Posts Tagged ‘ camera placement ’

Thursday, September 3rd, 2009
by Gary Myers

Since OV is the leader in the industry, we get asked a lot about analytics performance.  This can be hard to quantify as there are a lot of contributing factors. In general, accurate event detection is affected by some combination of camera angle, camera placement, lighting conditions, other environmental factors and system configuration. The goal when deploying and configuring an analytics-enabled system is to strike the proper balance between being too sensitive (causing false events) and not sensitive enough (causing missed events).

Over the years of building and testing our software, we’ve focused on three primary testing criteria when determining performance metrics: number of detected events, false events and missed events. The ideal case is to detect all expected events but have low numbers of false and missed events. If you catch all the expected events but you still have a lot of false ones, we would consider performance low as there will be too many nuisance events.  Likewise with the missed events – miss too many then overall user confidence goes down.

In future posts, I’ll cover some ways to improve effectiveness, either through camera setup or system adjustments, to enable the user to get the most from their investment in analytics.

Thursday, August 6th, 2009
by Brian Baker

“Video analytics don’t work.

I’m tired of hearing this.  As it relates to analytics, an ounce of prevention is definitely worth a pound of cure.  The success of a video analytics-enabled implementation is tied to the willingness of the seller/installer to:

- Plan system requirements with the end user
- Put the proper emphasis on camera selection and placement
- Consider environmental factors that can impact success.

I have learned from industry colleagues that the security value chain makes most of its margin on hardware.  I guess that’s no surprise given the industry is still driven at its core by physical products made of bent metal, stamped out silicon, cables and other physical components, with perhaps a bit of operating system software sprinkled in.  Also, I believe selling hardware is easier: Price it, install it, connect it, do some simple configuration, let it run, collect on maintenance contracts.

Video analytics, however, is not hardware.  The common denominator of unsuccessful deployments is the perfect storm of overselling the capabilities of the software and the lack of a trained expert when it comes time to install and configure.  Let’s first acknowledge that it’s software, and that it requires a different approach.  More next week in The Finest Whine, pt 2!