Person of Interest - the workings of Video Analytics

Up to now, we have discussed quite a few interesting applications and points on visual analytics. But we have received some feedback asking to explain how it works. So here goes!

The basis of visual analytics, a practice of using computers to identify things or people of interest without an operator or a person having to view the video, are mathematical algorithms that monitor, analyze and manage big volumes of video. This means that video inputs are digitally analyzed and transformed into data that help people take decisions. It can be real time to help alert to specific incidents that could happen, such as an illegal suspect fleeing the country, and so on, or they can be post-event, looking incidents that have already occurred, for example a bombing or a fire in a store.

VA can happen in the centre, for example a central monitoring station, at the "edge", built into cameras which is ideal to locate live happenings, or as a combination of both. The optimal place to locate post-event analytics is on a central server as it is possible to search a large amount of recorded video for events, however this requires network capacity and processing power. But the main point on VA is that it works on motion detection and pattern recognition.

Motion Detection is basically examining each pixel in a given frame to detect the slightest movement. Pattern Recognition, on the other hand, recognizes specific patterns within a frame. These patterns or objects can be programmed and i.e, should a change happen or an object go missing the software immediately recognizes and sounds an alert.

The most common used types of video analytics used is violation of perimeters and recognition of license plates. Not only can this be used in surveillance, but in retail segment market analysis, to measure the number of people that pass in a given time (footfall), gender counting, shelf space effectiveness, and so on.

A fun and different way to see a little bit of VA in action, is watching a series called Person of Interest. It's just a TV show... but is it really?

Sources:
http://www.mistralsolutions.com/hs-downloads/tech-briefs/aug09-article-1.html
http://www.addic7ed.com/serie/Person_of_Interest/2/22/God_Mode
http://alexandra135.deviantart.com/art/Person-of-Interest-349555095

Visual Analytics: Integrating with every thread of our life !!

In today's world, all the application areas where large information spaces have to be processed and analyzed, visual analytics can play a pivotal role.

In line with this utility of visual analytics, major fields/sectors that are either using visual analytics  or are candidates for using it for their advantage include:
physics, astronomy, climate control, catastrophe and emergency management, terrorism informatics, border protection, investigation support, computer tomography in field of medicine, ultrasound imaging, sequencing of DNA and other biological data, human genome study, study of protein cells, combinatorial chemistry with tens of millions of compounds, financial data analysis, stock exchange trades analysis, credit card usage analysis, monitoring efficiency of prison systems, traffic light systems, airport traffic control; analysis of player data, games history, sports team analysis and much more.

The point here is that Visual Analytics is no longer constrained to being that "trendy new thing" out there for geeks to try; It is a integrating itself in every sphere of life as we know it - from DNA research to finance sector to climate control to sports to social media to crime control and monitoring. You think of a field/sector and I am sure you will find a news about how this field is getting benefited by visual analytics.

Just recently, TCS, a major technology company announced how it is using visual analytics and big data analysis to predict the future of IT industry and the trends of future.

And what do this integration of visual analytics with various aspects of our life mean? Well, to start with technological implications, remember the buzzword of 'High Performance Computing' that I had mentioned in one of my previous posts? Well, for starters, this would not be just the cool thing which is deployed only by major investment banks; it will be a necessity for every sector.

And to generalize, It is a mathematical fact that more samples you process for getting your regression model, the lower is the error value associated and no matter what sector you belong to, you have to admit that there is so much data now available to be processed and analyzed. In today's world, this 'big data' goes hand-in-hand with the various visual analytics tools, when it comes to using this data and putting it for use. I mean, along with all the other advantages that this association of visual analytics and the large volume of data will bring to your sector, you won't mind that 'added' accuracy in predictions of trends you care about most, would you? :-)

Visual Analytics: Challenges that lie ahead

It all started in 2005, when an international team of inter-disciplinary panelists from IEEE CG&A coined the definition of term visual analytics as, "Science of analytical reasoning facilitated by interactive visual interfaces". Visual Analytics and its applications in various fields of research, security and business have come a long way since then.

Today in 2013, as we take a look at various aspects of visual analytics through our blog, an obvious question that comes to our minds is, what are the potential challenges that lie ahead for this promising sector? Can these challenges be overcome?

Lets take a brief overview of all this and more in my current post.

First and the foremost of the challenges for visual analytics going forward is to develop in-situ analysis capabilities. With the volumes of data to be processed increasing by minute, the traditional approach of storing this data into conventional database and then processing it may be a major bottleneck. High Performance Computing of data, even while it is in the memory in the need of this day and visual analytics platforms need to incorporate this requirement while coming up with new upgrades.

Another major challenge comes in terms of limitations in terms of human interaction and user interfacing of visual analytics systems. The challenges in this regards are multiple, ranging from handling heterogeneous inputs to scalability to accurate representation of all data uncertainties and evidences, all the way up to limitations of human cognitive abilities to process the visual analytics data for accurate interpretations.

Speaking of human and system performance limitations, another major challenge is also of storage of huge data that visual analytics takes in. With all companies preferring cloud based storage, data required to be processed by visual analytics tools that are deployed by say Facebook is huge and requires not only huge cloud based storage, but also a capability to maintain this storage online at all times. Various algorithms which process this data in cloud, are also many a times based in the cloud and updating and maintaining these algorithms is another challenge that comes along with this.

With these huge scales of data that we are now talking about, when it comes to future and current challenges, there is also a regulatory aspect involved with various governments restricting the flow and access of data between countries and regions. These government regulations impose new constraints on efficient processing logic needed.

Well, well, well .. so much to talk about when it comes to challenges that lie ahead. So, can these be overcome?

Why not? With efficient combination of High Performance Computing [HPC] and parallel/multi-thread processing, many of the computing issues can atleast be nailed down. Government regulations cannot be helped and processing logic and storage and data retrieval mechanisms will have to find the most efficient way around.

When it comes to human cognitive skills though, who knows we may soon have to defrost the Super-Human "Kahn" and his crew that the Star Trek folks has recently succeeded to freeze into state of coma :-D

Shopping for Visual Analytics Platform??

Well, all this talk about how Visual Analytics is good or bad; and our readers must now be wondering - does this visual analytics make any business sense? is there any commercial application, or a platform, which businesses can deploy to use visual analytics for making their life better?

Answer is a big YES.
And, while there are a number of vendors currently providing Visual Analytics packages - both server based and cloud based, I found one vendor particularly interesting. Name of vendor is SAS.

In March 2012, SAS introduced its Big Data Visual Analytics Platform. This is how "Information Week" describes the SAS platform,
"It promises the speed-of-thought data-analysis capabilities of SAP Hana, the scalability of Hadoop, and the intuitive visual-analysis capabilities of Tableau. But what makes SAS Visual Analytics, a platform announced Thursday, truly stand out is the tie to the Cary, N.C.-based vendor's extensive predictive analytics portfolio.
SAS Visual Analytics is not an in-memory database. In fact, it liberates customers (and SAS) from dependence on an expensive third-party database because it holds data in memory on a rack of blades running the Hadoop Distributed File System. Customers won't have to know anything about configuring or running Hadoop, said SAS, because all the deployment, provisioning, and administration will be handled by the platform's SAS LASR Analytic Server. The platform has been tested with more than 20,000 columns and 1 billion rows of data, according to SAS, and to scale out, customers simply add more nodes."

Jim Davis, SAS' senior VP and chief marketing officer, elaborated further, "If you look at what SAS is doing versus others, we're not just exploring past activity, we're supporting analyses that are predictive, so people can see into the future of their business performance"

As an example, Davis said that predictive marketing campaign optimization efforts that now take eight to 10 hours in a conventional SAS environment can be completed in less than three minutes on the platform, and bank-risk calculations that formerly took 18 hours now take 15 minutes.

Moving a step ahead with current trends, on 1st May 2013, SAS took its visual analytics paltform to the cloud.
"Every IT organization is either building their own private cloud of virtualized systems on commodity hardware or looking to third-party providers," said SAS CTO Keith Collins, in a statement. "These enhancements will make it easier for users to access new SAS high-performance analytics capabilities in our current analytic product portfolio. Our goal is to decrease the time-to-value for SAS users while reducing the total cost of ownership for IT."

With these features and developments, SAS currently offers Business Analytics solutions for variety of industries as Banking, Communications, Education, Government, Insurance, Life Sciences, Manufacturing, Retail, Utilities, etc.

To discuss the example of its application in banking, it is interesting to know that SAS Visual Analytics can be used to visually explore data sets of any size to spot trends, patterns and hidden insights that you can use to design a strategy, confirm a hypothesis or identify a new idea. For example, you can:
- Create more personalized customer interactions and an improved customer experience based on a better understanding of customer needs and preferences.
- Quickly and accurately perform interactive regulatory data analysis to spot patterns and trends, answer regulatory questions and deliver the exact information requested during inquiries.

More information about business application of SAS Visual Analytics can be explored at their website:
http://www.sas.com/software/visual-analytics/overview.html

This post may sound like a promo for SAS, but based on my lookout, this seems to be one of the best ways to implement Visual Analytics for any business, no matter how small or big it is; and it is this practical utility of our discussed topic 'Visual Analytics' that makes all this information even more appealing to our group.

I am sure our readers will also enjoy reading this post and knowing more about a prominent Visual Analytics vendor.

If you too forget people's names, there may be a light at the end of the tunnel...

As the battle between privacy protection and tech advancement continues, apparently Google has lost a battle. Intensified arguments and concerns towards access to personal information about people and other objects viewed by the Google Glass device forced the company to ban facial recognition and voice-print apps for the device. 

This means a halt on the stalkers and creeps, but also in the advancement of the ability to identify someone and bring up allergies, for example, in the case of a doctor, or prevention of people like me facing the embarrassment of not remembering a person's name. However, we all know that new things take time to sink in, so hopefully, our name-forgetting days are counted. And if this day should come sooner than later, and you still feel unsafe, rest assured that there will always be "rebel" technologies to protect you, such as the "Glasses to stop Google Glass from recognizing your face". Now isn't that something - Japan researchers already created the antimatter of the Google Glass even before it exists...

More info: 

http://bgr.com/2013/06/20/google-glass-facial-recognition-blocking/

http://www.entrepreneur.com/article/226906