printer friendly version

Smart surveillance implications for human operators using ANPR

The marketing of video analytics and smart surveillance over the previous few years has been dominated by statements that these facilities would justify their cost by getting rid of personnel. The last few months, however, has seen a serious questioning of the worth of video analytics, with the claims of replacing manpower seen as vastly inflated.

It is unfortunate though, that the marketing focus did not rather emphasise the potential gains from the genuine potential use of video analytics to greatly enhance the performance of operators rather than replace them. Video analytics do have a significant role in security, but their integration into security needs to be strategic and consider the nature of security risk and human factor implications.

The introduction of technology enhancements in many industries, not just security, brings with it a greater demand on human processing and decision making. It may involve less people, but inevitably it requires better people who can make more informed decisions based on the increased sophistication of information produced by the technology.

I was privileged recently to be able to ride in a specially designed traffic police car in Australia that had been introduced to do automated number plate recognition (ANPR) while driving on the city streets. This ANPR continually scans all surrounding vehicle number plates on the road and compares these against an online database that contains information on the vehicle status.

This could include anything from being a reported stolen vehicle, outstanding fines, or a person of interest in various categories. In the case of reported robberies, the vehicle could also be dispatched to the vicinity to assist in wide-scale scanning and detection of the vehicle used by criminals. Once a vehicle had been highlighted by the ANPR, the police officer in the passenger seat would access full details on the vehicle owner online via a 4G cellular connection, also in real time, and a decision to pursue the vehicle or not would be made. The car represented the combination of leading edge technologies in camera recognition and processing, transmission, data retrieval and management, information management and display technology. In that sense, it is a great representation of smart surveillance at work.

While driving, the ANPR vehicle constantly comes up with status reports on other vehicles on the road, and creates an ongoing need for the police officers to evaluate the context of target vehicle status. This assessment includes decisions on the seriousness of the initial flagging (e.g., stolen vehicle versus an unpaid traffic fine, or even 23 outstanding warrants as it was in one instance). The constant recognition of issues means that at times targets had to be prioritised and one may have a couple or several issues coming up within a short space of time. Also, as the ANPR was capable of viewing vehicles on the other side of the highway, the possibility of pursuing serious offences was possible, but would require changing roads.

After the initial flagging of a vehicle, the traffic officer checks online for a more detailed profile of the vehicle in order to evaluate what action to take. Part of this is an awareness of issues pertaining to the computer classification – for instance, a vehicle may be labelled as stolen but in some cases with car hire companies, late returns automatically are classified as stolen. The officer needs to decide if this is a genuine stolen vehicle or an administration issue, and weigh this against the other targets priorities being identified.

The use of ANPR as a smart surveillance technology sounds like a simple process. It is more complex than expected, however. The quality of information and speed of information flow is obviously critical to success. If put into a live mobile vehicle, the demands and potential complexity of analysis and decision-making increases significantly. During this period, the police traffic vehicle also needs to continue to review conventional issues and violations on the road.

The calibre of these staff needs to be high, they need to have extensive training, and the situational awareness of what is on the road and the nature of the computer systems and information supplied has to be high. As indicated in the start of this article, the implementation of smart surveillance does not just mean that for technology and simple computer decision-making – the human element of interpretation and decision-making needs to be smarter as well.

Dr Craig Donald is a human factors specialist in security and CCTV. He is a director of Leaderware which provides instruments for the selection of CCTV operators, X-ray screeners and other security personnel in major operations around the world. He also runs CCTV Surveillance Skills and Body Language, and Advanced Surveillance Body Language courses for CCTV operators, supervisors and managers internationally, and consults on CCTV management. He can be contacted on +27 (0)11 787 7811 or [email protected]

Share this article:

Further reading: