Surveillance camera use is growing ever faster. That’s an indisputable fact. And the fact is backed up by the numbers. While camera deployment figures may be up for debate — 2.75 million in China; 4.2 million in the UK; 30 million in the US; 40 million worldwide — there’s no arguing the exponential growth in CCTV camera sales.
A recently released report, Security Systems – The European Market 2008 to 2013, forecast that aggregate growth of CCTV/video surveillance sales will be 3.6% in 2009 “but that this will pick up thereafter and CAGR will be 5% up to 2013.” Last May, research firm RNCOS estimated the global CCTV market to be worth more than $13 billion in 2009, with growth at a CAGR of more than 27% during 2009-2012. And in April, ABI Research forecast “the total video surveillance market to be worth more than $41 billion in 2014.”
Indisputable facts. What does come into question is the value of all that recorded footage. Simply put: Who will watch the vast amounts of video footage being generated daily? How valuable is that footage if it can only be used after the fact for forensic investigation? And how much more valuable would that footage be if it could be investigated in almost real-time?
“Monitoring video screens is both boring and mesmerizing,” is the oft-quoted phrase from a 1999 National Institute of Justice report, The Appropriate and Effective Use of Security Technologies in U.S. Schools, which cited experiments run in the 1970’s “to test the effectiveness of an individual whose task was to sit in front of a video monitor(s) for several hours a day and watch for particular events. These studies demonstrated that such a task, even when assigned to a person who is dedicated and well-intentioned, will not support an effective security system. After only 20 minutes of watching and evaluating monitor screens, the attention of most individuals has degenerated to well below acceptable levels… This is particularly true if a staff member is asked to watch multiple monitors.”
There is no reason to assume that human behavior has changed. Take as proof the following quote from the landmark 2005 study by the UK Home Office, Assessing the Impact of CCTV, describing the behavior of control room operators who monitored several town centers. The operators tended to monitor busy areas only. “This neglect of quieter areas had a range of impacts. Operators were less likely to spot a live incident in residential or quieter areas but would rely principally on recorded evidence.”
In short: No one is watching the boring stuff, the quiet, out-of-the-way places, characterized by routine repetitive events. Places where nothing happens for hours on end. Until something happens. And then it’s too late.
Video content analytics is an excellent tool for detecting pre-defined suspicious behaviors – so-called “unusual events”. But there are many innocuous behavior patterns still undefined by analytics. And there are others that can never be defined by algorithms. Only the human eye can tell the difference between a comradely slap on the back and a malicious one. Only the human brain can differentiate between an envelope delivering birthday greetings and a similar-sized envelope filled with contraband. Only human instinct and experience can sense if someone carrying a backpack down a set of subway stairs is a friend or a foe.
There is an acute need for technologies that can assist operators in browsing massive quantities of video footage, and leveraging their experience, intelligence and instincts to review, identify, investigate and take action if necessary. Decision-makers should be on the lookout for those technologies that give even the least-skilled operator the ability to browse events in full on a daily, twice-daily and even an hourly basis. Those technologies are out there. Adopting them would reduce the expense of storage and the cost of personnel required to review footage manually. Events captured on surveillance video should be reviewed as part of the daily security routine – – all of them, not just the unusual ones.
Gideon Ben-Zvi is Chairman and President of BriefCam, Ltd., a developer of video synopsis technology for the rapid review of CCTV surveillance video footage. For more information, see www.briefcam.com.