GeoPointTransformer

How can 3D scans of public spaces become useful for infrastructure maintenance? GeoPointTransformer identifies objects in point clouds and extracts the geometry engineers need.

Centre of Expertise Digital Operations & Finance

openbare ruimte

Simultaneous segmentation and geometry extraction from mobile-mapping point clouds

Dutch infrastructure owners Rijkswaterstaat, ProRail, and municipalities increasingly depend on 3D digital twins built from Mobile Laser Scanning (MLS) point clouds for maintenance and inspection. Modern AI can label those clouds, but it does not output the cylinder axes, radii, or curb polylines that engineers actually use. Today, up to 90 % of MLS processing time is still spent on manual digitisation. GeoPointTransformer closes that gap with a single transformer that labels points and fits the geometry in one pass.

Goal

Develop and validate a compact transformer-based neural network that, from raw MLS point clouds, simultaneously labels every point and outputs the geometric primitives, cylinders for poles today, curbs and rails next, used by infrastructure engineers.

Target group 

  • Dutch surveying SMEs and engineering consultancies running MLS pipelines.
  • Public asset owners - Rijkswaterstaat, ProRail, municipalities, water authorities.
  • Smart-city / BIM-GIS integrators building automated inspection tooling on top of LiDAR.
  • The open-source geospatial-AI community.

Intended outcomes

  • Open-source prototype (PyTorch + Hydra, Docker-ready), code on GitHub, weights on Hugging Face.
  • Joint model - semantic mIoU > 70 % on KITTI-360, pole radius / height / axis errors within 10 % of ground truth.
  • Validation on at least one unseen Dutch corridor (360Geo) with qualitative sign-off from Hai Performance.
  • Dutch MLS dataset for the geospatial-AI community.
  • Dissemination - GeoBuzz presentation and a peer-reviewed paper.

Duration 

January 2026 – December 2026 

Team

THUAS — project lead
Research group Smart Sensor Systems, Faculty TIS.

  • dr. Ir. Amey Vasulkar - research lead, AI model development
  • dr. John Bolte - lector, Smart Sensor Systems · technical advisor
  • Jassar Hasiba - student, model development & experiments (ADS&AI)

Hai Performance BV - MLS domain partner:

  • dr. Ir. Tobias Witwer - domain lead, MLS workflows and asset annotation

360Geo BV - MLS data partner:

  • Jacob Muilwijk - domain lead, MLS data and visualisation
  • George Boot - tech lead, MLS data

Partners 

Funding 

Regieorgaan SIA - KIEM HighTech 2025.

Participating programmes

  • Bachelor Applied Data Science & AI 
  • Bachelor Applied Mathematics 
  • Master Next Level Engineering 

Contact

dr. Ir. Amey Vasulkar - [email protected]

Links and publications

Background references: