Receive up to € 20k to create your proof of concept


Access to leading corporate partners and opportunities for long-term collaboration
Receive up to EUR 20,000 in funding to draft a proof of concept – without giving up equity
Real-world use cases and unique datasets from established corporations

Data Challenges

DataHub Ruhr is a business building program that connects start-ups with established corporations in the Ruhr region. The program tasks start-ups with developing innovative, data-driven ideas to tackle use cases provided by our corporate partners. As part of a three-month collaboration, start-ups will draft a proof of concept, with the opportunity to receive up to EUR 20,000 in funding.
No items found.
Automated CAD generation from 3D Point Clouds
The RAG is maintaining and remodelling its industrial buildings on a continuous basis. A full featured BIM (Building Information Modeling) would speed up processes and increase efficiency. Detailed 3D point clouds of those buildings were already created by using drones and terrestrial laserscanning. Can you help transform these point clouds into solid objects and a BIM?

Use Case

RAG has been producing hard coal by underground mining in Germany until the end of 2018 and continues to be responsible for the resulting consequences in North Rhine-Westphalia and Saarland. For almost 200 years, thousands of mine shafts and other cavities have been developed underground, many of them at a time when computers and 3D models were still unknown. Today, preservation efforts are the main focus of RAG.

For many industrial buildings RAG performs maintenance and remodelling tasks on a continuous basis. A BIM or digital twin would speed-up planning and improve efficiency. About 20 locations were already measured by drones and 3D point clouds created. Those points do not have any semantic, but only consist of a single position in space and a color value. To create solid CAD objects from those 3D points requires significant time and effort by specialists. Additionally, the CAD objects have to be attributed to make building objects selectable, like a door, steps or just a wall.

The goal of this data challenge is to automate this process. Semantic segmentation can help to split 3D points into objects. Other techniques can help to identify objects as a part of a building. In the end, a CAD model enriched by attributes and colors is expected to be automatically created, which should be the basis for a full-features BIM in the long run. Of course, manual review of the generated CAD model will still be required, but human effort shall be minimized. 

For details on the point cloud data in .LAZ format, please download the data sample!

A project duration of approximately 3 months is expected.

What you will need

  • Expert knowledge of semantic segmentation and object recognition
  • Experience in CAD and point clouds
  • Understanding of BIM (Building Information Modeling) is a plus

Expected result

  • Solution to transform all RAG 3D point clouds into solid CAD objects
  • Objects like walls, grounds, ceilings, doors, windows get attributed as such
  • Minimal of manuel corrections required
  • CAD objects receive realistic color / texture
  • CAD objects are compatible with existing RAG viewer software (AutoCAD or Microstation (dwg/dgn) 


The project can be divided into three milestones:

  1. Point Cloud Segmentation
  2. The second milestone is reached when 3D point clouds can be transformed into CAD geometries.
  3. The third milestone is reached when CAD geometries can be correctly attributed (construction part, color/texture)
This is some text inside of a div block.

Let's talk

Felix Schröder
Program Manager DataHub Ruhr

Join the DataHub Network

We have made it our mission to boost data innovation in the B2B and industrial sectors. Become a member of our DataHub Ruhr network to receive all the latest information about exciting challenges and matchmaking events in the Ruhr region.

Let's talk

Felix Schröder
Program Manager DataHub Ruhr