At the edge or system embedded?

Optimize video analytics based on the application

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; if something can go wrong, it does often enough. 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 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 true open architecture

Regarding the issue of intelligent video analytics, integrators need to look at some key criteria, namely that 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, are characteristic of a system with real intelligence. To that extent, end-users need to question security professionals about the criteria they use to define truly intelligent video analytics.

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 it possible to cross-verify information or provide video information for each system where an alert has been triggered. For example, in the event that a back door alarm sounds, security personnel should be able to not only view who triggered the alarm but know if it is someone who has a history of such activity. To that end, the alarm must interface with a facial recognition or face capture system that can provide the information. An access control system that employs card swipe should have that same capability. If, for instance, an employee is swiping in after hours, the system should be able to provide video immediately so that the system can verify that it is the employee in question using the card (and not someone else or perhaps a case of forced entry). Such interfaces ensure making optimal use of video analytics in relation to the whole security system.

Both the public and private sector have an increasing need for video analytics solutions. This includes banks, retail, property and building management firms, government agencies, law enforcement and counterterrorism units. However, it is only with the smart combination of all involved security processes, including non-video related information sources (such as access control and asset management) that the user can reap optimal benefits. Video analytics supports the decision process, but only the cross verification of events with other devices and databases creates a truly smart system.

For cash-strapped law enforcement agencies, such a system can reduce the need for more personnel as well as be an important crime fighting partner and an aid in traffic safety and generating revenue by spotting more offenders (whether it be running red lights, illegal turns, etc.). Counterterrorism units simply demand the latest technical innovations available, including video analytics, to more effectively spot and reduce potential threats. As the role of video analytics increases, security sales forces and integration specialists must be knowledgeable experts prepared to custom fit solutions for their customers. This is one area in which one size definitely does not fit all.

Wolfgang Ritter is the Director of Sales and Marketing at Intelligent Security Systems, an industry provider of video management and image analytic software, contact him at