Background
While video technologies have long been utilised in retailing – some of the first installations of closed circuit television (CCTV) in a retail environment can be found in the 1970s – their role and indeed purpose has largely been limited by the nature of the technology deployed – analogue systems. This made them hard to use beyond offering a visual form of deterrence and/or watching events in real or near real time. There was little scope for doing more than that, for instance, searching back through recorded images was a painstaking task only possible by humans watching potentially thousands of hours of video footage, and so understandably it was only undertaken for very serious criminal cases.
The big change has been the digitisation of video technologies, in effect turning the images recorded into a data stream that can be analysed and interpreted like other forms of data. This change has fundamentally transformed the capabilities of video technologies and in turn, opened up a whole new horizon of possibilities for retailers. As well as making it more accessible – searches are now possible for particular objects and people at the click of a button, it has also brought opportunities for video analytics as well. These were defined in a recent ECR Report as: ‘a video system that uses the capacity of computers to automatically interpret digital images in order to generate clearly defined and actionable outcomes’.
Current Uses of Video Analytics in Retailing
The same ECR report also presented data on the top five most deployed video analytics in retailing to date. Based upon responses from 81 retailers from 20 countries and a combined turnover of over €2 trillion, the study found that four of the five were focussed upon generating alerts when there was unauthorised movement or access to restricted areas.
Table 1: Top 5 Currently Deployed Video Analytics in Retailing
The popularity of this use case is understandable – employing humans to keep watch over potentially hundreds of locations at the same time and looking out for the relatively rare occasions when a breach of security occurs, is inevitably expensive for the retailer and arduous for the observer. What this type of video analytic offers is in effect a digitised filter – only generating an alert for a human to become involved when something of interest has happened – bringing the vital few rather than the trivial many events into focus.
The other most highly used analytic was the use of video to automatically control vehicle access to retail distribution sites. Through the use of automatic licence plate recognition technology, together with a database of vehicles predetermined as having agreed access (sometimes within specified timeframes), retail companies are able to reduce the costs of securing access to some of their most valuable and vulnerable locations.
Future Use Cases of Video Analytics
The ECR research went on to explore what video analytics retailers were currently trialling or planning to use in the near future. As can be seen in Table 2, for all the retailers taking part (most were Grocery retailers) the future focus was very much upon the checkout area in retail stores, in particular self-checkouts. Other ECR research has highlighted growing concerns about the vulnerabilities presented by self-checkout systems and the risks they present in terms of customers not scanning items, mis-representing cheaper items for more expensive ones, and walking away from self-checkout transactions without paying. For all of these transgressions it can be seen that retailers are exploring video analytics as a way to try and control them.
Table 2: Top 5 Currently Planned/Trialling Video Analytics: All Retailers
Away from Grocery, a broader range of use cases can be found to be under consideration although the checkout remains a particular point of interest. In addition, some retailers are exploring ways in which video analytics can now be used to try and identify suspicious behaviour in the shopping aisle – in particular thieves that may be in the process of stealing produce.
Table 3: Top 5 Currently Planned/Trialling Video Analytics: Non-grocery
Video Analytics – Broadening the Use Case Portfolio
Traditionally, video technologies in retailing have largely been utilised to deal with issues associated with security and safety – detecting and deterring crime in particular. While the examples highlighted above have largely mirrored this, what was also evident from the ECR research was growing interest in developing other video analytics that can be deployed to improve customer service and retail sales. For instance, some companies are now using analytics to identify when a customer is waiting at a counter for service and automatically call for staff assistance. In addition, other analytics are being used that can automatically detect when products are no longer in stock on a shelf and generate a restocking alert.
These are indeed interesting times for video technologies and we are likely to see further growth in their use in the near future. For more information about how retailers are using video technologies in general and specifically video analytics, ECR Retail Loss has a comprehensive free report available on their website.
