Jan de Beer, MultiVid; Johan Raubenheimer, Fourier Systems and Carmen Lahr, Geutebruck GmbH note that modern video security systems are used for many different purposes and the development of specialised, integrated systems for specific environments has vastly increased the benefits they deliver to users. However, generally speaking in mining there is still considerable scope for exploiting the more sophisticated functions provided by integrated systems with data mining techniques which have added significant value in other business environments.

Besides those which secure the perimeter, environments such as diamond, gold and platinum mines normally have hundreds of CCTV cameras installed throughout the plant. These cameras are specifically installed to observe the many processes within the plant and are mostly installed in a permanent, overt manner, with portable covert cameras being used on a temporary basis. The control room operators observe the general movement of plant and people, but invariably with limited success. Without some means of effectively highlighting unusual or high risk events, video surveillance operators have too many cameras to watch all of them effectively and to pick up on the tell-tale co-incidences which could betray suspicious activities. After all, many illicit acts can be carried out under cover of apparently innocent activities.

However there are now mature intelligent video management systems which can provide strategic assistance and can integrate with virtually any source of event data. Complex rules can be constructed to take into account related, but disparate events which indicate impending failure or situations which warrant further investigation. These enable the video operator’s attention to be targeted much more effectively to potentially productive areas.

Nowadays any well-developed business administration system has many tools which allow a trend analysis of transactions to pinpoint fraud, operator input errors and much more. POS (point-of-sale) systems for example, which are used to observe cashier activities in a retail environment support real-time and post-event analysis and have proved to be of immeasurable value in both preventing fraud and proving where fraudulent transactions have taken place.

This kind of technology when used for monitoring transactions at toll plazas can handle metadata including identity of operator, event inputs from axle-counting and other road-side devices, vehicle number plate recognition, transaction detail, video motion detection, date and time etc. For toll applications a rule-based data processing engine generates events for detected anomalies. The system extracts off-line images for each of these events, while a powerful easy-to-use query tool allows the user to drill down to the relevant exceptions. This enables management to view each anomaly rapidly, and either, after auditing the event, close it off for higher management check-up, or print it via a customised and automated report writer. In the latter case an operator disciplinary investigation is possible. And being linked directly to the DVR or NVR system means the recordings can be reviewed immediately. Without this kind of rapid event viewing system, verification is a laborious or virtually impossible task, and users seldom verify events that take place.

To reveal the potential for adopting and adapting similar functions for use in mining we first need to look at systems already employed. Generally there are many process control elements such as weight measurements, conveyor belt control mechanisms (normal control and emergency stop), ore transportation systems, ore concentration or extraction processes and finally the product measuring and transport systems. Access control card readers are often installed throughout the plant to restrict the movement of people, and extended alarm systems monitor both the plant process operation and also the unauthorised opening of distribution boxes, PLCs and many other control systems.

In the ideal intelligent electronic security system for a mining operation, all the events captured in the sub systems should be critically analysed in a proper trend analysis. This would not only extract relevant process control data, but more specifically, the security risks. For example, the emergency stoppage of a conveyor belt might be an orchestrated event to create an environment in which the mined product can be removed by hand during the resultant spillage recovery operation.

Currently in such situations consideration is rarely given to which operators and security staff are on duty in the plant at the time. A well-defined trend analysis could quite conceivably extract the fact that it is always the same staff on duty when this transpires. To analyse this trend on a manual basis is nigh impossible. – Obviously the risk associated with this particular exception varies depending on the mining environment, as the concentration of the mined product may be so low that the risk is minimal. However, it may play a role within the context of the bigger picture.

Although it may be normal to investigate the unauthorised opening of control boxes, the authorised opening or dismantling of the same boxes should also be investigated for trends and hence suspicious patterns. Besides this, other plant failures such as motors, pumps etc, are seldom considered. Video motion detection events should be verified against all other events that take place, and both overactive alarms and under-active alarms should be considered.

The first weight measurements mentioned above are seldom compared against the measurement of the final product. The extended time factor from the start to finish of processing usually makes manual checking impractical. However, many sophisticated systems can be installed along this process and valuable events may be extracted from these systems to capture and highlight a trend in an exception reporting format. It is quite conceivable that a trend analysis would pinpoint a problem long before the end of the ore processing time has been reached.

Clearly any system which assists security staff concentrate on more fruitful activities increases efficiency and improves security. But the availability of a customised video security system which is integrated with other control and management systems can provide many mining operations with a very powerful tool which can deliver significant benefits in other areas too, such as safety and processing efficiency for example. Once managers realise the power at their fingertips they see new opportunities for applying it and considerable added value can be derived from the investment.

To produce an effective system a considerable amount of customisation is involved, so we are not talking here about off-the-shelf products. As a potential purchaser, you need to identify a suitable supplier who has relevant products and experience, and you also need to ensure that the chosen system has already been developed and installed successfully. This is to avoid vapourware or pie-in-the-sky systems which still need development.

You will need to confirm that all your currently installed systems can be interfaced to enable the necessary event extraction by external software controlled systems, and that software development kits (SDKs) and application programming interfaces (APIs) are available to facilitate this. If they are not, then your software integrator must be able to extract the data by other means. That person should be selected for appropriateness of skills and track record.

Alongside supplier representatives, the project team should include someone to represent you, the end-user. This person’s role is to provide the input to enable the definition and creation of a rules base which will then form the basis of the analysis through a filter process, so he needs to have an intimate knowledge of plant processes.

Any potential purchaser needs to realise that the system will need to be fine-tuned during use as everyone on the team will find methods of improving the system performance – and because of this, on-going software maintenance will form part of the complete solution.