Video Analytics for Perimeter Violation Examined

Author: Nick Grange, Published on Dec 17, 2008

Provides metrics and analysis of deploying video analytics for perimeter violation - Editor's note

For the past 3 years, my organization, C3 Shared Services, has been deploying video analytics for many facilities with the highest level of risk in South Africa. This report shares 3 key lessons we have learned:

  • Our customers demand very low levels of false alerts
  • Significant differences in performance exist between different video analytic manufacturers
  • Optimizing the on-site setup is crucial to performance

Low Levels of False Alerts

For our customers, it is common that a fee is charged every time a responder is dispatched to follow up on an alarm. The money for these fees can add up very quickly.  In fact, one of customers used to joke how false alarms from previous systems doubled the responder's salaries.  Unfortunately, high level of false alarms are not acceptable by customers - both from a cost and organization basis.

Significant Differences Between Vendors

We have been participated in numerous tests with many vendors offering video analytics for perimeter violation. The poor results can be alarming. For instance, one test had harsh environment shadows from smoke stacks and pedestrian shadows cast through concrete palisade into detection zones. We had 3 analytic vendors tested with 2 cameras each for 1 week. The results:
  • 6,000 alarms
  • 16,000 alarms
  • 175 alarms
As you can imagine, the first two (generated by two of the most respected European manufacturers) were totally unacceptable.

We went with ioimage and have been using them for many projects over the last 2 yeras.  We have deployed ioimage systems along extensive perimeters in adverse environments.

Across all of our deployments, the probability of detecting a true intruder is essentially 100%. This is actually tested by most of our customers every day and night.

False alarms have been low with the amount of false alerts depending on the environment. In our best performing environments, we rarely have more than 1 false alerts per camera per month. In our most demanding environments, with rain and reflecting light, we do not average more than 1 false alarm per camera per night.  In all cases, the operators find this manageable.

Optimizing On-Site Setup Crucial

On-site system optimization is crucial and consists of two major components: camera optimization and analytic configuration.

Camera optimization is the most important and significant part of our installations.  The cameras must provide clear images and a wide depth of field both day and night to allow for optimal alerting.

For perimeter violation, we place cameras on posts looking down the fenceline.  The distances between cameras depends whether it is a color/IR or thermal camera.
  • For color/IR infrared cameras, we place cameras every 60 meters. Our tests demonstrate that the cameras can reliably alert up to 70 meters. We provide 10 meters overlap of camera coverage to ensure that there are no deadspots and to detect anyone attempting to tamper a camera.
  • For thermal cameras, we place 75 mm thermal cameras every 400 meters. Our tests demonstrate that thermal camera can reliably alert up to 450 meters. We provide 50 meters overlap between each camera (because thermal cameras have a deadspot for the first 50 meters in front of the camera).
For all cameras, we position them 5 meters to 7.5 meters high. This height ensures depth perception.  Short heights make it more difficult to detect movement.

The positioning and the projection of light is important. We always seek to have lighting in front of the camera rather than behind. Specifically, we want to avoid aiming the camera directly into the rising or setting sun.  If we use artifical light (such as an IR illuminator), we want to ensure that the light is projected in parallel. If the light is projected too far downwards, the auto iris may reduce light entering the camera and therefore shrink the depth of the FOV.

We budget 3 or 4 hours for optimization of each camera, with tuning done during the day and a final tuning at night.

As part of this, we setup the analytics in the appliance's web-based setup.  The key element in the setup is to ensure that the depth perception is accurate because cameras provide 2 dimensional images of a 3 dimensional world.  A demonstration of this can be seen in the video below:


Finally, we make sure of monthly maintenace so that the lenses are clean and that the cameras are not moved. Dirty lenses or shifted cameras can both undermine performance so this is crucial.

All of our deployments have been done using analog cameras connected to intelligent encoders. Learn more about the details of a few of our projects.

Conclusion

While video analytics requires field expertise and care in selecting of manufacturers, we have had great success deploying video analytics.

Nick Grange is an Owner at C3 Shared Services.

1 report cite this report:

Camera Positioning Key to Video Analytics on Apr 13, 2009
A routinely overlooked but key aspect to using video analytics is camera positioning. Not simply an implementation issue, camera positioning...

