At the Edge and Embedded in the System
Once one has decided to purchase some form of a video analytics solution, the question often becomes: should the analytics come built into the software or would it be better to have them at the edge, that is, in the camera? The answer to that depends upon the purpose of the application. For instance, in a situation in which the user needs video analytics to know if a person has trespassed onto the rooftop of a high-security building, it will generally suffice to have a system that can distinguish between a human form and something else, like a bird. If the only need is to know whether it’s a person or a bird (or some other kind of animal) on the roof, then having the analytics built in at the edge, right into the cameras, will suffice because there is not a need to cross-reference a database to make any sort of identification.
However, extending this same situation, what if security spots a person in the parking garage at an unusually late hour and wants to try to identify the individual via facial recognition? To do so, security personnel may have to cross reference various databases, in which case having a system where the analytics are built into the software of the system will be most beneficial.
Adoption: One-Stop Shopping or Buying Down the Line?
There are often questions as well about the adoption process related to video analytics. In some cases, a user may not have a pressing need for video analytics and simply deals with their immediate security requirements and opts for basic VMS features, with the idea that down the line, if they need analytics, they can always bring in another vendor who specializes in that. The problem that many end users have found out from hard experience is that analytics is not a simple add-on and that dealing with a different vendor can be hugely disruptive to their whole video surveillance system.
Security professionals are all too familiar with the sort of Murphy’s Law that comes into play when adding new software programs to a system and if something can go wrong, it often does. As a point of comparison, changing to a new video management system is as challenging in its own way as changing one’s whole system from Windows to Mac or Linux. The learning curve for the operators and administrators, including intensive, costly trainings and system downtime can quickly become overwhelming. The decision for the video management and analytics platform has to be very carefully evaluated. Users should consider systems that utilize intelligence at the edge but also have the built-in capabilities of all other analytics. That way, modules can be switched on as they are needed while the staff has the convenience of the same well-known management platform.
True Intelligence and Open Architecture
A truly intelligent system will be able to analyze an event in depth and make or propose a decision regarding that. For instance, the ability to detect motion does not by itself make a system truly intelligent. As with our earlier example, the ability to distinguish between a human form and a bird, or to send an alert if a car is broken down on the highway, or to spot a package that has been left on a subway platform and notify relevant personnel—those are characteristic of a system with real intelligence.
In regards to architecture, it is not enough that a system provides video analytics, but interfaces need to be in place so that it communicates with other security applications like fire and burglar alarms and access control. This makes is possible to cross-verify information or provide video information for each system where an alert has been triggered.