Archive for the ‘ product discussion ’ Category

 
Thursday, October 25th, 2012

by Warren Brown

I have spent the better part of the last 10 years working with integrators and end users around the world and have seen the value analytics can provide by helping make sense of an overwhelming volume of video. I have also seen the confusion, chaos and frustration that video analytics can create when the software is confusing, doesn’t work or just doesn’t make sense.

The vast majority of these failures I attribute to one of two fundamental problems:

  1. Great expectations:  as an industry, manufacturers, systems integrators, end users: we have done a poor job of really understanding what problems analytics CAN and CAN’T solve and communicating that effectively (more on this topic in a future blog post.)
  2. Integrator unfriendly: as manufacturers with teams of smart engineers and computer vision scientists, we have too often been guilty of putting technology ahead of people. We have failed to understand the real-world environments in which installers operate and have designed products that are simply too hard and confusing to get up-and-running.

It’s this second point that I want to blog about today…what does it take to deliver Integrator-friendly analytics? And what are we at ObjectVideo doing to try to live up to an “Integrator-friendly” mission?

For us, Integrator-friendly starts by understanding the end-to-end process that our Systems Integrator partners go through in specifying, ordering, procuring, installing, configuring and maintaining a system. We will only have achieved true integrator-friendly status when each of these steps is as simple, fast and as repeatable as possible.

A few examples of the Integrator-friendly changes you will see in upcoming releases of OV6:

  1. Self-calibration
    Calibrating an analytics system is an important tool to improve accuracy (watch out for uncalibrated systems!) but how about we let the system automatically calibrate instead of asking an installer to do it manually? Check out the self-calibration capability coming later this year in our version 6.2.
  2. Diagnostic mode
    As much as we continue to strive for perfect accuracy, we all know that there will still be times when there are false alarms or problems with the system. Too often, more time is spent just trying to get the right information back to the manufacturer so that they can see and solve the issue. Rather than hundreds of emails, phone calls and tons of frustration, how about a “Troubleshoot” button that captures up all the info needed to properly diagnose an issue and makes it easy to share with OV? We think of this as the “Easy” button for analytics.
  3. Online Training
    OK, so we certainly can’t claim to be inventors on this one, but we do think the interactive online training modules we are developing are a cut above anything we’ve seen out there. They will be more detailed, and thus more effective. Look for the first batch later this year as a part of version 6.2.

These three items are really just a drop in the bucket – so don’t think we will stop there! We have a lot more ideas on how to make our analytics easy to sell, easy to quote, easy to install, easy to configure and easy to maintain…watch this space for more details about future releases!

AND, if you have an idea on what else we can do to make things more Integrator-friendly – let us know at support@objectvideo.com.

 
Monday, April 12th, 2010

by Gary Myers

Earlier this year, ObjectVideo released an updated OV Ready specification and the corresponding OV Ready reference application (which now includes an ‘event push’ functionality) to our partners to incorporate onto their devices. In addition, we provided the 1.0 version of our new web UIs, which we call the ObjectVideo management console.

For those who are unfamiliar with OV Ready, it is an ObjectVideo program that constitutes a protocol specification, reference code and compliance tools to allow interoperability between various devices and applications with respect to video analytics operations and alerting. More detailed info is provided on our website.

Even though that one-sentence summary is quite a mouthful, think of HTTP as an analogy. At a basic level, it is a protocol that specifies how web browsers and web servers can talk. It doesn’t matter if you are using Firefox or Chrome or IE, you can still talk to IIS or Apache. OV Ready is similar except the focus is on ObjectVideo OnBoard configuration, rule management and event output. We want to make sure all ObjectVideo-enabled devices (cameras, encoders, servers, etc.) can be used by a wide variety of management applications (VMS, PSIMs, etc.) regardless of type or brand.

(more…)

 
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.