Incident Management

What is being developed in the research project InREAKT

A sense of security is extremely important for passengers, especially during night time. Providing them a secure travel experience is the goal of public transport providers. Therefore it is essential to recognise security and safety hazards as early as possible and to handle them in the most effective way.The research project InREAKT deals with the development of a system that will detect critical incidents automatically, and initiate a quick and assisted response.

Early detection

A person leaves the bus and forgets a bag. It is very likely that that bag will be noticed over time and find its way to the lost & found. But, what if it was not left there accidentally? We would probably need to react swiftly. Technology exists to detect “sitting objects” by using artificial intelligence (AI).

InReakt logo

Live video streams are processed by neural networks specially trained to recognise these situations. Of course, not all sitting objects have actually been forgotten. When properly trained, however, this technology will know the difference with more certainty. Beyond a given level of probability, a threshold, the algorithms will trigger a warning report. Further individual intelligent cameras on the bus may confirm this warning, increasing the reliability of the observation. In the same way, later reports may strengthen or alter the severity and even the type of the initial report.

Eyes and ears

Sensors may detect many types of safety and security related hazards in their very early stages. An assortment of video, audio, scent, mechanical and other sensors may all individually trigger related messages that are collected in a central database, and subsequently matched, to come to an enhanced and improved conclusion. The incident management module of InREAKT will report whether there is an incident or not, and if deemed relevant enough, report it immediately to the dispatcher.

Human input

When time is of the essence, it is vital to quickly share precise information and to receive valuable feedback. This is why the exchange of information, to and from local staff, auxiliary services, passengers and bystanders is also welcome. Although professional and civilian sources should be evaluated differently, almost all human input should receive a high level of credibility, such as incoming emergency calls. Unfortunately, human input is often unstructured and therefore difficult to process automatically. A dedicated app largely helps to overcome this: one for professionals and one for civilians. The difference lies in the accepted levels of access, trust, data privacy and protection.

Assistive dispatching

The dispatcher sits at the receiving end of the generated incident reports. New alerts may flash up on his screen at any moment while he and his colleagues are handling several ongoing incidents. Their experience is often sufficient enough to quickly obtain an overview of the situation, and routinely manage the common scenarios for each type of incident.

Besides the early detection of incidents, even more precious time can be saved when the system itself provides a rather precise assessment of the situation. Ideally, it suggests the most appropriate sequence of dispatching actions to quickly resolve the incident. All the while, the system supports the dispatcher in properly informing each of the different parties involved. In parallel, a log is kept of all that happens up until the closing of the incident. The collected information will also end up in incident reports.

Self learning

This is where the log file comes in. You must learn from your mistakes, so you can continually improve your team! The system’s neural networks are trained to match initial incident reports with incidents that have been handled effectively. Feedback to adjust the parameters of the sensors is one area of self-learning. The modifications to the suggested incident handling procedures is a second.


The primary aims are to be warned earlier and to react faster and more efficiently to potential security critical incidents. INIT will be ready to support dispatching efforts, especially in such highly stressful situations. In the process, we will get one small step closer to the Future of Mobility!