played it. However a new “revolution” started a few years ago, initially with the Nintendo Wii (2006), and now with the Xbox Kinect (2010).  These consoles/additions/plug-ins use motion sensor devices to detect movement from the player or controller. So you might wonder how it works?

The Wii, and also the Kinect, detects player’s movements via a camera and with the help of clever software, analyses these movements, and translates them into inputs for the game/platform you are playing on. This is bread and butter Video Analytics and might help you imagine the plethora of other applications that this simple, yet sophisticated, technology could be applied to.

Sounds fancy. Did it work at all?

 "Guinness World Records has officially named Kinect the fastest selling consumer electronics device. The peripheral sold an average of 133,333 units per day - a total of 8 million units - in its first 60 days on shelves, between 4 November 2010 and 3 January 2011." - http://www.computerandvideogames.com

So, in short, yes. Movies from the 90s and 2000s might show virtual reality as the future of video gaming. The Kinects and the Wiis have so far proved otherwise and shown that they have a firm grip on the gaming market and the future direction of gaming looks set to be headed this way. The Video Analytics way. 

I'm still a bit sceptical. Any drawbacks?

Other than putting the good old PC gaming industry out of business, and sending some of the major games developers like EA Sports and Activision back to the blackboard - none. 

Well, except maybe one. Even though Video Anlaytics seems to have a firm grip on the future of the  industry, consumers seem to be having a harder "grip" while playing these games. This video can help demonstrate what we mean....

Well, this is really funny and exciting! Tell me more....

We are out of space and out of time for this week, but next week we promise to bring you another exciting application that shows the wonders of this technology. Till then, you can browse this link for some more serious usages of the technology....

Video Analytics? You’re talking about TV umpires, right?

 

Well, sort of. And a little bit more. Video Analytics is one of the most innovative emerging technologies out there today. It holds a lot of promise for a variety of applications, and over the next few weeks we will take deep dives into a few of them. For now, let us take you through a brief overview of what it is, what it does and what it promises.

OK, so tell me what it is…

 

Firstly, it is important to understand that the “video” we are talking about here is not the video of your 3^rd birthday, or the video of your prom dance. We are talking more about live camera feeds, etc. Think CCTV and you’ll get what we mean. Or even think Live TV – the sort of feeds that TV umpires watch.

When you are looking at a video, you are identifying patterns or you are trying to detect behaviour or you are trying to analyse throughputs (or you are a veteran procrastinator). The idea behind Video Analytics is that this video or stream can be analysed for the above reasons using clever algorithms and programs rather than me and you (or a poor policewoman in the London tube) having to sit and monitor all of it. Excited yet?

Getting there. So what does it actually do….

 

A video or a stream is nothing more than a collection of images. Lots and lots of images. By writing some very clever code, and understanding the behaviour patterns and how to map them onto the video, we can analyse a whole host of things. We can see if someone has parked his or her car correctly. Or we can see if the face we are looking for is boarding any of the planes leaving the airport. Or we can also play games. You know about Kinect, right? That’s also Video Analytics as we will see in a few weeks.

Bravo! So, what else can it do?

 

For that, you must return to our blog next week. We will try to share a variety of applications that Video Analytics could be used for. It’s really ground breaking and exciting stuff. If we haven’t got you hooked in the next few weeks, then…well, then we’ll keep trying.

Wait, wait, wait…. I didn’t get who you were? 

 

Ah! Nearly forgot. We are the Majo Pundits – six very talented, international and technology-focussed budding managers currently pursuing their MBA at IE Business School. We are Catalina Tejero, Hasan Sadigli, Kyle Fraser, Marcelo M. Fonseca, Pierre Landolt and Ushinor Dey. As part of our Technology and Innovation Management course, we are researching this topic under the guidance of Professor Gregory Truman and we want to keep you updated and posted on our work.

We know that you can’t wait till next week, but till then, we’ll leave you with this little video that should get your adrenaline pumping: