MORE THAN nine out of ten (93%, in fact) of England-based medium and large-sized businesses running CCTV systems with video analytics capabilities still find that they are generating too many false alerts linked to poor installation, maintenance or configuration.
For example, 27% of all system decision-makers questioned have reported an excess of false alerts being generated by their CCTV systems because of incorrectly specified or configured video analytics software. Just 7% of those running video monitoring systems with video analytics have reported receiving no significant false alarms from their systems.
These are some of the stark findings of a new market study focused on video analytics usage in video security systems commissioned by security tech firm NW Security back in May.
There is also clear evidence to suggest that video analytics vendors are sometimes guilty of over-promising and confusing the market with the language that is used in their sales and marketing literature:
One third (33%) of system owners have found the language vendors use in sales and marketing literature (such as AI analytics, deep learning, Analytics+ and smart motion detection) confusing. Nearly one-in-three (28%) went further to declare vendors’ literature ‘misleading’ and containing ‘too much over-promising’.
On a more positive note, 30% of firms believe that the video analytics software they use does help in reducing false alarms in their systems, in turn rendering systems more accurate.
Frank Crouwel, managing director of NW Security, commented: “There are some realities to video security system installations today which are often overlooked at the install stage or during configuration. For example, day/night cameras with built-in infrared lighting can be a problem at night because the light and heat from these cameras attracts insects which can then obscure the field of view and set off false alarms. Far better to site lights away from the cameras so that they provide the right level of lighting for the coverage area, but no insects are drawn close to the camera.”
Four out of every ten (ie 41%) of video system decision-makers reported obstructions on their CCTV cameras such as dirt or insects causing false alerts – the single most widespread cause of false alarms, in fact.
“Video analytics such as ANPR depend heavily on camera location. The ANPR camera must be installed at the right height and at the correct angle and distance from the vehicle, considering the speed of the vehicle when the plate is to be captured. You also need to consider environmental conditions such as rain or snow, as well as camera imaging performance itself, in order to cope with bright headlights and potential reflection from nearby objects.”
Crouwel continued: “For example, we have found problems with number plate reading accuracy where rain puddles build up between the ANPR camera and the vehicle whose number plate the camera needs to read. If the camera is not positioned, specified and lit correctly, the ANPR camera might pick up a distorted reflection of number plates in that puddle instead of the direct view of the plate on the front of the vehicle, in turn creating an alarm as the number plate logged by the system does not match the pre-authorised vehicles.”
Investment in analytics
Nearly a third (32.2%) of the full sample of 152 video security systems decision-makers whom NW Security contacted across England declared that they were not investing in video analytics or were otherwise unsure of the status of the video analytics software in their CCTV systems.
Of this group of video analytics sceptics, the main reasons for not investing right now were linked to lack of resources. 31% did not have the budget to invest in video analytics this year, while 29% were conscious that they needed to hire an expert integrator or security consultancy to help them with video analytics selection and configuration, but had not yet done so. Nearly one-in-five (18%) had other higher priority video security system improvements to complete this year.
64 High Street, RH19 3DE
04478 18 574309