New technologies reduce nuisance alarms for outdoor surveillance
(Editor's Note: This article first appeared in GSN's "Essential Guide to Video Surveillance," which accompanied our September 2010 print issue.)
Nuisance alarms can undermine security effectiveness and cause security teams to lose trust in their systems. Once nuisance alarms become part of the “background noise” of a dysfunctional security system, they can negatively impact accountability of the entire security organization and eventually condition security operators to ignore valid alerts.
Fortunately, there are new solutions available for outdoor surveillance and perimeter detection that virtually eliminate nuisance alarms, while providing higher levels of security and cost efficiency.
It is not uncommon for facilities with large outdoor surveillance areas to receive hundreds or even thousands of nuisance alarms every week. At the core of the issue is that organizations commonly deploy intelligent video systems that were originally designed for static indoor applications. Such systems are not equipped to compensate effectively for the much more challenging outdoor environment, where random movements from trees, weather changes, cloud shadows and small animals are all common. When indoor systems are misapplied to protect a facility's perimeter or buffer zone, the recurrence of nuisance alarms can undermine the mission critical objective of a perimeter security system -- to provide a first line of defense against potential threats. Often, the only option left in such cases is to decrease the system’s detection sensitivity in order to decrease the number of nuisance alerts. As a result, there is a high likelihood that such systems will never detect the threats that they were intended to stop.
Designing and implementing an effective outdoor security system without nuisance alarms and misdetects require surveillance systems specifically designed to provide accurate detection in outdoor environments despite uncontrolled factors. This starts by employing a higher degree of on-board image processing that accurately discriminates legitimate targets from extraneous surrounding motion and clutter. Such processing power within the camera can be used to stabilize images electronically before video content analysis takes place. This removes camera motion as a source of nuisance alarms, since video analytics software cannot detect an object entering into view if the whole scene is moving from wind. Such in-camera processing can also filter water reflections and tree motion as sources of nuisance alarms, and dynamically correct lighting to detect events that would otherwise be missed.
Additional environmental factors that are common causes of nuisance alarms can also be alleviated by sufficient processing techniques. Examples include the sun moving across the sky, clouds constantly in motion and shadows moving through a scene, all of which must be filtered so they do not appear to be targets that trigger alarms.
When such processing capacity is placed directly within the camera, 100 percent of the raw scene data becomes available to the analytics, providing an opportunity for making much more accurate determinations. In systems that employ video content analysis outside of the camera, such data must be compressed for network transmission, removing much of the finer scene details. Such extra processing can also be used to geo-register a camera's field-of-view to GPS coordinates, allowing the analytics to make very accurate determinations regarding target location, size, bearing and speed. Such geo-registration can be used to filter out small objects from triggering alerts, while also displaying a target’s precise location in the scene -- information which is not needed for indoor surveillance but becomes critical when protecting large outdoor areas.
The economics of covering large outdoor areas is also different. Outdoor surveillance involves additional infrastructure costs, including engineering design, construction, trenching, camera poles, network connectivity, video display and storage. By providing the appropriate level of computational power, such outdoor cameras are able to cover great distances, as much as three to five times the distance of indoor surveillance cameras, reducing the number of cameras, infrastructure and associated costs. While outdoor cameras may have a higher cost per unit, their extended range from extra processing leads to an overall reduction in project costs.
Applying new solutions with enhanced processing capabilities is the key to eliminating nuisance alarms. New tools designed specifically for outdoor surveillance offer the long-promised benefits of intelligent video -- and deliver new benchmarks in performance and cost efficiency for security professionals.