Video analytics under surveillance

Citation

(2009), "Video analytics under surveillance", Sensor Review, Vol. 29 No. 1. https://doi.org/10.1108/sr.2009.08729aab.002

Video analytics under surveillance

Article Type: News From: Sensor Review, Volume 29, Issue 1

The increasing need for security worldwide, along with loss prevention particularly within the retail sector, has produced a surge in network video surveillance and adoption of integrated and wireless security systems. As demand spreads from North America and Western Europe to the rest of the world, a promising new technology, called video analytics, takes surveillance to a whole new level. Video analytics can perform certain functions such as identifying abandoned objects, detecting motion, and identifying traffic flow. It is useful for both security and managerial purposes.

This smart tool finds good use in a variety of markets ranging from military, banking and finance, education, airport and even in retail. Although this technology is only in its beginning stage, Frost & Sullivan is certain that video analytics has a lot of potential which can be used in many critical and non-critical verticals.

“Video analytics is the process of using algorithms and software to analyse recorded or live video coverage,” notes Frost & Sullivan Research Analyst Janaki Padmanabhan. “It is the next step to video surveillance where the intelligence of the system is utilized to enable the end-user to identify key trends and significant changes in recorded images. The end-user will be alerted when there is an unusual event. Video analytics is the key to help end-users with the abundance of recorded information.”

The downside of regular surveillance cameras is that it relies on the alertness of those monitoring the cameras. However, often the staff/guards monitoring the video footage tend to become inattentive and loose focus. These guards run the risk of missing important information, not paying attention to trends in the traffic and ultimately risking a security breach. This type of human error diminishes when the video is recorded and later analyzed, it provides better analysis of the situation and reports can be generated in desired formats. Analysis of live video coverage also brings the attention of the staff/guards to a current security issue.

Video analytics and its applications generate a buzz of interest within this growing market. The technology offers a plethora of applications already in place with this new technology. Video analytics can be used as both a security and management tool. Recently, business intelligence divides the successful from the rest. This is clearly seen in retail.

In this competitive environment, any pattern or trend that can be identified as a part of business intelligence is crucial. Retailers are looking at various avenues to reduce operating cost, increase security, and operational efficiency. Video analytics software combined with video surveillance is used to identify certain distinctive patterns. The analytics of the video can be performed either live or on recorded content. By signaling to those monitoring the footage when something unusual happens, video analytics provides intelligence alerts.

The primary drawback for video analytics in the retail vertical is that it is difficult to define unusual behaviour. How many times does a customer have to return to the same place before the behaviour is flagged as unusual or suspected of shop lifting? Some behaviours are hard to quantify and vary amongst people.

But alongside these security features, video analytics can be used as a management tool. Retailers can use video analytics to make decisions on store planning, merchandising options and to study the success of marketing plans. It tracks how many people enter the store, the direction of the traffic, the reaction to product placement, the customer’s buying pattern and which product was purchased first. It can also be used to reveal if a customer has been too long without assistance. This information can be used to convert customer’s long-dwell time to make them buy merchandise, maintain customer loyalty and continued patronage.

If video analytics vendors take the time to educate end-users on the applications and performance capabilities, we should see this new technology make surveillance more intelligent. They will also need to provide video analytics software which is interoperable with the existing video surveillance system and easy-to-use.

If you would like to receive more information about video analytics or the security industry, please contact Joanna Lewandowska at: joanna.lewandowska@frost.com