Supplai: Automated railway gate entry and exit based on OCR object detection

Cargo train
Traditionally, container numbers and wagon numbers are read with OCR technology (optical character recognition) based on photos that are put together by stitching. Increasing amounts of environmental and safety legislation and regulations mean that it is becoming ever more important that containers and wagons get the correct labels.

As a result, the need for data-driven working methods is growing and keeping information up to date efficiently is becoming more important for the entire logistics chain. Supplai has developed a Wagon Analyses Model (WAM) and a Container Recognition Model (CRM) for ProRail that meets this need.

Using artificial intelligence

Artificial intelligence (AI) and OCR are used for reading the container numbers on box containers, ISO containers, tank wagons and train chassis, in combination with the GEVI–UN* sticker and associated labels. Supplai’s solution then checks if the rolling stock has the correct labels by comparing it against the GEVI number. The solution works in real time and passes on exactly the right data for each train or truck.

What challenge does it solve?

Hundreds of freight trains from all over Europe come into the stations in the Netherlands. That is why it is important to ProRail that they can compare the wagon lists against what actually comes in. At some marshalling yards, wagons with dangerous goods are only allowed to be stationary for a limited time. This can be checked by clever camera positioning.

Because there is now a clear picture of the train wagons, it will be easier to go one step further in the future. Is there graffiti on the rolling stock, are the brake pads worn, has the revision date for the tank wagons expired, has the maximum payload been adhered to? These are all data items that are visible on the exterior of the wagons and can be detected.

Gate entry and exit based on OCR object detection

For container depots, container terminals, bulk terminals and rail terminals, the system immediately gives information about incoming or outgoing rolling stock. Combined with Supplai’s registration plate cameras, advance notifications can be checked and barriers can be opened straight away. This saves time when transporting goods. The rolling stock arriving at the terminal is thus immediately known, which cuts down on manual checks and increases safety and compliance through correct labelling.

One future development of Supplai in CRM solutions for the logistics industry could be damage detection. This saves a lot of time, money and discussions afterwards.

More information

If you are interested in automated railway gate entry and exit based on OCR object detection using AI, please visit the website for more information or watch this video.

* The danger identification number (GEVI) is a number used when transporting dangerous substances by road and rail.
Share with

More information

Building blocks

The NL AIC collaborates on the necessary common knowledge and expertise, resulting in five themes, also called building blocks. Those are important for a robust impact in economic and social sectors.


AI is a generic technology that is ultimately applicable in all sectors. For the development of knowledge and experience in the use of AI in the Netherlands, it is essential to focus on specific industries that are relevant to our country. These industries can achieve excellent results, and knowledge and experience that can be leveraged for application in other sectors.

    Become a participant

    The Netherlands AI Coalition is convinced that active collaboration with a wide range of stakeholders is essential to stimulate and connect initiatives in Artificial Intelligence. Within fields of expertise and with other stakeholders in the ecosystem to achieve the most significant result possible in the development and application of AI in the Netherlands. Representatives from the business community (large, small, start-up), government, research and educational institutions and civil society organisations can participate.
    Interested? For more information, see the page about participation.