Using AI-powered techniques to generate high-definition road transport network data from aerial imagery
| Reference number | |
| Coordinator | Simactis Spatial Intelligence AB |
| Funding from Vinnova | SEK 500 000 |
| Project duration | May 2025 - February 2026 |
| Status | Ongoing |
| Venture | Transport and mobility services - FFI |
| Call | Transport and mobility services - FFI - spring 2025 |
Purpose and goal
The purpose is to improve Tapestry, an AI tool that automatically generates high-resolution road transport networks from satellite imagery. The project aims to enhance accuracy, explore methods for including pedestrian and cycling infrastructure, and deliver a validated prototype for Swedish conditions. The goal is to lay the foundation for a larger implementation project.
Expected effects and result
The project is expected to result in an improved version of Tapestry and develop methods for including pedestrian and cycling infrastructure. Dialogue with stakeholders will ensure that the solution meets real-world needs. The goal is to enable faster and more cost-effective data generation, thereby supporting sustainable urban and transport planning in Sweden and internationally.
Planned approach and implementation
The project runs from May 2025 to February 2026 and consists of three work packages: project management, technical development, and stakeholder dialogue. Activities include AI model development, training data annotation, API creation, and user feedback to ensure practical applicability and end-user value.