Related Reports

US Army Base Specifies 70+ Outdated Hikvision Cameras on Feb 22, 2018
A US Army base has specified 70+ Hikvision IP cameras, a month after the WSJ reported a different Army base removed Hikvision IP cameras. While...
Directory of 30+ LPR / ANPR Providers on Feb 21, 2018
License Plate Recognition / Automatic Number Plate Recognition are a type of video analytics software that can identify and match license / number...
Last Chance February 2018 Camera Course on Feb 15, 2018
This is the last chance to get into the Winter camera course, starts next Tuesday. Register now. IPVM provides the best education, live online...
Hikvision DeepInMind Tested Terribly on Feb 15, 2018
While Hikvision is heavily marketing deep learning and 'AI' as their next big thing, new IPVM test results of their DeepInMind NVR shows their deep...
Hanwha Wisenet X 5MP Camera Tested (XNV-8080R) on Feb 13, 2018
Wisenet X is Hanwha's high-end camera line. We tested their Wisenet X 1080p camera last year. Now Hanwha is offering 5MP cameras listing super low...
Motorola Targets Chinese With Avigilon Acquisition on Feb 09, 2018
Motorola joins the growing list of companies taking aim at Chinese manufacturers. Recall, last week it was Hanwha: Chinese Products Damaged...
Dahua Acquires Lorex From FLIR on Feb 06, 2018
Would you buy your own customer? Well, Dahua has just done that. FLIR has sold its Lorex / home / SMB business to Dahua, just over 5 years after...
Axis 'Best' Q3517-LVE 5MP Camera Tested on Feb 05, 2018
Axis boasts of its Q3517-LVE: Simply put, AXIS Q3517-LVE delivers the best video quality possible. But is it really the 'best'? We bought...
Dahua 5MP Starlight Camera Tested (N52BM3Z) on Jan 30, 2018
Is 5MP the new 1080p? According to our recent statistics, average resolution continues to trend upwards. And now, manufacturers releasing new...
CES 2018 Show Final Report on Jan 12, 2018
This is IPVM's final edition of our 2018 CES show report. Below are already numerous images and commentary, with more coming tomorrow.   CES is...

Most Recent Industry Reports

Directory of 30+ LPR / ANPR Providers on Feb 21, 2018
License Plate Recognition / Automatic Number Plate Recognition are a type of video analytics software that can identify and match license / number...
New Whole Foods Installs Hackable Access Control on Feb 21, 2018
Whole Foods has built a reputation for high quality. And their 2017 Amazon acquisition has increased that, plus added deep pockets for buying...
Remote Network Access for Video Surveillance Guide on Feb 21, 2018
Remotely accessing surveillance systems is key in 2018, with more and more users relying on mobile apps as their main way of operating the system....
Visio For Video Surveillance Design on Feb 20, 2018
Many integrators have standardized on AutoCAD for camera layouts but new users may be overwhelmed by its learning curve. Microsoft's Visio...
Health Care Insurance Integrator Benefits Statistics on Feb 20, 2018
How common and how much healthcare coverage is typically provided by security companies? 150+ integrators explained how their companies provide the...
Hikvision Deletes Genetec Support on Feb 20, 2018
There will be no peace between Hikvision and Genetec. A year after Genetec expelled Hikvision (and Huawei, citing Chinese government control...
Change Orders - Sometimes Necessary, Sometimes Unethical on Feb 19, 2018
Change orders are a common element in project sales. Sometimes they are a necessity and appropriate ways to deal with arising issues, but sometimes...
Bosch Merges Video, Intrusion and Access Businesses on Feb 19, 2018
Bosch is merging their "video systems, intrusion detection, as well as its access control and management software business units to form a single...
Why 3VR Failed on Feb 16, 2018
3VR destroyed transformed ~$65 million in VC funding into a $6.9 million exit. The reason they failed is simple. They bet on analytics. They...
"Fear Mongering": Hikvision USA Cybersecurity Director Dismisses Chinese Government Ownership Concerns on Feb 16, 2018
The facts are: The Chinese government created Hikvision and is Hikvision's controlling shareholder. Hikvision's Chairman, a Communist Party...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact