Posts Tagged ‘ Business intelligence ’

 
Friday, April 2nd, 2010

by Bob Cutting

ISC West asked ObjectVideo to participate in a panel discussion on the topic of where video analytics will be in the next 10 years.  Past events hosting such a discussion have yielded a somewhat “same old, same old” outcome.  But I thought the discussion at ISC resulted in a much more productive outlook to where video analytics is heading with respect to analytics technology and real world solutions for end users. 

 My key takeaway was a very consistent message from the panel on the age-old question of “where analytics?”—referring to whether we will see more analytics on the edge or on a server.  We all answered in our own way, but as I was listening to all the responses, I realized we were all saying the same thing.  What finally came out is that the question is typically only answered half-way.  People focus more on real-time video processing for event generation.  But there’s a growing solution focus on using those events or underlying metadata in more advanced ways, either for forensic searching or for correlation to other sensor outputs and data streams (POS, ATM, access control…)

So while it’s hard to argue against using edge devices with embedded analytics for video analytic processing and real-time event and data generation, there is a growing solution based on leveraging that data across multiple cameras and locations for advanced business analysis and innovative detection scenarios using multiple data inputs that require back-end, server-based systems to manage the data correlation and detection/search policies.  We’re seeing this exact trend in the market, and these future solutions further justify the value that can be extracted from video analytic technology.

 
Friday, February 12th, 2010

by Bob Cutting

Maybe it’s just me but I’m tired of hearing that analytics are “still not ready for prime time.”  In fact, on a weekly basis we see and hear about partners selling and deploying successful solutions using our analytics.  We don’t see the same downgraded projection for market adoption and, frankly, business is looking good, especially in the business intelligence arena.

But I get it – adoption has been slower than expected and hurdles still exist to deploy analytics successfully on a broader scale.  My objection is that the blame for this is often (sometimes correctly) assigned to the analytics companies.  But there are other factors contributing to this.  And, it’s easy to point the finger at the SI community, claiming they need to be “better trained and equipped,” but that’s a tired argument.  My biggest disappointment stems from video analytics not being accepted due to an organization’s inability to support technological change.  This can come from regulatory agencies, standards initiatives and the customers themselves not being functionally ready to incorporate new technology into their business practices.  Is it due to dated acceptance processes and/or antiquated corporate governance?  Whatever the cause, this techno-aversion can derail an organization’s efforts to improve efficiencies and be more competitive.

ObjectVideo experienced this during a recent pilot at a major casino.  As many state gaming commissions require casinos to pay a headcount tax, they often require casinos to have reliable primary and backup systems to report those counts.  It’s no surprise the casinos don’t want to pay excessively for a counting system that exists only to support another cost.  Compared to costly, bulky, manual alternatives, a video-based system is a perfect fit since it involves cameras (pulling those out of inventory and mounting them is a daily practice) and inexpensive analytics software that resides on those cameras or on a COTS back-end server.

 The expectations were high.  Our OEM partner was told up front the requirement was 98% accuracy, which is pushing the performance envelope in such a busy environment.  Turns out we had no problem achieving that, plus we had a great technology partner involved and a supportive end customer who was motivated to make it all work.

But there was one problem.  This particular state had loss limit laws, which have since been lifted, that required casinos to report head counts in 2-hour intervals at the same expected accuracy level of 98%.  Although it no longer has any validity with the loss limit legislation lifted, the 2-hour requirement is still in place.  Essentially, it’s a remnant from an old law, but something the gaming commission continues to require.

ObjectVideo’s results were consistently above the 98% mark during the ‘round-the-clock trial but every now and then we strayed out of the +/-2% band for one of these 2-hour increments.  Unfortunately for everyone, that became a NO GO.  Consistent 98.7% accuracy counting people in a busy casino with a standard deviation of only +/-1% didn’t meet the spec!

Cynics will argue that analytics failed in this case.  Not at all.  Our partner brought an excellent technology solution to their customer in their role as trusted advisor for video and surveillance systems.  The casino was extremely happy with the results and the effort everyone put in, so we now have an ally who can lead us to some of their other portfolio properties

In the end, the casino lost because of the antiquated legislation.  Instead of a video-based system that would have cost only a few thousand dollars all-in, they were forced to invest in a more expensive manual system – something they didn’t want not only based on the high cost and disruptions during installation, but also because the physical system would lower overall aesthetics and tend to make patrons uncomfortable.

Technology innovation is all around us.  Yes, there are times when technology doesn’t deliver on its claims and the technology companies become their own worst enemy.  But there are just as many times when new technology proves to be a clear winner that can save money and make sense for an entire industry.

This time the house lost.  But in due time the gaming industry, as well as a host of others, will win big.