UAVs use vision-only system for altitude-adaptive geo-localization in GPS-denied environments

Researchers have developed a novel vision-only system for Unmanned Aerial Vehicles (UAVs) to determine their location even when GPS is unavailable. The system first estimates the UAV's altitude from a single image by analyzing its frequency domain, then uses this information to normalize the image scale. This normalized image is then processed by a visual place recognition module, enhanced with a quality-adaptive classifier, to achieve accurate geo-localization. Experiments demonstrated significant improvements in retrieval accuracy, with the altitude adaptation alone boosting performance by over 40 percentage points. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a method for GPS-denied navigation, potentially enabling more robust autonomous drone operations.

RANK_REASON This is a research paper detailing a new method for UAV geo-localization.

Read on arXiv cs.CV →

• UAV
• GPS
• arXiv
• Computer Vision
• Xingyu Shao

• paper
• other