Real-time monitoring of busy stations helps to spread travelers better

The spreading of travelers on the train or metro starts at the station. By making crowds visible in real time, specific measures can be taken per platform. This can be done by combining check-in and check-out data with image recognition, says Mathijs Voorend of Thales. Existing cameras can even measure whether a meter and a half distance is kept.

Monitoring crowds at stations is not new, but it is suddenly a lot more relevant since the outbreak of the corona virus. “Now busy is quickly too busy. If you, as a transport operator or station manager, can measure this, you can, for example, stop escalators or close platforms. Or travelers, before they are on the way, ask to leave half an hour later, ”says Voorend.

Hong-Kong
Thales has been working for some time with IT systems that convert workload into data. A few years ago, together with the Hong Kong carrier MTR, a system was developed to use check-in and check-out data to determine in real time how many travelers are on a specific metro platform. “You know how many people fit in a metro, what the timetable is, whether a vehicle is delayed, and how long it takes to walk to the platform after checking in. That way you can calculate how many people are waiting.”

In Hong Kong, the system serves to improve service levels on one of the busiest networks in the world. The data also provides insight into the waiting time on the platform and the number of travelers who have to let a metro pass, because there is no space left. MTR uses this data to "guide" travelers by providing information about expected crowds. If it is busy on a particular line in the morning, it probably will be in the afternoon.

MTR learned about the behavior of their travelers. The carrier saw that some travelers, for example, first traveled two stops back - in the wrong direction - to a quieter station. Voorend: "Apparently it is worth that extra travel time for some, to have a seat for the next half hour."

Image recognition
Nowadays, a Hong Kong metro station cannot be compared with, say, Amsterdam Central, where train travelers can choose from numerous platforms from the same check-in gate. That is why Thales also developed a system with which existing cameras continuously measure how many people are on a certain part of a platform or in a station hall. For example, action can be taken when it is busy at the escalators, but not at the end of the platform.

It is about image recognition and not face recognition, emphasizes Voorend. “It is purely an algorithm that recognizes a person and distinguishes it from a trash can, dog or suitcase. It measures how many people there are per square meter and how close they are to each other.” In this way it can also be determined whether a distance of 1.5 meters is kept. In addition, the cameras can recognize whether luggage has been left behind, if there is aggression, and if someone is wearing a mouth mask.

The two systems complement each other and together provide good insight into passenger patterns. Check-ins do not say everything about the many platforms that travelers go to, while cameras do not have every corner in the picture. “Combined, you can easily determine where it is busy and at what times. You can steer and communicate on that. It is up to carriers what they do with this. "

Share data

During busy times or events, there is often a need to share data with other parties such as the police. Or, as a transporter, using cameras from the municipality around the stations and bicycle parking facilities, to gain insight into travelers heading for the trains. Thales developed the Secured Sharing platform for this purpose, with which all this data can be safely brought together and shared in a segmented manner.

“For example, NS supplies the check-in and check-out data, the municipality provides the traffic data around the station and ProRail measures how heavy the train is. If you combine that, you get a picture of how busy it is and how busy it will be,” explains Voorend. The big advantage here, he says, is that the owner of the data always keeps control with whom, what and when data is shared. So that conductors at Utrecht Central cannot view unnecessary information from Amsterdam Central, and the police only have access if something really goes wrong.

This article appeared earlier on www.OvPro.nl