Skip to content
GCC AI Research

Inferring and Improving Street Maps with Data-Driven Automation

arXiv · · Notable

CV Research Product Infrastructure

Summary

Researchers at MIT and QCRI developed Mapster, a human-in-the-loop street map editing system. Mapster incorporates high-precision automatic map inference, data refinement, and machine-assisted map editing. Evaluation across forty cities using satellite imagery, GPS trajectories, and ground-truth data demonstrates Mapster's ability to make automation practical for map editing. Why it matters: This system could significantly improve the accuracy and completeness of street maps in rapidly developing urban areas across the Middle East.

Keywords

street maps · automation · satellite imagery · GPS trajectories · QCRI

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

Using artificial intelligence to enrich digital maps - MIT News

QCRI ·

MIT researchers have developed a new AI system that uses satellite imagery and street-level photos to add details to digital maps. The AI model can identify features like building footprints, road networks, and vegetation cover with high accuracy. It then enriches existing maps by adding these features, improving their usability for navigation and urban planning. Why it matters: This technology can significantly enhance the quality and detail of digital maps, particularly in areas where up-to-date map data is lacking, enabling better AI-powered applications.