by Paul Brewer

If you ask security directors how they go back into the video archives to search for something abnormal or for a specific event, the answer is almost always, “I don’t.”  Unless they know which camera feed to watch, and have a fairly good idea of the when to start searching in the video, this manual task is just too daunting. 

Video analytics has brought some much needed automation to this problem.  Now if you know where the event of interest occurred and can create a tripwire or other event rule, then all you have to do is to scroll through the alert logs and jump to that point in the video feed.

That’s great as far as it goes, but it’s still pretty limited.

What do users really want?  Based on direct user feedback, they want to be able to search for specific people, vehicles or events across the enterprise video system.  They want to use what they learn from one search to refine the next.  They want to search by example—designating a specific vehicle or person of interest to flag in a database search that might be narrowed by a specific geographic region or time period.  They want to create searches and visualize search results on an intuitive geo-interface.  And, they don’t want to just be limited to the video archives.  Forensic search results need to then become the parameters for real-time rules to find exactly where that white cargo van of interest is right now. 

This is the future of video search and it is what we are demonstrating right now for our sponsors in the Department of Defense.  A recent field exercise allowed ObjectVideo to showcase the ability to visually “fingerprint” cars that were flagged by HUMINT (human intelligence) and pick them out of the video feeds to present ultra high resolution snapshots to the “Battle Captain.” 

This was not a carefully controlled lab experiment with rigidly scripted scenarios with a small set of total vehicles.  This was a real needle-in-the-haystack exercise with a very small number of “opposition” vehicles operating on crowded public streets.  These vehicles were controlled by an opposition commander with purposes known only to him.

Besides being a great chance to show off what we can currently do with this technology, it was a priceless opportunity to learn from users and hone some new interface and workflow ideas.  When it comes to video search, the best days are still ahead, and possibly not as far off as you might think.

by Edward Troha

You know that feeling you get after a long sales campaign that you finally win?  It’s like a combination of euphoria, exhaustion, relief and a realization that now-the-real-fun-starts.  We had such a day today at ObjectVideo, releasing to the wire an announcement of our participation in a major project at The Limited women’s clothing stores.  Our partner DIGIOP Technologies, an ObjectVideo OnBoard OEM and retail provider, deployed a counting solution in some 220 Limited stores nationwide that utilized OV’s Event Counting Suite.

I won’t bore you here with the details of this story finally going public, except to say that it took a long time to get there. Even though the project has been going on for some time, the folks at The Limited didn’t want to go public right away with their innovative approach to serving their customers more effectively. They wanted to be sure they were really as happy as they thought they were.

They are. 

During that time, they gained valuable knowledge about the operation of their stores they didn’t have before.  They are correlating counts from high-performing stores and comparing them to the counts from under-performing stores.  Bottom line is they now have significantly more information with which to make informed decisions about staffing, merchandising, promotions, and the list goes on.

I’m sure DIGIOP will be very busy in their booth (359) at ASIS.  Just today we have a story (possible feature) being written about this in STORES Magazine, interest from media and analyst types (we’ll get to see them next week) and a potential TV news feature on the local Washington, DC CBS affiliate.

Against this sometimes chaotic backdrop, there’s a natural tendency to get overly optimistic about the significance of this accomplishment.  We can think we’ve turned the corner on the acceptance of analytics in the market.  We can think other partners working on big sales of cameras and encoders and DVRs will now magically win sooner with their inclusion of intelligent products in their deals.  And we can think there will be this huge tidal wave of other national retailers knocking on the collective doors of DIGIOP and ObjectVideo to get their hands on this game-changing solution.

But that’s not how it works.  I guess we’ll just keep working to educate prospective end users about the value of analytics placed within their solutions as a high-value ingredient.  Maybe we’ll continue making more positive strides in the market as we support the inclusion of our software in our partners’ products.

Or maybe we’ll just be thankful this was a very good day for video analytics. 

by David McGuinness

A very interesting thing about being the industry leader is reading or hearing how everyone else is just like us, only better.  I guess it’s true that negative attention is better than no attention at all.  And it’s true in business that industry leaders are the yardstick by which competitors measure themselves.

I think our foundational roots in computer vision R&D are what gave us an early leg-up when we launched our first commercial-off-the-shelf software product in 2003, and those roots remain a core differentiator.  We learned and adapted based on real customer deployments and recognized that the best way to meet growing demand was to become an ingredient in other solutions.  Being an ingredient and not a system isn’t the only way to go to market, but it’s the strategy that has worked for us.

I think there’s room for all video analytics business models — OV just elected not to be constrained by hardware, meaning our embedded software library can run in an edge device or on a PC anywhere in the video ecosystem.  The fact that more than 40 manufacturers have signed up to embed our ObjectVideo OnBoard software in their own products proves that our business model has legs.  More importantly, these partners are selling those intelligent products all over the world.

Supported by an incredible distribution network, we remain focused on new science and improvements, new applications, interoperability, development toolkits and training.  While these advances aren’t as eye-popping as what Hollywood portrays, they do represent a significant commitment to innovation that overcomes adoption hurdles.  That’s good for us and the industry.

ObjectVideo has succeeded and grown because we’ve advanced our science, our software and the way we go to market.  If we’re being dinged for making analytics more flexible and practical, then I’ll take that kind of negative attention any day of the week.